蚁群参数自适应调整的优化设计*

介绍了蚁群优化算法利用粗搜索及精搜索过程获得多维有约束函数优化的基本思想,分析了影响蚁群优化多维有约束函数问题的关键参数,给出了获得较好的蚁群函数优化性能必须在优化过程中动态的自适应地调整蚁群优化算法的关键参数 及 的指导性结论,且调整的规则是 与 的值由大到小的调整,而 的值将由小到大的调整。建立了 及 的模糊动态调整器,给出了3个模糊控制器的参数调整过程、控制器的执行策略及控制过程。采用起重机主梁优化实例对比验证了蚁群优化算法及蚁群参数自适应调整的优化算法。结果表明,采用蚁群参数自适应调整的优化算法具有求解精度高、优化效率高及参与优化的蚁群数量少等优点,该方法是求解复杂多峰函数优化的一种极好的优化方法。     

基于蚁群算法的模糊控制规则的过滤简化

针对设计高维模糊控制器过程中会遇到的“规则爆炸”问题，利用蚁群算法进行控制规则的过滤简化。为了用尽量少的规则得到尽可能好的控制效果，利用蚁群算法在饵决组合优化问题中的强大优势，在已有的完备规则中优选出若干条规则嵌人模糊控制器。采用带有时间窗口的蚁群算法去克服遗传算法优选模糊控制规则时可能产生的规则不连续的问题。该文还从遗传算法和蚁群算法工作机制的角度分析了对这两种算法加入约束条件的可操作性。以单级倒立摆控制系统为对象进行仿真研究，最后的仿真结果表明该文方法可以使模糊控制规则具有更好的简化效果和鲁棒性，并能具有好的控制效果。     

基于多层蚁群算法的变论域模糊控制

针对模糊控制器控制精度不高、自适应能力有限等问题,提出一种变论域自适应模糊控制方式.首先在对离散蚁群算法改进的基础上,提出用于连续域寻优的多层蚁群算法.其通过将解空间分成有限网格,并且算法在迭代过程中采用三个阶段的搜索策略,每个阶段采用异构搜索机制.然后根据系统性能利用改进算法动态调整伸缩因子,从而构成基于多层蚁群算法的变论域自适应模糊控制器.最后将此控制器用于中厚板液压位置伺服系统中.仿真结果表明,采用自适应模糊控制器的伺服系统收敛速度明显加快,此控制策略在适应能力与鲁棒性好于其它控制方式.     

基于蚁群优化的模糊神经网络控制器的应用研究

针对传统PID控制方式的不足,文章提出了一种新的永磁同步电动机控制策略,即采用蚁群优化算法对模糊神经网络控制器的3个因子参数ka、kb、ku进行全局优化,给出了永磁同步电动机的数学模型,详细介绍了模糊神经网络控制器的设计,分析了蚁群优化算法,并进行了仿真实验。仿真结果表明,基于蚁群优化模糊神经网络控制器的永磁同步电动机调速系统具有很强的鲁棒性和自适应性,动态响应快,能够较好地跟踪负载变化。     

改进蚁群神经网络及其在滞后系统中的应用

针对热连轧监控AGC系统具有多变量、强耦合、非线性、大滞后及参数时变的特点,提出了一种改进蚁群神经网络,采用动态局部信息素更新和自适应调节信息素挥发的全局信息素更新相结合的方式对蚁群算法进行了改进。并利用改进后的蚁群算法对神经网络权值和阈值进行优化,利用优化后的神经网络对PID控制器参数进行整定。改进的蚁群算法稳定性好,寻优效率高,避免了神经网络参数陷入局部极小等问题,从而实现大滞后系统的优化控制。仿真结果表明,在监控AGC系统中,在对象的滞后时间发生变化的情况下,基于改进蚁群神经网络的优化控制系统具有动态响应速度较快,对外部扰动具有良好的鲁棒性,使控制品质得到很大的提高。     

基于蚁群算法固定翼无人机PID参数控制方法

针对传统固定翼无人机PID控制器比例、积分和微分参数调节控制精度低,响应速度慢,难以得到最优线性PID参数组合等问题。本文利用蚁群算法寻优搜索对传统PID控制器进行改进,本文将PID参数寻优过程转化为多约束条件组合优化问题,并通过蚁群算法针对PID参数整定多次迭代来进行搜索最优数值路径来更加快速,精确的优化PID线性组合参数值,提高对固定翼的精确PID参数控制。     

一种改进粒子群算法在水轮机控制中的应用

关于水轮发电机控制系统优化问题,水轮发电机组的控制技术对于水轮发电机组稳定工作非常重要。针对保证供电质量,改善调节系统的非线性时滞特性,利用具有局部搜索能力的粒子群算法对水轮发电机组进行模糊PID控制可以确保控制的稳定性。首先,根据水轮发电机组的控制原理和模糊PID控制器的基本结构,提出具有局部搜索能力的改进粒子群算法,利用模糊PID控制器以及采用了改进粒子群算法的模糊PID控制器,用MATLAB软件对水轮发电机组进行优化控制仿真,仿真结果表明采用改进粒子群算法的模糊PID控制器具有最优的控制效果。     

