摘要
为准确预测燃油消耗量,减少民航碳排放,分析飞行数据影响油耗的参数,提出两种爬升阶段油耗预测模型,即BP预测模型与基于自适应(简写为A)GA-BP强预测模型。GA-BP强预测模型以BP预测网络为弱预测器,经有限次数迭代得到强预测器输出,实现误差的优化调整,解决非线性复杂问题。实验结果表明,该模型在非线性预测方面有明显优势,预测精度和拟合度较好,验证了两种模型在油耗预测领域都具可行性。
To predict the fuel consumption and reduce civil aviation carbon emission,the parameters of fuel consumption were analyzed using QAR flight data,two kinds of fuel consumption prediction model were proposed,namely the BP prediction model and the adaptive GA-BP（genetic algorithm-back propagation）strong prediction model.The crossover and mutation probability of GA-BP strong prediction model were adaptively adjusted,and the BP neural network was taken as a weak predictor,after the limited number of iterations,error optimization adjustment was realized and the complicated nonlinear problem was solved.Results of the simulation indicate that the two models have obvious advantages in nonlinear prediction,and the prediction accuracy and the degree of fitting are good,so the two models are feasible in the field of fuel consumption prediction.
出处
《计算机工程与设计》
北大核心
2017年第10期2845-2849,2857,共6页
Computer Engineering and Design
基金
国家科技项目支撑计划基金项目(2012BAC20B03)
民航局科技基金项目(MHRD201121)
关键词
飞行数据
油耗
BP网络
自适应GA-BP强预测模型
误差
flight data
fuel consumption
BP networ k
a d a p t iv e GA-BP s t ro n g p re d ic t io n model
e r r o r
