Key Technology and Application of Production Scheduling for Heating Forming of Forgings: A Review

Abstract

Forgings represented by rocket body rings, engine casings, vehicle drive shafts, etc., are key components of important equipment in the fields of aerospace, automobiles and high-speed rail. In recent years, with the rapid development of the manufacturing industry, it is also facing an increasingly fierce international competition environment. In order to adapt to the new production mode and quickly respond to the changing market demand, forging enterprises urgently need a reasonable and efficient forging production scheduling method, and based on the excellent production organization, in order to further build an intelligent production line, develop a forging production intelligent management and control integration architecture. This paper analyzes the production scheduling problem of forging thermoforming from two aspects: forging production line scheduling and forging production workshop scheduling. The research progress of optimization objectives and optimization algorithms of production scheduling is systematically reviewed. The subsystems serving the production and processing process and the intelligent management and control architecture based on system integration are summarized. It is of great significance to effectively reduce production costs, improve product quality, realize energy saving and emission reduction in the production process and promote further intelligent upgrading of the forging industry through production scheduling and intelligent management and control of the heating and forming process of forgings.

1. Introduction

The “14th Five-Year” Development Outline of China’s Forging Industry puts forward the development goals of energy saving, high efficiency, stability and greenness, effectively improving the quality of products in the forging industry, and enhancing the international competitiveness of enterprises [1]. The metal forming process [2] is one of the important methods to achieve light weight [3,4] and high quality [5,6] of parts for aerospace and automobiles. Because the forging process, which is mainly based on heating and forming of forgings, has the characteristics of high energy consumption, high emission and complex production process [7]. Under the requirements of ensuring product quality, it is very important to shorten the production time of the forging process, reduce the production cost and realize the energy saving and emission reduction in the forging process. With the implementation of strategic measures such as German Industry 4.0 and Made in China 2025, it is pointed out that the digitization, networking and intelligence of the manufacturing industry are the core technologies of the new round of industrial revolution [8]. Building an intelligent forging production line is an important part of realizing innovation-driven development, adapting to the transformation of industrial models and promoting industrial transformation and upgrading.

With the acceleration of the industrialization process, the traditional production mode of single mass production has been unable to meet the diversified needs of the market, and has gradually transformed into a multi-variety and variable-batch production mode. This greatly increases the complexity of the production scheduling process and the frequency with which processing equipment is adjusted. The forging production scheduling process has the following characteristics:

• Multi-objective: The optimization objectives of forging heating forming production scheduling mainly include meeting the customer’s delivery time, minimum emissions, minimum energy consumption and minimum forging billet charging furnace capacity difference rate. In the actual scheduling process, multiple optimization objectives are often selected according to the specific production environment, and these objectives are often contradictory.

• Multiple constraints: Forging shape and size, production process requirements, forging equipment capacity and delivery time constraints.

• Dynamic uncertainty: Uncertain factors such as machine failure and damage, substandard product quality, uncertain processing time, advance or delay in delivery time and order insertion.

• Coordination: In the actual scheduling process, the coordination of the scheduling of each processing shop should be considered to ensure the global optimality.

• Complexity: Due to the diversity of forging production processes, the uncertainty of the production environment and the difference in the ability of different equipment to process forgings at the same time, this greatly increases the complexity of scheduling problem modeling and calculations.

At present, the production scheduling of the forging process mostly relies on manual production scheduling and experience scheduling. Facing the complex and changeable production process, there are prominent problems such as long production scheduling time, low equipment utilization rate and inability to pursue optimal goals. In addition, the production process of forgings also faces problems such as long process cycle, narrow window of forming thermodynamic parameters of complex forging materials, unstable forming quality and easy to be affected by random disturbance and process disturbance factors in the production process. In the increasingly competitive international market, enterprises urgently need a scientific and efficient intelligent scheduling method, and establish an intelligent forging production line with real-time management and control, so as to realize the coordinated allocation of resources and intelligent production. In recent years, many scholars have proposed corresponding optimization solutions around the above problems, but few have systematically reviewed them. The main research contents of this review include the overall and partial division of the current research on the production scheduling of forging heating forming, and the production scheduling analysis from the forging production line and the production workshop, respectively. Through the overview and analysis of the optimization objectives and algorithms of forging production scheduling, it is found that the use of meta-heuristic algorithm to solve the multi-objective forging production scheduling problem is the main optimization method. In order to realize the intelligent management and control of the forging production process, outlining the functions of common production subsystems and the advanced key technologies employed, and the architecture of the intelligent management and control platform based on system integration is summarized and analyzed. It is believed that this review can not only expand the thinking of researchers in the field of forging, but also be attractive and valuable to researchers in the field of production management or production engineering.

According to Figure 1, the organizational structure of this paper is as follows: Section 2 classifies and briefly outlines the production scheduling problem for thermoforming of forgings. Section 3 reviews the main optimization performance indicators and the research progress of solution algorithms for forging hot forming production scheduling. Section 4 summarizes the functions and key technologies of important subsystems of forging production and the integrated architecture of intelligent management and control based on system integration. Section 5 is the summary and outlook of the paper.

2. Overview of Production Scheduling of Forging Thermoforming

Production scheduling is defined as the problem of allocating limited human and material resources to production tasks in a given time domain to make the predetermined goal optimal or close to optimal [9].

The research on the production scheduling of forging heating forming is mainly divided into two aspects, as shown in Figure 2, which are the scheduling of forging production lines and the scheduling of forging production workshops. The production process of forging thermoforming mainly includes cutting (shearing, sawing, etc.), furnace heating, forging (upsetting, drawing, punching, etc.), machining (turning, milling, planning, grinding, etc.), heat treatment (quenching, tempering, etc.), machining, quality inspection, packaging and transportation, etc. It can be classified into four workshops: comprehensive workshop (cutting), forging workshop (furnace heating and forging processing), heat treatment workshop (heat treatment) and machining workshop (machining) [10].

2.1. Forging Production Line Scheduling

Forging production line scheduling is a complex process, multi-constraint (some constraints at different stages are diametrically opposed) and multi-objective (in addition to traditional time, cost and other optimization performance indicators, it is also necessary to consider green performance indicators such as energy consumption, emissions and noise reduction) scheduling question. Without considering batch scheduling in the heating stage, Liu et al. [11] proposed an energy-saving hybrid flow shop scheduling problem with forging operations (EHFSP-FO), and established a multi-time-constrained mixed production model considering variable parameter continuous processing and intermittent processing, as shown in Figure 3. On this basis, a mathematical model is built to minimize the manufacturing time and energy consumption, and the evolutionary algorithm improved by the weighted sum method is used to solve the problem. Xiuyuan Tan [12] established a multi-objective scheduling mathematical model for the hot die forging production line, used an improved genetic algorithm to solve it, and established a Manufacturing Execution System (MES) for remote monitoring and information management of hot die forging production lines. Liu et al. [13] proposed an improvement on the basis of considering a mixed flow shop scheduling model with continuous machining and intermittent machining stages, which transformed the mandatory constraint of forging holding time limit into adjustment for the optimization objective of the maximum time excess value, a multi-objective optimal scheduling model is established together with the construction makespan and energy consumption, and an adaptive selection multi-objective optimization algorithm with preference (ASMOAP) is proposed to solve the problem. Considering batch scheduling in the heating stage, Cheng et al. [14] proposed an energy-efficient hybrid flow shop scheduling problem with forging tempering (EEHFSP-FT), considering the temperature constraint requirements of the forging production process. Using the strategy of waste heat treatment, with the optimization objective of minimizing the completion time and energy consumption, three multi-objective evolutionary algorithms are used to solve the problem, and their performances are compared. At present, there are few studies on the scheduling of forging production lines, mainly focusing on the static scheduling of the simple production process. There is still a certain gap from the practical application.

2.2. Forging Workshop Scheduling

The forging workshop scheduling problem can be divided into comprehensive workshop scheduling, machining workshop scheduling, forging workshop scheduling and heat treatment workshop scheduling. Due to the different process flow and processing equipment of different workshops, the scheduling process is often very different.

As shown in Figure 4, the common cutting methods in the comprehensive workshop include sawing, shearing, etc. The machining methods in the machining workshop include milling, turning and grinding, etc. The production scheduling process of the two is very similar. Each machine can only process one workpiece at a time, and each workpiece cannot be operated by multiple machines at the same time. Meng et al. [15] established a hybrid flow shop scheduling problem model with one-to-many machining constraints for the two stages of cutting and machining processes, and used the gray wolf algorithm to optimize the maximum completion time of the workpiece. To solve the stochastic flexible job shop scheduling problem, Caldeir et al. [16] proposed a simulation optimization method consisting of Jaya algorithm, meta-heuristic algorithm and Monte Carlo simulation to minimize the expected makespan. Li et al. [17] proposed a mixed integer linear programming model and a decomposition-based hybrid adaptive multi-objective evolutionary algorithm to solve the multi-objective flexible job shop scheduling problem with fuzzy processing time, In order to achieve the optimization goal of minimizing the total workload and manufacturing time.

