为了能够在飞行数据不尽精确的情况下进行快速、准确的落点预报，提出一种基于径向基函数（RBF）神经网络和无迹卡尔曼滤波技术的弹丸落点预报方法。使用RBF神经网络逼近外弹道方程用以预报弹丸落点，并用改进型量子行为粒子群算法优化网络结构和权阈值，在此基础上对基于神经网络的初步预报数据进行滤波处理。最后进行预报仿真，在输入数据有噪声的情况下依然得到了较高的预报精度，从而证明该方法对预报弹丸落点是有效可行的，为弹丸的落点预报的实际应用提供了参考。
Abstract
A new prediction method based on radial basis function (RBF) neural network and an unscented Kalman filter technology is proposed for the precise and quick prediction of impact-point without exact flight data. Firstly, RBF neural network approximated external ballistics equation is used to predict the projectile impact-point, and the improved quantum-behaved particle swarm optimization algorithm is used to optimize the training method. On this basis, the tentative prediction data is processed with unscented Kalman filter. At last, the prediction simulation is carried out. The results show that a high prediction precision can be reached under the condition of input data with noise. The method proposed in this paper is efficient and available for impact-point prediction.
关键词
兵器科学与技术 /
径向基函数神经网络 /
粒子群优化 /
无迹卡尔曼滤波 /
落点预报
{{custom_keyword}} /
Key words
ordnance science and technology /
radial basis function neural network /
particle swarm optimization /
unscented Kalman filter /
impact-point prediction
{{custom_keyword}} /
{{custom_sec.title}}
{{custom_sec.title}}
{{custom_sec.content}}
参考文献
［1］ 杨绍卿. 火箭外弹道偏差与修正理论[M]. 北京: 国防工业出版社, 2011: 20-30.
YANG Shao-qing. The trajectory error and correction theory of rocket[M].Beijing: National Defense Industry Press, 2011: 20-30. (in Chinese)
[2] 柏杰锋, 王晓鸣, 李文彬. CCD与MEMS组合测量弹丸落点偏差的方法[J]. 系统仿真学报, 2009,21(2): 599-604.
BAI Jie-feng, WANG Xiao-ming, LI Wen-bin. Combined measuring method and simulation of deviation[J]. Journal of System Simulation,2009,21(2): 599-604. (in Chinese)
[3] 侯媛彬, 杜京义. 神经网络[M]. 西安: 西安电子科技大学出版社, 2007: 128-138.
HOU Yuan-bin, DU Jing-yi. Neural network[M].Xi’an: Xidian University Press, 2007: 128-138. (in Chinese)
[4] 隆金玲. Sum-of-Product 神经网络和径向基函数神经网络逼近能力研究[D]. 大连: 大连理工大学, 2008.
LONG Jin-ling. Approximation capability of sum-of-product neural networks and radial basis function neural networks[D].Dalian: Dalian University of Technology, 2008. (in Chinese)
[5] 段晓君. 神经网络的函数逼近能力分析[J]. 模糊系统与数学, 1998, 24(4): 80-84.
DUAN Xiao-jun. Analysis on neural network capability of approximation to function[J]. Fuzzy System and Mathematics, 1998,24(4):80-84. (in Chinese)
[6] FathiV, Montazer G A. An improvement in RBF learning algorithm based on PSO for real time applications[J]. Neurocomputing, 2013,111(2): 169-176.
[7] TsekourasG E. A simple and effective algorithm for implementing particle swarm optimization in RBF network's design using input-output fuzzy clustering[J]. Neurocomputing, 2013,108(2): 36- 44.
[8] SuX, Fang W, Shen Q, et al. An image enhancement method using the quantum-behaved particle swarm optimization with an adaptive strategy[J]. Mathematical Problems in Engineering, 2013, 2013(1): 1-14.
[9] SunJ, Fang W, Palade V, et al. Quantum-behaved particle swarm optimization with Gaussian distributed local attractor point[J]. Applied Mathematics and Computation, 2011, 218(7): 3763-3775.
[10] XiM, Sun J, Xu W. An improved quantum-behaved particle swarm optimization algorithm with weighted mean best position[J]. Applied Mathematics and Computation, 2008, 205(2): 751-759.
[11] RhudyM, Gu Y, Napolitano M R. An analytical approach for comparing linearization methods in EKF and UKF[J]. International Journal of Advanced Robotic Systems, 2013,208(10): 1- 9.
[12] 吴小文, 李擎. UKF 在 MEMS 陀螺随机噪声补偿的应用[J]. 火力与指挥控制, 2013,38(6): 8-10.
WU Xiao-wen，LI Qing. Research on application of UKF to compensation of MEMS gyro random noise[J]. Fire Control & Command Control, 2013,38(6): 8-10. (in Chinese)
{{custom_fnGroup.title_cn}}
脚注
{{custom_fn.content}}
