國立高雄大學圖資館 |

語系: 繁體中文

說明(常見問題)

圖資館首頁

登入

回首頁

切換: 標籤 | MARC模式 | ISBD

以離群值偵測技術分析無人飛行載具飛行紀錄異常之研究 = Analyzin...

國立高雄大學資訊管理學系碩士班

以離群值偵測技術分析無人飛行載具飛行紀錄異常之研究 = Analyzing Abnormal Flying Logs of Unmanned Aerial Vehicle Using Outlier Detection Approach

紀錄類型:	書目-語言資料,印刷品 : 單行本
並列題名:	Analyzing Abnormal Flying Logs of Unmanned Aerial Vehicle Using Outlier Detection Approach
作者:	張至哲,
其他團體作者:	國立高雄大學
出版地:	[高雄市]
出版者:	撰者;
出版年:	2014[民103]
面頁冊數:	52面圖，表 : 30公分;
標題:	無人飛行載具
標題:	Unmanned Aerial Vehicle
電子資源:	http://handle.ncl.edu.tw/11296/ndltd/16462366760558274636
附註:	參考書目：面44-46
附註:	103年12月16日公開
摘要註:	無人飛行載具UAV(Unmanned Aerial Vehicle)發展至今已有多年歷史，由於它具有成本低、地域限制低、飛行風險低與即時性等特性，近年來更是快速發展並且普及化，跳脫傳統在軍事方面的使用而廣泛應用於不同領域中，例如：災害應變、環境監測、交通控制、都市計畫與農林漁牧等，相關研究也因應而生，例如：空拍定位、3D建模與目標物辨識技術等。無人飛行載具的普遍性使得其飛行穩定性逐漸成為隱憂，而飛行異常事件會直接影響飛行穩定性，當發生飛行異常時容易造成UAV墜毀甚至影響飛場人身安全，飛行異常事件包含：衛星導航異常、機械異常、動力異常與失速等。目前無人飛行載具研究多著重於應用研究，而飛行異常偵測研究則較少被研究領域所重視。本研究為UAV中之定翼機，探討衛星導航異常與機械異常對UAV飛行之影響並歸納正常飛行資料特性，在衛星導航運作正常時， UAV在自動飛行過程中，航點方位(Target Bearing)會依照飛行腳本所規劃的航線維持穩定角度飛行，因此本研究利用航點方位區別衛星導航正常與異常飛行資料。在機械正常運作情況下，偏航角(Yaw)與航點方位具有收斂特徵，其偏航角會隨時間而逐漸趨近於航點方位，因此本研究利用偏航角與航點方位區別機械運作正常與異常飛行資料。本研究依據上述正常飛行資料所觀察之特徵建立常態分佈模式，並以真實異常飛行資料作為驗證，藉此建立異常偵測模型區分正常與異常飛行資料。本研究將以離群值偵測技術，依據飛行資料特徵建立即時異常偵測模型，期望透過此模型供未來UAV飛行過程中即時評估是否潛藏衛星導航以及機械異常之風險，並將飛行紀錄回饋至飛行數據資料庫中做異常分析，藉此更新異常偵測模型使其在判別上更具準確性。 UAV(Unmanned Aerial Vehicle) has been developing for years. With the benefits of low cost, nearly no geographical restrictions, low risk of flight and immediate response, it has been rapidly developing in recent years and are widely used in various fields such as disaster response, environmental monitoring, traffic control, urban planning, etc. However, with UAV’s increasing popularity, the problem of stability during the flight emerges. An abnormal event affects not only the stability but also can be the root cause of UAV crash. Threatening properties and safety of people in the flying fields. We draw our attention to flight anomaly detection of UAV since most prior UAV studies focus on applied research.This research studies the impacts that mechanical abnormalities and abnormal satellite navigation brought to UAV. During UAV automatic flight, we found that the target bearing remained stable. Therefore, we consider target bearing as a characteristic to differentiate between normal and abnormal flying logs. Moreover, we also found that under normal circumstances, both value of yaw angle and target bearing converged. Therefore, we also consider yaw angle and target bearing as a characteristic to judge between the normal and the abnormal. With normal flight data, this research uses Normal Distribution (Gauss Distribution) and outlier detection techniques to create anomaly detection model. By using this model can detect abnormal satellite navigation events and the risk of mechanical abnormalities can be detected instantly. In the future, UAV flight logs will be sent into databases as feedbacks to make a more accurate model.

