PSO-BP神经网络在油料产量预测中的应用  

Application of PSO-BP neural network in forecasting oil material production

作　　者：郭利进[1] 于洋 GUO Li-jin;YU Yang(College of Electrical Engineering and Automation,Tiangong University,Tianjin 300387,China)

机构地区：[1]天津工业大学电气工程与自动化学院,天津300387

出　　处：《粮食与油脂》2022年第4期107-110,共4页Cereals & Oils

摘　　要：针对传统油料产量预测方法精度低、需求数据量大的问题提出误差反传(back propagation,BP)神经网络预测模型,并利用粒子群算法优化该模型的权值和阈值,从而提高收敛速度以及预测精度。经历年油料产量及其相关数据训练测试,结果表明,该预测模型预测精度较高,为油料产量预测提供了一种有参考价值的应用方法。Aiming at the problems of low accuracy and large amount of demand data of traditional oil material production forecasting methods,a BP neural network forecasting model was proposed,and the weight and threshold of the model was optimized by particle swarm optimization algorithm,so as to improve the convergence speed and forecasting accuracy.Through the training test of annual oil production and its related data,the results showed that the forecasting model had high prediction accuracy,which provided a valuable application method for oil production forecasting.

关 键 词：油料产量 BP神经网络 粒子群优化 预测模型 

分 类 号：TP18[自动化与计算机技术—控制理论与控制工程]