Product Life Cycle Assessment Method Based on Incomplete Information Imputation

doi:10.3901/JME.2025.11.311

Abstract

Abstract: Regarding the mixed incomplete information issues in the life cycle inventory of electromechanical products, a comprehensive life cycle assessment(LCA) method based on incomplete information imputation is proposed. Firstly, based on defining the concept of life cycle environmental impact assessment and its structure, the incomplete inventory information problems in each stage of the electromechanical product life cycle are analyzed. Building on an existing LCA case database, when there are incomplete data in the real-time life cycle inventory but corresponding data exist in the LCA case database, a matching filling algorithm based on BP neural network is adopted. This algorithm calculates the similarity levels between various parameters of the components using both text and numerical similarity, and through the output layer, identifies components with a similarity of 100% to fill the missing data. When there are data missing in the real-time life cycle inventory and no corresponding data in the LCA case database, the support vector machine model is employed to predict missing categorical variables, while multiple imputation based on linear regression is used to fill missing continuous variables, effectively completing the incomplete mixed-type information. Finally, taking YDE3120 CNC gear hobbing machine as a case object, the entire lifecycle environmental impact assessment is conducted through steps such as purpose and scope analysis, characterization, and standardization, etc., to identify weak links in each life cycle stage and provide corresponding improvement suggestions.

Key words: life cycle assessment, incomplete information, BP neural network, support vector machine, multiple imputation

CLC Number:

U270

YANG Chen, LI Tao, WANG Mingyu, YANG Dongdong, YAN Meng. Product Life Cycle Assessment Method Based on Incomplete Information Imputation[J]. Journal of Mechanical Engineering, 2025, 61(11): 311-325.

