Vehicle System Control Using Predictive Model for Coupler Force Management
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing vehicle systems face challenges in controlling operations along routes to minimize coupler damage and ensure performance matches trip plans, particularly on uneven terrain where couplers experience dynamic forces leading to fatigue and potential damage.
Innovation Solution
A control system that generates and selects trial plans for operational settings using model predictive control to optimize system-handling metrics such as relative acceleration, speed, and forces between vehicles, reducing the risk of coupler damage and improving performance alignment with trip plans.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If the control system monitors lead locomotive speed and adjusts operational settings frequently to match trip plan, then speed control accuracy improves, but coupler damage risk increases due to excessive adjustments on uneven terrain
Solution Approach 1:
The control system predicts future coupler forces and operational requirements ahead of time, allowing it to plan operational setting changes that avoid excessive adjustments. By looking ahead at the route profile and predicting upcoming forces, the system can smooth out adjustments rather than reacting frequently to immediate speed deviations, thereby reducing coupler damage risk while maintaining speed control accuracy.
Solution Approach 2:
The system dynamically adapts its control strategy based on real-time conditions, including terrain variations and current coupler force states. Rather than applying fixed threshold-based adjustments, the control algorithm modulates operational settings continuously and smoothly, adapting the rate and magnitude of changes to current system conditions, which reduces shock loads on couplers while maintaining precise speed control.
2Speed
If the control system makes frequent adjustments to operational settings to maintain speed, then speed control improves, but fuel efficiency deteriorates
Solution Approach 1:
The control system performs predictive analysis of upcoming route conditions and schedules operational setting changes in advance rather than making frequent reactive adjustments. By planning throttle and brake changes ahead of time based on predicted terrain and speed requirements, the system reduces the total number of adjustments needed, thereby improving fuel efficiency while maintaining speed control.
Solution Approach 2:
Instead of continuous frequent adjustments, the system implements operational setting changes at optimized periodic intervals based on predicted system behavior and route conditions. This periodic control approach, rather than continuous adjustment, reduces energy consumption while maintaining acceptable speed control performance.
3Loss of time
If the control system uses lead speed for control adjustments, then response time improves, but control stability deteriorates due to higher variability
Solution Approach 1:
The system predicts future center-of-mass speed values based on current lead speed and route conditions, allowing it to make control decisions based on stabilized predicted values rather than highly variable instantaneous lead speed measurements. This predictive approach maintains fast response time while filtering out the variability inherent in lead speed measurements.
Solution Approach 2:
The system introduces a predictive model as an intermediary between the lead speed sensor and the control actuator. Rather than directly using noisy lead speed measurements for control decisions, the predictive model processes this information to generate smoothed, stabilized control commands, thereby reducing the impact of lead speed variability on control stability.
Data Source
AI summary
System includes a control system used to control operation of a vehicle system as the vehicle system moves along a route. The vehicle system includes a plurality of system vehicles in which adjacent system vehicles are operatively coupled such that the adjacent system vehicles are permitted to move relative to one another. The control system includes one or more processors that are configured to (a) receive operational settings of the vehicle system and (b) input the operational settings into a system model of the vehicle system to determine an observed metric of the vehicle system. The one or more processors are also configured to (c) compare the observed metric to a reference metric and (d) modify the operational settings of the vehicle system based on differences between the observed and the reference metrics.