针对智能制造全生命周期中多源异构数据集成困难、信息孤岛阻碍决策优化的问题，本研究构建了跨生命周期的智慧情报服务模型，提出基于事理图谱的知识推理方法，旨在提升制造系统的数据价值挖掘能力。

在智能制造全生命周期中，多源异构数据集成面临极大挑战，ERP、MES等系统数据格式各异、标准不统一，导致数据难以融合，形成信息孤岛。这使得企业无法有效利用数据进行决策优化，严重制约了生产效率和产品质量的提升。针对此，本研究构建跨生命周期的智慧情报服务模型，提出基于事理图谱的知识推理方法，致力于提升制造系统的数据价值挖掘能力。平台采用分层数据管理策略，通过设计包含资源感知、虚拟开发等核心模块的智慧情报中转平台架构，采用分层数据管理策略，实现产品全生命周期数据融合与共享。同时，引入事理图谱技术，建立事件驱动的知识推理模型，提出数据连接层、融合层与分析层的多级处理机制，有效解决制造事件因果关系建模与动态演化推理难题。

以比亚迪新能源汽车制造为案例,验证模型在故障诊断与工艺优化中的有效性。实验表明:平台实现全流程数据端到端集成，生产异常响应效率提升32%;事理图谱推理模型在故障根因追溯中准确率达89.5%，较传统方法提高11.7%。研究为企业突破《智能制造能力成熟度模型》第四级(网络协同)向第五级(生态引领)跃迁提供了技术路径。

创新点体现在:①构建覆盖全生命周期的智慧情报中转平台，突破多系统数据壁垒;②首

创制造领域事理图谱推理框架，实现知识驱动的动态决策支持。研究成果为智能制造数据价值转化提供了新范式，助力制造业新质生产力发展。

^{Aiming at the problems of multi-source heterogeneous data integration difficulties and information silos hindering decision optimization in the whole life cycle of intelligent manufacturing, this study constructed a cross-life cycle intelligent intelligence service model and proposed aknowledge reasoning method based on reasoning graph to improve the data value mining ability of manufacturing systems.}

^{In the whole life cycle of intelligent manufacturing,multi-source heterogeneous Data Transmission Service faces great challenges. ERP, MES and other systems have different data formats and inconsistent standards, which makes it difficult to integrate data and form information islands. This makes it impossible for enterprises to effectively use data for decision-making optimization, which seriously restricts the improvement of production efficiency and product quality. In response to this, this study constructs a cross-life cycle intelligent intelligence service model, proposes a knowledge reasoning method based on matter graph, and is committed to improving the data value mining ability of manufacturing systems. The platform adopts a hierarchical data management strategy. By designing a smart intelligence transit platform architecture including core modules such as resource perception and virtual development, and adopting a hierarchical data management strategy, it realizes data fusion and sharing in the whole life cycle of products. At the same time, the event-driven knowledge reasoning model is established by introducing the matter graph technology, and the multi-level processing mechanism of data connection layer, fusion layer and analysis layer is proposed to effectively solve the problem of causal relationship modeling and dynamic evolution reasoning of manufacturing events.}

^{Taking BYD new energy vehicle manufacturing as an example, the validity of the model in fault diagnosis and process optimization is verified. The experiment shows that the platform realizes end-to- end integration of the whole process data, and the abnormal response efficiency of production is increased by 32%; The accuracy of reasoning graph model in fault root cause tracing is 89.5%, which is 21.7% higher than that of traditional method. The research provides a technical path for enterprises to break through the fourth level (network collaboration) of the Intelligent Manufacturing Capability Maturity Model to the fifth level (ecological leadership).}

^{The innovation points are as follows: (1) Build an intelligent intelligence transfer platform covering the whole life cycle and break through the multi-system data barriers; (2) The first manufacturing domain reasoning framework, to achieve knowledge-driven dynamic decision support.The research results provide a new paradigm for the value transformation of intelligent manufacturing data and help the development of new quality productivity in manufacturing.}

[1]唐振羽.基于“BIM+”的智慧交通建设全生命周期信息管理技术研究及应用[D].绍兴：绍兴文理学院,2021.

[2]任晓栋.城市快速路全生命周期智慧管理系统[J].城市道桥与防洪,2023,(12):185-188+192+26-27.

[3]孙守强，李青青.基于情报感知的智慧图书馆网络舆情服务体系构建[J].情报科学,2023,41(07):146-152.

[4]]王秉，陈超群.智慧安全情报服务体系研究[J].现代情报,2021,41(04):3-9+164.

[5]]张伟明.国际高铁行业竞争情报决策支持系统研究[D].南京：东南大学,2022.

[6]孙兰芸.智慧统计数据全生命周期的数据安全实践与探索[J].内蒙古统计,2023,(03):20-23.

[7]张恒枫.“智慧校园”项目全生命周期风险管理研究[D].徐州：中国矿业大学,2023.

[8]王靖玮，贾兴良，李欣等.电梯全生命周期智慧云平台构建与应用[J].创新世界周刊,2023,(03):74-81.

