新型改进果蝇优化算法

针对传统果蝇优化算法在进行优化时所存在的寻优精度偏低和收敛速度较慢的问题,提出了一种新的改进果蝇优化算法。该算法在迭代过程中将每次迭代所得最优值的变化率作为下一次果蝇种群飞行距离变化的参考依据。动态改变果蝇种群每次飞行的距离,能够有效地权衡算法的全局搜索能力和局部搜索能力。将该改进算法在函数优化中与原果蝇算法和另外两种果蝇改进算法进行仿真对比,结果表明,所提出的改进算法在收敛精度、收敛速度以及稳定性方面具有明显优势。     

一种用于PID控制参数优化的混合果蝇算法

针对果蝇优化算法（ FOA）收敛速度快但寻优精度低的缺点,为了改善果蝇算法的优化性能,提出一种混合果蝇优化算法（ HFOA）。HFOA采用分段优化的思想,在优化过程后期采用收敛稳定性较好的粒子群优化（ PSO）算法优化果蝇算法中果蝇个体飞行距离和味道浓度的判定值,采用误差性能指标积分准则ITAE作为适应度函数,并将优化方案应用于一类不稳定系统的PID控制。Matlab仿真验证表明：HFOA计算高效,具有良好的稳定性,收敛精度高,进而验证了HFOA应用于PID控制参数优化是可行而有效的。     

一种新型的混沌步长果蝇优化算法

针对果蝇优化算法存在算法易早熟、收敛不足的问题,将Hénon混沌映射引用为步长因子,提出了一种混沌步长果蝇优化算法。利用Hénon映射所产生的混沌现象具有良好的遍历性、多样性的特点来改进果蝇算法的固定步长,并增加放大系数以提高算法的全局和局部搜索能力以及跳出局部最优解的能力。对10个经典测试函数进行测试,并与多个算法进行了对比分析,研究结果表明,该算法具有较高的全局搜索和跳出局部最优解的能力。     

融合学习策略与导向果蝇机制的气味源主动定位方法研究

工业生产过程中常发生由有害气体泄漏引起的火灾或爆炸事故,利用载有气体传感器的移动机器人实时监测并搜索定位泄漏气体源是预防重大事故的有效方法,而高效的搜索策略是保证机器人快速准确定位气味源的关键因素.现有的气味源搜索算法存在定位成功率不高和对气味源定位不准的问题,本文提出一种将仿生果蝇算法和学习策略相融合的气味搜索策略.针对传统果蝇算法易陷入饱和收敛的问题,提出一种新的导向果蝇极值更新方式;针对寻优不精的问题,进一步提出一种基于学习策略的导向果蝇气味源搜索算法(OCGFOA).仿真实验结果表明OCGFOA算法完成定位速度更快且离泄漏气味源位置更近,其定位效果更能满足对危险气味源定位的要求;最后,在物理场景下进行气味源主动定位验证实验,证明本文所提算法在实际场景下也具有可行性.     

基于细菌迁徙的自适应果蝇优化算法

针对果蝇优化算法的早熟收敛问题,提出了一种新的基于细菌迁徙的自适应果蝇优化算法。该算法在运行过程中根据进化停滞步数的大小自适应地引入细菌迁徙操作,提高算法跳出局部极值的能力;并且对每个个体根据适应值大小赋予不同的自适应迁徙概率,避免了迁徙可能带来的解退化的问题。对几种经典函数的测试结果表明,新算法具有更好的全局搜索能力,在收敛速度、收敛可靠性及收敛精度上比果蝇优化算法有较大的提高。     

基于柯西-高斯动态消减变异的果蝇优化算法研究

针对果蝇优化算法易陷入局部极值收敛速度减慢的不足,结合柯西变异和高斯变异的各自优点,提出了变异效能系数和柯西-高斯动态消减变异因子等概念,进而提出了一种柯西-高斯动态消减变异方法,将该方法应用于改进果蝇优化算法,提出了一种基于柯西-高斯动态消减变异的果蝇优化算法。该算法兼顾了全局探索和局部开发两个特性,丰富了种群的多样性,有效地消除了易陷入局部极值的弊端,提高了算法的收敛速度。仿真实验采用经典函数用例和实际工程用例进行验证,结果表明该算法的求解速度和精度更高,稳定性更好。     