References

[1] GUINÉE J. Handbook on life cycle assessment：Operational guide to the ISO standards[J]. The International Journal of Life Cycle Assessment，2001，6(5)：255.
[2] 江靖宇，刘予涵，庞雨桐，等. 北方农村复合颗粒燃料取暖全生命周期评价研究[J]. 太阳能学报，2022，43(12)：432-438. JIANG Jingyu，LIU Yuhan，PANG Yutong，et al. Study on life cycle evaluation of composite pellet fuel heating in rural areas of North China[J]. Journal of Solar Energy，2022，43(12)：432-438.
[3] TRAGNONE B M，D'EUSANIO M，PETTI L. The count of what counts in the agri-food social life cycle assessment[J]. Journal of Cleaner Production. 2022，354：131624.
[4] 来鑫，陈权威，顾黄辉，等. 面向“双碳”战略目标的锂离子电池生命周期评价：框架、方法与进展[J]. 机械工程学报，2022，58(22)：3-18. LAI Xin，CHEN Quanwei，GU Huanghui，et al. Life cycle evaluation of lithium-ion batteries for "dual carbon" strategy：Framework，methods and progress[J]. Chinese Journal of Mechanical Engineering，2022，58(22)：3-18.
[5] SOARES L A P，FIRMINO A S，OLIVEIRA J A，et al. Comparative LCA of automotive gear hobbing processes with flood lubrication and MQL[J]. The International Journal of Advanced Manufacturing Technology.2022，119(1-2)：1071-1090.
[6] 中国机械工业联合会，绿色制造产业技术创新战略联盟. T/CMIF 14-2017绿色设计产品评价技术规范金属切削机床[S]. 2017-11-01. China Machine Tool Industry Federation，Green Manufacturing Industry Technology Innovation Strategic Alliance. T/CMIF 14-2017 Specification for Green Design Product Evaluation-Metal Cutting Machine Tools [S]. 2017-11-01.
[7] 易茜，柳淳，李聪波，等. 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，et al. Carbon consumption prediction method based on improved generative adversarial filling network with missing data[J]. Journal of mechanical engineering，2023，59(11)：264-275.
[8] STEUBING B，WERNET G，REINHARD J，et al. The ecoinvent database version 3 (partⅡ)：Analyzing LCA results and comparison to version 2[J]. The International Journal of Life Cycle Assessment，2016，21(9)：1269-1281
[9] Life Cycle Assessment Software | Sphera(GaBi)[EB/OL]. [2023-07-08]. https://sphera.com/life-cycle-assessment-lca-software/.
[10] European Platform on LCA | EPLCA[EB/OL].[2023-07- 08]. https://eplca.jrc.ec.europa.eu/EUFRP/.
[11] 晔沙. 数据缺失及其处理方法综述[J]. 电子测试，2017(18)：65-67，60. YE Sha. Review of data missing and its processing methods[J]. Electronic Testing，2017(18)：65-67，60.
[12] BATISTA G E A P A，MONARD M C. An analysis of four missing data treatment methods for supervised learning[J].Applied Artificial Intelligence，2003，17(5/6)：519-533.
[13] ZARGAR S，YAO Y，TU Q S，et al. A review of inventory modeling methods for missing data in life cycle assessment[J].Journal of Industrial Ecology，2022，26(5)：1676-1689.
[14] MERON N，BLASS V，THOMA G. Selection of the most appropriate life cycle inventory dataset：new selection proxy methodology and case study application[J]. The International Journal of Life Cycle Assessment，2020，25(4)，771–783.
[15] ZHAO B，SHUAI C，HOU P，et al. Estimation of unit process data for life cycle assessment using a decision tree-based approach[J]. Environmental Science & Technology：ES&T，2021(12)：55.
[16] HOU P，CAI J R，QU S，et al. Estimating missing unit process data in life cycle assessment using a similarity- based approach[J]. Environmental Science & Technology，2018，52(9)：5259-5267.
[17] LIAO M C，KELLEY S，YAO Y. Generating energy and greenhouse gas inventory data of activated carbon production using machine learning and kinetic based process simulation[J]. ACS Sustainable Chemistry and Engineering，2020，8(2)，1252–1261.
[18] 王晓伟，李方义. 机电产品绿色设计与生命周期评价[M]. 北京：机械工业出版社，2015. WANG Xiaowei，LI Fangyi. Green design and life cycle evaluation of mechanical and electrical products[M]. Beijing：China Machine Press，2015.
[19] HAUSCHILD M A P J. Background for spatial differentiation in LCA imppact assessment：The EDIP2003 Methodology，Environmental Project No. 996 2005[R]. The Institute for Product Development of the Technical University of Denmark，2005.
