涡轴发动机高精度实时部件级模型研究

推进技术 ›› 2016, Vol. 37 ›› Issue (1): 25-33.

涡轴发动机高精度实时部件级模型研究

廖光煌^1,2,焦洋¹,李秋红¹,黄金泉¹

南京航空航天大学能源与动力学院，江苏省航空动力系统重点实验室，江苏南京 210016; 中国航空动力控制系统研究所，江苏无锡 214063,南京航空航天大学能源与动力学院，江苏省航空动力系统重点实验室，江苏南京 210016,南京航空航天大学能源与动力学院，江苏省航空动力系统重点实验室，江苏南京 210016,南京航空航天大学能源与动力学院，江苏省航空动力系统重点实验室，江苏南京 210016

发布日期:2021-08-15
作者简介:廖光煌，男，研究员，博士生，研究领域为航空发动机控制系统。

Research on High Accuracy Real-Time Component-Level Modeling Method for Turbo-Shaft Engine

Nanjing University of Aeronautics and Astronautics，Jiangsu Province Key Laboratory of Aerospace Power System，Nanjing 210016，China; Aviation Motor Control System Institute，Aviation Industry Corporation of China，Wuxi 214063，China,Nanjing University of Aeronautics and Astronautics，Jiangsu Province Key Laboratory of Aerospace Power System，Nanjing 210016，China,Nanjing University of Aeronautics and Astronautics，Jiangsu Province Key Laboratory of Aerospace Power System，Nanjing 210016，China and Nanjing University of Aeronautics and Astronautics，Jiangsu Province Key Laboratory of Aerospace Power System，Nanjing 210016，China

Published:2021-08-15

摘要/Abstract

摘要： 提出了基于神经网络的涡轴发动机共同工作方程求解方法。在基于牛顿-拉夫逊迭代法求解共同工作方程的模型上采集离线训练数据，以共同工作方程迭代求解前的残差为输入，迭代收敛后的共同工作方程猜值修正量为输出，训练BP神经网络，对共同工作方程进行求解。采用变缩放因子的萤火虫算法优化神经网络参数，提高了猜值修正量的预测精度。在飞行包线的某一区域内，采集额定发动机在直升机前飞过程的数据进行神经网络离线训练，并将网络参数代入部件级模型对共同工作方程进行求解，在训练数据采集区域附近的爬升状态、远离训练数据采集区域的前飞状态下进行测试，计算模型输出与牛顿-拉夫逊迭代算法模型输出的偏差，与一次通过算法相比，本文提出方法模型输出最大偏差约为一次通过算法的1/34到1/4，模型运行耗时约为一次通过算法的2/5，验证了算法的有效性。

关键词: 涡轴发动机；数学模型；共同工作方程；BP神经网络；萤火虫算法

Abstract: A co-working equations solving method based on neural network was proposed for turbo-shaft engine modeling. The back propagation (BP) neural network，for equations solving，was trained by the off-line data gathered from the model based on Newton - Raphson (N-R) method. The inputs of the network were the residuals of the co-working equations before N-R iteration start. The outputs of the network were the adjustment of the equation guess value after N-R iteration convergence. The varying zoom factor firefly algorithm was adopt to optimize the neural network parameters，and the adjustment of the equation guess value prediction accuracy was enhanced. The training data were gathered from the nominal engine model in certain area of the envelope，and the simulation state of the helicopter was flying forward. The parameters of the network train by the varying zoom factor firefly – BP method was applied to solve the co-working equation of the component level model of turbo shaft engine. The tests were carried out during the helicopter climbing at the envelope of training data gathering area，during the helicopter flying forward at the envelope far from the training data gathering area. The deviations of the model output to that of the model based on N-R method were calculated and compared with the single iteration per time step method，the max model output deviations of the proposed method are about 1/34 to 1/4 to that of the single iteration per time step method，and the time consuming of the model based on the proposed method is about 2/5 to that of the single iteration per time step method. The simulation results show the validation of the proposed method.

Key words: Turbo-shaft engine；Mathematical model；Co-working equation；BP Neural network；Firefly algorithm

廖光煌,焦洋,李秋红,黄金泉. 涡轴发动机高精度实时部件级模型研究[J]. 推进技术, 2016, 37(1): 25-33.

