利用长短期记忆网络预测飞行员在空中遭遇时的行为

IF 1 4区工程技术 Q3 ENGINEERING, AEROSPACE

Proceedings of the Institution of Mechanical Engineers Part G-Journal of Aerospace Engineering Pub Date : 2023-08-30 DOI:10.1177/09544100231198150

Yang Hu, Xiaoyan Wang

{"title":"利用长短期记忆网络预测飞行员在空中遭遇时的行为","authors":"Yang Hu, Xiaoyan Wang","doi":"10.1177/09544100231198150","DOIUrl":null,"url":null,"abstract":"Characterized by the wide use of advanced automation and the introduction of new operation concepts, the future air transportation system will be more complex. Advanced pilot behavior models with improved capability are required to support the design and analysis of the midair encounter situations in the future air transportation system. This paper first filters midair encounter data from Automatic Dependent Surveillance-Broadcast (ADS-B) observations. Based on the acquired midair encounter data, a comprehensive pilot behavior model is proposed based on a multi-layer Long Short-Term Memory (LSTM) network. The model is designed for the purpose of enhancing the predicting capability of pilot behaviors in both horizontal and vertical planes. Finally, the performance of the proposed model to predict pilot behavior in both horizontal and vertical planes is studied through evaluating against realistic midair encounter situations.","PeriodicalId":54566,"journal":{"name":"Proceedings of the Institution of Mechanical Engineers Part G-Journal of Aerospace Engineering","volume":"42 1","pages":""},"PeriodicalIF":1.0000,"publicationDate":"2023-08-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"Predicting pilot behavior during midair encounters using long short-term memory network\",\"authors\":\"Yang Hu, Xiaoyan Wang\",\"doi\":\"10.1177/09544100231198150\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"Characterized by the wide use of advanced automation and the introduction of new operation concepts, the future air transportation system will be more complex. Advanced pilot behavior models with improved capability are required to support the design and analysis of the midair encounter situations in the future air transportation system. This paper first filters midair encounter data from Automatic Dependent Surveillance-Broadcast (ADS-B) observations. Based on the acquired midair encounter data, a comprehensive pilot behavior model is proposed based on a multi-layer Long Short-Term Memory (LSTM) network. The model is designed for the purpose of enhancing the predicting capability of pilot behaviors in both horizontal and vertical planes. Finally, the performance of the proposed model to predict pilot behavior in both horizontal and vertical planes is studied through evaluating against realistic midair encounter situations.\",\"PeriodicalId\":54566,\"journal\":{\"name\":\"Proceedings of the Institution of Mechanical Engineers Part G-Journal of Aerospace Engineering\",\"volume\":\"42 1\",\"pages\":\"\"},\"PeriodicalIF\":1.0000,\"publicationDate\":\"2023-08-30\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Proceedings of the Institution of Mechanical Engineers Part G-Journal of Aerospace Engineering\",\"FirstCategoryId\":\"5\",\"ListUrlMain\":\"https://doi.org/10.1177/09544100231198150\",\"RegionNum\":4,\"RegionCategory\":\"工程技术\",\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"Q3\",\"JCRName\":\"ENGINEERING, AEROSPACE\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Proceedings of the Institution of Mechanical Engineers Part G-Journal of Aerospace Engineering","FirstCategoryId":"5","ListUrlMain":"https://doi.org/10.1177/09544100231198150","RegionNum":4,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q3","JCRName":"ENGINEERING, AEROSPACE","Score":null,"Total":0}

引用次数: 0

摘要

未来的航空运输系统将以先进自动化的广泛应用和新的运营理念的引入为特征，将更加复杂。在未来的航空运输系统中，需要先进的飞行员行为模型来支持空中遭遇情况的设计和分析。本文首先从广播自动相关监视(ADS-B)观测中过滤空中遭遇数据。基于获取的空中遭遇数据，提出了一种基于多层长短期记忆(LSTM)网络的飞行员综合行为模型。该模型是为了提高飞行员在水平和垂直方向上的行为预测能力而设计的。最后，通过对实际的空中遭遇情况进行评估，研究了该模型在水平和垂直平面上预测飞行员行为的性能。

本文章由计算机程序翻译，如有差异，请以英文原文为准。

查看原文本刊更多论文

Predicting pilot behavior during midair encounters using long short-term memory network

Characterized by the wide use of advanced automation and the introduction of new operation concepts, the future air transportation system will be more complex. Advanced pilot behavior models with improved capability are required to support the design and analysis of the midair encounter situations in the future air transportation system. This paper first filters midair encounter data from Automatic Dependent Surveillance-Broadcast (ADS-B) observations. Based on the acquired midair encounter data, a comprehensive pilot behavior model is proposed based on a multi-layer Long Short-Term Memory (LSTM) network. The model is designed for the purpose of enhancing the predicting capability of pilot behaviors in both horizontal and vertical planes. Finally, the performance of the proposed model to predict pilot behavior in both horizontal and vertical planes is studied through evaluating against realistic midair encounter situations.

求助全文

通过发布文献求助，成功后即可免费获取论文全文。去求助

来源期刊

Proceedings of the Institution of Mechanical Engineers Part G-Journal of Aerospace Engineering 工程技术-工程：机械

CiteScore

2.40

自引率

18.20%

发文量

212

审稿时长

5.7 months

期刊介绍： The Journal of Aerospace Engineering is dedicated to the publication of high quality research in all branches of applied sciences and technology dealing with aircraft and spacecraft, and their support systems. "Our authorship is truly international and all efforts are made to ensure that each paper is presented in the best possible way and reaches a wide audience. "The Editorial Board is composed of recognized experts representing the technical communities of fifteen countries. The Board Members work in close cooperation with the editors, reviewers, and authors to achieve a consistent standard of well written and presented papers."Professor Rodrigo Martinez-Val, Universidad Politécnica de Madrid, Spain This journal is a member of the Committee on Publication Ethics (COPE).