Design of fault diagnosis expert system based on fault tree and production rules
-
摘要:
目的 为充分运用核动力装置运行管理经验辅助核动力操纵人员进行故障诊断，设计一种船用核动力装置故障诊断专家系统。 方法 首先，根据故障树与产生式规则之间的逻辑一致性，提出一种将故障树知识转化为产生式规则的方法；然后，对采用正、反向混合推理方法的专家系统知识库和推理机进行优化设计，并依据故障树最小割集和重要度分析结果设计正向推理策略简化推理流程；最后，根据人工对故障状态判断的思路设计状态监测模块，实时采集关键设备参数以转化为专家系统可识别的设备信息。 结果 结果显示，采用所提方法解决了专家系统知识获取困难的问题，能在保证推理准确度的前提下提升推理效率，实现了专家系统的在线故障诊断功能。 结论 研究表明采用所提方法可提升专家系统获取知识的能力和推理效率，对保障核动力装置的运行管理安全具有重要意义。 Abstract:Purpose To fully utilize the experience of nuclear power plant operation and management to assist nuclear power operators in fault diagnosis, a marine nuclear power plant fault diagnosis expert system is designed. Method Firstly, based on the logical consistency between fault trees and production rules, a method is proposed to transform fault tree knowledge into production rules; Then, optimize the knowledge base and inference machine of the expert system using a mixed forward and backward inference method, and design a forward inference strategy to simplify the inference process based on the minimum cut set and importance analysis results of the fault tree; Finally, based on the idea of manually judging the fault status, a status monitoring module is designed to collect key equipment parameters in real time and convert them into equipment information that can be recognized by expert systems. Result The results showed that the proposed method solved the problem of difficult knowledge acquisition in expert systems, and improved inference efficiency while ensuring inference accuracy, achieving the online fault diagnosis function of expert systems. Conclusion Research has shown that using the proposed method can enhance the knowledge acquisition ability and inference efficiency of expert systems, which is of great significance for ensuring the operational management safety of nuclear power plants. -
Key words:
- nuclear power plant /
- fault tree /
- expert system /
- production rule /
- fault diagnosis
-
图 1 船用核动力装置故障诊断专家系统结构
Figure 1. Structure of fault diagnosis expert system for marine nuclear power plant
图 3 余热排出系统排热能力减少故障故障树
Figure 3. Fault tree for reducing heat removal capacity of residual heat removal system
表 1 底事件相关设备功能失效率
Table 1. Failure rate of equipment functions related to bottom events
事件编号 事件名称 参数值 X1 冷却器管程堵塞 1.81×10−08/h X2 控制阀A1故障 2.56×10−04/d X3 控制阀A2故障 2.56×10−04/d X4 冷却器外漏 3.60×10−07/h X5 水泵A1故障 4.25×10−06/h X6 止回阀A1故障 2.17×10−05/d X7 水泵A2故障 4.25×10−06/h X8 止回阀A2故障 2.17×10−05/d X9 水泵B故障 4.25×10−06/h X10 止回阀B故障 2.17×10−05/d X11 控制阀B1故障 2.56×10−04/d X12 控制阀B2故障 2.56×10−04/d X13 冷却器壳程堵塞 8.18×10−08/h 
下载: 导出CSV
表 2 底事件重要度结果
Table 2. Importance results of bottom event
