航空公司飞行安全风险评价研究
|
摘要
随着我国航空运输业的不断发展，航空公司运营规模的逐渐扩大，航线上投放的运力和经营的航线数目都在逐年增加，航空公司飞行安全面临着越来越大压力。近年来仍时有发生飞行事故征候和安全事故，对我国航空公司的飞行安全管理提出了严峻的挑战。同时，飞行安全是关系航空公司发展，影响航空公司国际地位的重要因素，也是航空旅客所关心的话题。论文构建了影响航空公司飞行安全的评价指标体系，通过引入BP神经网络评价方法，建立了航空公司飞行安全风险评价的神经网络模型，通过实例演算说明了该方法的有效性，这对于提高航空公司飞行安全管理水平具有重要的理论和现实意义。
论文首先全面分析了航空公司飞行安全对整个航空运输系统以及航空公司的重要性，在此基础上，应用系统理论的方法，以科学的、全面的、可比的、客观的和实用有效的原则确定了影响航空公司飞行安全的评价指标体系。评价指标体系由安全管理、运行环境、机组资源和飞机因素4个一级评价指标和27个二级评价指标构成。
其次，论文在介绍层次分析法、三角模糊分析法、模糊综合评价法和证据理论法及其应用特点进行分析的基础上，引入BP神经网络作为航空公司飞行安全风险评价研究的网络模型，详述BP神经网络的算法，并针对现有的标准BP神经网络的收敛速度慢、学习效率低、训练过程不稳定等缺陷提出改进后的BP算法模型。
然后，为了克服定性指标受专家主观因素影响，采用熵权法对定性指标进行客观量化处理，作为网络模型的输入数据。论文选取50组样本数据构建网络模型，随机抽取4组样本进行检验，通过MATLAB软件编程测得网络均方差为：0.0018，标准差为：0.044，满足评价精度，论证了方法的可行性。
最后,论文对航空公司飞行安全的评价指标进行了灵敏度分析，找出了影响航空公司飞行安全的关键指标：安全教育与技术培训管理情况、飞机维护达标情况、应急管理培训与实施情况、机务人员的素质和机组人员违规操作，针对影响航空公司飞行安全的关键指标提出了相应的建议措施。这对于加强飞行安全管理，改善飞行安全风险水平，保障航空公司飞行安全具有一定的指导意义。
With the continuous development of aviation industry in China, the scale of the airlineskept on expanding in recent years, transport capacity put on routes and airline numbers hadincreased year by year, while the pressure of flight safety was increasing. The flight safetyincidents and accidents occurred in recent year poses a severe challenge to the flight safetymanagers of Chinese airlines. Meanwhile, the flight safety is related to the development ofairlines and is an important influential factor on airlines’international image, and also it is atopic that passengers concerned deeply. Evaluation index system was identified thatinfluenced the flight safety, and BP neural network evaluation method was used to evaluatethe risk management level of flight safety, and some recommends were given that couldimprove flight safety management.
First, comprehensive importance analysis of flight safety for the air transportation systemand airlines was studied, on the base of which, using a system theory, evaluation index systemof airlines’flight safety was identified with scientific, comprehensive, comparable andfeasible principles. The evaluation index system was composed of four first-level indicatorsand twenty-seven second-level indicators.
Second, on the bases of analyzing the application characteristics of Analytic HierarchyProcess, Triangular Fuzzy Analysis, Fuzzy Comprehensive Evaluation and Evidence Theory,the BP Neural Network was elaborated to evaluate flight safety risk. Then algorithm of BPNeural Network was described, and the improved algorithm of BP Neural Network was alsodescribed because of the slow convergence speed, low learning efficiency and instability inthe training process of standard BP Neural Network algorithm.
Then, in order to overcome the influence of subjective factors from experts, thequalitative indexes were quantified by Entropy Method using MATLAB software, and to beused as input numbers of the network mode. Fifty samples were selected to build a networkmodel and four samples were selected to test the feasibility of the network model. The meansquare deviation of the network model is 0.0036 and the standard deviation is 0.06 using theMATLAB software programming, which met the evaluation accuracy and method’s feasibilitywas demonstrated.
