Analysis of the diversity of population and convergence of genetic algorithms based on Negentropy

With its wide use in different fields, the problem of the convergence of simple genetic algorithms (GAs) has been concerned. In the past, the research on the convergence of GAs was based on Holland's model theorem. The diversity of the evolutionary population and the convergence of GAs are studied by using the concept of negentropy based on the discussion of the characteristic of GA. Some test functions are used to test the convergence of GAs, and good results have been obtained. It is shown that the global optimization may be obtained by selecting appropriate parameters of simple GAs if the evolution time is enough.

The Distribution Population-based Genetic Algorithm for Parameter Optimization PID Controller

Enlightened by distribution of creatures in natural ecology environment, the distributionpopulation-based genetic algorithm (DPGA) is presented in this paper. The searching capability ofthe algorithm is improved by competition between distribution populations to reduce the search zone.This method is applied to design of optimal parameters of PID controllers with examples, and thesimulation results show that satisfactory performances are obtained.

Evaluation of Population Structure, Genetic Diversity and Origin of Northeast Asia Weedy Rice Based on Simple Sequence Repeat Markers

Weedy rice exerts a severe impact on rice production by competing for sunlight, water and nutrients. This study assayed the population structure, genetic diversity and origin of Northeast Asia weedy rice by using 48 simple sequence repeat markers. The results showed that weedy rice in Northeast Asia had a high genetic diversity, with Shannon＇s diversity index （I） of 0.748 and the heterozygosity （He） of 0.434. In each regional population, I value varied widely. The widest range of I （0.228-0.489） was observed in the weedy rice of Eastern China, which was larger than that of Northeast China and Korea （0.168-0.270）. The F-statistics of regional populations （Fis, Fit and Fst） also showed higher values in the weedy rice of Eastern China than those of Northeast China and Korea All weedy rice accessions were grouped into two clusters in the unweighted pair group method with arithmetic mean cluster analysis dendrogram, namely Eastern China branch and Northeastern China plus Korea branch. There was significant differentiation in genetic characteristics in weedy rice of northeastern and eastern Asia, especially in Eastern China.

Mitochondrial DNA control region diversity and population structure of Pacific herring(Clupea pallasii)in the Yellow Sea and the Sea of Japan

To investigate the genetic variation and population structure of Pacific herring in the Yellow Sea and the genetic differentiation between the Yellow Sea and the Sea of Japan, fragments of 479-bp mitochondrial DNA control region were sequenced for 110 individuals collected from three different periods in the Yellow Sea and one locality in the Sea of Japan. High haplotype diversity and moderate nucleotide diversity were observed in Pacific herring. AMOVA and exact test of population differentiation showed no significant genetic differentiations among the three populations of the Yellow Sea and suggested the populations can be treated as a single panmictic stock in the Yellow Sea. However, a large and significant genetic differentiation （ФST=0.11; P=0.00） was detected between the populations in the Yellow Sea and the Sea of Japan. The high sea water temperature in the Tsushima Strait was thought a barrier to block the gene exchange between populations of the two sea areas. The neutrality tests and mismatch distribution indicated recent population expansion in Pacific herring.

Fuzzy-second order sliding mode control optimized by genetic algorithm applied in direct torque control of dual star induction motor

The direct torque control of the dual star induction motor(DTC-DSIM) using conventional PI controllers is characterized by unsatisfactory performance, such as high ripples of torque and flux, and sensitivity to parametric variations. Among the most evoked control strategies adopted in this field to overcome these drawbacks presented in classical drive, it is worth mentioning the use of the second order sliding mode control(SOSMC) based on the super twisting algorithm(STA) combined with the fuzzy logic control(FSOSMC). In order to realize the optimal control performance, the FSOSMC parameters are adjusted using an optimization algorithm based on the genetic algorithm(GA). The performances of the envisaged control scheme, called G-FSOSMC, are investigated against G-SOSMC, G-PI and BBO-FSOSMC algorithms. The proposed controller scheme is efficient in reducing the torque and flux ripples, and successfully suppresses chattering. The effects of parametric uncertainties do not affect system performance.

A Novel Genetic Algorithm Preventing Premature Convergence by Chaos Operator

An improved genetic algorithm (GA) is proposed based on the analysis of population diversity within the framework of Markov chain. The chaos operator to combat premature convergence concerning two goals of maintaining diversity in the population and sustaining the convergence capacity of the GA is introduced. In the CHaos Genetic Algorithm (CHGA), the population is recycled dynamically whereas the most highly fit chromosome is intact so as to restore diversity and reserve the best schemata which may belong to the optimal solution. The characters of chaos as well as advanced operators and parameter settings can improve both exploration and exploitation capacities of the algorithm. The results of multimodal function optimization show that CHGA performs simple genetic algorithms and effectively alleviates the problem of premature convergence.

