Optimization Model of Urban Rail Transportation Planning Based on Evolutionary Algorithm of State Space Model

Urban mass transit (UMT) planning is a complex decision-making process with multi-objectives, multi-constraints, multi-uncertainties, unmeasurable factors, large capital expenditure and long term. As a branch of computer science development, artificial intelligence (AI) has played a great role in human production and life. Evolutionary algorithm based on state-space model (SEA) is an evolutionary algorithm based on discrete system state-space model. In this article, SEA and CAD technologies are used to build UMT planning optimization model, and the statistical analysis function of operational data collected by urban authorities is fully exerted. Based on GIS and traffic model platform, a targeted and responsive UMT network optimization system is realized by using CAD tools. The experiment highlights its effectiveness by comparing the proposed method with the traditional method, and takes particle swarm optimization (PSO) algorithm and genetic algorithm (GA) as comparison methods for common analysis and verification. The results show that the accuracy of traffic stream prediction of this algorithm is above 95%, and the accuracy of optimal path planning is about 13% higher than that of traditional GA. Therefore, it can be considered that applying SEA to UMT network CAD modeling can improve the efficiency of UMT planning. © 2024 CAD Solutions, LLC.