事件名称 关键重要度 概率重要度 结构重要度 水泵B故障 2.80×10−1 1 1.95×10−3 控制阀A1故障 1.71×10−1 1 1.95×10−3 控制阀A2故障 1.71×10−1 1 1.95×10−3 控制阀B1故障 1.71×10−1 1 1.95×10−3 控制阀B2故障 1.71×10−1 1 1.95×10−3 冷却器外漏 2.40×10−2 1 1.95×10−3 止回阀B故障 1.45×10−2 1 1.95×10−3 冷却器壳程堵塞 5.45×10−3 1 1.95×10−3 冷却器管程堵塞 1.21×10−3 1 1.95×10−3 水泵A1故障 1.27×10−4 4.47×10−4 4.88×10−4 水泵A2故障 1.27×10−4 4.47×10−4 4.88×10−4 止回阀A1故障 6.46×10−6 4.47×10−4 4.88×10−4 止回阀A2故障 6.46×10−6 4.47×10−4 4.88×10−4
下载: 导出CSV
表 3 知识库结构
Table 3. Structure of knowledge base
规则号 规则条件 规则结论 推理顺序 101 排热能力减少 水泵B故障 1 102 排热能力减少 控制阀A1故障 2 … … … … 112 排热能力减少 止回阀A1故障and水泵A2故障 12 113 排热能力减少 止回阀A1故障and止回阀A2故障 13 201 排热能力减少 一次侧流量减少and
二次侧冷却不足— 301 一次侧流量减少 控制阀A1故障 — 302 一次侧流量减少 控制阀A2故障 — 303 一次侧流量减少 冷却器管程堵塞 — 304 一次侧流量减少 水泵支路流量减少 — 401 二次侧冷却不足 冷却器外漏 — 402 二次侧冷却不足 海水流量减小 — 501 … … — … … … —
下载: 导出CSV
-
[1] 周东华, 胡艳艳. 动态系统的故障诊断技术[J]. 自动化学报, 2009, 35(6): 748–758. doi: 10.3724/SP.J.1004.2009.00748ZHOU D H, HU Y Y. Fault diagnosis techniques for dynamic systems[J]. Acta Automatica Sinica, 2009, 35(6): 748–758 (in Chinese). doi: 10.3724/SP.J.1004.2009.00748 [2] 刘才学, 罗能, 何攀, 等. 反应堆关键设备健康监测与故障诊断技术研究进展[J]. 核动力工程, 2023, 44(3): 8–20.LIU C X, LUO N, HE P, et al. Research progress of hearth monitoring and fault diagnosis for reactor critical equipment[J]. Nuclear Power Engineering, 2023, 44(3): 8–20 (in Chinese). [3] MANDAL S, SANTHI B, SRIDHAR S, et al. Nuclear power plant thermocouple sensor-fault detection and classification using deep learning and generalized likelihood ratio test[J]. IEEE Transactions on Nuclear Science, 2017, 64(6): 1526–1534. [4] GAUTAM S, TAMBOLI P K, ROY K, et al. Sensors incipient fault detection and isolation of nuclear power plant using extended Kalman filter and Kullback–Leibler divergence[J]. ISA Transactions, 2019, 92: 180–190. doi: 10.1016/j.isatra.2019.02.011 [5] ZHANG X, DENG Z G, JIAN Y F, et al. Reliability analysis of nuclear safety-class DCS based on T-S fuzzy fault tree and Bayesian network[J]. Nuclear Engineering and Technology, 2023, 55(5): 1901–1910. doi: 10.1016/j.net.2023.01.028 [6] YATSUGI K, PANDARAKONE S E, MIZUNO Y, et al. Common diagnosis approach to three-class induction motor faults using stator current feature and support vector machine[J]. IEEE Access, 2023, 11: 24945–24952. doi: 10.1109/ACCESS.2023.3254914 [7] CHOI J, LEE S J. Consistency index-based sensor fault detection system for nuclear power plant emergency situations using an LSTM network[J]. Sensors, 2020, 20(6): 1651. doi: 10.3390/s20061651 [8] WANG H, PENG M J, WESLEY HINES J, et al. A hybrid fault diagnosis methodology with support vector machine and improved particle swarm optimization for nuclear power plants[J]. ISA Transactions, 2019, 95: 358–371. doi: 10.1016/j.isatra.2019.05.016 [9] YIN W Z, XIA H, HUANG X Y, et al. A fault diagnosis method for nuclear power plant rotating machinery based on adaptive deep feature extraction and multiple support vector machines[J]. Progress in Nuclear Energy, 2023, 164: 104862. doi: 10.1016/j.pnucene.2023.104862 [10] 马杰, 张龙飞, 余刃, 等. 