Modeling of the hot metal silicon content in blast furnace using support vector machine optimized by an improved particle swarm optimizer

As a highly complex multi-input and multi-output system, blast furnace plays an important role in industrial development. Although much research has been done in the past few decades, there still exist many problems to be solved, such as the modeling problem. This paper adopts support vector regression (SVR) to construct the prediction model of blast furnace silicon content. To ensure a good generalization performance for the given datasets, it is important to select proper parameters for SVR. In view of this problem, a new particle swarm optimizer called DMS-PSO-CLS is presented to optimize the parameters of SVR. In DMS-PSO-CLS, a new cooperative learning strategy is hybridized with DMS-PSO, which makes particle information be used more effectively for generating better-quality solutions. DMS-PSO-CLS takes merits of the DMS-PSO and the cooperative learning strategy so that both the convergence speed and the convergence precision can be improved. Experimental results show that DMS-PSO-CLS can find the optimal parameters of SVR with high speed and the SVR model optimized by DMS-PSO-CLS can achieve a good regression precision on the predictive problem of blast furnace.     

Chaotic system identification using Wiener‐LSSVM model

In this paper, a new method is proposed for identifying chaotic system based on a Wiener‐least squares support vector machine (Wiener‐LSSVM) model. The model consists of a linear dynamic subsystem followed by a static nonlinear function, which is represented by LSSVM in this paper. The parameters of the linear dynamic part and those of LSSVM are estimated simultaneously by solving a set of linear equations using the least squares (LS) method. The proposed method incorporates partial structure information into the identification process and does not assume that the parameters of linear dynamic part are known. On the other hand, the LS algorithm is more efficient than gradient‐descendent‐based algorithms for estimating the parameters of Wiener‐LSSVM. Three identification examples are given to validate the effectiveness of the proposed method. © 2016 Institute of Electrical Engineers of Japan. Published by John Wiley & Sons, Inc.     

Making lightweight SiC(rGO,xMoSi2) bulk ceramics via polymeric precursor route

Unique properties of MoSi₂ open new opportunities for preparing bulk polymer-derived ceramics (PDCs) displaying favorable structural-functional capabilities. Herein, an ingenious production route via re-pyrolysis process of ball-milling-induced rigid SiC(rGO, xMoSi₂)_p fillers/flexible polycarbosilane-vinyltriethoxysilane-graphene oxide (PCS-VTES-GO, PVG) precursors blends is proposed to obtain in situ formed SiC(rGO, xMoSi₂) bulk PDCs. Interestingly, the possible dense β-SiC/SiOxCy/C_free(rGO, xMoSi₂) framework suffers load and tiny microsized pores relaxes stress, which is beneficial to providing optimized hardness and fracture toughness, ceramic yield, and linear shrinkage. Attractively, MoSi₂ prominently enhances thermal and electrical conductivities of the products owing to increased continuity and compactness. To the best of our knowledge, lightweight SiC(rGO, 20%MoSi₂) bulk PDCs own brilliant ceramic yield (92.13%), liner shrinkage (6.69%), hardness (10.34 GPa), fracture toughness (4.35 Mpa·m^1/2), and thermal conductivity (8.57 W·m^–1·K^–1), opening potential emerging uses in aerospace fields.     

奥氏体不锈钢纤维化过程磁性变化研究

通过对不同成分，不同丝径的纤维室温静态磁性测试，获得了一些不锈钢纤维磁性参数，从X射线衍射分析结果发现，纤维成分及纤维制备过程中，塑性加工引起的相变、内应力、组织细化等是影响纤维磁性的重要因素。这为超细不锈钢纤维生产工艺改进及开拓新的应用领域提供了理论依据。     

Optimum design of fractional order PID controller for AVR system using chaotic ant swarm

Fractional-order PID (FOPID) controller is a generalization of standard PID controller using fractional calculus. Compared to PID controller, the tuning of FOPID is more complex and remains a challenge problem. This paper focuses on the design of FOPID controller using chaotic ant swarm (CAS) optimization method. The tuning of FOPID controller is formulated as a nonlinear optimization problem, in which the objective function is composed of overshoot, steady-state error, raising time and settling time. CAS algorithm, a newly developed evolutionary algorithm inspired by the chaotic behavior of individual ant and the self-organization of ant swarm, is used as the optimizer to search the best parameters of FOPID controller. The designed CAS-FOPID controller is applied to an automatic regulator voltage (AVR) system. Numerous numerical simulations and comparisons with other FOPID/PID controllers show that the CAS-FOPID controller can not only ensure good control performance with respect to reference input but also improve the system robustness with respect to model uncertainties.     