以離群值偵測技術分析無人飛行載具飛行紀錄異常之研究 = Analyzing Abnormal Flying Logs of Unmanned Aerial Vehicle Using Outlier Detection Approach
張, 至哲

以離群值偵測技術分析無人飛行載具飛行紀錄異常之研究 = Analyzing Abnormal Flying Logs of Unmanned Aerial Vehicle Using Outlier Detection Approach / 張至哲撰 - [高雄市] : 撰者, 2014[民103]. - 52面 ; 圖，表 ; 30公分.
參考書目：面44-46103年12月16日公開.
無人飛行載具Unmanned Aerial Vehicle

以離群值偵測技術分析無人飛行載具飛行紀錄異常之研究 = Analyzing Abnormal Flying Logs of Unmanned Aerial Vehicle Using Outlier Detection Approach
LDR:04890nam0a2200289 450 001 430158
005 20170214091033.0
009 430158
010 0 $b 精裝
010 0 $b 平裝
100 $a 20170214d2014 k y0chiy05 e
101 1 $a chi $d chi $d eng
102 $a tw
105 $a ak am 000yy
200 1 $a 以離群值偵測技術分析無人飛行載具飛行紀錄異常之研究 $d Analyzing Abnormal Flying Logs of Unmanned Aerial Vehicle Using Outlier Detection Approach $z eng $f 張至哲撰
210 $a [高雄市] $c 撰者 $d 2014[民103]
215 0 $a 52面 $c 圖，表 $d 30公分
300 $a 參考書目：面44-46
300 $a 103年12月16日公開
314 $a 指導教授：蕭漢威博士
328 $a 碩士論文--國立高雄大學資訊管理學系碩士班
330 $a 無人飛行載具UAV(Unmanned Aerial Vehicle)發展至今已有多年歷史，由於它具有成本低、地域限制低、飛行風險低與即時性等特性，近年來更是快速發展並且普及化，跳脫傳統在軍事方面的使用而廣泛應用於不同領域中，例如：災害應變、環境監測、交通控制、都市計畫與農林漁牧等，相關研究也因應而生，例如：空拍定位、3D建模與目標物辨識技術等。無人飛行載具的普遍性使得其飛行穩定性逐漸成為隱憂，而飛行異常事件會直接影響飛行穩定性，當發生飛行異常時容易造成UAV墜毀甚至影響飛場人身安全，飛行異常事件包含：衛星導航異常、機械異常、動力異常與失速等。目前無人飛行載具研究多著重於應用研究，而飛行異常偵測研究則較少被研究領域所重視。本研究為UAV中之定翼機，探討衛星導航異常與機械異常對UAV飛行之影響並歸納正常飛行資料特性，在衛星導航運作正常時， UAV在自動飛行過程中，航點方位(Target Bearing)會依照飛行腳本所規劃的航線維持穩定角度飛行，因此本研究利用航點方位區別衛星導航正常與異常飛行資料。在機械正常運作情況下，偏航角(Yaw)與航點方位具有收斂特徵，其偏航角會隨時間而逐漸趨近於航點方位，因此本研究利用偏航角與航點方位區別機械運作正常與異常飛行資料。本研究依據上述正常飛行資料所觀察之特徵建立常態分佈模式，並以真實異常飛行資料作為驗證，藉此建立異常偵測模型區分正常與異常飛行資料。本研究將以離群值偵測技術，依據飛行資料特徵建立即時異常偵測模型，期望透過此模型供未來UAV飛行過程中即時評估是否潛藏衛星導航以及機械異常之風險，並將飛行紀錄回饋至飛行數據資料庫中做異常分析，藉此更新異常偵測模型使其在判別上更具準確性。 UAV(Unmanned Aerial Vehicle) has been developing for years. With the benefits of low cost, nearly no geographical restrictions, low risk of flight and immediate response, it has been rapidly developing in recent years and are widely used in various fields such as disaster response, environmental monitoring, traffic control, urban planning, etc. However, with UAV’s increasing popularity, the problem of stability during the flight emerges. An abnormal event affects not only the stability but also can be the root cause of UAV crash. Threatening properties and safety of people in the flying fields. We draw our attention to flight anomaly detection of UAV since most prior UAV studies focus on applied research.This research studies the impacts that mechanical abnormalities and abnormal satellite navigation brought to UAV. During UAV automatic flight, we found that the target bearing remained stable. Therefore, we consider target bearing as a characteristic to differentiate between normal and abnormal flying logs. Moreover, we also found that under normal circumstances, both value of yaw angle and target bearing converged. Therefore, we also consider yaw angle and target bearing as a characteristic to judge between the normal and the abnormal. With normal flight data, this research uses Normal Distribution (Gauss Distribution) and outlier detection techniques to create anomaly detection model. By using this model can detect abnormal satellite navigation events and the risk of mechanical abnormalities can be detected instantly. In the future, UAV flight logs will be sent into databases as feedbacks to make a more accurate model.
510 1 $a Analyzing Abnormal Flying Logs of Unmanned Aerial Vehicle Using Outlier Detection Approach $z eng
610 0 $a 無人飛行載具 $a 無人飛行載具異常偵測 $a 離群值偵測
610 1 $a Unmanned Aerial Vehicle $a UAV anomaly detection $a Outlier detection
681 $a 008M/0019 $b 464105 1115.1 $v 2007年版
700 1 $a 張 $b 至哲 $4 撰 $3 673380
712 0 2 $a 國立高雄大學 $b 資訊管理學系碩士班 $3 353936
801 0 $a tw $b NUK $c 20141021 $g CCR
856 7 $z 電子資源 $2 http $u http://handle.ncl.edu.tw/11296/ndltd/16462366760558274636