Machine tool fault classification diagnosis based on audio parameters

With the increasing precision, complexity, and diversification of CNC machine tools, the requirements for fault detection technology of CNC machine tools are getting essential.If problems such as tool wear and spindle locking can not be found in time, it will lead to the waste of a large number of raw materials and production time. Aiming at the fault problem of high-precision NC machine tools, this paper uses the method based on DWT and statistical domain to extract features from audio signals to form data sets, and proposes a lightweight convolution neural network to identify the fault types of machine tools.Firstly, features are extracted from MIMII public data sets, and evaluates the data sets by using three machine learning models (SVM, KNN, and GNB).The results show that when facing different materials and structures, the model trained by extracting features from mechanical audio signals based on wavelet transform and statistical domain has good prediction accuracy.Then, this method is used for audio data of CNC machine tools in a real factory environment.The data set includes six common machine tool faults, including normal operation, tool wear, spindle locking, tool idling, abnormal impact, and back cutting amount.A lightweight convolution neural network was used to identify fault types in machine tools. The experimental results show that the recognition accuracy of the trained model is 97.85%, AUC is 0.9984, and F1 is 0.9769. Compared with the DNN proposed by Jong-Yi (Kuo et al., 2022) [1] , it has been improved in all aspects. The accuracy of fault recognition is improved from 96.1% to 97.85% compared with the method of sound fusion feature and OCSVM (Ding et al., 2022) [2].