Content area
Inverse problem-solving methods have found applications in various fields, such as structural mechanics, acoustics, and non-destructive testing. However, accurately solving inverse problems becomes challenging when observed data are incomplete. Fortunately, advancements in computer science have paved the way for data-based methods, enabling the discovery of nonlinear relationships within diverse data sets. In this paper, a step-by-step completion method of displacement information is introduced and a data-driven approach for predicting structural parameters is proposed. The accuracy of the proposed approach is 23.83% higher than that of the Genetic Algorithm, demonstrating the outstanding accuracy and efficiency of the data-driven approach. This work establishes a framework for solving mechanical inverse problems by leveraging a data-based method, and proposes a promising avenue for extending the application of the data-driven approach to structural health monitoring.
Details
Structural health monitoring;
Nondestructive testing;
Genetic algorithms;
Inverse problems;
Acoustics;
Accuracy;
Data processing;
Numerical analysis;
Aerospace engineering;
Mechanics;
Boundary conditions;
Efficiency;
Machine learning;
Partial differential equations;
Sensors;
Neural networks;
Methods;
Optimization algorithms
1 Beijing Institute of Technology, School of Aerospace Engineering, Beijing, China (GRID:grid.43555.32) (ISNI:0000 0000 8841 6246)
2 Tsinghua University, Applied Mechanics Laboratory, Department of Engineering Mechanics, School of Aerospace, Beijing, China (GRID:grid.12527.33) (ISNI:0000 0001 0662 3178)
3 Beijing Institute of Technology, School of Aerospace Engineering, Beijing, China (GRID:grid.43555.32) (ISNI:0000 0000 8841 6246); Beijing Institute of Technology, Tangshan Research Institute, Tangshan, China (GRID:grid.43555.32) (ISNI:0000 0000 8841 6246)