基于粒子群优化的模糊聚类分析

基于求解实优化问题时,粒子群优化算法优于遗传算法。在基于遗传算法的模糊C均值聚类算法基础上,给出了基于粒子群的模糊C均值聚类算法,试验结果表明:该算法克服了传统的模糊C均值聚类算法的缺陷,同时在收敛速度方面明显优于基于遗传算法的模糊C均值聚类算法。     

An intelligent service matching method for mechanical equipment condition monitoring using the fibre Bragg grating sensor network

Due to the advantages of being able to function under harsh environmental conditions and serving as a distributed condition information source in a networked monitoring system, the fibre Bragg grating (FBG) sensor network has attracted considerable attention for equipment online condition monitoring. To provide an overall conditional view of the mechanical equipment operation, a networked service-oriented condition monitoring framework based on FBG sensing is proposed, together with an intelligent matching method for supporting monitoring service management. In the novel framework, three classes of progressive service matching approaches, including service-chain knowledge database service matching, multi-objective constrained service matching and workflow-driven human-interactive service matching, are developed and integrated with an enhanced particle swarm optimisation (PSO) algorithm as well as a workflow-driven mechanism. Moreover, the manufacturing domain ontology, FBG sensor network structure and monitoring object are considered to facilitate the automatic matching of condition monitoring services to overcome the limitations of traditional service processing methods. The experimental results demonstrate that FBG monitoring services can be selected intelligently, and the developed condition monitoring system can be re-built rapidly as new equipment joins the framework. The effectiveness of the service matching method is also verified by implementing a prototype system together with its performance analysis.     

基于分辨力增益的综合识别传感器管理方法

为提高目标综合识别的效能,需对综合识别系统中多种传感器资源进行科学管 理。在分析综合识别中目标优先级和传感器使用约束条件的基础上,建立了利用分辨力增益 作为传感器资源管理优化准则的目标函数,提出了利用传感器混淆矩阵的预测分辨力增益计 算方法,并将粒子群优化算法引入传感器-目标分配NP-hard问题的求解中。仿真结果表明该 方法合理高效。     

基于PSO的信息熵数据融合非均匀分簇路由算法

针对无线传感器网络分簇算法中能量分布不均衡导致的"热区"和簇头负载过重问题,提出了一种基于PSO算法优化簇头选举的非均匀分簇算法。在候选簇头选举和竞争半径计算过程中综合考虑节点动态能量、节点密度和节点距基站距离,将网络进行非均匀分簇,并引入PSO算法进行最终簇头选举。根据节点能量、节点密度和距基站距离确定簇间单跳多跳结合的路由规则,选取代价函数小的节点作为下一跳节点。基于节点信息熵确定融合阈值,进行簇内数据融合剔除冗余数据。仿真结果表明,改进算法的数据传输量比EEUC算法和UCRA算法分别提高了20%和10%,提升了数据的融合效率,有效延长了网络生命周期,簇头能量消耗得到均衡,减少了网络能量消耗,网络的整体性能显著优于其他对比算法。     

基于PSO算法的股权拍卖机制设计及仿真分析

运用PSO群体智能算法模拟信息交互条件下外部投资者报价决策的学习机制和演化规律,在此基础上设计了实现风险投资退出的股权拍卖机制。Netlog仿真结果表明,所设计的股权拍卖机制能在一定程度上揭示股权的真实价值,并降低竞买人和卖方之间的信息不对称程度。进一步的仿真分析结果表明:适当的激励力度对外部投资者的投标报价具有显著影响;引入更多的竞买人能产生更有利于风险投资家的拍卖结果;即使外部投资者过于强化单一的学习能力,最终也可得到相对理想的拍卖结果,从而证明了所设计的股权拍卖机制具有广泛的适用性。     

Service load balancing,task scheduling and transportation optimisation in cloud manufacturing by applying queuing system

Recently, there is a great deal of attention in Cloud Manufacturing (CMfg) as a new service-oriented manufacturing paradigm. To integrate the activities and services through a CMfg, both Service Load balancing and Transportation Optimisation (SLTO) are two major issues to ease the success of CMfg. Based on this motivation, this study presents a new queuing network for parallel scheduling of multiple processes and orders from customers to be supplied. Another main contribution of this paper is a new heuristic algorithm based on the process time of the tasks of the orders (LBPT) to solve the proposed problem. To formulate it, a novel multi-objective mathematical model as a Mixed Integer Linear Programming (MILP) is developed. Accordingly, this study employs the multi-choice multi-objective goal programming with a utility function to model the introduced SLTO problem. To better solve the problem, a Particle Swarm Optimisation (PSO) algorithm is developed to tackle this optimisation problem. Finally, a comparative study with different analyses through four scenarios demonstrates that there are some improvements on the sum of process and transportation costs by 6.1%, the sum of process and transportation times by 10.6%, and the service load disparity by 48.6% relative to the benchmark scenario.     

非线性互补问题计算机实现

分析了非线性互补问题求解困难，利用粒子群算法并结合极大熵函数法给出了该类问题的一种新的有效算法。该算法首先利用极大熵函数将非线性互补问题转化为一个无约束最优化问题，然后应用粒子群算法来优化该问题，计算机程序实现表明该算法是有效的。     

Evolving Purchasing and Supply Organizations: A contingency model for structural alternatives

Purchasing and Supply Management (PSM) is under significant pressure to find levers to further increase its contribution to corporate goals. In order to improve performance in line with expectations, Purchasing and Supply Organizations (PSOs) have to evolve continuously. To help address this challenge, a comprehensive contingency framework of PSO structures is presented. The framework is based on existing literature on PSO contingency factors as well as analysis of two case companies. The findings highlight the importance of taking a contingency perspective for understanding the PSO and combining a detailed view of macro-level structural dimensions with micro-level characteristics. These macro-level dimensions comprise category, business unit, geography and activity. The micro-level characteristics comprise centralization, formalization, specialization, participation and standardization. From a theoretical perspective, the contingency framework opens up insights that can be leveraged in future studies in the fields of hybrid PSOs, global sourcing organizations, and International Purchasing Offices (IPOs). From a practical standpoint, an assessment of external and internal contingencies and their relation to specific structural dimensions and characteristics provides the opportunity for more consciously evolving the PSO to continue to improve PSM's contribution.     

粒子群优化算法的研究现状与发展概述

粒子群优化算法(PSO)是基于群体智能的一种优化算法。该算法简单易于实现,可调参数少,得到了广泛的研究和飞速发展。介绍了PSO提出的背景、PSO的思想和原理,分析并总结了PSO的优缺点。根据PSO算法研究侧重点的不同,总结了PSO算法的发展现状及特点,分析并展望了PSO还需要完善或继续研究的问题,展望了PSO的研究热点及发展趋势。     

一种新的基于粒子群密度的聚类算法

提出了一种新的粒子群密度聚类算法和对粒子群的初始化方法。该算法具有传统粒子群算法寻找最优解的特点,同时从密度的角度考虑了数据总体的分布,增强了寻找局部最优解的能力,并通过对粒子群的初始化加快了粒子群的收敛速度,得到了更好的聚类效果。对仿真数据和IRIS真实数据的实验结果证明,该算法聚类效果优于传统粒子群聚类算法和K均值算法。