一种基于改进遗传算法的模糊神经网络控制器及其在烧结终点控制中的应用

针对烧结过程这一复杂、多参数耦合的高度非线性系统,融合遗传算法、神经网络和模糊控制的优点,提出一种基于改进遗传算法的模糊神经网络控制方法,并应用于烧结过程终点控制．首先采用遗传算法对给定的模糊神经网络控制器结构参数进行离线优化,然后利用BP算法较强的局部搜索能力和对对象的适应能力,进一步进行参数的在线调整．同时,为解决传统遗传算法早熟和收敛速度慢的问题,从交叉和变异算子、适应度函数选取等方面对遗传算法进行改进．采用精英保留策略,提高了全局搜索性能和收敛速度．仿真结果表明,所提出的控制器优于常规的模糊神经网络控制器(Fuzzy Neural Network Controller, FNNC)．算法的实际应用效果良好,为解决烧结终点控制问题提供了一条新的途径．     

一种新型自适应复合控制器在锂电池充电系统中的应用

为了解决锂电池充电系统的不确定性和参数整定困难的问题,本文提出了一种基于蚁群算法优化的模糊＋变论域模糊PID复合控制器的新方法。该控制器在系统波动频繁时,采用模糊控制使其具有最优的动态性能;当系统进入稳定阶段,采用PID参数自适应的变论域模糊控制以提高准确度。而用蚁群算法对PID参数值进行离线优化,并将优化后的值作为在线调节的初值,使系统更加稳定。将提出的复合控制策略应用于锂电池充电控制系统中。仿真结果表明,该系统具有良好的抗干扰性和鲁棒性。     

蚁群算法优化模糊规则

模糊控制器设计的关键是根据专家经验确定模糊规则。然而,在专家经验难以获取的情况下将无法进行设计,这就要求模糊规则能够自动优化。模糊规则的优化过程为前件选择后件的过程,是一个组合优化问题,本文应用蚁群算法对其进行优化。蚁群算法是一种新型的模拟进化算法,已被广泛且有效的应用到求解复杂的组合优化问题中。仿真结果显示了蚁群算法应用于优化模糊规则的可行性和有效性,扩大了蚁群算法的应用范围,也为模糊控制器的设计提供了新的思路。     

一种并行的多群蚁群算法研究与应用

针对蚁群算法易出现早熟收敛的缺陷,蚁群按照一定比例分解为具有启发信息的多种群,同时利用多核系统发挥蚁群算法并行性,提出一种并行的多群蚁群算法。该算法在初始化蚁群时产生带有启发信息的多种群,多种群采用多核系统并行处理方式相对独立求解最短路径。在求解过程中每个群体可分享路径信息,当某个种群求解到最短路径时即生成整个群体全局最短路径,从而保证种群多样性,算法求解速率及全局搜索均衡性。实验以Visual Studio2005中C＋＋编程实现仿真,结果表明此算法不但能有效求解GIS的最短路径,而且综合改善了算法性能。     

A study of fuzzy control with ant colony algorithm used in mobile robot for shortest path planning and obstacle avoidance

Microsystem Technologies - The fuzzy ant colony optimization (FACO) method proposed in this paper minimizes the iterative learning error of the ant colony optimization (ACO) algorithm using fuzzy...     

Multi-satellite control resource scheduling based on ant colony optimization

The multi-satellite control resource scheduling problem (MSCRSP) is a kind of large-scale combinatorial optimization problem. As the solution space of the problem is sparse, the optimization process is very complicated. Ant colony optimization as one of heuristic method is wildly used by other researchers to solve many practical problems. An algorithm of multi-satellite control resource scheduling problem based on ant colony optimization (MSCRSP–ACO) is presented in this paper. The main idea of MSCRSP–ACO is that pheromone trail update by two stages to avoid algorithm trapping into local optima. The main procedures of this algorithm contain three processes. Firstly, the data get by satellite control center should be preprocessed according to visible arcs. Secondly, aiming to minimize the working burden as optimization objective, the optimization model of MSCRSP, called complex independent set model (CISM), is developed based on visible arcs and working periods. Ant colony algorithm can be used directly to solve CISM. Lastly, a novel ant colony algorithm, called MSCRSP–ACO, is applied to CISM. From the definition of pheromone and heuristic information to the updating strategy of pheromone is described detailed. The effect of parameters on the algorithm performance is also studied by experimental method. The experiment results demonstrate that the global exploration ability and solution quality of the MSCRSP–ACO is superior to existed algorithms such as genetic algorithm, iterative repair algorithm and max–min ant system.     

