基于支持向量机的风轮不平衡故障诊断方法研究  

STUDY ON ROTOR IMBALANCE FAULT IDENTIFICATION METHOD BASED ON MULTI-KERNEL LEARNING SUPPORT VECTOR MACHINE

作　　者：曹沂风 Cao Yifeng(International Education Institute,North China Electric Power University,Baoding 071003,China)

机构地区：[1]华北电力大学国际教育学院,保定071003

出　　处：《太阳能学报》2024年第8期613-620,共8页Acta Energiae Solaris Sinica

摘　　要：针对风电机组风轮不平衡的识别与检测问题,提出一种基于多核融合支持向量机的风轮不平衡识别方法。首先,分析风轮不平衡的影响,提出一种基于变分模态分解(VMD)的信号分解与重构方法;其次,提出基于模糊熵的风轮不平衡特征提取方法,以高斯核函数作为模糊函数,该方法具有较好的噪声鲁棒性和较低的数据长度依赖性;再次,提出基于多核融合支持向量机的风轮不平衡识别方法,融合不同特征和尺度的核函数组成核函数库,并选取最优核函数;最后,在不同湍流强度的仿真中建立交叉验证数据库对该方法进行验证,识别准确率在98%以上,证明该方法能有效识别风轮不平衡。For the problem of identification and detection of rotor imbalance,an identification method of rotor imbalance based on multikernel learning support vector machine is proposed.Firstly,the influence of rotor imbalance is analyzed,and a signal decomposition and reconstruction method based on VMD is proposed.Secondly,a feature extraction method based on fuzzy entropy is proposed,which uses Gaussian kernel function as fuzzy function.The method has better noise robustness and lower data length dependence.Thirdly,an identification method based on multi-kernel learning support vector machine is proposed.Kernel functions of different features and scales are fused to form the kernel function library,and the optimal kernel function is selected.Finally,a cross-validation database is established to verify the proposed method in the simulation of different turbulence intensities.The accuracy is above 98%.The results show that the proposed method can identify rotor imbalance effectively.

关 键 词：风电机组 状态监测 机器学习 风轮不平衡 模糊熵 支持向量机 

分 类 号：TK81[动力工程及工程热物理—流体机械及工程]