The forging shop scheduling consists of two parts, the heating stage and the forging processing stage, as shown in Figure 5. In the heating stage, each heating furnace can heat multiple workpieces at the same time, whereas in the forging processing stage, each forging equipment can only process one workpiece at a time. The workpiece untreated by the forging equipment is still kept in the heating furnace for heat preservation, and the temperature of the workpiece during the forging process cannot be lower than the terminal temperature, otherwise it needs to be returned to the furnace for heating before forging. He et al. [18] established a scheduling model targeting the number of returns to the forging process to solve the problem of high production energy consumption in the forging process, and used the Hungarian method to solve it. Mingming Jiang [19] divided the forging production process into three links: pre-forging heating, forging and heat treatment, established a mathematical model of the problem for each link, and used related algorithms to solve them.

For heat treatment workshop scheduling, common heat treatment processes include normalizing, quenching and annealing, as shown in Figure 6. Each stage generally contains multiple heating furnaces. It is necessary to cluster and batch the workpieces first, and then put multiple workpieces in the same batch in the heating furnace for heating at the same time under the condition that the capacity constraints of the heating furnaces are satisfied, which belongs to the consideration of temperature constraints batch scheduling problem. Fei et al. [20] constructed a minimum cost and maximum flow network model to optimize the scheduling problem of the furnace charging quality during the heat treatment process. Wang et al. [21] proposed a multi-objective fuzzy logic optimization model to minimize energy consumption and total weighted delay for the batch scheduling problem of heat treatment under uncertain conditions, and adopted a non-dominated sorting genetic algorithm (NSGA-II) to solve. To solve the heat treatment scheduling problem for hot press forging, Kim et al. [22] proposed an optimization method based on evolutionary algorithms to minimize energy consumption and maximize productivity.

3. Performance Index and Solution Algorithm of Forging Thermoforming Production Scheduling Optimization

3.1. Optimize Performance Indicators

In the related literature, the main optimization objectives of forging production scheduling include minimizing total energy consumption, forging billet charging furnace capacity variance rate, total operating cost, total carbon emissions, delivery time and makespan. Due to the complexity of the real production environment and the diversity of enterprise manufacturing requirements, as shown in Table 1, the research on forging production scheduling focuses on the multi-objective optimal scheduling problem based on completion time and energy consumption. Moreover, green optimization performance indicators such as carbon emissions and noise pollution are gradually being valued by researchers.

In terms of single-objective optimization, Jiang et al. [23] established an energy-saving scheduling model for forging charging furnaces with the forging charging furnace capacity difference as the objective function in order to realize the energy-saving optimization of forging production. Zhang et al. [24] used an improved neural network algorithm based on particle swarm optimization algorithm to solve the single-objective job shop scheduling problem to minimize the optimization objective of the maximum makespan.

In terms of multi-objective optimization, Shi et al. [25] established a flexible job shop scheduling model with maximum makespan, energy consumption and consumption dissatisfaction as optimization objectives, which considered fuzzy delivery time. In order to solve the problem of high energy consumption in the forging production process, Cheng et al. [14] established a hybrid flow shop scheduling model with minimum energy consumption and completion time. Huang et al. [26] established a multi-objective flexible job shop scheduling model, which aims to minimize maximum makespan, bottleneck machine workload and total machine workload. To solve the multi-objective job shop scheduling problem, Huo et al. [27] developed an optimization model that aims to minimize total tardiness, total carbon emissions and maximum makespan. Mokhtari et al. [28] established a multi-objective flexible job shop scheduling model with the optimization goals of minimizing the total energy costs for maintenance and operation, minimizing makespan and maximizing the total availability of the system. Jing et al. [29] proposed a genetic algorithm to solve the multi-objective integrated optimization problem of preventive maintenance planning and flexible scheduling of job shops, and established a related optimization model to minimize the total equipment workload and maximum completion time.

3.2. Optimization Solution Algorithm

The optimal solution algorithm for the production scheduling problem of forging heating forming is shown in Table 2, which can be roughly divided into three categories: exact algorithm, heuristic algorithm and meta-heuristic algorithm. In recent years, the use of a meta-heuristic algorithm based on genetic algorithm is the main optimization method to solve the production scheduling problem of forging thermoforming.

3.2.1. Exact Algorithm

Exact algorithms are mainly based on mathematics and operations research methods, including mathematical programming (integer linear programming (ILP), mixed integer linear programming (MILP), etc.), branch-and-bound methods, cutting planes, etc. Early scheduling algorithms are devoted to solving the exact solution of scheduling problems, and traditional exact algorithms are often used to solve simple small-scale optimization problems. To solve the single-machine scheduling problem with availability constraints, Kacem et al. [36] proposed three exact algorithms, branch-and-bound, dynamic programming and mixed integer programming, to minimize the weighted sum of completion time. Yalaoui et al. [37] developed a branch-and-bound approach to solve the same parallel machine scheduling problem to minimize total tardiness. However, as the scale of the scheduling problem continues to increase and the scheduling environment becomes increasingly complex, only using an accurate algorithm to solve the forging production scheduling problem requires a large amount of computation and a long time, which is difficult to meet the needs of practical applications.

3.2.2. Heuristic Algorithms

The essence of heuristic algorithm is a set of rules with suggestion properties used to guide the search direction of the algorithm [38]. When solving complex scheduling problems, heuristic algorithms are difficult to obtain a global optimal solution, and generally only a better solution can be obtained. However, the solving process is simple in operation and low in computational complexity, and an ideal scheduling scheme can be obtained in a relatively short time. Many heuristics including scheduling rules have been applied to deal with the production shop scheduling problem [39]. In order to solve the multi-constraint multi-objective flexible job shop scheduling problem, Ma et al. [40] proposed a multi-objective real-time scheduling algorithm based on the weighted combination of scheduling rules, and used Flexsim software for modeling and simulation. Gao et al. [41] proposed four heuristic ensemble methods to solve the multi-objective flexible job shop scheduling problem with job insertion, and the results showed the effectiveness of the proposed heuristic algorithm in solving this problem. Wang et al. [42] proposed a heuristic algorithm and worst-case analysis for the two-stage flow shop scheduling problem with group batches to minimize the total completion time, and developed a hyper-heuristic based on genetic programming formula algorithm. To solve the multi-objective flexible job shop scheduling problem, Robert et al. [43] proposed an improved multi-objective heuristic Kalman algorithm (MOHKA). Zadeh et al. [44] proposed an improved heuristic model based on the Artificial Bee Algorithm to solve the dynamic flexible job shop scheduling problem considering variable processing time. Mohsen et al. [45] study a flexible job shop scheduling scaling problem considering machine and order acceptance, develop a mixed integer linear programming model, and propose a heuristic algorithm to solve the problem. David et al. [46] employed four variational quantum heuristics running on an IBM superconducting quantum processor to solve the job shop scheduling problem, and the results showed that the filtered variational quantum eigensolver (F-VQE) had the best performance index.

3.2.3. Meta-Heuristics

The meta-heuristic algorithm is a method that introduces random factors into the entire search process based on the initial scheduling scheme, and finds a better solution through iterative operations. Commonly used metaheuristic algorithms include genetic algorithm (GA), differential evolution algorithm (DE), artificial bee colony algorithm (ABC), particle swarm algorithm (PSO), ant colony optimization algorithm (ACO), tabu search algorithm (TS), simulated Annealing Algorithm (SA) and iterative Greedy Algorithm (IG), etc.

Genetic Algorithm

Genetic algorithm is a random search algorithm based on genetics and evolutionary theory. Genetic algorithm transforms the problem solving process into a process similar to the crossover and mutation of chromosomal genes in biological evolution by combining mathematical methods and computer simulation operations [47]. The main flow of the algorithm is shown in Figure 7.

Due to its excellent global search ability, highly parallel search method and strong robustness, the genetic algorithm has been widely used in solving large-scale complex forging production scheduling problems. However, in the face of complex and multi-constrained forging workshop scheduling problems, common genetic algorithms often have defects such as poor local search ability, slow convergence speed and easy precociousness. In order to overcome the above shortcomings, some scholars improve the genetic algorithm based on the initial population, genetic operators and individual similarity, whereas others combine the genetic algorithm with other algorithms to learn from each other’s strengths [48].

