基于FRS与GA-ELM的煤与瓦斯突出预测研究

针对煤与瓦斯突出发生内在机理复杂性、致突因素与突出事件之间模糊性导致预测精度不高这一问题,提出将模糊粗糙集理论（FRS）结合改进的极端学习机（ELM）进行煤与瓦斯突出预测。通过FRS信息约简理论降低致突因素原始数据属性维度,提取出致突辅助因素,与主要因素共同作为ELM网络神经元输入,利用遗传算法（GA）对极端学习机网络输入权值、隐含层阈值进行优化,建立GA-ELM预测模型,模型输出为煤与瓦斯突出强度预测结果。经过模型训练和试验验证,该模型泛化能力强、预测精度高、收敛速度明显加快。     

基于局部模型匹配的几何活动轮廓跟踪

目的 在复杂背景下,传统轮廓跟踪方法只考虑了目标的整体特征或显著性特征,没有充分利用目标的局部特征信息,尤其是目标发生遮挡时,容易发生跟踪漂移,甚至丢失目标.针对上述问题,提出一种基于局部模型匹配的几何活动轮廓(LM-GAC)跟踪算法.方法 首先,利用超像素技术将图像中的颜色特征相似的像素点归为一类,形成由一些像素点组成的超像素,从而把目标分割成若干个超像素块,再结合EMD(earth mover's distance)相似性度量构建局部特征模型.然后,进行局部模型匹配,引入噪声模型来估算局部模型参数θ,这样可以增强特征模型的自适应性,提高局部模型匹配的准确性.最后,结合粒子滤波的水平集分割方法提取目标轮廓,实现目标轮廓精确跟踪.结果 本文算法与多种目标轮廓跟踪算法进行对比,在部分遮挡、目标形变、光照变化、复杂背景等条件的基准图像序列均具有较高的跟踪成功率,平均成功率为79.6%.结论 实验结果表明,根据不同的图像序列,可以自适应地实时改变噪声模型参数和粒子的权重,使得本文算法具有较高的准确性和鲁棒性.特别是在复杂的背景下,算法能较准确地进行目标轮廓跟踪.     

融合全局和局部相关熵的图像分割

目的 针对LCK(local correntropy-based K-means)模型对初始轮廓敏感的问题,提出了新的基于全局和局部相关熵的GLCK(global and local correntropy-based K-means)动态组合模型。方法 首先将相关熵准则引入到CV(Chan-Vese)模型中,得到新的基于全局相关熵的GCK(global correntropy-based K-means)模型。然后,结合LCK模型,提出GLCK组合模型,并给出一种动态组合算法来优化GLCK模型。该模型分两步来完成分割:第1步,用GCK模型分割出目标的大致轮廓;第2步,将上一步得到的轮廓作为LCK模型的初始轮廓,对图像进行精确分割。结果 主观上,对自然图像和人工合成图像进行分割,并同LCK模型、LBF模型以及CV模型进行对比,结果表明本文所提模型的鲁棒性比上述模型都要好;客观上,对BSD库中的两幅自然图像进行分割,并采用Jaccard相似性比率进行定量分析,准确率分别为91.37%和89.12%。结论 本文算法主要适用于分割含有未知噪声及灰度分布不均匀的医学图像及结构简单的自然图像,并且分割结果对初始轮廓具有鲁棒性。     

非接触式掌脉图像的点集操作定位法

非接触式手掌静脉采集系统中存在诸多干扰因素影响感兴趣区域定位的准确性.为了克服干扰,提高认证性能,将“点集操作”引入掌脉图像的预处理中,直接实现针对区域的分析和处理.通过对分割手掌区域点集进行平移、交、并运算,获取手掌指根区域,即指根点集.然后根据约束条件对指根点集元素进行筛选,得到四个指根点的准确位置.根据指根点建立相应坐标系,动态定位感兴趣区域.实验对比证明,上述方法具有更优的抗干扰能力和定位准确性.     

