The prediction of asphalt pavement permanent deformation by T-GM(1,2) dynamic model

In this article, we propose a prediction model of asphalt pavement permanent deformation based on improved grey prediction model. This improved prediction model combines the first-order two variables grey differential equation model (abbreviated as GM(1,2) model) from grey system theory and Taylor approximation method from approximation optimisation theory. We abbreviate the combined model as T-GM(1,2) model. The combined model can obtain the most optimal predicted value by multiple approximate calculation. We validated the effectiveness of T-GM(1,2) model, through using the measured data of deformation depth obtained from the wheel tracking device test. The experimental result showed that the T-GM(1,2) model has high predictable power for asphalt pavement permanent deformation.     

基于等维新息灰色马尔可夫模型的校准间隔预测

针对测量仪器校准间隔的优化问题,分析了历史校准数据的特征,建立了等维新息马尔可夫GM(1,1)预测模型.在等维新息GM(1,1)模型的基础上,引入马尔可夫模型,克服了随机波动数据对预测精度的影响.通过仿真实验对预测模型进行了验证,结果表明,等维灰色马尔可夫GM(1,1)模型的预测精度高于常规灰色GM(1,1)模型、等维新息灰色GM(1,1)模型和常规灰色马尔可夫GM(1,1)模型,更适合用于测量仪器校准间隔的预测.     

A novel 3D GBSM for mmWave MIMO channels

In this paper, a novel three dimensional (3D) wideband geometry-based stochastic model (GBSM) for millimeter wave (mmWave) multiple-input multiple-output (MIMO) channels is proposed. A homogeneous Poisson point process (PPP) is used to generate the clusters in 3D space. The transmitter (Tx) and receiver (Rx) are surrounded by two spheres. The scatterers distributed in the two spheres are introduced to mimic the clustering effects of multipath components (MPCs) in delay and angular domains. The large-scale path loss model and line-of-sight (LOS) probability model are taken into account to make the channel model realistic. In addition, mmWave channel measurements are conducted in an indoor environment. Simulation results based on the two-sphere channel model are compared with measurement results and good agreements are achieved, which validates the proposed channel model. The results indicate that the proposed channel model has good adaptivity and can model the mmWave channel accurately.     

含分数阶多项式的离散灰色预测模型及其应用

为了进一步提高含时间幂次项的灰色预测模型的拟合预测精度,通过引入分数阶多项式,提出灰作用量优化的FPDGM(1,1,N)预测模型.在经典的DGM(1,1,$ N $)模型的基础上,将灰作用量整数阶多项式拓展为分数阶多项式,使得构造的模型能够生成更加贴近于一般特征的时间响应序列,从而得到拟合预测精度更高的灰色预测模型.对该模型的建模机理、参数估计、递推时间响应式等进行研究,并讨论模型参数几种特殊取值下该模型的性质.研究表明:DGM(1,1)模型、NDGM(1,1)模型和DGM(1,1,N)模型等均是FPDGM(1,1,N)模型的特殊形式,因此,该模型在形式上统一了现有的含时间幂次项灰色模型,扩大了灰色预测理论的应用范围.最后通过实验表明,所提出的新模型具有更好的拟合和预测精度,从而验证了所构建模型的有效性和适用性.     

废气氧传感器Hammerstein模型结构的确定

研究了废气氧(EGO)传感器Hammerstein模型结构辨识方法。静态非线性函数选用双曲正切与多项式组合形式,动态线性环节分别选用带外生变量的自回归(ARX)模型、输出误差(OE)模型和Box-Jenkins(BJ)模型结构。采用交叉准则法进行参数估计和阶次选择,通过仿真比较对模型进行检验。结果表明:最终输出误差(FOE)准则和最终预报误差(FPE)准则均适用于用估计数据选择阶次,但前者比后者更可靠。基于预测误差法的3阶OE模型和BJ模型均可用于EGO传感器Hammerstein模型动态线性环节的建模。     

灰色DNGM(1,1)预测模型及其优化

传统的灰色GM(1,1)预测模型是针对近似齐次指数序列建立的预测模型。为了拓广灰色预测模型的适用范围,建立了近似非齐次指数序列的灰色DNGM(1,1)预测模型。研究了这种灰色预测模型的性质,证明了这种模型都具有线性不变性,也能够完全拟合非齐次指数序列。考虑到初值条件对灰色模型的影响,对该模型进行了参数优化。数据仿真和实例分析表明,灰色DNGM(1,1)预测模型具有较高的预测精度。     