基于PCA与SDG的反应堆一回路系统故障诊断方法研究[J]. 核动力工程, 2021, 42(3): 197–202.MA J, ZHANG L F, YU R, et al. Research on accident diagnosis method for reactor primary circuit system based on SDG and PCA[J]. Nuclear Power Engineering, 2021, 42(3): 197–202 (in Chinese). [11] SMAILI R, EL HARABI R, ABDELKRIM M N. Design of fault monitoring framework for multi-energy systems using signed directed graph[J]. IFAC-PapersOnLine, 2017, 50(1): 15734–15739. doi: 10.1016/j.ifacol.2017.08.2304 [12] LIAO T T, ZHAI B J, HAN L J. Development and application of intelligent expert system for cold functional test of reactor vessel open in nuclear power plant[C]//2020 Chinese Automation Congress. Shanghai, China: IEEE, 2020: 4956-4958. [13] 周春娟. 基于故障树的反应堆故障诊断及在报警系统中的应用[D]. 上海: 上海交通大学, 2009.ZHOU C J. FTA based reactor fault diagnosis and its application to alarm system[D]. Shanghai: Shanghai Jiao Tong University, 2009 (in Chinese). [14] 马杰, 张龙飞, 彭俏, 等. 基于分层符号有向图的二回路系统故障诊断[J]. 兵器装备工程学报, 2020, 41(8): 176–181.MA J, ZHANG L F, PENG Q, et al. Research on fault diagnosis method for secondary system based on hierarchical signed directed graph[J]. Journal of Ordnance Equipment Engineering, 2020, 41(8): 176–181 (in Chinese). [15] ZHANG Q, DONG C L, CUI Y, et al. Dynamic uncertain causality graph for knowledge representation and probabilistic reasoning: statistics base, matrix, and application[J]. IEEE Transactions on Neural Networks and Learning Systems, 2014, 25(4): 645–663. doi: 10.1109/TNNLS.2013.2279320 [16] 康兴, 李维波, 余万祥, 等. 某舰用变压器在线监测与故障诊断系统研究[J]. 中国舰船研究, 2019, 14(4): 147–154. doi: 10.19693/j.issn.1673-3185.01434KANG X, LI W B, YU W X, et al. Study of on-line monitoring and fault diagnosis system for a naval transformer[J]. Chinese Journal of Ship Research, 2019, 14(4): 147–154 (in Chinese). doi: 10.19693/j.issn.1673-3185.01434 [17] 田增华. 汽轮机组振动故障诊断及专家系统研究[D]. 北京: 华北电力大学, 2007.TIAN Z H. The research on vibration fault diagnosis and expert system of steam turbine[D]. Beijing: North China Electric Power University, 2007 (in Chinese). [18] NABESHIMA K, SUZUDO T, OHNO T, et al. Nuclear reactor monitoring with the combination of neural network and expert system[J]. Mathematics and Computers in Simulation, 2002, 60(3/4/5): 233–244. [19] 彭俏, 郭立峰, 马杰. 基于模糊Petri网推理的核动力装置专家系统研究[J]. 原子能科学技术, 2012, 46(增刊1): 356–360.PENG Q, GUO L F, MA J. Study of nuclear power plant expert system based on fuzzy Petri net reasoning[J]. Atomic Energy Science and Technology, 2012, 46(Supp 1): 356–360. [20] 刘震. 基于SDG-ES的核动力装置故障诊断技术研究[D]. 哈尔滨: 哈尔滨工程大学, 2014.LIU Z. Research on fault diagnosis technology of nuclear power plant based on SDG-ES[D]. Harbin: Harbin Engineering University, 2014 (in Chinese). [21] 张强, 剡昌锋, 王慧滨, 等. 基于规则与案例推理的汽轮发电机组故障诊断专家系统[J]. 