Title :
Neural Network with Adaptive Immune Genetic Algorithm for Eddy Current Nondestructive Testing
Author :
Sun, Xiao-Yun ; Liu, Dong-Hui ; Chen, Ai-zu ; Zhi-Hong Xue
Author_Institution :
Hebei Univ. of Sci. & Technol., Shijiazhuang
Abstract :
For eddy current nondestructive testing (ECNDT), an immune genetic algorithm (IGA) is presented, which can overcome the disadvantages of genetic algorithm (GA), such as possibility of being trapped on locally minimum value and prematurity convergence. Moreover, crossover and mutation operators are selected by adaptive algorithm to overcome prematurity. Compared with GA, the convergence precision and generalization of IGA are improved remarkably
Keywords :
artificial intelligence; eddy current testing; genetic algorithms; neural nets; adaptive algorithm; adaptive immune genetic algorithm; convergence precision; eddy current nondestructive testing; neural network; Adaptive systems; Convergence; Eddy currents; Genetic algorithms; Humans; Immune system; Machine learning; Magnetic fields; Neural networks; Nondestructive testing; Pathogens; Adaptive algorithm; ECNDT; IGA; Prematurity;
Conference_Titel :
Machine Learning and Cybernetics, 2006 International Conference on
Conference_Location :
Dalian, China
Print_ISBN :
1-4244-0061-9
DOI :
10.1109/ICMLC.2006.258399
