摘要
烟草是最重要的经济作物,它从一开始就在农业经济和国际贸易中占有重要地位,是国民经济的重要组成部分。烟叶质量评价是风格特色烟叶研究、烟叶加工特性研究、模块配方手段研究和叶组替代技术研究等众多烟草前沿研究方向的基础。本试验以灰色理论为基础,结合神经网络理论、模糊理论等综合评价方法对烤烟化学成分、烤烟产区、烤烟形态特征与化学成分、烤烟感官质量等诸多问题进行了研究和评价,主要研究结论如下:
1、众多的烟草化学成分指标增加了烟叶品质分析和质量综合评价的难度。针对这一问题,本试验选取主要烤烟产区样品共247份,并运用灰色统计分析法研究了这些样品的10个化学成分指标。结果表明:氮碱比属于大影响指标,对烟叶品质的影响程度最大;总氮、糖碱比、氯、还原糖、烟碱、水溶性总糖、总植物碱、钾氯比为中影响指标,对烟叶品质的影响程度仅次于大影响指标,蛋白质属于小影响指标。配方叶组选择烟叶原料时,如果烟叶化学成分不在适宜区域内,总氮等大影响指标选择小于适宜区域的化学成分比较合理;还原糖、烟碱、水溶性总糖、总植物碱、钾氯比、糖碱比、氮碱比、氯等中影响指标应选择大于适宜区域的化学成分对烟叶品质损害较小。
2、烤烟化学成分指标之间的关系密切而复杂。为简化化学成分指标,本文选取我国主要烟区272份烟叶样品,对14个化学成分指标进行了灰色关联聚类分析。结果表明:当聚类临界值为0.8时,14个化学成分指标可被聚为5类,总氮、糖碱比、氮碱比、氯、总挥发性酸可以分别作为每类的代表;当聚类临界值为0.7时,化学成分指标被聚为酸性和碱性两大类,代表性指标分别为糖碱比和氮碱比。与系统聚类相比较,灰色关联聚类更具有合理性。
3、单料烟感官质量评定大多采用描述性语言对各单项指标进行评价,不易形成定量的综合评价结果。针对这一问题,本研究采用层次模糊法对单料烟感官质量进行了综合评价。结果表明:层次分析法确定各单项指标的权重符合实际的评吸要求,模糊综合评价容易给出定量的综合评价结果,在此基础上计算f函数值便于对不同的单料烟样品进行排序。
4、为了探索烤烟等级替代、分组加工的理论基础,本试验采用灰色等权聚类法对18个烤烟产区的68份下部叶化学成分进行了聚类,结果表明,福建将乐县下部叶化学成分属于A类,为化学成分很协调区域,其他17个烤烟产区下部叶化学成分都属于B类,为化学成分协调区域。当某个聚类系数与其他聚类系数同时差异显著,且该聚类系数为最大时,综合聚类系数和一般聚类系数结果一致。采用总氮、氮碱比、糖碱比、氯和总挥发性酸5个化学成分指标与采用14个指标对烤烟产区进行灰色等权聚类的结果具有较好的相似性。采用平均值—标准偏差法确定白化函数的值域,能有效避免人为因素对聚类结果的影响。
5、为了探讨不同烤烟产区化学成分的相似性,为烤烟分组加工和等级替代提供理论依据,本试验采用因子分析与广义灰色绝对关联相结合的方法对不同烤烟产区烟叶上部叶化学成分进行了统计分析,结果表明,与福建邵武产区烤烟上部叶化学成分最接近的地区为云南宜良,其次是广东南雄,化学成分差异最大的是云南华宁;因子分析法可以解决烤烟化学成分评价指标的多重共线性问题;以灰色绝对关联度为依据,结合烤烟感官质量评定可以评价不同烤烟产区化学成分的相似性;正、负相关与关联度大小的关系对于评价烤烟产区化学成分的接近程度来说没有影响,但负的原始数据需进行转换。
6、本试验采用多元方差分析法对不同部位烟叶的化学成分在烤烟产区间的差异性、同一产区不同品种间化学成分的差异性以及不同产区不同品种间化学成分的差异性进行了系统分析,结果表明,各个部位烟叶在各个产区之间的综合效应有极显著的差异;云南省各个部位烟叶在各个品种之间的综合效应有极显著的差异;烤烟B_2F品种之间、产区之间以及品种和产区的交互作用之间的综合效应差异都达到了极显著水平;烤烟C_2F品种之间、品种和产区的交互作用之间的综合效应差异都不显著,产区之间的综合效应差异达到了极显著水平;烤烟C_3F品种之间、产区之间以及品种和产区的交互作用之间的综合效应差异都不显著;烤烟X_2F品种之间、产区之间的综合效应差异都达到了极显著水平,品种和产区的交互作用之间综合效应差异不显著。多元方差分析法可以对多组样本的多指标样本进行综合效应分析,得到多组样本的综合检验结果。该评价结果对烟叶等级替代、分组加工、小配方模块等特色工艺技术更具有实际指导意义。
7、本试验采用多因素方差分析法对10个烤烟产区4个年份4个等级的烟叶进行了系统分析,结果表明,不同等级、不同产地和不同年份对烤烟糖碱比的影响大小分别为等级〉产地〉年份,F值和显著水平表明,不同等级、不同产地对烤烟糖碱比的影响都达到了极显著水平;不同年份对烤烟糖碱比的影响不显著。年份和产地、年份和等级的交互作用(共同作用)没有对糖碱比造成显著影响,等级和产地的交互作用对糖碱比造成了显著影响。不同等级、不同产地和不同年份对烤烟氮碱比的影响大小分别为等级)产地)年份,F值和显著水平表明,不同等级、不同产地、不同年份对烤烟氮碱比的影响都达到了极显著水平;年份和等级的交互作用没有对氮碱比造成显著影响,年份和产地、等级和产地的交互作用对氮碱比造成了显著影响。多因素方差分析法可以对产区、等级、年份及其交互作用对糖碱比、氮碱比的影响程度进行有效评价,该评价结果有助于等级替代时各影响因素的取舍。
8、以我国主产烟区的主栽烤烟品种K326为材料,测定了3个等级(C_3F、B_2F和X_2F)共计391份样品的烟碱含量和物理性状,分析了烟碱含量与物理性状的相互关系。结果表明:烟碱含量和物理性状在样品间存在着广泛的变异;在一定范围内,烟碱含量与上部叶单叶重呈显著正相关,与上、下部叶长分别呈极显著正相关和显著负相关;与中、下部叶宽分别呈显著负相关和极显著负相关,与厚度和叶面密度均不相关;烟叶烟碱含量与上部叶单叶重的关系可用S形曲线(?):e~((1.484-2.041/x))来描述,与上、下部叶长的关系可分别用逆函数(?)=8.225-265.750/x和(?)=0.427+105.053/x来描述,与中、下部叶宽的关系可分别用二次函数(?)=0.533+0.316x-0.010x~2和(?)=-0.157+0.307x-0.009x~2来描述,且均达到显著水平,烟碱含量与其他物理性状的曲线回归不显著,表明曲线回归一般较简单线性回归分析更有效。简单相关、曲线回归和次数分布三种方法结合可以较好地反映烟碱含量和物理性状的内在关系。
9、本试验以我国主产烟区的主栽烤烟品种K326为材料,测定了X_2F(下橘二)等级共计124份样品的总氮、烟碱含量和物理性状,系统地分析了总氮含量、氮碱比与物理性状的相互关系。结果表明:总氮含量、氮碱比和物理性状在样品间存在着广泛的变异。总氮含量随单叶重、叶长、叶面密度的增加而逐步下降;氮碱比随叶长、叶宽的增加而上升,随叶面密度的增加而逐渐下降。总氮与叶长、叶面密度的关系可分别用逆函数(?)=0.827+38.047/x、复合函数(?)=1.880×0.996~x描述;氮碱比与叶宽、叶面密度的关系可分别用复合函数(?)=0.413×1.023~x描述、幂函数(?)=2.791×x~(-0.354)描述。
10、本试验以我国主产烟区124份烤烟中部叶样品为研究材料,采用数理统计方法系统地分析了还原糖含量、还原糖烟碱比与若干形态特征的相互关系。结果表明:还原糖含量和形态特征在样本间存在着广泛的变异;还原糖、还原糖烟碱比与单叶重的变化趋势相似,即总体上随单叶重增加而呈下降趋势,至单叶重为12.3g时达到最低点,然后又呈上升趋势;随叶长的变化规律也相似,都是随叶长的增加而增大,在叶长超过64.9cm后,二者迅速增加;与叶厚的变化曲线一致,都是随叶厚的增加而逐渐下降,当叶厚大于0.126mm后,还原糖烟碱比下降幅度较大;还原糖烟碱比随叶宽增加逐渐上升;分别建立了单一形态特征对还原糖含量、还原糖烟碱比的曲线回归方程,还原糖与单叶重、叶厚的关系可分别用二次函数(?)=45.243-3.667x+0.139x~2、(?)=11.217+316.779x-2026.595x~2进行描述,还原糖烟碱比与单叶重、叶厚的关系可分别用对数函数(?)=16.278-3.375ln x、复合函数(?)=14.075×0.002~x进行描述;且均达到5%显著水平,表明曲线回归较简单线性回归分析更有效。经过数据验证,建立的曲线回归方程拟合性较好。
11、本研究以我国烤烟主产区122份烟叶中部叶样品为基础,系统地分析了烟叶钾含量、氯含量、钾氯比与物理性状之间的关系。结果表明:各性状在供试材料间存在着广泛的变异。烟叶钾含量与叶长、叶面密度分别呈极显著正相关、负相关;烟叶氯含量与叶面密度呈显著正相关;烟叶钾氯比与叶长、叶厚分别呈极显著正相关、显著负相关。南方烟区烤烟中部叶烟叶钾含量与叶长、叶面密度的关系可分别用逆函数(?)=7.803-343.262/x、复合函数(?)=4.612×0.991~x进行描述;烟叶氯含量与叶面密度的关系可用二次函数(?)=1.268-0.034x+0.0003x~2描述;烟叶钾氯比与叶长、叶厚的关系可分别用复合函数(?)=0.023×1.105~x、二次函数(?)=94.408-1355.208x+5897.907x~2进行描述;且均达到5%显著水平,表明曲线回归一般较简单线性回归分析更有效。烤烟中部叶钾含量、钾氯比随单叶重的增加而降低,随叶长的增长而增加明显;氯含量随单叶重的增加而升高,随叶长的增加而迅速下降,随叶厚的增加而增加;南方烟区烤烟叶宽为23.5cm、叶面密度为85.31 g/m~2是两个敏感闽值。
12、本文以我国南方烟区烤烟品种K326不同部位的166份样品为例,研究了烤烟主要化学成分与叶片长度的关系。结果表明,烟碱、总氮、还原糖、钾、氯、氮碱比、糖碱比、钾氯比、叶长在样品间存在广泛的变异。氯和钾氯比在部位间差异不显著,叶长、烟碱、氮碱比和糖碱比在部位间差异显著;总氮、还原糖在中部、下部间差异未达到显著水平,但二者均与上部叶差异显著;上部、中部叶的钾含量差异不显著,但二者均与下部叶差异显著。上部、下部叶长达到55.3cm时比较敏感,超过该长度时,烟碱、总氮、氮碱比出现明显变化;在中、下部叶长大于55.3cm后,还原糖含量也出现突变。上部叶的糖碱比与中、下部叶的钾氯比、钾、氯含量在叶长大于61.5cm后变化较大。
13、以烤烟品种K326为供试材料,采用典型相关分析方法研究了烤烟不同部位烟叶的主要物理性状和化学成分的关系。结果表明,烤烟物理性状和化学成分所具有的显著性指标因部位而异;上、中、下3个部位物理性状共有的显著性指标是叶长、叶厚和叶面密度,化学成分共有的显著性指标是氯含量、钾含量和钾氯比,且后者对典型变量的相对作用大小一致,表现为钾＞钾氯比＞氯;烤烟不同部位烟叶叶长、叶厚和叶面密度与钾、钾氯比和氯的关系最为密切。典型负载系数可以作为确定各部位物理特性和化学成分显著性指标的重要依据。
14、为了指导配方打叶的小配方模块设计,本试验利用灰色理论建立了烤烟醇化过程糖碱比GM(1,1)灰色模型、糖碱比新陈代谢GM(1,1)灰色模型、氮碱比GM(1,1)灰色模型、氮碱比指数平滑GM(1,1)灰色修正模型和氮碱比对数GM(1,1)灰色修正模型。模型检验结果表明,建立的各种糖碱比、氮碱比模型都有意义,而且可用作中、长期预测。糖碱比灰色模型精度较高,两种模型精度分别达到了98.37%和99.73%;氮碱比灰色模型通过指数平滑和对数修正后,模型精度分别达到了93.56%和88.52%。
15、利用灰色理论建立了烤烟醇化期间总香味成分、香气质、香气量的GM(1,1)灰色模型。河南B_2F的总香味成分、香气质、香气量的GM(1,1)灰色模型精度分别达到了98.63%、99.24%和99.91%;河南C_3F的总香味成分、香气质、香气量的GM(1,1)灰色模型精度分别达到了97.82%、99.94%和99.09%。
16、建立模型的首要问题是恰当地选取进入模型的解释变量。针对这一问题,本文采用灰色绝对关联度和灰色关联聚类相结合的综合评价方法,对烤烟主要化学成分和香气质的灰色模型变量进行了分析。结果表明,进入香气质灰色预测模型的化学成分指标变量为总氮、还原糖、pH值、糖碱比、氮碱比;进入香气量灰色预测模型的化学成分指标变量为总氮、还原糖、钾、pH值和糖碱比。灰色绝对关联度和灰色关联聚类相结合不仅解决了自变量与因变量之间的关系问题,也解决了自变量之间的多重共线性问题。
17、建立了烤烟化学成分与香气质、香气量的GM(1,N)-BP神经网络预测模型,结果表明,香气质GM(1,N)-BP神经网络预测模型的模拟精度、预测精度分别达到95.29%、98.56%,比单纯GM(1,N)模型的预测精度提高了3.4%;香气量GM(1,N)-BP神经网络预测模型的模拟精度、预测精度分别达到95.13%、98.20%,比单纯GM(1,N)模型的预测精度提高了2.16%。当网络结构为1-3-1时,香气质GM(1,N)-BP神经网络预测模型的预测精度最高;当网络结构为1-9-1时,香气量GM(1,N)-BP神经网络预测模型的预测精度最高。
18、采用时间序列分析法,建立了卷烟烟气焦油量的预测模型。结果表明,所建立的卷烟烟气焦油量的ARMA(2,2)预测模型,模型预测精度达到了99.51%,平均相对误差为0.49%,属于一级(优等)模型,预测精度优于因果模型;利用时间序列建立预测模型可以避开模型自变量的选择这一难题,但时间序列一般用于短期预测,不能用于长期预测。
Tobacco is important economic crop and has great influence on national economy.Tobacco quality evaluation is the base of grades of tobacco leaf substitution, grouping process and little formulation module.The test got such as follows results of tobacco chemical components,the relationship between chemical components and shape character and sensory quality by integrating grey theory,neural network theory and fuzzy theory.
1.It was difficult for fiue-cured tobacco leaves to analyze and evaluate quality because of numerous chemical compositions index.To solve the problem,the test analyzed ten routine chemical compositions index of 247 samples from main tobacco-growing areas of China by grey statistic analysis.The results indicated that the great influence index were ratio of total nitrogen to nicotine(RNN) which had the biggest influence on quality of flue-cured tobacco leaves,on the opposite,it was inferior to the great influence index that the influence of total nitrogen(TN),ratio of total sugar to nicotine(RSN),chlorine,reducing sugar,nicotine,total sugar,total alkaloid and ratio of potassium to chlorine(RPC) on quality of flue-cured tobacco leaves,and protein was little influence index.If the chemical compositions were beyond optimum range when blending leaf groups selected flue-cured tobacco leaves,it was rational to select less than optimum range for the great influence index such as RNN.On the opposite,it was rational to select more than optimum range for the chemical compositions index such as reducing sugar,nicotine,total sugar,total alkaloid,RPC,TN,RSN and chlorine.
2.There existed close and complicated relationship among chemical component indexes in flue-cured tobacco leaves.To simplify chemical component indexes,272 samples from main tobacco-growing areas of China were selected as materials,and 14 common chemical component indexes were analyzed by grey relational degree cluster.The results indicated that the 14 common chemical component indexes could be classified into five groups when cluster critical value was fixed at the level of 0.8.Meantime,total nitrogen,ratio of total sugar to nicotine,ratio of total nitrogen to nicotine,chlorine and total volatile acids were determined the representative indexes for each group.When cluster critical value was fixed at the level of 0.7, the chemical component indexes could be classified into two groups,named acids group and alkaloid group with representative indexes of the ratio of total sugar to nicotine and ratio of total nitrogen to nicotine,respectively.Grey relational degree cluster analysis was more rational than hierarchical cluster analysis.
3.It is difficult to obtain mensurable comprehensive evaluation results because descriptive language for different single index was mostly used to evaluating unblended cigarette sensory quality.In order to solve the problem,the hierarchical fuzzy systems were introduced to comprehensive evaluation for unblended cigarette sensory quality.The results indicated that the weight determined by analytic hierarchy process was in accord with actual needs;fuzzy evaluation could easily make mensurable comprehensive results;ffunction values estimated on the basis of analytic hierarchy process and fuzzy transformation were convenient for giving the quality order of different unblended cigarette samples.
4.In order to explore the theory basis of flue-cured tobacco grade substitute and grouping process,the test clustered 68 chemical component samples of 18 flue-cured tobacco-growing areas by grey equal weight cluster method.The results indicated that the chemical components of Jiangle county of Fujian province should be clustered A class which belonged to better region of chemical components,and other 17 flue-cured tobacco-growing areas should be clustered B class which belonged to good region of chemical components.The result of comprehensive cluster coefficient and common cluster coefficient was consistent when some cluster coefficient was distinguished difference with other cluster coefficients and it was the biggest.The cluster result was similar by applying 5 indexes including total nitrogen,the ratio of total nitrogen to nicotine,total sugar to nicotine,chlorine and volatile acid and 14 indexes.It could be avoided of influence on cluster results of factitious factor by applying mean-standard deviation method to confirm the values of albino function.
5.In order to discuss the chemical components comparability of different main tobacco-growing areas and explore the theory basis of flue-cured tobacco grade substitute and grouping process,the test analyzed the chemical components of different main tobacco-growing areas upper leaves by combining factor analysis and absolute degree of grey incidence.The results indicated the most similar area was Yiliang of Yunnan province with chemical components of upper leaf of Shaowu of Fujian province,the next was Nanxiong of Guangdong province,and the most difference of chemical components was Huaning of Yunnan province.The factor analysis method could solve the problem of multiple mutual linear of chemical components evaluation indexes.On the basis of absolute degree of grey incidence,the chemical components comparability of different main tobacco-growing areas was evaluated combining sensory evaluation.The relation between positive correlation, negative correlation and degree of grey incidence had no effect on evaluation of the chemical components comparability of different main tobacco-growing areas;however,the minus original data were converted.
6.The test systems analyzed the chemical components difference of different position tobacco leaves among main tobacco-growing areas,different variety in the same tobacco-growing area and different variety in the different tobacco-growing area,respectively. The results indicated that the comprehensive effect difference was significant at 1%level among main tobacco-growing areas;the comprehensive effect difference was significant at 1% level among different variety at Yunnan province;the comprehensive effect difference was significant at 1%level among different variety,different main tobacco-growing areas and interaction of tobacco-growing areas and variety for B_2F;the comprehensive effect difference was not significant at 5%level among different variety and interaction of tobacco-growing areas and variety,but the comprehensive effect difference was significant at 1%level among different tobacco-growing areas for C_2F;the comprehensive effect difference was not significant at 5%level among different variety,different main tobacco-growing areas and interaction of tobacco-growing areas and variety for C_3F;the comprehensive effect difference was significant at 1%level among different variety and tobacco-growing areas,but the comprehensive effect difference was not significant at 5%level among interaction of tobacco-growing areas and variety for X_2F.The multianalysis of variance could be used the comprehensive effect analysis for more indexes of samples,and the evaluation results had factual significance for grades of tobacco leaf substitution,grouping process and little formulation module.
7.The test analyzed tobacco leaves of four grades among four years of ten tobacco-growing areas by multifactor variance method.The results indicated that the influence orders was grades＞tobacco-growing areas＞years on the ratio of total sugar to nicotine of different grades,different tobacco-growing areas and different years,and the influence of different grades and different tobacco-growing areas were the significant at 1%level,but it was not significant at 5%level of different years.The mutual influence of years and tobacco-growing areas,years and grades was not significant at 5%level on the ratio of total sugar to nicotine,but the mutual influence of grades and tobacco-growing areas was significant at 5%level on the ratio of total sugar to nicotine.The influence orders was grades＞tobacco-growing areas＞years on the ratio of total nitrogen to nicotine of different grades, different tobacco-growing areas and different years,and the influence of different grades, different years and different tobacco-growing areas were the significant at 1%level.The mutual influence of years and grades was not significant at 5%level on the ratio of total nitrogen to nicotine,but the mutual influence of grades and tobacco-growing areas,grades and tobacco-growing areas was significant at 5%level on the ratio of total s nitrogen to nicotine. The multifactor variance method could be used the comprehensive evaluation on the influence of tobacco-growing areas,grades and years on the ratio of total sugar to nicotine and the ratio of total nitrogen to nicotine,and the evaluation results had factual significance for grades of tobacco leaf substitution.
8.K326,a flue-cured tobacco cultivar widely used in main tobacco-growing areas of China,was selected as materials to determine the nicotine content and physical properties;total 391 samples including three grades(C_3F,B_2F and X_2F) were employed to studying the relationship between the nicotine content and physical properties.The results indicated that there existed extensive variation among samples for physical properties and the nicotine content.In the given range,the nicotine content had significant positive correlation with the single leaf weight of upper leaf,high positive correlation and negative correlation with leaf length of upper leaf and lower leaf respectively,negative correlation and high negative correlation with leaf width of cutters and lower leaf respectively,and no correlation with other physical properties.The relationship could be described by S equation(?)=e~((1.484-2.041/x)) between nicotine content and single leaf weight of upper leaf,by inverse equation (?)=8.225-265.750/x and(?)=0.427 + 105.053/x between nicotine content and leaf length of upper leaf and lower leaf respectively,by quadratic equation(?)=0.533+0.316x-0.010x~2 and (?)=-0.157 + 0.307x-0.009x~2 between nicotine content and leaf width of cutters and lower leaf respectively.All above equations were significant at 5%level.However,the curve regression equation between nicotine content and other physical properties was not significant at 5%level, and were more efficient than simple linear regression.The relationship between nicotine and physical properties could be described by using the methods of linear correlation,curve regression and degree distribution.
9.Total 124 samples of X_2F grades of K326,a flue-cured tobacco cultivar widely planted in main tobacco-growing areas of China,were selected as materials to determine total nitrogen content,nicotine content and physical properties;relationships of total nitrogen content and ratio of total nitrogen to nicotine with physical properties were analyzed.The results indicated that there existed largely variation for total nitrogen content,ratio of total nitrogen to nicotine and physical properties among samples.The total nitrogen content decreased gradually along with the increase of single leaf weight,leaf length and leaf density;the ratio of total nitrogen to nicotine increased along with the increase of leaf length and leaf width,and decreased along with the increase of leaf density.Relationships of total nitrogen content could be described by inverse equation of(?)=0.827+38.047/x with leaf length,and compound equation of (?)=1.880 x 0.99~x with leaf density,respectively;relationships of ratio of total nitrogen to nicotine could be described by compound equation of(?)= 0.413×1.023~x with leaf width,and power equation of(?)= 2.791×x~(-0.354) with leaf density,respectively.
10.By using statistical analysis methods,124 samples of cutters in flue-cured tobacco leaves from main tobacco-growing areas of China were used as materials to analyze the relationship between the reducing sugar content(RS),ratio of reducing sugar to nicotine (RS/Nic) and shape characters.The results indicated that there existed extensive variation among samples for shape characters and RS.The variation tendency was similar between RS, RS/Nic and single leaf weight that was generally decrease along with increase of single leaf weight,however it was increase after single leaf weight was beyond 12.3g.Similarly,the variation tendency was similar between RS,RS/Nic and leaf length that was increase along with increase of leaf length,especially,both rapidly increased after leaf length was beyond 64.9cm.The variation tendency was also similar between RS,RS/Nic and leaf thickness that was generally decrease along with increase of leaf thickness,and RS/Nic rapidly decreased after leaf thickness was beyond 0.126mm.Moreover,RS/Nic gradually increased along with increase of leaf width.The curve regression equations between RS,RS/Nic and each shape characters were built respectively.The relationship of RS could be respectively described by quadratic equation(?)=45.243-3.667x+0.139x~2,(?)=11.217+316.779x-2026.595x~2 with single leaf weight,leaf thickness.Meantime,the relationship of RS/Nic could be respectively described by logarithmic equation(?)=16.278-3.375In x,compound equation (?)=14.075×0.002~x with single leaf weight,leaf thickness.All above equations were significant at the 5%level,and more efficient than simple linear regression analysis.The forecast effect was better after data validation.
11.122 samples of cutters in flue-cured tobacco leaves from main tobacco-growing areas of China were used as materials to analyze the relationship between potassium content, chlorine content,ratio of potassium to chlorine and physical property.The results indicated that there existed extensive variation among samples of flue-cured tobacco leaves studied.The potassium content had respectively high significant positive correlation with leaf length, negative correlation with leaf density.The chlorine content had significant positive correlation with leaf density.The ratio of potassium to chlorine had respectively high significant positive correlation with leaf length,significant negative correlation with leaf thickness.The relationship of potassium content could be respectively described by inverse equation (?)=7.803-343.262/x with leaf length,by compound equation(?)=4.612×0.991~x with leaf density of cutters in flue cured-tobacco leaves from south tobacco-growing areas of China. Meantime,the relationship of chlorine content could be described by quadratic equation (?)=1.268-0.034x + 0.0003x~2 with leaf density.The relationship of ratio of potassium to chlorine could be respectively described by compound cquation(?)=0.023×1.105~x with leaf length,by quadratic equation(?)=94.408-1355.208x + 5897.907x~2 with leaf thickness.All above equations were significant at the 5%level,and more efficient than simple linear regression analysis.The potassium content and chlorine content decreased along with increase of single leaf weight, significantly increased along with increase of leaf length of cutters in flue-cured tobacco.The chlorine content increased along with increase of single leaf weight,rapidly decreased along with leaf length,increased along with increase of leaf thickness.These were two sensitive values of leaf width as 23.5cm,leaf density as 85.31 g/m~2 of cutters in flue cured-tobacco leaves from south tobacco-growing areas of China.
12.In order to find the correlation between appearance quality and inner quality in flue-cured tobacco,the experiment studied the correlation between main chemical compositions and leaf length of different stalk positions in flue-cured tobacco by applying descriptive statistics,ANOVA,nonparametric tests,multiple comparisons and degree distribution.The results indicatcd that there existed extensive variation among chemical compositions and leaf length.The difference of chlorine,ratio of potassium versus chlorine among stalk positions was not significant in flue-cured tobacco.However,it is opposite of leaf length,nicotine,ratio of total nitrogen versus nicotine and ratio of rcductivc sugar versus nicotine.For total nitrogen and rcductivc sugar,the diffcrcncc between cutters and lower leaf was not significant,but it was significant between cutters,lower leaf and upper leaf.Similarly, for potassium,the difference between cutters and upper leaf was not significant,but it was significant between cutters,upper leaf and lower leaf.When leaf length was over 55.3cm,there was biggish change for nicotine,total nitrogen and ratio of total nitrogen versus nicotine of upper leave and lower leaf and for rcductive sugar of cutters and lower leaf.For ratio of rcductivc sugar versus nicotine of upper leaf and potassium,chlorine and ratio of potassium versus chlorine of cutters and lower leaf,there was also biggish change.
13.K326,a flue-cured tobacco variety,was selected as materials and employed to study the correlation between main chemical components and physical properties of different leaf positions by using the method of canonical correlation analysis.The results indicated that the significant indexes of chemical components and physical properties were different with different leaf positions.The common significant indexes of different leaf positions including upper leaf,cutters and lower leaf were leaf length,leaf thickness and leaf density for physical properties,and chlorine content,potassium content and the ratio of potassium to chlorine for chemical components.The effects of common significant indexes of chemical components showed the same order of potassium＞ratio of potassium to chlorine＞chlorine among different leaf positions.The correlations of leaf length,leaf thickness and leaf density with potassium,chlorine and ratio of potassium to chlorine were significant for different leaf positions.The canonical loading coefficients could be as a reference for determining the significant indexes of physical properties and chemical components in flue-cured tobacco leaves.
14.In order to advise the little blending leaf groups design of blending strips,the test founded GM(1,1) grey model and metabolic GM(1,1) grey model of ratio of total sugar to nicotine,and GM(1,1) grey mode,exponent smoothness GM(1,1) grey mode and logarithm GM(1,1) grey mode of ratio of total nitrogen to nicotine in aged flue-cured tobacco.The model test indicated that all model founded were significative and were applied in medium and long-term forecast.The model accuracy of ratio of total sugar to nicotine was higher and attained 98.37%and 99.73%,respectively.The model accuracy of ratio of total nitrogen to nicotine attained 93.56%and 88.52%after the GM(1,1) grey model was modified by exponent smoothness and logarithm.
15.The test founded GM(1,1) grey model of total aroma contents,aroma quality and aroma quantity of aged leaf by grey theory.The model accuracy of total aroma contents,aroma quality and aroma quantity of Henan B2F attained 98.63%,99.24%and 99.91%,respectively. The model accuracy of total aroma contents,aroma quality and aroma quantity of Henan C3F attained 97.82%,99.94%and 99.09%.
16.The most important problem of modeling was to correctly select the variable of model. To solve the problem,the test analyzed the grey model variable between main chemical components and aroma quality of flue-cured tobacco by integrated evaluation method both absolute degree of grey incidence and grey incidence.The results indicated that the variables of aroma quality modeling were total nitrogen,reducing sugar,ph values,the ratio of total sugar to nicotine and the ratio of total nitrogen to nicotine.The variables of aroma quantity modeling were total nitrogen,reducing sugar,potassium,ph values and the ratio of total sugar to nicotine The problem of relation between independent variable and dependent variable was solved by integrated evaluation method both absolute degree of grey incidence and grey incidence,so was the problem of multiple mutual linear of independent variable.
17.The test founded GM(1,N)-BP neural network forecast model of aroma quality and aroma quantity.The results indicated that the model simulation and forecast accuracy of aroma quality attained 95.29%and 98.56%,respectively,and the forecast accuracy increased 3.4% than that of GM(1,N).The model simulation and forecast accuracy of aroma quantity attained 95.13%and 98.20%,respectively,and the forecast accuracy increased 2.16%than that of GM (1,N).When network structure was 1-3-1,the forecast accuracy of aroma quality was the highest.So was when network structure of aroma quantity was 1-9-1.
18.In order to provide the base for computer-aided design blending,the tar of cigarettes from different batches of the same trademark as materials,were analyzed by time series analysis and the forecast model of tar of cigarettes smoke was built.The results indicated that the forecast precision of ARMA(2,2) model reached 99.51%and the average relative error was 0.49%,so the ARMA(2,2) model belonged to the first grade model(excellent model) and was superior to cause and effect model.Modeling by time series could escape the difficulty of independent variable choice of model,however,time series usually was used as short-term forecast and not long-term forecast.
引文
[1]Akehurst,B.C.Tobacco.Humanities Press,New York.1981,764.
[2]Garner,W.W.The production of tobacco.The Blakiston Co.,Maple Press,York,PA,1946.
[3]左天觉.朱尊权(译).烟草的生产、生理和生物化学[M].上海远东出版社,1993.
[4]Keene,C.K.,G.J.Wagner.Direct demonstration of duvatriendiol biosynthesis in glandular heads of tobacco trichomes.Plant physical.1985(79):1026-1032.
[5]Severson R.F.;R.F.Arrendale;O.T.Chortyk,C.F.Green;F.A.Thome;J.L.Stewart;A.W.Johnson.Isolation and characterization of the sucrose esters of the cuticular waxes of green tobacco leaf.J.Agric.Food Chem.1985(33):870-875.
[6]R.F.Severson;A.W.Johnson;D.M.Jackson.Cuticular constituents of tobacco:factors affecting their production and their role in insect and disease resistance and smoke quality.Rec.Ad v.Tob.Sci.1985(11):105-174.
[7]Coussirat,J.C.;P.Schlitz;W.W.Reid;Y.Bouteraou.Diterpenes in nicotiana tobacum Genetic vontrol of the production of(z)-abienol and α and βcembratriene diols.1983-84.Ann.du T abac.SEITA 1984(2):123-130.
[8]Gwynn,G.R.;R.F.Severson;D.M.Jackson;M.G.StepHenson.Inheritance of sucrose esters cont aining β-methyl-valeric acid in tobacco.Tob.Sci.,1985(29):79-81.
[9]Nielson,M.T.;G.A.Jones.G.B.Collins.Inheritance pattern for secreting and nonsecretiog gla ndular trichomes in tobacco,crop Sci.1982(22):1051-1053.
[10]Chaplin,J.F.,and G.S.Miner.Chemical,physical and production aspects of tobacco and s moke.In Recent Advances in Tobacco Sciences 6:3-14.34~(th) Tobacco Chemists Research Co nference.Oct.27-29,1980,Richmond,VA.
[11]Tso,T.C.PHysical and biochemistry of tobacco plants.Dowden,Hutchinson and Ross,Inc.,S troudsburg,PA,1972.
[12]朱尊权.烟叶的可用性与卷烟的安全性[J].烟草科技,2000(8):3-6.
[13]朱尊权.重点品牌的原料保障-论政策及农、商、工交接收购方式的创新[J].烟草科技,2007(11):5-7.
[14]Tso,T.C.Tobacco as potential food and smoking material.Beitr.zur Tabakforsh.1977,9(2):63-66.
[15]闫克玉,袁志永,吴殿信,等.烤烟质量评价指标体系研究[J].郑州轻工业学院学报(自然科学版),2001,16(4):57-60.
[16]吴殿信,袁志永,闫克玉。等.烤烟各等级烟叶质量指数的确定[J].烟草科技,2001(12):9-15.
[17]黎妍妍,黄元炯,许自成,等.河南烟区烟叶质量可用性的综合评价[J].安徽农业科学,200 6,34(9):1903-1904。
[18]杜文,谭新良,易建华,等.用烟叶化学成分进行烟叶质量评价[J].中国烟草学报,2007,13(3):25-31.
[19]Green,C.Relationship of leaf composition to smoke composition.In:Proceedings of Ameri can Chemical Society Symposium.Recent Advances in the Chemical Composition of Tobac co & Tobacco Smoke.1977.pp.426-71.
[20]Obi,Y.,Muramatsu,M.& Shimada,Y.Evaluation of tobacco quality from pyrolytic aspects.Part Ⅶ.Relationship between chemical constituents of tobacco leaves & gaseous constitue nts of cigarette smoke.Agri.Biol.Chem.1970(8):1220-23.
[21]The 173rd American Chem.Society Meeting.Agric.Food Chem.Division,New Orleans,L ouisiana,1977.
[22]Matsushita,H.,M.Noguchi,T.Kisaki,K.Kato,Y.Tsujino,and A.Saito.Nomicotine derivat ives as tobacco flavorants.Japan Kokai Tokyo Koho.Patent 1980 19,076.
[23]Ferretti,A.,Flanagan,V.P.& Ruth,J.M.Nonenzymatic browning in a lactose-casein model system.F.Agric.Food Chem.1970(18):13-18.
[24]Chaturvedi.V.K.Correlations among.extensibility bum thickness nitrogenous constituents pH ospHorus and potassium in fermented leaf of cigar-wrapper tobacco.Indian J.Agric,Sci.1987,57(4):241-244.
[25]PHilips,M.& Bacot,A.M.The chemical composition of certain grads of type 11,American flue-cured tobacco.Relationships of composition to grade characteristics.JAOAC,1953(36):504-523.
[26]Yamaoto,K.& Noguchi,M.Isolation of sugar compounds of asparagines,pHenylalanine,tyr osine,and valine from cured tobacco leaves.Agri.Biol.Chem.1973,37,2185-2187.
[27]Weeks,W.W.& Seltmann,H.Effect of sucker control on the volatile compounds in flue-c ured tobacco.F.Agric.Food.Chem.1986(34):899-904.
[28]Fenner,R.A.Thermo-analytical characterization of tobacco constituents.Rec.Adv.Tob.Sci.1988(14):82-113.
[29]Frankenburg W G.Chemical changes in the harvested tobacco leaf.Ⅱ.Chemical and enzymic conversions during fermentation and aging[J].Adv.Enzymology,1950(10):325-431.
[30]Lewis,E.B.,D.G.Card,and J.S.McHargue.Tobacco stalks,hemp hurds,and sorghum bag asse as sources of cellulose for making high-quality paper.Ky.Agr.Exp.Sta.Bull.1948(515):14.
[31]Heath,H.B.& Rrineccius,G..Flavor Chemistry & Technology.A Ⅵ Publishing Co.,Wes tport,CT,1986.
[32]Roberts,D.L.Natural tobacco flavor.Rec.Adv.Tob.Sci.1988(14):49-81.
[33]Shmuk,A.A.The Chemistry & Technology of Tobacco.Pishchepromedadat,Moscow,1953.
[34]Smith,W.T.Jr,Haidar,N.F.& Patterson,J.M.Pyrolysis of valine,a-aminobutyric acid & p raline.Tob.Sci.1975(19):142-143.
[35]Ivanov,N.G..& Ognyanov,I.On resins in Bulgarian Oriental tobaccos.In:Proceedings of 4~(th) International Tobacco Scientific Congress,Athens,Greece(organized by CORESTA and National Tobacco Board of Greece).1966,779-85.
[36]Davis,D.L.Waxes and lipids in leaf and their relationship to smoking quality and aroma.Rec.Adv.Tob.Sci.1976(2):80-106.
[37]Chortyk,O.T.,Severson,R.F.& Higrnan,H.C.ChromatograpHic determination of hydrocar bon waxes in tobacco leaf and smoke.Beitr.Tabakforsch.1975(8):204-10.
[38]Grossman,K.D.,Deszyck,E.J.,Ikeda,R.M.& Bavley,A.Study of the pyrolysis of solane sol.Chem.Ind.1962,1950-1951.
[39]Leffingwell,J.C.,Young,H.J.& Bernasek,E.Tobacco Flavoring for Smoking Products.R.J.Reynolds Tobacco Company,Winston-Salem,NC.1972.
[40]Kallianos,A.G..PHenolics and acids in leaf and their relationship to smoking quality and a roma.Rec.Adv.Tob.Sci.1976(2):61-79.
[41]Jarboe,C.H.& Rosene,C.J.Volatile products of pyrolysis of nicotine.F.Chem.Soc.1961(16):2455-2458.
[42]Weeks,W.W.,Campos,M.P.& Moldoveanu,S.Pyrolysis of cherry red tobacco and 1-deox y-1-[(s)-2-(3-pyridyl)-β-D-fructose(pyranose and furanose isomers) Amadori Products of cher ry red tobacco.F.Agric.Food Chem.1995,43(8):2247-2253.
[43]Dawson,R.F.(1946) Development of some recent concepts in the physiological chemistry of the tobacco alkaloids,Plant PHysiol.1946(21):115-130.
[44]Abadalah,F.Can Tobacco Quality be Measured ? Lockwood Publishing Co.,New York,1970.
[45]Enzell C R.Leaf composition in relation to smoking quality and aroma[J].Rec.Adv.Tob.Sci.,1980(6):64-122.
[46]Matsushima S.Relitionship between composition of tobacco essention oils and its aroma[J].Nippon Nogeikagaku Kalshi,1980,54(12):1027-1035.
[47]Kung,S.D.,J.A.Saunders,T.C.Tso,D.A.Vaughan,M.Womack,R.C.Staples and G.R.Beecher.J.Food Sci.1980,45(2):320-322.
[48]Kakovka,A.Cigarette paper from tobacco stalks.U.S.Patent 1964,3,126,010.
[49]Copley,M.J.,R.K.Eskew,and J.J.Willaman.Problems in the industrial utilization of tobacc o.Chem.and Eng.News,ACS,1942(20):1220-1222.
[50]Akehurst,B.C.Tobacco.2~(nd) Edit.Longman,London and New York.1981,764.
[51]Kratchanov,C.G.,and N.A.Kirtchev.Determination and characterization of pectic substances in tobacco.Comptes rendus de 1' Academic bulgare des Sciences 1978,31(11):1425-1427.
[52]Kung,S.D.,and T.C.Tso.Tobacco as a potential food source and smoke material:Soluble protein content,extraction and amino acid composition.J.Food Sci.1978(43):1844-1848.
[53]姜茱,谢胜利,范洪慈,等.烤烟叶片大小与烟叶化学成分的关系研究初报[J].中国烟草科学,1991(2):13-17.
[54]王玉军,谢胜利,邢淑华,等.烤烟叶片厚度与主要化学组成相关性研究[J].中国烟草科学,1997(1):11-13.
[55]肖吉中,江锡瑜,黄立栋,等.烤烟叶片重量与质量关系的初步研究[J].烟草科技,1995(2):30-31.
[56]于川芳,李晓红,罗登山,等.玉溪烤烟外观质量因素与其主要化学成分之间的关系[J].烟草科技,2005(1):5-7.
[57]许自成,刘国顺,刘金海,等,铜山烟区生态因素和烟叶质量特点[J].生态学报,2005,25(7):1748-1753.
[58]程昌新,卢秀萍,许自成,等,基因型和生态因素对烟草香气物质含量的影响[J].中国农学通报,2005,21(11):137-139,182.
[59]许自成,张婷,马国华,等,不同调控措施对烤烟质体色素及其降解产物的影响[J].河南农业大学学报,2006,40(1):15-17,26.
[60]许自成,王林,王金平,等,湖南烤烟化学成分与土壤有机质含量的关系[J].生态学杂志,2006,25(10):1186-1190.
[61]许自成,王林,肖汉乾.湖南烟区烤烟锌含量与土壤有效锌的分布特点及关系分析[J].生态环境,2007,16(1):180-185.
[62]黎妍妍,丁伟,李传玉,等.贵州烟区生态条件及烤烟质量状况分析[J].安全与环境学报,2007,7(2):96-100.
[63]许自成,王林,肖汉乾.湖南烟区烤烟磷含量与土壤磷素的分布特点及关系分析[J].浙江大学学报(农业与生命科学版),2007,33(3):290-297.
[64]许自成,王林,肖汉乾,等.湖南烟区烤烟(Nicotinan tobacum L.)硼含量与土壤有效硼含量的关系[J].生态学报,2007,27(6):2309-2317.
[65]许自成,王林,关博谦,等.湖南烟区烤烟锰与土壤有效锰含量的分布特点及关系分析[J].中国烟草学报,2007,13(5):27-32.
[66]许自成,闰新甫.统计学原理在烟草科学研究中的应用[J].中国烟草,2000(5):18-19.
[67]吴清烈,蒋尚华.预测与决策分析[M].南京:东南大学出版社,2004.
[68]方萍,何延.试验设计与统计[M].浙江:浙江大学出版社,2003.
[69]史宏志,韩锦峰,刘国顺,等.烤烟碳氮代谢与烟叶香吃味关系的研究[J].中国烟草学报,1998(2):56-62.
[70]余建英,何旭宏.数据统计分析与SPSS应用[M].北京:人民邮电出版社,2003.
[71]李天福,王树会,王彪,等.云南烟叶香吃味与海拔和经纬度的关系[J].中国烟草科学,2005(3):22-24.
[72]王树声,王宝华,李雪震,等.烤烟烟叶中游离氨基酸与内在质量关系的研究[J].中国烟草科学,2002(2):4-7.
[73]王允白,王宝华.晒红烟化学成分与评吸结果间关系研究[J].中国烟草科学,1997(1):17-20.
[74]许自成,张莉,肖汉乾,等.烤烟硝酸盐、亚硝酸盐含量与若干品质指标的典型相关分析[J].郑州轻工业学院学报(自然科学版),2005,20(1):43-46.
[75]于乃福.斯比尔曼样本秩相关系数显著性检验在纺织工程的应用[J].青岛大学学报,1999,14(3):102-103.
[76]梅永进,陆英英.用秩相关系数法分析沙溪河沙县段水质变化[J].闽江学院学报,2002,23(2):112-119.
[77]何晓群,刘文卿.应用回归分析[M].北京:中国人民大学出版社,2001.
[78]高家合,秦西云,谭仲夏,等.烟叶主要化学成分对评吸质量的影响[J].山地农业生物学报,2004,23(6):497-501.
[79]于川芳,罗登山,王芳,等.卷烟“三纸一棒”对烟气特征及感官质量的影响(二)[J].中国烟草学报,2001(3):6-10.
[80]阎克玉,徐杰,李兴波,等.烤烟(40级)烟叶烟碱与烟气烟碱相关性研究[J].郑州轻工业学院学报,1998(4)19-23.
[81]许萍,宁敏.计算机辅助工艺设计的研究与应用[J].合肥工业大学学报(自然科学版),1998,21(2):54-60.
[82]李常军,宫长荣,肖鹏,等.施氮水平和烘烤条件对烤后烟叶品质和含氮组分的影响[J].中国烟草科学,2001(1):4-7.
[83]李斌,于川芳,杨述元,等.卷烟材料对烟气特征的预测模型[J].烟草科技,2005(9):3-5.
[84]毕淑峰,朱显灵,马成泽.云南烤烟化学成分与香气品质的关系研究[J].中国农学通报,2004,20(6):67-68.
[85]闫克玉,王建民,屈剑波,等.河南烤烟评吸质量与主要理化指标的相关分析[J].烟草科技,2001(10):5-9.
[86]郭家明.不同类型烟草品质性状间关系的研究[J].合肥工业大学学报(自然科学版),1997(5)121-127.
[87]胡国松,康健,赵振山,等.统计分析在烤烟营养评价和推荐施肥中的应用.Ⅱ.多元线性回归分析和通径分析[J].河南农业大学学报,1998,32(增刊):9-14.
[88]刘学敏,李杰,李大壮,等.烟草赤星病流行动态预测[J].烟草科技,2005(9):36-38,42.
[89]李燕,Jennifer Unger,龚洁,等.武汉市青少年应激性生活事件和吸烟行为的关系[J].中国 心理卫生杂志,2003,17(2):113-116.
[90]董建群,张清华,蒋知新.吸烟与帕金森病关系的病例对照研究[J].中华流行病学杂志,2003,24(7):604-607.
[91]练文柳,吴名剑,孙贤军,等.不同预处理方法对烟草近红外光谱预测模型的影响[J].烟草科技,2005(2):19-23.
[92]张妍,尚金城,于相毅.主成分聚类复合模型在水环境管理中的应用[J].水科学进展,2005,16(4):592-595.
[93]许明辉.烟草数量性状遗传距离与杂种优势关系的研究[J].遗传,1999,21(5):47-50.
[94]钱时祥,陈学平,郭家明.聚类分析在烟草种植区划上的应用[J].安徽农业大学学报,1994(1):21-25.
[95]蔡宪杰,王信民,尹启生.烤烟外观质量指标量化分析初探[J].烟草科技,2004(6):37-39,42.
[96]陈学平,张良,郭家明,等.多个化学成分指标烟叶样品的聚类分析研究[J].中国烟草学报,2002(4):21-26
[97]周冀衡,杨虹琦,林桂华,等.不同烤烟产区烟叶中主要挥发性香气物质的研究[J].湖南农业大学学报(自然科学版),2004,30(1):20-23.
[98]申荣艳,刘学敏,胡钟胜,等.田间烟草赤星病菌繁殖代数与其对杀菌剂敏感性的关系[J].烟草科技,2005(2):38-40.
[99]许自成,肖汉乾,赵献章,等.植烟土壤养分丰缺状况评价的统计方法[J].土壤通报,2004,35(5):558-561.
[100]冯建跃,冯连梅.卷烟内在质量的气相色谱-数学聚类法研究[J].分析测试学报,2001(3):19-23.
[101]苏勇,刘强,彭黎明,等.主成分分析和聚类分析在配方模块中的应用[J].烟草科技,2005(6):3-5.
[102]王志德,牟建民,王卫锋,等.部分烟草核心种质过氧化物同工酶标记分析[J].中国烟草科学,2003(2):9-11.
[103]高新波,谢维信.模糊聚类理论发展及应用的研究进展[J].科学通报,1999,44(21):2241-2251.
[104]刘维涓,张虹娟,王乐.采用模糊聚类法辅助鉴别烟用香精的品质[J].烟草科技,2003(1):24-26
[105]C.T.Zahn.GrapH-theoretic methods for detecting and describing gestalt clusters[J].IEEE tran s.Computer,1971(20):68-86.
[106]Wu,R.leahy.An optimal grapH theoretic approach to data clustering:theory and its applica tion to image segmentation[J].IEEE trans.PAMI,1993,15(11):1101-1113.
[107]邓聚龙.灰色系统(社会与经济)[M].北京:国防工业出版社,1985.
[108]程建权,黄经南.一种基于时序数据的动态聚类分析方法[J].武汉测绘科技大学学报,1998,23(3):194-198.
[109]凌卫新,凌玲.关于图像色彩压缩的一种新聚类算法[J].计算机工程,1996,22(4):8-10.
[110]毕淑峰,朱显灵,马成泽.判别分析在烤烟品质鉴定中的应用[J].中国农学通报,2005,21(1):79-80.
[111]Saaty T L,Bennett J P.A theory of analytical hierarchies applied to political candidacy[J].Behavioral Science,1977(22):237-245.
[112]于英川.现代决策理论与实践[M].北京:科学出版社,2005.
[113]李祚泳,丁晶,彭荔红.环境质量评价原理与方法[M].北京:化学工业出版社,2004.
[114]尤长虹,张楚安,彭传新.制丝质量评价方法的设计与应用[J].烟草科技,2001(7):21-24.
[115]焦立新,谷立中.层次-关联评判法在种植制度综合评判中的应用[J].安徽农业技术师范学院院报,1994,8(1):74-78.
[116]焦立新,周应兵,林国平,等.烤烟品种综合性状评判的数学模型研究[J].农业工程学报,1998(3):215-220.
[117]徐宏图,李力红.应用层次分析法和模糊综合评判研究保健品消费心理[J].心理学报,2005,37(6):826-831.
[118]周应兵,孙学永,阮龙,等.烤烟品种的层次-模糊综合评判[J].安徽农业科学,1998(3):271-273.
[119]高洁,盛昭瀚.可拓层次分析法研究[J].系统工程,2002,20(5):6-11.
[120]刘宏宇,欧小松.双向层次分析法-原理及应用[J].系统工程理论方法应用,1994,3(3):33-38.
[121]Zadeh L A.Fuzzy Sets[J].Inf.Cont,1965(8):338-358.
[122]杨崇瑞.模糊数学及其应用[M].北京:农业出版社,1994.
[123]朱双印,刘石.模糊控制在烘丝含水率控制中的应用[J].烟草科技,2001(11):11-12.
[124]王季方,崔光照.模糊逻辑在滚筒式烘丝机筒体转速控制中的应用[J].烟草科技,2001(11):13-14.
[125]庞全,杨翠容.烟叶初烤计算机控制系统[J].农业工程学报,1997,13(4):174-178.
[126]于微波,刘俊萍,何伟明.烟叶发酵温度的模糊控制[J].吉林工学院学报,1998(1):34-38.
[127]胡丹,李敏,武小红.模糊数学在卷烟直径测量中的应用[J].计算机应用与软件,2002(7):38-40.
[128]王道勇.模糊综合评判的失效与处理[J].工科数学,1994,10(1):45-49.
[129]贺仲雄.模糊数学及其应用[M].天津:天津科学技术出版社,1983.
[130]韩力群,何为,段振刚,等.烤烟烟叶自动分级的智能技术[J].农业工程学报,2002,18(6):173-175.
[131]江建刚.模糊综合评判技术在卷烟评吸过程中的应用[J].安庆师范学院学报(自然科学版), 2002,8(1):38-40.
[132]高同启,张卫旗.卷烟质量多级模糊综合评判模型研究[J].合肥工业大学学报(自然科学版),1998,21(6):57-62.
[133]薛超群,刘迎昌.模糊概率值法在烤烟品种(系)综合评价中的应用探讨[J].烟草科技,2000(4):37-38.
[134]王艳.模糊概率值法在晒烟品种(系)综合评价中的应用[J].延边大学农学学报,2000,24(1):20-24.
[135]阎伍玫.环境质量的模糊综合评判-灰色关联分析[J].农村环境生态学报,1994,10(3):30-33.
[136]吴春,韩晓红,罗正友,等.运用灰色模糊多维综合评估烤烟新品种[J].贵州农业科学,2004,32(6):31-32.
[137]汪培庄.模糊集合论及其应用[M].上海:上海科技出版社,1983.
[138]罗怀良.川西南与玉溪烤烟区气候条件比较研究[J].四川师范大学学报(自然科学版),2001,24(2):197-199.
[139]曾黄麟.粗集理论及其应用[J].四川轻化工学院院报,1996,9(4):20-26.
[140]秦安文.模糊ARTMAP神经网络在一维信息聚类分析中的应用[J].山东工业大学学报,1999,29(5):400-496
[141]Deng Julong.Control problems of grey systems[J].Systems and Control Letters,1982,1(5):288-294.
[142]Deng Julong.Introduction to grey systems theory[J].The Journal of Grey System,1989,1(1):1-24.
[143]Deng Julong.Essential models for grey forecasting control[J].The Journal of Grey System,1990,2(1):1-10.
[144]邓聚龙.灰色控制系统[M].武汉:华中理工大学出版社,1985.
[145]邓聚龙.灰色预测与决策[M].武汉:华中理工大学出版社,1988.
[146]邓聚龙.灰色系统理论教程[M].武汉:华中理工大学出版社,1990.
[147]张歧山,高相炳,姜元章,等.应用灰色方法的误区[J].大庆石油学院院报,1995,19(3):108-110.
[148]殷凤生,林国平,唐经祥,等.用灰色关联度分析烤烟主要农艺性状间的相关性及其对经济指标的影响[J].烟草科技,2001(1):38-40.
[149]胡建军,马明,李耀光,等.烟叶主要化学指标与其感官质量的灰色关联分析[J].烟草科技,2001(1):3-7.
[150]巫厚长,魏重生,王方晓,等.各种天敌对烟蚜种群数量影响效果的灰色关联度分析[J].安徽农业大学学报,2002,29(3):224-229.
[151]董中强,张永民,段雪梅,等.河南烟区与云南优质烟区气候生态系统的灰色关联分析[J]. 河南气象,2000(2):21-22.
[152]雷铁栓,郭瑞林,王新海,等.灰色系统理论在农业上的应用[M].郑州:河南科学技术出版社,1996.
[153]谢小丹,陈顺辉,巫升鑫,等.烤烟新引品种的模糊综合评判和灰色关联度分析[J].福建农林大学学报(自然科学版),2002,32(2):160-163.
[154]蒋宗礼.人工神经网络导论[M].北京:高等教育出版社,2001.
[155]吴建生,周优军,金龙.神经网络及其研究进展[J].广西师范学院学报(自然科学版),2005,21(1):92-97.
[156]陈达,王芳,邵学广,等.近红外光谱与烟草样品总糖含量的非线性模型研究[J].光谱学与光谱分析,2004,124(16):672-674.
[157]任广伟,王凤龙,高汉杰,等.BP神经网络在烟草蚜传病毒病预测中的应用[J].中国烟草学报,2004,10(4):24-26.
[158]蔡健荣,方妇明,张世庆,等.利用计算机视觉技术的烟叶质量分选系统研究[J].农业工程学报,2000,16(3):118-122.
[159]骆德汉,郎文辉.一种神经网络专家系统的故障诊断方法[J].烟草科技,1999(5):25-27.
[160]丁香乾,曹均阔,贺英,等.Kohonen网络与BP网络的集成应用研究[J].青岛海洋大学学报,2003,33(4):615-620.
[161]贺英,冯天瑾,曹均阔.Kohonen网络在烟叶动态分类中的应用[J].中国海洋大学学报,2004,34(1):121-127.
[162]Okada Hiroyuki.Initializing multilayer neural network with fuzzy logic[J].Proceedings of I NCNN'92,New York:IEEE,1992:1239-1244.
[163]林丽莉,冯天瑾,周文晖,等.基于神经-模糊方法的单料烟感官质量评价专家系统[J].青岛海洋大学学报,2001,31(6):931-936.
[164]曹均阏,叶水生,丁香乾.模糊Kohonen网络在烟叶分类中的应用[J].计算机工程,2005,31(2):222-224.
[165]Cai yaling,Hon Keung Kwan.A fuzzy neural network with fuzzy classification[J].Procee dings of ASMESCI'94,Wuhan:Press of Huazhong University of Science and Technology,1994:894-899.
[166]高大启,吴守一.基于并联神经网络的烤烟内在质量分析方法[J].分析化学研究报告,1998,26(10):1174-1177.
[167]杨小勇,彭黔荣,苏红雪,等.单输出径向基神经网络在烟叶品质预测中的应用[J].贵州工业大学学报(自然科学版),2005,34(3):24-27.
[168]彭黔荣,蔡元青,王东山,等.根据化学指标识别烟叶品质的BP神经网络模型[J].中国烟草学报,2005,11(5):19-25.
[169]余道衡.人工神经网络[J].世界科技研究与进展,1996(2):47-49.
[170]殷勇,吴守一.遗传RBF神经网络在卷烟香气质量评定中的应用[J].农业工程学报,2001,17(6):147-149.
[171]彭黔荣,石炎福,刘钟祥,等.一种改进的混合遗传算法人工神经网络及其应用[J].化学反应工程与工艺,2005,21(1):70-74.
[172]何琴,高建华,刘伟.广义回归神经网络在烤烟内在质量分析中的应用[J].安徽农业大学学报,2005,32(3):406-410.
[173]曾黄麟,曾谦.基于粗集理论的神经网络[J].四川轻化工学院院报,2000,13(1):1-5.
[174]赵卫东,陈国华.粗集与神经网络的集成技术研究[J].系统工程与电子技术,2002,24(10):103-107.
[175]Pawlak Z,Busse J G.Rough sets[J].Communication on the ACM,1995,38(11):89-95.
[176]祝峰,王加佳,严向奎.粗集理论的现状与前景[J].新疆大学学报(自然科学版),2000,17(4):1-4.
[177]赵克勤.对分析及其初步应用[M].杭州:浙江科学技术出版社,2000.
[178]吕丹,吴孟达.集对分析与粗糙集的结合[J].计算机工程与应用,2005(33):176-178.
[179]倪克平,范铁桢,胡建军.基于同异反态势排序的河南烤烟化学成分指标评价[J].烟草科技,2004(3):28-30,34.
