基于模糊信息粒化和优化SVM的航空发动机性能趋势预测

李艳军; 张建; 曹愈远; 张丽娜

doi:10.13224/j.cnki.jasp.2017.12.027

基于模糊信息粒化和优化SVM的航空发动机性能趋势预测

doi: 10.13224/j.cnki.jasp.2017.12.027

1.
南京航空航天大学民航学院,南京 211106
2.
南京航空航天大学民航学院,南京 211106；中国航空发动机集团有限公司商用航空发动机有限责任公司,上海 200241

基金项目: 航空科学基金(20153352040)；南京航空航天大学校开放基金(kfjj20150701)

计量
- 文章访问数: 613
- HTML浏览量: 1
- PDF量: 445
- 被引次数: 0
出版历程
- 收稿日期: 2016-05-17
- 刊出日期: 2017-12-28

Forecasting of aeroengine performance trend based on fuzzy information granulation and optimized SVM

摘要

摘要: 提出采用模糊信息粒化(FIG)和优化的支持向量机(SVM)来预测航空发动机参数的变化趋势和变化空间。利用模糊信息粒化方法对性能参数进行粒化处理。以KCV验证误差最小作为优化目标,采用遗传算法(GA)实现支持向量机惩罚参数和核函数参数的自适应优化选择；训练SVM模型并进行并对模糊粒子非线性预测。利用某航空公司的某型航空发动机性能参数监测数据进行验证,结果表明:该算法可以有效实现航空发动机性能参数变化趋势和变化空间预测。在实例基础上分析了窗口大小对算法预测精度的影响以及算法多步预测的效果,得出算法最佳窗口大小为3个数据且算法3步以内预测误差小于10%。
- 航空发动机 /
- 参数预测 /
- 模糊信息粒化 /
- K-折交叉验证 /
- 遗传算法 /
- 支持向量机(SVM)
Abstract: A method to predict the change trend and space of aeroengine parameters with fuzzy information granulation (FIG) and optimized support vector machine (SVM) was put forward. FIG was adopted to granulate the parameters. Genetic algorithm (GA) was applied into adaptive selection of the best penalty parameter and kernel function parameter with Kfold cross validation (KCV) error minimum as the optimization goal. The SVM model was trained for nonlinear prediction of fuzzy particles. The verification results of some airlines monitoring performance parameters data of an aeroengine showed that the algorithm proposed can effectively realize the change trend and spatial prediction of aeroengine performance parameters. In addition, the influence of window size on prediction accuracy and the effect of multistep prediction were studied on the basis of instance. As a result, it was concluded that the best window size was three data and the forecasting error within three steps was less than 10%.
- aero-engine /
- parameter prediction /
- fuzzy information granulation /
- K-fold cross validation /
- genetic algorithm /
- support vector machine (SVM)

HTML

参考文献(21)

