Bayesian network analysis of unplanned shutdown of generating units

doi:10.3969/j.issn.2097-0706.2022.03.012

Abstract

Abstract:

To ensure the safe and stable operation of generator sets,it is necessary to analyze the causes of their failures intensively.Based on the analysis report on unplanned shutdowns of a power plant,the influencing factors of the unplanned outage events are summarized,and the Bayesian network diagram for predicting the unplanned outages is made.According to Bayesian network analysis on the unplanned shutdowns of the power plant,the causal inference analysis on the impacts of various factors on unplanned shutdowns is carried out.The results show that when the aging status evaluation of equipment is insufficient,the probability of outage events caused by equipment failure will be significantly increased.Placing equipment in an unfavorable environment for a long time will boost the probability of aging faults.Through Bayesian network analysis,the impact probabilities of various influencing factors on unplanned outage events are clarified,which provides reference for energy big data analysis of power generation enterprises and will improve the operation reliability and safety of units.

Key words: unplanned shutdown, generator set, Bayesian network, causal inference, energy big data

CLC Number:

TK01

MA Dongliang, CHEN Hui, ZHU Yanhai, JIANG Yuan. Bayesian network analysis of unplanned shutdown of generating units[J]. Integrated Intelligent Energy, 2022, 44(3): 77-82.

