Raw Material Model Selection for Faster Facility State Evaluation

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Existing systems face inefficiencies in evaluating the state of facilities that manufacture products from raw materials, particularly in scenarios where raw material properties change frequently, leading to increased processing loads and time losses due to the need for frequent generation of new evaluation models.

Innovation Solution

A model selection apparatus that stores multiple evaluation models associated with raw materials and selects a target model based on property data, using clustering and threshold adjustments to determine similar raw materials, thereby reducing the need for new model generation.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Productivity

If multiple evaluation models are stored and selected based on raw material properties, then processing load and time loss are reduced, but device complexity increases

Engineering Contradiction:
Improveprocessing efficiencyVSAvoidsystem complexity
Core Design Contradiction:
ProductivityVSDevice complexity

Solution Approach 1:

Multiple evaluation models are pre-generated and stored in the storage unit, each corresponding to different raw material property ranges. When a new raw material is input, the system selects the appropriate pre-generated model based on property matching, avoiding the need to generate a new model each time and thus reducing processing load and time loss.

Inventive Principle:
Principle #10Preliminary action

Solution Approach 2:

The system changes the parameter of model selection based on raw material properties. By clustering raw material properties and creating multiple evaluation models for different property ranges, the system adapts to varying raw material characteristics without requiring complex real-time analysis, thereby improving processing efficiency.

Inventive Principle:
Principle #35Parameter changes

2Reliability

If new evaluation models are generated frequently to adapt to changing raw material properties, then evaluation accuracy is improved, but time loss and processing load increase

Engineering Contradiction:
Improveevaluation accuracyVSAvoidmodel generation time
Core Design Contradiction:
ReliabilityVSLoss of time

Solution Approach 1:

Evaluation models are pre-generated for different raw material property clusters before actual use. This preliminary action ensures that when new raw materials are evaluated, the system can quickly select an appropriate pre-generated model rather than generating a new one, thus maintaining evaluation accuracy while significantly reducing model generation time.

Inventive Principle:
Principle #10Preliminary action

Solution Approach 2:

The system segments raw materials into different clusters based on their properties and generates separate evaluation models for each cluster. This segmentation allows the system to handle different raw material types with specialized models, improving evaluation accuracy for each segment while avoiding the need to generate a universal model for all variations.

Inventive Principle:
Principle #1Segmentation

3Measurement precision

If clustering with strict threshold is used to match raw materials, then model selection precision is improved, but adaptability decreases

Engineering Contradiction:
Improveproperty matching precisionVSAvoidraw material coverage
Core Design Contradiction:
Measurement precisionVSAdaptability or versatility

Solution Approach 1:

The system dynamically adjusts the threshold for raw material property matching based on the clustering results. When a new raw material is input, the system determines whether to use a strict threshold for precise matching or a more flexible threshold for broader adaptability, allowing it to balance between precision and versatility depending on the specific situation.

Inventive Principle:
Principle #15Dynamics

Solution Approach 2:

The threshold parameter for property matching is changed based on the clustering outcome. By adjusting this parameter, the system can achieve high precision when raw materials closely match existing clusters while maintaining adaptability to handle new or variant raw materials by relaxing the threshold when appropriate.

Inventive Principle:
Principle #35Parameter changes

Data Source

PatentEP4303671A1Model selection apparatus, model selection method, and model selection program
Publication Date: 2024.01.10 YOKOGAWA ELECTRIC CORP
  • EP4303671A1 patent drawingFigure 1
  • EP4303671A1 patent drawingFigure 2
  • EP4303671A1 patent drawingFigure 3

AI summary

Means for solving the problem: There is provided a model selection apparatus including: an evaluation model storage unit configured to store each of a plurality of evaluation models capable of outputting an index for evaluating a state of a facility that is configured to manufacture a product from a raw material, in association with the raw material; a property data acquisition unit configured to acquire property data indicating a property of the raw material which is used in the facility; a model selection unit configured to select a target model for evaluating the state of the facility based on the property data, from among the plurality of evaluation models, when a target raw material in the facility is used; and a target model output unit configured to output the target model.