[1]	尉询楷,杨立,刘芳,等.航空发动机预测和健康管理［M］.北京:国防工业出版社,2014.
[2]	崔文斌,叶志锋,彭利方.基于信息融合遗传算法的航空发动机气路故障诊断［J］.航空动力学报,2015,30(5):1275-1280.CUI Wenbin,YE Zhifeng,PENG Lifang.Aeroengine gas path fault diagnosis based on genetic algorithm of information fusion［J］.Journal of Aerospace Power,2015,30(5):1275-1280.(in Chinese)
[3]	吴娅辉,李新良,洪宝林,等.基于SVM和广义粗糙度特征的航空发动机振动故障诊断方法［J］.航空动力学报,2011,26(11):2445-2449.WU Yahui,LI Xinliang,HONG Baolin,et al.Research on aeroengine vibration fault diagnosis based on support vector machine and generalized roughness feature［J］.Journal of Aerospace Power,2011,26(11):2445-2449.(in Chinese)
[4]	李艳军,左洪福,吴振峰.基于磨粒分析方法的发动机磨损故障智能诊断技术［J］.南京航空航天大学学报,2001,33(3):221-226.LI Yanjun,ZUO Hongfu,WU Zhenfneg.Intelligent diagnostics for engine wear failure based on debris analysis［J］.Journal of Nanjing University of Aeronautics and Astronautics,2001,33(3):221-226.(in Chinese)
[5]	范庚,马登武.基于组合优化相关向量机的航空发动机性能参数概率预测方法［J］.航空学报,2013,34(9):2110-2121.FAN Geng,MA Dengwu.Probabilistic prediction method for aeroengine performance parameters based on combined optimum relevance vector machine［J］.Acta Aeronautica et Astronautica Sinica,2013,34(9):2110-2121.(in Chinese)
[6]	李晓白,崔秀伶,郎荣玲.航空发动机性能参数预测方法［J］.北京航空航天大学学报,2008,34(3):253-256.LI Xiaobai,CUI Xiuling,LANG Rongling.Forecasting method or aeroengine performance parameters［J］.Journal of Beijing University of Aeronautics and Astronautics,2008,34(3):253-256.(in Chinese)
[7]	GAN M L,YANG Z.Timeseries modeling and fault forecast study spectral analysis of lubricating oil［J］.Transactions of Nanjing University of Aeronautics and Astronautics,2001,18(1):86-90.
[8]	陈果.用结构自适应神经网络预测航空发动机性能趋势［J］.航空学报,2007,28(3):535-539.CHEN Guo.Forecasting engine performance trend by using structure selfadaptive neural network［J］.Acta Aeronautica et Astronautica Sinica,2007,28(3):535-539.(in Chinese)
[9]	丁刚,付旭云,钟诗胜.基于过程神经网络的航空发动机性能参数预测［J］.计算机集成制造系统,2011,17(1):198-207.DING Gang,FU Xuyun,ZHONG Shisheng.Aeroengine performance parameters prediction based on process neural network［J］.Computer Integrated Manufacturing Systems,2011,17(1):198-207.(in Chinese)
[10]	杨虞微,陈果.基于结构自适应径向基神经网络的油样光谱数据建模［J］.仪器仪表学报,2006,27(1):98-101.YANG Yuwei,CHEN Guo.Modeling of spectrometric oil analysis data based on structure selfadaptive RBF neural network［J］.Chinese Journal of Scientific Instrument,2006,27(1):98-101.(in Chinese)
[11]	郭阳明,姜红梅,翟正军.基于灰色理论的自适应多参数预测模型［J］.航空学报,2009,30(5):925-931.GUO Yangming,JIANG Hongmei,ZHAI Zhengjun.Adaptive multiparameter prediction model based on grey theory［J］.Acta Aeronautica et Astronautica Sinica,2009,30(5):925-931.(in Chinese)
[12]	崔立志.灰色预测技术及其应用研究［D］.南京:南京航空航天大学,2010.CUI Lizhi.Grey forecast technology and its application research［D］.Nanjing:Nanjing University of Aeronautics and Astronautics,2010.(in Chinese)
[13]	曾波.灰色预测建模技术研究［D］.南京:南京航空航天大学,2011.ZENG Bo.Research on modeling technologies of grey prediction［D］.Nanjing:Nanjing University of Aeronautics and Astronautics,2011.(in Chinese)
[14]	尉询楷,李应红,王硕,等.基于支持向量机的航空发动机滑油监控分析［J］.航空动力学报,2004,19(3):392-397.WEI Xunkai,LI Yinghong,WANG Shuo,et al.Aeroengine lubrication monitoring analysis via support vector machines［J］.Journal of Aerospace Power,2004,19(3):392-397.(in Chinese)
[15]	张弦,王宏力.嵌入维数自适应最小二乘支持向量机状态时间序列预测方法［J］.航空学报,2010,31(12):2309-2314.ZHANG Xian,WANG Hongli.Condition time series prediction using least squares support vector machine with adaptive embedding dimension［J］.Acta et Aeronauticaet Astronautica Sinica,2010,31(12):2309-2314.(in Chinese)
[16]	李本威,张赟,孙涛.基于免疫粒子群算法的滑油屑末支持向量机预测模型设计［J］.航空动力学报,2009,24(7):1639-1643.LI Benwei,ZHANG Yun,SUN Tao.Design of forecasting model for aero engine lubrication debris support vector machines based on immuneparticle swarm optimization algorithm［J］.Journal of Aerospace Power,2009,24(7):1639-1643.(in Chinese)
[17]	王小川,史峰,郁磊,等.MTALAB神经网络 30个案例分析［M］.北京:北京航空航天大学出版社,2010.
[18]	BARGIELA A,PEDRYCZ W.Granular computing:an introduction［M］.Dordrecht:Kluwer Academic Publishers,2003.
[19]	CORTES C V.Support vector networks［J］.Machine Learning,1995,20(3):273-293.
[20]	VAPNIK V N.The nature of statistical learning theory［M］.Berlin:SpringerVerlag,1995.
[21]	吴玫,陆金桂.遗传算法的研究进展综述［J］.机床与液压,2008,36(3):176-179.WU Mei,LU Jingui.Summary of research progress of the genetic algorithms［J］.Machinetool and Hydraulics,2008,36(3):176-179.(in Chinese)