Evolving artificial neural network ensembles

Using a coordinated group of simple solvers to tackle a complex problem is not an entirely new idea. Its root could be traced back hundreds of years ago when ancient Chinese suggested a team approach to problem solving. For a long time, engineers have used the divide-and-conquer strategy to decompose a complex problem into simpler sub-problems and then solve them by a group of solvers. However, knowing the best way to divide a complex problem into simpler ones relies heavily on the available domain knowledge. It is often a manual process by an experienced engineer. There have been few automatic divide-and-conquer methods reported in the literature. Fortunately, evolutionary computation provides some of the interesting avenues to automatic divide-and-conquer methods. An in-depth study of such methods reveals that there is a deep underlying connection between evolutionary computation and ANN ensembles. Ideas in one area can be usefully transferred into another in producing effective algorithms. For example, using speciation to create and maintain diversity had inspired the development of negative correlation learning for ANN ensembles, and an in-depth study of diversity in ensembles. This paper will review some of the recent work in evolutionary approaches to designing ANN ensembles.     

带材位置自动对中系统的工作原理及应用

本文详细介绍了金属带材轧机带材位置自动对中系统的工作原理、电路组成及调试方法。     

Programmable group-delay module using binary polarization switching

We demonstrate the first programmable group-delay module based on polarization switching. With a unique binary tuning mechanism, the device can generate any differential group delay value from -45 to +45 ps with a resolution of 1.40 ps, or any true-time-delay value from 0 to 45 ps with a resolution of 0.7 ps. The delay varying speeds for both applications are under 1 ms and can be as fast as 0.1 ms. We evaluate both the dynamic and static performances of the device while paying special attention to its dynamic figures of merit for polarization-mode dispersion emulation and compensation applications. Our experiment shows that the device exhibits a negligible transient-effect induced power penalty (<0.2 dB) in a 10-Gb/s nonreturn-to-zero system.     

分割电极片状压电致动器——(二)位移特性及狭缝宽度对其影响的实验研究

研究了悬臂梁式分割电极片状压电致动器的位移特性。理论分析表明，分割电极狭缝宽度会减小致动器自由端的位移输出，但当狭缝宽度小于致动器电极宽度的１０％时，可忽略狭缝宽度的影响。致动器端部位移的测试结果大于理论计算值。与现有磁头悬浮臂尺寸相近的致动器，在２０Ｖ～５０Ｖ的电压驱动下均可获得１μｍ～２μｍ的致动位移。对９８５０道／厘米的密度磁盘，该位移能覆盖至少一个磁道宽度，满足磁头定位两级伺服系统对第二级致动器位移的基本要求。     

关于Ada95变体部分等语法的修正意见

本文指出了Ａｄａ９５ 参考手册中记录变体部分、记录聚集、分情形语句与异常处理段等语法描述中存在的问题，并分别给出了它们的修正方案。     

多孔挡板流化床还原UO3反应器模型的研究

针对ＵＯ＿３的Ｎ＿２还原反应建立了多孔挡板流化床反应器模型。将多孔挡板床的每一级视为具有相似的流动状态，每一级的上、下段称为稀、密相段，分别用鼓泡床和活塞流模型描述。该模型的计算值与￠６３ｍｍ的多孔挡板床Ｈ＿２还原ＵＯ＿３的热态实验值能较好的吻合。还预计了还原温度、操作气速和挡板结构参数对固相转化率的影响，为该类反应器的工业设计、放大和优化提供了依据。     

Pore size control of porous silica by sol-gel process

Porous silica glass was prepared by sol-gel process from tetraethoxysilane (TEOS). The effects of solvents (water, ethanol), drying condition, heat treatment temperature on specific surface area and pore size distribution of porous silica were investigated. Gelation process accelerates with an increase of H₂O content, while retards with the increase of ethanol amount. Structure changes during heat treatment were studied by means of DTA, XRD. TEM micrographs show that the gel particles shrink after heated at 500°C, thus the average pore size decreases.