Modular Railway Intrusion Detection with Local Pattern Matching

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Current monitoring systems for railway systems are inadequate in detecting unauthorized intrusions with high reliability, often resulting in false alarms, insufficient security, and high operational costs, while being difficult to scale, install, and maintain.

Innovation Solution

A monitoring system utilizing multiple sensors to detect emissions from people, such as noise, speech, gases, and vibrations, with autonomous modules powered by batteries that can be easily deployed and adapted, featuring a central computer for pattern recognition and event sequencing, and designed to be robust and energy-efficient.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Reliability

If traditional surveillance systems are deployed to secure railway facilities, then security coverage is improved, but installation complexity and time consumption increase significantly

Engineering Contradiction:
Improvesecurity coverageVSAvoidinstallation complexity
Core Design Contradiction:
ReliabilityVSDevice complexity

Solution Approach 1:

The monitoring system is divided into multiple independent, modular monitoring units that can be individually deployed and configured. Each unit contains integrated sensors, processing equipment, and power supply, allowing flexible placement throughout the railway facility without complex interconnections.

Inventive Principle:
Principle #1Segmentation

Solution Approach 2:

The monitoring units are designed as universal, multi-functional devices capable of detecting various types of intrusions (acoustic, vibration, motion) and adapting to different railway environments. The same unit type can monitor tracks, platforms, or buildings, reducing the need for specialized equipment.

Inventive Principle:
Principle #6Universality (Multi-functionality)

2Measurement precision

If monitoring systems are installed to detect intrusions, then detection capability is improved, but false alarms increase due to limited information content

Engineering Contradiction:
Improveintrusion detection accuracyVSAvoidfalse alarm rate
Core Design Contradiction:
Measurement precisionVSReliability

Solution Approach 1:

Multiple sensor types (acoustic sensors, vibration sensors, motion detectors) are combined within each monitoring unit to capture comprehensive information about intrusions. The fusion of data from different sensing modalities enables more accurate distinction between legitimate intrusions and benign events, reducing false alarms.

Inventive Principle:
Principle #5Merging (Combining)

Solution Approach 2:

The system incorporates feedback mechanisms where detection results are continuously analyzed and used to adjust sensitivity thresholds. When false alarms occur, the system learns from the environmental context and adjusts its response criteria, improving detection accuracy over time while maintaining high reliability.

Inventive Principle:
Principle #23Feedback

3Productivity

If surveillance personnel are deployed to monitor facilities, then response capability is improved, but operational costs increase

Engineering Contradiction:
Improveresponse capabilityVSAvoidoperational costs
Core Design Contradiction:
ProductivityVSLoss of energy

Solution Approach 1:

The monitoring system operates autonomously, with automated detection, analysis, and alarm generation capabilities. The system self-manages surveillance functions without requiring constant human intervention, triggering alerts only when actual intrusions are detected, thereby eliminating the need for continuous manual monitoring and reducing operational costs.

Inventive Principle:
Principle #25Self-service

Solution Approach 2:

Instead of continuous manual surveillance, the system employs periodic automated scanning and event-triggered monitoring. Sensors continuously collect data, but active analysis and alarm generation occur only when anomalies are detected, optimizing resource utilization and reducing operational expenses while maintaining high response capability.

Inventive Principle:
Principle #19Periodic action

4Measurement precision

If monitoring devices are placed in railway facilities, then intrusion detection is improved, but the devices become vulnerable to damage and require frequent maintenance

Engineering Contradiction:
Improveintrusion detectionVSAvoiddevice vulnerability
Core Design Contradiction:
Measurement precisionVSObject-affected harmful factors

Solution Approach 1:

Sensors and electronic components are nested within protective housings that blend with the railway environment. The monitoring units are concealed within or near railway infrastructure elements, protecting them from deliberate damage while maintaining detection effectiveness. The nested design also allows for easy integration into existing structures.

Inventive Principle:
Principle #7Nested doll (Nesting)

5Area of stationary object

If traditional monitoring systems are deployed, then coverage area is improved, but scalability and adaptability to changing situations deteriorate

Engineering Contradiction:
Improvecoverage areaVSAvoidscalability
Core Design Contradiction:
Area of stationary objectVSAdaptability or versatility

Solution Approach 1:

The system covers large areas by deploying multiple independent monitoring units rather than using a single complex system. This segmentation allows flexible scaling - units can be added, removed, or repositioned based on changing security requirements without redesigning the entire system, maintaining high adaptability while achieving extensive coverage.

Inventive Principle:
Principle #1Segmentation

Applied Scientific Principles

This section explains which scientific principles are used to turn an abstract innovation direction into a practical engineering solution.

Function Achieved in This Case

The system effectively detects unauthorized intrusions early, reduces false alarms, and allows for scalable and efficient monitoring of large areas with minimal effort, providing reliable evidence for security responses and prolonged operation without maintenance.

Implementation Method 1

several sensors 15 which detect emissions from persons or devices, in particular noise, speech, gases, radiation and vibrations

Methodology Applied
Scientific EffectAcoustic detection: Sound

Implementation Method 2

several sensors 15 which detect emissions from persons or devices, in particular noise, speech, gases, radiation and vibrations

Methodology Applied
Scientific EffectVibration detection: Vibration

Data Source

PatentEP3968297B1Method for monitoring a railway system, monitoring system and monitoring module
Publication Date: 2024.11.20 SCHWEIZISCHE BUNDESBAHNEN SBB
  • EP3968297B1 patent drawingFigure 1
  • EP3968297B1 patent drawingFigure 2a~2b
  • EP3968297B1 patent drawingFigure 3

AI summary

The monitoring system (100) serves to monitor a railway installation (1000) and comprises several sensors (15) for detecting emissions from persons or equipment and for outputting corresponding sensor signals, as well as at least one computer unit (11; 101) with an implemented monitoring program (19, 109) for processing the sensor signals and for determining information about the intruders. According to the invention, several battery-operated monitoring modules (1, 1A, 1B) are arranged spaced apart from one another, each having a sensor (15) with which emissions are detected, and each having a computer module (11) with a storage unit (111) in which comparison patterns (M) are stored, which are events (E1, E2, ...) typical for the intrusion of persons and, if applicable, typical for the railway installation (1000)., En) represent, and in which a local monitoring program (19) is implemented, by means of which event patterns are determined for local sensor signals and compared with the stored comparison patterns (M) in order to determine local information which is transmitted to a central computer (101) in which a central monitoring program (109) is implemented, which evaluates the local information given by the monitoring modules (1A, 1B) in order to determine events (E1; E2; ..., En) individually or linked together as event sequences (E1 - E2 - E3, ..., En) relating to the behavior of intruding persons within the monitored railway facility (1000).