A Fault Recognition System for Gearboxes of Wind Turbines

1st International Conference on Frontiers of Materials Synthesis and Processing

材料科学;化学

Yang, Zhiling^1 ; Huang, Haiyue^1 ; Yin, Zidong^2

School of Energy Power and Mechanical Engineering, North China Electric Power University, Beijing

102206, China^1

China Datang New Energy Co. LTD, Beijing

100052, China^2

关键词: Acceleration sensors;    Fault recognition;    Glowworm swarm optimizations;    Least squares support vector regression machines;    Operational data;    Optimization algorithms;    Supervisory Control and Data Acquisition (SCADA) systems;    Wind turbines gearboxes;   

Others  :  https://iopscience.iop.org/article/10.1088/1757-899X/274/1/012002/pdf
DOI  :  10.1088/1757-899X/274/1/012002

学科分类：材料科学（综合）

来源: IOP

【 摘 要 】

Costs of maintenance and loss of power generation caused by the faults of wind turbines gearboxes are the main components of operation costs for a wind farm. Therefore, the technology of condition monitoring and fault recognition for wind turbines gearboxes is becoming a hot topic. A condition monitoring and fault recognition system (CMFRS) is presented for CBM of wind turbines gearboxes in this paper. The vibration signals from acceleration sensors at different locations of gearbox and the data from supervisory control and data acquisition (SCADA) system are collected to CMFRS. Then the feature extraction and optimization algorithm is applied to these operational data. Furthermore, to recognize the fault of gearboxes, the GSO-LSSVR algorithm is proposed, combining the least squares support vector regression machine (LSSVR) with the Glowworm Swarm Optimization (GSO) algorithm. Finally, the results show that the fault recognition system used in this paper has a high rate for identifying three states of wind turbines' gears; besides, the combination of date features can affect the identifying rate and the selection optimization algorithm presented in this paper can get a pretty good date feature subset for the fault recognition.