CAUSAL RELATIONSHIP MODEL VERIFICATION METHOD AND SYSTEM, AND FAILURE CAUSE EXTRACTION SYSTEM

PROBLEM TO BE SOLVED: To provide a system effectively using a causal relation model obtained from manufacturing process data to facilitate verification based on domain knowledge.SOLUTION: Provided is a causal relationship model verification method in an information processor including an input devic...

Full description

Saved in:
Bibliographic Details
Main Authors HORIWAKI KAZUKI, IMAZAWA KEI
Format Patent
LanguageEnglish
Japanese
Published 15.11.2018
Subjects
Online AccessGet full text

Cover

Loading…
More Information
Summary:PROBLEM TO BE SOLVED: To provide a system effectively using a causal relation model obtained from manufacturing process data to facilitate verification based on domain knowledge.SOLUTION: Provided is a causal relationship model verification method in an information processor including an input device, a display device, a processor, and a storage device. Executed in this method is a first step of acquiring, from the input device or the storage device, quality data as a result of evaluation of a resulting product, monitor data indicating a parameter upon generation of the resulting product, and domain knowledge indicating mutual relationship between the quality data and the monitor data. Next, the processor executes a second step of, by using a causal relationship model construction condition acquired from the input device or the storage device where the quality data and the monitor data are provided as nodes, constructing a causal relationship model defining relationship between the nodes. Also executed is a third step of performing at least one of comparison processing performed by the processor and comparison display performed by the display device for the causal relationship model and the domain knowledge.SELECTED DRAWING: Figure 5 【課題】製造工程データにより得られた因果関係モデルを有効活用し、ドメイン知識による検証を容易にするシステムを提供する。【解決手段】入力装置、表示装置、処理装置、および記憶装置を備える情報処理装置における、因果関係モデルの検証方法である。この方法では、入力装置あるいは記憶装置から、結果物の評価結果である品質データ、結果物を生成する際のパラメータを示すモニタデータ、および、品質データおよびモニタデータ相互の関係を示すドメイン知識を取得する第1のステップを実行する。また、処理装置が、入力装置あるいは記憶装置から取得される因果関係モデル構築条件を用い、品質データおよびモニタデータをノードとし、ノード間の関係を規定する因果関係モデルを構築する第2のステップを実行する。また、因果関係モデルとドメイン知識の、処理装置による比較処理および表示装置による比較表示の少なくともひとつを行う第3のステップを実行する。【選択図】 図5
Bibliography:Application Number: JP20170083068