摘要
目的 建立一种噪声小、自适应程度高的小麦粉预测模型的遗传算法-最小二乘法(genetic algorithm partial least squares, GA-PLS)检测小麦面粉品质。方法 采用AMBERⅡ手持式蓝牙光谱仪采集小麦面粉的近红外光谱,将采集的全波段光谱分段成波长相等的子区间,对每段子区间的小麦粉水分、灰度以及面筋含量进行最小二乘法预测建模(PLS模型),将每段建模数据进行遗传算法筛选优化,最终建立GA-PLS模型,幵与未分段的全谱段PLS模型进行对比分析。结果 基于遗传算法结合偏最小二乘的模型验证精度高于全谱段PLS模型,。其中小麦粉灰度值的相关系数(r~2)由0.679上升至0.919,小麦粉水分的r~2由0.701上升至0.923,小麦粉面筋的r~2由0.821上升至0.925。结论 该方法结果准确,精度高,适用于小麦面粉品质的现场快速检测。
Objective To establish a wheat flour prediction model with low noise and high adaptability for determination the wheat flour quality by genetic algorithm-least squares(GA-PLS). Methods The near-infrared spectrum of wheat flour was collected by AMBERII handheld Bluetooth spectrometer. The collected full-band spectrum was segmented into sub-intervals of equal wavelength, and the least squares prediction modeling of wheat flour moisture, gray scale and gluten content in each sub-interval were carried out. The PLS model was used to optimize the genetic algorithm for each segment of modeling data, and finally the GA-PLS model was established and compared with the unsegmented full-spectrum PLS model. Results The accuracy of the model based on genetic algorithm combined with partial least squares was higher than that of the full-spectrum PLS model. The correlation coefficient(r~2) of wheat flour gray value increased from 0.679 to 0.919, the r~2 of wheat flour moisture increased from0.701 to 0.923, and the r~2 of wheat flour gluten rose from 0.821 to 0.925. Conclusion The method is accurate and accurate, and suitable for the field rapid detection of wheat flour quality.
引文
[1]褚小立,袁洪福,陆婉珍.近红外分析中光谱预处理及波长选择方法进展与应用[J].化学进展,2004,16(4):528-542.Chu XL,Yuan HF,Lu WZ.Progress and application of spectral data pretreatment and wavelength selection methods in NIR analytical technique[J].Prog Chem,2004,16(4):528-542.
[2]杜朝,杨学举,刘桂茹,等.小麦面粉淀粉特性与烘烤品质关系的研究[J].河北农业大学学报,2002,25(4):29-33.Du C,Yang XJ,Liu GR,et al.Studies on the relations between starch properties of wheat flour and baking quality[J].J Hebei Agric Univ,2002,25(4):29-33.
[3]刘翠玱,徐莹莹,孙晓荣,等.基于多源大数据食品安全监测预控系统的设计与实现[J].食品科学技术学报,2018,36(3):88-94.Liu CL,Xu YY,Sun XR,et al.Design and realization of food safety monitoring and pre-control systembased on multi-source and big data[J].JFood Sci Technol,2018,36(3):88-94.
[4]Chen T,Chen G,Yang S,et al.Recent developments in the application of nuclear technology on agro-food quality and safety control in China[J].Food Control,2017,(72):309-312.
[5]Yue Y,Lei W,Wu YJ,et al.On-line monitoring of extraction process of flos lonicerae japonicae using near infrared spectroscopy combined with synergy interval PLS and genetic algorithm[J].Spectrochim Acta A,2017,(182):73-80.
[6]Muhammad A,Zou X,Elrasheid TH,et al.Near-infrared spectroscopy coupled chemometric algorithms for prediction of antioxidant activity of black goji berries(Lycium ruthenicum Murr.)[J].J Food Mesa Charact,2018,12(4):1-11.
[7]褚小立,骆献辉,袁洪福,等.在线近红外光谱测定MTBE进料中的醇烯比[C].中国分析测试协会科学技术奖发展回顾,2015Chu XL,Luo XH,Yuan HF,et al.Determination of the ratio of alcohol to olefin in MTBE feed by on-line near-infrared spectroscopy[C].Development Review of Science and Technology Awards of China Association for Analytical Testing,2015.
[8]Chinta S,Rao S,Viswanadha R.Similarity analysis between chromosomes of Homo sapiens and monkeys with correlation coefficient,rank correlation coefficient and cosine similarity measures[J].Genomics Data,2016,(7):202-209.
[9]Gu YF,Bao ZD,Lin YB,et al.The porosity and permeability prediction methods for carbonate reservoirs with extremely limited logging data:Stepwise regression vs.N-way analysis of variance[J].J Nat Gas Sci Eng,2017,(42):99-119.
[10]Atiye G,Mohammad,Akbari J.A hybrid imperialist competitive-simulated annealing algorithm for a multisource multi-product location-routinginventory problem[Z].
[11]Kumar N,Vidyarthi DP.A GA based energy aware scheduler for DVFSenabled multicore systems[J].Computing,2017,99(10):1-23.
[12]Jin H,Ricardo GO.Active wavelength selection for mixture identification with tunable mid-infrared detectors[J].Anal Chim Acta,2016,(937):11-20.
[13]刘翠玱,吴胜男,孙晓荣,等.基于近红外光谱的面粉灰分含量快速检测方法[J].农机化研究,2013,35(4):144-147.Liu CL,Wu SN,Sun XR,et al.Rapid detection of flour ash content in starch based on near infrared spectrum[J].J Agric Mech Res,2013,35(4):144-147.
[14]Bradford E,Schweidtmann AM,Lapkin A.Correction to:Efficient multiobjective optimization employing Gaussian processes,spectral sampling and a genetic algorithm[J].J Global Optim,2018,71(2):1-33.