LIAO Guang-huang^1,2,JIAO Yang¹,LI Qiu-hong¹,HUANG Jin-quan¹. Research on High Accuracy Real-Time Component-Level Modeling Method for Turbo-Shaft Engine[J]. Journal of Propulsion Technology, 2016, 37(1): 25-33.

参考文献

[1] Evans A L, Follen G, Naiman C, et al. Numerical Propulsion System Simulation’s National Cycle Program[R]. AIAA 98-3113.
[2] Lytle John, Follen G, Naiman C, et al. NPSS:Numerical Propulsion System Simulation, 1999 Industry Review[R]. NASA TM-2000-209795.
[3] 冯国泰, 黄家骅, 王松涛. 航空发动机数值仿真试验台建立中几个关键技术问题的讨论[J]. 航空动力学报, 2002, 17(4), 483～488.
[4] Fisbbacb L H, Koenig R W. GENENG II-A Program for Calculating Design and Off-Design Performance of Two- and Three-Spool Turbofans with as many as Three Nozzles[R]. NASA TN D-6553, 1972.
[5] Sellers J F, Daniele C J. DYNGEN-A Program for Calculating Steady-State and Transient Performance of Turbojet and Turbofan Engines[R]. NASA TND-7901, 1975.
[6] Daniele C J, Krosel S M, Szuch J R. DIGTEM- Digital Computer Program for Generating Dynamic Turbofan Engine Models[R]. NASA TM-83446, 1983.
[7] Sadler G G, Melcher K J. DEAN: A Program for Dynamic Engine Analysis[R]. NASA TM-87033, 1985.
[8] Brain P Curlett and James L Felder. Object-Oriented Approach for Gas Turbine Engine Simulation[R]. NASA-TM-106970, 1995.
[9] 陆军, 郭迎清, 张书刚. 航空发动机非线性模型实时计算的迭代方法研究[J]. 航空动力学报, 2010, 25(3): 681-686.
[10] 倪健, 马昌凤. 解非线性方程牛顿迭代法的一种新的加速技巧[J]. 广西科学院学报, 2010, 26(1): 1-3.
[11] 黄旭, 王占学, 张晓博. 基于Broyden改进算法的航空发动机性能模拟研究[J]. 科学技术与工程, 2012, 12(21): 5231-5234.
[12] 叶纬, 陈玉春, 崔高峰, 等. 拟牛顿法在航空发动机特性仿真中的应用[J]. 计算机仿真, 2007, 10(10): 78—82.
[13] Jonathan A DeCastro, Jonathan S Litt, Dean K Frederick. A Modular Aero-Propulsion System Simulation of a Large Commercial Aircraft Engine[R]. AIAA 2008-4579.
[14] Ryan D May, Jeffrey Csank, Thomas M Lavelle, et al. A High-Fidelity Simulation of a Generic Commercial Aircraft Engine and Controller[R]. AIAA 2010-6630.
[15] 姚文荣. 涡轴发动机/ 旋翼综合建模控制及优化研究[ D] . 南京:南京航空航天大学, 2008.
[16] 张海波, 王健康, 陈国强. 单旋翼直升机/涡轴发动机通用综合模型的构建方法[P]. 中国专利,CN102520620A, 2012.
[17] Yang X S. Nature-Inspired Metaheuristic Algorithms[M]. UK: Luniver Press, 2010.
[18] Yang X S. Firefly Algorithms for Multimodal Optimization[M]. Berlin: Springer, 2009: 169-178.
[19] 张海波, 姚文荣, 陈国强. 涡轴发动机/直升机综合控制仿真平台设计[J]. 推进技术, 2011, 32(3): 383-390. (ZHANG Hai-bo, YAO Wen-rong, CHEN Guo-qiang. Design of a Numeric Simulation Platform for Integrated Turbo-Shaft Engine /Helicopter Control System[J]. Journal of Propulsion Technology, 2011, 32(3): 383-390.) (编辑:史亚红)　　　　　　　　　　　　*　收稿日期:2014-09-23；修订日期:2014-10-27。作者简介:廖光煌,男,研究员,博士生,研究领域为航空发动机控制系统。E-mail: 1371936742@qq.com