|
|
Integrated condition monitoring and fault diagnosis technology for wind turbine drive-train |
REN Yan1,2*, ZHANG Kai3 |
1. School of Electric Power, North China Institute of Water Conservancy and Hydroelectric University, Zhengzhou, Henan 450045, China; 2. Hunan Provincial Key Laboratory of Renewable Energy Electric-Technology, Changsha University of Science & Technology, Changsha, Hunan, 410114, China; 3.Agricultural Science and Technology Exhibition Center of Henan Province, Zhengzhou, Henan 450002, China |
|
|
Abstract To monitor and diagnose structure and operation process of wind turbine drive-train, a single physical simulation or single empirical method is unable to achieve condition monitoring and fault diagnosis of the entire operation. In the paper, these two methods were combined together. A wind turbine drive-train online condition monitoring system was used to conduct data acquiring and pre-process. FFT, FNN and expert system were adopted to carry out diagnosis of various faults, and decision fusion technology was used to optimize the diagnosed results. As a result, an integrated online condition monitoring and fault diagnosis system was built for the wind turbine drive-train. The system was combined with CMS and SCADA to carry out condition monitoring and fault diagnosis for wind turbines. Based on this system, the fault diagnosis of main shaft bearings of a wind turbine in a wind farm was performed, and the vibration amplitude, failure time, fault location and fault degree were analyzed. According to the diagnosed results, the expert advices were provided. The system is very versatile, adaptable, fault-tolerant and easy to implement. Additionally, the system has improved the capabilities of analysis, reasoning, optimization and remote diagnostic, and a higher level of intelligence has been achieved.
|
Received: 03 June 2016
|
|
|
|
[1]CHOY F K, POLYSHCHUK V, ZAKRAJSEK J J, et al. Analysis of the effects of surface pitting and wear on the vibration of a gear transmission system[J]. Tribology international, 1996, 29(1): 77-83.[2]CHAARI F, FAKHFAKH T, HADDAR M. Dynamic analysis of a planetary gear failure caused by tooth pitting and cracking[J]. Journal of failure analysis & prevention, 2006, 6(2):73-78.[3]DING H, KAHRAMAN A. Interactions between nonlinear spur gear dynamics and surface wear[J]. Journal of sound & vibration, 2007, 307(3):662-679.[4]蒋维. 基于灰色粗糙集理论的风电机组传动链智能故障诊断方法[J]. 电网与清洁能源, 2012, 28(12):79-83. JIANG Wei. An intelligent diagnosis method based on grey rough set theory for wind turbine driving chain[J].Power system and clean energy,2012.28(12):79-83.(in Chinese)[5]曹婷, 郑源. 风力机故障诊断神经网络特征参数确定方法[J]. 排灌机械工程学报, 2014, 32(3):247-251. CAO Ting,ZHENG Yuan. Method for determining neural network characteristic parameters in fault diagnosis system for wind turbines[J]. Journal of drainage and irrigation machinery engineering,2014,32(3): 247-251.(in Chinese)[6]龙泉, 刘永前, 杨勇平. 基于粒子群优化BP神经网络的风电机组齿轮箱故障诊断方法[J]. 太阳能学报, 2012, 33(1):120-125. LONG Quan, LIU Yongqian, YANG Yongping. Fault diagnosis method of wind turbine gearbox based on BP neural network trained by trained by particle swarm optimization algorithm[J]. Acta energiae solaris sinica,2012,33(1): 120-125.(in Chinese)[7]黄永东. 如何选择风力发电机组的CMS系统[J]. 东方汽轮机, 2012(1):1-8. HUANG Yongdong. How to choose the CMS of wind turbine[J]. DongFang turbine,2012(1): 1-8.(in Chinese)[8]KOULOCHERIS D, GYPARAKIS G, STATHIS A, et al. Vibration signals and condition monitoring for wind turbines[J]. Engineering, 2013, 5(12):948-955.[9]吴万荣, 史建, 徐智. 双目立体视觉技术在潜孔钻机钻孔定位中的应用[J]. 江苏大学学报(自然科学版), 2015, 36(1):65-69. WU Wanrong, SHI Jian, XU Zhi. Application of binocular stereo vision in down-the-hole drill position[J]. Journal of Jiangsu University(natural science edition),2015,36(1): 65-69.(in Chinese)[10]赵光明, 陈金玉, 温敬平,等. 火电厂综合评选FGD技术专家系统的研究[J]. 江苏大学学报(自然科学版), 2003, 24(2):38-42. ZHAO Guangming, CHEN Jinyu, WEN Jingping, et al. Research on expert system for choosing FGD technology in coal-fired plants[J]. Journal of Jiangsu University(natural science edition),2003,24(2): 38-42.(in Chinese)[11]YANG D, LI H, HU Y, et al. Vibration condition monitoring system for wind turbine bearings based on noise suppression with multi-point data fusion[J]. Renewable energy, 2016, 92:104-116.[12]任岩,毕亚雄,王德宽,等.一种基于振动和油液的风电机组在线状态监测与健康评估系统:CN 204788494 U[P]. 2015-07-22. |
|
|
|