基于多级数据融合的核电站运行功能健康状态评估

doi:10.3901/JME.2024.04.200

机械工程学报 ›› 2024, Vol. 60 ›› Issue (4): 200-211.doi: 10.3901/JME.2024.04.200

扫码分享

基于多级数据融合的核电站运行功能健康状态评估

蒋翔宇¹, 冯毅雄^1,2, 洪兆溪^1,3, 胡炳涛¹, 司恒远⁴, 谭建荣¹

1. 浙江大学流体动力基础件与机电系统全国重点实验室杭州 310027;
2. 贵州大学省部共建公共大数据国家重点实验室贵阳 550025;
3. 浙江大学宁波科创中心宁波 315100;
4. 深圳中广核工程设计有限公司深圳 518172

收稿日期:2023-04-06 修回日期:2023-11-02 出版日期:2024-02-20 发布日期:2024-05-25
通讯作者: 洪兆溪,女,1990年出生,博士,助理研究员。主要研究方向为智能设计与不确定性优化决策。E-mail:hzhx@zju.edu.cn
作者简介:蒋翔宇,女,1997年出生,博士研究生。主要研究方向为复杂装备状态预测与健康管理。E-mail:11925071@zju.edu.cn冯毅雄,男,1975年出生,博士,教授,博士研究生导师。主要研究方向为现代设计理论与方法等。E-mail:fyxtv@zju.edu.cn胡炳涛,男,1992年出生,博士。主要研究方向为产品设计理论与智能制造。E-mail:hubingtao@zju.edu.cn司恒远,男,1982年出生,正高级工程师。主要研究方向为核电厂型号研发,总体设计和智能技术。E-mail:sihengyuan@cgnpc.com.cn谭建荣,男,1954年出生,博士,教授,博士研究生导师,中国工程院院士。主要研究方向为CAX方法学、工程图学、企业信息化。E-mail:egi@zju.edu.cn
基金资助:
浙江省“尖兵”“领雁”研发攻关计划(2023X01214); 国家自然科学基金(52130501,52105281)资助项目

Health Status Assessment on the Operation Function of Nuclear Power Plants Based on Multi-level Data Fusion

JIANG Xiangyu¹, FENG Yixiong^1,2, HONG Zhaoxi^1,3, HU Bingtao¹, SI Hengyuan⁴, TAN Jianrong¹

1. State Key Laboratory of Fluid Power and Mechatronic Systems, Zhejiang University, Hangzhou 310027;
2. State Key Laboratory of Public Big Data, Guizhou University, Guiyang 550025;
3. Ningbo Innovation Center, Zhejiang University, Ningbo 315100;
4. China Nuclear Power Design Co., Ltd. (Shenzhen), Shenzhen 518172

Received:2023-04-06 Revised:2023-11-02 Online:2024-02-20 Published:2024-05-25

摘要/Abstract

摘要： 随着新一代信息技术和人工智能技术与工业日益深度的融合协作，工业系统的运维从传统的人工定期运维向基于状态的智能维护迈进，其中健康状态评估作为智能运维的关键环节，通过源源不断的数据对系统的演化进行持续感知分析，为预测性维护提供决策支持。以核电站为研究对象，提出面向多部门协同环境下设备-系统-子功能-功能多层级融合的健康状态评估框架。针对工业系统控制的设备群具有大量状态参数的特点，提出基于偏差赋权的加权平均融合算子融合设备级参数，可快速定位并突出异常设备参数，避免评估结果因融合参数较多而展现“健康”假象；鉴于系统在不同健康状态下样本数据量的差异，提出考虑不平衡样本的非对称多分类学习方法融合系统健康值，多个健康等级之间通过信息有向迁移建立可自学习优化的健康评估模型，实现子功能健康状态及时自感知评估；最后基于集成学习融合多个子功能所属的健康评估器，得到宏观的运行功能健康状态评估决策。在提出的框架指导下对核电站反应性功能进行逐级健康状态评估，验证所提方法的有效性。

关键词: 工业系统, 健康状态评估, 数据融合, 核电站, 基于状态的维护

Abstract: With the new-generation information technologies and artificial intelligence that are deeply integrated with the industry, the maintenance of industrial systems is moving from the manual regular maintenance to state-based intelligent maintenance(IM). Health status assessment(HSA) is a key link in IM. Systemic states are recognized via the monitored data whereby provide decision support for maintenance. Taking nuclear power plants(NPP) as the research object, an HSA framework is proposed based on multi-level integration of equipment, system, sub-function and function in a multi-department collaboration. Due to equipment groups with numerous state parameters, a weighted average fusion operator based on deviation weighting is proposed to fuse equipment-level parameters, which can timely highlight the abnormal equipment. Considering the different amount of data in different health states, an asymmetric multi-class learning method under imbalanced datasets is proposed to fuse the systems’ health values. The self-learning HSA model is established by the information transfer between multiple health levels, so that the health status of sub-functions can be self-perceived and assessed in a timely manner. The health assessors of multiple sub-functions are fused based on ensemble learning to obtain a macro-level operational function HSA decision. Exemplified with the reactivity function of the NPP, the proposed HAS frame is verified effective.