From the aspect of algorithm improvement, Li et al. [49] proposed an improved genetic algorithm by designing a new selection operator to solve the multi-objective flexible job shop scheduling problem, so that it can converge to the global optimum faster untie. Jihao Wu [50] proposed an improved genetic algorithm based on priority coding for the multi-objective dynamic flexible job shop scheduling problem. Janes et al. [51] proposed a genetic algorithm with improved crossover and selection operators to solve the job shop scheduling problem. The experimental results show that the algorithm can achieve a satisfactory solution in a short time span. In order to solve the multi-objective flexible job shop intelligent scheduling problem, Sang et al. [52] proposed an improved intelligent decision-making optimization algorithm NAGA-III-APEV, which effectively improves the diversity and convergence of the population. Xuan et al. [53] proposed an adaptive genetic algorithm that improved the crossover and mutation operators of genetic algorithms by using cloud crossover, mutation operator and cloud generator for the multi-objective fuzzy flexible job shop scheduling problem. It can effectively reduce the probability of premature maturity and improve the efficiency of iterative search. Kong et al. [54] proposed an improved genetic algorithm to solve the mixed flow shop sustainable scheduling problem, and the matching distance was integrated into the mutation operation and elite strategy of the genetic algorithm to improve its convergence. Liu et al. [55] proposed an improved genetic algorithm based on a novel encoding and decoding method to solve the Integrated Planning and Scheduling Problem, and the experimental results verified the superiority of the algorithm. Guoliang Li [56] designed an improved genetic algorithm with adaptive adjustment of crossover mutation to solve the dual-objective flexible shop scheduling problem. The simulation results show that compared with the standard genetic algorithm, the algorithm has a faster convergence speed and can effectively avoid falling into the premature problem. Zhang et al. [57] proposed an improved genetic algorithm based on the initial population and genetic operators to solve the flexible shop floor scheduling problem with multiple time constraints, and the results showed the effectiveness of the algorithm.

In terms of combining with other algorithms, Gao et al. [58] proposed a genetic algorithm based on reinforcement learning to solve the large-scale flow shop scheduling problem, and used Q-learning to self-learn the crossover probability to overcome the instability and randomness of the genetic algorithm. Jiang et al. [59] used the method of combining genetic algorithm and scheduling rules for the production workshop scheduling problem of manufacturing enterprises. The simulation results showed the effectiveness and stability of the genetic algorithm. Wu et al. [60] improved GA by using deep learning neural network (DLNN), and applied the improved GA to solve the workshop scheduling problem. The simulation results show that the improved GA can effectively avoid falling into local optimum. To solve the flexible job shop scheduling problem with fuzzy delivery times, Shi et al. [25] proposed an improved immune genetic algorithm (IGA) to minimize energy consumption, maximum manufacturing time and consumer dissatisfaction. Peng et al. [61] proposed a multi-agent genetic algorithm based on tabu search to solve the job shop scheduling problem under the makespan constraints, which has good global search ability and can avoid the genetic algorithm to a certain extent convergence prematurely. Li et al. [62] proposed a branched population genetic algorithm (BPGA) based on a hybrid of genetic algorithm (GA) and ant colony algorithm (ACO) in order to minimize the makespan and cost for the workshop scheduling problem with dual resource constraints. Li et al. [63] proposed an improved genetic algorithm and a hybrid algorithm combined with simulated annealing algorithm to solve the dynamic multi-objective flexible job shop scheduling problem. The simulation results show that the algorithm has better global search ability and can obtain higher quality Pareto solution.

Other Meta-Heuristics

Jiang et al. [64] established a multi-objective batch scheduling model of complex aerospace components for the flexible job shop energy-saving scheduling problem with complex processes, and proposed a cross-artificial bee colony algorithm (CABC) inspired by differential evolution to solve this problem. Tian et al. [65] proposed a PN-ACO algorithm that combines a representation tool based on time-transformed Petri nets (TTPN) and an ant colony optimization (ACO) heuristic search method to solve the energy-saving scheduling problem of flexible job shops. Fengping Shen [66] proposed an improved particle swarm algorithm to minimize the workpiece waiting time expectation in the heat treatment batch scheduling problem considering the dynamic arrival of workpieces. To solve the flexible job scheduling problem, Gao et al. [67] proposed a novel differential evolution algorithm based on dynamic multi-population (DEDMP) to minimize critical machine workload, makespan and total workload. Shen et al. [68] developed a tabu search algorithm with specific neighborhood functions and a diversification structure to solve the flexible job shop scheduling problem. Alkhateeb et al. [69] proposed a discrete hybrid cuckoo search and simulated annealing algorithm (DCSA) for the shop-floor scheduling problem, and the experimental results show the superiority of the algorithm. To solve the wait-free job shop scheduling problem, Xu et al. [70] proposed a population-based iterative greedy (PBIG) algorithm to minimize makespan.

4. Research on Forging Production Subsystem and Intelligent Management and Control Integration Architecture

With the popularization of emerging technologies such as information and communication technology (ICT), cloud computing (CC), digital twin (DT), Internet of Things (IoT), big data analysis and edge computing (EC), in order to realize the transformation and upgrading of traditional manufacturing models, the development path of gradually moving towards digitization, networking and intelligence has injected new vitality. In order to build an intelligent forging factory, intelligent production lines have become the key development direction of domestic and foreign manufacturing enterprises. At present, advanced forging production lines at home and abroad generally integrate subsystems such as process planning, dynamic scheduling, quality inspection and process control [71].

4.1. Forging Production Subsystem

4.1.1. Process Planning CAPP System

Process planning is the bridge between product design and manufacturing process. As shown in Figure 8, computer-aided process planning (CAPP) quickly and accurately obtains product data information from computer-aided design (CAD) system through feature extraction and recognition technology, analyzes and processes, transforms into the process selection, operation sequence, tool and feed and depth of cut instructions that guide the manufacturing process of computer-aided manufacturing (CAM) system [72]. Wei et al. [73] proposed a new method for autonomous computer aided process planning (A-CAPP) in intelligent manufacturing system, the key functional components of the system include process simulation and evaluation, manufacturing process planning, numerical control machining Program planning, event scheduling management and operation process/step planning. Chen et al. [74] developed an intelligent computer-aided process planning (i-CAPP) based on two metrics of manufacturability and efficiency, and validated these metrics using a hybrid two-stage optimization algorithm.

4.1.2. Dynamic Scheduling System

Considering that the actual production process of forging is affected by various dynamic disturbance factors such as tasks, equipment, technology, time and quality, it is necessary to adopt a reasonable scheduling strategy to adjust. Research on scheduling strategies is mainly divided into three categories [75], namely completely-reactive scheduling strategies [76,77,78], predictive-reactive scheduling strategies [79,80,81,82,83] and robust scheduling strategies [84,85,86,87]. At present, many studies apply scheduling strategies to multi-objective dynamic scheduling systems. Long et al. [88] proposed a new robust dynamic scheduling system for the inaccurate release time of steelmaking-continuous casting production products, as shown in Figure 9, the system includes offline preparation and online robust dynamic scheduling. The offline preparation mainly builds the prediction model based on historical data to determine the prediction statistical accuracy of the model, and the online robust scheduling stage builds a chance constrained programming model for rescheduling based on the prediction information. Ghaleb et al. [89] proposed a real-time optimization system based on an modified hybrid genetic algorithm, an integrated predictive-reactive scheduling model and a hybrid rescheduling strategy, which mainly includes offline mode, online mode and integrated planning module.

4.1.3. Quality Inspection System

The relevant research of this research group shows that the quality disturbance factors in the process of forging heating forming process can be divided into two categories. As shown in Figure 10, one category is the random disturbance factors, mainly the time lag in the process, the temperature and humidity of the production site environment, the real-time state of production equipment and the vibration; the other category is the process fluctuation disturbance factors, mainly the flow speed, mechanical properties, real-time temperature, manufacturing time and product volume of forging products.

When the disturbance factor in the production process changes, the product quality will change accordingly. In order to accurately control the quality change caused by the fluctuation of the disturbance factor, it is necessary to carry out real-time quality inspection and control in the forging production process. Currently, advanced key inspection technologies include ultrasonic testing (UT) [90,91,92], X-ray testing [93,94,95,96] and machine vision testing [97,98,99,100]. Chu et al. [101] proposed an automated based-vision quality inspection system for Shell-Tube welding in order to nondestructive weld defect detection, including hardware and software systems, which can realize to detect and identify the undercut in the shell-tube welding. Du et al. [102] proposed a defect detection system based on X-ray oriented deep learning, which improved the detection accuracy from data enhancement and algorithm levels, respectively. Zhou et al. [103] developed a phased array ultrasonic water immersion C-Scan detection software and hardware system in order to improve the detection efficiency, adaptability and flexibility of ultrasonic water immersion C- Scan. The overall architecture is shown in Figure 11. The experimental results a significant improvement in detection rate and capability is demonstrated.

