PSO-SOM分类判别研究及其应用

针对网络初始权矢量选取的不确定性问题,提出了粒子群优化-自组织映射(PSO-SOM)算法,利用PSO算法优化SOM网络的初始权矢量,进而进行分类.将提出的方法用于基因表达数据的分类判别中,使得SOM网络的误差平方和大大下降,提高了网络的分类精度,表明PSO-SOM算法用于数据的分类判别是切实有效的.     

Comparison of clustering approaches with application to dual colour protein data

Cells communicate with their environment via proteins, located at the plasma membrane separating the interior of a cell from its surroundings. The spatial distribution of these proteins in the plasma membrane under different physiological conditions is of importance, since this may influence their signal transmission properties. In this study, the authors compare different methods such as hierarchical clustering, extensible Markov models and the gammics method for analysing such a spatial distribution. The methods are examined in a simulation study to determine their optimal use. Afterwards, they analyse experimental imaging data and extend these methods to simulate dual colour data.Inspec keywords: proteins, molecular biophysics, cellular biophysics, biomembranes, Markov processes, bioinformatics, statistical analysisOther keywords: clustering approaches, dual colour protein data, cell communication, plasma membrane, spatial protein distribution, signal transmission, hierarchical clustering, extensible Markov models, gammics method, experimental imaging data     

Development of correlation-based clustering method and its application to software sensing

The individuality of production devices should be taken into account when soft-sensors are designed for parallelized devices. Since it is expressed as differences of the correlation among measured variables, it is useful to cluster samples on the basis of the correlation among variables for adopting a multi-model approach. In addition, changes in process characteristics can be coped with in the same way. In the present work, a new clustering method, referred to as NC-spectral clustering, is proposed by integrating the nearest correlation (NC) method and spectral clustering. Spectral clustering is a graph partitioning method that can be used for sample classification when an affinity matrix of a weighted graph is given. The NC method can detect samples that are similar to the query from the viewpoint of the correlation without a teacher signal. In the proposed method, the NC method is used for constructing the weighted graph that expresses the correlation-based similarities between samples and the constructed graph is partitioned by using spectral clustering. In addition, a new soft-sensor design method is proposed on the basis of the proposed NC-spectral clustering. The usefulness of the proposed methods is demonstrated through a numerical example and a case study of parallelized batch processes. The performance of the proposed correlation-based method is better than that of the conventional distance-based methods.     

Hybrid order statistic filter and its application to image restoration

We introduce a new nonlinear filter for signal and image restoration, the hybrid order statistic (HOS) filter. Because it exploits both rank- and spatial-order information, the HOS realizes the advantages of nonlinear filters in edge preservation and reduction of impulsive noise components while retaining the ability of the linear filter to suppress Gaussian noise. We show that the HOS filter exhibits improved performance over both the linear Wiener and the nonlinear L filters in reducing mean-squared error in the presence of contaminated Gaussian noise. In many cases it also performs favorably compared with the Ll and rank-conditioned rank selection filters.     

A multi-view method of scientific paper classification via heterogeneous graph embeddings

The classification task of scientific papers can be implemented based on contents or citations. In order to improve the performance on this task, we express papers as nodes and integrate scientific papers’ contents and citations into a heterogeneous graph. It has two types of edges. One type represents the semantic similarity between papers, derived from papers’ titles and abstracts. The other type represents the citation relationship between papers and the journals or proceedings of conferences of their references. We utilize a contrastive learning method to embed the nodes in the heterogeneous graph into a vector space. Then, we feed the paper node vectors into classifiers, such as the decision tree, multilayer perceptron, and so on. We conduct experiments on three datasets of scientific papers: the Microsoft Academic Graph with 63,211 scientific papers in 20 classes, the Proceedings of the National Academy of Sciences with 38,243 scientific papers in 18 classes, and the American Physical Society with 443,845 scientific papers in 5 classes. The experimental results on the multi-class task show that our multi-view method scores the classification accuracy up to 98%, outperforming state-of-the-arts.

     

数字化矿山体系结构模型及其应用

分析国内外数字化矿山的概念及其研究现状,从3个层次给出数字化矿山基本内涵,从业务层面、数据层面、技术层面提出数字化矿山的应用模式和构成体系结构。设计了一个三层四级网络体系结构,并对每一层牵涉的关键技术都给出详细阐述。在此体系结构基础之上,结合试验煤矿给出了试验煤矿的具体实施方案、实施现状和实施效果。     

新型膨胀阀及其应用

随着空调技术的发展需要,不同类型的膨胀阀将替代原有的节流装置,以达到更有效的机电一体化控制,本文介绍了几种新型膨胀阀的结构及各自的特点,对其如何科学地使（选）用和管理提供一定的依据,以便逐步探索新型膨胀阀在使用管理方面的经验。     

