基于D-S证据理论的飞机空气制冷机寿命趋势分析  

Life Trend Analysis of Aircraft Air Refrigerator Based on D-S Evidence Theory

作　　者：崔建国[1] 滑娇娇 刘海港[2] 蒋丽英[1] 齐义文[1] 

机构地区：[1]沈阳航空航天大学自动化学院,沈阳110136 [2]沈阳飞机设计研究所,沈阳110035

出　　处：《火力与指挥控制》2015年第11期53-57,共5页Fire Control & Command Control

基　　金：航空科学基金(2010ZD54012);国防预研基金(A0520110023);国防基础科研基金(Z052012B002);辽宁省自然科学基金资助项目(2014024003)

摘　　要：针对飞机空气制冷机的寿命趋势分析问题,为了提高预测精度,提出了基于改进D-S证据理论融合的飞机空气制冷机寿命趋势分析方法。分别采用SVM、BP神经网络和GRNN神经网络预测模型对飞机空气制冷机的寿命进行趋势分析;然后采用改进的D-S证据理论求取每个模型的基本信度值,可使预测效果好的模型具有更大的信度值;最后通过D-S合成法则对得到的可信度进行分析评价并合成,确立最终的组合预测模型。研究表明,经过改进的证据理论融合后的趋势预测模型,能很好地实现对飞机空气制冷机的趋势分析和寿命预测,该方法有效可行。For the life trend analysis problem of the aircraft air refrigerator,in order to improve prediction accuracy,an fusion life trend analysis method based on improved D-S evidence theory is presented. Firstly,Support Vector Machine（SVM）,BP neural network and Generalized Regression Neural Network（GRNN） models respectively for the life trend analysis of aircraft air refrigerator are used; then the improved D-S evidence theory to calculate the basic belief values for each model is applied,which can predict the effect of a good value with greater reliability and to analyze and evaluate the credibility and composite them through the D-S combination rule; finally,the final combined forecasting model is established. The result show that the trend prediction model based on the improved evidence theory fusion can realize the trend analysis and life prediction of aircraft air refrigerating very good. This method is effective and feasible.

关 键 词：D-S证据理论 空气制冷机 寿命 趋势分析 

分 类 号：V245.343[航空宇航科学与技术—飞行器设计]