数据与模型混合驱动的箱体零件加工能耗预测

doi:10.3901/JME.2023.12.097

机械工程学报 ›› 2023, Vol. 59 ›› Issue (12): 97-108.doi: 10.3901/JME.2023.12.097

• 特邀专栏：制造大数据分析与决策 • 上一篇下一篇

扫码分享

数据与模型混合驱动的箱体零件加工能耗预测

张华^1,2, 李曙光^2,3, 鄢威^3,4, 江志刚^1,5, 朱硕^1,5, 马峰^1,3

1. 武汉科技大学冶金装备及控制教育部重点实验室武汉 430081;
2. 武汉科技大学绿色制造工程研究院武汉 430081;
3. 武汉科技大学机械传动与制造工程湖北省重点实验室武汉 430081;
4. 武汉科技大学汽车与交通工程学院武汉 430081;
5. 武汉科技大学精密制造研究院武汉 430081

收稿日期:2022-06-05 修回日期:2023-02-26 出版日期:2023-06-20 发布日期:2023-08-15
通讯作者: 鄢威(通信作者),男,1981年出生,博士,副教授。主要研究方向为绿色制造与再制造、智慧物流。E-mail:yanwei81@wust.edu.cn
作者简介:张华,女,1964年出生,博士,教授。主要研究方向为绿色制造、制造系统工程、制造业信息化。E-mail:zhanghua403@163.com;李曙光,男,1998年出生。主要研究方向为绿色制造。E-mail:lsg1079563851@163.com;江志刚,男,1978年出生,博士,教授。主要研究方向为绿色制造、再制造。E-mail:jiangzhigang@wust.edu.cn;朱硕,男,1989年出生,博士,副教授。主要研究方向为绿色制造、再制造、制造业信息化。E-mail:zhushuo@wust.edu.cn;马峰,男,1989年出生,博士研究生。主要研究方向为绿色制造、制造系统能效。E-mail:mf902@wust.edu.cn
基金资助:
国家自然科学基金(51975432，51775392)和武汉科技大学机械传动与制造工程湖北省重点实验室开放基金(MTMEOF2019B06)资助项目。

A Data and Model Hybrid Driven Method for Machining Energy Consumption Prediction of Boxy Parts

ZHANG Hua^1,2, LI Shuguang^2,3, YAN Wei^3,4, JIANG Zhigang^1,5, ZHU Shuo^1,5, MA Feng^1,3

1. Key Laboratory of Metallurgical Equipment and Control Technology, Ministry of Education, Wuhan University of Science and Technology, Wuhan 430081;
2. Academy of Green Manufacturing Engineering, Wuhan University of Science and Technology, Wuhan 430081;
3. Hubei Key Laboratory of Mechanical Transmission and Manufacturing Engineering, Wuhan University of Science and Technology, Wuhan 430081;
4. School of Automotive and Traffic Engineering, Wuhan University of Science and Technology, Wuhan 430081;
5. Precision Manufacturing Institute, Wuhan University of Science and Technology, Wuhan 430081

Received:2022-06-05 Revised:2023-02-26 Online:2023-06-20 Published:2023-08-15

摘要/Abstract

摘要： 箱体零件是机械产品与部件的载体和安装基础件，其制造过程耗费大量的资源和能源。加工能耗预测作为能效评估与优化的前置技术，具有积极的意义。然而，由于箱体零件往往具有复杂的加工特征，且特征间耦合关系复杂，导致现有基于加工特征的方法难以准确预测其加工能耗。基于此，提出一种数据与模型混合驱动的箱体零件加工能耗预测方法。首先，基于箱体零件结构组成，对其加工特征及其间耦合关系、以及加工能耗特性进行分析；其次，针对箱体零件加工特征的相交与非相交关系，分别构建数据驱动的非相交特征加工能耗预测模型与模型驱动的相交特征加工能耗预测模型，进而实现箱体零件加工能耗的准确预测；最后，以某箱体零件加工为例对所提方法的有效性进行验证，并通过与纯数据驱动和纯模型驱动能耗预测方法的横向对比，说明所提方法的优越性。

