基于电子鼻的芒果储存时间预测方法研究

摘要

本文研究了一种芒果储存期预测方法,使用智能电子鼻实验检测了存储于9天内的芒果样品,主成分分析法实现了不同贮存时间芒果样品的区分,采用阈值随机共振方法提取芒果品质特性信息,并以互相关系数极大值构建芒果储存期预测模型.预测实验结果表明该模型预测准确度为87.5％.该预测方法具有检测快速、准确性好、成本低等优势.%In this paper, a mango storage time predicting method utilizing electronic nose is proposed. The electronic nose responses to mango samples stored within 9 days are measured. Principal component analysis (PC A) method can distinguish mango samples of the different storage time. The aperiodic stochastic resonance method is used to extract the mango quality features, and the cross-correlation coefficient maximums are used to build mango storage time predicting model. The validating experiments results indicate that the predicting accuracy of the developed model is 87. 5% . This method presents some advantages including rapid detection, good accuracy,and low cost.