【作者】 张昆； 洪添胜； 代芬； 尹令； 代秋芳；

【Author】 Zhang Kun Hong Tiansheng Dai Fen Yin Ling Dai Qiufang (Key Laboratory of Key Technology for South Agricultural Machine and Equipment, South China Agricultural University, Ministry of Education, Guangzhou 510642; College of Engineering of South China Agricultural University, Guangzhou 510642, China)

【机构】 华南农业大学南方农业机械与装备关键技术省部共建教育部重点实验室； 华南农业大学工程学院；

【摘要】 为研究苹果内部品质,利用美国ASD公司生产的FieldSpec3便携式地物波谱仪对苹果进行反射率的光谱测量,将所得近红外光谱数据按照近红外短波和近红外长波分为两组,其中近红外短波选取的波长范围为400-1100nm,长波选取的波长范围为1300-2000nm,将两组数据分别间隔两点取一点作为人工神经网络的输入量,建立苹果糖度的预测模型,试验研究表明:利用近红外短波进行预测的平均误差为0.26%,而利用近红外长波进行预测的平均误差为0.33%。更多还原

【Abstract】 To study the interal quality of apples, FieldSpec 3 portable spectroradiometer was used to measure apple’s reflectance. Near infrared spectra data were divided into two groups: the near-infrared shortwave and near-infrared longwave . The wavelength range for near- infrared shortwave is 400-1100nm, the wavelength range for near-infrared longwave is 1300-2000nm. Take data as artificial neural network’s input, establish the prediction model of apple’s degree. The results show: the average error of near-infrared shortwave is 0.26%, while the average error of near-infrared longwave is 0.33%.更多还原