Multi-Objective Monitoring of CVD Diamond Micro-Grinding Tools Using Acoustic Emission and Force Signals with Neural Network Optimization

Micro-grinding has been widely used in aerospace and other industry, and its application was mainly the asymmetric microstructure. Chemical Vapor Deposition (CVD) diamond has drawn attention for its good wear resistance. However, the small diameter and high spindle speed may cause difficulties on the monitoring of the micro-grinding processes. In order to solve the mentioned problem, a novel multi-objective monitoring method of structured CVD diamond micro-grinding tool based on acoustic emission (AE) and force signals is presented in this study to achieve the high efficiency of the tool condition and grinding quality. The relationship between the grinding quality, tool condition, acoustic emission and grinding force signals is found through time, frequency and time–frequency domain analyze. Then, a predication method of the coating delamination is treated. Next, a multi-objective monitoring with Fully Connected Neural Network (FCNN) model is established to predict the tool condition, edge chipping size and surface roughness simultaneously. Finally, the multi-objective FCNN model has improved the overall accuracy of the tool condition from 64.2% to 95% after optimization, the error of the prediction of surface roughness is less than 5% and that of the edge chipping size is less than 15%, and the prediction time has been reduced 55%. The usage of the combination of AE and grinding force signals could improve the prediction accuracy with 10%.