共查询到19条相似文献,搜索用时 281 毫秒
1.
2.
3.
运用人工神经网络的典型模型——“反向传播”模型,建立了由亚麻纤维的品质预报其成纱质量的连接机制模型。最大拟合相对误差不超过3.2%,最大预测相对误差不超过0.23%。实验结果表明,该方法性能良好,在各类纺织品质量分析预测方面有广阔的应用前景。 相似文献
4.
采用布氏黏度计对桑枝多糖的黏度进行测定,分别考察温度、剪切速率以及pH值对桑枝多糖黏度的影响,结果表明:桑枝多糖溶液为假塑性流体,随着温度的升高其黏度逐渐降低且两者的关系符合阿累尼乌斯模型,温度和浓度对其黏度的综合影响可用数学模型η=-5.924 5exp 2.48/RT-0.123 8C+3.421×10-4C2)进行预测,适用范围温度20~80℃,浓度1%~8%;剪切速率对其黏度的影响可用幂律模型η=Mγn进行拟合,黏度随剪切速率的增加而降低,酸和碱均使桑枝多糖溶液黏度下降,中性条件下黏度值最高,说明桑枝多糖是中性多糖. 相似文献
5.
6.
7.
8.
目的:构建卷烟制丝过程成品烟丝质量模拟预测模型。方法:使用平均影响值法(the Mean Impact Value, MIV)对制丝加工过程工艺参数进行筛选,然后通过反向传播(Back-Propagation,BP)神经系统构建起制丝关键工艺参数和成品烟丝质量的模拟模型。结果:通过模拟数据与实测数据比较,填充值的模拟预测平均相对误差为3.16%;整丝率的模拟预测平均相对误差为0.67%;碎丝率的模拟预测平均相对误差为5.33%。结论:该模型预测值与实测值之间相对误差较小,精确性高,该模型适用于卷烟制丝生产过程工艺参数仿真优化。 相似文献
9.
为了简便、快速、准确地测定米糠油中的谷维素含量,以LS/T 6121.2—2017的高效液相色谱法为测定米糠油中谷维素含量的参比方法,采用近红外光谱分析技术结合偏最小二乘法建立了米糠油中谷维素含量的定量分析模型。结果表明:所建定量分析模型的决定系数为99.81%,预测标准差为0.02849%,交叉验证标准差为0.03113%;利用99个验证集样品对定量分析模型进行外部独立验证,预测决定系数为99.81%,预测标准差为0.03090%,用该定量分析模型检测样品绝对误差在-0.081%~0.057%之间,相对误差在-11.86%~9.84%之间。所建立的定量分析模型预测效果较好,准确度较高,可用于米糠油中谷维素含量的测定。 相似文献
10.
《食品科技》2017,(4)
婴幼儿乳粉的质量和安全日益受到人们的关注,研究了利用近红外漫反射光谱进行乳粉中各类营养物质含量的快速无损检测的适应性。以156个乳粉样本作为样本集,分别采用偏最小二乘回归(PLSR)和KNN保形映射(KNN-KSR)算法建立含量范围分别为14.5%~23.1%(蛋白质、脂肪)、(5.6~9.2)mg/g(钙)、(1.29~10.2)mg/100 g(锌、V_(B2))、(0.34~1.47)mg/g(Vc)的营养物质近红外定量分析模型。PLSR与KNN-KSR预测各类营养物质含量的平均相对误差分别小于5%与3%,2种方法对Vc的预测误差最大。不同光谱预处理方法所得结果显示一阶导预处理结果更为理想,可使每种营养物质的预测平均相对误差降低0.1%以上。将样品按照Vc浓度的量级划分为2个区间分别建立模型,平均相对误差较整个浓度区间建模结果减小1%以上。利用PLSR与KNN-KSR方法基于近红外光谱信息可快速预测乳粉中不同浓度量级的营养成分,KNN-KSR的预测效果更佳。为获得准确的预测结果,建议采用同量级浓度样品建立乳粉营养成分的近红外定量模型并分浓度区间进行应用。 相似文献
11.
