Adaptive Neuro-Fuzzy Inference System and a Multilayer Perceptron Model Trained with Grey Wolf Optimizer for Predicting Solar Diffuse Fraction

The accurate prediction of the solar diffuse fraction (DF), sometimes called the diffuse ratio, is an important topic for solar energy research. In the present study, the current state of Diffuse irradiance research is discussed and then three robust, machine learning (ML) models are examined using a large dataset (almost eight years) of hourly readings from Almeria, Spain. The ML models used herein, are a hybrid adaptive network-based fuzzy inference system (ANFIS), a single multi-layer perceptron (MLP) and a hybrid multi-layer perceptron grey wolf optimizer (MLP-GWO). These models were evaluated for their predictive precision, using various solar and DF irradiance data, from Spain. The results were then evaluated using frequently used evaluation criteria, the mean absolute error (MAE), mean error (ME) and the root mean square error (RMSE). The results showed that the MLP-GWO model, followed by the ANFIS model, provided a higher performance in both the training and the testing procedures.     

Support vector regression for warranty claim forecasting

Forecasting the number of warranty claims is vitally important for manufacturers/warranty providers in preparing fiscal plans. In existing literature, a number of techniques such as log-linear Poisson models, Kalman filter, time series models, and artificial neural network models have been developed. Nevertheless, one might find two weaknesses existing in these approaches: (1) they do not consider the fact that warranty claims reported in the recent months might be more important in forecasting future warranty claims than those reported in the earlier months, and (2) they are developed based on repair rates (i.e., the total number of claims divided by the total number of products in service), which can cause information loss through such an arithmetic-mean operation.To overcome the above two weaknesses, this paper introduces two different approaches to forecasting warranty claims: the first is a weighted support vector regression (SVR) model and the second is a weighted SVR-based time series model. These two approaches can be applied to two scenarios: when only claim rate data are available and when original claim data are available. Two case studies are conducted to validate the two modelling approaches. On the basis of model evaluation over six months ahead forecasting, the results show that the proposed models exhibit superior performance compared to that of multilayer perceptrons, radial basis function networks and ordinary support vector regression models.     

Numerical simulation of core convection by a multi-layer semi-implicit spherical spectral method

A semi-implicit multi-layer spherical spectral method for simulating stellar core convection is described. The fully compressible three-dimensional hydrodynamic equations with rotation and energy generation are solved. Prognostic variables are expressed as finite sums of spherical harmonics in the horizontal directions and handled by the finite difference method in the radial direction. The stratified approximation is used to simplify the nonlinearity to quadratic. A multi-layer scheme is employed to overcome the time step problem arising from shrinking grid sizes in the physical space near the center of the star. Despite of the different spectral truncations in different layers, round-off conservation of the total mass and total angular momentum of the whole domain can be maintained, and were confirmed numerically. The code is parallelized; with 12 processors the speedup factor is about 9. The solutions of model core convection with and without rotation are discussed.     

公共安全视域下精神药物光谱学无损分类

该文对苯二氮类和吩噻嗪类镇静安眠药样品的红外光谱数据进行采集,构建了不同数据分类模型并对比了不同波段光谱数据集对其分析准确率的影响.结果表明,借助贝叶斯判别分析的基于全波段数据集的二阶导数模型分类效果优于其他单一模型,对于苯二氮类和吩噻嗪类两个不同类型精神药物的总体分类准确率达92.7％.借助贝叶斯判别分析的基于全波段和指纹区融合数据集的二阶导数融合模型分类效果最佳,对苯二氮类和吩噻嗪类两个不同类型精神药物的总体分类准确率达到100％;对苯二氮类和吩噻嗪类中不同种类精神药物的总体分类准确率则分别达到96.7％和100％.该研究实现了不同类型及同一类型不同种类镇静安眠药的快速准确定性分析,为此类管制类药物走私案件的准确定性提供了一定的技术支持.     