[9]赵寒英.固定资产全生命周期管理模式实践研究——以总分馆服务体系和智慧技术背景下的大型公共图书馆为例[J].财经界,2023,(31):81-83.

[10]田怀谷，黄贤君，陈涛等.基于医疗设备全生命周期的智慧医院平台建设实践[J].中国卫生质量管理,2023,30(10):20-23+27.

[11]HELTON J W, KELLY F P, WILLIAMS R J, et al. A Fluid Model of a Traffic Network with Information Feedback and Onramp Controls[J]. Applied Mathematics & Optimization, 2021, 84(S1): 175-214.

[12]HAZIRI L. Improving Design for Remanufacturing Though Feedback from Remanufacturing to Design[M]//Linköping studies in science and technology. Dissertations. 2020.

[13]LIU Y, JIANG Q, YANG C, et al. Uncertainty analysis of reactivity feedback coefficient for LFR core power control system during reactivity insertion accident[J]. Annals of Nuclear Energy, 2021, 160:108401.

[14]LEE H. Strategic similarity in the co-evolution of technological and business diversification for firm growth: Evidence from smart-manufacturing related firms[J]. Technological Forecasting and Social Change, 2023, 189: 122356.

[15]QU Y, WANG Y, MING X, et al. Multi-stakeholder’s sustainable requirement analysis for smart manufacturing systems based on the stakeholder value network approach[J]. Computers & Industrial Engineering, 2023, 177: 109043.

[16]QU Y, MA Y, MING X, et al. Two-stage coevolution method for deep CNN: A case study in smart manufacturing[J]. Applied Soft Computing, 2023, 135: 110026.

[17]WANNER J, WISSUCHEK C, WELSCH G, et al. A Taxonomy and Archetypes of Business analytics in smart Manufacturing[J]. ACM SIGMIS Database the DATABASE for Advances in Information Systems, 2023, 54(1): 11-45.

[18]CHEN H. The practice of mechatronics technology in intelligent manufacturing[J]. Proceedings of SPIE, 2024:131.

[19]杨琴琴，张骁雄，田伟，等.基于注意力机制和多关系事件的时序知识图谱推理[J].微电子学与计算机, 2023, 40(7):18-26.

[20]王亚珅，刘弋锋，张欢欢，等.一种基于知识推理的预测环境危险度的方法及装置.中国，H04W84/18；G08B21/18；G06N5/04, CN201910007843.7[2022-08-16].

[21]李志鹏,杨阳朝,廖勇,等.数据驱动的事件预测技术最新研究进展[J].信息安全学报,2022,7(01):40-55.

[22]杨纪星，杨波，朱剑林，等.金融领域事件因果关系发现及事理图谱构建与应用[J].中文信息学报,2023,37(7):131-142.

[23]张聪聪，都云程，张仰森.事件抽取研究综述[J].计算机技术与发展,2023,33(1):7-13.

[24]魏建香，梁帅，朱云霞，等.事理图谱研究进展[J].情报资料工作,2023,44(06):35-43.

[25]中国计算机协会.事理图谱的构建与应用暨第二届事理图谱研讨会|CNCC2021[EB/OL].(2021-10-06)[2021-10-06].

[26]张海涛,李佳玮,刘伟利,等.重大突发事件事理图谱构建研究[J].图书情报工作,2021,65(18):133-140.

[27]PU R, LI Y, WANG S, et al. Enhancing Event Causality Identification with Event Causal Label and Event Pair Interaction Graph[J]. Findings of the Association for Computational Linguistics: ACL 2022, 2023: 10314-10322.

[28]宋成琳.《智能制造能力成熟度模型》国家标准在企业自评估的应用研究[J].中国设备工程,2021,(22):266-267.

[29]CHEN M, CAO Y, ZHANG Y, et al. CHEER: Centrality-Aware high-order event reasoning network for document-level event causality identification[J]. ACL, 2023: 10804-10816.

[30]徐祎.基于全自动化监测中的应用[J].测绘与空间地理信息,2024,47(01):148-151.

[31]舒志鹏.基于深度学习的无线定位技术的研究与应用[D].北京：北京邮电大学,2023.

[32]王建新，赵旭，房金良等.商用车智能制造能力成熟度模型及评估体系研究和应用[J].汽车制造业,2023,(06):20-24.

[33]张亮.加油机全生命周期智慧监管与服务体系构建的思考[J].中国计量,2022,(02):91-92+133.

[34]杨胜飞，刘明.基于供水全生命周期管控的智慧水务平台研建[J].水利信息化,2022,(03):66-71.

[35]邢海军，陈国忠，魏晓等.风力发电机组全生命周期智慧运维模式探索与实践浅析[C]//中国电力技术市场协会.2022年电力行业技术监督工作交流会暨专业技术论坛论文集.国华投资新疆公司，2022:3.

[36]杨启明.基于全生命周期的水电站智慧检修创新实践[J].中国设备工程,2020,(24):19-21.

[37]钱忠，张丽，付浩云等.全生命周期智慧化印染服务平台推广过程及效益[J].印染助剂,2023,40(04):1-5+14.

