Data-driven correction for anemometer in urban pedestrian level wind environment measurement with the aid of CFD database

DOI

Bibliographic Information

Other Title
  • 都市歩行者レベル風環境観測におけるCFDデータベースに基づくデータ駆動型風速計校正

Abstract

<p>Data-driven wind sensor correction based on wind observations and artificial neural networks (ANN) faces practical challenges due to the high temporal and equipment costs of collecting instantaneous wind speed data. This study aims to reduce the need for wind observations using a CFD database. In this report, we propose a two-stage prediction framework-based correction method and investigate the optimal construction of ANNs using the CFD database as training data. The results show that using measured data at one location and the CFD database as training data can improve the quantity and generalization performance of existing measured data, thereby enhancing the efficiency and accuracy of sensors at different locations.</p>

Journal

  • SEISAN KENKYU

    SEISAN KENKYU 76 (1), 25-31, 2024-02-01

    Institute of Industrial Science The University of Tokyo

Details 詳細情報について

  • CRID
    1390299229355548544
  • DOI
    10.11188/seisankenkyu.76.25
  • ISSN
    18812058
    0037105X
  • Text Lang
    ja
  • Data Source
    • JaLC
  • Abstract License Flag
    Disallowed

Report a problem

Back to top