【摘要】 应用BP神经网络,通过苹果贮藏期间多维数据与呼吸强度的相关分析确定网络的拓扑结构,建立苹果呼吸强度的人工神经网络模型。仿真结果表明,该神经网络能很好地拟合不同贮藏条件下的呼吸强度,模型预测精度达到90%以上。同时,通过遗传算法优化BP神经网络的初始权值和阈值矩阵,使神经网络的预测精度进一步提高。更多还原

【Abstract】 A network topological structure was determined and an artificial neural network model for predicting respiration rate of Red Fuji apple during storage was established by using BP neural network.The correlation between multi-dimension input data and respiration rate was reported.Compared to the determined respiration rate under different storage conditions,the BP neural network model well predicted the respiration rate with the prediction precision above 90%.Meanwhile,the optimization of the weight and threshold of matrix by the application of genetic algorithms of BP neural network can improve the prediction precision.更多还原