Research and Implementation of Intelligent Control Algorithm for Metro Trains Energy-saving Operation under Complex Operating Conditions

• Published in: 2024 International Conference on Advances in Electrical Engineering and Computer Applications (AEECA) pp. 160 - 165
• Main Authors: Zhou, Jixu, Zheng, Anping, Ma, Zhe, Li, Ming, Zhang, Lijun
• Format: Conference Proceeding
• Language: English
• Published: IEEE 16.08.2024
• Subjects: Analytical models; Complex operating conditions; Deep learning; DLA; Electrical engineering; energy conservation; Energy consumption; Heuristic algorithms; Intelligent control; Intelligent systems; Matrix decomposition; metro systems; optimized operation; Public transportation; Time factors
• DOI: 10.1109/AEECA62331.2024.00036

Taking the complex routes of actual metro operations as the research subject, the specific operational patterns of trains to construct an energy-saving optimized control model for train operations was analyzed. The aim is to optimize the train's operational speed profile and achieve energy-saving operational objectives. Initially, a multi-particle train operation dynamic model was established, followed by the separation of train routes between stations. Subsequently, a minimal energy consumption model was constructed under constraints such as time, speed, and acceleration. The Lagrange multiplier algorithm was introduced to enhance the convergence speed of the train's energy consumption model constraints. A matrix discretization algorithm was proposed, which discretizes, decomposes, and encodes the train's operational routes and parameters at various stages. This creates a discretized matrix model for different control stages of the train, aiming to find the optimal energy-saving optimized maneuvering strategy. Finally, based on deep learning algorithms (DLA), the simulation analysis of the train discretization matrix control model is completed. Based on this, an intelligent system for energy-saving optimized subway train operational speed profiles is designed, providing theoretical and practical references for energy-saving driving of trains. Examples demonstrate that this method and system are effective and computationally precise.