Dynamic Relative Advantage-Driven Multi-Fault Synergistic Diagnosis Method for Motors under Imbalanced Missing Data Rates

Missing data handling is vital for multi-sensor information fusion fault diagnosis of motors to prevent the accuracy decay or even model failure, and some promising results have been gained in several current studies. These studies, however, have the following limitations: 1) effective supervision is neglected for missing data across different fault types and 2) imbalance in missing rates among fault types results in inadequate learning during model training. To overcome the above limitations, this paper proposes a dynamic relative advantage-driven multi-fault synergistic diagnosis method to accomplish accurate fault diagnosis of motors under imbalanced missing data rates. Firstly, a cross-fault-type generalized synergistic diagnostic strategy is established based on variational information bottleneck theory, which is able to ensure sufficient supervision in handling missing data. Then, a dynamic relative advantage assessment technique is designed to reduce diagnostic accuracy decay caused by imbalanced missing data rates. The proposed method is validated using multi-sensor data from motor fault simulation experiments, and experimental results demonstrate its effectiveness and superiority in improving diagnostic accuracy and generalization under imbalanced missing data rates.