基于可见-近红外光谱技术研发便携式贝贝南瓜品质无损检测仪  

A Portable Non-destructive Detector for Kabocha Squash Quality Based on Visible and Near-Infrared Spectroscopy

作　　者：王加龙 马坤[2] 高鹏 朱金芳[1,3] 张平 黄凡 WANG Jialong;MA Kun;GAO Peng;ZHU Jinfang;ZHANG Ping;HUANG Fan(College of Chemistry and Chemical Engineering,Xinjiang Agricultural University,Ürümqi 830052,China;Shanghai Academy of Agricultural Sciences,Shanghai 201106,China;College of Food and Pharmaceutical Sciences,Xinjiang Agricultural University,Ürümqi 830052,China)

机构地区：[1]新疆农业大学化学化工学院,新疆乌鲁木齐830052 [2]上海市农业科学院,上海201106 [3]新疆农业大学食品科学与药学学院,新疆乌鲁木齐830052

出　　处：《食品科学》2025年第6期254-262,共9页Food Science

基　　金：上海市科技攻关项目(2022DX1900100);上海市农业科学院科技支撑领域专项(农科应基2023(03));上海市设施园艺技术重点实验室开放基金课题。

摘　　要：为实现贝贝南瓜内在品质的快速无损检测,搭建以微型光谱仪为核心部件的便携式可见-近红外光谱检测装置,使用该装置采集不同发育期和贮藏期贝贝南瓜的光谱数据,采用一阶导数、卷积平滑(Savitzky-Golay,SG)、多元散射校正(multiplicative scatter correction,MSC)及以上方法组合的方式进行光谱预处理,筛选最佳的光谱预处理方法。采用连续投影算法提取特征波长,分别建立贝贝南瓜可溶性固形物含量(soluble solids content,SSC)和硬度的反向传播神经网络、多元线性回归和偏最小二乘回归预测模型,然后筛选出最优的SSC和硬度预测模型并导入装置,用于贝贝南瓜SSC和硬度的快速无损检测。结果显示,贝贝南瓜SSC最佳光谱预处理方法为SG+MSC,最优预测模型为反向传播神经网络预测模型,其预测集的决定系数Rp2、预测均方根误差和残差预测偏差分别为0.895 5、0.874 4°Brix、2.809 7;贝贝南瓜硬度最佳光谱预处理方法为SG+MSC,最优预测模型为多元线性回归预测模型,其预测集的决定系数Rp2、预测均方根误差和残差预测偏差分别为0.910 7、3.029 4 kg/cm2、3.214 4。以上结果表明,该检测装置能够较好地预测贝贝南瓜的SSC和硬度,可用于贝贝南瓜SSC和硬度的快速无损检测。A portable visible and near-infrared(VIS-NIR)spectroscopy-based device with a micro-spectrometer as the core component was built for rapid and non-destructive quality detection of kabocha squash.The spectral data of kabocha squash at different development and storage periods were collected using this device and pretreated by first derivative,Savitzky-Golay(SG),multiplicative scatter correction(MSC)or their combinations.The best spectral pretreatment method was selected.The characteristic wavelengths were extracted by continuous projection algorithm,and predictive models for soluble solids content(SSC)and firmness were established by backpropagation neural network,multiple linear regression or partial least squares regression.The optimal SSC and firmness prediction models were selected and imported into the device for rapid non-destructive testing of the SSC and firmness of kabocha squash.The results showed that the optimal spectral preprocessing method for the SSC was SG+MSC,and the backpropagation neural network model was selected as the optimal prediction model.The prediction set determination coefficient(Rp 2),root mean squared error of prediction(RMSEP)and residual prediction deviation(RPD)were 0.8955,0.8744°Brix and 2.8097,respectively.The optimal spectral pretreatment method for kabocha squash firmness was SG+MSC,and the optimal prediction model was the multiple linear regression prediction model,with Rp 2,RMSEP and RPD of 0.9107,3.0294 kg/cm2 and 3.2144,respectively.The above results show that the device can predict the SSC and firmness of kabocha squash well and can be used for their rapidnondestructive testing.

关 键 词：贝贝南瓜 可见-近红外光谱 可溶性固形物含量 硬度 无损检测 

分 类 号：O433.4[机械工程—光学工程]