基于遗传算法优化BP神经网络的粮食温度预测研究  

Study on grain temperature prediction based on genetic algorithm optimized BP neural network

作　　者：郭利进[1] 乔志忠 GUO Li-jin;QIAO Zhi-zhong(School of Control Science and Engineering,Tiangong University,Tianjin 300387,China)

机构地区：[1]天津工业大学控制科学与工程学院,天津300387

出　　处：《粮食与油脂》2023年第1期34-37,51,共5页Cereals & Oils

摘　　要：针对粮食储存中温度参数的非线性时间序列问题,提出一种基于遗传算法(GA)优化BP神经网络算法的粮食温度预测模型,选取影响粮食温度的10个因素(仓外温度、仓外湿度、仓内顶温度、仓内中心温度、仓内底温度、仓内顶湿度、仓内中心湿度、仓内底湿度、仓内氧气浓度、粮食湿度)作为输入参数,分析后输出粮食温度。经验证,GA-BP模型具有比传统BP神经网络更好的预测精度和实用效果,在粮温预测领域中具有一定的应用前景。Aiming at the nonlinear time series problem of temperature parameters in grain storage,a grain temperature prediction model based on genetic algorithm(GA)optimized BP neural network algorithm was proposed.Ten factors affecting grain temperature(temperature outside the warehouse,humidity outside the warehouse,temperature at the top of the warehouse,temperature at the center of the warehouse,temperature at the bottom of the warehouse,humidity at the top of the warehouse,humidity at the center of the warehouse,humidity at the bottom of the warehouse,oxygen concentration in the warehouse,and grain humidity)were selected as input parameters,output grain temperature was after conducting outputted analysis.It was verified that the GA-BP model had better prediction accuracy and practical effect than the traditional BP neural network,and had a certain application prospect in the field of grain temperature prediction.

关 键 词：粮情温度预测 遗传算法 BP神经网络 

分 类 号：TS205[轻工技术与工程—食品科学]