Long-term prediction of compressive creep development in expanded polystyrene

The results obtained in investigating the creep of expanded polystyrene (EPS) boards under compressive stress are presented. Power and exponential equations were used for describing creep compliance. It was found that the curves of creep compliance approximated by both equations adequately represent the research results, taking into account the scatter of the experimental data. Based on the calculation and empirical estimate of long-term creep of EPS under compressive stress σ_c=(0.25–0.45)σ_10%, its creep compliance was determined for a period of 10 years in the future. The dependence of on the density of polystyrene boards and the value of long-term compressive stress σ_c was established. The expected values of creep strain development in expanded polystyrene boards EPS 80–EPS 250 under constant compressive stress σ_c=(0.25–0.45)σ_10% are presented for the prediction period of 10 years. To obtain the expected creep values for any other period of time in the interval of 5T50 years, the values of should be multiplied by the empirical coefficient .     

非线性灰色微分方程(dx)/(dt)+ax~(■a)=b 的拟合

本文给出了拟合非线性灰色微分方程 dx/dt+ax~(■a)=b 的计算方法,并讨论了它的性质及应用.     

A quest for error factors in predicting heavy weight floor impact sound levels using measured data in existing residential buildings

A number of datasets regarding the heavy weighted floor impact sound level and the driving point impedance level, i.e., twenty times the common logarithm of driving point impedance at an exciting point, were measured in existing residential buildings before the floor finishing of the excitation room and the ceiling finishing of the receiving room were installed. These data were compared to the calculated values by the impedance method, i.e., a practical method that estimates vibration energy of an excited slab using the driving point impedance at the exciting point as a major factor, as well as those using the Finite Element Method (FEM) models of slabs. Furthermore, correlations between the residual errors and the major dimensions of the receiving rooms were investigated. Two major error factors were found to influence the calculated values by the impedance method. The spectral characteristic of the tire impact source within the 63 Hz band effectively decreased the prediction errors when it was included in the calculation and combined with the FEM models of slabs. The length of the shorter side of the receiving room plan correlated to the residual errors of the receiving rooms having a pair of flat parallel walls. These errors arise from the fact that the receiving points were placed at the central and quarter positions within the wall distance, where the nodes of the horizontal mode exist. It was not possible to identify another dimension of the receiving room that significantly correlates to the residual errors of the prediction.     

A framework for classification with single feature kernel matrix

In this paper, we propose a novel classification framework using single feature kernel matrix. Different from the traditional kernel matrices which make use of the whole features of samples to build the kernel matrix, this research uses features of the same dimension of any two samples to build a sub-kernel matrix and sums up all the sub-kernel matrices to get the single feature kernel matrix. We also use single feature kernel matrix to build a new SVM classifier, and adapt SMO (Sequential Minimal Optimization) algorithm to solve the problem of SVM classifier. The results of the experiments on several artificial datasets and some challenging public cancer datasets display the classification performance of the algorithm. The comparisons between our algorithm and L₂-norm SVM on the cancer datasets demonstrate that the accuracy of our algorithm is higher, and the number of support vectors selected is fewer, indicating that our proposed framework is a more practical approach.     

近红外光谱的北方寒地土壤含水率预测模型研究

我国北方寒地温差大,土壤温差对近红外光谱测量土壤墒情有较大影响。针对这一问题,以北方寒地土壤为研究对象,探究大范围温度胁迫下（-20～40 ℃）土壤的近红外光谱与土壤不同含水率之间的关系预测模型方法。选取黑龙江八一农垦大学农学院试验基地中的黑土,经烘干、过筛等操作处理后配置含水率范围在15%～50%内八种不同湿度的土壤样品,建立北方寒地土壤大范围温度胁迫下土壤的近红外光谱信息与含水率之间的定量预测模型。在全波段光谱数据的基础上,结合五种不同光谱信号预处理方法,采用BP神经网络算法、优化支持向量机算法（SVM）、高斯过程算法（GP）三种智能算法建立北方寒地土壤近红外光谱与含水率的预测模型并验证模型的效果。利用69组数据进行训练建模, BP神经网络相关参数设置为学习速率0.05,最大训练次数设置为5 000,隐层单元数确定为20;SVM采用径向基函数,并利用leave-one-out cross validation确定了最佳惩罚参数为0.87,使模型预测的准确性提高;高斯过程算法内部采用马顿核。模型的定量评估采用决定系数(R2)和均方根误差（RMSE）。结果表明,在建立的全部BP神经网络模型中,效果最佳的为S_G-BP神经网络模型,模型的R2为0.960 9,RMSE为2.379 7;在SVM模型中SNV-SVM模型的效果最好,模型的R2为0.991 1,RMSE为1.081 5;在GP模型中S_G-GP模型的效果最好,模型的R2为0.928,RMSE为3.258 1,综上基于SNV预处理的SVM模型训练效果最优。利用剩余的35组光谱数据作为预测集验证模型性能,经模型对比分析发现基于SVM算法的预测模型效果优于其他两种算法,其中基于S_G的SVM模型效果最优,其预测模型的R2和差RMSE分别为0.992 1和0.736 9。综合建模集与预测集的参数最终确定基于S_G的SVM模型为最佳模型。此模型可以作为大范围温度胁迫条件下（寒地）的土壤含水率有效预测方法,为设计优化适宜寒地便携式近红外土壤含水率快速测量仪提供科学依据。     

