Title :
A hybrid GA-TS algorithm for solving the natural crack shape reconstruction from ECT signals
Author :
Siquan Zhang ; Haojun Xu ; Chang Yin
Author_Institution :
Dept. of Electr. & Autom., Shanghai Maritime Univ., Shanghai, China
Abstract :
This paper presents a method to solve the problem of natural crack shape reconstruction from eddy current testing signals by means of hybrid genetic - tabu search algorithm (GATS). In order to evaluate the efficiency on solving crack shape inversion problem, hybrid GA-TS algorithm is compared with some heuristic algorithms such as particles swarm optimization, ant colony optimization and simple genetic algorithm. The reconstructed results verify the efficiency of neural network based forward model and the promising of hybrid GA-TS algorithm in crack shape inversion.
Keywords :
cracks; eddy current testing; genetic algorithms; mechanical engineering computing; neural nets; search problems; signal reconstruction; ECT signals; ant colony optimization; crack shape inversion problem; eddy current testing signals; genetic algorithm; heuristic algorithms; hybrid GA-TS algorithm; natural crack shape reconstruction; neural network based forward model; particle swarm optimization; simple genetic algorithm; tabu search; Algorithm design and analysis; Eddy current testing; Genetic algorithms; Linear programming; Neural networks; Optimization; Shape; Artificial neural network; Crack shape reconstruction; Eddy current testing; Hybrid GA-TS algorithm;
Conference_Titel :
Mechatronics and Automation (ICMA), 2014 IEEE International Conference on
Conference_Location :
Tianjin
Print_ISBN :
978-1-4799-3978-7
DOI :
10.1109/ICMA.2014.6885930
