国家重点研发计划专项项目; 国家自然科学基金-河南联合基金; 河南省科技攻关项目; 河南师范大学面上项目培育项目
Henan Normal University
不同工况下轴承退化数据分布不一致，导致深度学习等方法对剩余寿命预测效果有限，而已有迁移学习预测方法未能充分挖掘不同工况退化序列的内在趋势性。本文提出了一种基于深度时序特征迁移的轴承剩余寿命预测方法。首先，提出一种深度时序特征融合的健康指标构建模型，利用时间卷积网络挖掘退化趋势的内在时序特征，得到源域多轴承的健康指标；其次，提出一种最小化序列相似度的领域自适应算法，利用源域健康指标作为退化趋势元信息，选取目标域与源域之间的公共敏感特征；最后，采用支持向量机构建预测模型。在IEEE PHM Challenge 2012轴承全寿命数据集上进行实验，结果表明，本文方法构建的健康指标可更有效地反映退化趋势，同时明显提升剩余寿命预测的准确度。
Due to the inconsistent distribution of bearing degradation data under different working conditions, the prediction performance of remaining useful life by using deep learning and other techniques would be limited. Moreover, most of existing transfer learning-based prediction method fails to fully exploit the inherent degradation trend under different working conditions. To solve these problems, a new prediction method of bearing remaining useful life is proposed based on deep temporal feature transfer. First, a health indicator (HI) construction model based on deep temporal features is proposed. The model uses the temporal convolutional network (TCN) to exploit inherent temporal features from the degradation trend of multiple bearings, and builds HI sequence of the bearings in source domain. Second, a new domain adaptation algorithm with minimizing sequence similarity is proposed. The HI sequence of source domain is used as meta-information of degradation trend for selecting common representative features between target domain and source domain. Finally, support vector machine is used to construct the prediction model. Experiments on the IEEE PHM Challenge 2012 bearing whole-life dataset have shown that the HI constructed by this method can effectively reflect the degradation trend, and significantly improve the prediction accuracy of remaining life.