数据缺失下基于改进生成对抗填补网络的碳耗预测方法

doi:10.3901/JME.2023.11.264

机械工程学报 ›› 2023, Vol. 59 ›› Issue (11): 264-275.doi: 10.3901/JME.2023.11.264

扫码分享

数据缺失下基于改进生成对抗填补网络的碳耗预测方法

易茜^1,2, 柳淳², 李聪波^1,2, 赵希坤^1,2, 易树平²

1. 重庆大学机械传动国家重点实验室重庆 400044;
2. 重庆大学机械与运载工程学院重庆 400044

收稿日期:2022-07-01 修回日期:2023-01-09 出版日期:2023-06-05 发布日期:2023-07-19
作者简介:易茜,女,1986年出生,博士,副教授,硕士研究生导师。主要研究方向为低碳节能技术及应用。E-mail:yiqian@cqu.edu.cn
基金资助:
国家自然科学基金(52005062)和国家重点研发计划(2018YFB1701205)资助项目

Prediction Method of Hobbing Carbon Consumption Based on Improved Generative Adversarial Imputation Net with Missing Data

YI Qian^1,2, LIU Chun², LI Congbo^1,2, ZHAO Xikun^1,2, YI Shuping²

1. State Key Laboratory of Mechanical Transmission, Chongqing University, Chongqing 400044;
2. College of Mechanical and Vehicle Engineering, Chongqing University, Chongqing 400044

Received:2022-07-01 Revised:2023-01-09 Online:2023-06-05 Published:2023-07-19

摘要/Abstract

摘要： 针对碳耗数据缺失导致碳耗预测模型预测精度低的问题，提出一种基于改进生成对抗填补网络的碳耗预测方法。以滚齿加工为对象，揭示加工过程的碳耗特性，分析其碳耗数据缺失机制；引入正则化机制构建生成对抗填补网络(GAIN)损失函数，提出基于正则化生成对抗填补网络(RGAIN)的碳耗数据填补方法；使用随机森林(RF)算法构造碳排放预测模型，实现数据驱动的加工碳耗预测。与其他数据填补及碳耗预测方法对比，该方法能有效降低滚齿碳耗数据缺失带来的预测误差。

关键词: 缺失数据, 滚齿加工, 碳耗预测, 生成对抗网络

Abstract: Aiming at the problem of low prediction accuracy of carbon consumption prediction model due to the missing data of carbon consumption, a prediction method of carbon consumption based on improved generative adversarial imputation net is proposed. Taking gear hobbing as an example, the carbon consumption characteristics of gear hobbing process are revealed, and the missing mechanism of carbon consumption data in gear hobbing process is analyzed. The loss function of generative adversarial imputation net (GAIN) is constructed by introducing regularization mechanism, and the carbon consumption data imputation method based on regularized generative adversarial imputation net (RGAIN) is proposed. Then, the random forest (RF) algorithm is used to construct a prediction model of hobbing carbon emission, and the dynamic prediction of hobbing carbon consumption is realized. Finally, the proposed method is compared with other data imputation and carbon consumption prediction methods. The results show that the proposed method can effectively reduce the prediction error caused by the missing carbon consumption data of gear hobbing,.

Key words: missing data, gear hobbing, carbon consumption prediction, generative adversarial network

中图分类号:

TH122

易茜, 柳淳, 李聪波, 赵希坤, 易树平. 数据缺失下基于改进生成对抗填补网络的碳耗预测方法[J]. 机械工程学报, 2023, 59(11): 264-275.

YI Qian, LIU Chun, LI Congbo, ZHAO Xikun, YI Shuping. Prediction Method of Hobbing Carbon Consumption Based on Improved Generative Adversarial Imputation Net with Missing Data[J]. Journal of Mechanical Engineering, 2023, 59(11): 264-275.

