Train ATO Speed Curve Optimization via Differential Evolution

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Traditional methods for optimizing target operation speed curves in Automatic Train Operation (ATO) result in inaccurate optimization and heavy computational burdens, often leading to local optima and non-convergence issues.

Innovation Solution

A method utilizing differential evolution algorithms to calculate performance indexes such as energy consumption, punctuality, and comfort, constructing objective functions based on these indexes, and solving them under speed limit and time constraints to obtain a target operation speed curve, which is then implemented by the ATO system.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Measurement precision

If traditional genetic algorithm or particle swarm algorithm is used to optimize train speed curve, then optimization can be performed, but the solution process becomes complicated and computational burden increases

Engineering Contradiction:

Improveoptimization accuracyVSAvoidsolution process complexity

Core Design Contradiction:

Measurement precisionVSDevice complexity

Solution Approach 1:

The patent extracts the core optimization logic from complex genetic algorithms and particle swarm algorithms, isolating only the essential differential evolution operations needed for speed curve optimization. This removes unnecessary complexity while retaining optimization effectiveness, directly addressing the contradiction between optimization accuracy and solution process complexity

Inventive Principle:

Principle #2Taking out (Extraction)

Solution Approach 2:

Instead of using traditional iterative optimization algorithms that gradually converge, the patent inverts the approach by using differential evolution to directly search for optimal solutions through population-based differentiation. This reversal of the optimization paradigm simplifies the solution process while maintaining accuracy

Inventive Principle:

Principle #13The other way round (Inversion)

2Measurement precision

If traditional genetic algorithm or particle swarm algorithm is used to optimize train speed curve, then optimization can be performed, but heavy computation is required

Engineering Contradiction:

Improveoptimization accuracyVSAvoidcomputational energy consumption

Core Design Contradiction:

Measurement precisionVSUse of energy by moving object

Solution Approach 1:

The patent applies partial action by using differential evolution with a controlled population size and iteration count, performing only the necessary computational steps to achieve optimization without excessive computation. This reduces energy consumption while maintaining optimization accuracy

Inventive Principle:

Principle #16Partial or excessive action

Solution Approach 2:

The patent changes the optimization parameters by switching from genetic algorithms to differential evolution, which requires different computational parameters (mutation factors, crossover rates). This parameter change reduces computational burden while preserving optimization effectiveness

Inventive Principle:

Principle #35Parameter changes

3Measurement precision

If traditional genetic algorithm or particle swarm algorithm is used to optimize train speed curve, then optimization can be performed, but it is easy to cause local optimum or non-convergence

Engineering Contradiction:

Improveoptimization accuracyVSAvoidconvergence reliability

Core Design Contradiction:

Measurement precisionVSReliability

Solution Approach 1:

The patent introduces dynamics into the optimization process through differential evolution, where the population dynamically evolves and adapts during the optimization iterations. This dynamic approach allows the system to escape local optima and reliably converge to global optima, addressing the reliability issue

Inventive Principle:

Principle #15Dynamics

4Productivity

If single target optimization of energy consumption is used, then optimization can be performed, but the optimization results are inaccurate

Engineering Contradiction:

Improveoptimization efficiencyVSAvoidoptimization accuracy

Core Design Contradiction:

ProductivityVSMeasurement precision

Solution Approach 1:

The patent merges multiple optimization targets (energy consumption, punctuality, comfort) into a unified multi-objective optimization framework using differential evolution. This combination allows simultaneous optimization of multiple parameters, improving accuracy while maintaining efficiency through the integrated approach

Inventive Principle:

Principle #5Merging (Combining)

Data Source

PatentUS11708098B2Method and device for optimizing target operation speed curve in ATO of train

Publication Date: 2023.07.25 TRAFFIC CONTROL TECH CO LTD

AI summary

Embodiments of the present application provide a method and a device for optimizing a target operation speed curve in an ATO of a train. The method includes: calculating a plurality of performance indexes of the train driving in a current section of a line, and constructing an objective function for optimizing the target operation speed curve of the train according to the plurality of performance indexes; determining constraint conditions of the objective function according to speed limit information of the line and running time of the train in the current section; and solving the objective function according to the constraint conditions based on a differential evolution algorithm to obtain the target operation speed curve of the train. The objective function for optimizing the target operation speed curve of the train are constructed using the plurality of performance indexes, which makes the optimization of the train speed curve more accurate.