[180]殷勇.烟草成分对其品质影响程度的粗糙集判别方法[J].农业机械学报,2004,35(4):124-127
[181]Cai Wei.Method of matter elements analysis[J].BUSEFAL,1984(20):51-56.
[182]张永红,吴鸣,胡建军,等.国内外香料烟香味物质与品质比较[J].烟草科技,2004(1):3-7.
[183]李祚泳.投影寻踪的理论及应用进展[J].大自然探索,1998,17(63):47-50.
[184]李世玲.基于投影寻踪和遗传算法的一种非线性系统建模方法[J].系统工程理论与实践,2005(4):22-28.
[185]邓新民,李祚泳.投影寻踪回归技术在环境污染预测中的应用[J].中国环境科学,1997,17(4):353-356.
[186]王顺久,张欣莉,侯玉,等.投影寻踪聚类分析在环境质量综合评价中的应用[J].重庆环境科学,2002,24(3):74-76.
[187]封志明,郑海霞,刘宝勤.基于遗传投影寻踪模型的农业水资源利用效率综合评价[J].农业工程学报,2005,21(3):66-70.
[188]Roberts D.L.,Natural tobacco flavor.Ree.Adv.of Tob.Sci.,1988,14:49-81.
[189]刘思峰,史开泉,等.灰色系统学术论文集[M].郑州:河南大学出版社,1993.
[190]刘思峰,郭天榜,等.灰色系统理论及其应用[M].郑州:河南大学出版社,1991.
[191]刘思峰,郭天榜,党耀国,等.灰色系统理论及其应用[M].北京:科学出版社,1999.
[192]胡国松,郑伟,王震东,等.烤烟营养原理[M].北京:科学出版社,2000.
[193]陈瑞泰.中国烟草栽培学[M].上海:上海科技出版社,1987.
[194]王东胜,刘贯山,李章海.烟草栽培学[M].合肥:中国科学技术大学出版社,2002.
[195]刘国顺.烟草栽培学[M].北京:中国农业出版社,2003.
[196]韩锦峰.烟草栽培生理[M].北京:中国农业出版社,2003.
[197]肖协忠.烟草化学[M].北京:中国农业科技出版社,1997.
[198]王瑞新.烟草化学[M].北京:中国农业出版社,2003.
[199]赵凤芹,张淑珍,张和远.模糊评价食品的感官质量方法[J].沈阳农业大学学报,1998,29(4):343-345.
[200]刘华,陈维平,李元元.绿色制造风险的群层次模糊综合评判[J].中国机械工程,2005,16(9):787-790.
[201]杨毅,陈庆华多因素层次模糊综合评判决策模型及其应用[J].中南工业大学学报,1995,26(4):443-446.
[202]马力,陈学中,原学梅.高技术产业投资风险的多因素层次模糊综合评判[J].数量经济技术经济研究,2001,(7):58-61.
[203]许树柏.实用决策方法-层次分析法原理[M].天津:天津大学出版社,1988.
[204]郭爱民,郭耀邦.层次分析法确定食品质量指标权重[J].食品科学,1994(7):6-10.
[205]钱时祥,陈学平,郭家明.聚类分析在烟草种植区划上的应用[J].安徽农业大学学报,1994(1):21-25.
[206]王海林,李建军,吴拥军,等.贵州省烤烟(40级)的聚类分析研究[J].中州大学学报,2005,22(1):124-125.
[207]武怡,曾晓鹰,番绍军,等.卷烟叶组配方分组研究[J].烟草科技,2005(11):3-6.
[208]于录,阮晓明,卢在雨,等.叶组配方分组加工模块设计[J].烟草科技,2006(7):11-13.
[209]刘建福,尹宾,陈刚,等.卷烟的分组加工[J].烟草科技,2006(11):5-9.
[210]殷凤生,林国平,唐经祥,等.用灰色关联度分析烤烟主要农艺性状间的相关性及其对经济指标的影响[J].烟草科技,2001(1):38-40.
[211]晏孝皋.新的食品感官质量评价函数及其数据处理程序[J].食品与发酵工业,1999,(1):65-68.
[212]唐其环.灰色聚类灰类白化函数确定方法的探讨[J].四川兵工学报,1996,17(4):4-6.
[213]党耀国,刘思峰,刘斌,等.聚类系数无显著性差异下的灰色综合聚类方法研究[J].中国管理科学,2005,13(4):69-73.
[214]郭志刚.社会统计分析方法-SPSS软件应用[M].北京:中国人民大学出版社,1999.
[215]王旭升,葛龙进.广义关联分析-兼论灰色关联的本质[J].系统工程理论与实践,1999(12):90-95.
[216]庄恒扬.灰色系统关联分析统计检验方法[J].农业系统科学与综合研究,1996,12(3):168-171
[217]唐启义,冯明光.实用统计分析及其DPS数据处理系统[M].北京:科学出版社,2006.
[218]阎克玉,李兴波,屈剑波,等.河南烤烟(40级)水溶性总糖和还原糖含量及其相关性研究[J].郑州轻工业学院学报,1997,12(4):42-47.
[219]杜咏梅,郭承芳,张怀宝,等.水溶性糖、烟碱、总氮含量与烤烟吃昧品质的关系研究[J].中国烟草科学,2000(1):7-10.
[220]阎克玉,王海燕,李兴波,等.烤烟国家标准(40级)河南烟叶叶厚、叶质重及叶片密度研究[J].郑州轻工业学院学报,1999,14(2):45-50.
[221]Hartana I.Estimation of leaf area of Besuki tobacco by means of length and breadth measu rements.TA,1975(2):214.
[222]王瑞新,韩富根,杨素勤.烟草化学品质分析方法[M].郑州:河南科学技术出版社,1990.
[223]曹志洪,李仲林,周秀如,等.烤烟干物质的累积及土壤环境对烟碱含量的影响[J].烟草科技,1989(5):29-33.
[224]胡国松,傅建政,刘永中,等.烤烟中全氮烟碱和还原糖之间关系的统计学研究[J].黑龙江烟草,2000(1):9-11.
[225]汪邓名,范思锋.钾素对烤烟成熟生理变化及成熟度影响的研究[J].植物营养与肥料学报1999,5(3):244-248.
[226]范坚强,宋纪真,陈万年,等.醇化过程中烤烟片烟化学成分的变化[J].烟草科技,2003(8):19-22.
[227]郭俊成,程晓蕾,肖厚荣,等.皖南烤烟陈化研究[J].中国烟草科学,1996(2):16-17.
[228]朱大恒,韩锦峰,张爱萍,等.自然醇化与人工发酵对烤烟化学成分变化的影响比较研究[J].烟草科技,1999(1):3-5.
[229]胡有持,杨述元,李炎强,等.陈化过程中河南复烤片烟B2F和C3F理化指标的变化[J].烟草科技,2004(5):11-15.
[230]刘思峰,党耀国,方志耕.灰色系统理论及其应用[M].北京:科学出版社,2004.
[231]姚晏斌,高金华.灰色模型GM(1,2)在机场旅客吞吐量预测中的应用[J].中国民航学院院报,2006,17(4):12-16.
[232]尹子民,罗丽兮.灰色模型GM(1,n)的变量选择及拟合度分析[J].系统工程理论与实践,1999(11):81-83,120.
[233]蔡家明.货运量多维灰色模型的预测[J].上海工程技术大学学报,2005,19(1):38-41.
[234]牛东晓,张彤彤,陈立荣,等.基于关联分析的多因素电力负荷预测灰色模型群研究[J].华北电力大学学报,2006,33(3):90-92.
[235]杨有清,袁涌铨,孙杰.青岛市生活垃圾量的关联度分析与灰色模型预测[J].中南民族大学学报(自然科学版),2005,24(3):5-8.
[236]习勤,陶国良.铁路货运量多维灰色模型研究[J].华东交通大学学报,1996,13(增刊):16-20,25.
[237]王耘,穆勇,刘庆红.基于灰关联分析的模糊聚类最优划分判定模型[J].山东大学学报(工学版),20 06,36(2):86-89.
[238]夏景明,肖冬荣,卓为.灰色神经网络预测模型的应用[J].统计与决策,2004(6):24-25.
[239]章敬东,刘小辉,邓飞其,等.灰色神经网络组合算法在复杂非线性预测中的应用[J].计算机工程与应用,2003(12):56-58.
[240]朱瑞祥,黄玉祥,杨晓辉.用灰色神经网络组合模型预测农机总动力发展[J].农业工程学报,2006,22(2):107-110.
[241]张宏伟,连鹏,闫晓强.最优化权值组合法用于大气质量中长期预测的研究[J].天津工业大学学报,2005,24(3):54-57,61.
[242]ZHU Hong--bing,WU Lian.Application of gray correlation analysis and artificial neural ne twork in rock mass blasting[J].JOURNAL OF COAL SCIENCE & ENGINEERING,2005,11(1):44-47.
[243]苏博,刘鲁,杨方廷.GM(1,N)灰色系统与BP神经网络方法的粮食产量预测比较研究[J].中国农业大学学报,2006,11(4):99-10.
[244]陈仅.多变量灰色数列预测模型在非典研究中的应用[J].成都纺织高等专科学校学报,2007,24(3):21-25,29.
[245]万星,周建中.改进灰色神经网络模型在电量预测中的应用[J].水力发电,2007,33(6):69-72,88.
[246]白根元,赵奇,孔芬英.灰色补偿RBF神经网络[J].河北建筑科技学院学报,2005,22(2):103-105.
[247]卢厚清,张永利,余勤,等.基于进化神经网络的灰色预测模型[J].解放军理工大学学报(自然科学版),2006,7(5):437-441.
[248]石为人,冯治恒.基于灰色理论与BP算法的宏观经济预测模型研究[J].计算机与数字工程,2007,35(1):8-10.
[249]Deng J L.Introduction to grey system theory[J].The Journal of Grey System(UK),1989,1(1):1-24.
[250]张文丽,路金喜,宋双虎,等.基于灰色广义回归神经网络的工业废水排放量预测[J].水资源与水工程学报,2007,18(1):64-67.
