AR-MED共振特征增强的风电齿轮箱故障诊断  

AR-MED Enhanced Resonance Features for Fault Diagnosis of Wind Turbine Gearbox

作　　者：孙抗[1] 史晓玉 赵来军[1] 杨明[1] SUN Kang;SHI Xiaoyu;ZHAO Laijun;YANG Ming(School of Electrical Engineering and Automation,Henan Polytechnic University,Jiaozuo 454000,China)

机构地区：[1]河南理工大学电气工程与自动化学院,焦作454000

出　　处：《组合机床与自动化加工技术》2024年第8期163-167,174,共6页Modular Machine Tool & Automatic Manufacturing Technique

基　　金：国家自然科学基金项目(U1804143);河南省科技攻关计划项目(202102210092);河南省高校青年骨干教师项目(2021GGJS056)。

摘　　要：针对风电齿轮箱故障时脉冲成分往往淹没在其他频率分量中,早期故障特征难以有效提取的问题,提出一种自回归最小熵解卷积(AR-MED)共振特征增强的风电齿轮箱故障诊断方法,并结合一维卷积神经网络(1DCNN),实现齿轮箱高精度故障诊断。首先,使用共振稀疏分解算法(RSSD)将振动信号分解成含有噪声和谐波成分的高共振分量和含有故障冲击成分的低共振分量;其次,对低共振分量使用自回归最小熵解卷积运算,增强低共振分量中微弱的周期性冲击成分;最后,构建自回归最小熵解卷积共振特征增强的1DCNN模型,将分解得到的谐波分量和周期性冲击分量进行特征融合以及有针对的训练和分类。实验结果表明,与现有故障诊断模型相比,所提方法在提取风电齿轮箱的故障特征信息以及提高故障诊断精度方面具有有效性和优越性。Addressing the challenge of that the pulse component is often submerged in other frequency components during the failure of the wind turbine gearbox,it is difficult to effectively extract the early fault characteristics.This paper proposed an autoregressive minimum entropy deconvolution(AR-MED)method for enhancing resonance features in wind turbine gearbox fault diagnosis and combined it with 1-dimension 1DCNN to achieve high accuracy fault diagnosis.Firstly,the Resonance Sparse decomposition algorithm was utilized to decompose the vibration signals into a high resonance component containing noise and harmonic components,and a low resonance component containing fault impulse components.Secondly,the autoregressive minimum entropy deconvolution was employed to enhance the weak impulse features in the low resonance component,thus further enhancing the periodic impulse components of the gearbox.Finally,a feature enhanced CNN was constructed to fuse the decomposed harmonic component and periodic impulse component for feature integration,targeted training,and classification.The experiment results demonstrated the effectiveness and superiority of the proposed method in extracting fault characteristic information and improving fault diagnosis accuracy in wind turbine gearbox systems compared to existing fault diagnosis models.

关 键 词：共振稀疏分解 自回归最小熵解卷积 特征增强 一维卷积神经网络 风电齿轮箱 

分 类 号：TH165[机械工程—机械制造及自动化] TG659[金属学及工艺—金属切削加工及机床]