A fast recursive algorithm based on fuzzy 2-partition entropy approach for threshold selection

The fuzzy c-partition entropy approach for threshold selection is an effective approach for image segmentation. The approach models the image with a fuzzy c-partition, which is obtained using parameterized membership functions. The ideal threshold is determined by searching an optimal parameter combination of the membership functions such that the entropy of the fuzzy c-partition is maximized. It involves large computation when the number of parameters needed to determine the membership function increases. In this paper, a recursive algorithm is proposed for fuzzy 2-partition entropy method, where the membership function is selected as S-function and Z-function with three parameters. The proposed recursive algorithm eliminates many repeated computations, thereby reducing the computation complexity significantly. The proposed method is tested using several real images, and its processing time is compared with those of basic exhaustive algorithm, genetic algorithm (GA), particle swarm optimization (PSO), ant colony optimization (ACO) and simulated annealing (SA). Experimental results show that the proposed method is more effective than basic exhaustive search algorithm, GA, PSO, ACO and SA.     

改进的模糊C-均值聚类算法

为了克服模糊C-均值（FCM）聚类算法易陷入局部极小值和对初始值敏感的缺点,提出了一种基于改进量子蚁群的模糊聚类算法。将量子计算原理和蚁群算法相结合来改进FCM算法。初期采用量子遗传算法生成信息素分布,后期利用蚁群算法的全局搜索性、并行计算性等特点避免聚类陷入局部最优解。实验证明该算法保证了种群的多样性,有较好的全局收敛性,克服了模糊C-均值聚类算法的不足,能有效解决未成熟收敛的问题,使聚类问题最终快速、有效地收敛到全局最优解。     

模糊相关机会规划的蚁群优化算法及收敛性分析

模糊相关机会规划(Fuzzy dependent-chance programming, FDCP)因其非线性、非凸性及模糊性,对经典的优化理论提出了极大的挑战. 本文为解决复杂的模糊相关机会规划问题设计了一种基于模糊模拟的蚁群优化算法, 证明了该算法的收敛性,并通过估算期望收敛时间以分析蚁群优化算法的收敛速度. 数值案例研究验证了该算法的有效性、稳定性及准确性.     

A NEW HYBRID ALGORITHM FOR MULTI-OBJECTIVE DISTRIBUTION FEEDER RECONFIGURATION

This article proposes an efficient hybrid algorithm for multi-objective distribution feeder reconfiguration. The hybrid algorithm is based on the combination of discrete particle swarm optimization (DPSO), ant colony optimization (ACO), and fuzzy multi-objective approach called DPSO-ACO-F. The objective functions are to reduce real power losses, deviation of nodes voltage, the number of switching operations, and the balancing of the loads on the feeders. Since the objectives are not the same, it is not easy to solve the problem by traditional approaches that optimize a single objective. In the proposed algorithm, the objective functions are first modeled with fuzzy sets to calculate their imprecise nature and then the hybrid evolutionary algorithm is applied to determine the optimal solution. The feasibility of the proposed optimization algorithm is demonstrated and compared with the solutions obtained by other approaches over different distribution test systems.     

Fuzzy entropy based optimal thresholding using bat algorithm

Image segmentation is a very significant process in image analysis. Much effort based on thresholding has been made on this field as it is simple and intuitive, commonly used thresholding approaches are to optimize a criterion such as between-class variance or entropy for seeking appropriate threshold values. However, a mass of computational cost is needed and efficiency is broken down as an exhaustive search is utilized for finding the optimal thresholds, which results in application of evolutionary algorithm and swarm intelligence to obtain the optimal thresholds. This paper considers image thresholding as a constrained optimization problem and optimal thresholds for 1-level or multi-level thresholding in an image are acquired by maximizing the fuzzy entropy via a newly proposed bat algorithm. The optimal thresholding is achieved through the convergence of bat algorithm. The proposed method has been tested on some natural and infrared images. The results are compared with the fuzzy entropy based methods that are optimized by artificial bee colony algorithm (ABC), genetic algorithm (GA), particle swarm optimization (PSO) and ant colony optimization (ACO); moreover, they are also compared with thresholding methods based on criteria of between-class variance and Kapur's entropy optimized by bat algorithm. It is demonstrated that the proposed method is robust, adaptive, encouraging on the score of CPU time and exhibits the better performance than other methods involved in the paper in terms of objective function values.     

An efficient hybrid approach based on PSO, ACO and k-means for cluster analysis

Clustering is a popular data analysis and data mining technique. A popular technique for clustering is based on k-means such that the data is partitioned into K clusters. However, the k-means algorithm highly depends on the initial state and converges to local optimum solution. This paper presents a new hybrid evolutionary algorithm to solve nonlinear partitional clustering problem. The proposed hybrid evolutionary algorithm is the combination of FAPSO (fuzzy adaptive particle swarm optimization), ACO (ant colony optimization) and k-means algorithms, called FAPSO-ACO–K, which can find better cluster partition. The performance of the proposed algorithm is evaluated through several benchmark data sets. The simulation results show that the performance of the proposed algorithm is better than other algorithms such as PSO, ACO, simulated annealing (SA), combination of PSO and SA (PSO–SA), combination of ACO and SA (ACO–SA), combination of PSO and ACO (PSO–ACO), genetic algorithm (GA), Tabu search (TS), honey bee mating optimization (HBMO) and k-means for partitional clustering problem.