Adversarial domain adaptation with classifier alignment for cross-domain intelligent fault diagnosis of multiple source domains

Abstract

Recently, most cross-domain fault diagnosis methods focus on single source domain adaptation. However, it is usually possible to obtain multiple labeled source domains in real industrial scenarios. The question of how to use multiple source domains to extract common domain-invariant features and obtain satisfactory diagnosis results is a difficult one. This paper proposes a novel adversarial domain adaptation with a classifier alignment method (ADACL) to address the issue of multiple source domain adaptation. The main elements of ADACL consist of a universal feature extractor, multiple classifiers and a domain discriminator. The parameters of the main elements are simultaneously updated via a cross-entropy loss, a domain distribution alignment loss and a domain classifier alignment loss. Under the framework of multiple loss cooperative learning, not only is the distribution discrepancy among all domains minimized, but so is the prediction discrepancy of target domain data among all classifiers. Two experimental cases on two source domains and three source domains verify that the ADACL can remarkably enhance the cross-domain diagnostic performance under diverse operating conditions. In addition, the diagnostic performance of different methods is extensively evaluated under noisy environments with a different signal-to-noise ratio.