A novel wind turbine fault diagnosis method based on intergral extension load mean decomposition multiscale entropy and least squares support vector machine

作者：Gao, Q. W.; Liu, W. Y.^*; Tang, B. P.; Li, G. J.

来源：Renewable Energy, 2018, 116: 169-175.

DOI：10.1016/j.renene.2017.09.061

• Wind turbine
• Integral extension load mean decomposition
• Multiscale entropy
• Feature extraction
• Fault diagnosis

Aimed at the non-stationary and nonlinear characteristics of wind turbine vibration signals, a novel fault diagnosis method based on integral extension load mean decomposition multiscale entropy and least squares support vector machine was proposed in this paper. At first, the raw vibration signals monitored from the wind turbine were divided into groups for the pre-process. Then the signals were processed in groups with integral extension load mean decomposition method and Product Functions were obtained. The characteristic parameters were achieved by multiscale entropy method of processing main Product Functions, which described the signal characteristics. Finally, the characteristic parameters were entered into least squares support vector machine, and least squares support vector machine was trained. Next the trained least squares support vector machine was tested and the pattern was classified. The method can not only extract characteristic parameters effectively, but also classify the fault type accurately. The effectiveness and availability of the proposed method were proved in the wind turbine measured data experiment.

• 出版日期2018-2
• 单位重庆大学; 中国科学院; 中国科学院深圳先进技术研究院; 机械传动国家重点实验室