An External Ballistics Fitting Method Based on the Support Vector Machine

Abstract:

It is because of many reasons the trajectory calculated from the theoretical model and the actual trajectory have some error, so the experimental results on the theoretical trajectory must be corrected. In this paper, two degrees of freedom of particle trajectory equations are used to determine the ballistic coefficient. And a SVM Neural Network which has a great learning ability and generalization ability of the extremely small sample is used to adaptive learning the solver deviation of the fit between the trajectory and measured trajectory and amend the ballistic coefficient and modified theoretical trajectory solver results. The test shows that this method has a good precision and stability, and the algorithm can be simple programmed. And it has some value in engineering.

• Periodical: Advanced Materials Research (Volumes 753-755)
• Pages: 2855-2858
• DOI: https://doi.org/10.4028/www.scientific.net/AMR.753-755.2855
• Online since: August 2013
• Authors: Zhong Liu, Jing Xin An, Guo Dong Zhang
• Keywords: Ballistic Coefficient, External Ballistics, Fitting, Support Vector Machine (SVM)

References

[1] Wu Xianju, Ni Qingjie and Guo Wenge: The Application of Improved Particle Ballistic to the BB and Rocket Compound Assisted Projectile, Journal of Shenyang Ligong University, Vol 2, pp.51-54, (2010).

[2] Xiao Liang, Wang Zhongyuan and Zhou Weiping: Research on Similar Conditions and Simulative Experiments of Exterior Ballistics for Low Trajectory, Acta Armam EntarII, Vol 4, pp.437-441, (2010).

[3] Zhu Minjie, Wang Jingye: A Method of Trajectory Simulation in Real Time Simulation System, Journal of System Simulation, Vol 11, pp.303-306, (2001).

[4] Wang Tao: Study on Ballistic Trajectory Simulation in Antiaircraft Artillery, Journal of System Simulation, Vol 6, pp.1184-1186, (2004).

[5] An Jingxin, Xu Lin, Liu Zhong, Zhang Guodong: An External Ballistics Fitting Method Based On the Ballistic Coefficient, Ship Electronic Engineering, Vol 1, pp.89-91, (2012).

[6] Zhong Lei, He Qinghua, Zhao Chunming: The Virtual Miss Shooting Forecasting Based on Support Vector Machine Algorithm, Command Control and Simulation, Vol 4, pp.66-69, (2008).

[7] Xu Xiuying, Sheng Weixin: Improvement of Radar Target Recognition Based on an Improved Support Vector Machine, Modern Radar, Vol 10, pp.53-56, (2005).

[8] Rong Haina, Zhang Gexiang and Jin Weidong: Selection of Kernel Functions and Parameters for Support Vector Machines in System Identification, Journal of System Simulation, Vol 11, pp.3204-3208, (2006).

DOI: 10.1109/isads.2005.1452120