一种航空发动机性能衰退预测的优化算法

中国机械工程 ›› 2011, Vol. 22 ›› Issue (9): 1009-1013.

一种航空发动机性能衰退预测的优化算法

张营;左洪福;任淑红;朱磊

南京航空航天大学,南京,210016

出版日期:2011-05-10 发布日期:2011-05-17
基金资助:
国家自然科学基金委员会-中国民用航空总局联合基金资助重点项目(60939003)

Research on an Algorithm for Prediction of Aeroengine Performance Deterioration

Zhang Ying;Zuo Hongfu;Ren Shuhong;Zhu Lei

Nanjing University of Aeronautics and Astronautics,Nanjing,210016

Online:2011-05-10 Published:2011-05-17

摘要/Abstract

摘要：

针对航空发动机性能衰退预测问题,采用基于过程神经网络的优化算法来对发动机的燃气温度裕度(EGTM)进行预测。为克服过程神经网络学习速度慢的缺点，提出一种基于Tent映射的混沌粒子群优化算法对网络进行训练，建立预测模型。采用某航空公司的EGTM监测数据进行验证，分析结果表明,基于Tent映射的混沌粒子群优化算法具有较高的收敛速度和预测精度，可为航空发动机视情维修决策提供支持。

关键词:

混沌粒子群优化算法, 过程神经网络, 性能衰退, 预测

Abstract:

Process neural networks were adopted to predict the engine gas temperature margin,which could reflect the performance deterioration of the civil aviation aircraft engine. In order to overcome the problem that the learning speed of existing learning algorithms for process neural network was slow, a chaotic particle swarm optimization based on Tent map was developed, which could improve the convergence speed and prediction accuracy. Simulation results demonstrate the validity and feasibility of the proposed algorithm.

Key words: chaotic particle swarm optimization, process neural network, performance deterioration, prediction

中图分类号:

TP183

张营, 左洪福, 任淑红, 朱磊.

一种航空发动机性能衰退预测的优化算法

[J]. 中国机械工程, 2011, 22(9): 1009-1013.

ZHANG Ying, ZUO Hong-Fu, LIN Chu-Gong, SHU Lei.

Research on an Algorithm for Prediction of Aeroengine Performance Deterioration

[J]. China Mechanical Engineering, 2011, 22(9): 1009-1013.

参考文献

[1]周茂军[1].考虑性能衰退的航空发动机总体性能裕度设计研究[J].航空动力学报,2008,23(10):1868-1874.
[2]Hornik K, Stincheombe M, White H. Multilayer Feedforward Networks Are Universal Approximators[J]. Neural Networks, 1989,2(5) :859-366.
[3]Watanabe E, Nakasako N, Mitani Y. A Prediction Method of Non- stationary Time Series Data by Using a Modular Structured Neural Network[J]. IEICE Transactions on Fundamentals of Electronicsm, 1997,80(6) :971-976.
[4]徐小力[1],徐洪安[2],曹爱东[3].旋转机组的基于变权重神经网络组合预测模型[J].中国机械工程,2003,14(4):332-335.
[5]谢红梅[1],廖小平[1],卢煜海[1].遗传神经网络及其在制品质量预测中的应用[J].中国机械工程,2008,19(22):2711-2714.
[6]何新贵[1],梁久祯[2].过程神经元网络的若干理论问题[J].中国工程科学,2000,2(12):40-44.
[7]何新贵[1],梁久祯[2],许少华[2].过程神经网络的训练及其应用[J].中国工程科学,2001,3(4):31-35.
[8]丁刚[1],钟诗胜[1].基于过程神经网络的时间序列预测及其应用研究[J].控制与决策,2006,21(9):1037-1041.
[9]Kennedy J,Eberhart R C. Particle Swarm Optimitation[C]//Proc. IEEE Int. Conf, on Neural Net works. Perth, WA, Australia.. IEEE Service Center 1995:1942-1948.
[10]Eker I, Ecerkale K, Esnaf S. The Use of Logistic Map as a Pseudo Random Number Generator for Particle Swarm Optimization[C]//Proceedings of the 2008 International Conference on Genetic and Evolutionary Methods. Las Vegas:CSREA Press, 2008:299-301.
[11]Xiang Tao, Liao Xiaofeng, Wong Kwok-- wo. An Improved Particle Swarm Optimization Algorithm Combined with Piecewise Linear Chaotic Map[J]. Applied Mathematics and Computation, 2007, 190 (2) : 1637-1645.
[12]Xin Jing, Zhang Xiujie, Song Shenmin. Chaotic Cooperative Particle Swarm Optimization Based on Tent Map[J]. Information Engineering and Computer Science, 2009,19 ( 20) : 1-4.