【摘要】 提出一种基于遗传算法优化BP神经网络的方法预测日光温室湿度环境因子。实测日光温室内影响空气湿度的环境因子组成数据样本作为神经网络的输入,采用基于实数编码的遗传算法替代随机设定神经网络的初始权阈值,然后通过改进的BP算法在由遗传算法确定的搜索空间中对网络进行精确训练。模型预报值和实测值基于1:1线的决定系数R2和预测平均相对误差MSE分别为0.9857和3.1%。结果表明,遗传算法优化BP神经网络预报模型收敛速度快、预测精度高,可为日光温室的湿度环境调控制提供理论依据和决策支持。更多还原

【Abstract】 A new method of mixed BP neural network and Genetic Algorithm was proposed to predict the air humidity of sunlight greenhouse. Measure the environment factors influencing air humidity as data input, and adopt the genetic algorithm based on real-coded instead of the weight beginning with random value to train the neural network with improved BP algorithm accurately. The determination coefficient R2 between predicting and measuring values based on 1:1 line and mean relative prediction error were 0.9857 and 3.1% respectively. The results show that the method has fast convergence speed and high prediction precision, which can be used theory instruction and management supplying in sunlight humidity environment control.更多还原