一种用于BP网络优化的并行模拟退火遗传算法

针对模拟退火算法和遗传算法存在的不足,提出了并行模拟退火遗传算法,并用于3层BP神经网络优化。在适应度函数中引入模拟退火机制,采用排序、最优保存策略选择算子、启发式交叉和多点非均匀变异改进遗传算子,利用模拟退火算法产生新解增加搜索方向,并结合并行进化思想对经典遗传算法进行改进。通过对英文字母识别的仿真实验,表明该方法全局搜索能力、局部搜索能力和收敛速度都优于经典遗传算法。     

基于捕食搜索策略的模拟退火优化算法

针对传统模拟退火算法初始温度和降温函数难以确定以及接收劣质解同时容易遗失当前最优解等缺陷,将禁忌搜索算法的禁忌表功能引入SA算法,避免遗失最优解和对某个解进行多次重复地搜索;根据函数的复杂程度确定初始温度,并定义新的降温函数,提高算法的搜索效率和精度;引入捕食搜索策略,平衡算法搜索能力和开发能力,避免陷入局部最优。通过对5个典型的基准测试函数的仿真表明,改进算法具有较强的全局搜索能力,同时寻优精度和收敛速度比原算法也有较大的提高。     

基于多线程模拟退火算法在配送路线选择中的应用

合理的配送路线可以提高物流配送的效率。针对标准模拟退火算法串行优化单个解,优化过程较长、效率较低的弱点,提出一种基于多线程模拟退火的并行机制。该机制通过将单个解的串行优化转化为多个串行解同时进行的并行的进行搜索、优化,来提高算法的整体优化效率。利用该算法求解配送路线的选择问题能够显著提高优化效率,计算结果表明该算法是有效的。     

Efficient contrast enhancement of images using hybrid ant colony optimisation,genetic algorithm,and simulated annealing

In this paper, we propose a hybrid algorithm including Genetic Algorithm (GA), Ant Colony Optimisation (ACO), and Simulated Annealing (SA) metaheuristics for increasing the contrast of images. In this way, contrast enhancement is obtained by global transformation of the input intensities. Ant colony optimisation is used to generate the transfer functions which map the input intensities to the output intensities. Simulated annealing as a local search method is utilised to modify the transfer functions generated by ant colony optimisation. And genetic algorithm has the responsibility of evolutionary process of ants? characteristics. The employed fitness function operates automatically and tends to provide a balance between contrast and naturalness of images. The results indicate that the new method achieves images with higher contrast than the previously presented methods from the subjective and objective viewpoints. Further, the proposed algorithm preserves the natural look of input images.     

基于遗传模拟退火算法的门阵列布局方法

为实现门阵列模式布局,将遗传算法与模拟退火算法相结合,提出一种新的遗传模拟退火算法,利用遗传算法进行全局搜索,利用模拟退火法进行局部搜索,在进化过程中采用精英保留策略,对进化结果进行有选择的模拟退火操作,既加强了局部搜索能力又防止陷入局部最优。实验结果表明,与传统遗传算法相比,该算法能够有效提高全局搜索能力。     

基于模拟退火的混合遗传算法研究

针对常规遗传算法会出现早熟现象、局部寻优能力较差等不足,在遗传算法运行中融入模拟退火算法算子,实现了模拟退火的良好局部搜索能力与遗传算法的全局搜索能力的结合。经验证,该混合算法可以显著提高遗传算法的运行效率和优化性能。     

基于二进制蚁群模拟退火算法的认知引擎

在认知无线电系统中,认知引擎依据通信环境的变化和用户需求动态配置无线电工作参数。针对认知引擎中的智能优化问题,提出一种二进制蚁群模拟退火（BAC&SA）算法用于认知无线电参数优化。该算法在二进制蚁群优化（BACO）算法中引入模拟退火（SA）算法,融合了BACO的快速寻优能力和SA的概率突跳特性,能有效避免BACO容易陷入局部最优解的缺陷。仿真实验结果表明,与遗传算法（GA）和BACO算法相比,基于BAC&SA算法的认知引擎在全局搜索能力和平均适应度等方面具有明显的优势。     

一种求解圆形Packing问题的模拟退火算法?

