A Variable-Scale Attention Mechanism Guided Time-Frequency Feature Fusion Transfer Learning Method for Bearing Fault Diagnosis in an Annealing Kiln Roller System

Featured Application The roller bearing and the through shaft bearing are the rotating and load-bearing components of the annealing kiln roller system, which operate at different locations and under different working conditions. Their health status is significant for maintaining the stable operation of the glass production line. In order to improve the efficiency of bearing condition monitoring, this paper proposes a variable-scale attention mechanism guided time-frequency feature fusion transfer learning method, which is used for bearing fault diagnoses at different installation locations in the annealing kiln roller system. It effectively achieves the intelligent diagnosis of roller bearing and through shaft bearing faults in the annealing kiln roller system.Abstract Effective real-time health condition monitoring of the roller table and through shaft bearings in the annealing kiln roller system of glass production lines is crucial for maintaining their operational safety and stability for the quality and production efficiency of glass products. However, the collected vibration signal of the roller bearing system is affected by the low rotating frequency and strong mechanical background noise, which shows the width impact interval and non-stationary multi-component characteristics. Moreover, the distribution characteristics of monitoring data and probability of fault occurrence of the roller bearing and through shaft bearing improve the difficulty of the fault diagnosis and condition monitoring of the annealing kiln roller system, as well as the reliance on professional experience and prior knowledge. Therefore, this paper proposes a variable-scale attention mechanism guided time-frequency feature fusion transfer learning method for a bearing fault diagnosis at different installation positions in an annealing kiln roller system. Firstly, the instinct time decomposition method and the Gini-Kurtosis composed index are used to decompose and reconstruct the signal for noise reduction, wavelet transform with the Morlet basic function is used to extract the time-frequency features, and histogram equalization is introduced to reform the time-frequency map for the blur and implicit time-frequency features. Secondly, a variable-scale attention mechanism guided time-frequency feature fusion framework is established to extract multiscale time-dependency features from the time-frequency representation for the distinguished fault diagnosis of roller table bearings. Then, for through shaft bearings, the vibration signal of the roller table bearing is used as the source domain and the signal of the through shaft bearing is used as the target domain, based on the feature fusion framework and the multi-kernel maximum mean differences metric function, and the transfer diagnosis method is proposed to reduce the distribution differences and extract the across-domain invariant feature to diagnose the through shaft bearing fault speed under different working conditions, using a small sample. Finally, the effectiveness of the proposed method is verified based on the vibration signal from the experimental platform and the roller bearing system of the glass production line. Results show that the proposed method can effectively diagnose roller table and through shaft bearings' fault information in the annealing kiln roller system.