无限隐Markov模型在缺失数据轴承退化趋势预测中的应用

相比较于在完整数据下设备性能退化预测,缺失数据下的预测是更加困难的,也是更有意义的。然而,现有的轴承性能退化预测方法都未考虑缺失数据下的预测,基于此,提出了一种基于无限隐马尔可夫模型的缺失数据下轴承退化预测方法。在提出的方法中,通过建立无限隐马尔可夫预测模型,预测了滚动轴承样本数据在振荡阶段所缺失的数据点,形成新的完整数据。同时,再使用建立的预测模型对新的完整数据进行单步预测。实验结果表明,与真实值对比,得到的预测数据具有较小的平均误差值;对比真实值、完整数据下的预测值和新的完整数据下的预测值,验证了提出方法的有效性,能够反映滚动轴承退化的变化趋势。提出的方法可为数据缺失下滚动轴承的退化趋势预测提供一种思路,具有重要的理论价值和工程应用价值。     

Wide area measurements-based model validation and its application

Simulation veracity is very important to the plan and operation of a power system. Too optimistic a simulation will put the system at risk whereas too pessimistic a simulation will waste investments. Wide area measurements (WAMs), one of the fast developing technologies in recent years, could record the synchronized phasors in the whole power grid, which provides the possibility for simulation validation work. Recent contingency reproduction work worldwide has shown the inaccuracy of current digital simulation. Therefore simulation validation and model calibration are necessary to enhance simulation veracity. However, because of the complexity of the power system, it is difficult to find the erroneous ones among a large amount of components, which makes the simulation validation a very challenging problem. A new approach for WAMs-based simulation validation work is proposed. The proposed method is very simple and easy to be implemented in the available power system simulation software. Then, the trajectory sensitivity method is applied to the parameter calibration work. Real applications via the proposed methods in the big NE power grid of China are studied, which fully show the efficiency of the proposed methods.     

基于注意力机制的TDNN-LSTM模型及应用

在大数据规模下,基于深度学习的语音识别技术已经相当成熟,但在小样本资源下,由于特征信息的关联性有限,模型的上下文信息建模能力不足从而导致识别率不高.针对此问题,提出了一种嵌入注意力机制层(Attention Mechanism)的时延神经网络(Time Delay Neural Network,TDNN)结合长短时记忆...     

索杆梁耦合结构分析模型及其应用研究

为了研究索杆滑动连接特性对索杆梁耦合结构受力的影响,定义了由一个通过滑动节点连接的三节点活动滑移索单元和多个两节点非活动滑移索单元组成的单元组,基于更新拉格朗日法推导了三节点直线型滑索单元几何非线性刚度矩阵,并建立了输电线路索杆梁耦合结构有限元模型。通过高压架空输电线路耐张段的非线性静力调索分析验证了耦合结构模型的可行性,探讨了耦合结构在导线发生断裂失效后的动响应变化规律及其传播特性。计算结果表明,导线静态张力与规范设计参数相差较小,可用于后续分析。考虑滑移的导线张力在导线断裂初期有短暂增加的趋势。导线断裂对邻近绝缘子和铁塔横担杆件的受力有明显的影响,且动响应的传播会导致邻近塔的导线张力增加。     

随机人行激励模型改进及其应用

为准确描述行人间人行激励的差异性和单人激励各相似周期的差异性,基于Zivanovic模型提取样板周期曲线,通过非线性最小二乘拟合,并考虑单人激励各周期、幅值和冲量的随机特性,提出一种改进的随机人行激励模型;与已有常用人行激励模型比较表明,改进模型能更有效地模拟人行激励的时频域特性,与实测时程更加吻合。以天津西站站房结构为例,将人体等效为双自由度质量弹簧阻尼系统,建立人—结构耦合动力平衡方程,采用逐步积分法分析进行随机人行激励下的结构振动响应分析;结果表明：采用改进随机人行激励模型分析的结构振动响应频域分布更宽,且激励中高频成分对结构振动有一定贡献;考虑人—结构耦合作用,将减小结构振动响应,但影响较小。     

C楞瓦楞纸板动态缓冲模型及应用

利用万能试验机和跌落试验台分别得到C楞瓦楞纸板静态、动态应力-应变数据,建立相应的理论模型,并用最小二乘法识别模型中的参数。给出了瓦楞纸板在缓冲动力学中应用的例子,结果表明所建立的缓冲模型,可以直接用于缓冲包装设计,克服了用最大加速度-静应力曲线来设计缓冲包装需要大量实验和较多的数据的弊端。     

Fractional order PID and application of its circuit model

In this paper, the circuit design of a fractional order proportional-integrated derivation (FO-PID) controller for synchronization between different FO chaotic systems has been described. Chaotic synchronization and control are used in different applications in nonlinear physical systems such as performance tests for controllers and chaotic communication systems. FO chaotic systems have been created, and the synchronization control of these two systems has been carried out using an FO-PID controller. The total square error should be minimized in order to determine the parameters and orders of the designed FO controller circuit. The results obtained using the FO controller are better than those obtained using classical control systems. Using an FO-PID controller, the time to reach synchronization decreased significantly.     

