Semantic Signal Rules for Consistent Assembly Data Annotation

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Current methods for data analysis in digital plants face challenges such as network transmission issues, limitations in local analysis algorithms, and dependency on manual operations, leading to inconsistent and unreliable data analysis.

Innovation Solution

A method and system for annotating data by using a semantic-based IoT apparatus with a semantic ontology module and rule determining apparatus to associate physical signals with data obtaining rules, enabling data to be annotated with context information, making it more consistent and suitable for migration and system configuration.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Reliability

If data is transmitted to the cloud center via network, then data analysis can be performed centrally, but network transmission issues may cause data loss or delay

Engineering Contradiction:
Improvedata transmission reliabilityVSAvoidnetwork transmission issues
Core Design Contradiction:
ReliabilityVSObject-affected harmful factors

Solution Approach 1:

The patent applies preliminary action by annotating data with contextual information before transmission to the cloud center. The annotation includes data source identification, collection time, and environmental conditions, which allows the data to be self-descriptive and reduces dependency on real-time network transmission for contextual understanding.

Inventive Principle:
Principle #10Preliminary action

Solution Approach 2:

The patent creates a local copy of the data processing capability by using pre-annotated data that contains all necessary contextual information. This allows edge devices to perform local analysis without requiring continuous cloud connection, effectively copying the analytical function to the edge.

Inventive Principle:
Principle #26Copying

2Productivity

If local analysis algorithm is downloaded and executed, then data can be analyzed locally, but the algorithm is limited to specific data types and cannot perform complex system-wide analysis

Engineering Contradiction:
Improvelocal data analysis capabilityVSAvoidalgorithm applicability
Core Design Contradiction:
ProductivityVSAdaptability or versatility

Solution Approach 1:

The patent achieves universality through a standardized data annotation format that can represent multiple data types and contexts uniformly. The annotation structure includes universal fields such as data source identification, collection time, and environmental conditions that apply across different sensor types and application scenarios, enabling a single analysis framework to handle diverse data.

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

Solution Approach 2:

The patent segments the analysis capability into two parts: standardized data annotation (which can be processed locally) and complex analysis algorithms (which can be executed in the cloud). This segmentation allows simple preprocessing and filtering to occur at the edge while complex system-wide analysis occurs centrally.

Inventive Principle:
Principle #1Segmentation

3Reliability

If historical data is used for analysis, then analysis can be performed offline, but online services cannot be provided during emergencies

Engineering Contradiction:
Improveoffline analysis capabilityVSAvoidonline service availability
Core Design Contradiction:
ReliabilityVSEase of operation

Solution Approach 1:

The patent applies preliminary action by pre-annotating data with contextual information at the time of collection. This preliminary annotation ensures that even when using historical offline data, the contextual information is already embedded, allowing meaningful analysis without requiring online cloud services during emergencies.

Inventive Principle:
Principle #10Preliminary action

4Measurement precision

If expert or system operator performs manual analysis, then complex system analysis can be achieved, but the process is too dependent on manual operation

Engineering Contradiction:
Improveanalysis accuracyVSAvoidmanual operation dependency
Core Design Contradiction:
Measurement precisionVSExtent of automation

Solution Approach 1:

The patent implements self-service by enabling data to carry its own contextual information through annotation. The data itself becomes self-descriptive with embedded information about its source, collection time, and environmental conditions, allowing automated systems to interpret and analyze data without requiring expert manual intervention for contextual understanding.

Inventive Principle:
Principle #25Self-service

Data Source

PatentEP3418837B1Method, apparatus and system for determining signal rules of data for data annotation
Publication Date: 2023.02.15 SIEMENS AG
  • EP3418837B1 patent drawingFigure 1
  • EP3418837B1 patent drawingFigure 2
  • EP3418837B1 patent drawingFigure 3

AI summary

The present invention provides a method, apparatus, and system for determining signal rules and annotating data. The method according to the present invention comprises the following steps: determining data obtaining logic based on assembly model information corresponding to the assembly; wherein the data obtaining logic comprises a to-be-obtained data object and an obtaining rule; determining at least one physical signal corresponding to the data obtaining logic; and determining, based on the data obtaining logic and the multiple physical signals corresponding to the data obtaining logic, a signal rule corresponding to the obtaining rule. The present invention has the following advantages: By annotating the running data of an assembly, the context of the data is indicated, so that the running data of the assembly can be made more consistent, easier to maintain, and applied to a new environment. Moreover, since the annotation information of data can adopt a common format, it is more suitable for information migration and system configuration.