4.1.4. Process Control System

The Process Control System (PCS) is the bridge between the Manufacturing Execution System (MES) and the underlying automation system. Integrate with advanced forming equipment through PCS, and use intelligent sensors to collect and feed back data such as temperature, geometry, and rolling force of workpieces in the production process in real time, so as to dynamically adjust parameters such as rolling force and rolling speed in real time [104]. Xianlei Meng [105] proposed an overall structure of the process control system for the hot rolling area of steel pipes, as shown in Figure 12, the main function of the steel pipe process control system is to receive the production contract and production plan information issued by the MES system and organize them according to contract standards. Realize the material tracking from the ring furnace process to the cooling bed process in the hot rolling area. Weihrauch et al. [106] developed a conceptual model of an intelligent process control system (APCS), which mainly consists of four features, including simulation and prediction of the future state of manufacturing, a real-time virtual representation of the manufacturing process, providing access to past manufacturing and quality records, support decision-making activities.

4.2. Intelligent Management and Control Integration Architecture

At present, although the subsystems integrated in advanced forging production lines at home and abroad can independently complete the functions of process planning, production scheduling, quality inspection and process control and solve various problems they face, the management and controls are not perfect. In order to promote the circulation of production data in the production management system, realize data optimization and improve system functions. It is of great significance to build an intelligent management and control architecture based on system integration. In order to solve the problems of long design cycle, unstable forming quality, high energy consumption and low efficiency in the forging production process, Sun et al. [104] constructed a multi-level closed-loop intelligent management and control architecture based on system integration, as shown in Figure 13. The Enterprise Service Bus (ESB) realizes the data interaction and integration between the intelligent management and control platform and various subsystems. In order to solve the problems of low production efficiency and poor product quality consistency caused by random disturbances and process disturbance factors during the heating forming process of ring forgings, Zhou et al. [107] developed an intelligent management and control system platform technology for production dynamic disturbance factors based on a fault tolerant and correction mechanism, which can realize dynamic analysis and regulation of production disturbance factors, and efficiently control the production of ring forgings. Zhou et al. [108] established an intelligent information scheduling system platform for the heat treatment production process, and realized real-time scheduling of the heat treatment process by using technologies such as information collection, information fusion and intelligent management and control.

5. Conclusions and Outlook

Developing an efficient intelligent scheduling method and establishing an intelligent forging production line with real-time control is a key step to comprehensively improve the design, manufacturing and management level of products of forging enterprises and enhance international competitiveness. It is also an important link to promote the forging industry to adapt to the change of production mode and further intelligently upgrade. This review mainly classifies the structure of forging production scheduling problem, summarizes and analyzes its main optimization performance indicators and solving algorithms, and further expands and outlines the research on the integrated architecture of forging production intelligent management and control. The specific summary is as follows.

• From the overall and local perspectives, forging production scheduling is divided into two aspects: production line scheduling and production workshop scheduling. Production workshop scheduling can be classified into comprehensive workshop scheduling, machining workshop scheduling, forging workshop scheduling and heat treatment workshop scheduling. The research on forging production line scheduling is summarized in terms of whether batch scheduling is considered in the heating stage. This paper mainly studies the multi-objective optimization scheduling problem of the assembly line with the forging workshop as the core. The research on comprehensive workshop scheduling and machining workshop scheduling mainly focuses on the multi-objective flexible job shop scheduling problem under uncertain conditions. The research on forging shop scheduling and heat treatment shop scheduling mainly focuses on the multi-objective optimization green scheduling problem with batch grouping under temperature constraints.

• By summarizing and analyzing the sorted literature, the research on forging heat forming production scheduling mainly focuses on the multi-objective scheduling problem considering the optimization objectives such as completion time and energy consumption. Multi-objective production scheduling is the main trend of future research, because the actual forging production process must not only consider the impact of the production environment, but also meet the production needs of the enterprise. In order to comply with the global green and low-carbon development trend, green optimization performance indicators such as carbon emission and noise pollution have gradually attracted the attention of scholars.

• Through literature review and induction, this paper divides the forging production scheduling optimization solution algorithm into three categories: exact algorithm, heuristic algorithm and meta-heuristic algorithm. The exact algorithm is suitable for solving simple small-scale scheduling problems, but it is difficult to apply to the actual complex forging production scheduling process. Heuristic algorithms and meta-heuristic algorithms are difficult to obtain global optimal solutions for complex scheduling problems, and generally only better solutions can be obtained, but the solution process is simple and has low computational complexity. Due to its excellent global search ability and strong robustness, genetic algorithm is widely used to solve the production scheduling problem of forging thermoforming. In order to adapt to different production environments, the genetic algorithm is improved from two aspects: the improvement of the algorithm and the integration with other algorithms, so as to improve the local search ability and convergence speed of the algorithm.

• The forging production subsystem mainly includes the process planning CAPP system, the dynamic scheduling system, the quality inspection system and the process control system, etc. Process planning CAPP system obtains product information from CAD system through feature extraction and recognition technology to guide CAM system processing. The dynamic scheduling system minimizes the impact of production interruptions caused by uncertain factors by adopting appropriate scheduling strategies. The quality inspection system uses advanced key inspection technologies such as ultrasonic testing, X-ray testing and machine vision testing to reliably detect internal and external defects of forgings caused by process disturbance factors and random disturbance factors. The process control system integrates with advanced forming equipment and uses intelligent sensors to collect and feed back production information in real time, so as to dynamically control the forming equipment.

• The intelligent management and control integration architecture is based on the MES extension function module. It uses ESB to realize the data interaction and integration between the intelligent management and control platform and various subsystems, and builds a closed loop between each subsystem and advanced equipment, so as to realize the integration of various subsystems. real-time control and function optimization. Effectively improving complex forging production lines faces the problems of complex process, high energy consumption, unstable forming quality and low efficiency.

At present, the research on forging production line scheduling mainly focuses on the simple process pipeline scheduling problem centered on the forging workshop, and rarely considers the influence of random and uncertain disturbance factors in actual production. Therefore, future research needs to conduct multi-objective dynamic scheduling research on complex forging production lines according to the actual production environment, and improve the performance of the algorithm from the aspects of algorithm improvement, fusion and new algorithm design. By coordinating the scheduling of each workshop for forging production to ensure global optimality. Accelerate the continuous development of advanced technologies such as data collection, information fusion and system integration to build an intelligent forging production line with real-time management and control, which lays a solid foundation for the forging industry to move towards intelligent production.

Author Contributions

Conceptualization, H.W., Y.C. and J.Z.; investigation, Y.C. and J.Z.; writing—original draft preparation, H.W. and J.Z.; writing—review and editing, H.M., Y.C. and X.H.; visualization, J.Z.; supervision, Y.Z., J.C. and Z.H.; project administration, H.W. and Y.C.; funding acquisition, H.W. and Y.C. All authors have read and agreed to the published version of the manuscript.

Institutional Review Board Statement

Not applicable.

Informed Consent Statement

Not applicable.

Data Availability Statement

Not applicable.

Acknowledgments

Thanks to Journal of Cleaner Production from Elsevier, The International Journal of Advanced Manufacturing Technology from Springer Nature, Applied Soft Computing from Elsevier, Journal of Mechanical Engineering, Industrial Control Computer and Forging & Stamping Technology for the copyright permissions of Figure 3, Figure 8, Figure 9, Figure 11, Figure 12, and Figure 13.

Conflicts of Interest

The authors declare no conflict of interest.

Publisher’s Note: MDPI stays neutral with regard to jurisdictional claims in published maps and institutional affiliations.

Figures and Tables

Figure 1. Organizational framework of the full text.

Figure 2. Forging production process.

Figure 3. Mixed flow shop scheduling model and mixed production model considering multiple time factors [11].

Figure 4. Comprehensive workshop and machining workshop.

Figure 5. Forging workshop production process.

Figure 6. Heat treatment process flow.

Figure 7. Flowchart of genetic algorithm.

Figure 8. CAD/CAPP/CAM system integration [72].

Figure 9. A novel robust scheduling framework based on release time series forecasting [88].

Figure 10. Category of disturbance factors for quality change in hot forming of forgings.

Figure 11. Overall structure of the detection system [103].

Figure 12. Overall architecture of the process control system [105].

Figure 13. Architecture of the multi-level closed-loop intelligent management and control system [104].

Table 1

Document arrangement for the optimization target of forging thermoforming production scheduling.

Symbol	Meaning	References
∑$T_j$	Total tardiness	Huo et al. [27]; Zhang et al. [30]; Hajibabaei et al. [31]
∑$E_j$	Total energy consumption	Liu et al. [11]; Cheng et al. [14]; Dai et al. [32]; Zhang et al. [30]
$C_{max}$	Makespan or maximum completion time	Liu et al. [11]; Cheng et al. [33]; Cheng et al. [14]; Huo et al. [27]; Dai et al. [32]; Hajibabaei et al. [31]; Sun et al. [34];Jing et al. [29]
∑$M_j$	Total machine load	Sun et al. [34]
∑$F_j$	Forging billet charging furnace Capacity difference rate	Jiang et al. [23]; Jing et al. [29]
∑$O_j$	Total operation cost	Huang et al. [35]; Hajibabaei et al. [31]
∑$D_j$	Total delivery time	Hajibabaei et al. [31]
∑$C_j$	Total carbon emission	Huo et al. [27]; Sun et al. [34]

Table 2

Algorithm for optimization of production scheduling for forging thermoforming.

