Machine tool operating vibration prediction based on multi-sensor fusion and LSTM neural network

Abstract

This study proposes a machine tool vibration prediction method based on multi-sensor fusion and a long short-term memory (LSTM) network. Machine tool vibration significantly impacts machining quality, surface roughness, dimensional accuracy, and tool wear. By combining deep learning with industrial applications, this method achieves high-precision vibration prediction through multi-sensor data fusion. Data is input into the LSTM model to predict the next moment's vibration. Experimental results demonstrate strong prediction capability for periodic vibrations and machining-specific vibration errors, effectively enhancing machining accuracy.