基于BP神经网络的旁热式辐射与对流粮食干燥过程模型

针对旁热式辐射与对流粮食干燥机的干燥特点,建立了一种粮食干燥机干燥过程的BP神经网络预测模型。该模型采用了3层神经网络结构(8-10-1),模型输入为粮食干燥机的8个变量,模型输出为出口粮食水分比或干燥速率。通过编写Matlab建模程序,基于实际干燥实验的样本数据训练与测试网络,实现了红外辐射与对流联合干燥的动力学模型,并给出了相应的模型数学表达式,模型预测的出口水分比与干燥速率的R2分别为0.998 9和0.998 0,均方根误差分别为0.009和0.004 1,预测结果与实际测量数据拟合较好;另外,结合实验干燥条件对模型干燥性能的预测结果进行了分析与总结,并依据同样方法建立了顺逆流粮食干燥过程的出口粮食水分比预测模型,对比了2种干燥方式的干燥性能。仿真预测表明用BP神经网络方法建模简单,具有自适应性、灵活性和自学习性等特点,相比于其他粮食干燥的经验数学模型,能综合考虑多种影响因素,可为红外辐射与对流联合干燥过程提供一种新的建模方法。     

利用近红外光谱技术快速分析全株玉米青贮营养成分

研究旨在利用近红外光谱技术(near infrared reflectance spectroscopy,NIRS)建立全株玉米青贮6种营养成分的近红外预测模型,为生产实践中合理利用全株玉米青贮饲料资源提供理论依据.选取玉米青贮样品64份作为定标集,16份作为验证集.利用NIRS结合改良偏最小二乘法(modified ...     

宁夏玉米营养成分近红外分析模型建立与应用

研究采集宁夏区内各市县(固原、海原、同心、中卫、中宁、永宁、平罗)抽取玉米样品120批,用近红外分析仪扫描定标样品集获得玉米近红外光谱图,利用偏最小二乘法建立模型,并分别经过无预处理、均值中心化、标准正态变量转换、一阶导数、标准正态变量转换结合去趋势校正(SNV+D)预处理光谱,获得水分、粗蛋白、粗脂肪、粗纤维预测模型,分别是经过MC、SNV+D、SNV+D、SNV+D光谱预处理后效果最好。预测决定系数R² _p分别为0.951、0.976、0.728、0.897,相对分析误差RPD除粗脂肪为2.62外,其他均大于3的近红外预测模型,通过预测模型验证集验证后,并对模型预测值与实测值进行U检验,结果为差异不显著(P>0.05)。该近红外预测模型对玉米中水分、粗蛋白、粗纤维具有较佳预测效果,粗脂肪的预测精度有待进一步提高。     

近红外光谱法检测饲料玉米品质的优化PLS模型

试验基于化学计量学方法,提出了饲料玉米品质检测的优化近红外光谱定量模型。首先以偏最小二乘法分别建立饲料玉米水分、蛋白质测定的全光谱定标模型,然后综合运用光谱变换、异常样本剔除和特征波长选择等技术方法优化其性能。结果表明:优化模型的建模波点数减至全光谱的5%以下,R_c²和R_p²升到0.99以上,RMSEC和RMSEP降至0.05以下,RPD提高到12以上,预测结果与参考值的差异不显著(P>0.05)。由此可见,优化模型的预测能力和运行效率得到了显著改善,可将其用于实际检测工作。     

应用MIR预测牛健康状况的研究进展

在牛遗传育种研究中,健康性状越来越受到人们关注,但大规模健康状况数据收集难度较大,故很难对其进行遗传评估。在过去近二十年中,国外研究人员探索了基于MIR的预测牛健康状况方法,其是一种高效、经济的工具。本文现从其对牛的酮病、亚临床酮病、能量平衡和其他疾病的预测几方面进行一个总结,为我国研究人员进行相关工作提供借鉴。     

Single‐voxel and multi‐voxel spectroscopy yield comparable results in the normal juvenile canine brain when using 3 Tesla magnetic resonance imaging

Conventional magnetic resonance imaging (MRI) characteristics of canine brain diseases are often nonspecific. Single‐ and multi‐voxel spectroscopy techniques allow quantification of chemical biomarkers for tissues of interest and may help to improve diagnostic specificity. However, published information is currently lacking for the in vivo performance of these two techniques in dogs. The aim of this prospective, methods comparison study was to compare the performance of single‐ and multi‐voxel spectroscopy in the brains of eight healthy, juvenile dogs using 3 Tesla MRI. Ipsilateral regions of single‐ and multi‐voxel spectroscopy were performed in symmetric regions of interest of each brain in the parietal (n = 3), thalamic (n = 2), and piriform lobes (n = 3). In vivo single‐voxel spectroscopy and multi‐voxel spectroscopy metabolite ratios from the same size and multi‐voxel spectroscopy ratios from different sized regions of interest were compared. No significant difference was seen between single‐voxel spectroscopy and multi‐voxel spectroscopy metabolite ratios for any lobe when regions of interest were similar in size and shape. Significant lobar single‐voxel spectroscopy and multi‐voxel spectroscopy differences were seen between the parietal lobe and thalamus (P = 0.047) for the choline to N‐acetyl aspartase ratios when large multi‐voxel spectroscopy regions of interest were compared to very small multi‐voxel spectroscopy regions of interest within the same lobe; and for the N‐acetyl aspartase to creatine ratios in all lobes when single‐voxel spectroscopy was compared to combined (pooled) multi‐voxel spectroscopy datasets. Findings from this preliminary study indicated that single‐ and multi‐voxel spectroscopy techniques using 3T MRI yield comparable results for similar sized regions of interest in the normal canine brain. Findings also supported using the contralateral side as an internal control for dogs with brain lesions.     