12.
13.
针对郫县豆瓣有机酸最佳提取工艺问题,提出了一种高精度遗传神经网络优化方法,解决回归分析方法拟合度精度和准确性不高的现象。以郫县豆瓣有机酸提取量为性能指标,用中心组合试验数据训练遗传神经网络,当神经网络训练误差达到1.1862×10^-11时,神经网络算法输出数据与试验数据几乎完全拟合,平均相对误差为0%,而回归模型为0.822%,对比分析得出遗传神经网络算法的拟合精度和拟合优度均高于回归模型。用训练好的遗传神经网络算法对郫县豆瓣有机酸提取工艺条件进行优化,得到最佳提取工艺条件为:乙醇体积分数68.50%,料液比1∶20.44(g/mL),超声时间35.28min。此时有机酸提取量达到最大值15.19mg/g。该方法可为郫县豆瓣有机酸提取工艺提供试验参考,为制定更加完善的产品质量标准提供了数据支撑。 相似文献
14.
为探究玉米赤霉烯酮和黄曲霉毒素B_1的无损快速定量测定方法,用电子鼻对7级不同霉变程度玉米样品进行检测,并用理化分析方法分别测定霉变玉米中的玉米赤霉烯酮与黄曲霉毒素B_1含量;在提取电子鼻响应信号的积分值作为特征参量的前提下,采用BP神经网络建立不同霉变程度下玉米样品中的玉米赤霉烯酮与黄曲霉毒素B_1含量的预测模型。同时,为了获得较为可靠的BP神经网络预测模型,在神经网络结构不变的条件下,对比分析了不同训练集、测试集构建的预测模型。结果发现在各预测模型的70组测试样本中,相对误差控制在5%以内的样本数量都在60个以上,最大相对误差控制在15%以内,从而证明了BP神经网络预测模型的有效性、可靠性。该研究为实施玉米霉变毒素的快速无损检测提供了一种途径。 相似文献
15.
针对目前大部分色纺企业仍然依靠有经验的配色人员进行人工配色,存在配色效率低、配色精度差等问题,提出运用反向传播(BP)神经网络的方法对色纺纱的黑白纤维混合配色进行预测,并与使用Datacolor MATCH系统模拟染料配色方法和基于颜色混合模型中的Kubelda-Munk双常数理论的配色方法对黑白纤维混合配色的结果进行对比。结果表明:上述3种方法均可对麻灰纱的黑白纤维混合配色进行有效的预测,配方的相对误差基本控制在7.36%之内,且配方样品与标准样品的色差小于1;比较而言,3种黑白纤维混合配色的预测模型中,基于BP神经网络的配色方法适用性及精度最佳,配方的相对误差最高,为3.08%。 相似文献
16.
近红外光谱定量技术在方便面油份快速测定中的应用 总被引:3,自引:0,他引:3
探讨了用近红外漫反射光谱快速无损检测方便面含油率的数据处理方法,采用浸反射光谱、一阶导数光谱和二阶导数光谱,使用了四元线性向前逐步回归和BP人工神经网络的数学方法,对40个校正样本建立了的线性和非线性两种校正模型,用28个预测样要检验了校正模型的预测精度,其中线性校正模型中,采用二阶导数光谱的预测精度最好,预测平均误差为5.741%,预测误差的标准差为1.842;非线性校正模型中,采用一阶导数光谱,隐层单元数为2时,校正模型的预测精度最好,预测平均相对误差为5.149%,预测误差的标准差为1.675结果表明近红外漫反射光谱分析检测方便面的含油率能满足实际生产的要求。 相似文献
17.