An improved fruit fly optimization algorithm for solving traveling salesman problem

The traveling salesman problem (TSP), a typical non-deterministic polynomial (NP) hard problem, has been used in many engineering applications. As a new swarm-intelligence optimization algorithm, the fruit fly optimization algorithm (FOA) is used to solve TSP, since it has the advantages of being easy to understand and having a simple implementation. However, it has problems, including a slow convergence rate for the algorithm, easily falling into the local optimum, and an insufficient optimi-zation precision. To address TSP effectively, three improvements are proposed in this paper to improve FOA. First, the vision search process is reinforced in the foraging behavior of fruit flies to improve the convergence rate of FOA. Second, an elimination mechanism is added to FOA to increase the diversity. Third, a reverse operator and a multiplication operator are proposed. They are performed on the solution sequence in the fruit fly’s smell search and vision search processes, respectively. In the experiment, 10 benchmarks selected from TSPLIB are tested. The results show that the improved FOA outperforms other alternatives in terms of the convergence rate and precision.     

果蝇耦合均匀设计算法及其优化SVM参数

支持向量机的参数选择仍无系统的理论指导,且参数优化一直是支持向量机的一个重要研究方向。传统果蝇优化算法能够较快寻得一个较优的近似最优解,随后在该解的邻域继续迭代而造成寻优时间的严重增加。针对该问题构建了果蝇优化算法与均匀设计相耦合的果蝇耦合均匀设计算法,并将其用于支持向量机的参数优化。该算法首先利用果蝇优化算法并行寻优以快速得到所研究问题的一个较优近似最优解,然后跳转执行均匀设计的局部寻优,以获得一个更优的近似最优解。数值实验结果表明:该算法具有较快的寻优效率和较高的分类精度,验证了其在支持向量机参数优化中的有效性和可行性。     

Image segmentation using Atanassov’s intuitionistic fuzzy sets

The problem of segmentation in spite of all the work over the last decades, is still an important research field and also a critical preprocessing step for image processing, mostly due to the fact that finding a global optimal threshold that works well for all kind of images is indeed a very difficult task that, probably, will never be accomplished.During the past years, fuzzy logic theory has been successfully applied to image thresholding. In this paper we describe a thresholding technique using Atanassov’s intuitionistic fuzzy sets (A-IFSs). This approach uses Atanassov’s intuitionistic index values for representing the hesitance of the expert in determining whether the pixel belongs to the background or that it belongs to the object. First, we describe the general framework of this approach to bi-level thresholding. Then we present its natural extension to multilevel thresholding. This multilevel threshold methodology segments the image into several distinct regions which correspond to a background and several objects.Segmentation experimental results and comparison with Otsu’s multilevel thresholding algorithm for the calculation of two and three thresholds are presented.     

基于自适应ABC/FOA融合定位算法研究

针对传统无线传感网络(WSN)节点定位算法定位慢、误差大的问题,提出了一种基于自适应ABC/FOA融合定位算法.该算法既吸收了ABC算法的全局寻优能力强的优点,又保留了FOA算法局部搜索能力强的特点;同时,引入自适应概念,对果蝇步长进行控制,提高种群多样性;接下来,对节点定位误差函数进行改进,提高了节点定位误差的区分度.仿真结果表明,利用自适应ABC/FOA融合定位算法以后,定位时间明显缩短,定位误差明显减小,能够满足工程领域对于定位精度的要求.     

求解约束优化问题的改进果蝇优化算法及其工程应用

针对基本果蝇优化算法收敛速度慢、求解精度低、易于陷入局部极值以及算法候选解不能取负值等不足,提出一种用于解决约束优化问题的改进果蝇优化算法.该算法利用果蝇个体历史最佳记忆信息和种群全局历史最佳记忆信息构建多策略混合协同进化的搜索机制,以达到有效平衡算法的全局探索与局部开发的目的,同时也能够较好地避免算法的早熟收敛问题;...     

