Tool Wear Predicting Based on Multisensory Raw Signals Fusion by Reshaped Time Series Convolutional Neural Network in Manufacturing

Zhiwen Huang,Xiaoru Li,Fengqing Tian,Jingtao Lei,Jianmin Zhu

doi:10.1109/access.2019.2958330

Abstract

Tool wear monitoring is a typical multi-sensor information fusion task. The handcrafted features may be a suboptimal choice that will lower the monitoring accuracy and require significant computational costs that hinder the real-time applications. In order to solve these problems, this paper proposed a new multisensory data-driven tool wear predicting method based on reshaped time series convolutional neural network (RTSCNN). In this method, the reshaped time series layer is introduced to represent the multisensory raw signals, the alternately convolutional and pooling layers is employed to adaptively learn distinctive characteristics of tool wear directly from multisensory raw signals while the multi-layer perceptron with regression layer performs automatic tool wear prediction. In addition, three tool run-to-failure datasets measured from three-flute ball nose tungsten carbide cutter of high-speed CNC machine under milling operations are used to experimentally demonstrate the performance of the proposed RTSCNN-based multisensory data-driven tool wear predicting method. The experimental results show that the prediction error of the RTSCNN-based data-driven method is observably lower than other state-of-art methods.

Highlights

As an important part of smart manufacturing, the tool condition monitoring and prognostic techniques have been increasingly investigated to ensure high surface quality of the workpiece and increase machining efficiency [1], [2]
MULTI-SENSOR FUSION To verify its effectiveness on the multi-sensor information fusion, the proposed reshaped time series convolutional neural network (RTSCNN) model is firstly utilized for the tool wear prediction based on different single signals in this paper
In this paper, we focused on the multisensory raw signals (i.e. 3-D forces, 3-D vibrations and acoustic emission (AE)) fusion and proposed a data-driven method based on RTSCNN architecture for tool wear prediction under the machine process

Summary

Introduction

As an important part of smart manufacturing, the tool condition monitoring and prognostic techniques have been increasingly investigated to ensure high surface quality of the workpiece and increase machining efficiency [1], [2]. These techniques can be divided into model-driven and data-driven methods. Data-driven methods establish the model about the tool wear based on a large volume of historical measured data, and make decisions upon the online data collected from various monitored sensors [5], which are very suitable for industrial field application of tool wear monitoring. Thanks to the development of Industry 4.0, the massive

Methods

Results

Conclusion