Title :
Natural crack recognition using inverse neural model and multi-frequency eddy current method
Author :
Chady, Tomasz ; Enokizono, Masato ; Sikora, Ryszard ; Todaka, Takashi ; Tsuchida, Yuji
Author_Institution :
Oita Ind. Res. Inst., Japan
fDate :
7/1/2001 12:00:00 AM
Abstract :
In this paper a Multi-Frequency Excitation and Spectrogram Eddy Current System and an inverse neural model were used to detect and identify natural flaws in steam generator tubes. It is shown that the applied dynamic neural model of the ECT sensor offers very high speed of operation and guarantees reliability of the recognition results
Keywords :
crack detection; eddy current testing; inverse problems; neural nets; nuclear reactor steam generators; NDE; crack recognition; dynamic neural inverse model; eddy current testing; magnetic sensor; multi-frequency excitation and spectrogram method; natural flaw; steam generator tube; Eddy current testing; Eddy currents; Electrical capacitance tomography; Fatigue; Frequency; Helium; Inverse problems; Magnetic sensors; Nuclear power generation; Spectrogram;
Journal_Title :
Magnetics, IEEE Transactions on
