Self-Organizing Map for Material Recommendation
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing systems for product development, such as those using self-organizing maps, are limited to determining important design variables and do not provide a comprehensive approach for searching materials that can generate products with desired physical properties.
Innovation Solution
A recommendation data generation apparatus that acquires material specification and physical property information, generates a self-organizing map with physical property vectors, assigns specification vectors to nodes, detects target nodes with desired physical properties, and generates recommendation data for materials that can produce products with those properties.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Adaptability or versatility
If a self-organizing map is used to determine important design variables, then the analysis of design variables can be performed, but the system cannot search for materials that can generate products with desired physical properties
Solution Approach 1:
The self-organizing map system is extended to perform multiple functions: it not only determines important design variables but also searches for materials that can generate products with desired physical properties. The specification assignment unit assigns material specification vectors to nodes, enabling the system to recommend materials based on desired product properties, thus achieving multi-functionality.
2Measurement precision
If comprehensive material search is performed to find materials with desired physical properties, then material specification accuracy is improved, but computational cost and time increase
Solution Approach 1:
The system performs preliminary organization of material specification information and physical property information in a self-organizing map structure before actual material search. By pre-assigning specification vectors to nodes and organizing data spatially, the system prepares the information structure in advance, enabling fast retrieval and recommendation when desired physical properties are specified, thus reducing computational time during actual search operations.
Data Source
AI summary
A recommendation data generation apparatus (2000) acquires material specification information (10) representing a material specification of a material (60) and physical property information (20) representing a physical property of a product (70). The recommendation data generation apparatus (2000) generates a self-organizing map (30) by using the physical property information (20). Each node on the self-organizing map (30) is assigned a position in a map space and a physical property vector representing a physical property. The recommendation data generation apparatus (2000) assigns each node a specification vector representing the material specification by using the material specification information (10). The recommendation data generation apparatus (2000) acquires target information (80) representing a desired physical property, and detects a target node to which a physical property vector matching that physical property is assigned. The recommendation data generation apparatus (2000) generates, by using the specification vector assigned to the target node, recommendation data (90) representing the material specification with which a product (70) having a desired physical property can be generated.