Finally, the sensitivity analysis of the flight safety indexes was studied, and the keyindexes was identified, which included safety and technical training management, aircraftmaintenance standards, implemention of emergency management training, quality of aircraftmaintenance personnel and illegal operation of airplane of aircrews, and corresponding measures of this key indexes was put forward, Which was of certain directive significance forstrengthening flight safety management, could improve flight safety risk level and ensureflight safety.
论文首先全面分析了航空公司飞行安全对整个航空运输系统以及航空公司的重要性，在此基础上，应用系统理论的方法，以科学的、全面的、可比的、客观的和实用有效的原则确定了影响航空公司飞行安全的评价指标体系。评价指标体系由安全管理、运行环境、机组资源和飞机因素4个一级评价指标和27个二级评价指标构成。
其次，论文在介绍层次分析法、三角模糊分析法、模糊综合评价法和证据理论法及其应用特点进行分析的基础上，引入BP神经网络作为航空公司飞行安全风险评价研究的网络模型，详述BP神经网络的算法，并针对现有的标准BP神经网络的收敛速度慢、学习效率低、训练过程不稳定等缺陷提出改进后的BP算法模型。
然后，为了克服定性指标受专家主观因素影响，采用熵权法对定性指标进行客观量化处理，作为网络模型的输入数据。论文选取50组样本数据构建网络模型，随机抽取4组样本进行检验，通过MATLAB软件编程测得网络均方差为：0.0018，标准差为：0.044，满足评价精度，论证了方法的可行性。
最后,论文对航空公司飞行安全的评价指标进行了灵敏度分析，找出了影响航空公司飞行安全的关键指标：安全教育与技术培训管理情况、飞机维护达标情况、应急管理培训与实施情况、机务人员的素质和机组人员违规操作，针对影响航空公司飞行安全的关键指标提出了相应的建议措施。这对于加强飞行安全管理，改善飞行安全风险水平，保障航空公司飞行安全具有一定的指导意义。
With the continuous development of aviation industry in China, the scale of the airlineskept on expanding in recent years, transport capacity put on routes and airline numbers hadincreased year by year, while the pressure of flight safety was increasing. The flight safetyincidents and accidents occurred in recent year poses a severe challenge to the flight safetymanagers of Chinese airlines. Meanwhile, the flight safety is related to the development ofairlines and is an important influential factor on airlines’international image, and also it is atopic that passengers concerned deeply. Evaluation index system was identified thatinfluenced the flight safety, and BP neural network evaluation method was used to evaluatethe risk management level of flight safety, and some recommends were given that couldimprove flight safety management.
First, comprehensive importance analysis of flight safety for the air transportation systemand airlines was studied, on the base of which, using a system theory, evaluation index systemof airlines’flight safety was identified with scientific, comprehensive, comparable andfeasible principles. The evaluation index system was composed of four first-level indicatorsand twenty-seven second-level indicators.
Second, on the bases of analyzing the application characteristics of Analytic HierarchyProcess, Triangular Fuzzy Analysis, Fuzzy Comprehensive Evaluation and Evidence Theory,the BP Neural Network was elaborated to evaluate flight safety risk. Then algorithm of BPNeural Network was described, and the improved algorithm of BP Neural Network was alsodescribed because of the slow convergence speed, low learning efficiency and instability inthe training process of standard BP Neural Network algorithm.
Then, in order to overcome the influence of subjective factors from experts, thequalitative indexes were quantified by Entropy Method using MATLAB software, and to beused as input numbers of the network mode. Fifty samples were selected to build a networkmodel and four samples were selected to test the feasibility of the network model. The meansquare deviation of the network model is 0.0036 and the standard deviation is 0.06 using theMATLAB software programming, which met the evaluation accuracy and method’s feasibilitywas demonstrated.
Finally, the sensitivity analysis of the flight safety indexes was studied, and the keyindexes was identified, which included safety and technical training management, aircraftmaintenance standards, implemention of emergency management training, quality of aircraftmaintenance personnel and illegal operation of airplane of aircrews, and corresponding measures of this key indexes was put forward, Which was of certain directive significance forstrengthening flight safety management, could improve flight safety risk level and ensureflight safety.
