Virtual Object-Oriented Data Model for Complex System Failure Analysis

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Conventional monitoring systems for complex systems like turbines require manual and cumbersome definition of failure mode detection rules, prone to errors and time-consuming, due to lack of unified conventions for sensor tags and event names across different systems, leading to delayed identification of failure causes.

Innovation Solution

A method using a base virtual object-oriented data model with abstract components and automatic mapping of sensor tags and event names to generate a dedicated data model for specific system types, enabling unified failure mode and root-cause analysis.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Reliability

If manual definition of failure mode detection rules is used, then monitoring can be performed, but the process is time-consuming and error-prone

Engineering Contradiction:
Improvefailure detection accuracyVSAvoidtime to identify failure causes
Core Design Contradiction:
ReliabilityVSLoss of time

Solution Approach 1:

The patent pre-establishes a standardized data model with unified sensor tag names and event name conventions before monitoring operations begin. This preliminary standardization allows automatic mapping of sensor data to the standardized model, eliminating the need for manual rule definition during failure analysis and significantly reducing identification time while maintaining reliability

Inventive Principle:
Principle #10Preliminary action

Solution Approach 2:

The patent introduces a standardized data model as an intermediary layer between raw sensor data and failure analysis. This intermediary model with unified conventions acts as a mediator that automatically maps diverse sensor tags and event names from different systems, enabling consistent failure detection without manual intervention while preserving detection accuracy

Inventive Principle:
Principle #24Intermediary (Mediator)

2Adaptability or versatility

If different sensor tag names and event names are used across systems, then system-specific monitoring is possible, but unified analysis becomes difficult

Engineering Contradiction:
Improvesystem-specific monitoring capabilityVSAvoiddata model complexity
Core Design Contradiction:
Adaptability or versatilityVSDevice complexity

Solution Approach 1:

The patent creates a universal standardized data model that can handle multiple system types through automatic mapping. The standardized model with unified sensor tag names and event name conventions serves multiple functions: it accommodates system-specific variations while providing a common framework for unified analysis across all monitored systems, reducing overall complexity

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

3Measurement precision

If manual monitoring and analysis is performed, then detailed failure analysis is possible, but productivity is reduced

Engineering Contradiction:
Improvefailure analysis precisionVSAvoidfailure identification speed
Core Design Contradiction:
Measurement precisionVSProductivity

Solution Approach 1:

The patent replaces the manual mechanical process of defining failure mode rules with an automated computational system. The standardized data model enables automatic mapping and analysis of sensor data, substituting manual engineer efforts with automated processing that maintains analytical precision while dramatically improving failure identification speed and overall productivity

Inventive Principle:
Principle #28Mechanics substitution (Replace mechanical system)

Data Source

PatentEP3394692B1Method and apparatus for analyzing an investigated complex system
Publication Date: 2020.03.25 SIEMENS AG
  • EP3394692B1 patent drawingFigure 1
  • EP3394692B1 patent drawingFigure 2
  • EP3394692B1 patent drawingFigure 3~4

AI summary

A method and apparatus for analyzing an investigated complex system (2) of a specific system type, said complex system (2) comprising a plurality of system components, the method comprising the steps of providing (S1) a base virtual object oriented data model comprising abstract components corresponding to system components of the investigated complex system (2), wherein each abstract component of the base virtual object oriented data model comprises parameters and attributes of the respective system component of the investigated complex system (2); mapping (S2) sensor tags of sensors deployed in the investigated complex system (2) and/or event names of events received from the investigated complex system (2) to the parameters of the abstract components of the provided base virtual object oriented data model to generate a dedicated data model for the system type of the investigated complex system (2); and performing (S3) a failure mode and/or a root-cause analysis of the investigated complex system (2) on the basis of the dedicated data model generated for the specific system type of the investigated complex system (2).