电力科学与工程, 2018, 34(6): 52–59.ZHANG Q, YAN C F, WANG H B, et al. Fault diagnosis expert system of turbine generator based on rule reasoning and case reasoning[J]. Electric Power Science and Engineering, 2018, 34(6): 52–59 (in Chinese). [22] XU X J, YAN X P, SHENG C X, et al. A belief rule-based expert system for fault diagnosis of marine diesel engines[J]. IEEE Transactions on Systems, Man, and Cybernetics: Systems, 2020, 50(2): 656-672. [23] 蔡猛, 张大发, 张宇声, 等. 基于故障树分析的核动力装置实时智能故障诊断专家系统设计[J]. 原子能科学技术, 2010, 44(增刊1): 373–377.CAI M, ZHANG D F, ZHANG Y S, et al. Design of nuclear power plants real-time intelligent fault diagnosis expert system based on FTA[J]. Atomic Energy Science and Technology, 2010, 44(Supp 1): 373–377. [24] 宗群, 李光宇, 郭萌. 基于故障树的电梯故障诊断专家系统设计[J]. 控制工程, 2013, 20(2): 305–308.ZONG Q, LI G Y, GUO M. Design of diagnostic expert system for elevator system based on FTA[J]. Control Engineering of China, 2013, 20(2): 305–308 (in Chinese). [25] 彭华亮, 沈暑龙, 李军, 等. 基于故障树的故障诊断专家系统设计[J]. 控制工程, 2019, 26(3): 584–588. doi: 10.14107/j.cnki.kzgc.160880PENG H L, SHEN S L, LI J, et al. Design of diagnostic expert system for launch vehicles based on FTA[J]. Control Engineering of China, 2019, 26(3): 584–588 (in Chinese). doi: 10.14107/j.cnki.kzgc.160880 [26] 蔡自兴, 约翰·德尔金, 龚涛. 高级专家系统: 原理、设计及应用[M]. 2版. 北京: 科学出版社, 2014: 271−272.CAI Z X, DURKIN J, GONG T. Advanced expert systems: principles, design and applications[M]. 2nd ed. Beijing: Science Press, 2014: 271−272 (in Chinese). [27] 江山青, 李英顺, 张银图. 基于故障树和规则的火控系统故障诊断专家系统[J]. 兵工自动化, 2019, 38(4): 40–44. doi: 10.7690/bgzdh.2019.04.010JIANG S Q, LI Y S, ZHANG Y T. Fault diagnosis expert system for fire control based on fault tree and rule[J]. Ordnance Industry Automation, 2019, 38(4): 40–44 (in Chinese). doi: 10.7690/bgzdh.2019.04.010 [28] 王学杰, 贺国, 陈连树. 基于二叉树的某型船柴油机控制系统故障诊断专家系统[J]. 中国舰船研究, 2009, 4(6): 34–37. doi: 10.3969/j.issn.1673-3185.2009.06.008WANG X J, HE G, CHEN L S. Fault diagnosis expert system for diesel control system on a certain ship based on binary fault tree[J]. Chinese Journal of Ship Research, 2009, 4(6): 34–37 (in Chinese). doi: 10.3969/j.issn.1673-3185.2009.06.008 [29] 维齐利W E. 故障树手册[M]. 疏松桂, 译. 北京: 原子能出版社, 1987: 65−66.VICILI W E, et al. Fault tree manual[M]. SHU S G, trans. Beijing: Atomic Energy Press, 1987: 65−66 (in Chinese). [30] 孙兰会, 成锋, 陆愈实. 关于事故树的结构重要度分析[J]. 科技通报, 2015, 31(4): 248–250. doi: 10.3969/j.issn.1001-7119.2015.04.082SUN L H, CHENG F, LU Y S. Analysis about structural importance of fault tree[J]. Bulletin of Science and Technology, 2015, 31(4): 248–250 (in Chinese). doi: 10.3969/j.issn.1001-7119.2015.04.082 [31] 吴进煌, 孙少华, 曹山根, 等. 基于故障树分析法的引信作用可靠性分析[J]. 海军航空大学学报, 2022, 37(1): 159–164.WU J H, SUN S H, CAO S G, et al. Analysis of fuze reliability based on fault tree analysis[J]. Journal of Naval Aviation University, 2022, 37(1): 159–164 (in Chinese). [32] 国家核安全局. 中国核电厂设备可靠性数据报告[R]. 北京: 国家核安全局, 2022.National Nuclear Safety Administration. Report on reliability data of nuclear power plant equipment in China[R]. Beijing: National Nuclear Safety Administration, 2022 (in Chinese). [33] 罗承昆, 陈云翔, 何桢, 等. 