飞机技术派遣智能决策支持系统框架研究——基于大数据视角
|
摘要
随着航空公司日常运行过程中重要和复杂航班的大幅增加,有效提升了飞机技术派遣的决策效率与精准性,对于保障航班安全性和正常性具有重要意义。飞机长期运行及维护过程中积累了海量的健康状况数据,对于飞机技术派遣决策具有重要价值。由于这些数据体量巨大、结构复杂、增长快,引入大数据技术,提出飞机技术派遣智能决策支持系统(ATD-IDSS)的基本框架。文中重点探讨了ATD-IDSS的总体框架结构以及基于该系统的飞机技术派遣决策过程。其中,系统总体框架由数据采集处理、数据管理、模型管理、知识管理、飞机健康评估和派遣决策控制六个子系统组成。详细阐述了各个子系统的组成、核心功能及运行机理。在此基础上,对系统实现涉及的关键技术进行了一一介绍。借助数据仓库相关技术,实现了飞机健康状况大数据的处理和分析,利用关联规则和聚类分析方法,进行飞机技术参数评估。采用人工神经网络和案例推理结合的智能推理策略,挖掘飞机健康状况相关规则和知识,结合云计算技术,提高资源利用率和运算效率。通过ATS-IDSS的框架研究,为进一步开发智能飞机派遣系统、实现飞机派遣的智能化和精准化及提升飞机健康管理水平提供重要指导。
With the sharp increase of the important and complex flights in the daily operation of the airlines,it is of great significance to effectively enhance the efficiency and accuracy of the aircraft technical dispatch decision-making to ensure the safety and regularity of the flight.Massive aircraft health data accumulated during the long-term operation and maintenance is of great value to the decision-making of aircraft technical dispatch.Due to huge volume,complex structure and rapid growth of these data,the basic framework of Aircraft Technical Dispatching-Intelligent Decision Support System( ATD-IDSS) is presented by introduction of big data technology.It is discussed with focuses on the overall structure of ATD-IDSS and the process of aircraft technical dispatch decision-making based on the system.The overall structure of ATD-IDSS is composed of six subsystems,which include data acquisition and processing,data management,model management,knowledge management,aircraft health assessment and dispatch decision control,and the composition,core functions and operating mechanism of each subsystem are described in detail.On this basis,the key technologies involved in the system are introduced.With the help of data warehouse technology,processing and analysis of massive aircraft data with health status is realized.Using association rules mining and cluster analysis to evaluate aircraft technical parameters. The intelligent reasoning strategy combing artificial neural network and case-based reasoning are used to explore the rules and knowledge of aircraft health status.Combined with the use of cloud computing technology,resource utilization and operational efficiency are improved. Through this research,it can provide important guidance for the further development of intelligent aircraft dispatching system,the realization of intelligent and accurate aircraft dispatch and the promotion of aircraft health management level.
With the sharp increase of the important and complex flights in the daily operation of the airlines,it is of great significance to effectively enhance the efficiency and accuracy of the aircraft technical dispatch decision-making to ensure the safety and regularity of the flight.Massive aircraft health data accumulated during the long-term operation and maintenance is of great value to the decision-making of aircraft technical dispatch.Due to huge volume,complex structure and rapid growth of these data,the basic framework of Aircraft Technical Dispatching-Intelligent Decision Support System( ATD-IDSS) is presented by introduction of big data technology.It is discussed with focuses on the overall structure of ATD-IDSS and the process of aircraft technical dispatch decision-making based on the system.The overall structure of ATD-IDSS is composed of six subsystems,which include data acquisition and processing,data management,model management,knowledge management,aircraft health assessment and dispatch decision control,and the composition,core functions and operating mechanism of each subsystem are described in detail.On this basis,the key technologies involved in the system are introduced.With the help of data warehouse technology,processing and analysis of massive aircraft data with health status is realized.Using association rules mining and cluster analysis to evaluate aircraft technical parameters. The intelligent reasoning strategy combing artificial neural network and case-based reasoning are used to explore the rules and knowledge of aircraft health status.Combined with the use of cloud computing technology,resource utilization and operational efficiency are improved. Through this research,it can provide important guidance for the further development of intelligent aircraft dispatching system,the realization of intelligent and accurate aircraft dispatch and the promotion of aircraft health management level.
