基于一维深度卷积自动编码器的刀具状态监测方法

摘要
图/表
参考文献(18)
相关文章 (15)

全文: PDF (4521 KB) HTML (1 KB)
输出: BibTeX | EndNote (RIS)

摘要由于现有智能刀具磨损状态识别方法存在过于依赖样本数据预处理手段的问题，提出了一种基于一维深度卷积自动编码器（ODCAE）的刀具磨损状态识别方法，提高利用原始时域信号作为模型输入的刀具磨损状态识别精度。首先采集不同工况下主轴电机的三相电流信号，将三相电流信号融合成电流有效值并做归一化处理，以此作为模型的输入。然后，利用一维深度卷积自动编码器对输入样本进行无监督预训练，提取基于信号本身的特征信息。最后保留自动编码器的编码部分，利用样本标签进行二次有监督微调，实现对刀具不同磨损状态的识别。实验结果表明，ODCAE方法对刀具不同的磨损状态平均识别率可达99%，卡帕系数0.9840，能够自适应地提取特征并高效率的实现刀具磨损状态识别。

	服务

	把本文推荐给朋友
	加入我的书架
	加入引用管理器
	E-mail Alert
	RSS
	作者相关文章
	杨国葳
	李宏坤
	张明亮
	黄刚劲

关键词 ：刀具磨损, 主轴电流, 深度学习, 卷积自动编码器

Abstract：Due to the problem that the existing intelligent tool wear state recognition methods rely too much on sample data preprocessing, a tool wear state recognition method based on One Dimensional Deep Convolution Autoencoder (ODCAE) was proposed to improve the accuracy of tool wear state recognition which used the original time domain signal as model input. Firstly, the three-phase current signal of the spindle motor under different working conditions was collected, and the three-phase current signal was fused into the current effective value and normalized, which was used as the input of the model. Then, the unsupervised pre-training of the input samples was carried out by using the one-dimensional deep convolution encoder to extract the characteristic information based on the signal itself. Finally, the coding part of the automatic encoder was retained, and the sample label was used for secondary supervised fine-tuning to realize the identification of different wear states of the cutter. The experimental results showed that the ODCAE method can achieve an average recognition rate of 99% and a kappa coefficient of 0.9840 for different tool wear states.

Key words： tool wear spindle current deep learning convolution autoencoder

收稿日期: 2020-05-18 出版日期: 2021-11-15

引用本文:

杨国葳，李宏坤，张明亮，黄刚劲. 基于一维深度卷积自动编码器的刀具状态监测方法[J]. 振动与冲击, 2021, 40(21): 223-233.
YANG Guowei, LI Hongkun, ZHANG Mingliang, HUANG Gangjin. Tool condition monitoring method based on ODCAE. JOURNAL OF VIBRATION AND SHOCK, 2021, 40(21): 223-233.

链接本文:

