Fault diagnosis is very important for condition based maintenance. Recently, deep learning models are introduced to learn hierarchical representations from raw data instead of using hand-crafted features, which exhibit excellent performance. The success of current deep learning lies in: 1) the training (source domain) and testing (target domain) datasets are from the same feature distribution; 2) Enough labeled data with fault information exist. However, because the machine operates under a non-stationary working condition, the trained model built on the source domain can not be directly applied on the target domain. Moreover, since no sufficient labeled or even unlabeled data are available in target domain, collecting the labeled data and building the model from scratch is time-consuming and expensive. Motivated by transfer learning (TL), we present a new fault diagnosis method, which generalizes convolutional neural network (CNN) to TL scenario. Two layers with regard to task-specific features are adapted in a layer-wise way to regularize the parameters of CNN. What’s more, the domain loss is calculated by a linear combination of multiple Gaussian kernels so that the ability of adaptation is enhanced compared to single kernel. Through these two means, the distribution discrepancy is reduced and the transferable features are learned. The proposed method is validated by transfer fault diagnosis experiments. Compared to CNN without domain adaptation and shallow transfer learning methods, the proposed method gets the best performance for fault classification.

Recently, various fault diagnosis methods based on domain adaptation (DA) have been explored to solve the problem of discrepancy between the source and target domains. However, given complex industrial scenarios, DA-based methods usually fail when the working conditions of machines are unseen, i.e., target data are unavailable during model training. In this article, a generic domain-regressive framework for fault diagnosis, namely, adversarial domain-invariant generalization (ADIG), is proposed. ADIG leverages multiple available domain data to exploit domain-invariant knowledge through adversarial learning between the feature extractor and the domain classifier. Simultaneously, the fault classifier generalizes the knowledge from the source-related domain to diagnose the unseen but related target domain signals. Moreover, customized strategies of feature normalization and adaptive weight are proposed to promote diagnosis performance. Comprehensive case studies show that ADIG achieves satisfactory diagnosis accuracy and robustness under unseen conditions, indicating that ADIG is a remarkably potential diagnosis tool for real-case industrial machines.