参考文献

[1] 中国碳排放数据库.中国分部门核算碳排放清单1997-2019[DB/OL]. [2022-05-10]. https://www.ceads.net/user/index.php?id=913&lang=cn.w.ceads.net/user/index.php?id=913&lang=cn. China Carbon Emission Database. China accounts for carbon emissions by sector 2016-2019[DB/OL]. [2022-05-10]. https://www.ceads.net/user/index.php?id=913&lang=cn.w.ceads.net/user/index.php?id=913&lang=cn.
[2] 李聪波，付松，陈行政，等. 面向高效节能的数控滚齿加工参数多目标优化模型[J]. 计算机集成制造系统，2020，26(3):676-687. LI Congbo，FU Song，CHEN Xingzheng，et al. Multi-objective CNC gear hobbing parameters optimization model for high efficiency and energy saving[J]. Computer Integrated Manufacturing Systems，2020，26(3):676-687.
[3] 倪恒欣，阎春平，陈建霖，等. 高速干切滚齿工艺参数的多目标优化与决策方法[J]. 中国机械工程，2021，32(7):832-838. NI Hengxin，YAN Chunping，CHEN Jianlin，et al. Multi-objective optimization and decision-making method of high speed dry gear hobbing process parameters[J]. China Mechanical Engineering，2021，32(7):832-838.
[4] CHEN Xingzhen，LI Congbo，TANG Ying，et al. Integrated optimization of cutting tool and cutting parameters in face milling for minimizing energy footprint and production time[J]. Energy，2019，175:1021-1037.
[5] PRIARONE P C，ROBIGLIO M，SETTINERI L，et al. Modelling of specific energy requirements in machining as a function of tool and lubricoolant usage[J]. CIRP Annals - Manufacturing Technology，2016:25-28.
[6] ALBERTELLI P，KESHARI A，MATTA A. Energy oriented multi cutting parameter optimization in face milling[J]. Journal of Cleaner Production，2016，137:1602-1618.
[7] 易茜，柳淳，李聪波，等. 基于小样本数据驱动的滚齿工艺参数低碳优化决策方法[J]. 中国机械工程，2022，33(13):1604-1612. YI Qian，LIU Chun，LI Congbo，et al. A low carbon optimization decision method for gear hobbing process parameters driven by small sample data[J]. China Mechanical Engineering，2022，33(13):1604-1612.
[8] BHIHGE R，PARK J，LAW K H，et al. Toward a generalized energy prediction model for machine tools[J]. Journal of Manufacturing Science & Engineering，2017，139(4):041013
[9] NGUYEN T. Prediction and optimization of machining energy，surface roughness，and production rate in SKD61 milling[J]. Measurement，2019，136:525-544.
[10] XIAO Qinge，LI Congbo，TANG Ying，et al. Energy efficiency modeling for configuration-dependent machining via machine learning:A comparative study[J]. IEEE Transactions on Automation Science and Engineering，2021，18:717-730.
[11] GUO Z，WAN Y，YE H. A data imputation method for multivariate time series based on generative adversarial network[J]. Neurocomputing，2019，360.
[12] PAN Jian，LI Congbo，TANG Ying，et al. Energy consumption prediction of a CNC machining process with incomplete data[J]. IEEE/CAA Journal of Automatica Sinica，2021，8(5):987-1000.
[13] 蓝艇，朱莹，俞海珍，等. 基于缺失数据的误差生成策略及其在故障检测中的应用[J]. 控制与决策，2020，35(2):396-402. LAN Ting，ZHU Ying，YU Haizhen，et al. Missing data based method for residual generation and its application for fault detection[J]. Control and Decision，2020，35(2):396-402.
[14] AFIFI A A，ELASHOFF R M. Missing observations in multivariate statistics I:Review of the literature[J]. Journal of the American Statistical Association，1966，61(315):595-604.
[15] YOON J，JORDON J，SCHAAR M. GAIN:Missing data imputationusing generative adversarial Nets[C]// Proceedings of the 35th International Conference on Machine Learning. Sweden，2018:5689-5698.
[16] 王立平，张兆坤，邵珠峰，等. 机床制造加工数字化车间信息模型及其应用研究[J]. 机械工程学报，2019，55(9):154-165. WANG Liping，ZHANG Zhaokun，SHAO Zhufeng，et al. Research on the information model of digital machining workshop for machine tools and its applications[J]. Journal of Mechanical Engineering，2019，55(9):154-165.
[17] TSENG H Y，JIANG L，LIU C，et al. Regularizing generative adversarial networks under limited data[C]// 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)，Nashville，2021:7917-7927.
[18] XIAO Qinge，LI Congbo，TANG Ying，et al. Multi-component energy modeling and optimization for sustainable dry gear hobbing[J]. Energy，2019，187(2):115911.
[19] SCHUDELEIT T，ZUST T S，WEISS L，et al. The total energy efficiency index for machine tools[J]. Energy，2016，102:682-693.
[20] 李爱平，古志勇，朱璟，等. 基于低碳制造的多工步孔加工切削参数优化[J]. 计算机集成制造系统，2015，21(6):1515-1522. LI Aiping，GU Zhiyong，ZHU Jing，et al. Optimization of cutting parameters for multi-pass hole machining based on low carbon manufacturing[J]. Computer Integrated Manufacturing Systems，2015，21(6):1515-1522.
[21] 汪千程，苏春，文泽军. 基于协整分析的风力机多工况监测与故障诊断[J]. 中国机械工程，2022，33(13):1596-160. WANG Qiancheng，SU Chun，WEN Zejun，Multi-condition monitoring and fault diagnosis of wind turbines based on cointegration analysis[J]. China Mechanical Engineerin，2022，33(13):1596-160.
[22] 常玉清，孙雪婷，钟林生，等. 基于改进随机森林算法的工业过程运行状态评价[J]. 自动化学报，2021，47(9):2214-2225. CHANG Yuqing，SUN Xueting，ZHONG Linsheng，et al. Industrial operation performance evaluation of industrial processes based on modified random forest[J]. Acta Automatica Sinica，2021，47(9):2214-2225.

数据缺失下基于改进生成对抗填补网络的碳耗预测方法

Prediction Method of Hobbing Carbon Consumption Based on Improved Generative Adversarial Imputation Net with Missing Data

PDF

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 6

编辑推荐

Metrics

本文评价

[1]	余晓霞, 汤宝平, 王伟影, 吴宣勇, 李彪. 复杂工况条件下多头注意力双向长短时记忆网络的风电机组缺失数据修复方法研究[J]. 机械工程学报, 2023, 59(14): 1-9.
[2]	邵海东, 李伟, 刘翊, 杨斌. 时变转速下基于双阈值注意力生成对抗网络和小样本的转子-轴承系统故障诊断[J]. 机械工程学报, 2023, 59(12): 215-224.
[3]	李雄, 苏建宁, 张志鹏. 基于深度学习的产品概念草图生成设计研究[J]. 机械工程学报, 2023, 59(11): 16-30.
[4]	李可, 祁阳, 宿磊, 顾杰斐, 苏文胜. 基于改进ACGAN的钢表面缺陷视觉检测方法[J]. 机械工程学报, 2022, 58(24): 32-40.
[5]	高翱, 王帅, 韩兴臣, 张智晟. 基于GRU神经网络的WGAN短期负荷预测模型^*[J]. 电气工程学报, 2022, 17(2): 168-175.
[6]	陈帅, 赵明, 郭栋, 林京. 基于SVD-KDR算法的工业监测数据插补技术[J]. 机械工程学报, 2021, 57(2): 30-38.