阻尼累加离散GM(1,1)模型及其应用

基于阻尼累加生成算子和离散灰色预测模型的思想,提出一类新的阻尼累加离散GM (1,1)模型,并详细给出模型的推导过程,从理论上分析与经典GM (1,1)模型、离散GM (1,1)模型以及最近提出的阻尼累加GM (1,1)模型的关系,探讨模型的稳定性和数据适用类型分析,并利用量子粒子群优化算法计算出最优阻尼累加参数.最后将所提出模型应用于两个实际案例,结果表明所提出的阻尼累加离散GM (1,1)模型的拟合和预测误差均优于上述基准模型.     

基于灰色神经网络的装备计量预测研究与实现

基于装备计量数据历史样本数据较少的特点,将适合小样本的灰色理论GM(1,1)模型应用于基于计量数据的装备状态预测,同时为提高GM(1,1)模型精度,提出了基于RBF神经网络优化GM(1,1)传统模型的灰色神经网络模型。装备计量数据实例应用分析表明,上述模型均可获得该装备计量数据的合理预测值,且相对于GM(1,1)传统模型,GM(1,1)优化模型具有更优的模型精度和预测效果,基于MATLAB开发的装备计量预测软件,实现了GM(1,1)传统及优化模型下装备计量状态预测及比较的可视化操作,为装备计量保障提供了可参考的技术方案。     

彩色纹理图像恢复的非局部TV模型

基于局部算子不同形式的TV(total variation)模型用于彩色图像的噪声去除时往往存在边缘模糊、纹理模糊、阶梯效应、Mosaic效应等问题.因此,将传统局部的Tikhonov模型、TV模型、MTV(multi-channel total variation)模型、CTV(color total variation)模型推广到基于非局部算子概念的NL-CT(non-local color Tikhonov)模型、NL-LTV(non-local layered total variation)模型、NL-MTV(non-local multi-channel total variation)模型、NL-CTV(non-local color total variation)模型,并通过引入辅助变量和Bregman迭代参数设计了相应的快速Split Bregman算法.实验结果表明,所提出的非局部TV模型都很好地解决了局部模型中出现的问题,在纹理、边缘、光滑度等特征保持方面取得了良好特性,其中NL-CTV处理效果最好,但是计算效率较低.     

Developing a novel inverse data envelopment analysis (DEA) model for evaluating after-sales units

This paper proposes a novel model of inverse data envelopment analysis (IDEA) based on the slack-based measure (SBM) approach. The developed inverse SBM model can maintain relative efficiency of decision making units (DMUs) with new input and output. This model can also measure the input and output volumes when a decision maker (DM) increases efficiency score. The inverse SBM model is a kind of multi-objective non-linear programming (MONLP) problem, which is not easy to solve. Therefore, we suggest a linear programming model for solving inverse SBM model. In this model efficiency score of DMU under evaluation remains unchanged. Furthermore, we suggest an optimal combination of inputs and outputs in the production possibility set (PPS). A case study is presented to demonstrate the efficacy of our proposed model.     

新息改进GM(1,1)模型参数估计的新方法

为了提高新息改进GM(1,1)模型的预测精度,引入累积法对新息改进GM(1,1)模型的参数进行估计,给出了新的参数估计公式。该方法避免了大量的矩阵运算,降低了计算量。数值计算结果表明,累积法新息改进GM(1,1)模型具有很高的预测精度,是一种值得推广的新模型。     

多阶灰色支持向量机集成预测模型研究

对灰色预测模型GM(1,1)和支持向量机SVM预测模型进行分析,提出了多阶灰色支持向量机集成预测模型Dm_GM(1,1)-SVM。通过多阶缓冲算子改进灰色预测模型的预测精度,对最终预测值的各个相关指标进行预测;同时,采用粒子群优化算法对支持向量机模型进行径向基核参数和惩罚参数寻优,得到最佳参数对(c,g),从而确定支持向量机的最佳回归模型;最后将各指标预测值作为支持向量机模型的输入,依据预测模型和预测模型的输入值求得预测结果。实验实例表明,多阶灰色支持向量机集成模型和传统的预测模型相比,在本例中预测精度更高,说明多阶灰色预测模型和支持向量机模型相结合在解决实际预测问题中具有实用价值。     

