基于改进遗传算法优化BP网络的密度预测  

Density Prediction of BP Networks Based on Improved Genetic Algorithm Optimization

作　　者：史慧芳 郭进勇 伍凌川 杨治林 袁申 李全俊 王勇 黄荔 Shi Huifang;GuoJinyong;Wu Lingchuan;Yang Zhilin;Yuan Shen;Li Quanjun;Wang Yong;Huang Li(Department of Intelligent Manufacture,Automation Research Institute Co.,Ltd.of China South Industries Group Corporation,Mianyang 621000,China)

机构地区：[1]中国兵器装备集团自动化研究所有限公司智能制造事业部,四川绵阳621000

出　　处：《兵工自动化》2024年第11期76-82,86,共8页Ordnance Industry Automation

摘　　要：为了能利用工艺参数实时预测药柱密度并提高密度预测精度,提出采用改进遗传算法优化BP网络(improved genetic algorithm backpropagation neural network,IGA-BPNN)的炸药密度预测模型。通过动态调整GA的交叉概率和变异概率,确定BPNN权重和阈值的最优值,构建IGA-BP预测模型,利用采集的工艺参数,基于所构建模型进行炸药密度预测。实验结果表明:改进的GA对交叉率和变异率做出了更好的调整,能快速搜寻BPNN的最优权重和阈值,提高炸药压制密度的预测精度。In order to predict the density of explosive column in real time and improve the prediction accuracy,an improved genetic algorithm was used to optimize the BP network(improved genetic algorithm backpropagation neural network,IGA-BPNN)model for predicting explosive density.By dynamically adjusting the crossover probability and mutation probability of GA,the optimal values of BPNN weights and thresholds were determined,and the IGA-BP prediction model was constructed to predict the explosive density based on the collected process parameters.The experimental results show that the improved GA makes a better adjustment to the crossover rate and mutation rate,can quickly search the optimal weight and threshold of BPNN,and improve the prediction accuracy of explosive pressing density.

关 键 词：炸药密度 改进遗传算法 交叉率 变异率 BP神经网络 

分 类 号：TJ55[兵器科学与技术—军事化学与烟火技术] TP391[自动化与计算机技术—计算机应用技术]