http://jvs.sjtu.edu.cn/CN/ 或 http://jvs.sjtu.edu.cn/CN/Y2021/V40/I21/223

[1] 郭景超，李安海. 刀具磨损状态监测技术研究进展[J]. 工具技术，2019,53(05):3-13.
GUO Jingchao, LI Anhai, Advances in Monitoring Technology of Tool Wear Condition[J]. Tool Engineering. 2019,53(05):3-13.
[2] REHORN A G,JIANG J,ORBAN P E. State-of-the-art methods and results in tool condition monitoring: a review[J]. The International Journal of Advanced Manufacturing Technology.2005,26(7)：693-710.
[3] 赵帅，黄奕翔，王浩任，等. 基于随机森林与主成分分析的刀具磨损评估[J]. 机械工程学报，2017，53(21)：181-189.
ZHAO Shuai,HUANG Yixiang,WANG Haoren,et al. Random Forest and Principle Components Analysis Based on Health Assessment Methodology for Tool Wear[J]. Journal of Mechanical Engineering. 2017，53（21）：181-189.
[4] 程灿，李建勇，徐文胜，等. 基于支持向量机与粒子滤波的刀具磨损状态识别[J]. 振动与冲击， 2018,37(17):48-55.
CHENG Can, LI Jianyong, XU Wensheng,et al.Tools’ wear state recognition based on support vector machine and particle filtering[J]. Journal of Vibration and Shock. 2018,37(17): 48-55.
[5] 吕震宇. 刀具磨损特征参数提取与状态识别方法[J]. 组合机床与自动化加工技术. 2019(07): 92-96.
LV Zhenyu. Cutting Tool Wear Characteristic Parameters Extraction and Wear State Recognition[J].Modular Machine Tool & Automatic Manufacturing Technique. 2019(07): 92-96.
[6] ZHAO R, YAN R, CHEN Z, et al. Deep learning and its applications to machine health monitoring[J]. Mechanical Systems and Signal Processing,2019,115: 213-237.
[7] 李宏坤，郝佰田，代月帮，等. 基于压缩感知和加噪堆栈稀疏自编码器的铣刀磨损程度识别方法研究[J]. 机械工程学报. 2019,55(14):1-10.
LI Hongkun,HAO Baitian,DAI Yuebang,et.al. Wear Status Recognition for Milling Cutter Based on Compressed Sensing and Noise Stacking Sparse Autoencoder[J]. Journal of Mechanical Engineering. 2019,55(14):1-10.
[8] 王丽华，杨家巍,张永宏，等. 基于堆叠降噪自编码的刀具磨损状态识别[J]. 中国机械工程. 2018, 29(17): 2038-2045.
WANG Lihua,YANG Jiawei,ZHANG Yonghong,et.al. Tool Wear Condition Recognition Based on SDAE[J]. China Mechanical Engineering, 2018, 29(17): 2038-2045.
[9] HUANG Z, ZHU J, LEI J, et al. Tool wear predicting based on multi-domain feature fusion by deep convolutional neural network in milling operations[J]. Journal of Intelligent Manufacturing. 2020, 31(4): 953-966.
[10] MARTINEZ-ARELLANO G, TERRAZAS G, RATCHEV S. Tool wear classification using time series imaging and deep learning[J]. The International Journal of Advanced Manufacturing Technology. 2019, 104(9-12): 3647-3662.
[11] ZHENG H , LIN J . A Deep Learning Approach for High Speed Machining Tool Wear Monitoring[C]// International Conference on Robotics & Automation Sciences. 2019.
[12] WANG X, JIAO J, YIN J, et al. Underwater sonar image classification using adaptive weights convolutional neural network[J]. Applied Acoustics. 2019, 146: 145-154.
[13] HINTON G E, SALAKHUTDINOV R R. Reducing the Dimensionality of Data with Neural Networks[J]. Science. 2006, 313(5786): 504-507.
[14] 王万良，杨小涵，赵燕伟，等. 采用卷积自编码器网络的图像增强算法[J]. 浙江大学学报(工学版). 2019, 53(09): 1728-1740.
WANG Wanliang, YANG Xiaohan, ZHAO Yanwei, et.al. Image enhancement algorithm with convolutional auto-encoder network[J]. Journal of Zhejiang University (Engineering Science).2019, 53(09): 1728-1740.
[15] 纪泽宇，张兴军，付哲，等. 分布式深度学习框架下基于性能感知的DBS-SGD算法[J]. 计算机研究与发展. 2019，56(11):2396-2409.
JI Zeyu, ZHANG Xingjun, FU Zhe, et al. Performance-Awareness Based Dynamic Batch Size SGD for Distributed Deep Learning Framework[J]. Journal of Computer Research and Development. 2019，56(11):2396-2409.
[16] AGRAWAL A, MITTAL N. Using CNN for facial expression recognition: a study of the effects of kernel size and number of filters on accuracy[J]. The Visual Computer. 2020, 36(2): 405-412.
[17] HE K , SUN J . Convolutional Neural Networks at Constrained Time Cost[C]// 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR). IEEE, 2014.
[18] INCE T, KIRANYAZ S, EREN L, et al. Real-Time Motor Fault Detection by 1-D Convolutional Neural Networks[J]. IEEE Transactions on Industrial Electronics. 2016, 63(11): 7067-7075.