Inverse physics–informed neural networks for digital twin–based bearing fault diagnosis under imbalanced samples

In actual engineering, insufficient bearing samples for each fault category presents a substantial obstacle to the intelligent fault diagnosis of rolling bearings. To address sample imbalance, this work explores a novel bearing fault data–generation approach based on digital twin technique. First, an inverse physics–informed neural network (PINN) is built to recognize dynamic model parameters by embedding a bearing dynamic model into a neural network. In this network, a boundary loss is designed to quickly determine the approximate ranges of parameters that can accelerate network convergence, and a true value loss is constructed for the assessment of spectral discrepancy between simulated and actual data. Then, using an inverse PINN, a bearing fault dynamic model, and real vibration data, we propose a digital twin–based fault data–generation method for producing high-quality bearing fault samples under multiple working conditions and fault modes. Finally, the developed approach is applied to generate bearing fault vibration samples under a specific working condition. The samples are used for training the diagnostic network, thus solving the issue of sample imbalance. The comparison results of several experiments suggest that the developed data-generation method effectively improves the precision of cross-working-condition bearing fault diagnosis and surpasses multiple state-of-the-art methods.