Research on Fault Diagnosis of Track Circuit Based on Optimied Variational Mode Decomposition

Hz phase sensitive track circuit is a common type of track circuit widely used in electrified railway lines to detect the operating status of trains. However, due to factors such as complex circuits, environmental changes, and equipment aging, fault detection and diagnosis have become major challenges in ensuring the normal operation of track circuits. In view of this, taking the 25 Hz phase sensitive track circuit as the research object, this paper proposes a fault diagnosis method based on SBOA, VMD, and BiGRU, denoted as SBOA-VMD-BiGRU. This method optimizes VMD for feature extraction through SBOA to select the optimal parameters. After optimization, extract the optimal IMF component for each sample and calculate it. After organizing the dataset according to the above process, the BiGRU classification model is used to achieve intelligent diagnosis of track circuits. The experimental results show that this method can effectively improve the accuracy and robustness of fault diagnosis, providing an intelligent and accurate solution for fault management of <tex xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">$\mathbf{2 5 H z}$</tex> phase sensitive track circuits.