Journal of Northeastern University(Natural Science) ›› 2021, Vol. 42 ›› Issue (4): 494-501.DOI: 10.12068/j.issn.1005-3026.2021.04.006

• Information & Control • Previous Articles     Next Articles

Error Control of Delay Prediction in Railway Sections Under State Space

ZHANG Lu-kai, FENG Xue-song   

  1. School of Traffic and Transportation, Beijing Jiaotong University, Beijing 100044, China.
  • Revised:2020-10-27 Accepted:2020-10-27 Published:2021-04-15
  • Contact: FENG Xue-song
  • About author:-
  • Supported by:
    -

Abstract: Considering the cascading effect of information between sections, an analysis framework of train delay prediction error control in state space was proposed. The fitting regression method was used to process the operating statistics to determine the ordinary differential equations. According to the modern control theory, a linear quadratic regulator was designed to reduce the error, and it provides reasonable support for the proposed method through deduction. The dual-temperature simulated annealing algorithm was designed to obtain the optimized parameters of the regulator, and the simulation calculation was realized in combination with the SIMULINK environment. Numerical experiment results show that compared with the traditional Bayesian network prediction method, the proposed state space analysis method has different degrees of improvement on various error performance indicators, it has obvious advantages in calculation indicators such as average error value, data demand and computing time.

Key words: transportation information engineering and control; operating section; delay prediction; error control; parameter optimization; dual-temperature simulated annealing algorithm

CLC Number: