基于高光谱成像的烟丝掺配比例检测研究
Detection of tobacco blend ratio based on hyperspectral imaging
-
摘要: 针对目前卷烟生产线缺乏快速检测烟丝掺配比例方法的问题,利用高光谱成像技术和机器学习方法,采集不同掺配比例的混合烟丝光谱数据,探讨单一及组合预处理方法对模型构建效果的影响。采用偏最小二乘回归(PLSR)和支持向量机回归(SVR)建立回归模型,并利用最小角回归(LARS)、连续投影算法(SPA)、竞争性自适应重采样(CARS)及遗传算法(GA)进行特征波段选择,建立简化模型。结果表明:不同预处理方法的单一或组合使用均会影响回归模型的精度,其中小波变换与SG滤波联用(Wave+SG)方法相比原始数据将平均绝对百分比误差(MAPE)降低了1.2%;基于Wave+SG-GA-PLSR建立的回归模型表现最佳,其在两组分掺配中的训练集和测试集MAPE分别为1.415%和1.531%;基于两组分掺配建立的方法同样适用于多组分掺配,在三组分和四组分的预测集中,MAPE均低于8.361 5%。高光谱成像技术结合机器学习方法能够较为准确地预测混合烟丝中各组分的掺配比例,可为烟丝掺配均匀性的在线监测及卷烟生产过程的质量控制提供参考。Abstract: This study focuses on detecting tobacco blend ratios using hyperspectral imaging. Due to the lack of rapid methods for detecting tobacco blend ratios on cigarette production lines, spectral data were collected from mixed tobacco with different blend ratios using hyperspectral imaging technology and machine learning methods. The effects of single and combined preprocessing techniques on model performance were explored. Regression models were established using partial least squares regression (PLSR) and support vector machine regression (SVR). Feature wavelength selection was performed with least angle regression (LARS), successive projections algorithm (SPA), competitive adaptive reweighted sampling (CARS), and genetic algorithm (GA) to build simplified models. The results showed that preprocessing methods, either individually or combined, affected model accuracy. The combined wavelet transform and SG filtering (Wave+SG) method reduced the mean absolute percentage error (MAPE) by 1.2% compared to raw spectral data. The Wave+SG-GA-PLSR model performed best, with MAPE values of 1.415% and 1.531% for the training and test sets in two-component blends, respectively. This method was also applicable to multi-component blends, with MAPE values below 8.361 5% for both three-component and four-component blends. Hyperspectral imaging combined with machine learning can accurately predict the proportions of components in mixed tobacco, providing a reference for online monitoring of blend uniformity and quality control in cigarette production.
-
Key words:
- hyperspectral imaging technology /
- blend ratio /
- band selection /
- machine learning /
- regression analysis
-
-
[1]
丁美宙,刘欢,刘强,等.梗丝形态对细支卷烟加工及综合质量的影响[J].食品与机械,2017,33(9):197-202.
-
[2]
陈帅伟,胡苏林,崔宁,等.“三丝” 掺配比例对卷烟理化指标的影响研究[J].西南农业学报,2015,28(6):2742-2745.
-
[3]
徐成龙,宋朝鹏,戴亚,等.梗丝与膨胀丝及薄片丝对卷烟主流烟气中3种有害成分释放量的影响[J].湖南农业大学学报(自然科学版),2013,39(1):23-25.
-
[4]
胡立中,张胜军,余小平,等.均匀设计-PLS-NIR法预测卷烟配方烟丝中梗丝及薄片丝含量[J].中国烟草学报,2010,16(2):26-30.
-
[5]
-
[6]
温若愚,席年生,张大波,等.不同混丝模式对烟丝掺配效果的影响[J].烟草科技,2008,41(9):13-16.
-
[7]
刘栋,陈越立,李华杰,等.取样量、取样次数对烟丝混合均匀性检测的影响[J].郑州轻工业学院学报(自然科学版),2013,28(1):45-49.
-
[8]
寇霄腾,张勇,张卉,等.基于RGB图像特征的卷烟梗丝掺配比例检测[J].食品与机械,2021,37(9):78-82.
-
[9]
-
[10]
LU Y Z,SAEYS W,KIM M,et al.Hyperspectral imaging technology for quality and safety evaluation of horticultural products:A review and celebration of the past 20-year progress[J].Postharvest Biology and Technology,2020,170:111318.
-
[11]
ZHANG C,GUO C T,LIU F,et al.Hyperspectral imaging analysis for ripeness evaluation of strawberry with support vector machine[J].Journal of Food Engineering,2016,179:11-18.
-
[12]
GOMEZ C,GHOLIZADEH A,BORU。VKA L,et al.Using legacy data for correction of soil surface clay content predicted from VNIR/SWIR hyperspectral airborne images[J].Geoderma,2016,276:84-92.
-
[13]
NEITTAANMÄKI-PERTTU N,GRÖNROOS M,TANI T,et al.Detecting field cancerization using a hyperspectral imaging system[J].Lasers in Surgery and Medicine,2013,45(7):410-417.
-
[14]
张卫正,张伟伟,张焕龙,等.基于高光谱成像技术的甘蔗茎节识别与定位方法研究[J].轻工学报,2017,32(5):95-102.
-
[15]
郭文孟,薛宇毅,罗靖,等.基于高光谱成像的烟叶泛青特征分析与表征[J].烟草科技,2023,56(7):84-91.
-
[16]
朱亚昆,梅吉帆,郭文孟,等.基于PPF投影算法和高光谱技术的卷烟牌号识别模型[J].轻工学报,2024,39(4):118-126.
-
[17]
陶发展,杨栋,洪伟龄,等.基于高光谱成像的烟丝中梗签分类识别研究[J].河南科技大学学报(自然科学版),2024,45(3):32-42
,5. -
[18]
梅吉帆,李智慧,李嘉康,等.基于高光谱成像技术的配方烟丝组分判别[J].分析测试学报,2021,40(8):1151-1157.
-
[19]
LI B,WANG Y Q,LI L S,et al.Research on apple origins classification optimization based on least-angle regression in instance selection[J].Agriculture,2023,13(10):1868.
-
[20]
WANG J G,TIAN T,WANG H J,et al.Improving the estimation accuracy of rapeseed leaf photosynthetic characteristics under salinity stress using continuous wavelet transform and successive projections algorithm[J].Frontiers in Plant Science,2023,14:1284172.
-
[21]
ZHU L,GU W Z,SONG T Q,et al.Coal seam in situ inorganic analysis based on least angle regression and competitive adaptive reweighted sampling algorithm by XRF-visNIR fusion[J].Scientific Reports,2022,12(1):22365.
-
[22]
褚小立,袁洪福,王艳斌,等.遗传算法用于偏最小二乘方法建模中的变量筛选[J].分析化学,2001,29(4):437-442.
-
[23]
令峰,邢富康,韦克苏,等.基于高光谱成像技术和深度学习的烤后烟叶品种分类判别[J].中国烟草科学,2024,45(4):83-92.
-
[24]
MISHRA P,NORDON A,TSCHANNERL J,et al.Near-infrared hyperspectral imaging for non-destructive classification of commercial tea products[J].Journal of Food Engineering,2018,238:70-77.
-
[25]
吴龙国,王松磊,何建国.基于高光谱技术的土壤水分无损检测[J].光谱学与光谱分析,2018,38(8):2563-2570.
-
[26]
FU P,MEACHAM-HENSOLD K,GUAN K Y,et al.Estimating photosynthetic traits from reflectance spectra:A synthesis of spectral indices,numerical inversion,and partial least square regression[J].Plant,Cell & Environment,2020,43(5):1241-1258.
-
[27]
ZHANG P P,SHEN B B,JI H W,et al.Nondestructive prediction of mechanical parameters to apple using hyperspectral imaging by support vector machine[J].Food Analytical Methods,2022,15(5):1397-1406.
-
[1]
-
点击查看大图
计量
- PDF下载量: 1
- 文章访问数: 15
- 引证文献数: 0
下载:
