基于模糊神经网络的民航物流预测研究与仿真分析  

Research on civil aviation logistics forecasting based on fuzzy neural networks and simulation analysis

作　　者：孟建军[1] 杨泽青[2] 

机构地区：[1]兰州交通大学机电工程学院,甘肃兰州730070 [2]河北工业大学机械工程学院,天津300130

出　　处：《计算机工程与设计》2010年第5期1056-1059,共4页Computer Engineering and Design

基　　金：甘肃省教育厅科研基金项目(0604-02);兰州交通大学"青蓝"人才工程基金项目(QL-05-14A)

摘　　要：为合理规划我国机场改扩建方案,针对目前民航业特点,从客运量的角度对民航物流预测进行研究,在综合分析影响客运量因素的基础上,提出了模糊对角回归神经网络滚动预测模型。此模型在前端网络处理层对不确定性因素进行模糊量化处理,对确定性因素进行归一化处理,有效地解决了模型输入量纲不一致的问题。通过实际数据的检验与内回归神经网络、外回归神经网络的预测结果相比较,证明应用此模型进行民航客运量预测有较高的预测精度。并在此基础上利用Visual Basic语言开发了民航物流预测仿真系统,对预测结果进行仿真验证,试验结果表明该仿真系统具有广阔的应用前景和推广价值。To plan the reform and expansion program of China＇ s airport rationally, the civil aviation logistics forecasting is studied mainly from the perspective of passenger traffic volume, in view of the characteristics of our civil aviation. A fuzzy diagonal regression neural networks recurrent forecast model is proposed based on analyzing influential factors of passenger traffic volume. This model dealt with the uncertain factors fuzzily and certainty factors using normalization in the front network layer, which solved the problem for inconsistent of importing dimension effectively. Throughout the test of the actual data and the contrast with the forecasting results of the inner and outer recursion neural networks forecast model, the prediction precision is higher using this model predict civil aviation passenger volume. Moreover, the simulation system of civil aviation logistics forecasting is developed using visual basic to verify the forecasting results, the experimental results show that the simulation system has well application prospect and the promoted value.

关 键 词：模糊逻辑 对角回归神经网络 预测 客运量 仿真 

分 类 号：TP183[自动化与计算机技术—控制理论与控制工程]