{"title":"不同载荷条件下无人机剩余飞行时间预测","authors":"Junchuan Shi, Wendy A. Okolo, Dazhong Wu","doi":"10.2514/1.i011198","DOIUrl":null,"url":null,"abstract":"Unmanned aerial vehicles (UAVs) are forecast to be widely used in the military and civilian domains. The remaining flying time is a critical parameter to monitor during a flight to ensure the safety of electric UAVs (e-UAVs). However, accurate remaining flying time prediction under different load conditions requires a large amount of data and is computationally expensive for online applications. To address these issues, a deep learning approach based on temporal convolutional networks and transfer learning is developed for lithium-ion battery systems for e-UAVs. A temporal convolutional network is used to extract features from monitoring data and predict the remaining flying time of flights under one load condition. A layer transfer strategy is then used to transfer the knowledge learned from one load condition to another load condition. Battery health monitoring data collected from a fixed-wing e-UAV are used to demonstrate the effectiveness of the proposed method. Experimental results show that the proposed temporal convolutional network with the transfer learning strategy can predict the remaining flying time of the e-UAV under two load conditions more efficiently and accurately than a temporal convolutional network without transfer learning.","PeriodicalId":50260,"journal":{"name":"Journal of Aerospace Information Systems","volume":"106 4","pages":"0"},"PeriodicalIF":1.3000,"publicationDate":"2023-11-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"Remaining Flying Time Prediction of Unmanned Aerial Vehicles Under Different Load Conditions\",\"authors\":\"Junchuan Shi, Wendy A. Okolo, Dazhong Wu\",\"doi\":\"10.2514/1.i011198\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"Unmanned aerial vehicles (UAVs) are forecast to be widely used in the military and civilian domains. The remaining flying time is a critical parameter to monitor during a flight to ensure the safety of electric UAVs (e-UAVs). However, accurate remaining flying time prediction under different load conditions requires a large amount of data and is computationally expensive for online applications. To address these issues, a deep learning approach based on temporal convolutional networks and transfer learning is developed for lithium-ion battery systems for e-UAVs. A temporal convolutional network is used to extract features from monitoring data and predict the remaining flying time of flights under one load condition. A layer transfer strategy is then used to transfer the knowledge learned from one load condition to another load condition. Battery health monitoring data collected from a fixed-wing e-UAV are used to demonstrate the effectiveness of the proposed method. Experimental results show that the proposed temporal convolutional network with the transfer learning strategy can predict the remaining flying time of the e-UAV under two load conditions more efficiently and accurately than a temporal convolutional network without transfer learning.\",\"PeriodicalId\":50260,\"journal\":{\"name\":\"Journal of Aerospace Information Systems\",\"volume\":\"106 4\",\"pages\":\"0\"},\"PeriodicalIF\":1.3000,\"publicationDate\":\"2023-11-07\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Journal of Aerospace Information Systems\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.2514/1.i011198\",\"RegionNum\":4,\"RegionCategory\":\"工程技术\",\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"Q2\",\"JCRName\":\"ENGINEERING, AEROSPACE\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Journal of Aerospace Information Systems","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.2514/1.i011198","RegionNum":4,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q2","JCRName":"ENGINEERING, AEROSPACE","Score":null,"Total":0}
Remaining Flying Time Prediction of Unmanned Aerial Vehicles Under Different Load Conditions
Unmanned aerial vehicles (UAVs) are forecast to be widely used in the military and civilian domains. The remaining flying time is a critical parameter to monitor during a flight to ensure the safety of electric UAVs (e-UAVs). However, accurate remaining flying time prediction under different load conditions requires a large amount of data and is computationally expensive for online applications. To address these issues, a deep learning approach based on temporal convolutional networks and transfer learning is developed for lithium-ion battery systems for e-UAVs. A temporal convolutional network is used to extract features from monitoring data and predict the remaining flying time of flights under one load condition. A layer transfer strategy is then used to transfer the knowledge learned from one load condition to another load condition. Battery health monitoring data collected from a fixed-wing e-UAV are used to demonstrate the effectiveness of the proposed method. Experimental results show that the proposed temporal convolutional network with the transfer learning strategy can predict the remaining flying time of the e-UAV under two load conditions more efficiently and accurately than a temporal convolutional network without transfer learning.
期刊介绍:
This Journal is devoted to the dissemination of original archival research papers describing new theoretical developments, novel applications, and case studies regarding advances in aerospace computing, information, and networks and communication systems that address aerospace-specific issues. Issues related to signal processing, electromagnetics, antenna theory, and the basic networking hardware transmission technologies of a network are not within the scope of this journal. Topics include aerospace systems and software engineering; verification and validation of embedded systems; the field known as ‘big data,’ data analytics, machine learning, and knowledge management for aerospace systems; human-automation interaction and systems health management for aerospace systems. Applications of autonomous systems, systems engineering principles, and safety and mission assurance are of particular interest. The Journal also features Technical Notes that discuss particular technical innovations or applications in the topics described above. Papers are also sought that rigorously review the results of recent research developments. In addition to original research papers and reviews, the journal publishes articles that review books, conferences, social media, and new educational modes applicable to the scope of the Journal.