IFDS: An Intelligent Fault Diagnosis System With Multisource Unsupervised Domain Adaptation for Different Working Conditions
Danya Xu, Yibin Li, Yan Song, Lei Jia, Yanjun Liu
Abstract
Intelligent fault diagnosis is an important subject of mechanical system maintenance. Domain adaptation is a method to solve the problem that the model trained on training set (source domain) is not suitable for the test set (target domain) due to different working conditions in fault diagnosis. In industrial scenarios, there may be multiple source domains. For this reason, we proposed an Intelligent Fault Diagnosis System (IFDS) with multi-source unsupervised domain adaptive network that adapts to single or multiple source domains. The proposed method considers the differences between sources, uses source domain data and a small amount of unlabeled target domain data to mine the feature information contained in the data. IFDS uses a feature extractor to learn the feature representations, constructs a domain discriminator for each source domain, and learns domain invariant features through adversarial training to diagnosis target domain faults. The validity of the method in fault diagnosis is verified by various transfer tasks of two public fault-bearing datasets.