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

Automatic control logic utilizing sparse modeling for natural ventilation operation

Research Project

Project/Area Number 19K04741
Research Category

Grant-in-Aid for Scientific Research (C)

Allocation TypeMulti-year Fund
Section一般
Review Section Basic Section 23020:Architectural environment and building equipment-related
Research InstitutionMeiji University

Principal Investigator

Hiyama Kyosuke  明治大学, 理工学部, 専任教授 (10533664)

Co-Investigator(Kenkyū-buntansha) Srisamranrungruang Thanyalak  明治大学, 研究・知財戦略機構(生田), 研究推進員(ポスト・ドクター) (40837267)
Project Period (FY) 2019-04-01 – 2023-03-31
Project Status Completed (Fiscal Year 2022)
Budget Amount *help
¥4,420,000 (Direct Cost: ¥3,400,000、Indirect Cost: ¥1,020,000)
Fiscal Year 2021: ¥1,040,000 (Direct Cost: ¥800,000、Indirect Cost: ¥240,000)
Fiscal Year 2020: ¥1,950,000 (Direct Cost: ¥1,500,000、Indirect Cost: ¥450,000)
Fiscal Year 2019: ¥1,430,000 (Direct Cost: ¥1,100,000、Indirect Cost: ¥330,000)
Keywords自然換気 / 機械学習 / 運用 / 温熱環境 / シミュレーション / 自動制御 / AI / ビッグデータ
Outline of Research at the Start

昨今、自動制御による自然換気システムを導入した建築物が増加しているが、設計時に期待した省エネ効果を実現できない事例も多く、一部においてはその運用が中止するに至る。この理由として、自然換気時の室内環境の不安定性の他、外部騒音や自然換気窓の開閉音等、音に起因する執務者の不満が挙げられる。本研究では、この二要素を加味した自然換気口の開閉ロジックを開発する。特に動作頻度の制御に関しては、高精度なフィードフォワード制御が必要であり、本研究ではその精度向上を目的とし、物理モデルを機械学習で補完する手法を提案する。

Outline of Final Research Achievements

The objective of this research is to develop an automatic control logic for natural ventilation openings that eliminates the dissatisfaction of workers and operators while guaranteeing the energy-saving effects of natural ventilation expected by designers. The developed automatic control logic is based on a policy of improving the indoor environment during natural ventilation operation by utilizing environmental prediction technology based on physical models and machine learning.
The effectiveness of the trial model, which was developed throughout the research period, was confirmed through case studies. In the case study, by simplifying the setting task to select the preferred natural ventilation window opening pattern of full-open and half-open throughout the day, we realized a learning model that can function redundantly even in situations where data size is small, which is the issue in this study.

Academic Significance and Societal Importance of the Research Achievements

特徴量変数の数と種類を設計変数としたパラメトリックスタディにおいては、特徴量変数を減少させることにより、モデルの冗長性を向上させるものの、運用の継続におけるデータ量の増加による予測精度向上の効果が小さくなる傾向が示された。また、その入力データの環境工学的知見に基づく加工の有無が、モデルの冗長性に影響をあたることも明らかにした。この建築環境工学の知見の導入に関しては、事前に対象建物を再現した仮想モデルにおけるシミュレーションを通し、建築物の特徴と気象の関係を明らかにする事前作業が有用であり、その方法論に関しては、建築環境工学が対象とする他の課題にも適用可能である点が本研究の学術的な意義となる。

Report

(5 results)
  • 2022 Annual Research Report   Final Research Report ( PDF )
  • 2021 Research-status Report
  • 2020 Research-status Report
  • 2019 Research-status Report
  • Research Products

    (6 results)

All 2023 2022 2020 2019

All Journal Article (5 results) (of which Peer Reviewed: 5 results,  Open Access: 3 results) Presentation (1 results) (of which Int'l Joint Research: 1 results)

  • [Journal Article] Low-carbon assessment of building facades using dynamic CO2 intensity of electricity generation in Japan2023

    • Author(s)
      Hiyama Kyosuke、Srisamranrungruang Thanyalak
    • Journal Title

      Energy and Buildings

      Volume: 278 Pages: 112637-112637

    • DOI

      10.1016/j.enbuild.2022.112637

    • Related Report
      2022 Annual Research Report
    • Peer Reviewed
  • [Journal Article] Regional adaptivity of electrochromic glazing in Japan and operational improvement in energy saving using machine learning2022

    • Author(s)
      Kobayashi Takuma、Hiyama Kyosuke、Omodaka Yuichi、Oura Yutaka、Asaoka Yukiyasu
    • Journal Title

      JAPAN ARCHITECTURAL REVIEW

      Volume: 5 Issue: 3 Pages: 269-278

    • DOI

      10.1002/2475-8876.12272

    • Related Report
      2022 Annual Research Report
    • Peer Reviewed / Open Access
  • [Journal Article] Operation strategy for engineered natural ventilation using machine learning under sparse data conditions2022

    • Author(s)
      Kyosuke Hiyama, Kenichiro Takeuchi, Yuichi Omodaka, Thanyalak Srisamranrungruang
    • Journal Title

      Japan Architectural Review

      Volume: 5 Issue: 1 Pages: 119-126

    • DOI

      10.1002/2475-8876.12255

    • NAID

      210000170168

    • Related Report
      2021 Research-status Report
    • Peer Reviewed / Open Access
  • [Journal Article] Regional classification maps for engineered natural ventilation design of office buildings in Japan2020

    • Author(s)
      Hiyama Kyosuke
    • Journal Title

      JAPAN ARCHITECTURAL REVIEW

      Volume: 4 Issue: 1 Pages: 253-261

    • DOI

      10.1002/2475-8876.12201

    • NAID

      210000180048

    • Related Report
      2020 Research-status Report
    • Peer Reviewed / Open Access
  • [Journal Article] Balancing of natural ventilation, daylight, thermal effect for a building with double-skin perforated facade (DSPF)2020

    • Author(s)
      Thanyalak Srisamranrungruang, Kyosuke Hiyama
    • Journal Title

      Energy and Buildings

      Volume: 210 Pages: 109765-109765

    • DOI

      10.1016/j.enbuild.2020.109765

    • Related Report
      2019 Research-status Report
    • Peer Reviewed
  • [Presentation] Practical natural ventilation performance metric based on thermal autonomy for sustainable building design2019

    • Author(s)
      Kyosuke Hiyama
    • Organizer
      Clima2019
    • Related Report
      2019 Research-status Report
    • Int'l Joint Research

URL: 

Published: 2019-04-18   Modified: 2024-01-30  

Information User Guide FAQ News Terms of Use Attribution of KAKENHI

Powered by NII kakenhi