基于果蝇算法优化的概率神经网络在变压器故障诊断中的应用

传统的变压器故障诊断方法存在编码不全,容易错判漏判的缺点。随着变压器在线监测技术的发展和产品需求的增加,变压器故障诊断技术朝着智能化的方向发展。为提高故障诊断率,结合油中气体分析法,本文提出了一种基于果蝇算法优化的概率神经网络模型的变压器故障诊断方法。作为一种新型的启发式和进化式算法,果蝇优化算法具有易理解和快速收敛到全局最优解的优点。概率神经网络结构简单、训练简洁,具有强大的非线性分类能力,将样本空间映射到故障模式空间中,从而形成一有较强容错能力和机构自适应能力的诊断网络。采用果蝇算法对模型参数进行优化,减少人为因素对神经网络设计的影响。仿真实验证明这种基于果蝇优化算法的概率神经网络可以有效地运用到变压器故障诊断中,为变压器故障诊断供了一条新途径,具有良好的研究价值和发展前景。     

冰雪天气下基于MFOA-LSSVR的跑道温度预测

跑道温度是跑道结冰的重要因素。针对机场跑道温度短时预测问题,提出一种改进果蝇算法优化最小二乘支持向量回归机(MFOA-LSSVR)的跑道温度预测方法。在原始果蝇算法(Fruit Fly Optimization Algorithm, FOA)中引入指数更新函数和距离扩张因子以增强果蝇种群全局寻优能力,避免其陷入局部极小值。同时考虑跑道温度多种影响因素对模型预测精度的影响,选用Spearman相关系数确定跑道温度主要影响特征。以冰雪天气下跑道温度的实际数据,对该模型进行仿真测试。结果显示:与果蝇优化最小二乘支持向量回归机(FOA-LSSVR)、反向传播(Backpropagation, BP)神经网络、机理模型、MFOA-LSSVR单变量模型相比,MFOA-LSSVR预测模型的平均绝对误差至少分别提高了17.24%、25.37%、69.76%和10.88%。实验结果验证了所提方法的有效性和泛化性,能够为跑道温度短时预测提供有效思路。     

双目标流水线调度的动态双子群离散果蝇算法

提出了一种基于动态双子群的离散果蝇优化算法,求解以最大完工时间和机床空闲时间的最小化为目标的无等待流水线调度问题。与传统的果蝇算法不同,该算法采用基于工序的编码方式,并用改进的NEH方法进行初始化,提高初始解的质量;根据算法在进化过程中个体的进化水平,动态地将整个群体划分为先进子群和后进子群,简单但有效地插入方法在先进个体邻域内进化精细搜索,贪婪迭代进化机制用于优化后进个体,以此平衡算法的全局开发能力和局部搜索能力;为了提高算法效率,快速算法用于计算函数目标值和判断更新非支配解。仿真试验表明了所提果蝇算法的有效性和高效性。     

Dynamic Gaussian bare-bones fruit fly optimizers with abandonment mechanism: method and analysis

The Fruit Fly Optimization Algorithm (FOA) is a recent algorithm inspired by the foraging behavior of fruit fly populations. However, the original FOA easily falls into the local optimum in the process of solving practical problems, and has a high probability of escaping from the optimal solution. In order to improve the global search capability and the quality of solutions, a dynamic step length mechanism, abandonment mechanism and Gaussian bare-bones mechanism are introduced into FOA, termed as BareFOA. Firstly, the random and ambiguous behavior of fruit flies during the olfactory phase is described using the abandonment mechanism. The search range of fruit fly populations is automatically adjusted using an update strategy with dynamic step length. As a result, the convergence speed and convergence accuracy of FOA have been greatly improved. Secondly, the Gaussian bare-bones mechanism that overcomes local optimal constraints is introduced, which greatly improves the global search capability of the FOA. Finally, 30 benchmark functions for CEC2017 and seven engineering optimization problems are experimented with and compared to the best-known solutions reported in the literature. The computational results show that the BareFOA not only significantly achieved the superior results on the benchmark problems than other competitive counterparts, but also can offer better results on the engineering optimization design problems.

