Green Compact Shape Prediction Using Sintering Viscosity Curves

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Existing techniques for predicting the shape of a green compact during sintering, particularly in liquid-phase sintering, suffer from low accuracy due to the lack of a established physical model and the use of viscosity derived from the Arrhenius equation, which reduces prediction accuracy.

Innovation Solution

The method incorporates a temperature/viscosity curve where viscosity decreases from a first to a second viscosity at a predetermined threshold, combining sensitivity analysis, design of experiments, and machine learning to optimize parameters for high-accuracy shape prediction using finite element method (FEM) simulations.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Measurement precision

If machine learning model is used to predict green compact shape, then prediction capability is provided, but prediction accuracy is insufficient

Engineering Contradiction:
Improveshape prediction accuracyVSAvoidprediction reliability
Core Design Contradiction:
Measurement precisionVSReliability

Solution Approach 1:

The patent changes the parameter representation from using Arrhenius equation parameters (activation energy, frequency factor) to using temperature/viscosity curve parameters (temperature threshold value, first viscosity, second viscosity) that directly characterize the sintering behavior. This parameter transformation enables the machine learning model to achieve higher prediction accuracy by using parameters that more accurately reflect the physical reality of liquid-phase sintering.

Inventive Principle:
Principle #35Parameter changes

Solution Approach 2:

The patent introduces temperature/viscosity curves as an intermediary between the sintering process and the prediction model. These curves serve as a bridge that captures the complex relationship between temperature and viscosity during sintering, allowing the machine learning model to indirectly access critical sintering behavior information without requiring direct measurement of viscosity at each temperature point.

Inventive Principle:
Principle #24Intermediary (Mediator)

2Ease of manufacture

If Arrhenius equation is used to derive viscosity, then theoretical framework is provided, but prediction accuracy decreases

Engineering Contradiction:
Improvemodel implementation easeVSAvoidshape prediction precision
Core Design Contradiction:
Ease of manufactureVSManufacturing precision

Solution Approach 1:

Instead of using the traditional approach of deriving viscosity from the Arrhenius equation (temperature-based model), the patent inverts the approach by directly measuring and using temperature/viscosity curves obtained from actual sintering experiments. This inversion allows the model to capture the true sintering behavior without being constrained by theoretical assumptions, thereby improving prediction precision while maintaining implementation ease through direct experimental measurement.

Inventive Principle:
Principle #13The other way round (Inversion)

3Device complexity

If traditional prediction methods are used, then process simplicity is maintained, but deformation control is insufficient

Engineering Contradiction:
Improveprediction system complexityVSAvoidgreen compact shape control
Core Design Contradiction:
Device complexityVSShape

Solution Approach 1:

The patent performs preliminary measurement of temperature/viscosity curves through sensitivity analysis and design of experiments before implementing the prediction system. By pre-characterizing the sintering behavior of different powder materials and storing this information in a database, the system eliminates the need for complex real-time measurements during actual sintering, maintaining system simplicity while enabling accurate shape prediction and deformation control.

Inventive Principle:
Principle #10Preliminary action

Applied Scientific Principles

This section explains which scientific principles are used to turn an abstract innovation direction into a practical engineering solution.

Function Achieved in This Case

This approach enables precise prediction of the final compact shape, reducing trial and error, minimizing deformation, and lowering costs by optimizing parameter settings through a combination of temperature/viscosity curves, design of experiments, and machine learning.

Implementation Method 1

a temperature threshold value that is a temperature at which a viscosity of the fabrication object decreases from a first viscosity to a second viscosity due to the sintering

Methodology Applied
Scientific EffectViscosity decrease due to sintering: Sintering

Data Source

PatentEP4640342A1Information processing method, information processing apparatus, and carrier means for predicting sintering shape based on viscosity model
Publication Date: 2025.10.29 RICOH CO LTD
  • EP4640342A1 patent drawingFigure 1~2
  • EP4640342A1 patent drawingFigure 3
  • EP4640342A1 patent drawingFigure 4

AI summary

An information processing method is performed by an information processing apparatus and includes receiving (S301) a shape of a fabrication object after sintering, predicting (S303) a shape of the fabrication object before the sintering based on the shape of the fabrication object after the sintering and a prediction condition stored in a storage unit, and outputting (S304) information relating to the predicted shape of the fabrication object before the sintering. The prediction condition includes information based on a temperature threshold value that is a temperature at which a viscosity of the fabrication object decreases from a first viscosity to a second viscosity due to the sintering, the first viscosity, and the second viscosity.