DocumentCode :
2973564
Title :
Inversion of eddy current NDE signals using artificial neural network based forward model and particle swarm optimization algorithm
Author :
Zhang, Siquan ; Yang, Hefa
Author_Institution :
Coll. of Air Transp., Shanghai Univ. of Eng. Sci., Shanghai, China
fYear :
2009
fDate :
22-24 June 2009
Firstpage :
1314
Lastpage :
1319
Abstract :
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 particle swarm optimization algorithm. Eddy current inspections are performed to measure signals caused by fatigue cracks introduced into plate specimens. The preprocessed ECT signals and the true crack shapes are used in the training of neural network. The parameters of the particle swarm optimization algorithm are modified and the results are discussed. The reconstruction results of crack shape verified both the efficiency of neural network based forward model and the promising of particle swarm optimization algorithm in crack shape inversion.
Keywords :
eddy current testing; fatigue cracks; neural nets; particle swarm optimisation; plates (structures); artificial neural network-based forward model; crack shape inversion; eddy current nondestructive evaluation; eddy current testing signals; fatigue cracks; inversion algorithm; natural crack shape; particle swarm optimization algorithm; plate specimens; Artificial neural networks; Current measurement; Eddy current testing; Eddy currents; Electrical capacitance tomography; Fatigue; Inspection; Particle swarm optimization; Performance evaluation; Shape;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Information and Automation, 2009. ICIA '09. International Conference on
Conference_Location :
Zhuhai, Macau
Print_ISBN :
978-1-4244-3607-1
Electronic_ISBN :
978-1-4244-3608-8
Type :
conf
DOI :
10.1109/ICINFA.2009.5205120
Filename :
5205120
Link To Document :
بازگشت