# 機械学習モデルを用いたセラミックスにおける強度ばらつきと欠陥分布の関係の予測

https://mdr.nims.go.jp/datasets/6a0f7805-770c-4110-9b93-b179b562fbb9

## File

- [GTSJ 定期講演会_2025_C-9.pdf](https://mdr.nims.go.jp/filesets/c0b44244-8c1e-4bd5-a18b-0cff6b95d36e/download) ([Detail](https://mdr.nims.go.jp/filesets/c0b44244-8c1e-4bd5-a18b-0cff6b95d36e.md))

## Id

6a0f7805-770c-4110-9b93-b179b562fbb9

## Local identifier



## Visibility

open_to_public

## State

published

## Created at

2026-07-09T02:52:31.686514Z

## Updated at

2026-07-10T03:00:08.865448Z

## Published at

2026-07-10T05:25:01.968121Z

## Doi

https://doi.org/10.48505/nims.6396

## First published url

https://www.gtsj.or.jp/thesis/

## Date published



## Recorded date published

2025年

## Resource type

journal_article

## Manuscript type

authors_original

## Collection



## Title

- title: 機械学習モデルを用いたセラミックスにおける強度ばらつきと欠陥分布の関係の予測
  title_type: original
  lang: ja
- title: Prediction of relationship between strength scatter and defect distribution
    in ceramics using a machine learning model
  title_type: alternative
  lang: en

## Description

- description: Ceramics are widely used as heat-resistant structural materials, such
    as thermal barrier coatings for gas turbines. However, they exhibit probabilistic
    fracture behavior due to the size distribution of defects such as pores and grain
    boundaries present within them. Experimental evaluation of this strength scatter
    in ceramic components is both time-intensive and costly. Our previous work successfully
    predicted strength scatter based on fracture mechanics from microstructural information,
    but this approach incurs enormous computational costs for large-scale applications.
    In this study, we develop a deep learning–based surrogate model that predicts
    the Weibull distribution parameters of ceramic bending strength directly from
    equivalent crack length distributions, enabling substantial reductions in computational
    cost without sacrificing predictive accuracy. Furthermore, we develop an inverse
    analysis framework that couples the surrogate model with particle swarm optimization
    to estimate defect distributions from reference strength data. The proposed method
    achieves high accuracy and efficiency.
  description_type: abstract
  lang: jpn

## Creator

- name: 前田太陽
  role: author
  organization: 横浜国立大学
- name: 長田 俊郎
  role: author
  orcid: https://orcid.org/0000-0003-1539-9264
  organization: 物質・材料研究機構
  department: 構造材料研究センター/材料創製分野/高信頼性耐熱材料グループ
- name: 尾崎伸吾
  role: author
  organization: 横浜国立大学

## Contact agent



## Publisher

organization: 日本ガスタービン学会

## Managing organization



## Keyword

- subject: セラミックス
  schema: not_defined
- subject: 破壊統計
  schema: not_defined
- subject: サロゲートモデル
  schema: not_defined
- subject: 機械学習
  schema: not_defined

## Rights

- identifier: http://rightsstatements.org/vocab/InC/1.0/

## Other identifier(s)



## Data origin

- data_origin_type: other

## Embargo



## Journal

- title: 第53回日本ガスタービン学会定期講演会 講演論文集

## Conference



## Related item



## Funding



## Instrument



## Instrument operator



## Instrument managing organization



## Measurement method



## Specimen



## Chemical composition



## Structure for specimen



## Structural feature for specimen



## Specific property for specimen



## Process for specimen treatment



## Computational method



## Energy level/transition state



## Software



## Custom property



## Fileset

- id: c0b44244-8c1e-4bd5-a18b-0cff6b95d36e
  filename: GTSJ 定期講演会_2025_C-9.pdf
  content_type: application/pdf
  size: 1002296
  md5: 4446c97a1b98cb5bd2c5bdd83162a310

## Thumbnail

fileset_id: c0b44244-8c1e-4bd5-a18b-0cff6b95d36e
filename: GTSJ 定期講演会_2025_C-9.pdf