| 5 | 0 | 688 |
| 下载次数 | 被引频次 | 阅读次数 |
针对可逆式抽水蓄能机组提出了一种故障诊断方法。利用机组故障和征兆间的属性关系构建因果图网络，通过引入隐变量节点和概率赋值，建立服从Leaky Noisy-Or假设的基于结构性因果模型（Structural Causal Model，SCM）的故障诊断模型；提出基于孪生网络的反事实推理诊断策略，根据故障模型的拓扑结构，结合孪生网络构建与约简，进行反事实推理，计算故障备选集的充分因和必要因两个指标，以此为依据对所有候选故障进行排序，得到明确的故障原因；最后以某可逆式抽水蓄能机组转子热弯曲故障为例，详细介绍基于因果图网络的故障诊断模型建立过程和基于孪生网络的反事实推理诊断方法，诊断结果与机组实际故障原因一致，证明了本文故障诊断方法的有效性。
Abstract：This paper proposes a fault diagnosis method for reversible pumped storage units. Firstly, a causal diagram network is constructed using the attribute relationship between unit faults and symptoms. By introducing hidden variable nodes and probability assignments, a fault diagnosis model based on structural causal model(SCM) is established that follows the Leaky Noisy-Or assumption. Then, a counterfactual reasoning diagnosis strategy based on twin network is proposed. According to the topology structure of the fault model, combined with the construction and reduction of twin network, counterfactual reasoning is carried out to calculate the sufficient and necessary factors of the fault candidate set. All candidate faults are sorted to obtain a clear fault causes. Finally, taking the rotor thermal bending fault of a reversible pumped storage unit as an example, the process of establishing a fault diagnosis model based on causal graph network and the counterfactual reasoning diagnosis method based on twin network are introduced in detail. The diagnosis results are consistent with the actual fault cause of the unit, therefore proving the effectiveness of the fault diagnosis method proposed in this paper.
[1] 鹿优，鹿存鹏，徐伟，等.含抽水蓄能电站的多能互补微网系统设计与研究[J].山东电力技术，2023，50（5）：34-40. LU You, LU Cunpeng, XU Wei, et al. Design and Research of Multi-Energy Complementary Microgrid System with Pumped Storage Power Station[J]. Shandong Electric Power, 2023, 50(5): 34-40.
[2] 景小兵，姜里运，许闫.某抽水蓄能电站机组运行稳定性分析[J]. 东北电力技术，2024，45（2）：50-53，57. JING Xiaobing, JIANG Liyun, XU Yan. Analysis on Unit Operation Stability of Pumped Storage Hydropower Station[J]. Northeast Electric Power Technology, 2024, 45(2): 50-53, 57.
[3] 温春雪，赵天赐，王鹏，等.计及配电网韧性的储能设备配置规划方法[J].内蒙古电力技术，2023，41（1）：15-20. WEN Chunxue, ZHAO Tianci, WANG Peng, et al. Energy Storage Device Configuration Planning Method Considering Distribution Network Toughness[J]. Inner Mongolia Electric Power, 2023, 41(1): 15-20.
[4] 张雪超，程璐，房文轩，等.抽水蓄能电站水轮机转轮叶片失效分析及防护[J].山东电力技术，2020，47（6）：78-80. ZHANG Xuechao, CHENG Lu, FANG Wenxuan, et al. Failure Analysis and Protection of Turbine Runner Blade in Pumped Storage Power Station[J]. Shandong Electric Power, 2020, 47(6): 78-80.
[5] 赵卫强，严单单，许贝贝，等.基于振动特性曲线的抽水蓄能机组状态监测优化方法[J].水电与抽水蓄能，2023，9（5）：47-52，60. ZHAO Weiqiang, YAN Dandan, XU Beibei, et al. Optimization Method for State Monitoring of Pumped Storage Units Based on Vibration Characteristic Curve[J]. Hydropower and Pumped Storage, 2023, 9(5): 47-52, 60.
