Rail Traffic Control Rules for Real-Time Deviation Handling

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Existing methods for controlling rail traffic struggle to optimize operations in real-time, especially when deviations from predefined timetables occur during rail transport operations, requiring complex adjustments to achieve goals like energy efficiency and minimal delays.

Innovation Solution

A method that utilizes action selection rules, configured for specific control goals, to determine and execute control actions based on real-time status data of rail vehicles, allowing for dynamic optimization of rail traffic during operation. These rules are trained using reinforcement learning and machine learning techniques, enabling efficient control of multiple objectives such as energy consumption and delay reduction.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Adaptability or versatility

If optimized timetables are generated offline for controlling rail traffic, then energy consumption is reduced and delays are minimized, but the system cannot adapt to real-time deviations during operation

Engineering Contradiction:
Improveadaptability to real-time deviationsVSAvoidcontrol efficiency
Core Design Contradiction:
Adaptability or versatilityVSProductivity

Solution Approach 1:

The patent implements dynamic control by switching from static offline timetables to real-time online control. The control system continuously receives status data during rail operation and dynamically adjusts control actions based on current conditions, enabling adaptation to real-time deviations while maintaining control efficiency through automated decision-making processes.

Inventive Principle:
Principle #15Dynamics

Solution Approach 2:

The patent establishes a feedback mechanism where the control system continuously receives status data from rail vehicles during operation. This feedback loop enables the system to monitor actual performance, detect deviations from planned schedules, and automatically adjust control actions to optimize energy consumption and minimize delays in real-time.

Inventive Principle:
Principle #23Feedback

2Reliability

If complex adjustments are made during rail operation to handle deviations, then control objectives can be met, but the system complexity increases

Engineering Contradiction:
Improvecontrol objective achievementVSAvoidsystem complexity
Core Design Contradiction:
ReliabilityVSDevice complexity

Solution Approach 1:

The patent applies preliminary action by pre-training multiple action selection rules offline using reinforcement learning for different control objectives (e.g., energy optimization, delay minimization). During real-time operation, the system simply selects and executes the appropriate pre-trained rule based on current status data, achieving reliable control without requiring complex real-time computations or adjustments.

Inventive Principle:
Principle #10Preliminary action

Solution Approach 2:

The patent introduces an intermediary component - the action selection rule selection unit - that mediates between status data input and control actions output. This intermediary selects appropriate pre-trained action selection rules based on current conditions and executes them, simplifying the overall system architecture while maintaining the ability to achieve multiple control objectives reliably.

Inventive Principle:
Principle #24Intermediary (Mediator)

3Adaptability or versatility

If multiple action selection rules are maintained for different control objectives, then real-time optimization is enabled, but memory requirements increase

Engineering Contradiction:
Improvemulti-objective optimization capabilityVSAvoidmemory storage
Core Design Contradiction:
Adaptability or versatilityVSQuantity of substance

Solution Approach 1:

The patent segments the control system into multiple specialized action selection rules, each optimized for a specific control objective (e.g., energy consumption, delay minimization). Instead of maintaining one large complex controller, the system divides functionality into smaller, focused modules that can be independently trained and stored, reducing overall memory requirements while maintaining multi-objective optimization capability.

Inventive Principle:
Principle #1Segmentation

Data Source

PatentEP4082869B1Method for controlling rail traffic of a plurality of railway vehicles, computing unit and computer program
Publication Date: 2025.01.15 SIEMENS MOBILITY GMBH
  • EP4082869B1 patent drawingFigure 1~2
  • EP4082869B1 patent drawingFigure 3
  • EP4082869B1 patent drawingFigure 4

AI summary

The invention relates to a method (100) for controlling a rail traffic of a plurality of rail vehicles (215), comprising: - receiving (101) status data of the rail traffic; - receiving (103) a control target (KPI1, KPI2, KPIN) for controlling the rail traffic of the plurality of rail vehicles (215); - Selecting (105) at least one action selection rule (Π1, Π2, ΠN) from a plurality of action selection rules (Π1, Π2, ΠN) based on the control objective (KPI1, KPI2, KPIN), wherein the action selection rules (Π1, Π2, ΠN) are set up to determine control actions of the rail traffic based on state data of the rail traffic, wherein by executing the control actions by the rail vehicles (215) the rail traffic can be transformed into a state optimized with respect to a control objective (KPI1, KPI2, KPIN);- Executing (107) the at least one selected action selection rule (Π1, Π2, ΠN) on the received state data and determining control actions; and - providing (109) the control actions for controlling the majority of rail vehicles (215).;