基于分段线性函数的功放模型及数字预失真应用

为了克服通信系统中功率放大器的非线性和记忆效应,数字预失真技术成为研究的热点。提出一种基于分段线性函数的多项式模型,与广义记忆多项式模型相比,我们把多项式中的高阶项转换为分段求和项,消除了高阶相乘带来的不稳定性,同时由于分段阈值的存在,该模型的适用性和稳定性均有所提高。把功放模型应用于数字预失真结构中的实验结果表明:与广义记忆多项式模型相比,分段线性函数模型所需系数要少40%,邻信道功率比提高约1dB,归一化均方误差提高约8dB,因此该模型在数字预失真方面具有较好的效果。     

Static, Dynamic, and Hybrid Neural Networks in Forecasting Inflation

The back-propagation neural network (BPN) model has been the most popular form of artificial neural network model used for forecasting, particularly in economics and finance. It is a static (feed-forward) model which has a learning process in both hidden and output layers. In this paper we compare the performance of the BPN model with that of two other neural network models, viz., the radial basis function network (RBFN) model and the recurrent neural network (RNN) model, in the context of forecasting inflation. The RBFN model is a hybrid model with a learning process that is much faster than the BPN model and that is able to generate almost the same results as the BPN model. The RNN model is a dynamic model which allows feedback from other layers to the input layer, enabling it to capture the dynamic behavior of the series. The results of the ANN models are also compared with those of the econometric time series models.     

用于纹理分类的多元旋转不变自回归模型

本文在Kashyap提出的CAR模型的基础上,发展了一种多元旋转不变自回归纹理模型 (RISAR).利用RISAR模型的参数作为纹理图象的旋转不变特征,进行纹理分类,分类精度 相对于CAR模型有较大的提高;同时识别速度比SAR模型大大提高.如果把RISAR模型 用于多分辨率自回归纹理模型[2]中,分类精度可提高到100%.     

农业模型组件主题图的生成方法

分析农业模型的信息组织需求,提出一种农业模型组件主题图的生成方法,对模型组件的元数据信息进行XTM标注,形成属性元主题图。利用实例化和反射技术,生成具体模型组件的局部原子主题图。通过主题信息的字符匹配算法,融合同类模型的原子主题图,形成农业模型组件的全局原子主题图。以作物生育期模型组件的主题图为实例,验证了该方法的有效性。     

MTO 管理模式下钢铁企业生产合同计划建模与优化

基于对钢铁企业MTO管理模式下合同计划的编制策略、约束条件和优化目标的研究，建立了合同计划优化模型，模型综合考虑了拖期惩罚费用、设备能力均衡利用和库存成本等优化目标，并采用加权法将多目标优化模型转换为单目标优化模型，针对模型的特点设计了求解模型的特殊PSO算法，以某钢铁企业的实际合同计划问题作为实例，在算法不同参数组合下进行了系统的测试，实验结果表明模型和算法是令人满意的。     

基于多Agent的可重构制造系统集成模型

应用控制、管理和维护一体化的自动化技术,建立了基于多Agent的可重构制造系统RMS（Reconfigurable Manufacturing System）集成模型。该模型集成了基于多Agent 的RMS重构模型、控制模型和故障诊断模型,将RMS的控制、管理和维护联系起来,并给出了该模型的UML（Unified Modeling Langurage）活动图,最后举例验证了模型的可行性。     

A distributed coupled atmosphere–wave–ocean model for typhoon wave numerical simulation

A distributed coupled framework system was developed. The framework consists of atmosphere model (MM5), ocean model (Princeton Ocean Model), wave model (WW3) and a coupled programme (coupled model). The coupled programme controls atmosphere–wave–ocean model calculations and data exchanges. The impact of air–sea–wave interactions was considered to examine the validity and performance of this coupled model. Two typical typhoon cases Vongfong (No. 0214) and Rananim (No. 0414) were modelled to examine the wave simulation validity in the China Seas. The coupled model can obviously improve the precision of the significant wave height when compared with the uncoupled run.