Structure noise reduction of ultrasonic signals using artificial neural network adaptive filtering

A multi-layer linear neural network within the framework of adaptive FIR filtering is presented for enhancing the signal-to-noise ratios of ultrasonic signals. The backpropagation (BP) algorithm is used to train and adjust the network weights. From the results obtained on large grained materials and on composites, it is apparent that the performance of the new approach is better than those of conventional adaptive algorithms in reducing the structure noise of ultrasonic signals.

[1]  Xing Li,et al.  Wiener filter realization for target detection using group delay statistics , 1993, IEEE Trans. Signal Process..

[2]  E. S. Furgason,et al.  Flaw-to-grain echo enhancement by split-spectrum processing , 1982 .

[3]  P. M. Shankar,et al.  Split spectrum processing: Determination of the available bandwidth for spectral splitting , 1988 .

[4]  Mohamed Ibnkahla,et al.  Multi-layer adaptive filters trained with back propagation: A statistical approach , 1994, Signal Process..

[5]  Jianqiang Xin Jianqiang Xin,et al.  frequency-diverse geometric- and arithmetic-mean filtering for ultrasonic flaw detection , 1991 .

[6]  S.P. Neal,et al.  Flaw signature estimation in ultrasonic nondestructive evaluation using the Wiener filter with limited prior information , 1993, IEEE Transactions on Ultrasonics, Ferroelectrics and Frequency Control.

[7]  K. D. Donohue,et al.  Maximum likelihood estimation of A-scan amplitudes for coherent targets in media of unresolvable scatterers , 1992, IEEE Transactions on Ultrasonics, Ferroelectrics and Frequency Control.

[8]  Yong Zhu,et al.  Ultrasonic nondestructive evaluation of highly scattering materials using adaptive filtering and detection , 1994, IEEE Transactions on Ultrasonics, Ferroelectrics and Frequency Control.

[9]  Bernard Widrow,et al.  Adaptive Signal Processing , 1985 .

[10]  R. Murthy,et al.  Spectral histogram using the minimization algorithm-theory and applications to flaw detection , 1992, IEEE Transactions on Ultrasonics, Ferroelectrics and Frequency Control.

[11]  J. Aussel.  Split-spectrum processing with finite impulse response filters of constant frequency-to-bandwidth ratio , 1990 .

[12]  T. Stepinski,et al.  Split spectrum algorithms rely on instantaneous phase information-a geometrical approach (US NDE) , 1993, IEEE Transactions on Ultrasonics, Ferroelectrics and Frequency Control.

[13]  P.M. Shankar,et al.  Split-spectrum processing: analysis of polarity threshold algorithm for improvement of signal-to-noise ratio and detectability in ultrasonic signals , 1989, IEEE Transactions on Ultrasonics, Ferroelectrics and Frequency Control.