基于优化的VMD融合信息熵和FA_PNN的风电机组齿轮箱故障诊断

针对风电机组齿轮箱在故障信号处理、特征提取和故障诊断存在的问题,提出一种基于优化的变分模态分解(VMD)融合信息熵和萤火虫优化的概率神经网络(FAPNN)的风电机组齿轮箱故障诊断方法。首先利用皮尔逊相关系数法来确定VMD的分解数量和惩罚因子,并利用VMD分解齿轮箱振动信号获取多个固有模态分量,在此基础上融合时域、频域及时频域等信号故障特征熵,最后用FAPNN网络进行故障识别分类,仿真结果验证了所提出算法在风电机组齿轮箱早期故障诊断研究中的有效性和可行性。

FAULT DIAGNOSIS OF WIND TURBINE GEARBOX BASED ON OPTIMIZED VMD FUSION INFORMATION ENTROPY AND FA_PNN

Aiming at the problems of fault signal processing,feature extraction and fault diagnosis of wind turbine gearbox. an improved variational mode decomposition(VMD)fusion information entropy and firefly optimization probabilistic neural network(FA_PNN)are proposed. Wind turbine gearbox fault diagnosis method. Firstly,the Pearson correlation coefficient method is used to determine the optimal decomposition number and penalty factor of VMD,and then the VMD decomposition of the gearbox vibration signal is used to obtain several modal components,and from the time domain,frequency domain and time-frequency domain. To extract the information entropy characteristics of the fault signal,and finally use the probabilistic neural network optimized by the firefly algorithm to classify the fault. The simulation results verify the effectiveness and feasibility of the method.