Train Control Architecture With Real-Time Self-Tuning
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current automatic train operation (ATO) systems face challenges in optimizing energy consumption, reducing CO2 emissions, and ensuring precise control of train movements, as they often rely on ad-hoc techniques and linear controllers that are not designed for non-linear systems, leading to inefficiencies and suboptimal performance.
Innovation Solution
A control system with a two-loop architecture, comprising an outer-loop controller for determining optimal speed, acceleration, and jerk profiles, and an inner-loop controller for generating motoring and braking commands, along with an auto-tuner for real-time self-tuning, which learns the vehicle's response to adapt the control system for improved performance.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Use of energy by moving object
If ad-hoc techniques and linear controllers are used for train operation, then the control system is simple to implement, but energy consumption increases and performance becomes suboptimal
Solution Approach 1:
The control system is divided into two distinct loops: an outer-loop controller that determines optimal speed, acceleration, and jerk profiles, and an inner-loop controller that generates motoring and braking commands. This segmentation allows each controller to specialize in specific control functions, optimizing energy consumption while maintaining manageable complexity through modular architecture.
Solution Approach 2:
The patent implements a real-time self-tuning process where the auto-tuner dynamically adjusts controller parameters based on learned vehicle response characteristics. This dynamic adaptation enables the system to optimize energy consumption across varying operating conditions without requiring manual retuning, resolving the contradiction between performance optimization and system complexity.
2Productivity
If real-time self-tuning is implemented to learn vehicle response, then control performance improves and tuning efforts are reduced, but system complexity and computational requirements increase
Solution Approach 1:
The auto-tuner enables the control system to self-adjust and optimize its own parameters through real-time learning of vehicle response characteristics. This self-service capability eliminates the need for extensive manual tuning efforts and adapts to changing vehicle conditions automatically, improving control performance while the modular architecture keeps the added complexity manageable.
Solution Approach 2:
The self-tuning process incorporates continuous feedback from vehicle response measurements to adjust controller parameters in real-time. This feedback mechanism allows the system to learn and adapt to optimal control strategies dynamically, enhancing performance while the structured two-loop architecture organizes the complexity of the feedback processing.
3Measurement precision
If two-loop architecture is used with outer-loop and inner-loop controllers, then control precision and energy optimization improve, but device complexity increases
Solution Approach 1:
The control system is divided into two distinct loops: an outer-loop controller that determines optimal speed, acceleration, and jerk profiles, and an inner-loop controller that generates motoring and braking commands. This segmentation allows each controller to specialize in specific control functions, optimizing control precision while maintaining manageable complexity through modular architecture.
4Use of energy by moving object
If optimal speed and acceleration profiles are determined in real-time, then energy consumption is reduced and timetable adherence is guaranteed, but computational load and system complexity increase
Solution Approach 1:
The outer-loop controller pre-calculates optimal speed, acceleration, and jerk profiles based on learned vehicle characteristics and operational conditions. By determining these optimal profiles in advance through the self-tuning process, the system can execute energy-efficient trajectories without requiring complex real-time computations during actual operation, thus reducing energy consumption while keeping computational complexity manageable.
Data Source
AI summary
A control system for a vehicle includes a first controller, a second controller, and an auto-tuner. The first controller is configured to generate an optimal trajectory of the vehicle along a path. The second controller is configured to, based on the optimal trajectory generated by the first controller, generate motoring and braking commands to a motoring and braking system of the vehicle for controlling the vehicle to travel along the path. The auto-tuner includes a processor configured to solve a real-time optimization problem to determine at least one parameter of at least one of the first controller or the second controller.