引文
[1]李建. 2011年全国民航航空安全工作报告[R].北京:中国安全办公室, 2011
[2]中国民航大学民航安全科学研究所, 2010世界民航安全分析报告[R].天津:安全科学研究所,2011
[3]中国民用航空总局航空安全办公室.中国民航航空安全报告[R].北京:中国安全办公室, 2008
[4]中国民航局.中国航空运输发展报告（2007/2008）[DB/OL].http://www.caac.gov.cn/H1/H2/200808/t20080828_18587.html, 2011-08-10
[5]马晓君.民航飞行学院广汉分院安全评估系统研究[D].成都:西南交通大学, 2006
[6]钱颂迪.运筹学[M].北京:清华大学出版社, 2005
[7]中国民用航空总局规划发展财务司.从统计看民航2009[M].北京:中国民航出版社, 2009
[8]鞠彦兵,冯允成,姚李刚.基于证据理论的软件开发风险评估方法[J].系统工程理论方法应用,2003, 12(4): 218-223
[9]罗帆,佘廉.航空交通灾害预警管理[M].石家庄:河北科学技术出版社, 2004: 342-349
[10]谈云峰.我国民航安全运行管理的进一步完善[D].大连:大连理工大学, 2003
[11]罗军.民用航空运输安全管理的博弈[D].成都:西南交通大学, 2008
[12]王济雯.航空安全报道现状探析[D].浙江:浙江大学, 2009
[13]王振华.国内航空公司内部控制体系改进的研究[D].北京:中国农业科学院, 2007
[14]马志刚.民航飞行安全研究[D].成都:西南交通大学, 2003
[15]徐江,吴弯.安全管理学[M].北京:航空工业出版社, 1993: 25-30
[16]民航总局空管局.民航空中交通事件报告（2003年）[M].北京:民航总局空中交通管理局, 2004
[17]孙瑞山,刘汉辉.航空公司安全评估理论与实践[J].中国安全科学学报, 1996, 9(3): 69-73
[18]章明. IATA运行安全审计及在我国的实践[J].中国民用航空, 2006, 66(6): 59-62
[19]文军.基于灰色多层次的航空公司飞行安全评价研究[J],中国安全科学学报, 2010, 20(2): 29-34
[20]文军.航空公司安全系统风险的模糊综合评价研究[J],中国安全生产科学技术, 2010, 6(1): 4-48
[21]丁松滨,石荣,施和平.基于证据理论的航空公司安全系统风险评价[J].交通运输系统工程与信息, 2007, 7(2): 38-41
[22]丁松滨,茹毅.基于贝叶斯网络的航空公司飞行安全系统评价[J].中国民航大学学报, 2009,27(3): 30-36
[23]丁松滨,王飞.基于BP神经网络的民航安全评价方法研究[J].中国民航学院学报, 2006, 24(1):53-56
[24] DING Song bin, RU Yi. Flight Risk Assessment to Airlines Using Bayesian Belief Networks and Fuz-zy Comprehensive Evaluation[A]. International Conference on Industrial Engineering and Engineer-ing Management IEEM[C]. IEEM: 2008 INTERNATIONAL CONFERENCE ON INDUSTRIALENGINEERING AND ENGINEERING MANAGEMENT, 2008: 1280-1284
[25]苏淑玲.航空运输企业风险管理及防范措施研究[D].北京:中国农业科学院, 2007
[26]王浩峰.给予BP神经网络的航段安全评估研究[D].绵阳:中国工程物理研究院, 2010
[27]祁元福等.世界航空安全与事故分析[M].北京:中国民航出版社, 1998: 25-35
[28]王华伟,左洪福.航空公司安全评估研究[J].系统工程, 2006, 24(2): 46-51
[29]中国民航局安全办公室.航空公司安全评估系统[R].北京:中国民航局安全办公室, 2000
[30]中国民航局飞行标准司.航空运输监察系统（ATOS）[S].北京:中国民航局飞行标准司, 2000
[31]安妮·费布雷斯. FOM计划_保障安全的预防性措施[J].航空维修与工程, 2003, 2: 48-49
[32] FAA. Introduction to Safety Management Systems for Air Operators[S]. USA: Federal Aviation Ad-ministration, 2006
[33] A. J. M.Castro, E.Oliveira. A new concept for disruption management in airline operations control[J].PROCEEDINGS OF THE INSTITUTION OF MECHANICAL ENGINEERS PART GJOURNALOF AEROSPACE ENGINEERING, 2011, 225(G3): 269-290
[34] ROSE N L. Fear of flying: economic analyses of airline safety[J]. Journal of Economic Perspectives.1992, 6(2): 75-94
