论文部分内容阅读
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1 300.623ms。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。
In order to predict the projectile falling point quickly and accurately, a projectile falling point prediction method based on a generalized regression neural network is proposed. Firstly, the model of GRNN network is set up. Secondly, particle swarm optimization is used to optimize the smoothing factor in the forecasting model, and the best model of GRNN network is obtained. Finally, numerical simulation of the model is carried out . The results show that the maximum error of this method is less than 40 m and the horizontal deviation is less than 0.2 m. The mean time of forecasting is 6.645 ms, which is 1 300.623 ms lower than the numerical integration method. Therefore, it is effective and feasible to forecast the projectile falling point quickly and accurately by this method, which can be used as a theoretical reference for practical engineering application.