RTS-LCSS: A New Method for Real-Time Monitoring of Pantograph Structure

As an important device for high-speed railway (HSR) to obtain electrical energy from outside, the structure of pantograph will directly affect the safety and stability of HSR operation. The current pantograph structure detection algorithm has a low accuracy rate, which cannot effectively cope with various complex scenarios and external disturbances during the actual operation of HSR and is difficult to achieve real-time detection of the pantograph structure. In order to solve the current problems in pantograph structure detection, the rigid target subregion longest common sub-sequence (RTS-LCSS) is proposed, which is a new method for real-time pantograph structure detection. This paper realizes the positioning of pantograph region by you only look once (YOLO) V7, then the pantograph characteristic curve is fitted according to the pantograph feature points, and finally compares the fitted pantograph characteristic curve with the normal pantograph characteristic curve to achieve the accurate evaluation of the pantograph structure. Meanwhile, in order to improve the accuracy of YOLO, this paper adopts deep convolution generative adversarial nets (DCGAN) to expand the training samples in conjunction with the real situation of HSR. The method proposed in this paper can realize the real-time detection of pantograph structure in addition to the specific localization of structural abnormal regions. The experimental results show that the proposed method has higher robustness and stronger environmental adaptation. The algorithm accuracy and real-time performance meet the actual operation requirements of HSR, and it continues to function well under the influence of complex scenes and external environment interference.