Estimation of Tool Wear and Surface Roughness Development Using Deep Learning and Sensors Fusion.

Pao-Ming Huang,Ching-Hung Lee

doi:10.3390/s21165338

Abstract

This paper proposes an estimation approach for tool wear and surface roughness using deep learning and sensor fusion. The one-dimensional convolutional neural network (1D-CNN) is utilized as the estimation model with X- and Y-coordinate vibration signals and sound signal fusion using sensor influence analysis. First, machining experiments with computer numerical control (CNC) parameters are designed using a uniform experimental design (UED) method to guarantee the variety of collected data. The vibration, sound, and spindle current signals are collected and labeled according to the machining parameters. To speed up the degree of tool wear, an accelerated experiment is designed, and the corresponding tool wear and surface roughness are measured. An influential sensor selection analysis is proposed to preserve the estimation accuracy and to minimize the number of sensors. After sensor selection analysis, the sensor signals with better estimation capability are selected and combined using the sensor fusion method. The proposed estimation system combined with sensor selection analysis performs well in terms of accuracy and computational effort. Finally, the proposed approach is applied for on-line monitoring of tool wear with an alarm, which demonstrates the effectiveness of our approach.

Highlights

IntroductionTool wear and surface roughness play important roles during the machining process
Accepted: 5 August 2021In the manufacturing industry, tool wear and surface roughness play important roles during the machining process
The 1D-convolutional neural networks (CNNs) combined with sensor fusion based on the relevant sensor selection analysis is introduced, and the experimental results are presented

Summary

Introduction

Tool wear and surface roughness play important roles during the machining process. Surface roughness and tool wear are performance indices for customers in finished products that affect the machining cost. The chosen model and data directly affect estimation accuracy. Most of these studies utilized vibration signals and focused on machine learning model selection; variation of the machining conditions was less common. A variety of data corresponding to the machining parameters should be considered in the data collection process. This results in the effectiveness and performance of the estimation model. In this study, machining experiments with CNC parameters are designed using a uniform experimental design method (UED) to guarantee a variety of collected data

Methods

Results

Conclusion