论文部分内容阅读
为防止飞机着陆时冲出跑道,采用支持向量机(SVM)模型预测飞机着陆距离。基于机场、气象以及飞机自身等3方面影响因素,选取B737-800为参考机型。利用波音公司的LAND软件采集相关运行数据。通过选择误差最小、精度最优的径向基核函数(RBF)构建最有效的SVM模型。探讨网格参数算法、遗传算法(GA)和粒子群优化(PSO)算法对最佳惩罚函数c和核函数参数g的影响。结果表明,预测着陆数据与实测着陆数据吻合较好——最大绝对误差在20 m范围内,最大相对误差为1%。
To prevent the runway from getting out of the runway when it landed, a support vector machine (SVM) model was used to predict the landing distance of the aircraft. Based on the influencing factors of the airport, meteorology and the aircraft itself, the B737-800 is selected as the reference model. Acquire relevant operating data using Boeing LAND software. The most efficient SVM model is constructed by choosing the Radial Basis Function (RBF) with the least error and the best accuracy. The effects of grid parameter algorithm, genetic algorithm (GA) and particle swarm optimization (PSO) algorithm on optimal penalty function c and kernel function parameter g are discussed. The results show that the predicted landing data is in good agreement with the measured landing data - the maximum absolute error is within 20 m and the maximum relative error is 1%.