神经网络在无人机电控活塞发动机试验中应用

郭荣化; 吴玉生; 陈庆荣

神经网络在无人机电控活塞发动机试验中应用

中国华阴兵器试验中心, 陕西华阴 714200

计量
- 文章访问数: 1537
- HTML浏览量: 84
- PDF量: 13
- 被引次数: 0
出版历程
- 收稿日期: 2010-06-23
- 修回日期: 2011-03-04
- 刊出日期: 2011-07-28

Application of neural networks in the test for electronic-controlled gasoline engine of unmanned aerial vehicle

Huayin Ordnance Test Center of China,Huayin Shanxi 714200,China

摘要

摘要: 分析了无人机用电控活塞发动机试验特点以及试验中存在的难点,针对电控发动机高海拔标定试验中进气歧管压力(manifold air pressure,简称MAP)传感器数据的传统线性插值方法不能完全表述电控发动机非线性特性的缺陷,提出采用BP(back propagation)神经网络模型的解决方案.为避免目前应用神经网络方法中所存在的不足,通过采用原始数据分组方法进行网络训练误差的实时反馈和控制,较好地解决了神经网络训练过程中容易陷入"局部最优"和"过拟合"状态,并对BP神经网络预测结果给予了详细研究,训练误差和预测误差分析结果表明了该方法的可行性和计算结果的可信性.
- 标定试验 /
- 神经网络 /
- 电子控制单位参数 /
- 无人机 /
- 电控活塞发动机
Abstract: The characters and difficulties in the test for electronic-controlled gasoline engine of unmanned aerial vehicle (UAV) were analyzed in detail.For mending the traditional liner interpolation methods,which are not completely in conformity with nonlinear characteristics of electronic-controlled gasoline engine,a solution was applied in the predication for the manifold air pressure (MAP) of high-altitude calibration of electronic-controlled gasoline engine,by adopting back propagation (BP) neural networks.To avoid the limitation of neural networks in application at present stage,a grouping method of raw-data was put forward to control the feedback of the training error in real-time;this method provided a good solution for the problem that the neural network training result easily leads to the situation of "local optimum" and "over-fitting".The prediction results based on BP neural networks have been studied thoroughly;and the results of the training error and the prediction error reveal that the method is feasible and the result is effective.
- calibrating test /
- neural networks /
- parameters of electronic-controlled unit(ECU) /
- unmanned aerial vehicle (UAV) /
- electronic-controlled gasoline engine

HTML

参考文献(12)

[1]	刘永,张立毅.BP和RBF神经网络的实现及其性能比较[J].电子测量技术,2007,30(4):77-80. LIU Yong,ZHANG Liyi.Implementation of BP and RBF neural network and their performance comparison[J].Electronic Measurement Technology,2007,30(4):77-80.(in Chinese)
[2]	张恒喜,郭基联,朱家元,等.小样本多元数据分析方法及应用[M].西安:西北工业大学出版社,2002. ZHANG Hengxi,GUO Jilian,ZHU Jiayuan,et al.Multivariate data analysis methods and applications with few observations[M].Xi'an:Northwestern Polytechnical University Press,2002.(in Chinese)
[3]	李映颖,朱立贵,张德全,等.基于BP和RBF神经网络对试飞数据预处理比较研究[J].计量与测试技术,2009,36(2):1-2. LI Yingyi,ZHU Ligui,ZHANG Dequan,et al.The pretreatment of the pre-processing data with BP and RBF neural network[J].Metrology & Measurement Technique,2009,36(2):1-2.(in Chinese)
[4]	叶志锋,杨固东,苏伟生.基于试车数据的发动机神经网络模型[J].南京航空航天大学学报,2007,39(1):26-29. YE Zhifeng,YANG Gudong,SU Weisheng.Neural network model of aeroengine based on experimental data[J].Journal of Nanjing University of Aeronautics & Astronautics,2007,39(1):26-29.(in Chinese)
[5]	Kara T N,Baysec S.Prediction of torque and specific fuel consumption of a gasoline engine by using artificial neural networks[J].Applied Energy,2010,87(1):349-355.
[6]	任天睿.基于BP神经网络模型的发动机怠速预测控制 .南京:南京理工大学,2003. REN Tianrui.The idle speed control-model of engine based on BP neural network .Nanjing:Nanjing University of Science and Technology,2003.(in Chinese)
[7]	Sayin C,Ertunc H M,Hosoz M,et al.Performance and exhaust emissions of a gasoline engine using artificial neural network[J].Applied Thermal Engineering,2007,27(1):46-54.
[8]	邓元望,张邦基,龚金科,等.CFA6470HEV发动机燃油经济性的BP神经网络建模及优化[J].汽车工程,2009,31(2):141-145,155. DENG Yuanwang,ZHANG Bangji,GONG Jinke,et al.BP neural network modeling and optimization on engine fuel economy of CFA6470HEV[J].Automotive Engineering,2009,31(2):141-145,155.(in Chinese)
[9]	Hou X,Gong X,Du C,et al.Calibration and optimization for electronically controlled parameters of gasoline engine based on the RBF neural network[J].China Mechanical Engineering,2009,20(18):2264-2267.
[10]	刘鑫.基于神经网络的汽油机电控标定技术研究 .武汉:武汉理工大学,2008. LIU Xin.Study on calibration technology for electronic controlled gasoline engine basedon neural netwok .Wuhan:Wuhan University of Technology,2008.(in Chinese)
[11]	张翠平.电控汽油机燃油喷射及点火控制系统的设计与实验研究 .太原:太原理工大学,2007. ZHANG Cuiping.Design and experimental research of fuel injection and ignition control system for electronically controlled gasoline .Taiyuan:Taiyuan Universtiy of Technology,2007.(in Chinese)
[12]	Levenberg K.A method for the solution of certain nonlinear problems in least squares[J].Quart. Appl. Math.,1944,2(2):164-168.