Algorithm	Including
Exact algorithm	Mathematical programming, branch and bound, cutting planes, etc.
Heuristic algorithm	Scheduling rules, etc.
Meta-heuristic algorithms	Genetic algorithm
	Other meta-heuristic algorithms: differential evolution algorithm, artificial bee colony algorithm, particle swarm algorithm, ant colony optimization algorithm, Tabu search algorithm, simulated annealing algorithm, iterative greedy algorithm, etc.

References

1. Wu, S.D. “14th Five-Year” Development Outline of China’s Forging Industry (3/4). Forg. Metalform.; 2021; 16, pp. 56-61.

2. Sun, Y.; Luzin, V.; Duan, Y.; Varma, R.; Shi, L.; Weiss, M. Forming-Induced Residual Stress and Material Properties of Roll-Formed High-Strength Steels. Automot Innov; 2020; 3, pp. 210-220. [DOI: https://dx.doi.org/10.1007/s42154-020-00112-2]

3. Li, H.-x.; Wang, K.; Luo, R.; Zhu, Z.-z.; Deng, S.; Luo, R.; Zhang, J.-y.; Fang, F.-s. Influence of radial forging process on strain inhomogeneity of hollow gear shaft using finite element method and orthogonal design. J. Cent. South Univ.; 2020; 27, pp. 1666-1677. [DOI: https://dx.doi.org/10.1007/s11771-020-4398-7]

4. Rosenthal, S.; Maaß, F.; Kamaliev, M.; Hahn, M.; Gies, S.; Tekkaya, A.E. Lightweight in Automotive Components by Forming Technology. Automot. Innov.; 2020; 3, pp. 195-209. [DOI: https://dx.doi.org/10.1007/s42154-020-00103-3]

5. Chen, Y.; Xie, B.; Ma, H.; Wang, H.; Zhou, Y.; Chen, J.; Hua, L. Production Scheduling Optimization during Thermoforming of Ring Forgings Based on Genetic Algorithms. Metals; 2022; 12, 1631. [DOI: https://dx.doi.org/10.3390/met12101631]

6. Wang, D.; Xie, C.; Liu, Y.; Xu, W.; Chen, Q. Multi-objective Collaborative Optimization for the Lightweight Design of an Electric Bus Body Frame. Automot. Innov.; 2020; 3, pp. 250-259. [DOI: https://dx.doi.org/10.1007/s42154-020-00105-1]

7. Qi, W.D. Forging Process and Die Design; 2nd ed. Beijing Institute of Technology Press: Beijing, China, 2012; ISBN 978-7-5640-6458-7 (In Chinese)

8. Zhou, J. Intelligent Manufacturing—Main Direction of “Made in China 2025”. China Mech. Eng.; 2015; 26, pp. 2273-2284.

9. Deng, G.L.; Gu, X.S.; Cui, Z. Workshop Scheduling Method Based on Swarm Intelligence Optimization; Tsinghua University Press: Beijing, China, 2016; 4. ISBN 7-302-43682-0 (In Chinese)

10. Xu, Q.; Li, D.B. Research on the integration of forging production process planning and workshop scheduling based on multi-agent. Mach. Des. Manuf. Eng.; 2013; 42, pp. 29-32.

11. Liu, Z.; Yan, J.; Cheng, Q.; Yang, C.; Sun, S.; Xue, D. The mixed production mode considering continuous and intermittent processing for an energy-efficient hybrid flow shop scheduling. J. Clean. Prod.; 2020; 246, 119071. [DOI: https://dx.doi.org/10.1016/j.jclepro.2019.119071]

12. Tang, X.Y. Analysis and Optimization of Intelligent Forging Production Line Based on Improved GeneTic Algorithm. Master’s Thesis; Beijing Industry University: Beijing, China, 2020; [DOI: https://dx.doi.org/10.26935/d.cnki.gbjgu.2020.000380]

13. Liu, Z.; Yan, J.; Cheng, Q.; Chu, H.; Zheng, J.; Zhang, C. Adaptive selection multi-objective optimization method for hybrid flow shop green scheduling under finite variable parameter constraints: Case study. Int. J. Prod. Res.; 2021; 60, pp. 3844-3862. [DOI: https://dx.doi.org/10.1080/00207543.2021.1933239]

14. Cheng, Q.; Liu, C.; Chu, H.; Liu, Z.; Zhang, W.; Pan, J. A New Multi-Objective Hybrid Flow Shop Scheduling Method to Fully Utilize the Residual Forging Heat. IEEE Access; 2020; 8, pp. 151180-151194. [DOI: https://dx.doi.org/10.1109/ACCESS.2020.3017239]

15. Meng, R.H.; Sun, A.W.; Wu, Z.J.; Zhu, Y.Y.; Chen, B.J.; Zhang, B.; Rao, Y.Q. Research on Improved Grey Wolf Algorithm to Solve Complex Mixed Pipeline Scheduling Problems. Acta Electron. Sin.; 2021; 49, pp. 1515-1523.

16. Caldeira, R.H.; Gnanavelbabu, A. A simheuristic approach for the flexible job shop scheduling problem with stochastic processing times. Simulation; 2020; 97, pp. 215-236. [DOI: https://dx.doi.org/10.1177/0037549720968891]

17. Li, R.; Gong, W.; Lu, C. Self-adaptive multi-objective evolutionary algorithm for flexible job shop scheduling with fuzzy processing time. Comput. Ind. Eng.; 2022; 168, 108099. [DOI: https://dx.doi.org/10.1016/j.cie.2022.108099]

18. He, F.; Ma, X.; Jiang, M. Research on Energy Saving Dispatching of Forging Link Based on Number of Reheating Times. Proceedings of the 2nd International Conference on Frontiers of Materials Synthesis and Processing (FMSP); Sanya, China, 10–11 November 2018; [DOI: https://dx.doi.org/10.1088/1757-899x/493/1/012076]

19. Jiang, M.M. Research on Energy-Saving Scheduling for Forging Production. Master’s Thesis; Nanjing University of Science and Technology: Nanjing, China, 2017.

20. He, F.; Wang, Z.Y.; Shen, K.; Jia, R.J. Research on Scheduling of Furnace Loading Quality Maximization in Forging Heat Treatment Process. IOP Conf. Ser. Mater. Sci. Eng.; 2019; 562, 12152. [DOI: https://dx.doi.org/10.1088/1757-899X/562/1/012152]

21. Wang, J.; Qiao, F.; Zhao, F.; Sutherland, J.W. Batch scheduling for minimal energy consumption and tardiness under uncertainties: A heat treatment application. CIRP Ann. Manuf. Technol.; 2016; 65, pp. 17-20. [DOI: https://dx.doi.org/10.1016/j.cirp.2016.04.115]

22. Kim, S.; Choi, J.; Ryu, K.R. Optimization of Heat Treatment Scheduling for Hot Press Forging Using Data-Driven Models. Intell. Automat. Soft. Comput.; 2022; 32, pp. 207-220. [DOI: https://dx.doi.org/10.32604/iasc.2022.021752]

23. Jiang, M.M.; He, F.; Li, D.B.; Tong, Y.F. Forging Billet Charging Energy-conservation Scheduling for Heating Furnaces Efficiency. Forg. Technol.; 2016; 41, pp. 115-121. [DOI: https://dx.doi.org/10.13330/j.issn.1000-3940.2016.08.023]

24. Zhang, Z.; Guan, Z.L.; Zhang, J.; Xie, X. A Novel Job-Shop Scheduling Strategy Based on Particle Swarm Optimization and Neural Network. Int. J. Simul. Model.; 2019; 18, pp. 699-707. [DOI: https://dx.doi.org/10.2507/IJSIMM18(4)CO18]

25. Shi, D.L.; Zhang, B.B.; Li, Y. A Multi-Objective Flexible Job-Shop Scheduling Model Based on Fuzzy Theory and Immune Genetic Algorithm. Int. J. Simul. Model.; 2020; 19, pp. 123-133. [DOI: https://dx.doi.org/10.2507/IJSIMM19-1-CO1]

26. Huang, X.; Guan, Z.; Yang, L. An effective hybrid algorithm for multi-objective flexible job-shop scheduling problem. Adv. Mech. Eng.; 2018; 10, [DOI: https://dx.doi.org/10.1177/1687814018801442]

27. Huo, D.X.; Xiao, X.J.; Pan, Y.J. Multi-Objective Energy-Saving Job-Shop Scheduling Based on Improved NSGA-II. Int. J. Simul. Model.; 2020; 19, pp. 494-504. [DOI: https://dx.doi.org/10.2507/IJSIMM19-3-CO12]

