Full-Text Search:
Home|About CNKI|User Service|中文
Add to Favorite Get Latest Update

Nonlinear compensation of eddy current sensor based on wavelet neural network

FU Lihua;WANG Gang;School of Electrical Information Engineering,Henan Institute of Engineering;  
To eliminate the nonlinear error and improve the measurement accuracy of eddy current sensor,a nonlinear compensation method of eddy current sensor based on wavelet neural network and genetic algorithm was proposed.The method uses nonlinear mapping ability of wavelet neural network to make input and output of the sensor linearization,and uses genetic algorithm to search the optimal initial value of the wavelet neural network to strengthen network nonlinear approximation ability and convergence capability,which can significantly improve nonlinear compensation effect of eddy current sensor.The experimental results show that accuraty of the sensor is improved greatly after the compensation,the maximum absolute error of output voltage of the sensor is 15.55 mV,the maximum relative error is1.36%,and nonlinear error is 0.34%.
Download(CAJ format) Download(PDF format)
CAJViewer7.0 supports all the CNKI file formats; AdobeReader only supports the PDF format.
©CNKI All Rights Reserved