[38]耿明菲，佘佳蔓，卫荣.医院智慧档案全生命周期视角下的安全管理模式设想研究[J].临床医学研究与实践,2019,4(20):185-187.

[39]杨胜飞，刘明.基于供水全生命周期管控的智慧水务平台研建[J].水利信息化,2022,(03):66-71.

[40]张建国，萧白，侯建飞等.基于BIM技术的绿色、智慧港口建设项目全生命周期管理方法[J].运输经理世界,2020,(07):9-10.

[41]赵博.物联网技术在智能制造中的应用研究[J].产品可靠性报告,2023,(02):83-85.

[42]WANG Y, WANG X, TAO F, et al. Digital twin-driven complexity management in intelligent manufacturing[J]. Digital Twin,2021,1:9.

[43]李伯虎,柴旭东,刘阳,等.智慧物联网系统发展战略研究[J].中国工程科学,2022,24(04):1-11.

[44]王进宏，大数据生命周期管理技术及其在智慧城市中的应用.广东省,北明软件有限公司,2018-10-26.

[45]何文杰.基于智能水表多参数数据的智慧管理平台的应用和展望[J].智能建筑与智慧城市,2025,(02):21-23.

[46]曹彬，胡江洪，陈立名，等.大数据与人工智能技术支撑下的汽车产业智能制造工程实践[J].新型工业化, 2023, 13(7):95-103.

[47]王晶，姜睿.面向"智慧工厂"的"机器人学"课程实践环节设计[J].装备制造技术, 2023(10):86-88.

[48]陈思怡,陈尧,陈裔月,等.精密元器件工业生产自动化检测的算法研究[J].现代信息科技,2024,8(22):156-160.

[49]孙一元.上海电气:从传统制造向智能制造转型[J].上海国资, 2021(7):53-55.

[50]WEN D, LIU P, ZHU G, et al. Task-Oriented sensing, computation, and communication integration for Multi-Device Edge AI[J]. IEEE Transactions on Wireless Communications, 2023, 23(3): 2486-2502.

[51]WANG Y, WANG X, TAO F, et al. Digital twin-driven complexity management in intelligent manufacturing[J]. Digital Twin, 2021, 1: 9.

[52]张杰，王淑侠，何卫平，等.航空发动机叶片装配执行过程智能检测及AR引导[J].计算机集成制造系统,2024,30(04):1263-1272.

[53]曹宁.浅谈物联网+智能生产线应用技术专业群建设[J].广东教育:职教, 2021(10):2.

[54]李冰,梁国强,黄浪.企业社会责任项目全生命周期管理方法与模式的探究[J].质量与认证,2025,(03):71-74.

[55]杨媚.基于全生命周期管理的船舶制造业产品数据电子文件归档体系构建[J].兰台内外,2025,(03):49-51.

[56]张鑫蕊.面向重大突发事件公众认知的智慧情报服务研究[D].吉林大学,2024.

[57]黄少年，王焕然，李佩霖.基于大语言模型的群体性突发事件事理图谱构建与演化分析[J].情报杂志,2024,43(12):161-169.

[58]周京艳，刘如，李佳娱，等.情报事理图谱的概念界定与价值分析[J].情报杂志,2018, 37(05):31-36+42.

[59]范黎林，杨凯，毛文涛，等.融合结构化信息与时序演化信息的多变量间歇性时间序列预测[J].控制与决策，2024(1):263-270.

[60]钱榕,许建婷,张克君,等.隐马尔可夫模型的异质网络链接预测方法研究[J].通信学报,2022,43(05):214-225.

[61]尹梓诺，马海龙，胡涛.基于联合注意力机制和一维卷积神经网络-双向长短期记忆网络模型的流量异常检测方法[J].电子与信息学报,2023,45(10):3719-3728.

[62]胡姗.基于贝叶斯网络的ERP项目风险管理研究[D].武汉：中南财经政法大学,2019.

[63]李汝资，陈巧娟，高雄愿，等.长江经济带城市绿色经济效率梯度转换规律及其影响因素[J].自然资源学报,2024,39(01):125-139.

[64]吴洁.制造领域知识图谱的构建及应用[J].现代信息科技,2024,8(8):186-193.

[65]陈诗琦.运用思维可视化促进学生学会学习——以高中信息技术《从E-R模型到关系数据模型的转换》教学为例[J].福建教育学院学报,2020,21(06):63-65.

[66]LI Q, GUO Z, LI X, et al. Research on Threat Detection of SQL Injection Attacks in Large Scale Web Applications[J]. ACTCE, 2024: 195-198.

[67]刘冰.基于JDBC数据库连接池技术的研究与实现[J].计算机与现代化,2010(7):32-34.

[68]XIAO C. A new Data bases access Technigue——OLE DB Interface technique[J]. Journal of East China Shipbuilding Institute, 2001.

[69]TANG S, HE B, YU C, et al. A survey on SpARk Ecosystem: big data processing infrastructure, machine learning, and applications[J]. IEEE Transactions on Knowledge and Data Engineering, 2020: 1.