雷杨博,朱智勤,柴 毅,齐观秋,安翼尧,徐 鹏.基于联合分布偏移差异的跨域滚动轴承 故障诊断方法[J].电子测量与仪器学报,2022,36(10):146-156
基于联合分布偏移差异的跨域滚动轴承 故障诊断方法
Cross-domain fault diagnosis method of rolling bearings basedon joint distribution offset difference
  
DOI:
中文关键词:  跨域故障诊断  域自适应  分布对齐  卷积神经网络
英文关键词:cross-domain fault diagnosis  domain adaptation  discrepancy alignment  CNN
基金项目:国家自然科学基金(61803061, 61906026)、重庆市教委重庆市高校创新群体“成渝双城经济圈建设”科技创新项目(KJCXZD2020028)、重庆市技术创新与应用发展专项(cstc2019jscx zdztzx0068)项目资助
作者单位
雷杨博 1. 重庆邮电大学自动化学院 
朱智勤 1. 重庆邮电大学自动化学院 
柴 毅 2. 重庆大学自动化学院 
齐观秋 3. 布法罗州立学院计算机信息系统系 
安翼尧 2. 重庆大学自动化学院 
徐 鹏 1. 重庆邮电大学自动化学院 
AuthorInstitution
Lei Yangbo 1. School of Automation, Chongqing University of Posts and Telecommunications 
Zhu Zhiqin 1. School of Automation, Chongqing University of Posts and Telecommunications 
Chai Yi 2. School of Automation, Chongqing University 
Qi Guanqiu 3. Computer Information Systems Department,Buffalo State College Buffalo 
An Yiyao 2. School of Automation, Chongqing University 
Xu Peng 1. School of Automation, Chongqing University of Posts and Telecommunications 
摘要点击次数: 682
全文下载次数: 738
中文摘要:
      现有的无监督域自适应故障诊断方法大多只基于单一域信号实现,提取的故障信息不够全面。 只注重实现源域和目标 域特征的边缘分布对齐,忽略了样本的条件分布差异,限制了诊断精度的提升。 为克服以上问题,提出一种基于联合分布偏移 差异(joint distribution offset difference, JDOD)的跨域滚动轴承故障诊断方法。 使用两个结构一致的卷积神经网络(CNN)分别 提取信号的时域与频域特征,获取更完整的故障信息。 提出联合分布偏移差异,实现不同域特征的边缘分布对齐和条件分布对 齐。 在两个多工况轴承数据集上与多种先进方法展开对比实验,取得了 99%以上的平均诊断精度。 实验结果表明联合分布偏 移差异有效提升了跨域故障精度。
英文摘要:
      Most of the existing unsupervised domain adaptive fault diagnosis methods are only implemented based on a single domain signal, and the extracted fault information is not comprehensive enough. Only focus on realizing the edge distribution alignment of source and target domain features, ignoring the conditional distribution differences of samples, which limits the improvement of diagnostic accuracy. To overcome the above problems, a cross-domain fault diagnosis method of rolling bearings based on joint distribution offset differences (JDOD) is proposed. Two structurally consistent CNNs are used to extract the time-domain and frequency-domain features of the signal respectively to obtain more complete fault information. Joint distribution offset difference is proposed to realize edge distribution alignment and conditional distribution alignment of different domain features. Comparing experiments with various advanced methods on two multi-condition bearing datasets, the average diagnostic accuracy of more than 99% is obtained. The experimental results show that the joint distribution offset difference effectively improves the cross-domain fault diagnostic accuracy.
查看全文  查看/发表评论  下载PDF阅读器