Linear approximation model network and its formation via evolutionary computation

To overcome the deficiency of ’local model network’ (LMN) techniques, an alternative ’linear approximation model’ (LAM) network approach is proposed. Such a network models a nonlinear or practical system with multiple linear models fitted along operating trajectories, where individual models are simply networked through output or parameter interpolation. The linear models are valid for the entire operating trajectory and hence overcome the local validity of LMN models, which impose the predetermination of a scheduling variable that predicts characteristic changes of the nonlinear system. LAMs can be evolved from sampled step response data directly, eliminating the need for local linearisation upon a pre-model using derivatives of the nonlinear system. The structural difference between a LAM network and an LMN is that the overall model of the latter is a parameter-varying system and hence nonlinear, while the former remains linear time-invariant (LTI). Hence, existing LTI and transfer function theory applies to a LAM network, which is therefore easy to use for control system design. Validation results show that the proposed method offers a simple, transparent and accurate multivariable modelling technique for nonlinear systems.     

RAFT聚合调控的聚甲基丙烯酸β-羟乙酯/纳米二氧化硅杂化材料的制备及性能

首先将偶氮类引发剂引到纳米二氧化硅的表面,然后以此为引发剂,以甲基丙烯酸叔丁酯基二硫代萘甲酸酯(TNPBE)为链转移剂(CTA),进行甲基丙烯酸β-羟乙酯的可逆加成-断裂链转移(RAFT)自由基聚合,制备了甲基丙烯酸β-羟乙酯/纳米二氧化硅(PHEMA/nano-SiO2)有机/无机杂化材料,并用红外光谱(FT-IR)、透射电镜(TEM)和热失重(TG)等方法对其结构和性能进行了表征与测试。研究结果表明,聚合物已经接枝到了纳米二氧化硅的表面,整个非均相体系中的聚合反应都是在链转移剂的作用下进行的,TG分析说明了此杂化材料的热稳定性良好。     

A hybrid model of the CO2 geochemical cycle and its application to large impact events

A hybrid model of the carbonate-silicate geochemical cycle is presented which is capable of calculating the partitioning of carbon dioxide between the atmosphere, ocean, and sedimentary rocks. The ocean is subdivided into a shallow, mixed layer, which remains in equilibrium with the atmosphere, and a massive, deep layer which does not. Gradients in dissolved carbon content are established between the mixed layer and the deep ocean as a consequence of downward fluxes of fecal matter and of dead planktonic organisms. The dissolved carbon content and alkalinity of the ocean as a whole are controlled by weathering and metamorphism of sedimentary rocks. Equilibrium solutions are derived for the preindustrial atmosphere/ocean system and for a system that may be similar to that existing during the Late Cretaceous Period. The model is then used to determine how the modern and ancient marine biospheres might be affected by an oceanic impact of a large asteroid or comet. Such an event could perturb the carbon cycle in several different ways. Global darkening caused by stratospheric dust veil could destroy most of the existing phytoplankton in a period of several weeks to several months. At the same time, dissolution of atmospheric NOx compounds synthesized during the impact would lower the pH of ocean surface waters and release CO2 into the atmosphere. Both effects might be enhanced by an influx of CO2 released from upwelling of deep ocean water near the hot impact site, from oxidation of dead organic matter, and from the comet itself. The net result could be to raise surface temperatures by several degrees and to make the surface ocean uninhabitable by calcareous organisms for as much as 20 yrs (the time scale for mixing with deep ocean). It appears unlikely, however, that an impact could create a "Strangelove ocean," in which surface waters remained corrosive to calcium carbonate for thousands or tens of thousands of years. Thus, disruption of the carbon cycle by an impact event cannot by itself explain the scarcity of calcium carbonate in sediments found within the first few centimeters above the K/T boundary.     

一种等效拉延筋阻力模型及其应用

 为了提高板料成形件质量,提出了一种等效拉延筋阻力模型.该拉延筋阻力模型在平面应变假设的前提下,考虑中性层偏移、鲍辛格效应等多种因素影响,通过与经典的Nine试验数据比较,证明了该模型的准确性.以翼子板为成形对象,结合改进的等效拉延筋阻力模型,采用非线性优化算法对拉延筋结构进行优化设计.利用优化获得的等效拉延筋阻力反求拉延筋几何参数,建立成形中的实体拉延筋仿真模型,获得了质量较好的成形件.研究结果表明该等效拉延筋阻力模型能够较好地适用于板料成形中.     

Dynamic model of multipass ultrashort-pulse laser amplifiers and its application

We developed a dynamic model for evaluating the gain and amplified spontaneous emission of multipass ultrashort-pulse laser amplifiers. This model takes into account the time dependence of the population inversion that is due to the time-varying pump power and the evolution of the amplified spontaneous emission. For gain media of a short upper-state lifetime, a time-dependent analysis is essential for the model to extend beyond order-of-magnitude estimation. We verified the model with a femtosecond dye laser amplifier. The calculated output energy is accurate to within +/-5% of the experimental data. We utilized this model to optimize the conversion efficiency of the dye laser amplifier under low-energy pumping. An efficiency of 2.3% is achieved with an optimal pump energy of only 4 muJ.     

Rheological-dynamical model of concrete and its application on RC beams

Mechanics of Time-Dependent Materials - An improved analytical model based on rheological-dynamical analogy (RDA) is briefly explained and used for the analysis of concrete cylinders under...