Digital twin station system, job scheduling method based on system and application

Abstract

The invention discloses a digital twin station system, a job scheduling method based on the system and application. The job scheduling method comprises: inputting processed static data and dynamic data of a physical station into a trained prediction model to obtain job prediction parameters; inputting the operation prediction parameters into a digital twin station simulation model, and performing operation process simulation to obtain simulation operation indexes; and making a scheduling decision based on the simulation operation index. According to the invention, a digital twin station system in which a physical station and a virtual station cooperatively interact is constructed, real-time connection and dynamic feedback between a physical system and a digital system are formed, and efficient and accurate prediction, simulation and decision scheduling can be carried out on station operation.

Description

technical field [0001] The present invention relates to the technical field of digital twins. Background technique [0002] With the increase of railway passenger travel volume and the continuous increase of the number of passenger trains along the whole railway, the workload of receiving and departing trains at stations and related technical operations continues to increase, resulting in frequent operation delays. How to dispatch station technical operations in real time to resolve conflicts and ensure the smooth completion of operations has become an urgent development technology for large railway passenger stations. One of the ideas to solve this technical problem is to establish a station operation simulation system and make decisions based on the simulation system. [0003] Among them, in the aspect of establishing station operation simulation system, it is often realized by discrete simulation in the prior art. The design and operation of the passenger dedicated line...

AI Technical Summary

Problems solved by technology

[0008] However, most mathematical optimization methods are deterministic methods, which need to be solved under a given specific calculation example. For the actual operation conditions with strong randomness, the adaptability of the output scheme is poor, and it cannot be used for real-time guidance. On-site dispatch work

At the same time, the mathematical optimization method still has the problem of insufficient solution efficiency. With the continuous expansion of the scale of the problem to be optimized, many mathematical models such as the

Images