Remaining Useful Life Prediction of Machining Tools by 1D-CNN LSTM Network

In the field of machining, machining tool life (degree of wear) is a key factor affecting the quality of the machined workpiece. Over-protection strategies may increase production costs and cause unnecessary machining tool downtime. Therefore, if the remaining useful life (RUL) of the machining tool can be accurately predicted, the work schedule will be effectively optimized and the machining tool procurement cost will be reduced. In this paper, we propose a system schema that integrates programmable logic controller (PLC) signals with sensor signals for online RUL prediction of machining tools. The preprocessed sensor signals are segmented and we propose ensemble discrete wavelets transform (EDWT) to eliminate the noise of three-dimensional vibration signals and get time-frequency information. Then statistics features are extracted based on time domain and frequency domain analysis. Further, we use spearman's coefficient, autocorrelation and monotonicity indicators for feature selection to reduce feature dimensions. Finally, we use a 1D-CNN LSTM network architecture for machining tools RUL prediction. The evaluation results show that our system schema is feasible for the industrial field, and has a better performance than other common methods.