Design of Soft Computing Based Optimal PI Controller for Greenhouse System

Greenhouse system (GHS) is the worldwide fastest growing phenomenon in agricultural sector. Greenhouse models are essential for improving control efficiencies. The Relative Gain Analysis (RGA) reveals that the GHS control is complex due to 1) high nonlinear interactions between the biological subsystem and the physical subsystem and 2) strong coupling between the process variables such as temperature and humidity. In this paper, a decoupled linear cooling model has been developed using a feedback-feed forward linearization technique. Further, based on the model developed Internal Model Control (IMC) based Proportional Integrator (PI) controller parameters are optimized using Genetic Algorithm (GA) and Particle Swarm Optimization (PSO) to achieve minimum Integral Square Error (ISE). The closed loop control is carried out using the above control schemes for set-point change and disturbance rejection. Finally, closed loop servo and servo-regulatory responses of GHS are compared quantitatively as well as qualitatively. The results implicate that IMC based PI controller using PSO provides better performance than the IMC based PI controller using GA. Also, it is observed that the disturbance introduced in one loop will not affect the other loop due to feedback-feed forward linearization and decoupling. Such a control scheme used for GHS would result in better yield in production of crops such as tomato, lettuce and broccoli.

A New Fuzzy Adaptive Genetic Algorithm

Multiple genetic algorithms (GAs) need a large population size, which will take a long time for evolution. A new fuzzy adaptive GA is proposed in this paper. This algorithm is more effective in global search while keeping the overall population size constant. The simulation results of function optimization show that with the proposed algorithm, the phenomenon of premature convergence can be overcome effectively, and a satisfying optimization result is obtained.

长薄鳅(Leptobotia elongata)线粒体DNA控制区遗传多样性研究

对采自泸州（长江干流）、南溪（长江干流）、柏溪（金沙江段）、攀枝花（雅砻江段）、重庆（嘉陵江段）4个流域的45尾长薄鳅（Leptobotia elongata）的线粒体DNA控制区部分序列（798 bp）进行了扩增,共检测出19个单倍型,未发现群体间有共享的单倍型,5群体单倍型多样性在0.833~1.000之间,显示不同流域的长薄鳅群体单倍型类型较为丰富。分析了D-Loop的碱基组成、变异情况和核苷酸序列差异,计算了核苷酸多样性（π）、单倍型多样性（h）、FST值和基因流数值（Nm）,构建了长薄鳅不同单倍型分子系统树和中间网络图。5个群体内各序列核苷酸多样性指数（π）在0.276%~0.905%之间;群体间遗传距离范围为0.0028~0.0092,结果显示长薄鳅自然群体存在较丰富的线粒体控制区序列多态性（h=0.916,π=0.00450）,Tajima’s D统计（？2.09890）和Fu’sFs统计（？7.56940）分析都显示各种群之间差异显著（P〈0.05）,但FST值（FST〈0.05）的分析结果显示重庆、柏溪、南溪、攀枝花和泸洲种群间没有明显的遗传分化,暗示了柏溪和攀枝花种群历史上,可能发生过群体扩张和种群瓶颈,而泸州、南溪和重庆种群一直是平衡种群。Nm值计算结果显示各地理种群间无明显基因交流,暗示了长薄鳅虽然在各条不同的河流里洄游产卵,但并未因此而产生独立分化的群体。所有群体中,泸洲和攀枝花种群的遗传多样性比重庆、柏溪和南溪种群丰富。进行长薄鳅人工繁殖时,可以将遗传多样性较丰富地区的个体补充到人工繁殖中来,以提高长薄鳅的遗传素质,为人工增殖放流提供遗传多样性更丰富的个体。

