Condition Level Monitoring for Dynamic Production Quality Testing

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Current manufacturing systems face challenges in detecting anomalies caused by inferior quality components or targeted manipulation, which can affect production integrity and quality, and struggle to balance productivity with maintaining high-quality output, especially in distributed production environments where data integration and interpretation across hierarchical levels are complex.

Innovation Solution

A monitoring system that uses a modular, real-time capable sensor mesh and artificial intelligence, specifically a federated learning algorithm, to determine a condition level value by capturing parameters from production machines, components, and surroundings, enabling predictive quality characterization and proactive countermeasures while maintaining data privacy and security.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Reliability

If minimum test requirements are implemented to maintain quality, then product quality is ensured, but productivity is reduced due to extensive testing steps

Engineering Contradiction:
Improveproduct qualityVSAvoidmanufacturing efficiency
Core Design Contradiction:
ReliabilityVSProductivity

Solution Approach 1:

The patent implements dynamic test concepts where the extent and type of testing are adjusted in real-time based on monitored condition level values. When components show optimal boundary conditions, testing steps are reduced or omitted; when anomalies are detected, testing is intensified. This dynamic adaptation resolves the contradiction by making testing flexible rather than static, allowing productivity increases without compromising quality assurance.

Inventive Principle:
Principle #15Dynamics

Solution Approach 2:

The system changes the parameter of test intensity based on condition level values derived from monitoring data. By continuously adjusting testing parameters according to real-time component status, the system achieves both high productivity (by reducing unnecessary tests) and high reliability (by intensifying tests when needed), directly resolving the quality-productivity trade-off.

Inventive Principle:
Principle #35Parameter changes

2Device complexity

If hierarchical manufacturing pyramid structure is used to reduce complexity, then system manageability is improved, but data integration and anomaly detection across levels become difficult

Engineering Contradiction:
Improvesystem manageabilityVSAvoiddata integration capability
Core Design Contradiction:
Device complexityVSLoss of information

Solution Approach 1:

The patent introduces a monitoring system as an intermediary layer that bridges the hierarchical manufacturing pyramid levels. This intermediary collects, integrates, and analyzes data from multiple hierarchical levels (ERP, MES, SCADA, PLC, sensors), enabling comprehensive anomaly detection without requiring direct integration between all hierarchical levels. The condition level values serve as intermediate metrics that synthesize information across the hierarchy, resolving the data integration problem while preserving system manageability.

Inventive Principle:
Principle #24Intermediary (Mediator)

3Reliability

If classic MES systems are used to monitor production, then defined minimum requirements are checked, but additional data sources and flexible monitoring are not utilized

Engineering Contradiction:
Improvequality controlVSAvoiddata source flexibility
Core Design Contradiction:
ReliabilityVSAdaptability or versatility

Solution Approach 1:

The monitoring system is designed with multi-functionality, serving both the traditional quality control function of checking minimum requirements and the additional function of utilizing diverse data sources from the distributed manufacturing environment. The system can operate in multiple modes: basic compliance checking like classic MES, and advanced predictive monitoring using condition level values from various sensors and data sources, thereby achieving both reliability and adaptability.

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

Data Source

PatentEP4418059A1Determining a condition level value
Publication Date: 2024.08.21 SIEMENS AG
  • EP4418059A1 patent drawingFigure 1
  • EP4418059A1 patent drawingFigure 2
  • EP4418059A1 patent drawing

AI summary

A method for determining a condition level value (12) for a production process (14) a component (18), comprising the steps of: - capturing a first parameter (28a, 28b), wherein the first parameter (28a, 28b) is a value describing a parameter of a production machine (30a, 30b); - capturing a second parameter (32a, 32b) of the component (18), wherein the second parameter (32a, 32b) is a value describing a parameter of the component (18); - capturing a third parameter (34) of the surroundings (36), wherein the third parameter (24) is a value describing the surroundings (36); and - determining the condition level value (12) depending on at least the first parameter (28a, 28b), the second parameter (32a, 32b) and the third parameter (34). Furthermore, the invention relates to a computer program product, a computer-readable storage medium as well as a monitoring system (10).