[35] MEYER J R, OSTER Jr C V. Deregulation and the future of intercity passenger travel[M]. Cambridge:MIT Press, 1987: 109-125
[36]肖玮,游旭群,苗丹民.德国汉沙航空公司和西班牙航空公司联合心理选拔系统简介[J].航空军医, 1999, 1(2): 95-96
[37] A. Ahmadi, P. Soderholm. Assessment of Operational Consequences of Aircraft Failures: Using EventTree Analysis[A]. 2008 IEEE Aerospace Conference[C]. 2008 IEEE AEROSPACE CONFERENCE,2008: 3824-3837
[38] A. Parasuraman, L.L. Berry, V.A. Zeithaml. SERVQUAL: A Multi-Item Scale for Measuring Consu-mer Perceptions of Service Quality[J]. Journal of Retailing, 1988, 64(1): 12-40
[39] T．Kiatcharoenpol, T.Laosirihongthong. Innovations in Service Strategy: An Evaluation of Quality inAirline Service Operations by Using SERVQUAL Model[A]. IEEE International Conference onManage- ment of Innovation and Technology（ICMIT 2006）[C]. Piscataway, NJ, USA: IEEE, 2006:748-752
[40] Michael C. Dorneich. An Experimental Evaluation of Weather Avoidance using Route Optimization asa Decision Aid[A]. 2002 IEEE International Conference on Systems, Man and Cybernetics [C].Piscataway, NJ, USA: IEEE, 2002: 608-612
[41] Walid EI Moudani. An Intelligent Approach for Solving the Airlines Crew Rostering Problem[A].ACS/IEEE INTERNATIONAL CONFERENCE ON COMPUTER SYSTEMS AND APPLICAT-IONS [C]. Los Alamitos, CA, USA: IEEE Comput. Soc, 2001: 73-79
[42]董肇君.系统工程与运筹学[M].北京:国防工业出版社, 2007
[43]刘礼金,范如国.基于三角模糊数比较大小原理的模糊层次分析法在供应商合作伙伴选择中的应用[J].物流科技, 2006, 29(127): 117-121
[44] Buckley J J. Fuzzy hierarchical analysis[J]. Fuzzy Stes and Systems, 1985, 17(3): 233-247
[45] Abdel-kader M G, Dugdale D. Investment in advanced manufacturing technology: a study of practicein large UK companies[J]. Management Accounting Research, 1998, 9(3): 261-284
[46] Constantin Virgil Negoita. Expert Systems and Fuzzy Systems[M], Benjamin-Cummings Pub.Co.Menlo Park, CA, 1985: 58-64
[47] Xiao Wei shu. Fuzzy mathematic elements and application[M]. Beijing: Aviation Industry Press, 1992
[48]康耀红.数据融合理论与应用[M].西安:西安电子科技大学出版社, 1997
[49] Dempster A P. Upper and Lower Probabilities Induced by A multiplicand Mapping[J]. Ammals ofMathematical Statistics, 1967, 38: 325-339
[50]杨风暴,王肖霞. D-S证据理论的冲突证据合成方法[M].北京:国防工业出版社, 2010
[51]闻新. MATLAB神经网络应用设计[M].科学出版社, 2000
[52]丁世飞.人工智能[M].清华大学出版社, 2011
[53]孙一兵.浅议B P网络的优缺点及改进[J].科技创新导报, 2009, 24: 18
[54]中国民用航空局航空安全办公室. 2011中国民航不安全事件统计分析报告[R].北京:中国安全办公室, 2012
[55]文军.航空联盟形成机理及协调管理中若干问题研究[D].成都:西南交通大学, 2008
[56]李敬,陈艳秋.中国民航业安全风险监测与仿真研究[J].中国安全科学学报, 2009, 19(7): 20-25