Figures/Tables 7

Table 1

Fig.1

Fig.2

Fig.3

Fig.4

Fig.5

Fig.6

References 19

[1]	夏克晁, 滕卫明, 尹峰. 2017年全国发电厂热控系统故障统计分析与建议[J]. 中国电力, 2018, 51(12):132-138.
	XIA Kechao, TENG Weiming, YIN Feng. Statistics and analysis of the thermal control system faults in the power plants nationwide throughout 2017[J]. Electric Power, 2018, 51(12):132-138.
[2]	张学延, 屈杰, 何国安, 等. 大型汽轮发电机组非典型故障分析[J]. 中国电力, 2020, 53(12):284-292,300.
	ZHANG Xueyan, QU Jie, HE Guoan, et al. Case analysis of several atypical faults of large turbo-generator set[J]. Electric Power, 2020, 53(12):284-292,300.
[3]	于彦宝, 周佺. 大型汽轮发电机组EH系统的典型故障分析及处理[J]. 应用能源技术, 2007(1):18-20.
	YU Yanbao, ZHOU Quan. Analysis and treatment of typical failure of EH system of large-scale steam turbine power generation set[J]. Applied Energy Technology, 2007(1):18-20.
[4]	杨勤, 张震伟, 杨茉, 等. 基于故障预警系统的燃煤发电设备状态检修[J]. 中国电力, 2019, 52(3):109-114.
	YANG Qin, ZHANG Zhenwei, YANG Mo, et al. Conditional maintenance of coal-fired power generation equipment based on early fault warning system[J]. Electric Power, 2019, 52(3):109-114.
[5]	李建锋, 周宏, 吕俊复. 中国1 000 MW等级火力发电机组可靠性分析[J]. 中国电力, 2017, 50(11):1-7.
	LI Jianfeng, ZHOU Hong, LYU Junfu. Reliability analysis of 1 000 MW thermal power generating units in China[J]. Electric Power, 2017, 50(11):1-7.
[6]	胡杰, 唐静, 谢仕义, 等. 基于大数据技术的电厂设备状态评估和预警应用研究[J]. 华电技术, 2020, 42(2):1-6,11.
	HU Jie, TANG Jing, XIE Shiyi, et al. State assessment and early warning application for power plant equipment based on big data technology[J]. Huadian Technology, 2020, 42(2):1-6,11.
[7]	王凤, 周铁梁. 基于大数据的大型装备全生命周期管理研究[J]. 华电技术, 2020, 42(2):12-16.
	WANG Feng, ZHOU Tieliang. Explore the value of data for lifecycle management of large equipment[J]. Huadian Technology, 2020, 42(2):12-16.
[8]	王忠杰, 文乐, 杨新民. 大数据在智能化电厂中的应用研究与展望[J]. 中国电力, 2019, 52(3):133-139.
	WANG Zhongjie, WEN Le, YANG Xinmin. Applied research and prospect of big data in power plant intelligence[J]. Electric Power, 2019, 52(3):133-139.
[9]	张筱辰, 朱金大, 杨冬梅, 等. 基于t-SNE流形学习与快速聚类算法的光伏逆变器故障预测技术[J]. 中国电力, 2020, 53(6):41-47.
	ZHANG Xiaochen, ZHU Jinda, YANG Dongmei, et al. Photovoltaic inverter fault prediction technology based on t-SNE manifold learning and fast clustering algorithm[J]. Electric Power, 2020, 53(6):41-47.
[10]	贾志军, 白德龙, 宋燕杰, 等. 基于KPCA算法的电厂设备在线故障诊断研究[J]. 华电技术, 2021, 43(8):48-53.
	JIA Zhijun, BAI Delong, SONG Yanjie, et al. Research on on-line fault diagnosis and treatment of power plant equipment based on KPCA[J]. Huadian Technology, 2021, 43(8):48-53.
[11]	彭维珂, 聂椿明, 陈衡, 等. 基于智能算法的空冷火电机组负荷预测研究[J]. 华电技术, 2021, 43(3):57-64.
	PENG WeikeNIE ChunmingCHEN Heng, et al. Study on load forecasting for air cooling thermal power units based on intelligent algorithm[J]. Huadian Technology, 2021, 43(3):57-64.
[12]	YUAN C F, CUI H, MA S M, et al. Analysis method for causal factors in emergency processes of fire accidents for oil-gas storage and transportation based on ISM and MBN[J/OL]. Journal of Loss Prevention in the Process Industries,2019.(2019-09-16)[2021-06-02]. https://doi.org/10.1016/j.jlp.2019.103964.
[13]	QAZI A, SIMSEKLER M C E. Assessment of humanitarian crises and disaster risk exposure using data-driven Bayesian networks[J/OL]. International Journal of Disaster Risk Reduction,2021.(2020-11-04)[2021-06-02]. https://doi.org/10.1016/j.ijdrr.2020.101938.
[14]	HUANG W C, KOU X Y, ZHANG Y, et al. Operational failure analysis of high-speed electric multiple units:A bayesian network-K2 algorithm-expectation maximization approach[J/OL]. Reliability Engineering and System Safety, 2020.(2020-09-29)[2021-06-02]. https://doi.org/10.1016/j.ress.2020.107250Get rights and content.
[15]	JAFARI M J, POUYAKIAN M, KHANTEYMOORI A, et al. Reliability evaluation of fire alarm systems using dynamic Bayesian networks and fuzzy fault tree analysis[J/OL]. Journal of Loss Prevention in the Process Industries,2020.(2020-07-17)[2021-06-02]. https://doi.org/10.1016/j.jlp.2020.104229.
[16]	吴琳, 杨萌, 吴烜, 等. 基于贝叶斯网络算法的发电系统可靠性评估[J]. 通信电源技术, 2019, 36(5):5-8,11.
	WU Lin, YANG Meng, WU Xuan, et al. Reliability evaluation of generation system based on Bayesian network algorithms[J]. Telecom Power Technology, 2019, 36(5):5-8,11.
[17]	崔家文, 张春茂, 张宏彪, 等. 光伏发电系统可靠性分析的贝叶斯网络模型[J]. 分布式能源, 2016, 1(1):47-51.
	CUI Jiawen, ZHANG Chunmao, ZHANG Hongbiao, et al. Bayesian network model for photvoltatic power plant reliability analysis[J]. Distributed Energy, 2016, 1(1):47-51.
[18]	MARSLAND S. Machine learning：An algorithmic perspective（second edition）[M]. Boca Raton： Chapman and Hall/CRC. 2019:19-22, 226-233.
[19]	WANG Y, WONG C W H, CHEUNG T K Y, et al. How influential factors affect aviation networks:A Bayesian network analysis[J/OL]. Journal of Air Transport Management,2021.(2020-12-10)[2021-06-02]. https://doi.org/10.1016/j.jairtraman.2020.101995.

因素	变量	发生次数	取值	百分比/%
外部因素	外部环境恶劣	115	1	22.12
	基建安装工艺差	139	1	26.73
	结构设计不合理	95	1	18.27
	煤质变化	24	1	4.62
人为因素	管理不到位	386	1	74.23
	检修不当	407	1	78.27
	运行操作不当	185	1	35.58
	老化评估不足	76	1	14.62
	风险评估不足	330	1	63.46
设备因素	产品质量差	300	1	57.69
	冗余设备失效	48	1	9.23
	设备故障	410	1	78.85
	参数异常	183	1	35.19
逻辑因素	保护逻辑不完善	96	1	18.46
	自动调节不完善	39	1	7.50
	报警不完善	77	1	14.81
	保护信号误发	81	1	15.58