收稿日期: 2015-11-10
修回日期: 2016-02-02
网络出版日期: 2016-07-30
基金资助
国家自然科学基金（No.61462063）；航空科学基金（No.20135756010）；江西省高等学校科技落地项目基金（No.KJLD13058）资助
Recognition of Helicopter Flight Condition Based onSupport Vector Machine
Received date: 2015-11-10
Revised date: 2016-02-02
Online published: 2016-07-30
针对直升机飞行状态识别训练样本数据少而导致识别率不高的问题，提出一种基于支持向量机(support vector machine，SVM)的直升机飞行状态识别方法.首先利用限幅、去野点和均值滤波对飞行数据进行去噪，用最小二乘法对飞行数据进行直线拟合获取变化率，并根据线性相关性提取状态特征参数，以减少数据冗余；然后根据特征参数将飞行状态分为10小类，对每一小类进行SVM分类器设计以提高识别效率；最后利用训练样本训练每个SVM分类器，用训练好的SVM分类器识别直升机全起落飞行状态.通过某型直升机实飞数据进行飞行状态识别实验，并将所提出的方法与RBF神经网络法进行对比，所得结果表明该方法在小样本情况下的识别率有明显提高，可为直升机故障诊断和寿命预测提供依据.
熊邦书, 刘雨, 莫燕, 黄建萍, 李新民 . 基于SVM的直升机飞行状态识别[J]. 应用科学学报, 2016 , 34(4) : 469 -474 . DOI: 10.3969/j.issn.0255-8297.2016.04.012
To solve the problem of low recognition rate due to insufficient training samples, a flight condition recognition method based on SVM is proposed. The flight data first undergo denoising by clipping, outlier removal, and averaging. The changing rate of flight data is obtained with least square line fitting. Redundancy in the data is reduced based on the characteristic parameters extracted using linear correlation. The flight condition is classified into ten categories according to the characteristic parameters. An SVM classifier is designed for each category to improve identification efficiency. Finally, every SVM classifier is trained with training samples, and all flight conditions of the helicopter are identified by the trained SVM classifier. Actual flight experiments show that, compared with the RBF neural network method, the proposed method can improve performance under a small sample condition. It provides a reference for helicopter fault diagnoses and life prediction.
[1] 赵良堂, 干伟民, 夏千友. 等寿命曲线在直升机动部件疲劳定寿中的应用[J]. 直升机技术, 2000(4): 16-22. Zhao L T, Gan W M, Xia Q Y. The application of equality life curve for fatigue life evaluation of the helicopter dynamic components [J]. Helicopter Technique, 2000(4): 16-22. (in Chinese)
[2] Davies D P, Jenkins S L, Belben F R. Survey of fatigue failures in helicopter components and some lessons learnt [J]. Engineering Failure Analysis, 2013, 32(9): 134-151.
[3] Lombardo D C. Helicopter flight condition recognition: a minimalist approach [C]// Proceedings of Australian Joint Conference on Artificial Intelligence, 1998, 1502: 203-214.
[4] Voskuijl M, Tooren M J L V, Walker D J. Condition-based flight control for helicopters: an extension to condition-based maintenance [J]. Aerospace Science and Technology, 2015, 42: 322-333.
[5] 赵世峰, 张海, 范耀祖. 一种基于计算机视觉的飞行器姿态估计算法[J]. 北京航空航天大学学 报, 2006, 32(8): 885-888. Zhao S F, Zhang H, Fan Y Z. Attitude estimation method for flight vehicles based on computer vision [J]. Journal of Beijing University of Aeronautics and Astronautics, 2006, 32 (8): 885-888. (in Chinese)
[6] Wu W, Chen R. Set-membership identification method for helicopter flight dynamics modeling[J]. Journal of Aircraft, 2015, 52(2): 553-560.
[7] 陈海, 单甘霖, 吉兵, 张凯. 基于图像机动检测的飞行目标姿态角估计算法[J]. 系统仿真学报, 2013, 25(4): 732-736. Chen H, Shan G L, Ji B, Zhang K. Estimating algorithm of attitude angles of flying target based on image maneuver detection [J]. Journal of System Simulation, 2013, 25(4): 732-736. (in Chinese)
[8] Wu W. Identification method for helicopter flight dynamics modeling with rotor degrees of freedom [J]. Chinese Journal of Aeronautics, 2014, 27(6): 1363-1372.
[9] Kaiser M K, Gans N R, Dixon W E. Vision-based estimation for guidance, navigation, and control of an aerial vehicle [J]. IEEE Transactions on Aerospace and Electronic Systems, 2010, 46(3): 1064-1077.
[10] 王少萍, 李凯, 张超. 基于预分类技术和RBF 神经网络的直升机飞行状态识别方法:中 国, 201010190352.X [P], 2010-10-06.
[11] 陶新民, 张冬雪, 郝思媛, 付丹丹. 基于谱聚类欠取样的不均衡数据SVM 分类算法[J]. 控制与决 策, 2012, 27(12): 1761-1768. Tao X M, Zhang D X, Hao S Y, Fu D D. SVM classifier for unbalanced data based on spectrum cluster-based under-sampling approaches [J]. Control and Decision, 2012, 27(12): 1761-1768. (in Chinese)
[12] 张孝远, 周建中, 黄志伟, 李超顺, 贺徽. 基于粗糙集和多类支持向量机的水电机组振动故障诊断[J]. 中国电机工程学报, 2010, 30(20): 88-92. Zhang X Y, Zhou J Z, Huang Z W, Li C S, He H. Vibrant fault diagnosis for hydro-turbine generating unit based on rough sets and multi-class support vector machine [J]. Proceedings of the CSEE, 2010, 30(20): 88-92. (in Chinese)
[13] Nieto P J G, García-Gonzalo E, Lasheras F S, Juez F J D C. Hybrid PSO-SVM based method for forecasting of the remaining useful life for aircraft engines and evaluation of its reliability [J]. Reliability Engineering and System Safety, 2015, 138: 219-231.
[14] 刘振丙, 陈忠, 刘建国. 一种新的构造SVM 分类器的几何最近点法[J]. 自动化学报, 2010, 36(6): 791-797. Liu Z B, Chen Z, Liu J G. A novel geometric nearest point algorithm for constructing SVM classifiers [J]. Acta Automatica Sinica, 2010, 36(6): 791-797. (in Chinese)
[15] Goldoni M, Caglieri A, Andreoli R, Poli D, Manini P, Vettori M C, Corradi M, Mutti A. Application of LS-SVM classifier to determine stability state of asphaltene in oil fields by utilizing SARA fractions [J]. Petroleum Science & Technology, 2015, 33(1): 31-38.
[16] You D, Gao X, Katayama S. WPD-PCA-based laser welding process monitoring and defects diagnosis by using FNN and SVM [J]. IEEE Transactions on Industrial Electronics, 2015, 62(1): 628-636.
[17] 石瑞敏, 杨兆建. 基于复杂网络优化的DAG-SVM 在滚动轴承故障诊断中的应用[J]. 振动与冲 击, 2015, 34(12): 1-6. Shi R M, Yang Z J. Application of optimized directed acyclic graph support vector machine based on complex network in fault diagnosis of rolling bearing [J]. Journal of Vibration and Shock, 2015, 34(12): 1-6. (in Chinese)
[18] Keskes H, Braham A. Recursive undecimated wavelet packet transform and DAG SVM for iInduction motor diagnosis [J]. IEEE Transactions on Industrial Informatics, 2015, 11(5): 1059-1066.
/
| 〈 |
|
〉 |
