基于优化IGNN的飞机爬升段性能燃效估计  

Performance Fuel Efficiency Estimation for Aircraft Climbing Phase Based on Optimized IGNN Model

作　　者：乔雨石 QIAO Yushi(College of Electronic Information and Automation,Civil Aviation University of China,Tianjin 300300)

机构地区：[1]中国民航大学电子信息与自动化学院,天津300300

出　　处：《计算机与数字工程》2024年第6期1691-1696,共6页Computer & Digital Engineering

基　　金：民航局专项项目(编号:GH201661279);国家科技支撑计划(编号:2012BAC20B0304)资助。

摘　　要：针对飞机爬升过程中性能燃效变化受多种不确定性因素影响,呈现出复杂非线性和随机性特征,提出基于优化嵌入型灰色神经(Inlaid Grey Neural Network,IGNN)的爬升段性能燃效估计方法。该方法利用灰色理论弱化原始数据随机性,结合BP神经网络非线性拟合能力强的特点,构建基于IGNN的爬升段性能燃效估计模型;利用思维进化算法(Mind Evolutionary Algorithm,MEA)优化IGNN的初始权值和阈值,解决随机初始化网络权值和阈值对模型精度的不利影响。实验结果表明,该模型估计精度和稳定性更高,可有效准确估计飞机爬升段性能燃效。Aiming at the change of performance fuel efficiency during the climbing phase of the aircraft,which is affected by a variety of uncertain factors,it presents non-linear and random characteristics.A method of performance fuel efficiency estimation based on the optimized inlaid grey neural network(IGNN)is proposed.This method uses the grey theory to weaken the randomness of the original data,and combines the characteristics of BP neural network with strong nonlinear fitting ability,to build the perfor-mance fuel efficiency estimation model based on IGNN in the climbing phase.Mind evolutionary algorithm(MEA)is used to opti-mize the initial weights and thresholds of IGNN,and to solve the adverse effects of random initialization network weights and thresh-olds on model accuracy.Experimental results show that the model has higher estimation accuracy and stability,and can effectively and accurately estimate the performance fuel efficiency for aircraft climbing phase.

关 键 词：飞机爬升段 性能燃效估计 嵌入型灰色神经网络 思维进化算法 精度 

分 类 号：TP391.9[自动化与计算机技术—计算机应用技术]