电子测量与仪器学报

赵运基,危思成,许孝卓.基于时频滤波器和偏移注意神经网络的轴承故障诊断[J].电子测量与仪器学报,2024,38(11):48-57

基于时频滤波器和偏移注意神经网络的轴承故障诊断

Bearing fault diagnosis based on time-frequency filterandoffset attention neural network

DOI：

英文关键词:fault diagnosis feature offset distinctive feature time-frequency filter offset attention

基金项目:国家自然科学基金(61973105，61573130，52177039)、河南省科技攻关项目(242102221034，232102240096)资助

作者	单位
赵运基	河南理工大学电气工程与自动化学院焦作454003
危思成	河南理工大学电气工程与自动化学院焦作454003
许孝卓	河南理工大学电气工程与自动化学院焦作454003

Author	Institution
Zhao Yunji	School of Electrical Engineering and Automation, Henan Polytechnic University, Jiaozuo 454003, China
Wei Sicheng	School of Electrical Engineering and Automation, Henan Polytechnic University, Jiaozuo 454003, China
Xu Xiaozhuo	School of Electrical Engineering and Automation, Henan Polytechnic University, Jiaozuo 454003, China

摘要点击次数: 394

全文下载次数: 1316

中文摘要:

针对轴承故障数据分布不一致导致特征偏移、标志性特征提取困难的问题,提出一种基于时频滤波器和偏移注意神经网络的轴承故障诊断方法,从离线和在线两个方向分别对故障信号进行处理。在离线部分提出时频滤波器,分别从时域和频域提取故障信号的标志性特征;提出兼顾全局特征和局部特征的空间采样方法。在线部分提出偏移注意神经网络,与自注意相比,偏移注意更有利于偏移特征的提取,从而降低数据分布不一致造成的影响。在西安交通大学和凯斯西储大学的轴承数据集上进行实验,达到了100%的精度,证明了所提方法能够很好的提取故障信号的标志性特征,并且能够有效抑制特征偏移对故障识别精度的影响。而在凯斯西储大学轴承数据集上的对比实验则证明了所提方法的优越性。除此之外,还在工业现场采集的燃气轮机主轴承数据集上进行了实验,结果证明所提方法具有实际应用意义。

英文摘要:

To address the inconsistent bearing fault data distribution that leads to the difficulty of feature offset and distinctive feature extraction, a bearing fault diagnosis method based on time-frequency filter and offset attention neural network is proposed, which processes the fault signal from offline and online parts. In the offline part, a time-frequency filter is proposed to extract the distinctive features from time domain and frequency domain; A spatial sampling method considering both global and local features is proposed. In the online part, an offset attention neural network is proposed. Compared with self attention, offset attention is more conducive to the extraction of offset features, so as to reduce the impact caused by inconsistent data distribution. Experiments on the bearing datasets of Xi′an Jiaotong University (XJTU) and Case Western Reserve University (CWRU) have achieved 100% accuracy, which proves that the proposed method can efficiently extract the distinctive features of fault signals, and effectively suppress the influence of feature offset. The comparative experiment on the bearing dataset of CWRU proves the superiority of the proposed method. In addition, experiments are also carried out on the dataset of gas turbine main bearing collected in the industrial field, and the results show that the proposed method has practical significance.

查看全文查看/发表评论下载PDF阅读器