Spring Steel Property Prediction Using Surface and XRD Data

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Existing methods struggle to accurately predict the properties of steel, particularly dislocation density and solid-solution carbon content, and fail to effectively quantify time-dependent properties like strain and fatigue from map data.

Innovation Solution

A learning model is employed to analyze both surface and internal information of spring steel, using parameters from SEM observations and XRD to quantify finer structures, enabling accurate prediction of material properties such as hardness, tensile properties, and time-dependent properties like strain and fatigue.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Productivity

If machine learning is performed using map data from optical microscopes and scanning electron microscopes, then material property prediction becomes faster and easier, but prediction accuracy for dislocation density and solid-solution carbon content deteriorates

Engineering Contradiction:

Improveprediction speedVSAvoidprediction accuracy

Core Design Contradiction:

ProductivityVSMeasurement precision

Solution Approach 1:

The patent introduces XRD analysis as an intermediary measurement technique between the microscope map data and the target properties. XRD provides intermediate data about crystal structure, dislocation density, and solid-solution carbon content that serves as a bridge, enabling the machine learning model to achieve both fast prediction and high accuracy for dislocation density and carbon content.

Inventive Principle:

Principle #24Intermediary (Mediator)

Solution Approach 2:

The patent replaces direct mechanical/visual observation methods (optical microscope, SEM) with XRD-based measurement for certain properties. XRD uses diffraction physics to indirectly measure dislocation density and solid-solution carbon content, substituting direct imaging with a physics-based indirect measurement that provides more accurate quantitative data for these specific parameters.

Inventive Principle:

Principle #28Mechanics substitution (Replace mechanical system)

2Device complexity

If only surface information is used for analysis, then the analysis process is simpler and faster, but prediction accuracy for internal properties deteriorates

Engineering Contradiction:

Improveanalysis complexityVSAvoidprediction accuracy

Core Design Contradiction:

Device complexityVSMeasurement precision

Solution Approach 1:

The patent merges surface information from optical microscopes and scanning electron microscopes with internal information from XRD analysis. This combination of multiple information sources (surface morphology + internal crystal structure) enables accurate prediction of both surface and internal properties without significantly increasing analysis complexity, as the integration is performed through a unified machine learning framework.

Inventive Principle:

Principle #5Merging (Combining)

Data Source

PatentUS20260023002A1Analysis method, non-transitory computer-readable storage medium, and analysis device

Publication Date: 2026.01.22 NHK SPRING CO LTD

AI summary

An analysis method includes providing first material information obtained from a first spring steel of an analysis target to a learning model, the learning model having learned a relationship between material information and property information, the material information including first information obtained from a surface of spring steel and second information obtained from the interior of the spring steel, and the property information representing material properties of the spring steel, and obtaining first property information on the first spring steel from the learning model.