[6] 钱文华.水电站机组技术供水改造的探讨[J].云南电力技术，2019， 47（4）：87-90. QIAN Wenhua. Discussion on Technical Water Supply Reformation of Hydropower Station Units[J]. Yunnan Electric Power, 2019, 47(4): 87-90.
[7] 任家朋.抽水蓄能机组振动故障诊断与劣化趋势预测研究[D].武汉：华中科技大学，2022.
[8] 李晓波，贾斌，云杰，等.300 MW可逆式抽水蓄能水轮机组摆度大原因分析与处理[J].电气应用，2023，42（5）：72-75. LI Xiaobo, JIA Bin, YUN Jie, et al. Cause analysis and treatment of large hydroturbine swing on 300 MW reversible pumped - storage unit[J]. Electrotechnical Application, 2023, 42(5): 72-75.
[9] 杨增杰，曾令龙，谭尚仁，等.基于深度学习的水轮发电机定子绕组绝缘故障诊断[J].电力大数据，2022，25（1）：26-34. YANG Zengjie, ZENG Linglong, TAN Shangren, et al. Isolation Fault Diagnosis of Water Turbine Generator Stator Winding Based on Deep Learning[J]. Power Systems and Big Data, 2022, 25(1): 26-34.
[10] 赵明，梁俊宇，李孟阳，等.基于主元分析的水轮机组导轴承异常诊断方法研究[J].云南电力技术，2019，47（6）：24-27. ZHAO Ming, LIANG Junyu, LI Mengyang, et al. Research on Abnormal Diagnostic Method of Hydroturbine Guide Bearing Based on Principal Component Analysis[J]. Yunnan Electric Power, 2019, 47(6): 24-27.
[11] 徐浩，聂靓靓，黄俊恺.抽水蓄能电厂发电电动机励磁绕组匝间短路故障仿真分析[J].内蒙古电力技术，2019，37（6）：30-35. XU Hao, NIE Liangliang, HUANG Junkai. Analysis on Inter - Turn Short Circuit of Excitation Winding for Generator- Motor in Pumped - Storage Power Plant[J]. Inner Mongolia Electric Power, 2019, 37(6): 30-35.
[12] Pearl J. Causality: Models, Reasoning and Inference[M]. Cambridge: Cambridge University Press, 2009.
[13] Pearl J. The seven tools of causal inference with reflections on machine learning[J]. Communications of Association for Computing Machinery, 2018, 1(1): 1-6.
[14] 王凯，李玄玄.基于贝叶斯网络和关联规则的航电系统故障诊断[J].计算机应用与软件，2023，40（3）：45-51，148. WANG Kai, LI Xuanxuan. Avionics System Fault Diagnosis Based on Bayesian Network and Association Rule[J]. Computer Applications and Software, 2023, 40(3): 45-51, 148.
[15] 孙少楠，李博宇，聂相田.基于贝叶斯网络的水轮机故障诊断研究[J].水电能源科学，2023，11（3）：190-194. SUN Shaonan, LI Boyu, NIE Xiangtian. Research on Fault Diagnosis of Hydraulic Turbine Based on Bavesian Network[J]. Water Resources and Power, 2023, 11(3): 190-194.
[16] Pearl J. Causal inference in statistics: An overview[J]. Statistics Surveys, 2009(3): 96-146.
基本信息:
DOI：10.19929/j.cnki.nmgdljs.2025.0035
引用信息:
[1]李晓波1,张利慧1,云杰1,等.可逆式抽水蓄能机组故障诊断方法及应用[J],2025,43(3):54-61.DOI:10.19929/j.cnki.nmgdljs.2025.0035.
基金信息:
内蒙古电力（集团）有限责任公司内蒙古电力科学研究院分公司科技项目“抽水蓄能机组全工况水力激振分析与对策研究”（2023-ZC-10）
2024-01-05
2024
2024-04-16
2024
1