Application of Distributed Convolutional Neural Network in Wear Prediction of Tool
-
摘要: 刀具磨损量预测对提高设备运行的安全性和可靠性具有重大意义。为了提高刀具磨损量预测精度，本文提出了基于分布式卷积神经网络的刀具磨损量预测方法，该方法将原始高频信号样本作为输入，在模型中分为若干个子序列，利用分布式卷积-池化层作为局部特征提取器，从子序列中自适应提取特征，并对特征数据进行批标准化处理，最后经过非线性映射，对刀具磨损量进行预测。本文提出的模型与BPNN模型相比均方误差降低了51.3%，具有更高的预测精度。Abstract: The wear prediction of tool is of great significance for improving the safety and reliability of equipment operation. In order to improve the accuracy of wear prediction of tool, a method based on distributed convolutional neural network is proposed. This method takes the original high-frequency signal sample as input and divides it into several sub-sequences in the model with distributed convolution pooling layer as local feature extractors. Features are adaptively extracted from subsequences and batch normalization is performed. Finally, the wear of tool is predicted with nonlinear mapping. Comparing with BPNN model, the present model reduces the mean square error by 51.3% and it has a higher tool wear prediction accuracy.
-
[1] 张栋梁, 莫蓉, 孙惠斌, 等.基于混沌时序分析方法与支持向量机的刀具磨损状态识别[J].计算机集成制造系统, 2015, 21(8):2138-2146 http://d.old.wanfangdata.com.cn/Periodical/jsjjczzxt201508020Zhang D L, Mo R, Sun H B, et al. Tool wear state recognition based on chaotic time series analysis and support vector machine[J]. Computer Integrated Manufacturing Systems, 2015, 21(8):2138-2146(in Chinese) http://d.old.wanfangdata.com.cn/Periodical/jsjjczzxt201508020 [2] Li X, Lin B S, Zhou J H, et al. Fuzzy neural network modelling for tool wear estimation in dry milling operation[C]//Proceedings of the Annual Conference of the Prognostics and Health Management Society. United States: Annual Conference of the Prognostics and Health Management Society, 2009 [3] 肖鹏飞, 张超勇, 罗敏, 等.基于自适应动态无偏最小二乘支持向量机的刀具磨损预测建模[J].中国机械工程, 2018, 29(7):842-849 doi: 10.3969/j.issn.1004-132X.2018.07.014Xiao P F, Zhang C Y, Luo M, et al. Modeling method for tool wear prediction based on ADNLSSVM[J]. China Mechanical Engineering, 2018, 29(7):842-849(in Chinese) doi: 10.3969/j.issn.1004-132X.2018.07.014 [4] Tobon-Mejia D A, Medjaher K, Zerhouni N. CNC machine tool's wear diagnostic and prognostic by using dynamic Bayesian networks[J]. Mechanical Systems and Signal Processing, 2012, 28:167-182 doi: 10.1016/j.ymssp.2011.10.018 [5] 林杨.基于深度学习的刀具磨损状态监测技术的研究[D].合肥: 中国科学技术大学, 2017Lin Y. Research on tool wear state monitoring technology of high speed milling based on deep learning[D]. Hefei: University of Science and Technology of China, 2017(in Chinese) [6] 张存吉, 姚锡凡, 张剑铭, 等.基于深度学习的刀具磨损监测方法[J].计算机集成制造系统, 2017, 23(10):2146-2155 http://d.old.wanfangdata.com.cn/Periodical/jsjjczzxt201710008Zhang C J, Yao X F, Zhang J M, et al. Tool wear monitoring based on deep learning[J]. Computer Integrated Manufacturing Systems, 2017, 23(10):2146-2155(in Chinese) http://d.old.wanfangdata.com.cn/Periodical/jsjjczzxt201710008 [7] 谢阳阳.基于声发射和深度学习的刀具状态识別研究[D].南京: 南京信息工程大学, 2017Xie Y Y. Research on tool state recognition based on acoustic emission and deep learning[D]. Nanjing: Nanjing University of Information Science and Technology, 2017(in Chinese) [8] Jing L Y, Wang T Y, Zhao M, et al. An adaptive multi-sensor data fusion method based on deep convolutional neural networks for fault diagnosis of planetary gearbox[J]. Sensors, 2017, 17(2):414 doi: 10.3390/s17020414 [9] Gómez-Ríos A, Tabik S, Luengo J, et al. Towards highly accurate coral texture images classification using deep convolutional neural networks and data augmentation[J]. Expert Systems with Applications, 2019, 118:315-328 doi: 10.1016/j.eswa.2018.10.010 [10] Bozkurt B, Germanakis I, Stylianou Y. A study of time-frequency features for CNN-based automatic heart sound classification for pathology detection[J]. Computers in Biology and Medicine, 2018, 100:132-143 doi: 10.1016/j.compbiomed.2018.06.026 [11] 安晶, 艾萍, 徐森, 等.一种基于一维卷积神经网络的旋转机械智能故障诊断方法[J].南京大学学报, 2019, 55(1):133-142 http://d.old.wanfangdata.com.cn/Periodical/njdxxb201901014An J, Ai P, Xu S, et al. An intelligent fault diagnosis method for rotating machinery based on one dimensional convolution neural network[J]. Journal of Nanjing University, 2019, 55(1):133-142(in Chinese) http://d.old.wanfangdata.com.cn/Periodical/njdxxb201901014 [12] Ioffe S, Szegedy C. Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift[C] // Proceedings of the 32nd International Conference on Machine Learning. France: International Machine Learning Society (IMLS), 2015: 448-456 [13] 陶耀东, 曾广圣, 李宁.基于回归树和AdaBoost方法的刀具磨损评估[J].计算机系统应用, 2017, 26(12):212-219 http://d.old.wanfangdata.com.cn/Periodical/jsjxtyy201712035Tao Y D, Zeng G S, Li N. Tool wear evaluation based on decision tree regression and AdaBoost algorithm[J]. Computer Systems & Applications, 2017, 26(12):212-219(in Chinese) http://d.old.wanfangdata.com.cn/Periodical/jsjxtyy201712035 [14] 王晓强.刀具磨损监测和剩余寿命预测方法[D].武汉: 华中科技大学, 2016Wang X Q. Tool wear monitoring and remaining useful life prognosis[D]. Wuhan: Huazhong University of Science and Technology, 2016(in Chinese) [15] Qiao H H, Wang T Y, Wang P, et al. A time-distributed spatiotemporal feature learning method for machine health monitoring with multi-sensor time series[J]. Sensors, 2018, 18(9):2932 doi: 10.3390/s18092932 -
下载:
点击查看大图
图(10) / 表(1)
计量
- 文章访问数: 704
- HTML全文浏览量: 413
- PDF下载量: 150
- 被引次数: 0