基于故障树分析的航空装备体系结构贡献率评估方法[J]. 国防科技大学学报, 2021, 43(1): 155–162. doi: 10.11887/j.cn.202101020LUO C K, CHEN Y X, HE Z, et al. Evaluation method of aviation equipment's structure contribution rate to system-of-systems based on fault tree analysis[J]. Journal of National University of Defense Technology, 2021, 43(1): 155–162 (in Chinese). doi: 10.11887/j.cn.202101020 [34] 杜雨菲, 吴保国, 陈栋. 基于产生式规则的乔灌木识别推理算法研究[J]. 计算机工程与应用, 2020, 56(5): 242–250. doi: 10.3778/j.issn.1002-8331.1811-0276DU Y F, WU B G, CHEN D. Study of trees and shrubs recognition inference algorithm based on production rules[J]. Computer Engineering and Applications, 2020, 56(5): 242–250 (in Chinese). doi: 10.3778/j.issn.1002-8331.1811-0276 [35] 李雷. 基于产生式规则的变压器故障诊断专家系统[D]. 西安: 西安电子科技大学, 2009.LI L. A fault diagnosis expert system based on production rule for power transformers[D]. Xi'an: Xidian University, 2009 (in Chinese). [36] 杨莎莎. 基于故障树的直流充电桩故障诊断专家系统研究[D]. 北京: 北京交通大学, 2019.YANG S S. Research on DC charging pile fault diagnosis expert system based on fault tree[D]. Beijing: Beijing Jiaotong University, 2019 (in Chinese). [37] 柳炽伟, 景玉军, 郭美华. 基于故障树的DCT故障诊断专家系统的研究[J]. 机床与液压, 2014, 42(1): 169–172,160. doi: 10.3969/j.issn.1001-3881.2014.01.045LIU C W, JING Y J, GUO M H. Research on DCT fault diagnosis expert system based on fault tree[J]. Machine Tool & Hydraulics, 2014, 42(1): 169–172,160 (in Chinese). doi: 10.3969/j.issn.1001-3881.2014.01.045 [38] 鹿智, 杨军. 基于故障树和规则的航天设备诊断系统的实现[J]. 计算机应用, 2015, 35(增刊2): 181–184.LU Z, YANG J. Implementation of aerospace equipment diagnosis system based on fault tree and rule[J]. Journal of Computer Applications, 2015, 35(Supp 2): 181–184. [39] 潘学文, 张福生, 路超. 基于故障树的故障诊断专家系统设计[J]. 煤矿机械, 2021, 42(3): 174–176. doi: 10.13436/j.mkjx.202103054PAN X W, ZHANG F S, LU C. Design of fault diagnosis expert system based on fault tree[J]. Coal Mine Machinery, 2021, 42(3): 174–176 (in Chinese). doi: 10.13436/j.mkjx.202103054 [40] 江山青. 基于规则和案例D-S证据融合的坦克火控系统故障诊断专家系统的研究与应用[D]. 北京: 北京化工大学, 2019.JIANG S Q. Research and application of tank fire control system fault diagnosis expert system based on rule and case D-S evidence fusion[D]. Beijing: Beijing University of Chemical Technology, 2019 (in Chinese). [41] 丁冠军. 基于规则的巡检机器人自动越障专家系统研究[D]. 青岛: 山东科技大学, 2017.DING G J. Research on expert system for automatic obstacle of inspection robot based on rules[D]. Qingdao: Shandong University of Science and Technology, 2017 (in Chinese). [42] 孟显海. 电动汽车充电过程故障智能诊断专家系统研究[D]. 南京: 南京邮电大学, 2021.MENG X H. Research on expert system of intelligent fault diagnosis in the charging process of electric vehicles[D]. Nanjing: Nanjing University of Posts and Telecommunications, 2021 (in Chinese). -
点击查看大图
图(8) / 表(3)
计量
- 文章访问数: 83
- HTML全文浏览量: 3
- PDF下载量: 1
- 被引次数: 0
