CNC Machine Tool Fault Diagnosis Database via Fault Simulation

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Current fault diagnosis methods for CNC machine tools rely on historical records and expert experience, struggling to provide comprehensive and accurate fault diagnosis due to the complex nature of these tools, where faults occur irregularly and are difficult to diagnose.

Innovation Solution

A method and apparatus for generating a fault diagnosis database by simulating fault conditions in a CNC machine tool, allowing for comprehensive fault coverage by setting fault conditions involving all or multiple components, and using semantic descriptions to improve usability and accuracy in fault diagnosis.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Reliability

If fault diagnosis relies on historical fault records and expert experience, then the method is simple to implement, but the fault coverage is incomplete and diagnosis accuracy is insufficient

Engineering Contradiction:
Improvefault diagnosis accuracyVSAvoidcomplexity of fault diagnosis system
Core Design Contradiction:
ReliabilityVSDevice complexity

Solution Approach 1:

The patent applies preliminary action by pre-establishing a fault diagnosis knowledge base that contains fault trees, diagnostic rules, and solution methods before actual fault occurrence. This knowledge base is built in advance through expert systems and historical data analysis, enabling the system to quickly diagnose faults without relying solely on real-time expert experience, thus improving diagnosis accuracy while maintaining manageable system complexity

Inventive Principle:
Principle #10Preliminary action

Solution Approach 2:

The patent uses copying by creating a virtual representation of the CNC machine tool's fault diagnosis knowledge through structured databases that replicate expert diagnostic reasoning. The fault diagnosis knowledge base copies and formalizes expert experience into machine-readable rules and fault trees, allowing the system to access comprehensive diagnostic knowledge without requiring physical presence of experts, thereby improving reliability without proportionally increasing system complexity

Inventive Principle:
Principle #26Copying

2Adaptability or versatility

If the structure of CNC machine tool is complex with multiple components, then the machine tool functionality is enhanced, but fault diagnosis becomes more difficult and time-consuming

Engineering Contradiction:
Improvemachine tool functionalityVSAvoidfault detection difficulty
Core Design Contradiction:
Adaptability or versatilityVSDifficulty of detecting and measuring

Solution Approach 1:

The patent applies segmentation by decomposing the complex CNC machine tool system into modular fault tree structures where each component (PLC, servo drive, servo motor, ball screw, encoder, etc.) has its own fault branches. This hierarchical segmentation allows diagnosticians to systematically isolate and diagnose specific component failures without being overwhelmed by the overall system complexity, making fault detection more manageable while preserving full system functionality

Inventive Principle:
Principle #1Segmentation

Solution Approach 2:

The patent introduces an intermediary fault diagnosis knowledge base that mediates between the complex machine tool system and the diagnostic process. This knowledge base acts as an intermediary layer containing pre-processed fault trees, diagnostic rules, and component relationships, translating complex system states into interpretable diagnostic information, thereby reducing the difficulty of fault detection in highly functional machines

Inventive Principle:
Principle #24Intermediary (Mediator)

3Reliability

If comprehensive fault conditions are simulated involving all components, then the fault coverage is improved, but the time and resources required for database generation increase

Engineering Contradiction:
Improvefault coverageVSAvoiddatabase generation time
Core Design Contradiction:
ReliabilityVSLoss of time

Solution Approach 1:

The patent applies preliminary action by pre-generating a comprehensive fault diagnosis knowledge base that includes all possible fault conditions for every component (PLC, servo drive, servo motor, coupling, bearings, ball screw, encoder) before actual operation. This pre-established database contains fault trees and diagnostic rules for all potential failures, enabling the system to handle any fault scenario immediately without requiring time-consuming analysis during actual diagnosis, thus achieving comprehensive coverage without losing time during operation

Inventive Principle:
Principle #10Preliminary action

Solution Approach 2:

The patent employs partial or excessive action by creating a complete fault diagnosis knowledge base that covers all possible fault conditions even though not all faults will occur in practice. This excessive coverage ensures that every potential component failure mode is accounted for in the fault trees and diagnostic rules, guaranteeing comprehensive fault coverage while the systematic organization keeps the generation process manageable

Inventive Principle:
Principle #16Partial or excessive action

Data Source

PatentEP3674822B1Method and apparatus for generating fault diagnosis information base of numerical control machine tool
Publication Date: 2022.10.26 SIEMENS AG
  • EP3674822B1 patent drawingFigure 1
  • EP3674822B1 patent drawingFigure 2
  • EP3674822B1 patent drawingFigure 3

AI summary

The present invention relates to the technical field of industrial automation, in particular to a method and apparatus for generating a fault diagnosis database of a CNC machine tool, intended to conveniently provide comprehensive fault diagnosis information. The method comprises: setting a fault condition of the CNC machine tool; running a simulation model of the CNC machine tool under each set fault condition in order to generate a fault, and recording a fault phenomenon of the fault; backtracking a possible fault generating each fault phenomenon, in order to establish an association between the fault phenomenon and a possible fault generating the fault phenomenon; generating a fault diagnosis database of the CNC machine tool according to the association established. Due to the fact that what is being run is a simulation model of the CNC machine tool, various fault conditions can be conveniently set. The fault diagnosis database established by the method has the advantages of comprehensive coverage of fault situations and abundant fault diagnosis information. The result of performing fault diagnosis on the basis of such a fault diagnosis database is more accurate.