Multiobjective PSO based adaption of neural network topology for pixel classification in satellite imagery

The proposed work involves the multiobjective PSO based adaption of optimal neural network topology for the classification of multispectral satellite images. It is per pixel supervised classification using spectral bands (original feature space). This paper also presents a thorough experimental analysis to investigate the behavior of neural network classifier for given problem. Based on 1050 number of experiments, we conclude that following two critical issues needs to be addressed: (1) selection of most discriminative spectral bands and (2) determination of optimal number of nodes in hidden layer. We propose new methodology based on multiobjective particle swarm optimization (MOPSO) technique to determine discriminative spectral bands and the number of hidden layer node simultaneously. The accuracy with neural network structure thus obtained is compared with that of traditional classifiers like MLC and Euclidean classifier. The performance of proposed classifier is evaluated quantitatively using Xie-Beni and β indexes. The result shows the superiority of the proposed method to the conventional one.     

Quadratic control of stochastic hybrid systems with renewal transitions

We study the quadratic control of a class of stochastic hybrid systems with linear continuous dynamics for which the lengths of time that the system stays in each mode are independent random variables with given probability distribution functions. We derive a condition for finding the optimal feedback policy that minimizes a discounted infinite horizon cost. We show that the optimal cost is the solution to a set of differential equations with unknown boundary conditions. Furthermore, we provide a recursive algorithm for computing the optimal cost and the optimal feedback policy. The applicability of our result is illustrated through a numerical example, motivated by stochastic gene regulation in biology.     

Z源逆变器光伏发电系统变量调制范围随动的两级控制研究

Z源逆变器光伏发电系统是一种具有升/降压功能的单级系统,可以通过调节直通占空比实现前级光伏电池的最大功率跟踪（MPPT）控制,然后由逆变器调制因子m实现并网控制.提出了一种直通占空比调制范围上限随动的两级控制策略.该策略兼顾了两级控制和单级控制的优点：充分利用了直通零矢量,使逆变器的调制因子m增大,直流电压利用率高,相应的有源器件的电压应力和逆变器输出电流谐波得到很大地改善;消除了光伏电池和电网之间的影响.仿真和实验结果验证了理论分析的正确性与实用性.     

轮胎压力智能检测与预警系统的设计

在充分考虑降低轮胎压力检测系统的功耗,减小轮胎压力检测系统的质量和体积的基础上,应用传感器技术、微电子技术、嵌入式技术和射频通信技术等设计了一种新型的轮胎压力智能检测与预警系统;在系统设计上采用模块化思想,主要包括了信号采集、基站与端机的设计、射频通信模块的设计、显示和键盘模块的设计和数据处理等;轮胎压力智能检测和预警系统可以明显的提高汽车行驶的平缓性、安全性和舒适性,具有非常广泛的应用前景.     

驾驶模拟系统人机界面的真实性评价

驾驶模拟系统是进行各项交通研究的有效手段和工具.详细描述了基于驾驶模拟器和Quest3D自行开发的驾驶模拟系统体系结构,着重介绍了其视觉呈现、听觉混成、体感模拟等模块组成的人机界面的设计,并采用综合分析法对系统人机界面的真实性进行了综合评价.结果表明,本文实现的驾驶模拟系统所建立的虚拟驾驶环境符合真实环境,其真实性能满足相关研究的需求.     

土-结构相互作用系统地震动力特性的突变理论分析

地震荷载作用下,将土和结构作为一个系统,可较好体现地震作用下结构动力特性的影响.对一个简单的土-结构相互作用系统模型,计算了其动能和形变能,通过拉格朗日方程导得对土-结构相互作用系统的运动方程,并将其归结为以结构振幅为状态变量的尖点突变模型,来对结构的动力特性进行分析.尖点突变模型的对应性状表明,非线性弹簧使系统具有可变频特性,使得地震作用下的土-结构相互作用系统不发生线性系统中的"共振"现象;当系统频率变化使控制点(u,v)跨越尖点突变模型分叉集时,结构的振幅和振动相位会发生突变,并且结构振幅的突变值随地震频率而变,也即地震频率变化对土-结构相互作用系统动力特性的影响有"路径"效应.     

基于电磁场的无刷直流电动机转子结构优化

利用电磁场有限元法，对目前无刷直流电动机本体普遍采用的表面式结构进行分析，结合电磁场分析结果，提出了改进电机转子结构的方法，并给出了优化后几个主要尺寸的实用工程算法。     

时滞离散广义不确定系统的变结构控制

研究了一类线性离散时滞广义不确定系统的变结构控制的综合与设计问题.首先引入了一种新的受限系统等价分解形式,把所给的系统分解成两个低维的不确定子系统.其次,在上述分解的基础上,根据离散时滞广义系统鲁棒稳定性的有关结果,设计了带有差分补偿器的切换函数,使得系统在准切换流形上的运动渐近稳定.然后设计了离散变结构控制律,使得在此控制律的作用下,系统的运动轨迹要么在有限步内到达准切换流形并在其上渐近滑向原点;要么在有限步内进入准切换流形的一个较小的邻域内并稳定于原点附近的某个小的抖振.最后，给出了两个数值例子以说明该综合设计方法的有效性与实用性.     

Comparison of spherical and truncated cone geometries for single abrasive-grain cutting

The purpose of the present work was to compare the cutting action of two different abrasive-grain geometries using experimental observations and a validated finite element model. A spherical tool was used to approximate a dull abrasive grain while a truncated cone tool was used to approximate an abrasive grain with a well defined cutting edge. The selected geometries were chosen to represent extreme cases in order to bracket the cutting action of a range of cutting geometries. The results showed that both tools produced similar normal and tangential forces per unit width up to a depth of cut of approximately 3 μm. The improved cutting geometry of the truncated cone tool caused the normal force per unit width to decrease and the tangential force per unit width to increase in relation to the spherical tool. The truncated cone tool was shown to experimentally and numerically be more efficient based on the reduced pile-up heights and improved stress distributions. It was also shown that both geometries converged towards the same specific energy to displace material at suitably large depths of cut, which suggests that there is a minimum specific energy obtainable for a given workpiece material that is independent of the grain geometry. However, specific energies to remove material were higher for the spherical tool as compared to the truncated cone tool. Analysis of the energy components of the finite element model showed that frictional energy contributions were high with the spherical tool and low with the truncated cone tool. Finally, it was found that both tools required approximately the same energy to shear a chip from a workpiece when friction was subtracted from the specific energy for material removal.