基于改进自适应多种群遗传算法的结构-控制系统一体化优化

提出一种改进的自适应多种群遗传算法,以更好地解决建筑结构-主动控制系统一体化优化问题,即同时对被控结构参数、控制算法参数、主动作动器布置位置进行优化。该遗传算法对编码方法、初始种群生成、选择策略、交叉概率和变异概率的自适应调整、多种群协同进化中移民策略等进行改进。研究结果表明:改进的自适应多种群遗传算法和改进的基本遗传算法优化结果总体一致,表明前者分析结果是正确的,并且具有较高的精度;改进的自适应多种群遗传算法和改进的基本遗传算法首次得到优化分析最优解的平均进化代数分别为320与730,表明前者比后者收敛速度更快;改进的自适应多种群遗传算法每次能达到或接近最优解,可有效克服基本遗传算法优化结果随机性较强的缺点;经改进的自适应多种群遗传算法优化的主动控制系统取得明显减振效果,E1 Centro波输入时,主动控制结构层间位移角峰值和绝对加速度峰值较无控时分别平均减小54.5%与46.7%。算例结果表明了改进的自适应多种群遗传算法的有效性,实现了对建筑结构-主动控制系统的一体化优化。

基于改进自适应遗传算法的渠系优化配水分析

为减少渠系在输水过程中的渗漏损失,提高渠系水利用系数,以两级渠系渗漏损失、水流波动最小为目标函数,以下级渠道配水流量、配水开始和结束时间为决策变量,构建配水模型,并采用改进的自适应遗传算法(SIGGA)进行实例求解.提出了一种基于Sigmoid函数的自适应交叉、变异算子,并通过引入信息熵和新种群来减少种群多样性的损失.与人工制定、向量评估遗传算法(VEGA)、多目标粒子群算法(MOPSO)、粒子群混合模拟退火遗传算法(GSPSO)的配水结果进行对比分析,SIGGA求解的配水时长由25.00,15.00,11.00,11.55 d缩短为10.00 d,渗漏损失由97.89×10^(4),71.76×10^(4),70.36×10^(4),32.63×10^(4) m^(3)减少到31.58×10^(4) m^(3),渠系水利用系数由0.651,0.706,0.745,0.828提高到0.833.SIGGA能够克服传统遗传算法(SGA),VEGA易陷入局部最优的缺点,可实现高效、精确地按需配水,为水资源的集约节约化利用提供理论参考.

Characteristic analysis and prevention on premature convergence in genetic algorithms

The identification and characteristics of premature convergence in genetic algorithms (GAs) are investigated Through a detailed quantitative analysis on the search capability and the degree of population diversity, the cause of premature convergence in GAs is recognized, and attributed to the maturation effect of the GAs: The minimum schema deduced from current population, which is the largest search space of a GA, converges to a homogeneous population in probability 1 ( so the search capability of the GA decreases and premature convergence occurs). It is shown that, as quantitative features of the maturation effect, the degree of population diversity converges to zero with probability 1, and the tendency for premature convergence is inversely proportional to the population size and directly proportional to the variance of the fitness ratio of zero allele at any gene position of the current population. Based on the theoretical analysis, several strategies for preventing premature convergence are suggested A specific GA formulation that converges assuredly to the global optimum without appearance of premature convergence is proposed.

双精英协同进化遗传算法

针对传统遗传算法早熟收敛和收敛速度慢的问题,提出一种双精英协同进化遗传算法(double elitecoevolutionary genetic algorithm,简称DECGA).该算法借鉴了精英策略和协同进化的思想,选择两个相异的、高适应度的个体(精英个体)作为进化操作的核心,两个精英个体分别按照不同的评价函数来选择个体,组成各自的进化子种群.两个子种群分别采用不同的进化策略,以平衡算法的勘探和搜索能力.理论分析证明,该算法具有全局收敛性.通过对测试函数的实验,其结果表明,该算法能搜索到几乎所有测试函数的最优解,同时能够有效地保持种群的多样性.与已有算法相比,该算法在收敛速度和搜索全局最优解上都有了较大的改进和提高.

遗传算法种群多样性的分析研究

种群的多样性是遗传算法进化的前提条件．本文提出用种群方差和熵两个量来全面刻画遗传算法中种群的多样性，分析了选择、交换和变异三个主要算子对种群方差和嫡的影响，同时比较了编码机制对种群多样性的影响．得出了一些重要的结论．

基于遗传优化的无人车横向模糊控制

以视觉导航式无人车DLUIV-1为控制对象,对其进行横向运动控制研究。建立视觉导航式无人车横向运动控制系统模型,对无人车的横向运动行为进行描述。在此基础上,分析预瞄距离对横向控制系统动态性能的影响,并建立考虑速度因素的预瞄距离计算公式。针对无人车具有非完整运动约束、高度非线性动态特性以及参数的不确定性等特点,提出基于遗传算法的无人车横向模糊控制策略,通过遗传算法对横向模糊控制器的隶属度函数参数和控制规则的自动优化,从而有效地确定出横向模糊控制器的隶属度函数和控制规则。最后通过仿真和实车试验对该横向模糊控制器进行验证和评价,仿真和试验结果表明,该横向控制器可保证无人车稳定准确地跟踪参考路径,且具有较强的鲁棒性。

