Fault Rule Knowledge Base Updating for Distributed Railway Diagnosis

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Railway signal monitoring systems lack a comprehensive and complete knowledge base for intelligent analysis, leading to inefficient data analysis and reliance on manual methods due to fragmented data collection and lack of frontline operator involvement in updating fault rules.

Innovation Solution

A method and apparatus for updating a fault rule knowledge base by combining node fault data and test data from multiple servers to create a central fault rule knowledge base, enabling iterative and comprehensive updates through a central server and node servers, with data security measures.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Reliability

If fault rule knowledge base is updated through centralized manual processes by research and development personnel, then knowledge base completeness can be improved, but updating speed and responsiveness to new faults deteriorates due to fragmented data collection across dispersed monitoring points

Engineering Contradiction:
Improveknowledge base completenessVSAvoidupdating speed
Core Design Contradiction:
ReliabilityVSProductivity

Solution Approach 1:

The system divides the centralized knowledge base updating process into distributed node servers at various monitoring points, each independently collecting and processing fault data locally. This segmentation enables parallel data collection across multiple locations simultaneously, dramatically increasing updating speed while maintaining completeness through centralized aggregation of all node contributions

Inventive Principle:
Principle #1Segmentation

Solution Approach 2:

The system implements automated feedback loops where node servers continuously monitor faults, automatically update local knowledge bases, and feed results back to the central server for consolidation. This feedback mechanism ensures the knowledge base remains current and complete without requiring manual intervention at each stage, resolving the contradiction between completeness and updating speed

Inventive Principle:
Principle #23Feedback

2Reliability

If fault rule knowledge base is established as proprietary black box with machine source codes, then system security is improved, but operator ability to edit and understand rules deteriorates, creating dependency on research and development personnel

Engineering Contradiction:
Improvesystem securityVSAvoidoperator editability
Core Design Contradiction:
ReliabilityVSEase of operation

Solution Approach 1:

The system introduces an intermediary layer between the proprietary knowledge base and operators: a user-friendly interface that allows operators to interact with, query, and contribute to fault rules without needing to understand or access the underlying machine source codes. This intermediary preserves security while enabling operator participation and understanding

Inventive Principle:
Principle #24Intermediary (Mediator)

Solution Approach 2:

The system enables operators to independently update and contribute to the knowledge base through automated tools and interfaces, eliminating dependency on research and development personnel. Operators can directly input fault observations and suggestions, which are automatically processed and integrated, maintaining security while improving ease of operation

Inventive Principle:
Principle #25Self-service

Data Source

PatentEP4708153A1Fault rule knowledge base updating methods and apparatuses, device and storage medium
Publication Date: 2026.03.11 CRSC RESEARCH & DESIGN INSTITUTE GROUP CO LTD
  • EP4708153A1 patent drawingFigure 1A~1B
  • EP4708153A1 patent drawingFigure 2
  • EP4708153A1 patent drawingFigure 3A

AI summary

The present invention discloses a fault rule knowledge base updating method and apparatus, a device and a storage medium. The method is applied to a central server and comprises: acquiring node fault data and a node fault rule knowledge base uploaded by at least one node server, the node fault rule knowledge base being obtained by the node server updating an inherent fault rule knowledge base according to the node fault data and a node test data set; updating an inherent test data set through the node fault data to obtain a central test data set; updating the inherent fault rule knowledge base through each node fault rule knowledge base to obtain a central fault rule knowledge base; and transmitting the central test data set and the central fault rule knowledge base to each node server, then updating the node test data set of nodes of the node server according to the central test data set by each node server, and updating the node fault rule knowledge base of the nodes of the node server according to the central fault rule knowledge base.