     

自适应变异的果蝇优化算法

针对基本果蝇优化算法(FOA)寻优精度不高和易陷入局部最优的缺点, 提出自适应变异的果蝇优化算法(FOAAM)。该算法在运行过程中根据群体适应度方差和当前最优解的大小判断算法陷入局部最优时, 首先将最优果蝇个体复制M个; 然后对复制的最优果蝇个体进行扰动, 按一定的概率P执行高斯变异操作; 最后对变异后的最优果蝇个体进行二次寻优, 从而跳出局部极值而继续优化。对几种经典测试函数的仿真结果表明, FOAAM算法具有更好的全局搜索能力, 在收敛速度、收敛可靠性及收敛精度上均比基本FOA算法有较大的提高。     

具有Levy飞行特征的双子群果蝇优化算法

针对果蝇优化算法(FOA)易陷入局部最优和收敛精度不高等缺点,在果蝇算法中引入Levy飞行策略,提出了具有Levy飞行特征的双子群果蝇优化算法(LFOA).在迭代寻优过程中,根据果蝇种群的进化程度动态地将果蝇种群划分为以当代最差个体为中心的较差子群和以当代最优个体为中心的较优子群;较差子群在最优个体指导下进行全局搜索,较优子群则围绕最优个体做Levy飞行进行局部搜索,这样既平衡了种群的全局和局部搜索能力,同时又可以利用Levy飞行偶尔的长跳跃来跳出局部最优;两个子群的信息通过最优个体的改变和子群的重组进行交换.对6个典型测试函数的仿真实验表明,LFOA具有全局收敛的能力,相比FOA具有更好的收敛精度、收敛速度和收敛可靠性.     

A novel local contrast fusion-based fuzzy model for color image multilevel thresholding using grasshopper optimization

The segmentation process is considered the significant step of an image processing system due to its extreme inspiration on the subsequent image analysis. Out of various approaches, thresholding is one of the most popular schemes for image segmentation. In segmentation, image pixels are arranged in various regions based on their intensity levels. In this paper, a straightforward and efficient fusion-based fuzzy model for multilevel color image segmentation using grasshopper optimization algorithm (GOA) has been proposed. Thresholding based segmentation lacks accuracy in segmenting the ambiguous images due to their complex characteristics, uncertainties and inherent fuzziness. However, the fuzzy entropy resolves these problems, but it is unable for segmenting at higher levels and also the complexity level for selecting suitable thresholds is high. The selection of metaheuristic GOA reduces this problem by selecting optimal threshold values. Therefore, to increase the quality of the segmented image, a simple and effective multilevel thresholding method is exploited by using the concept of fusion which is based on the local contrast. Experimental outputs demonstrate that fusion-based multilevel thresholding is better than most specific segmentation methods and can be validated by comparing the different numerical parameters. Experiments on standard daily-life color and satellite images are conducted to prove the effectiveness of the proposed scheme.     

基于SQP局部搜索的多子群果蝇优化算法

针对基本果蝇优化算法在寻优过程中种群多样性降低导致算法易陷入早熟收敛的问题,提出了基于序列二次规划（SQP）局部搜索的多子群果蝇优化算法（MFOA-SQP）。新算法将果蝇种群均匀划分为多个子群,并引入粒子群算法中的惯性权重和学习因子,协同调节果蝇移动方向和步长;每隔一定迭代次数重新划分子群,避免种群单一化,使算法更易跳出局部最优;对子群最优个体进行SQP搜索,提高局部寻优性能。通过6个测试函数和优化广义回归神经网络对银行客户进行分类的实验结果表明,算法在寻优精度和速度方面性能优越,能够有效提高广义回归神经网络的分类准确率。     

基于维度分区的果蝇优化新算法

为提高果蝇算法的收敛稳定性,提出了一种基于维度分区的果蝇优化新算法。将果蝇种群均分为两组:跟随果蝇和搜索果蝇。跟随果蝇在全局最优果蝇附近实现精细化局部搜索,而搜索果蝇则将位置向量的每个维度搜索范围划分为若干个区间,通过比较各个区间的最优位置来更新果蝇位置。为加快算法收敛速度,若某搜索果蝇在连续若干次迭代过程中 均 表现最差,则在当前最优果蝇位置附近产生该果蝇的新位置。针对8种典型函数的仿真实验表明:与传统算法相比, 所提算法所需参数较少,收敛稳定性高,并且在收敛精度及收敛速度等方面具有明显优势。