为求解矩形区域内的圆形Packing问题,提出一种启发式模拟退火算法。寻求多个圆在一个矩形区域内的优良布局,使这些圆两两互不嵌入地放置。算法从任一初始构形出发,采用模拟退火(SA)算法进行全局寻优,在SA执行过程中,应用基于自适应步长的梯度法进行局部搜索,同时介绍一些启发式策略。对2组共20个算例进行实算测试,计算结果证明了该算法的有效性。     

How to Maximize the Likelihood Function for a DSGE Model

This paper extends two optimization routines to deal with objective functions for DSGE models. The optimization routines are (1) a version of Simulated Annealing developed by Corana A, Marchesi M, Ridella (ACM Trans Math Softw 13(3):262–280, 1987), and (2) the evolutionary algorithm CMA-ES developed by Hansen, Müller, Koumoutsakos (Evol Comput 11(1), 2003). Following these extensions, we examine the ability of the two routines to maximize the likelihood function for a sequence of test economies. Our results show that the CMA-ES routine clearly outperforms Simulated Annealing in its ability to find the global optimum and in efficiency. With ten unknown structural parameters in the likelihood function, the CMA-ES routine finds the global optimum in 95% of our test economies compared to 89% for Simulated Annealing. When the number of unknown structural parameters in the likelihood function increases to 20 and 35, then the CMA-ES routine finds the global optimum in 85 and 71% of our test economies, respectively. The corresponding numbers for Simulated Annealing are 70 and 0%.     

改进的核可能性C-均值聚类算法研究

提出了一种改进的核可能性C-均值聚类算法,它是对PCM聚类模型的推广。通过限制PCM聚类模型中解的可行域,利用全局优化技术（以模拟退火（SA）为例）来求解,使其保持了PCM对噪声鲁棒的优点,又避免了重合聚类的产生,且能较好地找到问题的全局最优解,减少了全局优化方法的搜索范围,加快了收敛速度。     

Inventory of damageable items with variable replenishment and unit production cost via simulated annealing method

Items made of glass, ceramic, etc. are normally stored in stacks and get damaged during the storage due to the accumulated stress of heaped stock. The researchers have overlooked the inventory problems for this type of items. Again the classical iterative optimization techniques very often stuck to the local optimum present in the search space. This is one of the hindrances in optimizing the non-linear problems.Annealing is the physical process of heating up a solid until it melts followed by cooling it down until it crystallizes into a state with perfect lattice. Following this physical phenomenon, recently a soft computing method, Simulated Annealing (SA), has been developed to find the global optimum for a complex cost surface through stochastic search process.In this paper, a deterministic inventory model of a damageable item is developed with variable replenishment rate and unit production cost. Here replenishment rate and unit production cost are dependent on demand. Demand and damageability are stock dependent. This dependency may be linear or non-linear. The optimum inventory level is evaluated by the profit maximization principle through SA algorithm. The model is illustrated numerically with different forms of demand and damage functions.     

A stochastic version of Expectation Maximization algorithm for better estimation of Hidden Markov Model

This paper attempts to overcome the local convergence problem of the Expectation Maximization (EM) based training of the Hidden Markov Model (HMM) in speech recognition. We propose a hybrid algorithm, Simulated Annealing Stochastic version of EM (SASEM), combining Simulated Annealing with EM that reformulates the HMM estimation process using a stochastic step between the EM steps and the SA. The stochastic processes of SASEM inside EM can prevent EM from converging to a local maximum and find improved estimation for HMM using the global convergence properties of SA. Experiments on the TIMIT speech corpus show that SASEM obtains higher recognition accuracies than the EM.     

直接搜索模拟退火算法的自适应改进

针对直接搜索模拟退火算法求解高维优化问题存在稳定性差、收敛成功率低现象,提出一种自适应的直接搜索模拟退火算法。该算法通过构造基于迭代温度动态调整搜索范围的新点产生方式和自适应寻优模块,增强了算法跳出局部极值和加快邻域搜索的能力,利用柯西分布状态发生函数的大范围遍历特点,弥补了直接搜索模拟退火算法求解高维多峰值问题易陷入局部解和计算效率低的不足。结合可行规则法处理约束问题,典型高维函数和工程优化设计实例的测试结果表明,该算法能够有效求解高维优化问题,整体性能较直接搜索模拟退火算法有显著提高。     

混沌协同人工鱼粒子群混合算法及其应用

针对基本人工鱼群算法（AFSA）收敛速度较慢、精度较低和粒子群易陷于局部的缺点,提出了混沌协同人工鱼粒子群混合算法（CCAFSAPSO）。该算法采取AFSA、PSO的全局并行搜索与模拟退火算法（SA）的局部串行搜索机制相结合的搜索方式,并用混沌映射的遍历性和模拟退火算法的突跳功能,克服了AFSA、PSO的收敛速度、求解精度和易陷于局部最优的不足。典型函数测试进一步表明CCAFSAPSO算法和同类算法相比,收敛速度更快、求解精度较高。最后将算法应用于化工数据处理,获得满意效果。     

