基于EB-1D-TP编码算法的风电机组滚动轴承故障特征提取研究

Research on Fault Feature Extraction of Wind Turbine Rolling Bearings Based on EB-1D-TP Encoding Algorithm

滚动轴承运行状态检测是保证整个风电机组安全、稳定运行的关键,但由于风电机组所处的运行工况多变,难以准确识别滚动轴承的故障类型。为解决传统风电机组滚动轴承故障诊断需要大量采集信号、存在严重噪声干扰等问题,提出一种基于增强二进制1D-TP编码算法的故障特征提取方法。通过引入去“零”增强处理,提高不同状态下滚动轴承振动信号之间的区分度,并改进传统1D-TP编码算法,融合高、低两种模式,充分保留信号特征。最后通过对信号点和像素点之间相关性差异的分析,重新设定信号编码顺序。实验结果证明:该方法能够有效提高故障诊断系统对轴承振动信号特征的提取效果,增强不同特征之间的区分度,故障特征提取精度提升25%,且在提取效率上也表现出明显优势。

The detection of the operating status of rolling bearings is the key to ensuring the safe and stable operation of the entire wind turbine.However,due to the variable operating conditions of the wind turbine,it is difficult to accurately identify the fault type of rolling bearings.A fault feature extraction method based on enhanced binary 1D-TP encoding algorithm is proposed to solve the problems of traditional wind turbine rolling bearing fault diagnosis that requires a large amount of signal acquisition and severe noise interference.By introducing"zero"enhancement processing,the differentiation between vibration signals of rolling bearings in different states is improved,and the traditional 1D-TP encoding algorithm is improved to fuse high and low modes,fully preserving signal features.Finally,by analyzing the correlation differences between signal points and pixel points,the signal encoding order is reset.The experimental results show that this method can effectively improve the extraction effect of bearing vibration signal features in fault diagnosis systems,enhance the differentiation between different features,improve the accuracy of fault feature extraction by 25%,and also show significant advantages in extraction efficiency.