关键词: 箱体零件, 能耗预测, 数据与模型混合驱动, 特征, 特征耦合

Abstract: Boxy parts are the carrier and installation base of mechanical products and components, and their manufacturing process consumes a lot of resources and energy. As a leading technology for energy efficiency assessment and optimization, it is of great significance to predict the energy consumption in machining process. However, due to the various features and their complicated relationship of boxy parts, it is difficult to predict the machining energy consumption accurately. In order to fill this gap, a data and model hybrid driven method for machining energy consumption prediction of boxy parts is proposed. Firstly, the structure of boxy parts is analyzed, on this basis, the machining energy consumption characteristics of machining features and their coupling relationship are analyzed. Then, according to the intersecting and non-intersecting relationship of boxy parts, in order to realize the machining energy consumption prediction of boxy parts, a data-driven energy consumption prediction model for non-intersecting feature and a model-driven energy consumption prediction model for intersecting feature are established respectively. Finally, the validity of the proposed model and method are verified by an example of machining a boxy part, at the same time, compared with the energy consumption prediction method of pure data-driven and pure model-driven, the superiority of the proposed method is illustrated.

Key words: boxy part, energy consumption prediction, data and model hybrid driven, features, coupling feature

中图分类号:

TG501

张华, 李曙光, 鄢威, 江志刚, 朱硕, 马峰. 数据与模型混合驱动的箱体零件加工能耗预测[J]. 机械工程学报, 2023, 59(12): 97-108.

ZHANG Hua, LI Shuguang, YAN Wei, JIANG Zhigang, ZHU Shuo, MA Feng. A Data and Model Hybrid Driven Method for Machining Energy Consumption Prediction of Boxy Parts[J]. Journal of Mechanical Engineering, 2023, 59(12): 97-108.

