基于迁移成分分析的近红外光谱定量分析通用模型  

A Universal Model for Quantitative Analysis of Near-Infrared Spectro sc opy Based on Transfer Component Analysis

作　　者：王雪[1,2,4] 王子文 张广月 马铁民 陈争光[1] 衣淑娟[3,4] 王长远[2] WANG Xue;WANG Zi-wen;ZHANG Guang-yue;MA Tie-min;CHEN Zheng-guang;YI Shu-juan;WANG Chang-yuan(College of Electrical and Information,Heilongjiang Bayi Agricultural University,Daqing 163319,China;Daqing Center of Inspection and Testing for Agricultural Products and Processed Products,Ministry of Agriculture and Rural Affairs,Daqing 163319,China;College of Engineering,Heilongjiang Bayi Agricultural University,Daqing 163319,China;Heilongjiang Province Research Center of Ecological Rice Seedling Raising Device and Whole Course Mechanized Engineering Technology,Daqing 163319,China)

机构地区：[1]黑龙江八一农垦大学信息与电气工程学院,黑龙江大庆163319 [2]农业农村部农产品及加工品质量监督检验测试中心(大庆),黑龙江大庆163319 [3]黑龙江八一农垦大学工程学院,黑龙江大庆163319 [4]黑龙江省水稻生态育秧装置及全程机械化工程技术研究中心,黑龙江大庆163319

出　　处：《光谱学与光谱分析》2024年第11期3213-3221,共9页Spectroscopy and Spectral Analysis

基　　金：国家自然科学基金项目(52275246);黑龙江省自然科学基金项目(LH2022C061);黑龙江省博士后科研启动基金项目(LBH-Z19217);黑龙江八一农垦大学三横三纵支持计划项目(ZRCQC201907)和黑龙江八一农垦大学学成人才科研启动基金项目(XDB202004)资助。

摘　　要：在近红外光谱定量分析中,由于光谱数据采集设备和环境条件的不同,已有模型在使用到不同设备或不同环境时会出现预测精度低的现象。为了增强定量分析模型的普适性和通用性,提高模型的预测精度,提出一种基于改进的迁移成分分析转移方法(TM-TCA)的近红外光谱定量分析通用模型构建策略。改进的迁移成分分析方法采用二次校正策略,通过对从机光谱数据的两次校正,改善由于仪器偏移、漂移或不稳定性引起的光谱差异性,确保数据的一致性和准确性,消除仪器不同或外界条件影响产生的偏差,使校正后的从机光谱数据特征尽可能接近主机光谱,以此增强模型对从机光谱的预测能力。首先求出主机与从机光谱转换矩阵,通过转换矩阵进行待测样品的一次校正,缩小主机与从机样品间受外界条件因素产生的差异性。将经过转换矩阵转换后的主机-从机光谱数据矩阵作为迁移成分分析方法的输入。接下来,基于多指标综合迭代优化选择迁移学习中的核函数和特征值个数的基础上构建定量分析通用模型。为了验证迁移成分分析改进效果,与多种方法的转移效果进行比较。通过优化分析选择RBF核函数,特征值个数为52,实验表明,基于TM-TCA的光谱校正率达到97.1%,光谱平均差异(ARMS)与转移前相比下降了82.9%,比TM和TCA方法分别降低了46.5%和30.2%。为了验证模型构建策略的有效性,构建基于TM-TCA和偏最小二乘回归(PLSR)的玉米水分定量分析通用模型,并对不同设备条件下的模型通用性进行分析。TM-TCA-PLSR模型的预测效果与TCA-PLSR模型的预测效果相比较,模型的预测决定系数达到了0.8729,提升了41%,预测均方根误差(RMSEP)和平均绝对误差(MAE)分别为0.1543和0.1159,均降低了90%以上,并且TM-TCA-PLSR模型相对分析误差(RPD)值超过了2.5,模型具有实际应用的价值。表明了TM-TCA转移方法能有效减There are differences in spectral data acquisition equipment and environmental conditions.In near-infrared spectroscopy quantitative analysis,low prediction accuracy was found in the models established.To enhance the universality and generalizability of near-infrared spectroscopy quantitative analysis models and improve their predictive accuracy,a universal model strategy is proposed based on the transfer component analysis method improved by the transfer matrix(TM-TCA).The TM-TCA method adopts a two-step correction strategy to correct the slave spectral data,reducing the spectral differences caused by instrument offsets,drifts,or instabilities.It can make the characteristics of the corrected slave spectral data similar to the master's to the maximum extent,eliminate the deviation caused by different instruments or external conditions,and enhance the prediction ability of the model to the slave spectral data.Firstly,the spectral transfer matrix between the master and the slave is obtained.The transfer matrix converts the master-slave spectral data matrix,which is then used as the input for the transfer component analysis method.Subsequently,the kernel function and the number of eigenvalues in transfer learning are chosen using iterative optimization of multiple indicators.The RBF kernel function is selected,and the number of eigenvalues is 52.Comparative experiments are conducted with other methods to verify the effectiveness of TM-TCA.The experimental results show that the spectral correction rate based on TM-TCA reaches 97.1%,with a reduction of 82.9%in the average relative mean squared(ARMS).The ARMS value surpasses that achieved by the transfer matrix and TCA methods,46.5%and 30.2%,respectively.To validate the effectiveness of the model construction strategy,a universality quantitative analysis model is established based on TM-TCA and partial least squares regression(PLSR)under different device conditions.Compared to the prediction performance,the TCA-PLSR model's coefficient of determination of the TM-TCA-PL

关 键 词：近红外光谱 定量分析 模型转移 迁移成分分析 

分 类 号：O657.33[理学—分析化学]