模糊逻辑遗传算法的新方法

模糊逻辑是近年来提出的一种自适应调整策略,可以用来动态调整遗传算法的参数,以提高其性能。在此提出一种模糊逻辑遗传算法（FGA）的新模糊控制系统,它根据种群的进化速度和多样性的反馈信息,通过模糊逻辑控制器来对交叉率和变异率进行动态的自适应控制。实验结果表明,提出的FGA相对于简单遗传算法（SGA）,不仅在与实际最优值差值上获得高1~3个数量级的精度,而且还提高了收敛的速度,较好地解决了SGA容易陷入早熟状态、某些函数进化速度慢等问题。

中国对虾养殖群体与野生群体线粒体控制区序列的比较

比较分析了中国对虾养殖群体与野生群体mtDNA控制区序列。研究结果显示,在长度为563bp的mtDNA控制区片段中,中国对虾养殖群体与野生群体序列间存在一定程度的遗传差异。野生群体的基因多样度为0.9672,略高于养殖群体(0.9380),两群体间未检测到共享单倍型;野生群体mtDNA控制区核苷酸多样度为0.0106,养殖群体核苷酸多样度为0.0094,略低于野生群体的核苷酸多样度。基于K-2P模型计算得到中国对虾两群体间的平均遗传距离为0.0108,野生群体个体间平均遗传距离为0.0107,养殖群体个体间平均遗传距离为0.0095;单倍型最小跨度树和NJ系统树均未检测到显著的谱系结构。确切P检验显示两群体间没有随机交配现象(P=0.0009)。两群体间的FST值为0.0698(P=0.00),表明两群体间存在显著的遗传分化。

河鲈养殖与野生群体遗传多样性比较分析

河鲈（Perca fluviatilis），又名五道黑，五彩斑鱼，于比利牛斯半岛以外的全欧洲，以及黑海、里海和咸海等水系广泛分布，是我国乌伦古河水系及额尔齐斯河的主要土著鱼类。为鲈形目（Perciformes）、鲈亚目（Percoidei）、鲈科（Percidae）、鲈属（Perca）的一种名贵肉食性冷温带淡水鱼。

优化水稻群体种植模式与稻瘟病控制研究

【目的】探索水稻遗传多样性控制稻瘟病的最佳种植模式,探讨水稻品种群体结构对稻瘟病控制效果的影响。【方法】选择遗传背景差异较大的两个水稻品种——汕优63与黄壳糯,采用混合间栽法,研究不同种群结构的混合间栽种植模式对稻瘟病的控制效果。【结果】不同种群结构对黄壳糯稻瘟病的控制效果不同,相对防治效果随杂交稻群体所占比例的增加而增大,种群结构为1﹕15.01时对叶瘟的相对防治效果达到100%,种群结构为1﹕12.40时对穗颈瘟的相对防治效果达到100%。混合间栽的不同群体结构的复合产量都比净栽有所增加,土地当量比均大于1。【结论】黄壳糯与汕优63的群体比例为1﹕12.40～18.88是最优化的群体结构,不但对稻瘟病的控制效果好,而且产量高、经济效益好,是值得大面积推广的混合间栽种植模式。

高原鼢鼠线粒体谱系地理学和遗传多样性

高原鼢鼠是一类地下独居啮齿动物,为青藏高原特有种之一。为研究该物种的谱系地理学和遗传多样性,本文测定了采自青藏高原东部3个地理种群8个小种群共37个个体的线粒体D-loop区序列变异。在长度为627bp的序列中,共发现50个变异位点,定义了26种单倍型。该物种的单倍型多样性(Haplotype diversity,H)较高和核苷酸多样性(Nucleotide diversity,πn)较低。谱系分析得到3个稳定的分支,分别与采集的地理种群相吻合:同一地理种群内单倍型之间遗传差异小,而不同地理来源的单倍型之间存在较大区别。距离隔离分析表明高原鼢鼠的遗传分化与地理距离呈正相关。AMOVA分析同样表明地理种群之间存在显著差异:地理种群间变异占遗传变异的80.45%。高原鼢鼠的这种遗传结构特点可能主要是由于第四纪气候变迁、该物种稳定的地下生活环境和有限的迁移能力造成的。