Content area
Full text
Abstract:
This work presents a hybridized neuro-genetic control solution for R^sup 3^ workspace application. The solution is based on a multi-objective genetic algorithm reference generator and an adaptive predictive neural network strategy. The trajectory calculation between two points in an R^sup 3^ workspace is a complex optimization problem considering the fact that there are multiple objectives, restrictions and constraint functions which can play an important role in the problem and be in competition. We solve this problem using genetic algorithms, in a multi objective optimization strategy. Subsequently, we enhance a training algorithm in order to achieve the best adaptation of the neural network parameters in the controller which is responsible for generating the control action for a nonlinear system. As an application of the proposed hybridized control scheme, a crane tracking control is presented.
Key words: Hybrid neuro-genetic solution, optimal trajectory generation, multi-objective genetic algorithm, nonlinear neural control, adaptive predictive control
Received: 20th September 2010
Revised and accepted: 13th November 2010
(ProQuest: ... denotes formulae omitted.)
1. Introduction
Nowadays, our aggressive market requires more accurate, reliable, productive, and competitive industrial solutions. This involves a monumental effort from researchers and technicians in order to solve complex, real- world problems. One of these problems is the industrial kinematic control (where it is necessary to handle raw materials, semi- finished and finished products), which implies a wide number of goals to reach [1]. In sequential industrial processes, for the transportation, handling and machining of materials and products into different manufacturing workplaces, it is more essential than ever to obtain automated and enhanced solutions based on new technologies such as computational intelligence.
This work presents a hybrid intelligent solution that solves tracking and movement problems in an jR3 workspace. It uses a complex calculation of a precise trajectory. It also solves accuracy and control action issues for precise and safe tracking operations. Our solution uses different computational intelligence techniques for solving these problems. We initially implemented one device for tracing optimal trajectories as the reference to the control system. Later on, we chose a control scheme based on adaptive and predictive control fields. Previous control loop approaches have been studied as presented in [2] where a 2D crane ant i- swing problem is solved.
The first part...