基于时空全卷积循环神经网络的零件表面形貌预测

doi:10.3901/JME.2021.20.292

机械工程学报 ›› 2021, Vol. 57 ›› Issue (20): 292-304.doi: 10.3901/JME.2021.20.292

• 交叉与前沿 • 上一篇

扫码分享

基于时空全卷积循环神经网络的零件表面形貌预测

邵益平, 谭健, 鲁建厦

浙江工业大学机械工程学院杭州 310023

收稿日期:2021-03-08 修回日期:2021-09-20 出版日期:2021-10-20 发布日期:2021-12-15
通讯作者: 鲁建厦(通信作者),男,1963年出生,硕士,教授,博士研究生导师。主要研究方向为智能物流装备与技术、智能制造与质量控制、精益生产。E-mail:ljs@zjut.edu.cn
作者简介:邵益平,男,1991年出生,博士,讲师。主要研究方向为精密制造与质量控制。E-mail:syp123gh@zjut.edu.cn
基金资助:
浙江省重点研发计划（2018C01003）和浙江省博士后科研择优（ZJ2021119）资助项目。

A Spatio-temporal Fully Convolutional Recurrent Neural Network Based Surface Topography Prediction

SHAO Yiping, TAN Jian, LU Jiansha

College of Mechanical Engineering, Zhejiang University of Technology, Hangzhou 310023

Received:2021-03-08 Revised:2021-09-20 Online:2021-10-20 Published:2021-12-15

摘要/Abstract

摘要： 零件表面形貌预测对于降低产品质量波动和加工成本、减少零件废品率有重要意义。基于高清晰测量数据，提出一种时空全卷积循环神经网络非平稳时空序列预测模型，实现零件加工表面三维形貌的预测。通过计算全局莫兰指数和时间自相关函数进行时空相关性分析，为模型构建准确的输入，并克服传统预测方法未充分利用数据全局特征和局部特征的缺点以及模型输入的随意性。实例研究的结果表明，提出的方法具有更优的综合预测效果，其预测精度优于传统方法12%~18%，预测时间是传统方法的1/5。

Abstract: Surface topography prediction is of great significance to reduce the fluctuation of product quality and processing cost as well as the scrap rate of parts. Based on the high definition metrology (HDM) measured data, a spatio-temporal series prediction model called spatio-temporal fully convolutional recurrent neural network (STFCRNN) is proposed, which achieves the 3D surface topography prediction of machining surface. The time autocorrelation function and global Moran's I are calculated to analyze the spatiotemporal correlation of the surface data, which is used to conduct an accurate input of the model, thereby overcoming the shortcomings of traditional prediction methods that do not make full use of the global and local features of the data and the randomness of model input. Moreover, the result of case study shows that the proposed method has a better comprehensive prediction performance, and its prediction accuracy is 12%-18% better than that of traditional methods and the prediction time is 1/5 of traditional methods.

Key words: surface topography prediction, spatio-temporal correlation analysis, neural networks, high definition metrology, nonstationary spatio-temporal series

中图分类号:

TH161

邵益平, 谭健, 鲁建厦. 基于时空全卷积循环神经网络的零件表面形貌预测[J]. 机械工程学报, 2021, 57(20): 292-304.

SHAO Yiping, TAN Jian, LU Jiansha. A Spatio-temporal Fully Convolutional Recurrent Neural Network Based Surface Topography Prediction[J]. Journal of Mechanical Engineering, 2021, 57(20): 292-304.

