Research on Tool Remaining Life Prediction Method Based on CNN-LSTM-PSO

Efficient and accurate prediction of tool Remaining Useful Life (RUL) is the key to improve product accuracy, improve work efficiency and reduce machining costs. Aiming at the problems of weak tool wear state features, difficult extraction, and low prediction precision and accuracy, this research proposes a CNN-LSTM-PSO tool remaining life prediction method based on multi-channel feature fusion. Firstly, based on computer vision, feature extraction, information fusion technology, the multi-source sensor signals collected during the tool life cycle are effectively processed and analyzed, and a sample data set of spatio-temporal correlation of traffic flow is constructed. Secondly, the sample data set was input into the CNN-LSTM-PSO model, the CNN network obtained the sequence feature vector by extracting the spatial characteristics of traffic flow data, and the feature vector was input into the multi-layer LSTM network to extract the time-dependent features, and the PSO algorithm optimized the hyperparameters in the CNN-LSTM model. The accuracy of tool RUL prediction model and the efficiency of model fitting are further improved. The results show that the CNN-LSTM-PSO model can effectively predict tool wear, with the mean absolute error (MAE) value of 1.0892, the root mean square error (RMSE) value of 1.3520, and the determination coefficient $R^{2}$ value of 0.9961; Through the comparative analysis of ablation experiments, it is found that the method proposed in the research has the highest efficiency in fitting the tool RUL prediction model, the lowest values of MAE value and root mean square error RMSE, and the value of determination coefficient $R^{2}$ is closest to 1, which has certain advantages.The proposed method has reference value and engineering practical significance for the related research of tool wear residual life prediction.