民航旅客服务信息系统报警规则提取

在民航客服报警系统优化设计的研究中,民航旅客服务信息系统承载民航大量的重要业务,结构庞杂,系统安全运行要求高,某个子系统出现异常,会产生大量的告警信息,给维护人员对故障源定位带来极大困难。实现报警信息的提取和压缩,对系统维护来说是要急需解决的问题。针对上述问题,利用粗糙集的理论对抽取的报警信息生成决策表,并对其进行属性约简和值约简,提取报警规则。通过实验取得了比较有效精简的报警规则,将报警信息准确提供给系统维护人员,另外对报警规则进行实验验证,能对系统进行准确的报警,实现报警信息处理的初步的智能化。     

Input‐output triggered control using ‐stability over finite horizons

This paper investigates stability of nonlinear control systems under intermittent information. Following recent results in the literature, we replace the traditional periodic paradigm, where the up‐to‐date information is transmitted and control laws are executed in a periodic fashion, with the event‐triggered paradigm. Building on the small gain theorem, we develop input–output triggered control algorithms yielding stable closed‐loop systems. In other words, based on the currently available (but outdated) measurements of the outputs and external inputs of a plant, a mechanism triggering when to obtain new measurements and update the control inputs is provided. Depending on the noise in the environment, the developed algorithm yields stable, asymptotically stable, and ‐stable (with bias) closed‐loop systems. Control loops are modeled as interconnections of hybrid systems for which novel results on ‐stability are presented. The prediction of a triggering event is achieved by employing ‐gains over a finite horizon. By resorting to convex programming, a method to compute ‐gains over a finite horizon is devised. Finally, our approach is successfully applied to a trajectory tracking problem for unicycles. Copyright © 2014 John Wiley & Sons, Ltd.     

An analysis of the exponential stability of linear stochastic neutral delay systems

This paper is concerned with the analysis of the mean square exponential stability and the almost sure exponential stability of linear stochastic neutral delay systems. A general stability result on the mean square and almost sure exponential stability of such systems is established. Based on this stability result, the delay partitioning technique is adopted to obtain a delay‐dependent stability condition in terms of linear matrix inequalities (LMIs). In obtaining these LMIs, some basic rules of the Ito calculus are also utilized to introduce slack matrices so as to further reduce conservatism. Some numerical examples borrowed from the literature are used to show that, as the number of the partitioning intervals increases, the allowable delay determined by the proposed LMI condition approaches h_max, the maximal allowable delay for the stability of the considered system, indicating the effectiveness of the proposed stability analysis. Copyright © 2013 John Wiley & Sons, Ltd.     

Exponential stability of stochastic singular delay systems with general Markovian switchings

In recent years, Markovian jump systems have received much attention. However, there are very few results on the stability of stochastic singular systems with Markovian switching. In this paper, the discussed system is the stochastic singular delay system with general transition rate matrix in terms of uncertain and partially unknown transition rate matrix. The aim is to answer the question whether there are conditions guaranteeing the underlying system having a unique solution and being exponentially admissible simultaneously. The proposed results show that all the features of the underlying system such as time delay, diffusion, and general Markovian switchings play important roles in the system analysis of exponential admissibility. A numerical example is used to demonstrate the effectiveness of the proposed methods. Copyright © 2014 John Wiley & Sons, Ltd.     

Target point‐based path‐following controller for a car‐type vehicle using bounded controls

In this paper, we have studied the control problem of target point‐based path following for car‐type vehicles. This special path‐following task arises from the needs of vision‐based guidance systems, where a given target point located ahead of the vehicle, in the visual range of the camera, must follow a specified path. A solution to this problem is developed through a nonlinear transformation of the path‐following problem into a reference trajectory tracking problem, by modeling the target point as a virtual vehicle. The use of target point complicates the control problem, as the development produces a first‐order nonlinear nonglobally Lipschitz differential equation with finite escape time. This problem is solved by using small control signals. Bounded feedback laws are designed to control the real vehicle's angular acceleration and the virtual vehicle's velocity, to achieve stability. The resulting controller is globally asymptotically stable with respect to the origin, the proof of which is derived from Lyapunov‐based arguments and a bootstrap argument. It is also shown that the use of exponentially convergent observers/differentiators does not affect the stability of the closed‐loop system. The effectiveness of this controller has been illustrated through simulations. Copyright © 2014 John Wiley & Sons, Ltd.     

Asymptotic stability in probability and stabilization for a class of discrete‐time stochastic systems

This paper investigates asymptotic stability in probability and stabilization designs of discrete‐time stochastic systems with state‐dependent noise perturbations. Our work begins with a lemma on a special discrete‐time stochastic system for which almost all of its sample paths starting from a nonzero initial value will never reach the origin subsequently. This motivates us to deal with the asymptotic stability in probability of discrete‐time stochastic systems. A stochastic Lyapunov theorem on asymptotic stability in probability is proved by means of the convergence theorem of supermartingale. An example is given to show the difference between asymptotic stability in probability and almost surely asymptotic stability. Based on the stochastic Lyapunov theorem, the problem of asymptotic stabilization for discrete‐time stochastic control systems is considered. Some sufficient conditions are proposed and applied for constructing asymptotically stable feedback controllers. Copyright © 2014 John Wiley & Sons, Ltd.