28. Mokhtari, H.; Hasani, A. An energy-efficient multi-objective optimization for flexible job-shop scheduling problem. Comput. Chem. Eng.; 2017; 104, pp. 339-352. [DOI: https://dx.doi.org/10.1016/j.compchemeng.2017.05.004]

29. Jing, Z.; Hua, J.; Yi, Z. Multi-objective Integrated Optimization Problem of Preventive Maintenance Planning and Flexible Job-Shop Scheduling. Proceedings of the 23rd International Conference on Industrial Engineering and Engineering Management; Wuhan, China, 2016; pp. 137-141. [DOI: https://dx.doi.org/10.2991/978-94-6239-255-7_25]

30. Zhang, R.; Chiong, R. Solving the energy-efficient job shop scheduling problem: A multi-objective genetic algorithm with enhanced local search for minimizing the total weighted tardiness and total energy consumption. J. Clean. Prod.; 2015; 112, pp. 3361-3375. [DOI: https://dx.doi.org/10.1016/j.jclepro.2015.09.097]

31. Hajibabaei, M.; Behnamian, J. Flexible job-shop scheduling problem with unrelated parallel machines and resources-dependent processing times: A tabu search algorithm. Int. J. Manag. Sci. Eng.; 2021; 16, pp. 242-253. [DOI: https://dx.doi.org/10.1080/17509653.2021.1941368]

32. Dai, M.; Tang, D.; Giret, A.; Salido, M.A. Multi-objective optimization for energy-efficient flexible job shop scheduling problem with transportation constraints. Robot. Comput. Integr. Manuf.; 2019; 59, pp. 143-157. [DOI: https://dx.doi.org/10.1016/j.rcim.2019.04.006]

33. Cheng, C.-Y.; Pourhejazy, P.; Ying, K.-C.; Lin, C.-F. Unsupervised Learning-based Artificial Bee Colony for minimizing non-value-adding operations. Appl. Soft Comput.; 2021; 105, 107280. [DOI: https://dx.doi.org/10.1016/j.asoc.2021.107280]

34. Sun, X.; Wang, Y.; Kang, H.; Shen, Y.; Chen, Q.; Wang, D. Modified Multi-Crossover Operator NSGA-III for Solving Low Carbon Flexible Job Shop Scheduling Problem. Processes; 2020; 9, 62. [DOI: https://dx.doi.org/10.3390/pr9010062]

35. Huang, J.; Liu, J. Hierarchical Production Planning and Real-Time Control for Parallel Batch Machines in a Flow Shop with Incompatible Jobs. Math. Probl. Eng.; 2018; 2018, 7268578. [DOI: https://dx.doi.org/10.1155/2018/7268578]

36. Kacem, I.; Chu, C.; Souissi, A. Single-machine scheduling with an availability constraint to minimize the weighted sum of the completion times. Comput. Oper. Res.; 2008; 35, pp. 827-844. [DOI: https://dx.doi.org/10.1016/j.cor.2006.04.010]

37. Yalaoui, F.; Chu, C. Parallel machine scheduling to minimize total tardiness. Int. J. Prod. Econ.; 2002; 76, pp. 265-279. [DOI: https://dx.doi.org/10.1016/S0925-5273(01)00175-X]

38. Duan, G.L.; Zha, J.Z.; Xu, A.P.; Zhang, M.T. Heuristic Algorithm and Its Application in Engineering. J. Mach. Des.; 2000; 6, 1-5+52. [DOI: https://dx.doi.org/10.13841/j.cnki.jxsj.2000.06.001]

39. Xie, J.; Gao, L.; Peng, K.; Li, X.; Li, H. Review on flexible job shop scheduling. IET Collab. Intell. Manuf.; 2019; 1, pp. 67-77. [DOI: https://dx.doi.org/10.1049/iet-cim.2018.0009]

40. Ma, L.M.; Li, J.Y.; Xu, W.S.; Kong, L.J. Multi-Objective Scheduling Based on Weighted Combination of Heuristic Rules and the Simulation Method. Adv. Mater. Res.; 2012; 424–425, pp. 1132-1138. [DOI: https://dx.doi.org/10.4028/www.scientific.net/AMR.424-425.1132]

41. Gao, K.Z.; Suganthan, P.N.; Tasgetiren, M.F.; Pan, Q.K.; Sun, Q.Q. Effective ensembles of heuristics for scheduling flexible job shop problem with new job insertion. Comput. Ind. Eng.; 2015; 90, pp. 107-117. [DOI: https://dx.doi.org/10.1016/j.cie.2015.09.005]

42. Wang, R.; Shen, Y.; Wang, W.; Shi, L. Formulation and Methods for a Class of Two-stage Flow-shop Scheduling Problem with the Batch Processor. Proceedings of the 16th IEEE International Conference on Automation Science and Engineering (CASE); Hong Kong, China, 20–21 August 2020; pp. 728-733. [DOI: https://dx.doi.org/10.1109/case48305.2020.9216748]

43. Robert, O.; Hankun, Z.; Shifeng, L.; Borut, B. Improved Heuristic Kalman Algorithm for Solving Multi-Objective Flexible Job Shop Scheduling Problem. Procedia Manuf.; 2018; 17, pp. 895-902. [DOI: https://dx.doi.org/10.1016/j.promfg.2018.10.142]

44. Zadeh, M.S.; Katebi, Y.; Doniavi, A. A heuristic model for dynamic flexible job shop scheduling problem considering variable processing times. Int. J. Prod. Res.; 2018; 57, pp. 3020-3035. [DOI: https://dx.doi.org/10.1080/00207543.2018.1524165]

45. Ziaee, M.; Mortazavi, J.; Amra, M. Flexible job shop scheduling problem considering machine and order acceptance, transportation costs, and setup times. Soft Comput.; 2021; 26, pp. 3527-3543. [DOI: https://dx.doi.org/10.1007/s00500-021-06481-y]

46. Amaro, D.; Rosenkranz, M.; Fitzpatrick, N.; Hirano, K.; Fiorentini, M. A case study of variational quantum algorithms for a job shop scheduling problem. EPJ Quantum Technol.; 2022; 9, [DOI: https://dx.doi.org/10.1140/epjqt/s40507-022-00123-4]

47. Zheng, S.Q.; Wang, Q.; WU, Z.X.; Xu, K. Industrial Intelligence Technology and Application; Shanghai Science and Technology Press: Shanghai, China, 2019; 250. ISBN 978-7-5478-4277-5 (In Chinese)

48. Luo, X.; Qian, Q.; Fu, Y.F. Review of Application of Genetic Algorithms for Solving Flexible Job Shop Scheduling Problems. Comput. Eng. Appl.; 2019; 55, 15–21+34.

49. Li, M.; Yao, M. Research on Improved Genetic Algorithm Solving Flexible Job-Shop Problem. Proceedings of the 3rd International Conference on Manufacturing Science and Engineering (ICMSE 2012); Xiamen, China, 27–29 March 2012; pp. 1918-1921. [DOI: https://dx.doi.org/10.4028/www.scientific.net/AMR.479-481.1918]

50. Wu, J.H. Research and Application of Multi-Objective Dynamic Production Scheduling Method for Aerospace Products. Master’s Thesis; Southwest University of Science and Technology: Mianyang, China, 2019.

51. Janes, G.; Perinic, M.; Jurkovic, Z. An efficient genetic algorithm for job shop scheduling problems. Tehnički Vjesnik; 2017; 24, pp. 1243-1247. [DOI: https://dx.doi.org/10.17559/tv-20150527133957]

52. Sang, Y.; Tan, J.; Liu, W. Research on Many-Objective Flexible Job Shop Intelligent Scheduling Problem Based on Improved NSGA-III. IEEE Access; 2020; 8, pp. 157676-157690. [DOI: https://dx.doi.org/10.1109/ACCESS.2020.3020056]

53. Xuan, J.; Li, C.; Jiang, X. Research on Multi-objective Fuzzy Flexible Job-Shop Scheduling Based on Cloud Computinger. Proceedings of the 8th IEEE International Conference on Computer Science and Network Technology (ICCSNT); Dalian, China, 20–22 November 2020; pp. 7-10.

54. Kong, L.; Wang, L.; Li, F.; Wang, G.; Fu, Y.; Liu, J. A New Sustainable Scheduling Method for Hybrid Flow-Shop Subject to the Characteristics of Parallel Machines. IEEE Access; 2020; 8, pp. 79998-80009. [DOI: https://dx.doi.org/10.1109/ACCESS.2020.2982570]

55. Liu, Q.; Li, X.; Gao, L.; Li, Y. A Modified Genetic Algorithm with New Encoding and Decoding Methods for Integrated Process Planning and Scheduling Problem. IEEE Trans. Cybern.; 2021; 51, pp. 4429-4438. [DOI: https://dx.doi.org/10.1109/TCYB.2020.3026651]

56. Li, G. Improved Adaptive Genetic Algorithm for Flexible Job Shop Scheduling Problem. Sci. J. Econ. Manag. Res.; 2022; 4, pp. 77-88.

