Title :
Application of ANN in the Thickness Measuring of Conductive Materials
Author :
Zhang Wei ; Qu Surong ; Li, Li ; Miao Qinglin ; Song Changyuan
Author_Institution :
Sch. of Mechinery & Electron., Henan Inst. of Sci. & Technol., Xinxiang, China
Abstract :
Eddy current testing (ECT) is becoming a widely used inspection technique, particularly in the aircraft, power and nuclear industries. Many factors may affect the eddy current response. Inverse problems to determine the thickness from ECT signals of multilayer conductors have been a challenge for a certain degree. The objectives of this study are to introduce a method based on improved back propagation neural network (BPNN) to identify the multilayer thickness from their ECT signals. The simulation study and an experimental validation carried out on a number of specimens with different known thickness confirmed the suitability of the proposed approach for multilayer thickness measuring.
Keywords :
backpropagation; eddy current testing; inspection; neural nets; production engineering computing; ANN; back propagation neural network; conductive materials; eddy current response; eddy current testing; inspection technique; inverse problems; multilayer conductors; multilayer thickness measuring; Aerospace materials; Aircraft; Artificial neural networks; Conducting materials; Conductivity measurement; Eddy current testing; Electrical capacitance tomography; Inspection; Multi-layer neural network; Thickness measurement;
Conference_Titel :
Artificial Intelligence and Computational Intelligence, 2009. AICI '09. International Conference on
Conference_Location :
Shanghai
Print_ISBN :
978-1-4244-3835-8
Electronic_ISBN :
978-0-7695-3816-7
DOI :
10.1109/AICI.2009.468