[20] 闫萌，李涛，杨晨，等. 面向机电产品绿色设计与评价协同的生命周期评价参数计算方法[J]. 中国机械工程，2023，34(12)：1453-1464. YAN Meng，LI Tao，YANG Chen，et al. Life cycle evaluation parameter calculation method for synergistic green design and evaluation of electromechanical products[J]. China Mechanical Engineering，2023，34(12)：1453-1464.
[21] 李方义，李剑峰，颜利军，等. 产品绿色设计全生命周期评价方法研究现状及展望[J]. 现代制造技术与装备，2006(1)：8-13. LI Fangyi，LI Jianfeng，YAN Lijun，et al. Research status and prospect of the whole life cycle assessment method of product green design[J]. Modern Manufacturing Technology and Equipment，2006(1)：8-13.
[22] FORTES I，MORA-LÓPEZ L，MORALES R，et al. Inductive learning models with missing values[J]. Mathematical and Computer Modelling，2006，44(9-10)：790-806.
[23] 丁永新. 基于FSMPT模型和神经网络的机电产品LCA评价系统研究[D]. 大连：大连理工大学，2022. DING Yongxin. Research on mechanical and electrical products LCA evaluation system based on FSMPT model and neural network[D]. Dalian：Dalian University of Technology，2022.
[24] 陈晓琳. 基于迁移学习的信息流行度跨域预测研究[D].北京：对外经济贸易大学，2021. CHEN Xiaolin. Research on cross-domain prediction of information popularity based on transfer learning[D]. Beijing：University of International Business and Economics，2021.
[25] 车万翔，刘挺，秦兵，等. 基于改进编辑距离的中文相似句子检索[J]. 高技术通讯，2004，14(7)：15-19. CHE Wanxiang，LIU Ting，QAN Bing，et al. Chinese similar sentence retrieval based on improved editing distance[J]. High-tech Communication，2004，14(7)：15-19.
[26] 马浩杰. 基于卷积神经网络的单目深度估计和深度补全研究[D]. 杭州：浙江大学，2019. MA Haojie. Research on monocular depth estimation and depth completion based on convolutional neural networks[D]. Hangzhou：Zhejiang University，2019.
[27] 丁世飞，齐丙娟，谭红艳. 支持向量机理论与算法研究综述[J]. 电子科技大学学报，2011，40(1)：2-10. DING Shifei，QI Bingjuan，TAN Hongyan. Research review of support vector machine theory and algorithm[J]. Journal of University of Electronic Science and Technology of China，2011，40(1)：2-10.
[28] 王纯杰，张乐，陈嘉，等. 基于随机森林插补的缺失数据的印度肝脏病人数据支持向量机分类分析[J]. 吉林师范大学学报，2020，41(4)：36-40. WANG Chunjie，ZHANG Le，CHEN Jia，et al. Support vector machine classification of Indian liver patient data based on random forest interpolation missing data[J]. Journal of Jilin Normal University，2020，41(4)：36-40.
[29] 孙玲莉，董世杰，杨贵军. 常用多重插补法的插补重数选择[J]. 统计与决策，2019，35(23)：5-10. SUN Lingli，DONG Shijie，YANG Guijun. Interpolation multiplicity selection by common multiple interpolation method[J]. Statistics and Decision，2019，35(23)：5-10.
[30] 谈翼飞. 高速干切滚齿机床生命周期评价及绿色创新优化[D]. 重庆：重庆大学，2018. TAN Yifei. Life cycle assessment and green innovation optimization of high-speed dry cutting gear hobbing machine[D]. Chongqing：Chongqing University，2018.
[31] 苏姝. 基于QFD和TRIZ的机床全生命周期绿色创新设计优化模型及其应用研究[D]. 重庆：重庆大学，2019. SU Shu. Research on optimization model of green innovation design for machine tool whole life cycle based on QFD and TRIZ and its application[D]. Chongqing：Chongqing University，2019.
[32] 刘志超. 发动机原始制造与再制造全生命周期评价方法[D]. 大连：大连理工大学，2013. LIU Zhichao. Whole Life Cycle evaluation method of engine original manufacturing and remanufacturing[D]. Dalian：Dalian University of Technology，2013.
[33] 刘凤芹. 基于链式方程的收入变量缺失值的多重插补[J]. 统计研究，2009，26(1)：71-77. LIU Fengqin. Multiple interpolation of missing value of income variable based on chain equation[J]. Statistical Research，2009，26(1)：71-77.
[34] 黄强. YE3120CNC7高速干切滚齿机的研发与应用[J]. 世界制造技术与装备市场，2014(6)：95-98. HUANG Qiang. Research and application of YE3120CNC7 high speed dry cutting gear hobbing machine[J]. World Manufacturing Technology and Equipment Market，2014(6)：95-98.
[35] 杨东东. 风力发电机全生命周期多属性决策与仿真研究[D]. 大连：大连理工大学，2023. YANG Dongdong. Research on life cycle multi-attribute decision making and simulation of wind turbine[D]. Dalian：Dalian University of Technology，2023.
[36] 曾北昌，倪俊芳，顾军. 面向机电产品回收的选择性拆卸技术[J]. 机械设计与制造，2010(1)：216-218. ZENG Beichang，NI Junfang，GU Jun. Selective disassembly technology for mechanical and electrical product recycling[J]. Machine Design & Manufacture，2010(1)：216-218.