玉米叶片重金属铅含量的SVD-ANFIS高光谱预测模型

重金属污染农作物后可通过食物链进入人体从而严重危害身体健康。如何快速准确地监测农作物中重金属含量已成为当今生态与粮食安全等领域的重要研究内容。常规的生化监测方法存在操作繁琐、过程长、具有破坏性等缺点,而高光谱遥感具有光谱分辨率高、信息量大、生化反演能力强、方便快捷、对监测对象无损伤等优势,因此利用高光谱遥感技术监测农作物中重金属含量已成为遥感领域的热点研究之一。以不同浓度Pb(NO₃)₂溶液胁迫下盆栽玉米植株为研究对象,基于不同铅离子(Pb2+)胁迫梯度下玉米叶片的反射光谱及其中Pb2+含量的测定数据,结合奇异值分解(SVD)理论和自适应模糊神经网络推理系统(ANFIS)结构,建立了一种Pb2+含量预测的SVD-ANFIS模型。首先对各胁迫梯度下玉米的老叶(O)、中叶(M)、新叶(N)三种叶片的反射光谱数据进行SVD处理,获取原始光谱信息的奇异值;然后选择O,M和N叶片对应的奇异值来寻求ANFIS结构的最佳输入组合,最终选定O-M（双输入）组合作为ANFIS结构的输入量,通过训练和学习获得最优模糊规则库后,ANFIS结构的输出量即为叶片中Pb2+含量,从而实现了SVD-ANFIS模型的预测性能。研究结果表明,该模型的输出误差值较小,精度较高,在模糊训练过程中隶属函数选为钟型函数时预测效果最佳。利用多参数的反向传播(BP)神经网络预测模型对SVD-ANFIS模型的预测优越性进行验证时,得到BP模型和SVD-ANFIS模型的决定系数(R2)分别为0.977 6和0.988 7,均方根误差(RMSE)分别为2.455 9和0.601 3,可见SVD-ANFIS模型的拟合度更高,预测效果更好。同时选取不同年份的Pb污染玉米叶片等光谱数据对SVD-ANFIS模型进行可行性检验,其R2和RMSE分别为0.986 4和0.887 4,说明SVD-ANFIS模型能较好的用于玉米叶片中Pb2+含量预测且具有较高的鲁棒性,可作为预测玉米叶片中重金属含量的一种方法。     

基于GARCH模型的短期汇率预测

研究人民币对美元的汇率预测,通过对2010年7月1日至2013年11月30的周汇率平均值进行数据分析,发现其基本符合时间序列分析中的GARCH模型,因此采用该模型进行预测,预测结果比较成功。预测表明人民币呈现升值的趋势.     

动态水声环境不确定性的预报与估计

水声环境具有强烈的时空易变性,为了解其变化中的规律和产生的不确定性,将POM海洋数值模型和水声传播模型FOR3D进行耦合,建立海洋—声学耦合数值模式。对海区的温盐等环境参数和水下声场进行预报,给出了典型断面的温度垂直结构、实验海区声速剖面和传播损失。同时,采用集合卡尔曼滤波(EnKF)方法结合海洋—声学耦合数值模式分析了水声环境的不确定性,对不同深度与频率下,传播损失的均值与满足90%的可能区间进行了计算,同时给出了不同点声速、传播损失、声纳作用距离的不确定性直方图。和实验数据的对比结果表明该方法具有较高的有效性,能对水声环境的不确定性进行合理的预报与估计。