[2]中国民航大学民航安全科学研究所, 2010世界民航安全分析报告[R].天津:安全科学研究所,2011
[3]中国民用航空总局航空安全办公室.中国民航航空安全报告[R].北京:中国安全办公室, 2008
[4]中国民航局.中国航空运输发展报告（2007/2008）[DB/OL].http://www.caac.gov.cn/H1/H2/200808/t20080828_18587.html, 2011-08-10
[5]马晓君.民航飞行学院广汉分院安全评估系统研究[D].成都:西南交通大学, 2006
[6]钱颂迪.运筹学[M].北京:清华大学出版社, 2005
[7]中国民用航空总局规划发展财务司.从统计看民航2009[M].北京:中国民航出版社, 2009
[8]鞠彦兵,冯允成,姚李刚.基于证据理论的软件开发风险评估方法[J].系统工程理论方法应用,2003, 12(4): 218-223
[9]罗帆,佘廉.航空交通灾害预警管理[M].石家庄:河北科学技术出版社, 2004: 342-349
[10]谈云峰.我国民航安全运行管理的进一步完善[D].大连:大连理工大学, 2003
[11]罗军.民用航空运输安全管理的博弈[D].成都:西南交通大学, 2008
[12]王济雯.航空安全报道现状探析[D].浙江:浙江大学, 2009
[13]王振华.国内航空公司内部控制体系改进的研究[D].北京:中国农业科学院, 2007
[14]马志刚.民航飞行安全研究[D].成都:西南交通大学, 2003
[15]徐江,吴弯.安全管理学[M].北京:航空工业出版社, 1993: 25-30
[16]民航总局空管局.民航空中交通事件报告（2003年）[M].北京:民航总局空中交通管理局, 2004
[17]孙瑞山,刘汉辉.航空公司安全评估理论与实践[J].中国安全科学学报, 1996, 9(3): 69-73
[18]章明. IATA运行安全审计及在我国的实践[J].中国民用航空, 2006, 66(6): 59-62
[19]文军.基于灰色多层次的航空公司飞行安全评价研究[J],中国安全科学学报, 2010, 20(2): 29-34
[20]文军.航空公司安全系统风险的模糊综合评价研究[J],中国安全生产科学技术, 2010, 6(1): 4-48
[21]丁松滨,石荣,施和平.基于证据理论的航空公司安全系统风险评价[J].交通运输系统工程与信息, 2007, 7(2): 38-41
[22]丁松滨,茹毅.基于贝叶斯网络的航空公司飞行安全系统评价[J].中国民航大学学报, 2009,27(3): 30-36
[23]丁松滨,王飞.基于BP神经网络的民航安全评价方法研究[J].中国民航学院学报, 2006, 24(1):53-56
[24] DING Song bin, RU Yi. Flight Risk Assessment to Airlines Using Bayesian Belief Networks and Fuz-zy Comprehensive Evaluation[A]. International Conference on Industrial Engineering and Engineer-ing Management IEEM[C]. IEEM: 2008 INTERNATIONAL CONFERENCE ON INDUSTRIALENGINEERING AND ENGINEERING MANAGEMENT, 2008: 1280-1284
[25]苏淑玲.航空运输企业风险管理及防范措施研究[D].北京:中国农业科学院, 2007
[26]王浩峰.给予BP神经网络的航段安全评估研究[D].绵阳:中国工程物理研究院, 2010
[27]祁元福等.世界航空安全与事故分析[M].北京:中国民航出版社, 1998: 25-35
[28]王华伟,左洪福.航空公司安全评估研究[J].系统工程, 2006, 24(2): 46-51
[29]中国民航局安全办公室.航空公司安全评估系统[R].北京:中国民航局安全办公室, 2000
[30]中国民航局飞行标准司.航空运输监察系统（ATOS）[S].北京:中国民航局飞行标准司, 2000
[31]安妮·费布雷斯. FOM计划_保障安全的预防性措施[J].航空维修与工程, 2003, 2: 48-49
[32] FAA. Introduction to Safety Management Systems for Air Operators[S]. USA: Federal Aviation Ad-ministration, 2006
[33] A. J. M.Castro, E.Oliveira. A new concept for disruption management in airline operations control[J].PROCEEDINGS OF THE INSTITUTION OF MECHANICAL ENGINEERS PART GJOURNALOF AEROSPACE ENGINEERING, 2011, 225(G3): 269-290
[34] ROSE N L. Fear of flying: economic analyses of airline safety[J]. Journal of Economic Perspectives.1992, 6(2): 75-94
