Research On Structural Health Monitoring Based On Genetic Algorithms And Fuzzy Neural Network

Firstly, a comprehensive discussion about the intelligence algorithm for structure health monitoring, and the models of neural network were also presented in this paper, while the shortcoming of various neural networks were pointed out. On the basis of the state-of-the-art investigation, the genetic algorithms, fuzzy sets theory and neural network technology were combined together, and then new training algorithms for neural network were constructed for structural health monitoring. Secondly, a improved training algorithm of Radial Base Function (shorted for RBF) neural network was presented and a program of RBF neural network base on hybrid hierarchy genetic algorithm was finished. The hybrid hierarchy genetic algorithm, which was introduced by combining hierarchy genetic algorithm and least-square method, was able to determine the structure and parameters of the RBF neural network; Thirdly, genetic algorithms was introduced into the algorithm of fuzzy neural network to optimize the part of Fuzzy clustering algorithm, and the relevant program were finished. Furthermore, fiber reinforced composite beams were fabricated, and the composite beams' modal frequencies were measured by an experiment method. moreover, a novel method combining computational mechanics and neural network was demonstrated for composite health monitoring; The first six flexure modal frequencies obtained by FEM were modified by a primary revising approach and were used to train the RBF neural network base on hybrid hierarchy genetic algorithm and Fuzzy RBF neural network base on genetic algorithm, respectively. Finally, the first six flexure experimental modal frequencies were input to the RBF neural network and Fuzzy RBF neural network to predict the demalination location and extent respectively. The predicted results of the above-mentioned networks demonstrate that Fuzzy RBF neural network base on genetic algorithm was more robust and better than RBF neural network base on hybrid hierarchy genetic algorithm in the field of health monitoring for composite structures.