Train Control Method Dynamic State Weighting
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current vehicle control methods using model prediction face challenges in accurately predicting vehicle states in dynamic environments due to the complexity of environmental and vehicle parameters, leading to inaccurate results when the vehicle leaves a fixed platform.
Innovation Solution
A train control method that determines state weights and traveling constraints based on real-time parameters of a reference vehicle to calculate optimal target parameters for the vehicle under control, allowing for real-time and accurate control regardless of the environment.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If fixed parameters are used in model prediction, then prediction accuracy is improved in fixed environments, but prediction accuracy deteriorates in dynamic environments
Solution Approach 1:
The patent transforms the static prediction model into a dynamic one by introducing real-time state parameters and environmental factors. The prediction model continuously updates based on current vehicle state (position, speed, acceleration) and environmental conditions, allowing it to adapt to changing environments while maintaining prediction accuracy.
Solution Approach 2:
The patent changes the parameters used in prediction from fixed values to dynamic parameters that vary with vehicle state and environment. By incorporating real-time state parameters and environmental factors into the prediction model, the system can adjust its predictions according to current conditions, resolving the contradiction between fixed-parameter accuracy and environmental adaptability.
2Reliability
If multiple control parameters are used in model prediction, then prediction comprehensiveness is improved, but system complexity increases
Solution Approach 1:
The patent segments the control parameters into distinct categories: vehicle state parameters (position, speed, acceleration) and environmental parameters (track conditions, signals, obstacles). This segmentation allows the system to manage multiple parameters systematically, improving control comprehensiveness while maintaining manageable complexity through structured parameter organization.
Solution Approach 2:
The patent creates a universal prediction framework that handles multiple types of parameters through a unified model structure. The prediction model can process various state parameters and environmental factors using the same computational approach, reducing system complexity while maintaining comprehensive control capability.
Data Source
AI summary
Embodiments of the application provide a train control method, system, computer device and storage medium. A scheme applying the train control method of the application determines a current travelling state of a vehicle under control firstly, and configures different state weights according to different travelling states to determine a corresponding target travelling parameter in a particular travelling state. The scheme can ensure to determine and obtain in real time an optimal target travelling parameter for the vehicle under control according to its current travelling state, regardless of the travelling environment of the vehicle under control, and control the vehicle under control in real time and effectively by the target travelling parameter during a travelling process. Thereby, the real-time performance and control accuracy of vehicle control can be improved, and the control effect of the train control method provided by the embodiments of the application can be further improved.