A novel two-stage heterogeneous transfer learning framework for the estimation of the remaining useful life of industrial components
提出两阶段异构迁移学习方法，先通过域适应模型估计目标域退化指标，再估计剩余使用寿命，在电池数据上比现有方法准确率提升4%-7%。
It is a practical situation that the data used to develop data-driven prognostic models are collected from run-to-failure experiments performed in laboratory (source domain), where the component degradation is measured, whereas the data to which the model is applied are acquired during in-field operation (target domain), where operating conditions are different and degradation cannot be directly measured. This problem cannot be effectively tackled using traditional deep learning approaches; in this paper, an innovative Heterogeneous Transfer Learning (HTL) method is developed for the estimation of the Remaining Useful Life (RUL) of degrading components. The missing information about the degradation of the target component is estimated by developing a first-stage Domain Adaptation (DA) model, which learns the mapping between the signals measured in both domains and the degradation indicator. Then, the RUL of the target component is estimated by developing a second-stage DA model, which leverages the prognostic knowledge in the labeled source domain data. Both DA models use an encoder based on a Long-Short Term Memory (LSTM) neural network for extracting features, and the Maximum Mean Discrepancy (MMD) metric for reducing the domain discrepancy. The proposed HTL method is validated considering the data of the Aramis Data Challenge and of the MIT and Stanford University battery benchmark. The proposed method achieves more satisfactory performances than other DA state-of-the-art methods, with an increase of the Cumulative Relative Accuracy (CRA) of 4% and 7% in the two application cases, respectively. • A prognostic framework for RUL estimation under different operating conditions between training and test data. • A two-stage transfer learning model for RUL estimation across feature spaces of different dimensionality. • Enables fault prognostics without requiring run-to-failure data from in-field applications. • Achieves superior RUL prediction accuracy over other state-of-the-art transfer learning methods.