VURAL GÖKMEN ÖZGE ÇETNKAYA AÇAR ARDA SERPEN DRS SÜÜT 《Journal of food process engineering》2009,32(2):248-264
An artificial neural network (ANN) was developed to model the dead-end ultrafiltration process of apple juice. Molecular weight cutoff, transmembrane pressure, gelatin–bentonite concentration and time were the input variables, while filtrate flux and filtrate volume were the output variables of the ultrafiltration process. According to error results and correlation values for two types of network (one or two hidden layer configurations), configurations with two hidden layers had comparatively better performance. The highest correlation coefficient with the minimum prediction error was calculated for two hidden layers with 6-5 nodes configuration. Trained ANN (4-6-5-2) predicted filtrate flux and filtrate volume with 2.33 and 1.38% mean relative error, respectively. The results suggest that the ANN modeling can be effectively used to optimize filtration process.
Membrane separation processes including ultrafiltration have gained importance in the food industry. Today, fruit juices are widely clarified by means of ultrafiltration process instead of tedious and laborious conventional clarification treatments. Membrane fouling which results in flux decline is the main problem associated with the ultrafiltration of fruit juices. In order to perform an efficient ultrafiltration process, optimization is required to obtain maximum filtrate volume per unit time. Artificial neural network (ANN) modeling offers great advantage on improving the performance of ultrafiltration process by accounting the effects of different variables, i.e., feed properties, transmembrane pressure and membrane pore size on filtrate volume as the main output of the filtration process. ANN modeling of ultrafiltration may be an alternative to previously proposed empirical and semiempirical models. 相似文献
PRACTICAL APPLICATION
Membrane separation processes including ultrafiltration have gained importance in the food industry. Today, fruit juices are widely clarified by means of ultrafiltration process instead of tedious and laborious conventional clarification treatments. Membrane fouling which results in flux decline is the main problem associated with the ultrafiltration of fruit juices. In order to perform an efficient ultrafiltration process, optimization is required to obtain maximum filtrate volume per unit time. Artificial neural network (ANN) modeling offers great advantage on improving the performance of ultrafiltration process by accounting the effects of different variables, i.e., feed properties, transmembrane pressure and membrane pore size on filtrate volume as the main output of the filtration process. ANN modeling of ultrafiltration may be an alternative to previously proposed empirical and semiempirical models. 相似文献
18.
A multiple regression form of the integrated Michaelis-Menten equation was developed and evaluated with simulated data having controlled error. Both multiple and traditional linear regression fit errorless data perfectly, but multiple regression is much more stable with regard to accuracy and precision of estimating the Michaelis constant and maximum rate of reaction when data contain error. Bias in determining estimators of kinetic coefficients was -4 and -3% versus -56 and -35% with 10% error in the data. Multiple regression estimates for Michaelis constant and maximum rate of reaction directly as opposed to estimating 1/Km and maximum rate of reaction/Michaelis constant by linear regression. The difference in accuracy in estimating actual Michaelis constant, for example, is 4% versus 227% error with only 10% error in the data Precision of estimation is approximately the same as precision of the data for multiple regression. For the 800 data sets examined, R2 was always greater than .92 for multiple regression, but frequently was not significant for linear regression. The actual initial concentration was provided for linear regression but calculated by multiple regression with accuracy and precision equivalent to estimation of Michaelis constant and maximum rate of reaction. The multiple regression method has statistical power to determine treatment effects on Michaelis constant and maximum rate of reaction with a practical number of animals. 相似文献
19.
建立微波消解-火焰原子吸收光谱法测定食品中痕量镍的新方法。通过微波消解条件优化,确定最佳消解条件为浓硝酸-双氧水(4:1,V/V)为消解液,1.5MPa消解15min。通过实验介质、活化剂、仪器操作条件的考察,确定最佳分析条件。在pH4.7的醋酸-醋酸钠介质中及NP-10活化下,在仪器的最佳操作条件下,镍在3.1×10-6~4.8×10-4g/L范围内,吸光度与镍质量浓度遵循比尔定律。该方法的测定波长为232.6nm,检出限为3.1×10-6g/L。所建方法用于食品中痕量镍的测定,最大相对标准偏差为4.2%,加标回收率为95.1%~106.4%,所建方法与GB/T 5009.138-2003《食品中镍的测定》进行对比,方法相对误差不高于5.8%。 相似文献