Research On Tool Wear Condition Recognition Based On Acoustic Emission In Milling

Real-time monitoring of tool wear condition is the key technology of advanced manufacture system and is a very important problem in machine processing. How to realize automatic monitoring of tool wear is the significant factor for improvement of machining quality, productivity, and automation of production, which has been considered as a very key technology and important problem that is not yet been solved. Based on the technology status of tool condition monitoring, this paper has carried out research on the tool wear condition monitoring by acoustic emission signals, primarily deals with the following research efforts:(1) Construct tool wear monitoring experiment system in milling. The sensing unit of acoustic emission and data-acquisition card are used to detect and collect the acoustic emission signals of different wear stages. Then the acoustic emission signals were analyzed by statistics analysis and power spectrum. The characteristic component which changes with the increase of tool wear degree has been discovered by above analysis. So it has been proved feasible that the tool condition could be monitored well by acoustic emission signals.(2) The acoustic emission signals are affected by some factors such as spindle revolution, feed rate, cutting depth. By analyzing data of single-factor experiment, the influences of these factors on acoustic emission frequency are discussed in detail. The result indicates that with the change of the factors, the increasing trend of root-mean-square deviation among the feature extraction by cutting depth is the most obvious, then is spindle revolution and the feed rate factor shows the most unobvious increasing trend.(3) Based on the characteristic that wavelet transform can analyze the high-frequency signal, we process the multi-resolution wavelet decomposition frequency band energy of the acoustic emission signals, abstract characteristic number reflecting tool wear condition remarkably which is used as the input of neural network.(4) Use neural network and build the non-linear mapping relation between tool wear characteristic vector and tool wear condition, accordingly to realize the effective identification of different tool wear conditions.