基于GM(1,1)-BP组合模型在炮口初速预测的应用  

Application of GM(1,1)-BP Combined Model in Muzzle Velocity Prediction

作　　者：于晓 魏成亮 杨起 YU Xiao;WEI Chengliang;YANG Qi(Unit 32201 of PLA,Baicheng 137001,China)

机构地区：[1]解放军32201部队,吉林白城137001

出　　处：《火力与指挥控制》2024年第5期179-183,共5页Fire Control & Command Control

摘　　要：炮口初速是影响火炮射击精度的重要因素,如何能够准确预测出炮口初速,把握短暂战机精确打击目标,成为研究的重要方向。以往对炮口初速的预测大多采用单一的预测模型进行预测,虽运算过程简单但是预测精度并不理想。为提高模型预测精度,提出在GM(1,1)、BP神经网络预测模型基础上,利用误差平方和最小原则建立组合预测模型,对炮口初速进行预测。预测结果表明组合模型预测结果精度高于其他两个单项模型。Muzzle velocity is an important factor that affects the firing accuracy of artillery.How to accurately predict muzzle velocity and grasp the transient combat opportunity to strike targets precisely has become an important research direction.In the past,most of the muzzle velocity was predicted by a single prediction model.Although the calculation process is simple,the prediction accuracy is not ideal.In order to improve the prediction accuracy of the model,a combined prediction model is established based on the GM(1,1)and BP neural network prediction models with the principle of minimum the sum of error squares to predict the muzzle velocity.The prediction results show that the prediction accuracy of the combined model is higher than that of the other two single models.

关 键 词：GM(1 1)模型 BP神经网络模型 组合预测模型 炮口初速 

分 类 号：TJ35[兵器科学与技术—火炮、自动武器与弹药工程]