[251]刘芳,刘民,吴澄.基于灰色关联分析的分层模糊神经网络[J].系统仿真学报,2006,18(4):886-889.
[252]米鸿燕,蒋兴华.基于灰色BP神经网络的沉降预测模型应用研究[J].昆明理工大学学报(理工版),2007,32(2):65-68,72.
[253]刘豹,胡代平.神经网络在预测中的一些应用研究[J].系统工程学报,1999,14(4):338-344.
[254]杨再波,叶冲,韩伟,等.基于BP神经网络在卷烟焦油预测中的应用[J].黔南民族师范学院学报,2006,(6):5-8.
[255]张志刚,王二彬,苏东赢.卷烟化学成分与焦油的线性回归分析[J].烟草科技,2003(11):32-33.
[256]徐雅静,汪远征,王建民.卷烟焦油含量预测的数学模型[J].郑州轻工业学院学报(自然科学版),20 05,20(3):35-38.
[257]彭传新,尤长虹,李兵役,等.影响卷烟焦油量的因素探讨[J].烟草科技,2000(11):5-8.
[258]王燕.应用时间序列分析[M].北京:中国人民大学出版社,2005.
[259]George E.P.Box,Gwilym M.Jenkins,Gregory C.Reinsel,顾岚译.时间序列分析预测与控制[M].北京:中国统计出版社,1997.
[260]徐国祥.统计预测与决策[M].上海:上海财经大学,2000.
[261]胡永红,吴志峰,李定强,等.基于ARIMA模型的区域水生态足迹时间序列分析[J].生态环境,2006,15(1):94-98.
[262]朱丹.非典型的时间序列预测法的选择与应用[J].广东职业技术师范学院院报,2000(1):47-52.
[263]杨住钦,顾岚.时间序列分析与动态数据建模[M].北京:北京工业学院出版社,1986.
[264]崔敬巍,谢里阳.自相关过程的统计控制方法研究[J].机械制造,2006,44(505):66-68.
[265]Jiang Wei,Tsui K L.A New SPC Monitoring Method:The ARMA Chart[J].Technometri cs,2000,42(4):399-410.
[266]鲍士旦.土壤农化分析[M].北京:中国农业出版社,2000.
[267]GB/T 16447-2004/ISO 3402:1999,烟草及烟草制品 调节和测试的大气环境[S].
[268]GB/T 16450-2004,分析用吸烟机定义和标准条件[S].
[269]GB/T 19069-2004,卷烟 用分析用吸烟机测定和焦油[S].
[270]YC/T 157-2001,卷烟 总粒相物中水分的测定 气相色谱法[S].
[271]张圣勤.MATLAB7.0应用教程[M].北京:机械工业出版社,2006.
[272]Duane Hanselman,Bruce Littlefield.精通MATLAB7[M].北京:清华大学出版社,2006.
[273]王国锋,王子良,王太勇,等.Matlab在时间序列分析中的应用[J].应用科技,2003,30(5):36-38.
[274]曹鲜花,吴美平,胡小平.Matlab在光纤陀螺随机漂移建模中的应用[J].航天控制,2007,25(1):18-20,25.
[275]张善文,雷英杰,冯有前.MATLAB在时间序列分析中的应用[M].西安:西安电子科技大学出版社,2007.
[276]韩路跃,杜行检.基于MATLAB的时间序列建模与预测[J].计算机仿真,2005,22(4):105-107,182.
[277]吕安林,张晶,赵树民.灰色模型的精度及误差检验研究[J].华中理工大学学报,1998,26(1):41-42,45.
[278]朱宝璋.关于灰色建模的模型精度问题的研究[J].系统工程,1991,9(5):13-19.
[279]熊岗,陈章潮.灰色预测模型的缺陷及改进方法[J].系统工程,1992,10(6):32-36.
[280]吕海涛,赵林明。应用灰色模型(G M)时注意的一些问题[J].华北水利水电学院学报,2000,21(1):76-78.
[281]史玉峰,宁津生.指数平滑法改进灰色模型及其在形变数据分析中的应用[J].煤炭学报,2005,30 (2):200-209.
[282]秦肖生,曾光明.非线性灰色模型在污染物总量预测中的应用[J].江苏环境科技,2000,13(4):18-21.
[283]宋中民.灰色GM(1,1)模型参数的优化方法[J].烟台大学学报(自然科学与工程版),2001,14(3):161-163.
[284]陈涛捷.灰色预测模型的一种拓广[J].系统工程,1990,8(4):50-52.
[285]McCulloch W S,Pitters W.A Logical calculus of the ideas immanent in nerves activity.Bu lletin of MathematicalBiopHysicus,1943,10(5):115-133.
[286]Hebb D O.The organization of behavior.New York:Wiley,1949.
[287]Rosenblatt F.The perception:A Probabilistic model for information storage and organization in the brain.Psychological Review,1958(65):386-408.
[288]Widrow B,Hoff M E.Adaptive Switching Circuits.IRE WESCON convention record,part4.pp.96-104,1960.
[289]Hopfield J.Neural networks and physical systems with emergent collective computer abilitie s.Proc Natl.Acad.Sci.USA,1982,79(6):2554-2558.
[290]Hopfield J.Computing with neural circuits:A Model,Science.1986,233:625-633.
[291]McClelland J.L.,Rumelhart D.E.Exploration in parallel distributed processing,A Handbook of Models,Programs,and Exercises,Cambridge:MIT Press,1986.
[292]Chua L O,Yand L.Cellular Neural Networks:Application,IEEE Transactions on Circuits a nd Systems,1988,28(35):1257-1272.
[293]Chua L O,Yand L.Cellular Neural Networks:Theory.IEEE Transactions on Circuits and Systems,1988,28(35):1237-1290.
[294]Kosko B.Adaptive Bidirectional Associative Memories.Applied Optical,1987,26(23):4667-4680.
[295]Kosko B.Bidirectional Associative Memories.IEEE Transactions On Man,System and Cyb emetics.1988,26(18):49-59.
[296]Jenkins B K,A R Tanguay.Jr Optical Architectures for Neural Network Implementation,H andbook of Neural Computing and Neural Networks.Boston:MIT Press,1995:673-677.
[297]McAulay A D,Wang J,Ma C.Optical Hetero-associative Memory Using Spatial Light Rebroadcasters.Applied Optical,1990,29(14):2067-2073.
[298]Narendra K,Parthassarthy K.Identification and Control of Dynamical Systems Using Neural Networks.IEEE Transactions on Neural Networks,March 1990,1(1):4-27.
[299]Miller W T.Real-time Application of Neural Networks for Sensor-based Control of Robots,With Vision.IEEE,Transactions on Man,System and Cybernetics,1989,27(19):825-831.
[300]Bulsari A.Some Analytical Solutions to the General Approximation Problem for Feedback Neural Networks.Neural Networks,1993,28(6):991-996.
[301]Aibara K.Chaotic Neural Networks.PHysical letter A,1991,158(8):373-376.
[302]Inoue M,Nagayoshi A.A Chaos Neural-computer.PHysical Letter A,1991,158(8):373-376.
[303]Inoue M,Nakamoto K.Epilepsy in a Chaos Neural-computer model,Chaos in Biology and Medicine,SPIE 1993,236:77-84.
[304]Satoru Isaka.On neural approximation of fuzzy system.In:Proceedings of INCNN'92,New York:IEEE,1992:1263-1268.
[305]Jokinen Petri A.On the relations between radial basis function networks and fuzzy system [C].In:Proceedings of INCNN'92,New York:IEEE,1992,1220-1225.
[306]Okada Hiroyuki.Initializing multilayer neural network with fuzzy logic.In:Proceedings of I NCNN'92,New York:IEEE,1992,1239-1244.
[307]Lapedes A,Farber.Nonlinear signal processing using neural networks:prediction and system modelling[R].Technical Report LA-UR-87-2662,Los Alamos National Laboratory.Los Ala mos.NM,1987.
[308]Werbos P J.Generalization of backpropagation with application to a recurrent gas market m odel[J].NeuralNetworks,1988,(1):339-356.
[309]Varfis A,Versino C.Univariate economic time series forecasting by connectionist methods [C].IEEE ICNN-90.1990,342-345.
[310]Weigend A B et al.Predicting the future:a connectionist approach[J].Intl,J.Neur.Sys.1990;1:193-209.
[311]Matsuba I.Application of neural networks equential associator to long-term stock price pred iction[C].IJCNN'91,Singapore,1991,1196-1202.
[312]Chakraborty K et al.Forecasting the behavior of multivariate time series using neural networ ks[J].Neural Networks,1992,5:961-970.
[313]Bates J H,Granger C W J.The combination of forecasts[J].Operations Research Quarterly,1969,20:319-325.
[314]Granger C W J,Terasvirta T.Experiments in modeling nonlinear relationshipsbetween time series[M].in M.Casdagliand S.Eubank(Eds.),Nonlinear Modeling and Forecasting,Addison-Wesley,Redwood City,CA.1992.
[315]Lisoba P G J.Neural network-current applications[M].Chapman&Hall,London.1992.
[316]周志华,曹存根.神经网络及其应用[M].北京:清华大学出版社,2004.
[317]A.H.加卢什金.阎平凡(译).神经网络理论[M].北京:清华大学出版社,2002.
[318]冯定.神经网络专家系统[M].北京:科学出版社,2006.
[319]朱大奇,史慧.人工神经网络原理及应用[M].北京:科学出版社,2006.
[320]韩力群.人工神经网络教程[M].北京:北京邮电大学出版社,2006.
[321]飞思科技产品研发中心.神经网络理论与MATLAB7实现[M].北京:电子工业出版社,2006.
[322]董长虹.MATLAB神经网络与应用[M].北京:国防工业出版社,2005.
[323]黄良文,曾五一.统计学原理[M].北京:中国统计出版社,1999.
[324]孙振球,徐勇勇.医学统计学[M].北京:人民卫生出版社,2004.
[325]闫克玉,赵献章.烟叶分级[M].北京:中国农业出版社,2003.