A weak prior embedding-based method for transfer fault diagnosis of rolling bearing.

• A powerful domain adaption method is proposed for bearing fault diagnosis. • This method deals with the feature misalignment problem in difficult transfer tasks. • Unknown target labels are reliably estimated by weak prior embedding. • The effectiveness and superiority of this method have been verified by challenging experiments. Transfer learning extends the application scope of deep intelligent fault diagnosis models. However, when operation conditions are significantly varied, existing transfer learning methods may encounter a bottleneck. The unsupervised methods will mismatch features, while supervised methods are constrained by insufficient target labeled instances. A weak prior embedding-based domain adaption network (WPEDAN) is proposed to resolve this problem. Specifically, the cluster ability of source data pre-trained network to target data is emphasized and enhanced directly and indirectly so as to obtain discriminative feature clusters. The target prior template samples are embedded and automatically delivered to the most relevant feature clusters, so the class information of target instances can be estimated based on similarity and supervised training on target is following. Moreover, an improved conditional maximum mean discrepancy (ICMMD) is developed to further align conditional distribution. Experiments on two challenging bearing datasets show that proposed method achieves more than 99% diagnosis accuracy in all tasks, and is significantly ahead of the comparison methods in complex transfer tasks. [ABSTRACT FROM AUTHOR]