摘要
针对现有水轮发电机组状态检修研究大多侧重于故障诊断结果,而忽略了为检修人员提供良好的辅助维修决策的问题。文章引入贝叶斯网络,设计了一种基于传感器诊断策略与贝叶斯网络模型的状态检修方法。该方法采用传感器诊断策略对传感器监测信号进行误报警、冗余报警与潜在故障判断后,通过贝叶斯网络模型对传故障进行有效诊断,并以输出的故障可能性与故障的危险性配合进行风险评估,通过风险评估结果为检修人员对检修过程中故障排查的顺序提供合理的参考。最后,通过精准度分析、受试者工作特征(ROC)曲线、校准曲线进行模型验证,结果表明,系统运行准确度达到80%。
A Bayesian network model is adopted in the maintenance of hydroelectric generating sets to provide maintenance personnel with a better tool in decision making of auxiliary maintenance. Based on the sensor diagnosis strategy and a Bayesian network model, we design a condition-based maintenance method that uses the strategy to handle the cases of false alarm, redundant alarm, and potential fault diagnosis on sensor monitoring signals. We apply the Bayesian network model to effective diagnosis of transmission faults, and carry out risk assessment via combining fault probability and fault risk. The results of risk assessment provide reasonable information for the maintenance personnel to set up a procedure for failure checking during maintenance. Finally, we use accuracy analysis to analyze the method and its practical operation, and verify the calibration curve by comparing the modeled results with field data, showing that the operating accuracy of the system is 80%.
引文
[1]徐洪泉,陆力,潘罗平,等.“仿医疗”的水电机组故障诊断系统[J].水力发电学报,2014,33(3):306-310.XU Hongquan,LU Li,PAN Luoping,et al.Fault diagnosis system of hydropower unit based on imitating medical diagnosis[J].Journal of Hydroelectric Engineering,2014,33(3):306-310.(in Chinese)
[2]付文龙,周建中,李超顺,等.基于模糊K近邻支持向量数据描述的水电机组振动故障诊断研究[J].中国电机工程学报,2014,34(32):5788-5795.FU Wenlong,ZHOU Jianzhong,LI Chaoshun,et al.Vibrant fault diagnosis for hydro-electric generating unit based on support vector data description improved with fuzzy K nearest neighbor[J].Proceedings of the CSEE,2014,34(32):5788-5795.(in Chinese)
[3]谢国财,李朝晖.基于Community Intelligence的水电机组融合监测方法[J].电力自动化设备,2013,33(1):153-159.XIE Guocai,LI Zhaohui.Integrated monitoring of hydroelectric generators based on Community Intelligence[J].Electric Powcr Automation Equipment,2013,33(1):153-159.(in Chinese)
[4]潘罗平,桂中华.水轮发电机组状态监测技术[M].广州:华南理工大学出版社,2008.PAN Luoping,GUI Zhonghua.Condition monitoring technology of hydraulic-turbine and generator units[M].Guangzhou:South China University of Technology Press,2008.(in Chinese)
[5]钱新博.水力发电机组故障预测与状态维修策略研究[D].武汉:华中科技大学,2014.QIAN Xingbo.Research on the prognostics and condition-based maintenance policy for the hydroelectric generating unit[D].Wuhan:Huazhong University of Science and Technology,2014.(in Chinese)
[6]于晓东,潘罗平,安学利.基于VMD和排列熵的水轮机压力脉动信号去噪算法[J].水力发电学报,2017,36(8):78-85.YU Xiaodong,PAN Luoping,AN Xueli.Denoising algorithm of pressure fluctuation signals of hydraulic turbines based on VMD and permutation entropy[J].Journal of Hydroelectric Engineering,2017,36(8):78-85.(in Chinese)
[7]李辉,焦毛,杨晓萍,等.基于EEMD和SOM神经网络的水电机组故障诊断[J].水力发电学报,2017,36(7):83-91.LI Hui,JIAO Mao,YANG Xiaoping,et al.Fault diagnosis of hydroelectric sets based on EEMD and SOM neural networks[J].Journal of Hydroelectric Engineering,2017,36(7):83-91.(in Chinese)
[8]郭鹏程,孙龙刚,李辉,等.基于多重分形谱和改进BP神经网络的水电机组振动故障诊断研究[J].水力发电学报,2014,33(3):299-305.CUO Pengcheng,SUN Longgang,LI Hui,et al.Vibration fault diagnosis of hydropower unit based on multi-fractal spectrum and improved BP neural network[J].ournal of Hydroelectric Engineering,2014,33(3):299-305.(in Chinese)
[9]李辉,李欣同,贾嵘,等.基于经验模态分解和支持向量机的水电机组振动故障诊断[J].水力发电学报,2016,35(12):105-111.LI Hui,LI Xintong,JIA Rong,et al.Fault diagnosis of vibration for hydropower units based on empirical mode decomposition and support vector machine[J].Journal of Hydroelectric Engineering,2016,35(12):105-111.(in Chinese)
[10]潘罗平,周叶,唐澍,等.水电机组故障诊断技术的发展现状与展望[C]//第十七次中国水电设备学术讨论会.2009.PAN Luoping,ZHOU Ye,TAN Peng,et al.Development status and Prospect of fault diagnosis technology for hydropower units[C]//17th Symposium on Hydropower equipment in China.2009.(in Chinese)
[11]葛新峰,徐广文,周叶,等.水电机组故障智能诊断研究综述[C]//第十七次中国水电设备学术讨论会.2009.GE Xingfeng,XU Guangwen,ZHOU Ye,et al.Review on intelligent fault diagnosis of hydropower units[C]//17th Symposium on Hydropower Equipment in China.2009.
[12]胡勇健,肖志怀,周云飞,等.基于贝叶斯网络Noisy Or模型的水电机组故障诊断研究[J].水力发电学报,2015,34(6):197-203.HU Yongjian,XIAO Zhihuai,ZHOU Yunfei,et al.Study of hydropower units fault diagnosis based on Bayesian network Noisy Or model[J].Journal of Hydroelectric Engineering,2015,34(6):197-203.(in Chinese)
[13]Jun H B,Kim D.A Bayesian network-based approach for fault analysis[J].Expert Systems with Applications,2017,81(4):332-348.
[14]Cai Z,Zhang L,Hu J,et al.Comprehensive alarm information processing technology with application in petrochemical plant[J].Journal of Loss Prevention in the Process Industries,2015,38:101-113.
[15]李娟莉,杨兆建.提升机故障诊断不确定性推理方法[J].煤炭学报,2014,39(3):586-592.LI Juanli,YANG Zhaojian.An uncertain reasoning method of hoist fault diagnosis[J].Journal of China Coal Society,2014,39(3):586-592.(in Chinese)
[16]李硕豪,张军.贝叶斯网络结构学习综述[J].计算机应用研究,2015,32(3):641-646.LI Shuohao,ZHANG Jun.Review of Bayesian networks structure learning[J].Application Research of Computers,2015,32(3):641-646.(in Chinese)
[17]Selak L,Butala P,Sluga A.Condition monitoring and fault diagnostics for hydropower plants[J].Computers in Industry,2014,65(6):924-936.
[18]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.
[19]Cook J A.ROC curves and nonrandom data[J].Pattern Recognition Letters,2017,85(2):35-41.
[20]Jurado J M,Alcázar A,Mu?izvalencia R,et al.Some practical considerations for linearity assessment of calibration curves as function of concentration levels according to the fitness-for-purpose approach[J].Talanta,2017,172(3):221-231.