引文
[1]Zhang X Y,Chen J S.Decision model of flight safety based on flight event[J].Physics Procedia,2012,33:462-469.
[2]景博,汤巍,黄以锋,等.故障预测与健康管理系统相关标准综述[J].电子测量与仪器学报,2014,28(12):1301-1307.
[3]刘敏,周桂林.决策支持系统在航空公司的应用[J].计算机工程,2005,31:33-35.
[4]Wen Z,Liu Y P.Applications of prognostics and health management in aviation industry[C]//Prognostics and system health management conference.[s.l.]:IEEE,2011:503-514.
[5]谭雪花,王华伟.飞机维修方案优化支持系统框架研究[J].计算机技术与发展,2008,18(11):183-186.
[6]孟小峰,慈祥.大数据管理:概念、技术与挑战[J].计算机研究与发展,2013,50(1):146-149.
[7]袁炳南,霍朝晖,白效贤.飞行试验大数据技术发展及展望[J].计算机测量与控制,2015,23(6):1844-1847.
[8]曾德华,郑晓齐.智能决策支持系统框架研究[J].中国电化教育,2011(6):113-117.
[9]郭宏宁,南建国,万明.飞行参数数据仓库建模研究[J].现代电子技术,2010,33(8):130-133.
[10]吴丽娟,张健宇,高立新.基于神经网络和案例推理的智能诊断系统综述[J].机械设计与制造,2009(3):261-263.
[11]Miah S J,Ahamed R.A cloud-based DSS model for driver safety and monitoring on Australian roads[J].International Journal of Emerging Sciences,2011,1(4):634-648.
[12]罗贺,杨善林,丁帅.云计算环境下的智能决策研究综述[J].系统工程学报,2013,28(1):134-142.
[13]高宏宾,张小彬,杨海振.一种实时挖掘数据流近似频繁项的算法[J].计算机应用,2008,28:219-222.
[14]崔曼,薛惠锋.基于云计算的智能决策支持系统研究[J].管理现代化,2014(2):72-74.
[2]景博,汤巍,黄以锋,等.故障预测与健康管理系统相关标准综述[J].电子测量与仪器学报,2014,28(12):1301-1307.
[3]刘敏,周桂林.决策支持系统在航空公司的应用[J].计算机工程,2005,31:33-35.
[4]Wen Z,Liu Y P.Applications of prognostics and health management in aviation industry[C]//Prognostics and system health management conference.[s.l.]:IEEE,2011:503-514.
[5]谭雪花,王华伟.飞机维修方案优化支持系统框架研究[J].计算机技术与发展,2008,18(11):183-186.
[6]孟小峰,慈祥.大数据管理:概念、技术与挑战[J].计算机研究与发展,2013,50(1):146-149.
[7]袁炳南,霍朝晖,白效贤.飞行试验大数据技术发展及展望[J].计算机测量与控制,2015,23(6):1844-1847.
[8]曾德华,郑晓齐.智能决策支持系统框架研究[J].中国电化教育,2011(6):113-117.
[9]郭宏宁,南建国,万明.飞行参数数据仓库建模研究[J].现代电子技术,2010,33(8):130-133.
[10]吴丽娟,张健宇,高立新.基于神经网络和案例推理的智能诊断系统综述[J].机械设计与制造,2009(3):261-263.
[11]Miah S J,Ahamed R.A cloud-based DSS model for driver safety and monitoring on Australian roads[J].International Journal of Emerging Sciences,2011,1(4):634-648.
[12]罗贺,杨善林,丁帅.云计算环境下的智能决策研究综述[J].系统工程学报,2013,28(1):134-142.
[13]高宏宾,张小彬,杨海振.一种实时挖掘数据流近似频繁项的算法[J].计算机应用,2008,28:219-222.
[14]崔曼,薛惠锋.基于云计算的智能决策支持系统研究[J].管理现代化,2014(2):72-74.