蔡利斯熵
支持向量机
特征提取
方位(导航)
风力发电
涡轮机
模式识别(心理学)
熵(时间箭头)
人工智能
计算机科学
断层(地质)
控制理论(社会学)
工程类
地质学
机械工程
物理
控制(管理)
量子力学
地震学
电气工程
作者
Zhibo Gao,Caiping Xi,Yunfan Yang
摘要
Due to the harsh environment in which wind turbines work for long periods of time, the internal drive train is prone to fatigue failure. Rolling bearings are an important component within wind turbines, so it is essential to implement condition detection and fault diagnosis of rolling bearings. This paper proposes a fault signal feature extraction method based on VMD and Tsallis entropy. Firstly, the bearing signals of four different states are decomposed using VMD decomposition, and the IMF components generated after the decomposition are quantitatively characterized using Tsallis entropy, and the features with stability and differentiation are selected to form the feature vector of the fault and input to a support vector machine for classification. The experimental results show that the proposed method can distinguish different fault bearing signals and has some improvement in classification effect compared with KNN, fine tree and intermediate tree classifiers. The proposed method presents a new idea for the fault diagnosis of rolling bearings in wind turbines.
科研通智能强力驱动
Strongly Powered by AbleSci AI