NMR-Based Configurational Assignments of Natural Products: Gibbs Sampling and Bayesian Inference Using Floating Chirality Distance Geometry Calculations

Floating chirality restrained distance geometry (fc-rDG) calculations are used to directly evolve structures from NMR data such as NOE-derived intramolecular distances or anisotropic residual dipolar couplings (RDCs). In contrast to evaluating pre-calculated structures against NMR restraints, multiple configurations (diastereomers) and conformations are generated automatically within the experimental limits. In this report, we show that the “unphysical” rDG pseudo energies defined from NMR violations bear statistical significance, which allows assigning probabilities to configurational assignments made that are fully compatible with the method of Bayesian inference. These “diastereomeric differentiabilities” then even become almost independent of the actual values of the force constants used to model the restraints originating from NOE or RDC data.     

基于NIR定量模型快速预测发酵麸皮中还原糖和可溶性蛋白成分的含量

为建立一种能快速预测发酵麦麸还原性糖和可溶性蛋白含量的定量分析模型,本研究以发酵麦麸为样本,采用3,5-二硝基水杨酸比色法（3,5-dinitrosalicylic acid, DNS）和BCA蛋白浓度测定法分别测定样品的还原性糖和可溶性蛋白含量;利用近红外光谱技术（Near infrared spectrum instrument, NIR）结合偏最小二乘法（Partial least squares regression, PLS）,比较预处理方法、最佳波长及主成分因子的决定系数R²,建立发酵麦麸还原性糖和可溶性蛋白含量的NIR快速检测定量模型。结果表明：1）发酵麦麸还原性糖定量模型的预处理方法使用一阶导数 （First derivative, FD）+二阶导数 （Second derivative, SD）+标准正态变换 （Standard normal variate, SNV）,光谱范围为908~1 670 nm ,主因子数为7时,模型效果最优,其决定系数Rc²为0.904 8,校正均方根误差（Square error corrected, SEC）为1.576 1,相对分析误差（Relative percentage difference, RPD）为3.240 8;外部验证集决定系数Rp²为0.954 9且还原糖活性成分的验证集样本的测定值与NIR光谱预测值的P值为0.959 5>0.05。2）发酵麦麸可溶性蛋白定量模型的预处理方法使用一阶导数 （First derivative, FD）+二阶导数 （Second derivative, SD）+标准正态变换 （Standard normal variate, SNV）,光谱范围为908~1 670 nm ,主因子数为10时,模型效果最优,其决定系数Rc²为0.938 2,校正均方根误差（Square error corrected, SEC）为2.003,相对分析误差（Relative percentage difference, RPD）为4.021 9;外部验证集决定系数Rp²为0.994 4,且可溶性蛋白活性成分的验证集样本测定值与NIR光谱预测值的P值为0.901 9>0.05。综上,建立的NIR光谱定量模型稳定性和准确性较好,且预测准确度良好,可用于快速预测发酵麦麸样品的还原性糖和可溶性蛋白含量。     

山药片红外联合热风干燥热质传递收缩模拟与品质

为了准确揭示山药片红外联合热风干燥传热传质机理,在考虑山药片收缩变形特性的基础上,通过有限元软件COMSOL6.1建立了“温度场-湿度场”多场耦合的山药片红外联合热风干燥传热传质模型。模拟研究基于山药片在不同温度（50、60、70 ℃）下收缩变形的传热传质,并通过试验进行验证。分析不同温度对山药片品质（色差、复水比、多糖和尿囊素含量）的影响。结果表明：1）山药片体积比随干燥温度的升高而增加,在干燥温度分别为50、60、70 ℃时,其值分别为34.55%、37.23%、39.04%。2）在干燥温度为50、60、70 ℃时,红外联合热风干燥收缩模型可准确预测山药片干燥过程中干燥温度和含水率,其决定系数R²分别为0.973、0.976、0.981和0.983、0.984、0.974。3）山药片外部温度升高,表面水分开始蒸发,形成水分梯度。随着干燥的继续,红外热量在山药片内部不断积累,导致内部温度升高,水分向外扩散,进而减小了内外水分梯度。随着干燥温度的升高,增加了山药片温度和湿度梯度,促进了热量和质量的传递,提高了水分迁移的速率。4）在60 ℃时,干燥品质最优,其色差为7.49、复水比为2.65 kg/kg、多糖含量为24.17 mg/g、尿囊素含量为2.66 μg/g。该模型为其他物料在红外联合热风干燥技术的模拟研究提供有益借鉴。