参考文献

[1] DENKENA B,BÖß V,NESPOR D,et al. Prediction of the 3D surface topography after ball end milling and its influence on aerodynamics[J]. Procedia CIRP,2015,31:221-227.
[2] OMAR O,EL-WARDANY T,NG E,et al. An improved cutting force and surface topography prediction model in end milling[J]. International Journal of Machine Tools & Manufacture,2007,47(7-8):1263-1275.
[3] BENARDOS P G,VOSNIAKOS G C. Predicting surface roughness in machining:A review[J]. International Journal of Machine Tools and Manufacture,2003,43(8):833-844.
[4] 董永亨,李淑娟,李言,等. 球头铣刀余摆线加工表面形貌的建模与仿真研究[J]. 机械工程学报,2018,54(19):212-223. DONG Yongheng,LI Shujuan,LI Yan,et al. Research on modeling and simulation of surface topography obtained by trochoidal milling mode with ball end milling cutter[J]. Journal of Mechanical Engineering,2018,54(19):212-223.
[5] 王艳,李德蔺,刘建国,等. 基于动态轮廓采样法的轴向超声振动辅助磨削工件表面形貌预测与试验验证[J].机械工程学报,2018,54(21):221-230. WANG Yan,LI Delin,LIU Jianguo,et al. Prediction and experimental verification of workpiece surface topology in axial ultrasonic vibration assisted grinding based on dynamic profile sampling method[J]. Journal of Mechanical Engineering,2018,54(21):221-230.
[6] LU Xiaohong,HU Xiaochen,JIA Zhenyuan,et al. Model for the prediction of 3D surface topography and surface roughness in micro-milling Inconel 718[J]. The International Journal of Advanced Manufacturing Technology,2018,94(5):2043-2056.
[7] TORTA M,ALBERTELLI P,MONNO M. Surface morphology prediction model for milling operations[J]. The International Journal of Advanced Manufacturing Technology,2020,106(1):3189-3201.
[8] WANG Wei,LI Qingzhao,JIANG Yunfeng. A novel 3D surface topography prediction algorithm for complex ruled surface milling and partition process optimization[J]. The International Journal of Advanced Manufacturing Technology,2020,107(9):3817-3831.
[9] BUSTILLO A,GRZENDA M,MACUKOW B. Interpreting tree-based prediction models and their data in machining processes[J]. Integrated Computer-Aided Engineering,2016,23(4):349-367.
[10] COSTES J P. A predictive surface profile model for turning based on spectral analysis[J]. Journal of Materials Processing Technology,2013,213(1):94-100.
[11] DUAN Chunzheng,HAO Qinglong. Surface roughness prediction of end milling process based on IPSO-LSSVM[J]. Journal of Advanced Mechanical Design,Systems,and Manufacturing,2014,8(3):1-12.
[12] MANDAL N,DOLOI B,MONDAL B. Surface roughness prediction model using zirconia toughened alumina (ZTA) turning inserts:Taguchi method and regression analysis[J]. Journal of The Institution of Engineers (India):Series C,2016,97(1):77-84.
[13] MAUDES J,BUSTILLO A,GUERRA A J,et al. Random forest ensemble prediction of stent dimensions in microfabrication processes[J]. The International Journal of Advanced Manufacturing Technology,2017,91(1):879-893.
[14] PIMENOV D Y,BUSTILLO A,MIKOLAJCZYK T. Artificial intelligence for automatic prediction of required surface roughness by monitoring wear on face mill teeth[J]. Journal of Intelligent Manufacturing,2018,29(5):1045-1061.
[15] TABERNIK D,ELA S,SKVAR J,et al. Segmentation-based deep-learning approach for surface-defect detection[J]. Journal of Intelligent Manufacturing,2019,31(3):759-776.
[16] 胡茑庆,陈徽鹏,程哲,等. 基于经验模态分解和深度卷积神经网络的行星齿轮箱故障诊断方法[J]. 机械工程学报,2019,55(7):9-18. HU Niaoqing,CHEN Huipeng,CHENG Zhe,et al. Fault diagnosis for planetary gearbox based on EMD and deep convolutional neural networks[J]. Journal of Mechanical Engineering,2019,55(7):9-18.
[17] 雷亚国,贾峰,孔德同,等. 大数据下机械智能故障诊断的机遇与挑战[J]. 机械工程学报,2018,54(5):94-104. LEI Yaguo,JIA Feng,KONG Detong,et al. Opportunities and challenges of machinery intelligent fault diagnosis in big data era[J]. Journal of Mechanical Engineering,2018,54(5):94-104.
[18] WANG Meng,XI Lifeng,DU Shichang. 3D surface form error evaluation using high definition metrology[J]. Precision Engineering,2014,38(1):230-236.
[19] HUANG Zhenhua,SHIH A J,NI Jun. Laser interferometry hologram registration for three- dimensional precision measurements[J]. Journal of Manufacturing Science and Engineering,2006,128(4):1006-1013.
[20] MARTIN R L,OEPPEN J E. The identification of regional forecasting models using space:Time correlation functions[J]. Transactions of the Institute of British Geographers,1975,66:95-118.
[21] HOCHREITER S,SCHMIDHUBER J. Long short-term memory[J]. Neural Computation,1997,9(8):1735-1780.
[22] SHI Xingjian,CHEN Zhourong,WANG Hao,et al. Convolutional LSTM network:A machine learning approach for precipitation nowcasting[C]//Advances in Neural Information Processing Systems. December 7-12,2015,New York:Curran Associates,2015:802-810.
[23] SHELHAMER E,LONG J,DARRELL T. Fully convolutional networks for semantic segmentation[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence,2017,39(4):640-651.
[24] FAYYAZ M,SAFFAR M H,SABOKROU M,et al. STFCN:Spatio-temporal fully convolutional neural network for semantic segmentation of street scenes[C]//Asian Conference on Computer Vision. November 20-24,2016,Cham:Springer,2016:493-509.