参考文献

[1] 黄学荣. 箱体零件形位公差设计及加工检测工艺分析[J]. 煤矿机械,2017,38(3):72-74. HUANG Xuerong. Box part tolerances of form design and process analysis of detection technology[J]. Coal Mine Machinery,2017,38(3):72-74.
[2] 田崇言. 基于Pro/Toolkit的智能箱体零件数控工艺设计系统研究[D]. 青岛:山东科技大学,2016. TIAN Chongyan. Research on NC process design system based on Pro/Toolkit of smart box parts[D]. Qingdao:Shandong University of Science and Technology,2016.
[3] 王德伦,申会鹏,孙元,等. 复杂零件结构设计的概念单元方法[J]. 机械工程学报,2016,52(7):152-163. WANG Delun,SHEN Huipeng,SUN Yuan,et al. A novel approach for conceptual structural design of complex machine elements[J]. Journal of Mechanical Engineering,2016,52(7):152-163.
[4] BHINGE R,PARK J,LAW K,et al. Toward a generalized energy prediction model for machine tools[J]. Journal of Manufacturing Science and Engineering:Transactions of the ASME,2017,139(4):041013.
[5] 徐兴硕,李方义,孔维森,等. 基于Vericut的机床能耗建模与仿真[J]. 中国机械工程,2018,29(21):2533-2538. XU Xingshuo,LI Fangyi,KONG Weisen,et al. Energy consumptions modeling and simulation of machine tools based on vericut[J]. China Mechanical Engineering,2018,29(21):2533-2538.
[6] 周志雄,李伟,宋铁军,等. 微细切削加工用微主轴的性能要求及其研究现状[J]. 机械工程学报,2011,47(19):149-157. ZHOU Zhixiong,LI Wei,SONG Tiejun,et al. Performance requirements and research state of micro-spindles for micro-cutting[J]. Journal of Mechanical Engineering,2011,47(19):149-157.
[7] 刘培基,刘飞,王旭,等. 绿色制造的理论与技术体系及其新框架[J]. 机械工程学报,2021,57(19):165-179. LIU Peiji,LIU Fei,WANG Xu,et al. The theory and technology system of green manufacturing and their new frameworks[J]. Journal of Mechanical Engineering,2021,57(19):165-179.
[8] 王蕾,郭钰瑶,张泽琳,等. 再制造服务的广义内涵、研究现状与发展趋势[J]. 机械工程学报,2021,57(7):138-153. WANG Lei,GUO Yuyao,ZHANG Zelin,et al. Extensive concept,state-of-the art developing trends of remanufacturing service[J]. Journal of Mechanical Engineering,2021,57(7):138-153.
[9] 刘雪梅,周易,黄剑锋,等. 基于制造资源的复杂箱体零件加工特征识别方法[J]. 计算机集成制造系统,2015,21(12):3166-3173. LIU Xuemei,ZHOU Yi,HUANG Jianfeng,et al. Machining feature recognition method for complicated boxy parts based oil manufacturing resources[J]. Computer Integrated Manufacturing Systems,2015,21(12):3166-3173.
[10] 李爱平,鲁力,王世海,等. 复杂箱体零件柔性机加工生产线平衡优化[J]. 同济大学学报,2015,43(4):625-632. LI Aiping,LU Li,WANG Shihai,et al. Optimization of flexible machining line balancing for complex prismatic parts[J]. Journal of Tongji University,2015,43(4):625-632.
[11] HU Luoke,TANG Renzhong,JIA Shun,et al. Estimating machining-related energy consumption of parts at the design phase based on feature technology[J]. International Journal of Production Research,2015,53(23-24):7016-7033.
[12] 张雷,赵希坤,蒋诗新,等. 低碳低成本约束下箱体零件加工路线优化方法[J]. 中国机械工程,2018,29(23):2836-2844. ZHANG Lei,ZHAO Xikun,JIANG Shixin,et al. Optimization method of process routes for housing parts under low-carbon and low-cost constraints[J]. China Mechanical Engineering,2018,29(23):2836-2844.
[13] SRINIVASAN M,SHENG P. Feature-based process planning for environmentally conscious machining-part 1:Microplanning[J]. Robotics and Computer-Integrated Manufacturing,1999,15(3):257-270.
[14] SRINIVASAN M,SHENG P. Feature-based process planning for environmentally conscious machining-part 1:Microplanning[J]. Robotics and Computer-Integrated Manufacturing,1999,15(3):257-270.
[15] HU Luoke,PENG Chen,EVANS S,et al. Minimising the machining energy consumption of a machine tool by sequencing the features of a part[J]. Energy,2017,121:292-305.
[16] LI Wen,KARA S. An empirical model for predicting energy consumption of manufacturing processes:a case of turning process[J]. Proceedings of the Institution of Mechanical Engineers,Part B:Journal of Engineering Manufacture,2011,225(9):1636-1646.
[17] KARA S,LI Wen. Unit process energy consumption models for material removal processes[J]. CIRP Annals,2011,60(1):37-40.
[18] JIA Shun,TANG Renzhong,LÜ Jingxiang,et al. Energy modeling for variable material removal rate machining process:an end face turning case[J]. The International Journal of Advanced Manufacturing Technology,2016,85(9/12):2805-2818.
