Yarn Properties Prediction Based on Machine Learning Method

Although many works have been done to constructprediction models on yarn processing quality, the relationbetween spinning variables and yam properties has not beenestablished conclusively so far. Support vector machines(SVMs), based on statistical learning theory, are gainingapplications in the areas of machine learning and patternrecognition because of the high accuracy and goodgeneralization capability. This study briefly introduces theSVM regression algorithms, and presents the SVM basedsystem architecture for predicting yam properties. Model.selection which amounts to search in hyper-parameter spaceis performed for study of suitable parameters with grid-research method. Experimental results have been comparedwith those of artificial neural network(ANN) models. Theinvestigation indicates that in the small data sets and real-life production, SVM models are capable of remaining thestability of predictive accuracy, and more suitable for noisyand dynamic spinning process.     

Stability analysis of BAM neural networks with time-varying delays

Some new criteria for the global asymptotic stability of the equilibrium point for the bi-directional associative memory neural networks with time varying delays are presented. The obtained results present the structure of linear matrix inequality which can be solved efficiently. The comparison with some previously reported results in the literature demonstrates that the results in this paper provide one more set of criteria for determining the stability of the bi-directional associative memory neural networks with delays.     

基于关系矩阵的复合宽边界区域拓扑关系计算

简单宽边界区域拓扑关系计算比较简单,而复合宽边界区域拓扑关系计算比较复杂,因而需要一个计算方法以实现复合宽边界区域拓扑关系计算、查询和分析处理。在分析复合宽边界区域与简单宽边界区域关系联系的基础上,研究了根据复合宽边界区域中简单宽边界区域拓扑关系矩阵计算复合宽边界区域拓扑关系的方法,并根据复合宽边界区域的性质,简化了算法。计算方法使得扩展九交模型不再是一个概念模型,而是可计算的,从而为查询和分析处理宽边界区域拓扑关系奠定了基础。     

Microstructure and Corrosion Resistance of Cr7C3/γ-Fe Ceramal Composite Coating Fabricated by Plasma Cladding

A new type in situ Cr7C3/γ-Fe ceramal composite coating was fabricated on substrate of hardened and tempered grade C steel by plasma cladding with Fe-Cr-C alloy powders. The ceramal composite coating has a rapidly solidified microstructure consisting of primary Cr7C3/γ- and the Cr7C3/γ-Fe eutectics, and is metallurgically bonded to the degree C steel substrate. The corrosion resistances of the coating in water solutions of 0.5 mol/L H2SO4 and 3.5% NaCl were evaluated utilizing the electrochemical polarization corrosion-test method. Because of the inherent excellent corrosion-resisting properties of the constituting phase and the rapidly solidified homogeneous microstructure, the plasma clad ceramal composite coating exhibits excellent corrosion resistance in the water solutions of 0.5 mol/L H2SO4 and 3.5% NaCl.     

绢丝/化纤长丝Sirofil复合纱扭转性能

在自制纱线扭矩-捻度装置（扭力秤法）上对绢丝／锦纶长丝、绢丝／涤纶长丝Sirofil复合纱的扭矩及其扭矩松弛行为进行测试分析，探讨其扭矩及其扭矩松弛率与复合纱纺纱捻度和纺纱间距间的关系，为这类仿丝型Sirofil复合纱的加工、应用提供实验依据和参考．     

两种新型石油磺酸盐基复合驱油剂的研制

为提高驱油剂降低油水界面张力的能力,提高原油的采收率,在研究了石油磺酸盐表面活性剂表面活性的基础上,研制了改性纳米二氧化硅-石油磺酸盐和磺酸盐型Gemini-石油磺酸盐两种复合驱油剂,采用TX-500界面张力仪考察了两种复合驱油剂降低胜利油田油水界面张力的能力。研究表明,在一定的浓度条件下,石油磺酸盐能降低油水界面张力至1×10-2mN.m-1,改性纳米二氧化硅-石油磺酸盐复合驱油剂能降低油水界面张力至3.2×10-3mN.m-1,磺酸盐型Gemini-石油磺酸盐复合驱油剂能降低油水界面张力至(4~6)×10-4mN.m-1。与传统驱油剂相比,两种复合驱油剂降低油水界面张力的能力显著提高。     

离散Hopfield神经网络在混烧控制系统故障诊断中的应用

给出了离散Hopfield神经网络结构和模型．利用Hopfield神经网络的演变过程是一种计算联想记忆的过程,它适用于正交(或近似正交)模式的记忆性质,给出了一种Hopfield神经网络的双向联想记忆模式的记忆矩阵构造方法,并提出了一种改进的基于Hopfield神经网络的控制系统故障诊断的算法,利用此算法实现实时检测混烧控制系统的故障和异常,对混烧控制系统的调节器和阀门进行故障诊断和故障信息提示．     

Active Vibration Isolation System for Sub-microultra-precision Turning Machine

Now vibration isolation of ultra-precision machine tool is usually achieved through air-springs systems. As far as HCM-I sub-micro turning machine developed by HIT, an active vibration isolation system that consists of air-springs and electro-magnetic actuators was presented. The primary function of air-springs is to support the turning machine and to isolate the high-frequency vibration. The electro-magnetic actuators controlled by fuzzy-neural networks isolate the low-frequency vibration. The experiment indicates that active vibration isolation system isolates base-vibration effectively in all the frequency range. So the vibration of the machine bed is controlled under 10-6g and the surface roughness is improved.     

Coverability of Wireless Sensor Networks

The coverability of Wireless Sensor Networks (WSNs) is essentially a Quality of Service (QoS) problem that measures how well the monitored area is covered by one or more sensor nodes.The coverability of WSNs was examined by combining existing computational geometry techniques such as the Voronoi diagram and Delaunay triangulation with graph theoretical algorithmic techniques.Three new evaluation algorithms,known as CRM (Comprehensive Risk Minimization),TWS (Threshold Weight Shortest path),and CSM (Comprehen...     

具有随机性的确定性网络模型

为了进一步研究复杂网络的统计特性,简单介绍了复杂网络的几个统计指标,给出了一种通过边的迭代方式生成一种确定性网络模型的方法.在此模型构造算法的基础上对网络的个别特性进行了推导,并通过计算机编程构造了模拟网络,对比了不同规模模拟网络的部分统计特性.由推导结果和模拟数据可知,迭代生成的网络具有较小的平均路径长度和较大的群聚系数,度分布服从指数分布.因此可判断出生成的确定性网络既具有小世界特性,又具有完全随机网络的特性.