HUANG Xin, ZHAO Han-dong
(School of Mechatronic Engineering, North University of China, Taiyuan 030051, China)
Abstract： In order to forecast projectile impact points quickly and accurately, a projectile impact point prediction method based on generalized regression neural network (GRNN) is presented. Firstly, the model of GRNN forecasting impact point is established; secondly, the particle swarm algorithm （PSD） is used to optimize the smooth factor in the prediction model and then the optimal GRNN impact point prediction model is obtained. Finally, the numerical simulation of this prediction model is carried out. Simulation results show that the maximum range error is no more than 40 m, and the lateral deviation error is less than 0.2 m. The average time of impact point prediction is 6.645 ms, which is 1 300.623 ms less than that of numerical integration method. Therefore, it is feasible and effective for the proposed method to forecast projectile impact points, and thus it can provide a theoretical reference for practical engineering applications.
Key words： trajectory correction; impact point prediction; generalized regression neural network（GRNN）; numerical integration method
CLD number： TP391 Document code： A
Article ID： 1674-8042（2016）01-0007-06 doi： 10.3969/j.issn.1674-8042.2016.01.002
References
［1］ ZHAO Han-dong. The study of theory and technique for rocket trajectory correction by the control force of lateral push jet. Nanjing: Nanjing University of Science & Technology, 2008.
［2］ ZHAO Xin-sheng, SHU Jing-rong. Trajectory calculation theory and application. Beijing: The Publishing House of Ordnance Industry, 2006.
［3］ Leonard C, Hainz III, Costello M. In flight projectile impact point prediction. AIAA Atmospheric Flight Mechanics Conference and Exhibit, 2004.
［4］ SHI Jin-guang, XU Ming-you, WANG Zhong-yuan, et al. Application of Kalman filtering in calculation of trajectory falling point of trajectory correction projectiles. Journal of Ballistics, 2008, 20(3): 41-48.
［5］ DAI Ming-xiang, YANG Xin-ming, YI Wen-jun, et al. Kalman filtering algorithm for impact point prediction of satellite-guided projectile. Journal of Projectiles, Rockets, Missiles and Guidance, 2012, 32(5): 117-120.
［6］ Hainz L, Costello M. Modified linear theory for rapid trajectory prediction. Journal of Guidance, Control, and Dynamics, 2004.
［7］ XIU Guan, WANG Liang-ming, YANG Rong-jun. Construction and simulation of linear trajectory model. Journal of Naval University of Engineering, 2010, 22(2): 86-94.
［8］ MATLAB Chinese Forum. 30 case analysis of Matlab neural network. Beijing: Beijing University of Aeronautics, 2010.
［9］ Kennedy J, Eberhart R. Particle swarm optimization. Neural Networks, 1995, (4): 1942-1948.
基于广义回归神经网络的弹丸落点预报方法
黄 鑫， 赵捍东
（中北大学， 机电工程学院， 山西 太原 030051）
摘 要: 为快速精确地预报弹丸落点， 提出了基于一种广义回归神经网络的弹丸落点预报方法。 首先， 建立了GRNN网络落点预报模型； 其次， 采用粒子群算法对预报模型中的光滑因子进行了优化， 得到了最佳的GRNN网络的落点预报模型； 最后， 对该预报模型进行数值仿真。 结果表明， 该方法预报射程的最大误差不超过40 m， 横偏误差不超过0.2 m； 且预报落点的平均时间为6.645 ms， 与数值积分法相比， 减少了1 300.623 ms。 因此， 该方法快速精确地预报弹丸落点是有效可行的， 可作为工程实际应用的理论参考。
关键词: 弹道修正； 落点预报； 广义回归神经网络； 数值积分法
引用格式： HUANG Xin, ZHAO Han-dong. Projectile impact point prediction method based on GRNN. Journal of Measurement Science and Instrumentation, 2016, 7(1)： 7-12. ［doi： 10.3969／j.issn.1674-8042.2016.01.002］
[full text view]
