摘要
飞行事故预测对于预防飞行事故具有十分重要的意义.首先系统分析了空军飞行事故的主要影响因素,对其中的定性因素进行了量化;然后利用系统分析的成果和历史统计数据建立了空军飞行事故的自适应模糊神经网络预测模型.整个预测过程突破了纯数学模型预测的局限性,实现了预测的定性和定量的结合;由于预测中使用了一种基于高木-关野模糊模型的自适应模糊神经网络,从而使预测模型具有很强的自适应能力,预测结果也比较令人满意.
The prediction of aircraft accident has the extremely vital significance for preventing aircraft accident. First of all, the main factors are systemically analyzed, which influence the air force aircraft accident, and the related qualitative factors are quantified. Then an adaptive fuzzy neural network prediction model is established according to historical data and the result of system analysis. The forecast process eliminates the limitation of pure mathematics model, and realizes the integration of the quantitative and qualitative forecast. The prediction model has very strong self-adaptability because of using adaptive fuzzy neural network based on Sugeno-Tanaka fuzzy model, and the forecast result is also satisfactory.
出处
《系统科学与数学》
CSCD
北大核心
2008年第4期425-433,共9页
Journal of Systems Science and Mathematical Sciences
基金
空军资助项目.