Key words: industrial system, health status assessment, data fusion, nuclear power plant, state-based maintenance

中图分类号:

TG156

蒋翔宇, 冯毅雄, 洪兆溪, 胡炳涛, 司恒远, 谭建荣. 基于多级数据融合的核电站运行功能健康状态评估[J]. 机械工程学报, 2024, 60(4): 200-211.

JIANG Xiangyu, FENG Yixiong, HONG Zhaoxi, HU Bingtao, SI Hengyuan, TAN Jianrong. Health Status Assessment on the Operation Function of Nuclear Power Plants Based on Multi-level Data Fusion[J]. Journal of Mechanical Engineering, 2024, 60(4): 200-211.

参考文献

[1] 陈俊洵,程龙生,余慧,等.基于EMD-SVD与马田系统的复杂系统健康状态评估[J].系统工程与电子技术,2017,39(7):1542-1548. CHEN Junxun,CHENG Longsheng,YU Hui,et al. Health status assessment for complex systems based on EMD-SVD and Mahalanobis-Taguchi system[J]. Systems Engineering and Electronics,2017,39(7):1542-1548.
[2] 孙强,岳继光.基于不确定性的故障预测方法综述[J].控制与决策,2014,29(5):769-778. SUN Qiang,YUE Jiguang. A review of fault prediction methods based on uncertainty[J]. Control and Decision,2014,29(5):769-778.
[3] ALASWAD S,XIANG Y. A review on condition-based maintenance optimization models for stochastically deteriorating system[J]. Reliability Engineering&System Safety,2017,157:54-63.
[4] 王庆锋,李中,许述剑,等.基于故障案例学习的设备健康评价方法研究[J].机械工程学报,2020,56(20):28-37. WANG Qingfeng,LI Zhong,XU Shujian,et al. Research on equipment health evaluation method based on fault case learning[J]. Journal of Mechanical Engineering,2020,56(20):28-37.
[5] 杨敏.液体火箭发动机试验台健康状态评估方法研究[D].哈尔滨:哈尔滨工业大学,2011. YANG Min. Assessment method research of health condition for liquid rocket engine test facilities[D]. Harbin:Harbin Institute of Technology,2011.
[6] 金飞.核电厂反应性控制功能健康状态评估方法研究[D].哈尔滨:哈尔滨工程大学,2017. JIN Fei. Research on evaluation methods of reactivity control function's health state for nuclear power plant[D]. Harbin:Harbin Engineering University,2017.
[7] 李雪争.核电厂运行健康状态建模与可视化分析[D].天津:天津大学,2017. LI Xuezheng. Modeling for healthy operation state of nuclear power plant and research on visual analysis method[D]. Tianjin:Tianjin University,2017.
[8] HU X,LI S E,YANG Y. Advanced machine learning approach for lithium-ion battery state estimation in electric vehicles[J]. IEEE Transactions on Transportation Electrification,2016,2(2):140-149.
[9] TOLO S,TIAN X,BAUSCH N,et al. Robust on-line diagnosis tool for the early accident detection in nuclear power plants[J]. Reliability Engineering&System Safety,2019,186:110-119.
[10] RAMASSO E,GOURIVEAU R. Remaining useful life estimation by classification of predictions based on a neuro-fuzzy system and theory of belief functions[J]. IEEE Transactions on Reliability,2014,63(2):555-566.
[11] 阮羚,谢齐家,高胜友,等.人工神经网络和信息融合技术在变压器状态评估中的应用[J].高电压技术,2014,40(3):822-828. RUAN Ling,XIE Qijia,GAO Shengyou,et al. Application of artificial neural network and information fusion technology in power transformer condition assessment[J]. High Voltage Engineering,2014,40(3):822-828.
[12] WANG J,SHI J,HE Q. Research on component-level health quantitative assessment based on SVM algorithm for analog electronic circuits[C]//2015 Prognostics and System Health Management Conference (PHM). 2015:1-5.
[13] ZHOU Y,XIAO H,CHEN Z,et al. A dynamic health assessment method for industrial equipment based on SG-FCM clustering algorithm[C]//2019 International Conference on Internet of Things (iThings) and IEEE Green Computing and Communications (GreenCom) and IEEE Cyber,Physical and Social Computing (CPSCom) and IEEE Smart Data (SmartData),2019:34-39.
[14] 张黎明,赵新文,蔡琦.基于SVM的核动力屏蔽泵老化状态评估[J].核动力工程,2011,32(2):124-127. ZHANG Liming,ZHAO Xinwen,CAI Qi. Aging state evaluation of nuclear power shield pump based on SVM[J]. Nuclear Power Engineering,2011,32(2):124-127.
[15] JAVED K,GOURIVEAU R,ZERHOUNI N. A new multivariate approach for prognostics based on extreme learning machine and fuzzy clustering[J]. IEEE Transactions on Cybernetics,2015,45(12):2626-2639.
[16] 罗家祥,罗丹,胡跃明.带权重变化和决策融合的ELM在线故障检测[J].控制与决策,2018,33(6):1033-1040. LUO Jiaxiang,LUO Dan,HU Yueming. A new online extreme learning machine with varying weights and decision level fusion for fault detection[J]. Control and Decision,2018,33(6):1033-1040.
[17] 张文博,姬红兵.融合极限学习机[J].电子与信息学报,2013,35(11):2728-2732. ZHANG Wenbo,JI Hongbing. Fusion of extreme learning machines[J]. Journal of Electronics&Information Technology,2013,35(11):2728-2732.
[18] MAHLER R,EBRARY I. Statistical multisource-multitarget information fusion[M]. Boston:Artech House,Inc.,2007.
[19] LI H,HUANG H Z,LI Y F,et al. Physics of failure-based reliability prediction of turbine blades using multi-source information fusion[J]. Applied Soft Computing,2018,72:624-635.
[20] ZHANG Y,YANG Q. An overview of multi-task learning[J]. National Science Review,2018,5(1):30-43.
[21] TAN Z,DE G,LI M,et al. Combined electricity-heat-cooling-gas load forecasting model for integrated energy system based on multi-task learning and least square support vector machine[J]. Journal of Cleaner Production,2020,248:119252.
[22] LEE G,YANG E,HWANG S J. Asymmetric multi-task learning based on task relatedness and loss[C]//BALCAN M F,WEINBERGER K Q. International Conference on Machine Learning,48. San Diego:Jmlr-Journal Machine Learning Research,2016.
[23] XU J,LI L,JI M. Ensemble learning based multi-source information fusion[C]//SU R. 2019 International Conference on Image and Video Processing,and Artificial Intelligence. Shanghai,China:SPIE,2019:81.