基于时空全卷积循环神经网络的零件表面形貌预测

A Spatio-temporal Fully Convolutional Recurrent Neural Network Based Surface Topography Prediction

PDF

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 15

编辑推荐

Metrics

本文评价

[1]	郑杰, 权伟, 刘洋, 卢学民, 刘晓红, 岳雅楠, 周腾, 蔡振兵. Cr/Zr涂层环向压缩表面裂纹识别研究[J]. 机械工程学报, 2024, 60(8): 1-10.
[2]	刘占广, 张云, 刘晴雨. 基于差分融合长短期记忆神经网络数控机床热误差建模[J]. 机械工程学报, 2024, 60(7): 249-257.
[3]	狄子钧, 袁东风, 李东阳, 梁道君, 周晓天, 信苗苗, 曹凤, 雷腾飞. 基于多尺度-高效通道注意力网络的刀具故障诊断方法[J]. 机械工程学报, 2024, 60(6): 82-90.
[4]	王俊玖, 刘金玉, 侯秀娟, 齐振国, 李志敏, 刘涛. 列车车体柔性装配精度预测的力学-数据混合建模方法[J]. 机械工程学报, 2024, 60(6): 177-186.
[5]	李春凯, 王嘉昕, 石玗, 代悦. GTAW熔池激光条纹动态行为与熔透预测方法研究[J]. 机械工程学报, 2024, 60(6): 236-244.
[6]	周宁, 姚建勇, 邓文翔. 基于神经网络的比例伺服阀阀芯液动力补偿鲁棒智能控制[J]. 机械工程学报, 2024, 60(4): 126-133.
[7]	王丹丹, 黄伟迪, 张军辉, 赵守军, 于斌, 刘施镐, 吕飞, 苏琦, 徐兵. 基于边缘计算的轴向柱塞泵磨损状态辨识方法研究[J]. 机械工程学报, 2024, 60(4): 189-199.
[8]	张昊, 魏超, 胡纪滨, 陈泳丹. 基于转向模式切换的三轴独立转向车辆路径跟踪控制研究[J]. 机械工程学报, 2024, 60(2): 243-251.
[9]	段书用, 杨建华, 韩旭, 刘桂荣. 高维数据自适应降维方法[J]. 机械工程学报, 2024, 60(17): 283-296.
[10]	刘建琴, 胡桂菘, 乔金丽, 郭晓. 基于双路神经网络的TBM实时性能预测研究[J]. 机械工程学报, 2024, 60(16): 43-53.
[11]	胡伟飞, 廖家乐, 郭云飞, 鄢继铨, 李光, 岳海峰, 谭建荣. 基于物理信息神经网络的时变可靠性分析方法[J]. 机械工程学报, 2024, 60(13): 141-153.
[12]	张德权, 李星奥, 张宁, 宁国松, 韩旭. 工业机器人全域误差场精细化建模方法及其误差补偿策略[J]. 机械工程学报, 2024, 60(13): 316-329.
[13]	王俊, 杨轶青, 刘金朝, 沈长青, 黄伟国, 朱忠奎. 小波核编码的脉冲卷积神经网络在可解释性智能诊断中的应用研究[J]. 机械工程学报, 2024, 60(12): 41-50.
[14]	袁静, 任港星, 蒋会明, 赵倩, 魏臣隽, 朱骏. 基于多元提升核神经网络的机械故障诊断方法及其特征提取可解释性研究[J]. 机械工程学报, 2024, 60(12): 51-64.
[15]	陈钱, 陈康康, 董兴建, 皇甫一樊, 彭志科, 孟光. 一种面向机械设备故障诊断的可解释卷积神经网络[J]. 机械工程学报, 2024, 60(12): 65-76.