数据驱动的配电开关设备交互式诊断平台
|
摘要
高效和准确的设备缺陷诊断有助于提升配电网运行可靠性和安全性。受益于信息化建设,配电设备到货抽检、型式试验、在线监测等环节积累了大量检测大数据,奠定了数据挖掘和智能诊断的基础。为了满足配电设备智能运维需求,本文提出了一种大数据驱动的配电开关设备故障交互式诊断方法。利用设备的物理模型、历史故障诊断结果、在线监测数据以及仿真结果,所提方法挖掘故障表征与潜在缺陷间的关联关系,并训练贝叶斯网络,实现设备缺陷推理。进一步,根据试验人员的反馈调整诊断结果,提出设备故障的交互式诊断方法,通过动态修正推理模型,提升检测准确性。实际案例测试说明所提方法的有效性。
Efficient and accurate device fault diagnosis helps to improve the reliability and safety of the distribution network. Benefiting from the development of information technology, a large amount of data has been accumulated in sampling inspection, type test, and online monitoring, laying the foundation of data mining and intelligent diagnosis. To meet the requirement of intelligent operating and maintenance of the distribution network, a data-driven and interactive diagnosis method of distribution switches is proposed. Using the physical model, historical fault diagnosis results, on-line monitoring data and simulation results, the proposed method excavates the relationship between fault representation and potential defects and trains Bayesian network to realize equipment defect reasoning. Furthermore, the diagnosis results are adjusted according to the feedback of the test personnel, and an interactive diagnosis method of equipment fault is proposed, which improves the detection accuracy by dynamically modifying the reasoning model. Practical case tests illustrate the effectiveness of the proposed method.
Efficient and accurate device fault diagnosis helps to improve the reliability and safety of the distribution network. Benefiting from the development of information technology, a large amount of data has been accumulated in sampling inspection, type test, and online monitoring, laying the foundation of data mining and intelligent diagnosis. To meet the requirement of intelligent operating and maintenance of the distribution network, a data-driven and interactive diagnosis method of distribution switches is proposed. Using the physical model, historical fault diagnosis results, on-line monitoring data and simulation results, the proposed method excavates the relationship between fault representation and potential defects and trains Bayesian network to realize equipment defect reasoning. Furthermore, the diagnosis results are adjusted according to the feedback of the test personnel, and an interactive diagnosis method of equipment fault is proposed, which improves the detection accuracy by dynamically modifying the reasoning model. Practical case tests illustrate the effectiveness of the proposed method.
引文
[1] Jadid S B, Jeyasurya B, Khaparde S A. Power system fault diagnosis expert system using PROLOG[A]. Fourth IEEE Region 10 International Conference TENCON[C]. Bombay, India, 1989. 778-781.
[2] Park Young Moon, Kim Gwang-Won, Sohn Jin-Man. A logic based expert system (LBES) for fault diagnosis of power system[J]. IEEE Transactions on Power Systems, 1997, 12(1): 363-369.
[3] Cardoso G, Rolim J G, Zurn H H. Application of neural net-work modules to electric power system fault section estimation[J]. IEEE Transactions on Power Delivery, 2004, 19(3): 1034-1041.
[4] Wen F S, Chang C S. Probabilistic approach for fault-section estimation in power systems based on a refined genetic algorithm[J]. IEE Proceedings - Generation, Transmission and Distribution, 1997, 144(2): 160-168.
[5] Jong C G, Leu S S. Bayesian-network-based hydro-power fault diagnosis system development by fault tree transformation[J]. Journal of Marine Science & Technology, 2013, 21(4): 367-379.
[6] Lo C H, Wong Y K, Rad A B. Bayesian network for fault diagnosis[A]. 2003 European Control Conference (ECC) [C]. Cambridge, UK, 2003. 1381-1386.
[7] Dasseni E, Verykios V S, Elmagarmid A K, et al. Hiding association rules by using confidence and support[A]. International Workshop on Information Hiding[C]. 2001. 369-383.
[8] Li H, Wang Y, Zhang D, et al. Pfp: Parallel fp-growth for query recommendation[A]. ACM Conference on Recommender Systems[C]. 2008. 107-114.
[9] Chi Y, Wang H, Yu P S, et al. Moment: Maintaining closed frequent itemsets over a stream sliding window[A]. Fourth IEEE International Conference on Data Mining (ICDM’04) [C]. Brighton, UK, 2004. 59-66.
[10] Cheng J, Greiner R, Kelly J, et al. Learning Bayesian networks from data: An information-theory based approach[J]. Artificial Intelligence, 2002, 137(1-2): 43-90.
[11] Aliferis C F, Tsamardinos I, Statnikov A. HITON: A novel Markov Blanket algorithm for optimal variable selection[A]. AMIA 2003 Symposium Proceedings[C]. 2003. 21-25.
[2] Park Young Moon, Kim Gwang-Won, Sohn Jin-Man. A logic based expert system (LBES) for fault diagnosis of power system[J]. IEEE Transactions on Power Systems, 1997, 12(1): 363-369.
[3] Cardoso G, Rolim J G, Zurn H H. Application of neural net-work modules to electric power system fault section estimation[J]. IEEE Transactions on Power Delivery, 2004, 19(3): 1034-1041.
[4] Wen F S, Chang C S. Probabilistic approach for fault-section estimation in power systems based on a refined genetic algorithm[J]. IEE Proceedings - Generation, Transmission and Distribution, 1997, 144(2): 160-168.
[5] Jong C G, Leu S S. Bayesian-network-based hydro-power fault diagnosis system development by fault tree transformation[J]. Journal of Marine Science & Technology, 2013, 21(4): 367-379.
[6] Lo C H, Wong Y K, Rad A B. Bayesian network for fault diagnosis[A]. 2003 European Control Conference (ECC) [C]. Cambridge, UK, 2003. 1381-1386.
[7] Dasseni E, Verykios V S, Elmagarmid A K, et al. Hiding association rules by using confidence and support[A]. International Workshop on Information Hiding[C]. 2001. 369-383.
[8] Li H, Wang Y, Zhang D, et al. Pfp: Parallel fp-growth for query recommendation[A]. ACM Conference on Recommender Systems[C]. 2008. 107-114.
[9] Chi Y, Wang H, Yu P S, et al. Moment: Maintaining closed frequent itemsets over a stream sliding window[A]. Fourth IEEE International Conference on Data Mining (ICDM’04) [C]. Brighton, UK, 2004. 59-66.
[10] Cheng J, Greiner R, Kelly J, et al. Learning Bayesian networks from data: An information-theory based approach[J]. Artificial Intelligence, 2002, 137(1-2): 43-90.
[11] Aliferis C F, Tsamardinos I, Statnikov A. HITON: A novel Markov Blanket algorithm for optimal variable selection[A]. AMIA 2003 Symposium Proceedings[C]. 2003. 21-25.