無人機磁力探勘與異常視覺化分析系統;Unmanned Aerial Vehicle Magnetic Survey and Anomaly Visualization Analysis System

NCUIR > College of Electrical Engineering & Computer Science > International Graduate Program in Artificial Intelligence > Electronic Thesis & Dissertation > Item 987654321/94413

Please use this identifier to cite or link to this item: http://ir.lib.ncu.edu.tw/handle/987654321/94413

Title:	無人機磁力探勘與異常視覺化分析系統;Unmanned Aerial Vehicle Magnetic Survey and Anomaly Visualization Analysis System
Authors:	楊承學;Yang, Cheng-xue
Contributors:	人工智慧國際碩士學位學程
Keywords:	無人機;磁力探勘;異常視覺化;分析系統;分散式資料分發服務;Drone;Magnetic Survey;Anomaly Visualization;Analysis System;Data Distribution Service
Date:	2024-08-13
Issue Date:	2024-10-09 14:41:44 (UTC+8)
Publisher:	國立中央大學
Abstract:	傳統的磁場探測方法受到地形和範圍的限制，效率通常較低。為了解決這些問題，本論文提出一種無人機磁力探測及異常視覺化分析系統，結合無人機技術與磁場感測器，利用無人機的高機動性，於大範圍區域收集磁場數據，大幅減少探測與分析的時間。此系統除了具備磁場數據收集功能外，也提供無人機自動控制、機器學習模型分析磁場數據以及視覺化輸出等三大功能。無人機自動控制使用穩定且可靠的分散式資料服務(DDS)與無人機連線，負責規劃磁場探測飛行路徑；通過霍爾效應感測器收集地面磁場數據；再由數據分析模組對磁場數據進行分析，同時以孤立森林演算法標記磁場異常區域；而視覺化模組則將分析結果透過二維和三維圖像直觀呈現，協助使用者進行深入分析和作出決策。實驗結果顯示，本系統能夠在複雜環境中迅速且精確地完成磁場探測任務，有效識別地下磁場異常。相比傳統方法，大幅提升了探測的時效性和精確性。 ;Traditional magnetic field detection methods are often constrained by terrain and range limitations, resulting in lower efficiency. To address these issues, this paper proposes a drone-based magnetic detection and anomaly visualization analysis system. The system integrates drone technology with magnetic field sensors, leveraging the high mobility of drones to collect magnetic field data over large areas, thereby significantly reducing the time required for detection and analysis. The system comprises three major functionalities: magnetic field data collection, automatic drone control, and machine learning-based data analysis and visualization. The automatic drone control employs a stable and reliable Data Distribution Service (DDS) to connect with the drone and plan the magnetic detection flight path. Ground magnetic field data is collected using Hall effect sensors. The data analysis module processes the magnetic field data, utilizing the Isolation Forest algorithm to identify and mark anomalous magnetic field regions. The visualization module then presents the analysis results intuitively through two-dimensional (2D) and three-dimensional (3D) images, aiding users in conducting in-depth analyses and making informed decisions. Experimental results demonstrate that the proposed system can efficiently and accurately perform magnetic field detection tasks in complex environments, effectively identifying underground magnetic anomalies. Compared to traditional methods, this system significantly enhances detection timeliness and accuracy.
Appears in Collections:	[ International Graduate Program in Artificial Intelligence ] Electronic Thesis & Dissertation

Files in This Item:

File	Description	Size	Format
index.html		0Kb	HTML	36	View/Open

社群 sharing

Loading...