Tool wear prediction based on multidomain feature fusion by attention-based depth-wise separable convolutional neural network in manufacturing

Guofa Li,Jialong He,Jili Wang,Yanbo Wang,Yongchao Huo

doi:10.1007/s00170-021-08119-7

Abstract

Computer numerical control (CNC) machine tool is the foundation of the equipment manufacturing industry, and its technical level is an important indicator to measure the development level of a country’s equipment manufacturing industry. Tool wear during machining has a great impact on the important performance indicators of CNC machine tools, such as machining accuracy, machining efficiency and reliability. Tool wear monitoring is of great significance to improve the machining efficiency, machining accuracy and reliability of CNC machine tools. Multidomain features (time domain, frequency domain and time–frequency domain) can accurately characterise the degree of tool wear. However, manual feature fusion is time consuming and prevents the improvement of monitoring accuracy. A new tool wear prediction method based on multidomain feature fusion by attention-based depth-wise separable convolutional neural network is proposed to solve these problems. In this method, multidomain features of cutting force and vibration signals are extracted and recombined into feature tensors. The proposed hypercomplex position encoding and high-dimensional self-attention mechanism are used to calculate the new representation of input feature tensor, which emphasizes the tool wear sensitive information and suppresses large area background noise. The designed depth-wise separable convolutional neural network is used to adaptively extract high-level features that can characterise tool wear from the new representation, and the tool wear is predicted automatically. The proposed method is verified on three sets of tool run-to-failure data sets of three-flute ball nose cemented carbide tool in machining centre. Experimental results show that the prediction accuracy of the proposed method is remarkably higher than other state-of-art methods. Therefore, the proposed tool wear prediction method is beneficial to improve the prediction accuracy and provide effective guidance for decision making in processing.

Highlights

Pandiyan et al [6] combined genetic algorithm and support vector machine (SVM) for belt wear monitoring in grindingIn the cutting process, the slight wear or damage of cutting process
The proposed hypercomplex position encoding and high dimensional self-attention mechanism are used to calculate the new representation of input feature tensor, which emphasizes the tool wear sensitive information and suppresses large area background noise
The proposed depth-wise separable convolutional neural network (CNN) is used to model the nonlinear relationship between tool wear and the new representation

Summary

Introduction

Pandiyan et al [6] combined genetic algorithm and support vector machine (SVM) for belt wear monitoring in grindingIn the cutting process, the slight wear or damage of cutting process. Pandiyan et al [6] combined genetic algorithm and support vector machine (SVM) for belt wear monitoring in grinding. Genetic algorithm was used to extract a small tool reduces the quality of processing parts. The serious number of tool wear sensitive features from the set of time damage of cutting tool leads to the scrapping of parts, domain and frequency domain features. Kong et al [7] used interruption of cutting process, and machine tool damage. In an integrated radial basis function-based kernel principal the actual machining process, approximately 20% of component analysis (KPCA) to fuse the multidomain downtime is caused by tool wear [1,2]. Real-time features extracted from the original signals. To avoid corresponding confidence interval in real time.

Methods

Results

Conclusion