Multi-Station Passenger Flow Coordinated Control Method
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
During peak hours in urban rail transit, passenger flow at key stations becomes unbalanced, leading to stranded passengers and potential safety hazards due to exceeded platform capacity. Existing solutions, such as manual adjustments and mathematical models, lack accuracy and timeliness in controlling passenger flow across multiple stations.
Innovation Solution
A coordinated control method for urban rail transit passenger flow is implemented, which includes predicting passenger flow using a rail simulation system, constructing a mixed integer programming model for multi-station passenger flow control, and optimizing passenger flow restrictions using a branch and bound algorithm. This method simultaneously optimizes the start and end times of passenger flow control, the stations under coordinated control, and the size of the controlled passenger flow.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Ease of operation
If manual adjustment strategies are used for passenger flow control, then operational flexibility is improved, but control accuracy and timeliness deteriorate
Solution Approach 1:
The patent replaces manual mechanical adjustment strategies with an automated intelligent system that uses machine learning models and algorithms to predict passenger flow and generate control strategies. This substitution maintains operational flexibility while significantly improving control accuracy and timeliness through automated decision-making based on real-time data analysis.
Solution Approach 2:
The system enables self-service by allowing the passenger flow control system to automatically predict, analyze, and generate control strategies without continuous manual intervention. The intelligent algorithms autonomously optimize control parameters based on predicted passenger flow patterns, improving both accuracy and responsiveness while reducing reliance on manual operations.
2Stability of the object's composition
If coordinated control of multiple stations is implemented using mathematical models, then passenger flow balance is improved, but system complexity increases
Solution Approach 1:
The patent segments the complex multi-station control problem into independent station-level predictions and coordinated control strategies. By using machine learning models to predict passenger flow at each station independently and then coordinating these predictions through optimized control strategies, the system achieves passenger flow balance while managing complexity through modular processing.
Solution Approach 2:
The system manages complexity by dynamically changing control parameters such as control timing, control intensity, and station selection based on predicted passenger flow patterns. Instead of fixing the entire control system structure, the patent optimizes specific parameters adaptively, simplifying the overall system while maintaining effective coordinated control.
3Reliability
If existing mathematical models are used for passenger flow prediction, then theoretical foundation is improved, but consideration of transfer passenger flow and real-time accuracy deteriorates
Solution Approach 1:
The patent incorporates feedback mechanisms that continuously monitor actual passenger flow data and use it to refine predictions and adjust control strategies. This feedback loop enables the system to account for transfer passenger flow patterns and improve real-time prediction accuracy while maintaining the theoretical foundation of mathematical models through iterative optimization.
Solution Approach 2:
The system transitions from static mathematical models to dynamic machine learning models that adapt to changing passenger flow patterns in real-time. By using dynamic prediction algorithms that continuously learn from new data, the patent improves accuracy regarding transfer passenger flow and real-time conditions while building upon the theoretical foundation of operational research.
Data Source
AI summary
Disclosed are a coordinated control method for urban rail transit passenger flow, an electronic device, and a storage medium. The method includes: predicting passenger flow in peak hours of urban rail lines using a simulation deduction function in a rail simulation system, including station entry ID, station exit ID, station entry time period, and passenger number data; obtaining passenger flow of passengers arriving at stations s and preparing to board during time periods t by dividing according to the different time periods t and the stations s; counting passenger flow in each direction of historical passenger flow, and calculating a proportion of the passenger flow in each direction of the historical passenger flow; constructing a mixed integer programming model of multi-station passenger flow coordinated control; and obtaining an optimal station entry passenger flow scheme by solving the mixed integer programming model of multi-station passenger flow coordinated control.