[19] WANG Lihui,MENG Yue,JI Wei,et al. Cutting energy consumption modelling for prismatic machining features[J]. The International Journal of Advanced Manufacturing Technology,2019,103(5/8):1657-1667.
[20] ZHAO Guoyong,LI Chunxiao,TIAN Yingzhou,et al. Prediction model for net cutting specific energy in cnc turning[J]. Transactions of Nanjing University of Aeronautics and Astronautics,2020,37(3):385-392.
[21] 李涛,孔露露,张洪潮,等. 典型切削机床能耗模型的研究现状及发展趋势[J]. 机械工程学报,2014,50(7):102-111. LI Tao. KONG Lulu,ZHANG Hongchao,et al. Recent research and development of typical cutting machine tool's energy consumption model[J]. Journal of Mechanical Engineering,2014,50(7):102-111.
[22] 李聪波,尹誉先,肖溱鸽,等. 数据驱动下基于元动作的数控车削能耗预测方法[J]. 中国机械工程,2020,31(21):2601-2611. LI Congbo,YIN Yuxian,XIAO Qinge,et al. Data-driven energy consumption prediction method of cnc turning based on meta-action[J]. China Mechanical Engineering,2020,31(21):2601-2611.
[23] 吕景祥,唐任仲,郑军. 数据驱动的车削和钻削加工能耗预测[J]. 计算机集成制造系统,2020,26(8):2073-2082. LÜ Jingxiang,TANG Renzhong,ZHENG Jun. Data-driven methodology for energy consumption prediction of turning and drilling processes[J]. Computer Integrated Manufacturing Systems,26(8):2073-2082.
[24] LIU Ziye,GUO Yuebin. A hybrid approach to integrate machine learning and process mechanics for the prediction of specific cutting energy[J]. CIRP Annals,2018,67(1):57-60.
[25] HE Yan,WU Pengcheng,LI Yufeng,et al. A generic energy prediction model of machine tools using deep learning algorithms[J]. Applied Energy,2020,275(1):115402
[26] LÜ Lishu,DENG Zhaohui,YAN Can,et al. Modelling and analysis for processing energy consumption of mechanism and data integrated machine tool[J]. International Journal of Production Research,2020,58(23/24):7078-7093.
[27] 张英杰,许艾. 基于特征的箱体类零件数控编程技术[J].西安交通大学学报,2008,42(5):578-582. ZHANG Yingjie,XU Ai. Efficient feature-based approach to numerical control programming for prismatic parts[J]. Journal of Xi'an Jiaotong University,2008,42(5):578-582.
[28] 段现银,余胜,彭芳瑜,等. 基于特征矩阵的大型舱体类构件毛坯模型复杂特征分层识别方法[J]. 机械工程学报,2021,57(5):166-176. DUAN Xianyin,YU Sheng,PENG Fangyu,et al. Feature matrix based complex feature hierarchical recognition for blank model of large cabin component[J]. Journal of Mechanical Engineering,2021,57(5):166-176.
[29] 徐立云,史楠,段建国,等. 基于特征加工元的复杂箱体类零件工艺路线优化[J]. 中国机械工程,2013,24(2):202-208. XU Liyun,SHI Nan,DUAN Jianguo,et al. Process route optimization of complex housing-type parts based on feature machining element[J]. China Mechanical Engineering,2013,24(2):202-208.
[30] 刘舒,姜琦刚,马玥,等. 基于多目标遗传随机森林特征选择的面向对象湿地分类[J]. 农业机械学报,2017,48(1):119-127. LIU Shu,JIANG Qigang,MA Yue,et al. Object-oriented wetland classification based on hybrid feature selection method combining with relief f,multi objective genetic algorithm and random forest[J],Journal of Agricultural Machinery,2017,48(1):119-127.
[31] 王干军,李锦舒,吴毅江,等. 基于随机森林的高压电缆局部放电特征寻优[J]. 电网技术,2019,43(4):1329-1335. WANG Ganjun,LI Jinshu,WU Yijiang,et al. Random forest based feature selection for partial discharge recognition of HV cables[J]. Power System Technology,2019,43(4):1329-1335.
[32] 赵帅,黄亦翔,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.
[33] 刘锡炀,卞永明,陈启凡,等. 基于图像识别的液压同步提升系统漏油在线检测[J]. 中国工程机械学报,2022,20(3):257-262. LIU Xiyang,BIAN Yongming,CHEN Qifan,et al. Online detection of oil leakage in hydraulic synchronous lifting system based on image recognition[J]. Chinese Journal of Construction Machinery. 2022,20(3):257-262.
[34] 秦继鹏,刘俨后,麻娟,等. 基于BP神经网络的轮胎模具微铣削能耗预测[J]. 机床与液压,2021,49(24):57-60. QIN Jipeng,LIU Yanhou, MA Juan. Energy consumption prediction for radial tire die micro-milling based on BP neural network[J]. Machine Tool &Hydraulics,2021,49(24):57-60.
[35] 陈世平,谢俊,罗小,等. 基于BP-Adaboost算法的数控机床材料切削能耗预测研究[J]. 制造技术与机床,2020(12):20-24. CHEN Shiping,XIE Jun,LUO Xiao,et al. Study onmaterial cutting energy consumption prediction of CNC machine t00I based on BP-adaboost aIgorithm[J]. Green Manufacturing,2020(12):20-24.
[36] 刘飞,刘培基,李聪波,等. 制造系统能量效率研究的现状及难点问题[J]. 机械工程学报,2017,53(5):1-11. LIU Fei,LIU Peiji,LI Congbo,et al. The statue and difficult problems of research on energy efficiency of manufacturing systems[J]. Journal of Mechanical Engineering,2017,53(5):1-11.

