USING NEURAL-NETWORK FOR TOOL CONDITION MONITORING BASED ON WAVELET DECOMPOSITION

This paper presents a neural network application for on-line tool cond ition monitoring in a turning operation. A wavelet technique was used to decompose dynamic cutting force signal into different frequency ban ds in time domain. Two features were extracted from the decomposed sig nal for each frequency band. The two extracted features were mean valu es and variances of the local maxima of the absolute value of the comp osed signal. In addition, coherence coefficient in low frequency band was also selected as a signal feature. After scaling, these features w ere fed to a back-propagation neural network for the diagnostic purpos es. The effect on tool condition monitoring due to the presence of chi p breaking was studied. The different numbers of training samples were used to train the neural network and the results were discussed. The experimental results show that the features extracted by wavelet techn ique had a low sensitivity to changes of the cutting conditions and th e neural network has high diagnosis success rate in a wide range of cu tting conditions.