内容：
 针对目前弹丸落点预报方法预报时间较长和精度不高的问题,提出了基于粒子群(PSO)优化的支持向量机(SVM)神经网络预测方法。该方法采用PSO优化算法优化SVM训练参数,以获得最优SVM神经网络落点预测模型。在此基础上,使用卡尔曼滤波处理外弹道数据形成神经网络训练数据,进行落点预报仿真测试。仿真结果表明,射程最大误差为7.371m,横偏最大误差为0.886m;落点预报时间在35ms之内,比数值积分法快了一个数量级,为弹丸落点预报的实际应用提供了一种途径。A SVM neural network prediction method based on particle swarm optimization (PSO) is proposed to solve the problem that the forecasting method of bullets has a long time and the accuracy is not high. The PSO optimization algorithm is used to optimize the SVM training parameters to obtain the optimal SVM neural network placement prediction model. On this basis, the Kalman filter is used to deal with the outer trajectory data to form the neural network training data, and the drop forecasting simulation test is carried out. The simulation results show that the maximum error is 7.371 m and the maximum error is 0.886 m. The prediction time of the drop point is within 35 ms, which is one order of magnitude higher than the numerical integration method, which provides a way for the practical application of the bullet drop forecast The

文件列表（点击上边下载按钮，如果是垃圾文件请在下面评价差评或者投诉）: