• Search Research Projects
  • Search Researchers
  • How to Use
  1. Back to previous page

Development of Artificial Intelligence that Automatically builds first-principle models from the literature

Research Project

Project/Area Number 21K18849
Research Category

Grant-in-Aid for Challenging Research (Exploratory)

Allocation TypeMulti-year Fund
Review Section Medium-sized Section 27:Chemical engineering and related fields
Research InstitutionKyoto University

Principal Investigator

KANO Manabu  京都大学, 情報学研究科, 教授 (30263114)

Co-Investigator(Kenkyū-buntansha) 加藤 祥太  京都大学, 情報学研究科, 助教 (60883402)
Project Period (FY) 2021-07-09 – 2023-03-31
Project Status Completed (Fiscal Year 2022)
Budget Amount *help
¥6,500,000 (Direct Cost: ¥5,000,000、Indirect Cost: ¥1,500,000)
Fiscal Year 2022: ¥2,340,000 (Direct Cost: ¥1,800,000、Indirect Cost: ¥540,000)
Fiscal Year 2021: ¥4,160,000 (Direct Cost: ¥3,200,000、Indirect Cost: ¥960,000)
Keywords人工知能 / 第一原理モデル / 物理モデル / 自然言語処理 / 数式処理 / 化学工学 / プロセスシステム工学 / デジタルツイン
Outline of Research at the Start

プロセス産業の生産現場におけるデジタルトランスフォーメーション(DX)を実現し,生産性革新を進めるために,デジタルツインが期待されている.しかし,特にデータ取得が困難な状況下で不可欠な第一原理モデル(物理モデル)の構築には膨大な手間がかかる.本研究では,対象プロセスを指定されると,関連する文献を収集し,文献中の変数や数式の意味を理解し,モデル構築に必要な情報を抽出・編集し,第一原理モデルを自動的に構築する人工知能(AI)の実現を究極目標として,必要な要素技術とプロトタイプの開発を行う.

Outline of Final Research Achievements

To optimize the design and operation of a manufacturing process, a first-principle model (physical model) of the process plays a crucial role. However, building such a model requires an enormous effort. The ultimate goal of this research is to realize an artificial intelligence (AI) that automatically builds a first-principle model by collecting relevant literature, understanding the meaning of variables and formulas in the literature, and extracting and editing information necessary for model construction, given a target process. We developed several elemental technologies, including a method for extracting variables and their definitions and a method for determining the equivalence of variables and formulas, and also we developed a prototype of AI.

Academic Significance and Societal Importance of the Research Achievements

様々な能力を持つ人工知能(AI)が開発され,活用されている.しかし,製造業で決定的に重要でありながらその構築が困難な第一原理モデルを自動的に構築してくれるAIを開発しようという試みは本研究が世界初である.自然言語処理や数式処理の新しい方法論を開発するという点で学術的意義が大きいのみならず,第一原理モデル自動構築AIが完成すれば,製造業の生産性を劇的に向上させることができるため,その社会的意義も計り知れない.

Report

(3 results)
  • 2022 Annual Research Report   Final Research Report ( PDF )
  • 2021 Research-status Report
  • Research Products

    (25 results)

All 2023 2022 2021

All Presentation (25 results) (of which Int'l Joint Research: 9 results)

  • [Presentation] Efficient physical model building algorithm using equations extracted from documents2023

    • Author(s)
      Shota Kato, Manau Kano
    • Organizer
      33rd European Symposium on Computer-aided Process Engineering (ESCAPE33)
    • Related Report
      2022 Annual Research Report
    • Int'l Joint Research
  • [Presentation] 化学工学関連論文中の命名法と数式に基づく変数定義予測手法2023

    • Author(s)
      加藤 祥太,加納 学
    • Organizer
      第37回人工知能学会全国大会
    • Related Report
      2022 Annual Research Report
  • [Presentation] 化学工学関連論文中の命名法に基づく変数定義予測手法2023

    • Author(s)
      加藤 祥太,加納 学
    • Organizer
      第255回自然言語処理研究会
    • Related Report
      2022 Annual Research Report
  • [Presentation] 化学工学関連文書の変数を理解するための言語モデル構築手法2023

    • Author(s)
      加藤 祥太,張 純朴,山本 蒔志,加納 学
    • Organizer
      化学工学会第88年会
    • Related Report
      2022 Annual Research Report
  • [Presentation] 二段階のファインチューニングを行ったBERTによる変数定義抽出2023

    • Author(s)
      山本 蒔志,加藤 祥太,加納 学
    • Organizer
      言語処理学会第29回年次大会
    • Related Report
      2022 Annual Research Report
  • [Presentation] 数学的表現の構造的情報のトークン化手法によるProcessBERT の性能改善2023

    • Author(s)
      張 純朴,加藤 祥太,加納 学
    • Organizer
      言語処理学会第29回年次大会
    • Related Report
      2022 Annual Research Report
  • [Presentation] 化学工学分野の論文に含まれる命名法に基づく変数記号および定義の解析2023

    • Author(s)
      加藤 祥太,加納 学
    • Organizer
      言語処理学会第29回年次大会
    • Related Report
      2022 Annual Research Report
  • [Presentation] Language model for understanding variables in documents on chemical engineering2023