基于多级数据融合的核电站运行功能健康状态评估

Health Status Assessment on the Operation Function of Nuclear Power Plants Based on Multi-level Data Fusion

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]	高凯, 罗攀, 谢进, 胡林, 陈彬, 杜荣华. 基于数据融合的混合动力汽车速度轮廓预测[J]. 机械工程学报, 2024, 60(6): 342-353.
[2]	吕黎曙, 邓朝晖, 岳文辉, 万林林, 刘涛. 单颗磨粒磨削机理与数据融合驱动的磨削过程建模分析[J]. 机械工程学报, 2023, 59(7): 200-215.
[3]	郭锐, 张印浩, 牛雯雯, 骆雄帅, 蔡伟, 王建伟, 王岳峰, 赵静一. 基于GLCT及CPA-SVM的变转速齿轮泵健康状态分类研究[J]. 机械工程学报, 2023, 59(14): 310-319.
[4]	黄松岭, 孙洪宇, 王珅, 赵伟, 彭丽莎. 压水堆核电站无损检测与状态监测研究综述[J]. 机械工程学报, 2022, 58(4): 1-13.
[5]	方燕琼, 唐升卫, 顾博川, 代仕勇, 叶向前. 基于二进制位缺失标识与改进D-S证据理论的数据融合技术研究^*[J]. 电气工程学报, 2021, 16(3): 184-191.
[6]	李文龙, 李中伟, 毛金城, 王刚. 核主泵复杂零件机器人在位自动光学检测系统开发[J]. 机械工程学报, 2020, 56(13): 179-191.
[7]	王军庄. 核电站对时系统设计优化[J]. 电气工程学报, 2018, 13(2): 41-44.
[8]	雍文亮, 管欣, 王博, 卢萍萍. 基于多传感数据融合滤波的纵向坡度识别算法[J]. 机械工程学报, 2018, 54(14): 116-124.
[9]	石饶桥, 李健, 张彪, 许传龙, 王式民. 基于卡尔曼滤波的烟气NO_x浓度融合测量方法[J]. 机械工程学报, 2017, 53(24): 63-69.
[10]	李作胜, 张衍, 刘育建, 方俊, 栾伟玲, 吴国章. 电子器件γ辐射屏蔽材料设计及性能研究[J]. 机械工程学报, 2017, 53(21): 31-36.
[11]	欧志新. 变电所非对称电压畸变的自适应数据融合研究[J]. 电气工程学报, 2017, 12(12): 26-32.
[12]	陈洪磊, 邓菲, 刘增华. 基于Lamb波传播路径分析的复合材料板中缺陷成像^*[J]. 机械工程学报, 2016, 52(24): 72-79.
[13]	李巍华翁胜龙张绍辉. 一种萤火虫神经网络及在轴承故障诊断中的应用[J]. 机械工程学报, 2015, 51(7): 99-106.
[14]	邵景峰, 贺兴时, 王进富, 白晓波, 雷霞, 刘聪颖. 大数据环境下的纺织制造执行系统设计[J]. 机械工程学报, 2015, 51(5): 160-170.
[15]	高欣健;张旭东;高亚捷;Peter Ott. 基于单幅灰度图像的快速三维重建方法研究[J]. , 2014, 50(2): 42-47.