A hybrid optimization approach to conformance testing of finite automata

Unique Input–Output sequences (UIOs) are quite commonly used in conformance testing. Unfortunately finding UIOs of minimal length is an NP hard problem. This study presents a hybrid approach to generate UIOs automatically on a basis of the finite state machine (FSM) specification. The proposed hybrid approach harnesses the benefits of hill climbing (Greedy search) and heuristic algorithm. Hill climbing, which exploits domain knowledge, is capable of quickly generating good result however it may get stuck in local minimum. To overcome the problem we used a set of parameters called the seed, which allows the algorithm to generate different results for a different seed. The hill climbing generates solutions implied by the seed while the Genetic Algorithm is used as the seed generator. We compared the hybrid approach with Genetic Algorithm, Simulated Annealing, Greedy Algorithm, and Random Search. The experimental evaluation shows that the proposed hybrid approach outperforms other methods. More specifically, we showed that Genetic Algorithm and Simulated Annealing exhibit similar performance while both of them outperform Greedy Algorithm. Finally, we generalize the proposed hybrid approach to seed-driven hybrid architectures and elaborate on how it can be adopted to a broad range of optimization problems.     

基于模拟退火的花朵授粉优化算法

针对花朵授粉算法寻优精度低、收敛速度慢、易陷入局部极小的不足,提出一种把模拟退火(SA)融入到花朵授粉算法中的混合算法。该算法通过SA的概率突跳策略使其避免陷入局部最优,并利用SA的全域搜索的性能增强算法的全局寻优能力。通过6个标准测试函数进行测试,仿真结果表明,改进算法在4个测试函数中能够找到理论最优值,其收敛精度、收敛速度、鲁棒性均比基本的花朵授粉算法(FPA)、蝙蝠算法(BA)、粒子群优化(PSO)算法及改进的粒子群算法有较大的提高;同时,对非线性方程组问题进行求解的算例应用也验证了改进算法的有效性。     

改进的退火遗传优化策略应用研究

地震参数反演属于典型的非线性优化问题。针对遗传算法和模拟退火算法各自的优缺点,将改进的遗传算法与模拟退火算法相结合,提出了改进的退火遗传算法（ISAGA）。该方法通过筛选和修复进行初始种群的选择,采用允许父代参与竞争的退火选择机制,并根据模拟退火思想对交叉和变异概率进行自适应的调整,从而增加了种群的多样性并提高了收敛速度。该方法既具备了遗传算法强大的全局搜索能力,也拥有模拟退火算法强大的局部搜索能力。经理论模型试算结果表明,该方法不仅收敛速度快,优化精度高,抗干扰能力强,而且避免了局部收敛和依赖初始模型等问题,计算所得反演参数更接近于实际观测值。     

求解作业车间调度问题的微粒群遗传退火算法

标准微粒群算法（PSO）通常被用于求解连续优化的问题,很少被用于离散问题的优化求解,如作业车间调度问题（JSP）。因此,针对PSO算法易早熟、收敛慢等缺点提出一种求解作业车间调度问题（JSP）的混合微粒群算法。算法将微粒群算法、遗传算法（GA）、模拟退火（SA）算法相结合,既增强了算法的局部搜索能力,降低了算法对参数的依赖,同时改善了PSO算法和GA算法易早熟的缺点。对经典JSP问题的仿真实验表明：与标准微粒群算法相比,该算法不仅能有效避免算法中的早熟问题,并且算法的全局收敛性得到了显著提高。     

融合模拟退火的遗传算法在文档聚类中的应用

为了准确高效地对网上获取的文档进行聚类,在布尔逻辑模型的基础上提出了一种改进的最优相似度搜索方法。该方法将模拟退火的思想融入到遗传算法当中,通过“撒种”操作将模拟退火算法的局部搜索能力以及遗传算法的全局搜索能力结合起来。实验表明,使用该混合算法对文档进行聚类,不仅搜索效率得到了提高,而且准确度优于使用传统的遗传算法。     

双层规划的改进混合布谷鸟搜索量子行为粒子群优化算法

为解决粒子群优化（PSO）算法求解双层规划问题时易陷入局部最优解的问题,提出了一种基于模拟退火（SA）Metropolis准则的改进混合布谷鸟搜索量子行为粒子群优化（ICSQPSO）算法。首先,该混合算法引入SA算法中的Metropolis准则,在求解过程中既能接受好解也能以一定的概率接受坏解,增强全局寻优能力;接着,为布谷鸟搜索算法设计一种改进动态步长Lévy飞行,以保持粒子群在优化过程中较高的多样性,保证搜索广度;最后,利用布谷鸟搜索算法中的偏好随机游走机制帮助粒子跳出局部最优解。通过对13个涵盖非线性规划、分式规划、多个下层规划的双层规划实例的数值实验,结果表明：ICSQPSO算法所得12个双层规划的目标函数最优值显著优于对比算法,只有1例的结果稍差,并且有半数实例的结果优于对比算法50%。由此可见,ICSQPSO算法对双层规划的寻优能力明显优于对比算法。