Material Specification Recommendations Using Self-Organizing Maps

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Existing systems, such as those described in Patent Literature 1, primarily utilize self-organizing maps for determining important tire design variables and do not explore their application for other product development purposes.

Innovation Solution

A recommendation data generation apparatus and method that utilizes a self-organizing map to assign physical property vectors to nodes, select target nodes based on node arrangement, and generate recommendation data indicating material specifications for products with desired properties, enhancing product development information.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Adaptability or versatility

If a self-organizing map is used to determine important tire design variables, then the analysis of tire design variables is improved, but the system cannot be applied to other product development purposes

Engineering Contradiction:

Improveapplication scope of self-organizing mapVSAvoidunused potential of self-organizing map

Core Design Contradiction:

Adaptability or versatilityVSLoss of information

Solution Approach 1:

The patent applies the self-organizing map technique to multiple product development tasks beyond its original tire design variable analysis purpose. The system uses the same self-organizing map framework to (1) determine important design variables, (2) select optimal material specifications, and (3) recommend materials for new product development, thereby achieving multi-functionality and eliminating the loss of unused potential

Inventive Principle:

Principle #6Universality (Multi-functionality)

2Reliability

If material specifications are selected based on existing physical property data, then the reliability of known properties is maintained, but the diversity of physical properties in new products is limited

Engineering Contradiction:

Improveaccuracy of physical property predictionVSAvoiddiversity of physical properties

Core Design Contradiction:

ReliabilityVSAdaptability or versatility

Solution Approach 1:

The patent extends the selection process into a new dimension by identifying and selecting target nodes in the self-organizing map that correspond to physical properties different from those in the training data. This dimensional extension allows the system to recommend materials with novel physical property combinations while maintaining reliability through the structured self-organizing map framework

Inventive Principle:

Principle #17Another dimension (Dimensionality change)

Solution Approach 2:

The system changes the selection criteria from simply matching known physical properties to actively seeking target nodes with different physical property characteristics. By modifying the selection parameters to prioritize diversity while maintaining the self-organizing map's structural integrity, the system achieves both reliability and property diversity

Inventive Principle:

Principle #35Parameter changes

Data Source

PatentUS20250232083A1Recommendation data generation apparatus, recommendation data generation method, and non-transitory computer-readable medium

Publication Date: 2025.07.17 NEC CORP

AI summary

A recommendation data generation apparatus performs: acquiring a plurality of pieces of material specification information indicating a material specification; acquiring, for each material specification information, physical property information indicating a physical property value of each of a plurality of physical properties of a product that can be generated with the material specification indicated by the material specification information;-generating a self-organizing map in which a physical property vector indicating a value related to the physical property value is assigned to each node on a map space by using the physical property information; selecting at least one target node from among nodes in the self-organizing map based on arrangement of the nodes corresponding to respective pieces of the physical property information in the map space; generating recommendation data indicating the material specification corresponding to the target node.