Study on wear state of ultrasonic-assisted grinding of glass-ceramics with diamond tools based on DBO-BiLSTM

Abstract

With the development of precision manufacturing technology, diamond tools play a vital role in industrial machining because of their high hardness and excellent wear resistance. However, tool wear can seriously affect machining accuracy and efficiency. In order to ensure the efficient and high-quality machining, it is of paramount importance to monitor the state of the tools used with the utmost accuracy. First, the fixed area of the diamond tool after machining was observed. The ratio of the number of abrasive particles falling off and the presence of scratches in the matrix were used as the evaluation indexes of the wear state of the diamond tool. The vibration signal was used as a monitoring signal to identify the wear state of the diamond tools. To obtain a feature set sensitive to the tool wear state, the vibration signal was analyzed in the time domain, frequency domain, and wavelet packet. The dimensionality of the sensitive feature set is reduced through the application of principal component analysis (PCA). The tool wear state was identified using the dung beetle optimizer bidirectional long short-term memory (DBO-BiLSTM) model and the bidirectional long short-term memory (BiLSTM) model. The results demonstrate that the DBO-BiLSTM has a higher accuracy in wear state identification, showing an improvement of 10.05% over the BiLSTM. Moreover, optimizing feature dimension reduction can enhance the model’s identification accuracy.