Title :
Application of self-adaptive wavelet neural networks in ultrasonic detecting
Author :
Yin, Xi-Peng ; Fan, Yang-yu ; Duan, Zhe-Min ; Cheng, Wei
Author_Institution :
Dept. of Electron. Eng., Northwestern Polytech. Univ. (NPU), Xi´´an, China
Abstract :
It is important to remove the noise signal effectively in non-destructive testing. Using the wavelet and neural network algorithm, the author constructed self-adaptive wavelet neural networks in the ultrasonic testing. Better fitting signal is achieved by choosing Orthogonal Daubechies wavelet neuron and optimized scale parameter. The simulation results showed less distortion and better noise cancellation, and the method can be widely applied ton ultrasonic detecting.
Keywords :
interference suppression; neural nets; self-adjusting systems; testing; ultrasonic applications; wavelet transforms; less distortion; neural network algorithm; noise cancellation; nondestructive testing; optimized scale parameter; orthogonal Daubechies wavelet neuron; self-adaptive wavelet neural network; ultrasonic detecting; ultrasonic testing; Automatic testing; Electronic equipment testing; Feedforward neural networks; Neural networks; Noise cancellation; Nondestructive testing; Signal analysis; Signal processing; Signal processing algorithms; Wavelet analysis; neural networks; self-adaptive; ultrasonic; wavelet analysis;
Conference_Titel :
Anti-counterfeiting, Security, and Identification in Communication, 2009. ASID 2009. 3rd International Conference on
Conference_Location :
Hong Kong
Print_ISBN :
978-1-4244-3883-9
Electronic_ISBN :
978-1-4244-3884-6
DOI :
10.1109/ICASID.2009.5276998