[35] MEYER J R, OSTER Jr C V. Deregulation and the future of intercity passenger travel[M]. Cambridge:MIT Press, 1987: 109-125
[36]肖玮,游旭群,苗丹民.德国汉沙航空公司和西班牙航空公司联合心理选拔系统简介[J].航空军医, 1999, 1(2): 95-96
[37] A. Ahmadi, P. Soderholm. Assessment of Operational Consequences of Aircraft Failures: Using EventTree Analysis[A]. 2008 IEEE Aerospace Conference[C]. 2008 IEEE AEROSPACE CONFERENCE,2008: 3824-3837
[38] A. Parasuraman, L.L. Berry, V.A. Zeithaml. SERVQUAL: A Multi-Item Scale for Measuring Consu-mer Perceptions of Service Quality[J]. Journal of Retailing, 1988, 64(1): 12-40
[39] T．Kiatcharoenpol, T.Laosirihongthong. Innovations in Service Strategy: An Evaluation of Quality inAirline Service Operations by Using SERVQUAL Model[A]. IEEE International Conference onManage- ment of Innovation and Technology（ICMIT 2006）[C]. Piscataway, NJ, USA: IEEE, 2006:748-752
[40] Michael C. Dorneich. An Experimental Evaluation of Weather Avoidance using Route Optimization asa Decision Aid[A]. 2002 IEEE International Conference on Systems, Man and Cybernetics [C].Piscataway, NJ, USA: IEEE, 2002: 608-612
[41] Walid EI Moudani. An Intelligent Approach for Solving the Airlines Crew Rostering Problem[A].ACS/IEEE INTERNATIONAL CONFERENCE ON COMPUTER SYSTEMS AND APPLICAT-IONS [C]. Los Alamitos, CA, USA: IEEE Comput. Soc, 2001: 73-79
[42]董肇君.系统工程与运筹学[M].北京:国防工业出版社, 2007
[43]刘礼金,范如国.基于三角模糊数比较大小原理的模糊层次分析法在供应商合作伙伴选择中的应用[J].物流科技, 2006, 29(127): 117-121
[44] Buckley J J. Fuzzy hierarchical analysis[J]. Fuzzy Stes and Systems, 1985, 17(3): 233-247
[45] Abdel-kader M G, Dugdale D. Investment in advanced manufacturing technology: a study of practicein large UK companies[J]. Management Accounting Research, 1998, 9(3): 261-284
[46] Constantin Virgil Negoita. Expert Systems and Fuzzy Systems[M], Benjamin-Cummings Pub.Co.Menlo Park, CA, 1985: 58-64
[47] Xiao Wei shu. Fuzzy mathematic elements and application[M]. Beijing: Aviation Industry Press, 1992
[48]康耀红.数据融合理论与应用[M].西安:西安电子科技大学出版社, 1997
[49] Dempster A P. Upper and Lower Probabilities Induced by A multiplicand Mapping[J]. Ammals ofMathematical Statistics, 1967, 38: 325-339
[50]杨风暴,王肖霞. D-S证据理论的冲突证据合成方法[M].北京:国防工业出版社, 2010
[51]闻新. MATLAB神经网络应用设计[M].科学出版社, 2000
[52]丁世飞.人工智能[M].清华大学出版社, 2011
[53]孙一兵.浅议B P网络的优缺点及改进[J].科技创新导报, 2009, 24: 18
[54]中国民用航空局航空安全办公室. 2011中国民航不安全事件统计分析报告[R].北京:中国安全办公室, 2012
[55]文军.航空联盟形成机理及协调管理中若干问题研究[D].成都:西南交通大学, 2008
[56]李敬,陈艳秋.中国民航业安全风险监测与仿真研究[J].中国安全科学学报, 2009, 19(7): 20-25