摘要
目前由于我国飞机维修单位存在数量多、工作量大等特点,监管当局无法对维修单位进行细致的风险量化评价,导致其存在较大的潜在风险。为解决此问题,本文基于国内外航空风险分析方法,提出了基于广义线性回归模型的飞机维修单位风险管理研究,建立了飞机维修单位风险监测指标与飞机维修单位的风险等级之间的关系模型,确定监测指标和风险等级的因果关系。在建模过程中,利用皮尔逊检验模型的拟合优度,采用极大似然估计法对模型参量进行估计。最后本文利用所建立的模型对一些维修企业进行实例验证,得到的风险评估结果与实际情况相符,从而此模型可为监管单位及企业提供决策支持。
Due to a number of aircraft maintenance unit and the big workload, the government can't have a detailed quantitative evaluation of the maintenance enterprise, which lead to the existence of large potential risks.To solve this problem, this paper proposed the research of aircraft maintenance unit risk management based the generalized linear regression model, established the relationship model between the aircraft maintenance unit risk monitoring indicators and the aircraft maintenance unit risk level,based on aviation risk analysis methods at home and abroad. The model uses the Pearson chi-square to test the goodness of the model and uses the maximum likelihood estimation for estimating the model parameter. At the end, the paper assess some maintenance enterprise by using the model, the results close to actual experiences. So the model can provide decision support for the government and enterprises.
引文
[1]王衍洋,曹义华.航空运行风险的灰色神经网络模型[J].航空动力学报,2010,15(5):1036-1042.
[2]李祥,黄建辉,陈可嘉.中美民航安全管理比较[J].中国安全生产科学技术,2012,8(12):138-142.
[3]李敬,陈艳秋,何珮,等.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.
[4]持续适航检察员手册[S].CASM R2,2003.
[5]民用航空器维修单位合格审定规定[S].CCAR-145-R3,2005.
[6]曹元坤,王光俊.企业风险管理发展历程及其研究趋势的新认识[J].当代财经,2011,1:85-92
[7]Galileo Tamasi.Risk assessment techniques for civil aviation security[J].Reliability Engineering&System Safety,2011,96(8):892-899.
[8]王衍洋,李敬,曹义华.中国民航安全评价方法研究[J].中国安全生产科学技术,2008,4(5):111-113.
[9]Zenga J,Ana M,Smith N J.Application of a fuzzy based decision making methodology to construction project risk assessment[J].International Journal of Project Management,EI,2007,25(6):589-600.
[10]陈希孺.广义线性模型(一)[J].数理统计与管理,2002,21(5):54-61.
[11]Jiang J.Linear and Generalized Linear Mixed Models and their Applications[M].New York:Spring,2007.
[12]花俊洲,梅长林,吴冲锋.变系数广义线性模型及其估计[J].系统科学与数学,2004,24(1):041-050.
[13]Menard S.Coefficients of determination for multiple logistic regression analysis[J].The American Statistician.2000,EI,51(1):17-24.
[14]Sugata S R,Guria S.Diagnostics in logistic regression models[J].Journal of the Korean Statistical Society,2008,EI,37:89-94.
[15]张进春,吴超.基于广义线性模型的概率风险评价方法及其应用[J].中南大学学报(自然与科学版),2011,42(6).