A method and device for automatic simulation modeling of rail transit based on reinforcement learning

Abstract

The invention discloses a rail transit automatic simulation modeling method and device based on reinforcement learning, and the method comprises the steps: building a passenger flow simulation systemthrough employing passenger flow as a research object of simulation; initializing the state of the passenger flow simulation system at the moment t, and then performing analogue simulation to obtain asection passenger flow congestion degree penalty function of the train in the running section and a penalty function of path selection action of passengers at the moment t; then, taking a reward value obtained by the passenger selecting the path action as a return function of the research object at the moment t; then, executing simulation training of a passenger flow simulation system, updating related network parameters, and then, obtaining a trained passenger flow simulation model; and finally, extracting an action function as a passenger path selection probability generation function. A simulation system is established according to known operation logic and parameters, unknown parameter values in the simulation system are automatically obtained, and therefore the obtained simulation model can accurately describe a real system.

Description

technical field [0001] The invention belongs to the field of rail traffic, and in particular relates to an automatic simulation modeling method and device for rail traffic based on reinforcement learning. Background technique [0002] The existing simulation modeling applied in the field of rail transit adopts the logical induction method from special to general, based on a certain amount of physical quantity data measured and observed during the operation of the system, and using statistical laws, system identification and other theories to reasonably estimate the reflection The mathematical model of the mutual constraints of various physical quantities of the system is mainly based on a large number of measured data from the system. When the internal structure and characteristics of the system under study are not clear, and some parameters are unknown, the internal mechanism change law of the system cannot be determined, and it is often difficult to obtain simulation param...

AI Technical Summary

Problems solved by technology

When the internal structure and characteristics of the system under study are not clear, and some parameters are unknown, the internal mechanism change law of the system cannot be determined, and it is often difficult to obtain simulation parameters that can accurately describe the real system, resulting in a gap between the simulation model and the real system. There are differences, that is, the simulation system does not match the real system, and it is difficult to support in-depth research analysis and decision making on complex systems

[0003] In addition, in the existing simulation modeling methods, through expert analysis or the subjective setting of researchers, usually because the complex operating logic and state transition process in the system are not fully considered, the factors considered are too one-sided, and there are differences between them and the actual system. larger

Furthermore, when the simulation parameters are obtained by means of function calibration, a large amount of tag data is often required to simulate the relationship between the real system operating parameters and operating indicators, which is often difficult to obtain in the process of simulation modeling and simulation system development

Images