Optimization of the grinding process to improve the surface integrity of bearing raceways

To improve the grinding process towards a higher surface integrity, in this study, an orthogonal test was designed and conducted to determine the effect of the wheel speed, workpiece speed, and the grinding depth on the surface integrity of a bearing raceway. After the grinding process, the residual stress, the residual austenite content, the surface hardness, the thickness of the affected layer, the surface roughness, and other properties were measured, and a parametric characterization of the surface integrity of the raceway was performed. Using the results of the orthogonal test as training samples, two support vector machine (SVM) models were established, and the prediction accuracy was tested through cross-validation. Finally, the step size search method was used starting at the optimal grinding parameters obtained through the orthogonal test, and the grinding parameters were further optimized using the two SVM models. The results showed that combining an orthogonal test with an SVM model can effectively shorten the time required for optimizing the grinding process, and that a global optimum can be obtained for the surface integrity.