数字图像法测定养殖水中的孔雀石绿

建立一种简单、可靠的养殖水中孔雀石绿的数字图像检测方法。以1-己基-3-甲基咪唑四氟硼酸盐离子液体富集水样品,再用手机拍照获取样品信息,最后用数字图像结合多层感知器神经网络定量分析孔雀石绿的含量。该法测定结果的相对标准偏差不大于6%(n=5),加标回收率为97.8%~103.0%。该方法可用于养殖水中孔雀石绿的含量测定。     

Analytical solutions to time-fractional partial differential equations in a two-dimensional multilayer annulus

In this paper, analytical solutions to time-fractional partial differential equations in a multi-layer annulus are presented. The final solutions are obtained in terms of Mittag-Leffler function by using the finite integral transform technique and Laplace transform technique. In addition, the classical diffusion equation (α=1$\alpha =1$), the Helmholtz equation (α→0$\alpha \to 0$) and the wave equation (α=2$\alpha =2$) are discussed as special cases. Finally, an illustrative example problem for the three-layer semi-circular annular region is solved and numerical results are presented graphically for various kind of order of fractional derivative.     

More spherical large fullerenes and multi-layer fullerene cages

According to the experimental investigation, the carbon nano-particles have spherical multi-layer structure (also called onion-like carbon structure). Theoretically, the optimum structures of these large fullerenes contain highly faceted shapes with icosahedral symmetry. This discrepancy in structure may be attributed to the formation mechanism. Thus, a method is devised to construct spherical large fullerenes (C₂₄₀, C₅₄₀, C₉₆₀, C₂₁₆₀, C₂₉₄₀, C₃₈₄₀, C₄₈₆₀) by using the triangular motif. The 5–7–5–7 shape defect is applied in this method for assembling the large spherical fullerenes which could transform the graphene sheet to a spherical motif via SW rearrangement. The geometry-optimized structures of large spherical fullerenes have been generated by molecular mechanics calculation. Then, the average radius and standard deviation of these large fullerenes were obtained to verify the spherical shape. The multi-layer fullerene with spherical shape was confirmed by the TEM observation. According to the structure analysis, the distance between two neighboring encapsulating carbons is about 3.5 Å, which approximately coincides with the distance between two layers of graphite. The van der Waals force per carbon atom and of multi-layer fullerene with the spherical shape generated by force field calculation, predict their relative stability.     

基于叶绿素荧光光谱分析的稻瘟病害预测模型

为了实现稻瘟病的快速、准确和无损检测,力求构建稻瘟病害预测模型。根据水稻叶片相对病害面积将稻瘟病划分为3个等级,通过激光诱导法采集不同病害等级的活体水稻叶片叶绿素荧光光谱。选取502~830 nm波段激光诱导叶绿素荧光光谱(LICF)作为研究对象,利用Savitzky-Golay平滑法(SG)和一阶导数变换(FDT)对光谱信息进行预处理,通过主成分分析(PCA)方法获取经SG-FDT预处理后光谱的特征向量,根据累积贡献率和方差选取前3个主成分进行分析。将试验样本分为建模样本和检验样本,以稻瘟病害等级为预测指标,利用建模样本的133片叶片的光谱和病害信息分别结合判别分析(DA)、多类逻辑回归分析(MLRA)和多层感知器(MLP)建立稻瘟病的预测模型,利用检验样本的89片叶片的光谱和病害信息对所建模型进行预测检验,完成对PCA-DA、PCA-MLRA和PCA-MLP的对比寻优。结果表明,PCA-DA,PCAMLRA和PCA-MLP模型均能完成对稻瘟病害的预测,但PCA-MLP模型的平均预测准确率能够达到91.7%,相比PCA-DA和PCA-MLRA模型,在稻瘟病害3个等级上均具有较好的分类和预测能力。     

Super-stable parallel flows of multiple visco-plastic fluids

We consider the stability of a multi-layer plane Poiseuille flow of two Bingham fluids. It is shown that this two-fluid flow is frequently more stable than the equivalent flow of either fluid alone. This phenomenon of super-stability results only when the yield stress of the fluid next to the channel wall is larger than that of the fluid in the centre of the channel, which need not have a yield stress. Our result is in direct contrast to the stability of analogous flows of purely viscous generalised Newtonian fluids, for which short wavelength interfacial instabilities can be found at relatively low Reynolds numbers. The results imply the existence of parameter regimes where visco-plastic lubrication is possible, permitting transport of an inelastic generalised Newtonian fluid in the centre of a channel, lubricated at the walls by a visco-plastic fluid, travelling in a stable laminar flow at higher flow rates than would be possible for the single fluid alone.