Comparison of intelligent optimization algorithms for crack shape reconstruction from ECT signals

Intelligent optimization is a vibrant area of investigation, with some of the widely known and used approaches being Genetic Algorithm, Ant Colony Optimization and Particle Swarm Optimization Algorithm. An inversion algorithm for the reconstruction of natural crack shape from eddy current testing signals is developed by using an artificial neural network based forward model and intelligent inversion algorithm. The true crack shapes and the measured eddy current testing signals are used to train the neural network. The parameters of the algorithms are modified, their effectiveness on crack shape inversion problem are compared and discussed. The reconstructed results verified the efficiency of neural network based forward model and the promising of intelligent optimization algorithms in crack shape inversion.