Prof. Li Guo
College of Mechanical and Vehicle Engineering,
Hunan University, China
Title: Acoustic emission Intelligent monitoring in grinding
The accuracy of acoustic emission monitoring wear state of diamond grinding wheel in the current engineering ceramics grinding is not high. In Acoustic emission monitoring for precision grinding of partly stabilized zirconia (PSZ), under the condition of severe wear of diamond grinding wheel, the RMS and variances of the wavelet decomposition coefficients of the AE signals and the wavelet energy spectrum coefficients of the acoustic emission signals are increased at low frequency band than that of grinding wheel slight wear. Using the 3 coefficients as the discriminant feature values of wear state of the diamond grinding wheel, classification accuracy of diamond grinding wheel wear states is 100% by genetic algorithm support vector machine(GA-SVM),the classification accuracy by the GA-SVM is better than that by the support vector machine and the BP neural network.