Multi-model train state estimation based on multi-sensor parallel fusion filtering

• Published in: Accident analysis and prevention 2022-02, Vol.165, p.106506-106506, Article 106506
• Main Authors: Jin, Yongze, Xie, Guo, Li, Yankai, Shang, Linyu, Hei, Xinhong, Ji, Wenjiang, Han, Ning, Wang, Bo
• Format: Article
• Language: English
• Subjects: Accidents, Traffic; Algorithms; Computer Simulation; Gaussian sum filter; High-speed train; Humans; Particle filter; Sensor fusion; State estimation
• ISSN: 0001-4575; 1879-2057
• DOI: 10.1016/j.aap.2021.106506

•An improved train multi-mode model is established based on the analysis of operation mechanism.•A distributed fusion filter composed of the Gaussian sum filter and particle filter is proposed.•The real-time train mode discrimination based on the voting mechanism is proposed. Accurately determining a train's state is essential for passenger safety, operation efficiency, and maintenance. However, the actual operation state of a train is composed of a variety of modes and is disturbed by several known or unknown factors, for which an accurate estimator is required. Hence, in this paper, a train multi-mode model considering the actual operation environment is established, and a train state estimation method based on multi-sensor parallel fusion filter is proposed. In the parallel fusion filter, the current mode of train is determined by the proposed sliding window error and voting mechanism, and the global filter are constituted by the local filters, which are fused by linear-weighted summation. The simulation results demonstrate the effectiveness of our method in estimating the train's state. It is worth noting that even if monitoring data are missing or are abnormal, the state estimation accuracy of the proposed technique still meets the requirements of a real system, and the effectiveness and robustness of the method can be verified.