Grinding wheel wear evaluation with the PMSCNN model

The grinding wheel wear significantly affects machining efficiency and machining quality. Consequently, the grinding wheel wear assessment model PMSCNN derived from the Convolutional Neural Network (CNN) and the Transformer model is presented. Firstly, the grinding wheel spindle motor current signal is measured using a current sensor. Then, the time domain features are computed for the current signal obtained after median filtering. The importance of the features is analyzed using the gradient boosting regressor. The four features that have a relatively large impact on the model prediction results are selected based on the importance scores. Finally, the accuracy of the PMSCNN model is confirmed by employing these four features. It is found that the predicted values have a good similarity to the real wear trend, and average values of mean absolute error (MAE), root mean square error (RMSE), and coefficient of determination R² of the cross-validated prediction findings are 3.028, 3.938 and 0.919. It is explained in detail that each module improves the model utilizing modular analysis. The PMSCNN model can extract wear-related patterns and information from the current signal and obtain good prediction accuracy.