    • Author(s)
      加藤 祥太
    • Organizer
      NII MathNL 2nd Seminar
    • Related Report
      2022 Annual Research Report
  • [Presentation] Variable Definition Extraction from Documents on Chemical Processes Utilizing Semantic Information on Variable Symbols and Definitions2022

    • Author(s)
      Masaki Numoto, Shota Kato, Manabu Kano
    • Organizer
      The 10th Asian Symposium on Process Systems Engineering (PSE Asia 2022)
    • Related Report
      2022 Annual Research Report
    • Int'l Joint Research
  • [Presentation] Annotation Tool for Variable Extraction from Documents on Manufacturing Processes2022

    • Author(s)
      Shota Kato, Manabu Kano
    • Organizer
      The 10th Asian Symposium on Process Systems Engineering (PSE Asia 2022)
    • Related Report
      2022 Annual Research Report
    • Int'l Joint Research
  • [Presentation] Equivalence Judgment of Equation Groups Representing Process Dynamics2022

    • Author(s)
      Chunpu Zhang, Shota Kato, Manabu Kano
    • Organizer
      The 14th International Symposium on Process Systems Engineering (PSE 2021+)
    • Related Report
      2022 Annual Research Report
    • Int'l Joint Research
  • [Presentation] Towards An Automated Physical Model Builder: CSTR Case Study2022

    • Author(s)
      Shota Kato, Manabu Kano
    • Organizer
      The 14th International Symposium on Process Systems Engineering (PSE 2021+)
    • Related Report
      2022 Annual Research Report
    • Int'l Joint Research
  • [Presentation] ProcessBERT: A Pre-trained Language Model for Judging Equivalence of Variable Definitions in Process Models2022

    • Author(s)
      Shota Kato, Kazuki Kanegami, Manabu Kano
    • Organizer
      13th IFAC Symposium on Dynamics and Control of Process Systems, including Biosystems (DYCOPS 2022)
    • Related Report
      2022 Annual Research Report
    • Int'l Joint Research
  • [Presentation] 変数消去順序を考慮した数式群同義性判定手法2022

    • Author(s)
      加藤 祥太,張 純朴,加納 学
    • Organizer
      化学工学会第53回秋季大会
    • Related Report
      2022 Annual Research Report
  • [Presentation] 化学工学分野の専門用語を理解するBERTモデルの開発2022

    • Author(s)
      加藤 祥太,加納 学
    • Organizer
      NLP若手の会第17回シンポジウム
    • Related Report
      2022 Annual Research Report
  • [Presentation] Towards Automated Physical Model Builder2022

    • Author(s)
      加藤 祥太
    • Organizer
      NII MathNL 1st Seminar
    • Related Report
      2022 Annual Research Report
  • [Presentation] 物理モデル自動構築に向けて:1)変数アノテーションツールの開発2022

    • Author(s)
      加藤祥太
    • Organizer
      化学工学会第87年会
    • Related Report
      2021 Research-status Report
  • [Presentation] 物理モデル自動構築に向けて:2)ProcessBERT化学工学のための事前学習言語モデル2022

    • Author(s)
      加藤祥太
    • Organizer
      化学工学会第87年会
    • Related Report
      2021 Research-status Report
  • [Presentation] 物理モデル自動構築AIの実現に向けたProcessBERTの構築2022

    • Author(s)
      加藤祥太
    • Organizer
      第9回計測自動制御学会制御部門マルチシンポジウム
    • Related Report
      2021 Research-status Report
  • [Presentation] ProcessBERT: A Pre-trained Language Model for Judging Equivalence of Variable Definitions in Process Models2022

    • Author(s)
      Shota Kato
    • Organizer
      The 13th IFAC Symposium on Dynamics and Control of Process Systems, including Biosystems (DYCOPS)
    • Related Report
      2021 Research-status Report
    • Int'l Joint Research
  • [Presentation] Towards an automated physical model building system: CSTR Case Study2022

    • Author(s)
      Shota Kato
    • Organizer
      The 14th International Symposium on Process Systems Engineering (PSE2021+)
    • Related Report
      2021 Research-status Report
    • Int'l Joint Research
  • [Presentation] Equivalence judgment of equation groups representing process dynamics2022

    • Author(s)
      Chunpu Zhang
    • Organizer
      The 14th International Symposium on Process Systems Engineering (PSE2021+)
    • Related Report
      2021 Research-status Report
    • Int'l Joint Research
  • [Presentation] 製造プロセスの物理モデルを文献から自動生成するAIの開発2021

    • Author(s)
      加藤祥太
    • Organizer
      NLP若手の会第16回シンポジウム
    • Related Report
      2021 Research-status Report
  • [Presentation] 複数文献中の変数の同義性判定手法の開発2021

    • Author(s)
      金上和毅
    • Organizer
      NLP若手の会第16回シンポジウム
    • Related Report
      2021 Research-status Report
  • [Presentation] 計算機代数システムを用いた数式群の同義性判定手法2021

    • Author(s)
      張純朴
    • Organizer
      NLP若手の会第16回シンポジウム
    • Related Report
      2021 Research-status Report

URL: 

Published: 2021-07-13   Modified: 2024-01-30  

Information User Guide FAQ News Terms of Use Attribution of KAKENHI

Powered by NII kakenhi