Discriminant Analysis-Guided Alignment Network for Multimachine Fault Collaborative Learning and Diagnosis

In general, the safety and efficiency of thermal power plants require the collaboration of multiple coal mills. However, running data from different coal mills will introduce significant inconsistent distribution, resulting in suboptimal performance or even the unavailability of conventional diagnosis methods. To this end, this article presents an advantageous discriminant analysis-aided collaborative alignment network (DA-CAN) for cross-device fault diagnosis. First, the contribution of each feature in distinguishing source and target domains is determined by assigning the adaptive updated weight, which is helpful to keep the gradient direction more stable in domain transferring. To avoid destroying the inherent data structure of different domains, we design multiple complementary class-wise discrepancy metrics to enhance the domain consistency during the domain adaption process. After that, a joint training loss term with an adjustment factor is introduced to transform the private data of individual coal mills into collective representations and smooth the conditional and marginal distribution discrepancy collaboratively. Finally, the experimental results of the real-world coal mill group indicate that the DA-CAN is more effective and practical than the state-of-the-art transfer learning methods regarding multimachine fault diagnosis.