连分式扩充的粒子群神经网络压气机特性重构方法

王星博; 李本威; 王永华; 杨欣毅

连分式扩充的粒子群神经网络压气机特性重构方法

海军航空工程学院飞行器工程系,山东烟台 264001

计量
- 文章访问数: 1609
- HTML浏览量: 3
- PDF量: 608
- 被引次数: 0
出版历程
- 收稿日期: 2011-08-20
- 刊出日期: 2012-07-28

Neural network reconstruction method of compressor characteristics with continued fraction expanded data

Department of Aerocraft Engineering, Naval Aeronautical and Astronautical University,Yantai Shandong 264001,China

摘要

摘要: 对航空发动机压气机原始二维等转速线的数据点进行连分式扩充,通过两次网络训练,增加转速特性数据,在三维空间中进行BP(back propagation)网络模型重构.根据压气机特性数据空间分布的特点,引入压力比函数,调整计算区域,定义网络的输入输出数据,利用试探法确定隐含层维数.采用基于趋利避害原则的粒子群算法对网络的初始权值和阈值进行优化,建立了压气机压比和效率特性的整体代理模型.最后以某型发动机的低压压气机为例进行了压气机特性模型的重构.通过模型的校核与验证表明:采用这种方法建立的模型精度较高,优于普遍采用的传统二维插值方法和普通BP神经网络模型.最终建立的重构模型对于采用选配法、坐标法和部件法等以压气机通用特性曲线为基础的发动机模型的求解,可提高计算精度和迭代速度,具有一定的工程应用价值.
- 航空发动机 /
- 压气机特性 /
- 连分式 /
- 粒子群优化 /
- 趋利避害 /
- BP神经网络 /
- 重构模型
Abstract: Original two-dimensional constant rotating speed curve data points of aero-engine compressor were expanded using continued fraction interpolation.Rotating speed characteristic data through twice network training was increased and BP(back progagation) neural network model reconstruction in three-dimensional space was performed.According to the space distribution of compressor characteristics data,pressure ratio function was introduced,computational domain was adjusted,input and output data were defined and dimension of hidden layer was determined by cut-and-try method.Particle swarm optimizing algorithm based on seek advantage and avoid disadvantage principle was used to optimize the initial weight and threshold of neural network,and to establish the integral surrogate model of compressors was taken pressure ratio and efficiency characteristics.In the end,some aero-engine low pressure compressor for example to conduct the model reconstruction method.The check and verification results indicate the surrogate model established by the method proposed is more accurate than traditional two-dimensional interpolation and common BP neural network model.The reconstruction model can increase computational accuracy and boost iteration speed when used in solving aero-engine mathematic model based on general characteristic curve of compressor such as trial and error procedure,coordinate method and components method,therefore it is of engineering value.
- aero-engine /
- compressor characteristics /
- continued fraction /
- particle swarm optimization /
- seek advantage and avoid disadvantage /
- BP neural network /
- reconstruction model

HTML

参考文献(15)

[1]	陈玉春,徐思远,屠秋野,等.求解航空发动机非线性方程组的变步长牛顿法[J].航空计算技术,2009,39(1):39-44. CHEN Yuchun,XU Siyuan,TU Qiuye,et al.Variable step newton method for solving the nonlinear equations of aero turbine engines[J].Aeronautical Computing Technique.2009,39(1):39-44.(in Chinese)
[2]	王鑫.航空发动机数学模型与控制规律研究 .西安:西北工业大学,2007. WANG Xin.Research on aero-engine mathematical model and control stragety .Xi'an:Northwestern Polytechnical University,2007.(in Chinese)
[3]	Tirnovan R,Giurgea S,Miraoui A,et al.Surrogate modelling of compressor characteristics for fuel-cell applications[J].Applied Energy,2008,85(5):394-403.
[4]	Hu M,Tan J Q.Adaptive osculatory rational interpolation for image processing[J].J Comp Appl Math,2006,195(1/2):46-53.
[5]	Hu M,Tan J Q,Xue F.A new approach to the image resizing using interpolating rational linear splines by continued fractions[J].Journal of Information & Computational Science,2005,2(4):681-685.
[6]	Zhao Q J,Tan J Q.Block based thiele-like blending rational interpolation[J].J. Comp. Appl. Math.,2006,195(1/2):312-325.
[7]	杨欣毅.弹用涡喷发动机气动过程数值仿真与试验研究 .山东烟台:海军航空工程学院,2009. YANG Xinyi.Numerical simulation and experimental study on the missile turbojet engine start process .Yantai Shandong:Naval Aeronautical Engineering University,2009.(in Chinese)
[8]	张强,李本威,马力.粒子群算法在航空发动机部件模型求解中的应[J].系统仿真学报,2009,21(12):3584-3587. ZHANG Qiang,LI Benwei,MA Li.Application of particle swarm optimization in solution to aeroengine component-level model[J].Journal of System Simulation.2009,21(12):3584-3587.(in Chinese)
[9]	Kennedy J,Mendes R.Population structure and particle swarm performance //Proceedings of the IEEE Congress on Evolutionary Computation.Hawaii:IEEE Press,2002:1671-1675.
[10]	Liang J J,Suganthan P N.Dynamic multiswarm particle swarm optimizer //Proceedings of the IEEE Swarm Intelligence symposium.Piscataway:IEEE Press,2005:124-129.
[11]	Li L L,Wang L,Liu L.An effective hybrid PSOSA strategy for optimization and its application to parameter estimation[J].Applied Mathematics and Computation,2006:179(1):135-146.
[12]	He S,Wu Q H,Wen J Y,et al.A particle swarm optimizer with passive congregation[J].Biosystems,2004,78(1/2/3):135-147.
[13]	Mendes R,Kennedy J.The full informed particle swarm:Simpler,maybe better[J].IEEE Transaction on Evolutionary Computation,2004,8(3):204-210.
[14]	纪震,廖惠连,吴青华.粒子群算法及应用[M].北京:科学出版社,2009.
[15]	宋金光.人工神经网络在航空发动机中的应用[J].中国民航学院学报,2002,20(3):46-50. SONG Jinguang.Application of artificial neural network in aeroengine[J].Journal of Civil Aviation University of China,2002,20(3):46-50.(in Chinese)