论文部分内容阅读
研究了利用主成分分析与BP神经网络结合的方法对黄山毛峰茶进行品质检测。首先应用主成分分析法对反映茶叶香气信息的原始特征变量进行分析,提取出前5个主成分,再以这些主成分作为BP神经网络的输入,建立3层BP神经网络预测模型。试验结果表明,该模型相对于未经过主成分分析的BP神经网络模型,建模效率大大提高,判别准确率也由92.5%提高到97.5%。说明主成分分析与BP神经网络结合应用于黄山毛峰茶品质检测是有效的。
The method of combining principal component analysis and BP neural network was used to test the quality of Huangshan Maofeng tea. Principal component analysis (PCA) is used to analyze the original characteristic variables that reflect the aroma of tea, and the first five principal components are extracted. Then these principal components are used as the input of BP neural network to establish a 3-layer BP neural network prediction model. The experimental results show that compared with the BP neural network model without principal component analysis, the model greatly improves the modeling efficiency and increases the accuracy of the discrimination from 92.5% to 97.5%. It indicates that the combination of principal component analysis and BP neural network is effective in quality inspection of Huangshan Maofeng tea.