57. Zhang, G.; Hu, Y.; Sun, J.; Zhang, W. An improved genetic algorithm for the flexible job shop scheduling problem with multiple time constraints. Swarm Evol. Comput.; 2020; 54, 100664. [DOI: https://dx.doi.org/10.1016/j.swevo.2020.100664]

58. Gao, X.; Yang, S.; Li, L. Optimization of flow shop scheduling based on genetic algorithm with reinforcement learning. J. Phys. Conf. Ser.; 2022; 2258, [DOI: https://dx.doi.org/10.1088/1742-6596/2258/1/012019]

59. Jiang, P.; Ding, J.L.; Guo, Y. Application and Dynamic Simulation of Improved Genetic Algorithm in Production Workshop Scheduling. Int. J. Simul. Model.; 2018; 17, pp. 159-169. [DOI: https://dx.doi.org/10.2507/IJSIMM17(1)CO3]

60. Wu, P.J.; Yang, D. E-Commerce Workshop Scheduling Based on Deep Learning and Genetic Algorithm. Int. J. Simul. Model.; 2021; 20, pp. 192-200. [DOI: https://dx.doi.org/10.2507/IJSIMM20-1-CO4]

61. Peng, C.; Wu, G.; Liao, T.W.; Wang, H. Research on multi-agent genetic algorithm based on tabu search for the job shop scheduling problem. PLoS ONE; 2019; 14, e0223182. [DOI: https://dx.doi.org/10.1371/journal.pone.0223182]

62. Li, J.; Huang, Y.; Niu, X. A branch population genetic algorithm for dual-resource constrained job shop scheduling problem. Comput. Ind. Eng.; 2016; 102, pp. 113-131. [DOI: https://dx.doi.org/10.1016/j.cie.2016.10.012]

63. Li, B.; Jin, B.-F. Research on Dynamic Multi-objective FJSP Based on Genetic Algorithm. Proceedings of the 2018 IEEE 16th Intl Conf on Dependable, Autonomic and Secure Computing, 16th Intl Conf on Pervasive Intelligence and Computing, 4th Intl Conf on Big Data Intelligence and Computing and Cyber Science and Technology Congress (DASC/PiCom/DataCom/CyberSciTech); Athens, Greece, 12–15 August 2018; pp. 347-352. [DOI: https://dx.doi.org/10.1109/dasc/picom/datacom/cyberscitec.2018.00-97]

64. Jiang, X.; Tian, Z.; Liu, W.; Suo, Y.; Chen, K.; Xu, X.; Li, Z. Energy-efficient scheduling of flexible job shops with complex processes: A case study for the aerospace industry complex components in China. J. Ind. Inf. Integr.; 2021; 27, 100293. [DOI: https://dx.doi.org/10.1016/j.jii.2021.100293]

65. Tian, S.; Wang, T.; Zhang, L.; Wu, X. An Energy-Efficient Scheduling Approach for Flexible Job Shop Problem in an Internet of Manufacturing Things Environment. IEEE Access; 2019; 7, pp. 62695-62704. [DOI: https://dx.doi.org/10.1109/ACCESS.2019.2915948]

66. Shen, F.P.; Li, J.J.; Yang, Y.L.; Liao, S.L. Batch scheduling model of heat treatment with minimization waiting time and the solution with PSO. Comput. Simul.; 2020; 37, pp. 200-204.

67. Cao, Y.; Shi, H.; Chang, D. Differential evolution algorithm with dynamic multi-population applied to flexible job shop schedule. Eng. Optim.; 2021; 54, pp. 387-408. [DOI: https://dx.doi.org/10.1080/0305215X.2021.1872067]

68. Shen, L.; Dauzère-Pérès, S.; Neufeld, J.S. Solving the flexible job shop scheduling problem with sequence-dependent setup times. Eur. J. Oper. Res.; 2018; 265, pp. 503-516. [DOI: https://dx.doi.org/10.1016/j.ejor.2017.08.021]

69. Alkhateeb, F.; Abed-Alguni, B.H.; Al-Rousan, M.H. Discrete hybrid cuckoo search and simulated annealing algorithm for solving the job shop scheduling problem. J. Supercomput.; 2021; 78, pp. 4799-4826. [DOI: https://dx.doi.org/10.1007/s11227-021-04050-6]

70. Xu, M.; Zhang, S.; Deng, G. No-Wait Job Shop Scheduling Using a Population-Based Iterated Greedy Algorithm. Algorithms; 2021; 14, 145. [DOI: https://dx.doi.org/10.3390/a14050145]

71. Ma, H.; Huang, X.; Cui, X.; Wang, P.; Chen, Y.; Hu, Z.; Hua, L. Management Control and Integration Technology of Intelligent Production Line for Multi-Variety and Complex Aerospace Ring Forgings: A Review. Metals; 2022; 12, 1079. [DOI: https://dx.doi.org/10.3390/met12071079]

72. Al-Wswasi, M.; Ivanov, A.; Makatsoris, H. A survey on smart automated computer-aided process planning (ACAPP) techniques. Int. J. Adv. Manuf. Technol.; 2018; 97, pp. 809-832. [DOI: https://dx.doi.org/10.1007/s00170-018-1966-1]

73. Wei, S.; Bai, Y.; Wang, X.; Kai, L.; Xu, L.; de Vrieze, P.; Kasse, J.P. A New Method for Manufacturing Process Autonomous Planning in Intelligent Manufacturing System. Proceedings of the Advanced Information Systems Engineering Workshops (CAISE 2019); Rome, Italy, 3–7 June 2019; pp. 51-63. [DOI: https://dx.doi.org/10.1007/978-3-030-20948-3_5]

74. Chen, C.-S.; Sun, Y.T.A. Intelligent Computer-aided Process Planning of Multi-axis CNC Tapping Machine. IEEE Access; 2017; 5, pp. 2913-2920. [DOI: https://dx.doi.org/10.1109/ACCESS.2017.2671864]

75. Ouelhadj, D.; Petrovic, S. A survey of dynamic scheduling in manufacturing systems. J. Sched.; 2008; 12, pp. 417-431. [DOI: https://dx.doi.org/10.1007/s10951-008-0090-8]

76. Toba, H. Segment-based approach for real-time reactive rescheduling for automatic manufacturing control. IEEE Trans. Semicond. Manuf.; 2000; 13, pp. 264-272. [DOI: https://dx.doi.org/10.1109/66.857934]

77. Zhang, Y.; Huang, G.Q.; Sun, S.; Yang, T. Multi-agent based real-time production scheduling method for radio frequency identification enabled ubiquitous shopfloor environment. Comput. Ind. Eng.; 2014; 76, pp. 89-97. [DOI: https://dx.doi.org/10.1016/j.cie.2014.07.011]

78. Zhang, Y.; Wang, J.; Liu, S.; Qian, C. Game Theory Based Real-Time Shop Floor Scheduling Strategy and Method for Cloud Manufacturing. Int. J. Intell. Syst.; 2016; 32, pp. 437-463. [DOI: https://dx.doi.org/10.1002/int.21868]

79. Takeda Berger, S.L.; Zanella, R.M.; Frazzon, E.M. Towards a data-driven predictive-reactive production scheduling approach based on inventory availability. Proceedings of the 9th IFAC/IFIP/IFORS/IISE/INFORMS Conference on Manufacturing Modelling, Management and Control (IFAC MIM); Berlin, Germany, 28–30 August 2019; pp. 1343-1348. [DOI: https://dx.doi.org/10.1016/j.ifacol.2019.11.385]

80. Kalinowski, K.; Krenczyk, D.; Grabowik, C. Predictive—Reactive strategy for real time scheduling of manufacturing systems. Proceedings of the International Conference on Mechatronics and Computational Mechanics (ICMCM 2012); Dubai, United Arab Emirates, 20–21 December 2012; pp. 470-473. [DOI: https://dx.doi.org/10.4028/www.scientific.net/AMM.307.470]

81. Jiang, S.-L.; Liu, M.; Lin, J.-H.; Zhong, H.-X. A prediction-based online soft scheduling algorithm for the real-world steelmaking-continuous casting production. Knowledge-Based Syst.; 2016; 111, pp. 159-172. [DOI: https://dx.doi.org/10.1016/j.knosys.2016.08.010]

82. Tighazoui, A.; Sauvey, C.; Sauer, N. Predictive-reactive Strategy for Flowshop Rescheduling Problem: Minimizing the Total Weighted Waiting Times and Instability. J. Syst. Sci. Syst. Eng.; 2021; 30, pp. 253-275. [DOI: https://dx.doi.org/10.1007/s11518-021-5490-8]