数据与模型混合驱动的箱体零件加工能耗预测

A Data and Model Hybrid Driven Method for Machining Energy Consumption Prediction of Boxy Parts

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]	杨思愚, 徐连勇, 赵雷, 韩永典. EH36钢焊接接头预腐蚀下的疲劳性能及断裂机制研究[J]. 机械工程学报, 2024, 60(8): 204-211.
[2]	方从富, 李弘扬, 沈剑云, 吴贤. 融合磨粒特征和工艺参数的粗糙度智能预测研究[J]. 机械工程学报, 2024, 60(7): 224-235.
[3]	杜文博, 李晓亮, 李霞, 胡深恒, 朱胜. 搅拌摩擦沉积增材技术研究现状[J]. 机械工程学报, 2024, 60(7): 374-384.
[4]	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.
[5]	郭翼彪, 周云水, 黄圣杰, 刘硕, 谢国涛, 秦晓辉. 结构化环境下基于点线特征的VI-SLAM系统[J]. 机械工程学报, 2024, 60(6): 296-305.
[6]	杨树财, 韩佩, 佟欣, 刘献礼, 张晓辉. 刀具介观几何特征成形技术及其作用研究[J]. 机械工程学报, 2024, 60(5): 317-351.
[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]	裴昊男, 杜思哲, 罗明. W形金属封严环成形型面几何质量在机检测研究[J]. 机械工程学报, 2024, 60(20): 35-50.
[9]	朱海华, 王健杰, 李霏, 刘长春, 蔡祺祥. 基于特征选择和SSA-LSTM的车间订单剩余完工时间预测[J]. 机械工程学报, 2024, 60(20): 388-402.
[10]	姚丹, 张捷, 王瑞乾, 肖新标. 阻尼处理对铝型材结构隔声特性的影响分析[J]. 机械工程学报, 2024, 60(18): 299-309.
[11]	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.
[12]	王耀南, 谢核, 邓晶丹, 毛建旭, 李文龙, 张辉. 智能制造测量机器人关键技术研究综述[J]. 机械工程学报, 2024, 60(16): 1-18.
[13]	李春凯, 代悦, 王嘉昕, 顾玉芬, 石玗. 脉冲熔化极气体保护焊熔池振荡行为检测及特征分析[J]. 机械工程学报, 2024, 60(16): 141-150.
[14]	何骏驰, 张李超, 王森林, 汤名锴, 史玉升. 基于骨架线特征识别的激光选区熔化区域性能匹配成形方法[J]. 机械工程学报, 2024, 60(15): 272-282.
[15]	孙雨欣, 蔡守宇, 张旭, 王珂. 基于自适应特征驱动法的散热结构拓扑优化设计[J]. 机械工程学报, 2024, 60(15): 346-357.