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

2023 Fiscal Year Final Research Report

Understanding drill bit motion through measurement integrated analysis and identifying drilling conditions through machine learning

Research Project

  • PDF
Project/Area Number 20H02380
Research Category

Grant-in-Aid for Scientific Research (B)

Allocation TypeSingle-year Grants
Section一般
Review Section Basic Section 24020:Marine engineering-related
Research InstitutionJapan Agency for Marine-Earth Science and Technology

Principal Investigator

Inoue Tomoya  国立研究開発法人海洋研究開発機構, 技術開発部, 主任研究員 (10359127)

Co-Investigator(Kenkyū-buntansha) 鈴木 博善  大阪大学, 大学院工学研究科, 教授 (00252601)
和田 良太  東京大学, 大学院新領域創成科学研究科, 准教授 (20724420)
中川 友進  国立研究開発法人海洋研究開発機構, 研究プラットフォーム運用開発部門, 特任研究員 (50513454)
勝井 辰博  神戸大学, 海洋底探査センター, 教授 (80343416)
Project Period (FY) 2020-04-01 – 2023-03-31
Keywords海洋掘削 / ドリルパイプダイナミクス
Outline of Final Research Achievements

We performed theoretical analysis using a mathematical model as well as numerical analysis of drill bit motion and demonstrated its characteristics. We also proposed a method to understand the drilling status via detecting anomalies, understanding geological formations, and predicting sediment properties and core recovery rates using drill bit motion analysis and machine learning. We performed predictions based on data obtained from Chikyu's past cruises. The effectiveness of proposed method was confirmed.
Furthermore, with the aim of real-time understanding of the drill bit motion and drilling conditions during drilling operations, we have developed drilling data acquisition and transfer system, and a data integrated analysis method uses drilling data as input to provide the drill bit motion and drilling conditions in real-time. We conducted a practical test of the real-time drill bit analysis during the actual drilling operations and confirmed the method and system.

Free Research Field

船舶海洋工学

Academic Significance and Societal Importance of the Research Achievements

ドリルビット挙動解析,機械学習を用いた掘削状態予測手法,掘削データ取得装置,リアルタイム解析システムの開発を行った.これらにより,掘削操業に大きな影響を与えるものでありながら実操業において計測不可能なドリルビット挙動を示すことができ,また,掘削地層予測など掘削状態を提示することができ,掘削操業への貢献が期待できる.また,本研究課題で開発した掘削データ取得装置により,掘削航海中のデータの取得が可能となり,このデータを公開することができれば,海洋掘削に関する研究の進展に貢献できる.

URL: 

Published: 2025-01-30  

Information User Guide FAQ News Terms of Use Attribution of KAKENHI

Powered by NII kakenhi