Milling cutter wear prediction method based on improved PCANet model

Abstract

The invention belongs to the related technical field of cutter state monitoring, and discloses a milling cutter wear prediction method based on an improved PCANet model, and the method comprises the following steps: (1) inputting a training set into the improved PCANet model for training; the improved PCANet model is divided into an APCANet-MP model and an SVR model, the APCANet-MP model is further divided into three stages, the data processing modes of the first stage and the second stage are completely consistent, and each stage comprises a preprocessing layer, a PCA convolution layer and an activation layer; the post-processing stage comprises a maximum pooling layer and an output layer; the SVR model adopts a linear kernel function; (2) evaluating the trained improved PCANet model by using an evaluation index, and optimizing structural parameters of the improved PCANet model according to an evaluation result; and (3) inputting signal data of a to-be-predicted milling cutter into the optimized improved PCANet model so as to predict the wear of the milling cutter. According to the invention, the parameter scale is reduced, and the analysis efficiency and prediction precision are improved.

Description

technical field [0001] The invention belongs to the related technical field of cutter state monitoring, and more particularly relates to a milling cutter wear prediction method based on an improved PCANet model. Background technique [0002] Milling is a commonly used machining method. The health status of the milling cutter directly affects the machining quality and efficiency of the workpiece during the machining process. Therefore, real-time tool condition monitoring has become the focus of current academic and industrial circles. In recent years, many scholars at home and abroad have applied deep learning algorithms represented by convolutional neural networks (CNN) to tool state monitoring. Analyzed, built and trained different network models, and then achieved a more accurate prediction of the current tool wear. However, the feature self-learning process of these models is poorly interpretable, and the prediction results of the same model under the same parameters ar...

AI Technical Summary

Problems solved by technology

Compared with the existing technology, this method can effectively solve the problems of poor interpretability and limited generalization ability faced by the existing deep learning-based tool condition monitoring model, greatly reducing the parameter scale of the model output, and effectively improving the predictive accuracy of the model

Images