基于PSO-SVM的民航发动机送修等级决策研究

推进技术 ›› 2013, Vol. 34 ›› Issue (5): 687-692.

基于PSO-SVM的民航发动机送修等级决策研究

郑波

中国民航飞行学院,四川广汉 618307

发布日期:2021-08-15
作者简介:郑波(1984—),男,研究生,讲师,研究领域为航空设备故障诊断。E-mail:ttccll123321@126.com
基金资助:
中国民航飞行学院青年基金项目(Q2010-67)。

Investigation on Aeroengine Maintenance Level Decision Based on PSO-SVM

Civil Aviation Flight University of China,Guanghan 618307,China

Published:2021-08-15

摘要/Abstract

摘要： 为降低航空公司维修成本,增强送修等级决策科学性,保障飞行安全,提出基于PSO-SVM的民航发动机送修等级决策算法。首先利用改进的粒子群优化(Particle Swarm Optimization,PSO)算法对支持向量机(Support Vector Machine,SVM)参数进行寻优,并提出将交叉验证(Cross Validation,CV)的平均分类精度作为PSO的适应度值。对某型发动机送修等级的真实数据进行了决策对比研究,研究数据表明:与传统的Grid和GA算法相比,PSO的参数寻优效果要更优；在小样本分类时,PSO-SVM的分类精度要远高于常用的神经网络分类模型径向基函数(Radial Basis Function,RBF)模型和学习向量量化(Learning Vector Quantization)模型。 

关键词: 粒子群优化算法;支持向量机;交叉验证;送修等级决策 

Abstract: In order to reduce airline repairment cost, enhance the scientific nature of maintenance level decision and ensure flight safety, the aeroengine maintenance level decision algorithm based on the PSO-SVM was developped. The improved particle swarm optimization (PSO) was used to optimize parameters of support vector machine (SVM)and the average classified precision based on cross validation (CV) was used as PSO fitness value. The decision comparison study on the real data of engine maintenance level was carried out. The research data shows that the PSO parameter optimization is superior to the traditional Grid and GA optimization algorithm. In small sample classification, the PSO-SVM classified precision is better than that of neural network model RBF and LVQ. 

Key words: Particle swarm optimization；Support vector machine；Cross validation；Maintenance level decision

郑波. 基于PSO-SVM的民航发动机送修等级决策研究[J]. 推进技术, 2013, 34(5): 687-692.

ZHENG Bo. Investigation on Aeroengine Maintenance Level Decision Based on PSO-SVM[J]. Journal of Propulsion Technology, 2013, 34(5): 687-692.

参考文献

[1] 雍成喜.民航发动机送修方案制定及其送修系统开发[D].南京:南京航空航天大学,2008.
[2] 赵洪利.航空发动机监控技术[J].民航经济与技术,1997,(10):8-11.
[3] Dieulle L.Sequential Condition-Based Maintenance Scheduling for a Deteriorating System[J].European Journal of Operational Research, 2003,0(2):451-461.
[4] 井立国,王端民,廖博.航空发动机维修灰色模糊决策方法研究[J].黑龙江大学自然科学学报,2009,6(3):342-346.
[5] 严志军,严立,朱新河.逻辑决断法与模糊综合评价在机械设备维修类型决策中的应用[J].中国设备管理, 2000,(7):9-10.
[6] 谢庆华,梁剑,张琦,基于统计粗集模型的航空发动机维修成本组合预测方法[J].兵工学报,2006,(5):91-95.
[7] GE Transportation.CF6-80C2A5Workscope Planning Guide[M].USA:General Electric Company,1999.
[8] Vapnik V N.The Nature of Statistical Learning Theory[M].New York:Spring-Verlag,1999.
[9] 邓乃扬,田英杰.支持向量机——理论、算法与拓展[M].北京:科技出版社,2009.
[10] Maji S, Berg A C, Malik J.Classification Using Intersection Kernel Support Vector Machines is Efficient[C] .Alaska:IEEE Computer Vision and Pattern Recognition,2008.
[11] Venter, Sobieszczanski-sobieski J.Particle Swarm Optimization[J].AIAA Journal, 2003,1(8):1583-1589.
[12] Eberhart R, Shi Yuhui.Particle Swarm Optimization:Developments, Applications and Resources[C].Seoul:Proc IEEE Int Conf on Evolutionary Computation,2001.
[13] 张海军.民航发动机性能评估方法与视情维修决策模型研究[D].南京:南京航空航天大学,2007.
[14] Oconnor Patrick D T.Practical Reliability Engineering (Fourth Edition)[M].London:JohnWiley & Sons, Inc., 2002.
[15] Anderson J A.Introduction to Neural Networks[M].Cambridge,MA:MIT Press,1999.
[16] 林升梁,刘志.基于RBF核函数的支持向量机参数选择[J].浙江工业大学学报,2007,5(12):163-165.
[17] Du Shiqiang, Li Wanshe, Cao Kai.A Learning Algorithm of Artificial Neural Network Based on GA-PSO[C].USA:Proceedings of the 6th World Congress on Intelligent Control and Automation, 2000.