Intelligent fault diagnosis method for rolling bearings based on adaptive feature mode decomposition and TCN-BiGRU-Attention

Abstract

In complex working environments and noisy conditions, the vibration signals of bearings are highly non-stationary, and the fault characteristics are easily masked by noise, making it difficult to effectively identify the faults. Moreover, existing methods are relatively sensitive to parameter and working condition changes and lack diagnostic stability. To address this issue, a smart fault diagnosis method based on the Time Convolution Network - Bidirectional Gated Recurrent Unit - Attention Model (TCN-BiGRU-Attention) was proposed. This method uses the Newton-Raphson optimization algorithm to optimize the parameters of the feature mode decomposition, extracts the feature modes, and combines them with the TCN-BiGRU-Attention deep temporal sequence model to achieve multi-scale feature modes and key temporal discrimination. The experiments were conducted based on two public datasets - Case Western Reserve University and XJTU-SY, with each group of experiments repeated at least 10 times under the same initial conditions. At the same time, ablation experiments and performance comparison experiments with other advanced methods were carried out. The results show that in the fault identification task, the accuracy of this research method reached 96.32%, which is higher than 89.15% of one-dimensional convolutional neural networks, 91.45% of bidirectional long short-term memory neural networks, and 92.84% of time convolutional networks. In conclusion, this method can achieve high-precision and stable fault diagnosis for rolling bearings, providing an effective intelligent diagnosis solution for engineering applications.