Enhanced Discriminate Feature Learning Deep Residual CNN for Multitask Bearing Fault Diagnosis With Information Fusion

Deep learning-based diagnosis methods currently face some challenges and open problems. First, domain knowledge of fault modes and operating conditions are not integrated in most existing approaches, which results in low diagnosis accuracy and training efficiency. Second, existing methods treat all features with indiscriminate attention, which causes unnecessary computation and even false diagnosis results in some cases. Third, multitask diagnosis becomes more important for health maintenance. To address these challenges, this article proposes a deep residual convolutional neural network with an enhanced discriminate feature learning capability and information fusion for multitask bearing fault diagnosis. In the proposed approach, domain knowledge is integrated with monitoring data to build the information map. Two attention modules are introduced to enhance the discriminate feature learning ability. Two classifiers are employed for multitask diagnosis. Experiments on two bearing cases demonstrate that the proposed approach has significant improvements in terms of diagnostic accuracy and training efficiency.