Optimization and Prediction of Tool Wear Using Hybrid Grey Relation Analysis and Regression for Milling Operation

Milling is a machining process that is used to remove material from a workpiece by rotating a tool with cutting edges. The efficiency and accuracy of the milling process can be improved by optimizing the cutting parameters, such as the feed rate, spindle speed, and depth of cut. In this study, a hybrid regression and grey relation analysis (GRA) approach is proposed for the optimization of milling operations. The hybrid regression model is used to predict the cutting force, which is a key parameter that affects the efficiency and accuracy of the milling process. The GRA algorithm is used to optimize the cutting parameters based on the predicted cutting force. The proposed approach was evaluated on a set of milling experiments. The results showed that the proposed approach can effectively optimize the cutting parameters and improve the efficiency and accuracy of the milling process. The proposed approach is a promising new method for the optimization of milling operations. It is more efficient and accurate than traditional methods, and it can be easily implemented in practice linear regression as an optimizer has a tendency of deviate from the optimal point based upon the learning rate. Tuning of these hyperparameters is not easy as it sounds on paper and it is also computationally expensive. An alternate way is to use GRA which focuses more on the data provided to it, thereby completely avoiding the need of tuning the parameters, but also ensuring that the optimal point is reached on a lesser computational expense.