83. Zhang, X.; Han, Y.; Królczyk, G.; Rydel, M.; Stanislawski, R.; Li, Z. Rescheduling of Distributed Manufacturing System with Machine Breakdowns. Electronics; 2022; 11, 249. [DOI: https://dx.doi.org/10.3390/electronics11020249]

84. Xiao, S.; Wu, Z.; Yu, S. A two-stage assignment strategy for the robust scheduling of dual-resource constrained stochastic job shop scheduling problems. Proceedings of the 9th IFAC/IFIP/IFORS/IISE/INFORMS Conference on Manufacturing Modelling, Management and Control (IFAC MIM); Berlin, Germany, 28–30 August 2019; pp. 421-426. [DOI: https://dx.doi.org/10.1016/j.ifacol.2019.11.092]

85. Du, W.; Tang, Y.; Leung, S.Y.S.; Tong, L.; Vasilakos, A.V.; Qian, F. Robust Order Scheduling in the Discrete Manufacturing Industry: A Multiobjective Optimization Approach. IEEE Trans. Ind. Inform.; 2017; 14, pp. 253-264. [DOI: https://dx.doi.org/10.1109/TII.2017.2664080]

86. Mejía, G.; Lefebvre, D. Robust scheduling of flexible manufacturing systems with unreliable operations and resources. Int. J. Prod. Res.; 2019; 58, pp. 6474-6492. [DOI: https://dx.doi.org/10.1080/00207543.2019.1682706]

87. Zanchettin, A.M. Robust scheduling and dispatching rules for high-mix collaborative manufacturing systems. Flex. Serv. Manuf. J.; 2021; 34, pp. 293-316. [DOI: https://dx.doi.org/10.1007/s10696-021-09406-x]

88. Long, J.; Sun, Z.; Pardalos, P.M.; Bai, Y.; Zhang, S.; Li, C. A robust dynamic scheduling approach based on release time series forecasting for the steelmaking-continuous casting production. Appl. Soft Comput.; 2020; 92, 106271. [DOI: https://dx.doi.org/10.1016/j.asoc.2020.106271]

89. Ghaleb, M.; Taghipour, S.; Zolfagharinia, H. Real-time integrated production-scheduling and maintenance-planning in a flexible job shop with machine deterioration and condition-based maintenance. J. Manuf. Syst.; 2021; 61, pp. 423-449. [DOI: https://dx.doi.org/10.1016/j.jmsy.2021.09.018]

90. Chabot, A.; Laroche, N.; Carcreff, E.; Rauch, M.; Hascoët, J.-Y. Towards defect monitoring for metallic additive manufacturing components using phased array ultrasonic testing. J. Intell. Manuf.; 2019; 31, pp. 1191-1201. [DOI: https://dx.doi.org/10.1007/s10845-019-01505-9]

91. Park, S.-H.; Choi, S.; Jhang, K.-Y. Porosity Evaluation of Additively Manufactured Components Using Deep Learning-based Ultrasonic Nondestructive Testing. Int. J. Precis. Eng. Manuf. Technol.; 2021; 9, pp. 395-407. [DOI: https://dx.doi.org/10.1007/s40684-021-00319-6]

92. Song, Y.; Zi, X.; Fu, Y.; Li, X.; Chen, C.; Zhou, K. Nondestructive testing of additively manufactured material based on ultrasonic scattering measurement. Measurement; 2018; 118, pp. 105-112. [DOI: https://dx.doi.org/10.1016/j.measurement.2018.01.020]

93. Dong, W.; Hu, W.; Niu, H.; Zhang, X.; Liu, Y. X-ray non-destructive inspection of automobile subframe based on machine learning. Proceedings of the 6th International Conference on Electromechanical Control Technology and Transportation (ICECTT); Chongqing, China, 14–16 May 2021; [DOI: https://dx.doi.org/10.1117/12.2624144]

94. Hangai, Y.; Kawato, D.; Ohashi, M.; Ando, M.; Ogura, T.; Morisada, Y.; Fujii, H.; Kamakoshi, Y.; Mitsugi, H.; Amagai, K. X-ray Radiography Inspection of Pores of Thin Aluminum Foam during Press Forming Immediately after Foaming. Metals; 2021; 11, 1226. [DOI: https://dx.doi.org/10.3390/met11081226]

95. Tang, Z.; Tian, E.; Wang, Y.; Wang, L.; Yang, T. Nondestructive Defect Detection in Castings by Using Spatial Attention Bilinear Convolutional Neural Network. IEEE Trans. Ind. Inform.; 2020; 17, pp. 82-89. [DOI: https://dx.doi.org/10.1109/TII.2020.2985159]

96. Wankerl, H.; Stern, M.L.; Altieri-Weimar, P.; Al-Baddai, S.; Lang, K.-J.; Roider, F.; Lang, E.W. Fully convolutional networks for void segmentation in X-ray images of solder joints. J. Manuf. Process.; 2020; 57, pp. 762-767. [DOI: https://dx.doi.org/10.1016/j.jmapro.2020.07.021]

97. Allam, A.; Moussa, M.; Tarry, C.; Veres, M. Detecting Teeth Defects on Automotive Gears Using Deep Learning. Sensors; 2021; 21, 8480. [DOI: https://dx.doi.org/10.3390/s21248480]

98. Joshi, K.; Patil, B. Evaluation of Surface Roughness by Machine Vision Using Neural Networks Approach. Proceedings of the International Conference on Recent Advances in Mechanical Infrastructure (ICRAM), Inst Infrastructure Technol Res & Management; Ahmedabad, India, 20–21 April 2019; pp. 25-31. [DOI: https://dx.doi.org/10.1007/978-981-32-9971-9_3]

99. Hashmi, A.W.; Mali, H.S.; Meena, A.; Khilji, I.A.; Hashmi, M.F.; Saffe, S.N.B.M. Machine vision for the measurement of machining parameters: A review. Proceedings of the International Conference on Applied Research and Engineering (ICARAE); Cape Town, South Africa, 26–28 November 2021; pp. 1939-1946. [DOI: https://dx.doi.org/10.1016/j.matpr.2021.11.271]

100. Wang, J.; Lee, S. Data Augmentation Methods Applying Grayscale Images for Convolutional Neural Networks in Machine Vision. Appl. Sci.; 2021; 11, 6721. [DOI: https://dx.doi.org/10.3390/app11156721]

101. Chu, H.-H.; Wang, Z.-Y. A study on welding quality inspection system for shell-tube heat exchanger based on machine vision. Int. J. Precis. Eng. Manuf.; 2017; 18, pp. 825-834. [DOI: https://dx.doi.org/10.1007/s12541-017-0098-0]

102. Du, W.; Shen, H.; Fu, J.; Zhang, G.; He, Q. Approaches for improvement of the X-ray image defect detection of automobile casting aluminum parts based on deep learning. NDT E Int.; 2019; 107, 102144. [DOI: https://dx.doi.org/10.1016/j.ndteint.2019.102144]

103. Zhou, Z.G.; Li, W.T.; Li, Y.; Gao, Y.F. Development of Ultrasonic Phased Array Immersion C-Scan Automatic Detection System. J. Mech. Eng.; 2017; 53, pp. 28-34. [DOI: https://dx.doi.org/10.3901/JME.2017.12.028]

104. Sun, Y.; Li, F.G.; Liang, D.C.; Ling, Y.H. Intelligent line control and integration technology in aerospace large-scale ring forgings. Forg. Stamp. Technol.; 2020; 45, pp. 192-197. [DOI: https://dx.doi.org/10.13330/j.issn.1000-3940.2020.05.033]

105. Meng, X.L. Design and Application of Seamless Steel Pipe Process Control System. Ind. Control Comput.; 2021; 34, pp. 1-3.

106. Weihrauch, D.; Schindler, P.A.; Sihn, W. A conceptual model for developing a smart process control system. Proceedings of the 1th CIRP Conference on Intelligent Computation in Manufacturing Engineering (CIRP ICME); Naples, Italy, 19–21 July 2017; pp. 386-391. [DOI: https://dx.doi.org/10.1016/j.procir.2017.12.230]

107. Zhou, Y.L.; Yuan, M.; Zhou, Y.S.; Chen, J.; Zhang, Z.; Chen, Y.Z. Intelligent management and control technology for dynamic disturbance factors in production of complex ring forgings in aerospace. Forg. Stam. Technol.; 2020; 45, pp. 7-14. [DOI: https://dx.doi.org/10.13330/j.issn.1000-3940.2020.12.002]

108. Zhou, Y.L.; Zhang, Z.; Zhou, Y.S.; Chen, J.; Yin, H.P.; Li, J.; Zhang, J.L.; Lin, X. Intelligent information production scheduling technology of heat treatment process. Heat Treat. Met.; 2020; 45, pp. 242-247. [DOI: https://dx.doi.org/10.13251/j.issn.0254-6051.2020.12.047]