A fast recursive algorithm based on fuzzy 2-partition entropy approach for threshold selection

The fuzzy c-partition entropy approach for threshold selection is an effective approach for image segmentation. The approach models the image with a fuzzy c-partition, which is obtained using parameterized membership functions. The ideal threshold is determined by searching an optimal parameter combination of the membership functions such that the entropy of the fuzzy c-partition is maximized. It involves large computation when the number of parameters needed to determine the membership function increases. In this paper, a recursive algorithm is proposed for fuzzy 2-partition entropy method, where the membership function is selected as S-function and Z-function with three parameters. The proposed recursive algorithm eliminates many repeated computations, thereby reducing the computation complexity significantly. The proposed method is tested using several real images, and its processing time is compared with those of basic exhaustive algorithm, genetic algorithm (GA), particle swarm optimization (PSO), ant colony optimization (ACO) and simulated annealing (SA). Experimental results show that the proposed method is more effective than basic exhaustive search algorithm, GA, PSO, ACO and SA.     

基于动量动力学模型的行人关系分析

进行了行人行为分析及行人关系研究。考虑到在机器视觉领域大多数研究仅关注于目标行为分类与识别,而目标间因果关系判别研究较少,且现有理论停留在心理学领域中的因果关系表达,提出了一种基于动量动力学模型的目标间因果关系识别方法,用于实现行人间因果关系的识别及量化计算。该方法利用Cam shift算法获得目标在视频中的位置并依据因果概念,构建动量动力模型,然后基于动量动力模型进行因果关系判别,最后计算因果值。根据因果值范围识别出视频行人间的三种因果关系:导致、促进和阻碍。实验表明,上述方法可以在视频监控条件下识别两运动行人间的因果关系。     

Structural behavior and in vitro bioactivity evaluation of hydroxyapatite-like bioactive glass based on the SiO2-CaO-P2O5 system

Silicate bioglass is of great importance in bone engineering because of its excellent bioactivity and osteogenic effects. In this study, hydroxyapatite-like bioactive glass based on the xSiO₂-CaO-P₂O₅ (x = 30, 45, 60 and 90 mol.%, Ca/P = 1.67) system was synthesized by the sol-gel method, and the corresponding structural evolution, apatite-forming ability and cytotoxicity were systematically investigated. The results suggest that both a higher heat treatment temperature and a lower SiO₂ content increase the crystallinity tendency of the bioglass, and the samples become obviously compact as the SiO₂ amount increases from 30 to 90 mol.%. Compared with the samples with higher SiO₂ content, the 30Si sample shows more remarkable internal connected mesoporous structures, with a higher specific surface area up to 129.12 m²/g, exhibiting excellent hydroxyapatite formation in simulated body fluid. Moreover, no obvious inhibitory effect was presented on human periodontal ligament cells (hPDLCs) for any of the silicate glass samples.     

Using graphene networks to build SiC(rGO,Gx) bulk ceramics from polymeric precursors

Unique properties of graphene open new opportunities for preparing composites with favorable functional capabilities. Herein, an ingenious synthesis route via re-pyrolysis process of ball-milling-induced SiC(rGO, Gx)_p fillers/polycarbosilane-vinyltriethoxysilane-graphene oxide (PCS-VTES-GO, PVG) precursors blends is proposed to obtain structural-functional integrated SiC(rGO, Gx) bulk polymer-derived ceramics (PDCs). The introduction of SiC(rGO, Gx)_p provides favorable moldability, ceramic yield and linear shrinkage. Attractively, graphene networks with more free-moving electrical-charge carriers and wider phonon-channel prominently enhance electrical and thermal conductivities of products. Particularly, SiC(rGO, G_20%) bulk PDCs generated at 1300 °C own satisfactory ceramic yield (90.74%), linear shrinkage (5.00%), fracture toughness (2.07 MPa m^1/2), bending strength (35.37 MPa), electrical conductivity (25.72 S cm^?1) and thermal conductivity (6.72 W m^?1·K^?1), realizing outstanding values to the best of our knowledge. This fabrication method favors mass production of larger-sized PDCs and possess potential emerging uses.     

基于相关性分析的OLTC运行状态评价方法研究

在有载调压变压器分接开关(OLTC)动作过程中,监测驱动电机电流信号和切换振动信号并对其进行处理。通过分析信号与OLTC运行状态的关联关系,选取能显著反映OLTC运行状态的重要指标量,并将其处理形成基于正常运行标准值的标准化后的相对值。以每次监测获得的一组指标量为一个样本,通过采集样本与正常样本间的相关性分析,或两组以上的样本中某两个关注样本之间的偏相关性分析,得到相关系数或偏相关系数。以相关系数或偏相关系数作为OLTC运行状态评价的重要参考指标,判断OLTC运行的正常与否及运行状态变化趋势。