改进遗传算法在配电网无功优化中的应用

遗传算法是近年来被广泛应用于无功优化的一种新型的优化算法。结合配电网的特征，对遗传算法的选择操作、交叉和变异算子、终止判据等核心操作进行改进，提出一种适合于配电网无功优化的改进遗传算法。计算实例表明，其优化效果优于传统遗传算法。     

基于遗传算法的污水换热器的优化研究

以污水换热器的年总费用为目标函数,应用遗传算法对污水换热器进行了设计参数的优化计算.介绍了遗传算法工具箱的使用方法.该方法克服了传统优化算法的缺陷;优化结果更加符合工程实际.并指出了减小污水换热器年总费用的主要方向.     

一种用于MPPT的改进型遗传算法

在众多最大功率点跟踪(MPPT)算法中,遗传算法具有收敛速度快的优点,但实际应用中其存在准确率较低、在最大功率点附近摆动的问题,所以在传统遗传算法的基础上引入扰动观察法来提高遗传算法的准确率,并将改进型遗传算法和传统遗传算法进行了仿真对比。结果表明,改进型遗传算法具有更高的准确率,可提高光伏阵列的发电效率。     

基于遗传算法的汽轮机非线性调节系统的参数辨识研究

简要介绍了遗传算法应用于参数辨识的基本思想，并将其应用于汽轮机非线性调节系统的参数辨识，结果表明，采用遗传算法可准确地辨识系统中死区，限幅等非线性发生部位和参数，辨识结果准确可靠，相对误差在2%以内，与传统的辨识方法相比，具有辨识精度高，收敛速度快的优点，结合计算机仿真，可以实现系统的性能预测，控制优化，状态监测与故障诊断。     

遗传算法和Rosenbrock法在水文预报汇流参数优选中的比较研究

将遗传算法和Rosenbrock法应用于陕西石头河水库流域，并对优选结果进行了比较研究。研究表明，只要初值选择得当，无论采用何种方法来优选三水源新安江模型中的6个参数，均可获得相近的结果和相同的预报合格率，但从使用方便的角度看，遗传算法优于Rosenbrock法。     

利用面阵CCD进行火焰温度分布测量(Ⅱ)——三维截面温度场的测量

利用CCD（电荷耦合器件）进行火焰截面温度分布测量的测试系统，作了简化处理建立了实用的模型。对遗传算法的略改进后，用以求解所建立的模型以重建出待测的火焰截面温度分布。最后对遗传算法的数值性质进行了分析，并在油煤混烧试验台上进行了试验，给出了测试结果。     

基于神经网络的输变电工程造价研究

本文采用神经网络算法对输变电工程造价进行研究,以输变电工程造价的影响因素为输入变量,成本评价值为输出结果,针对神经网络算法的不足,采用遗传算法对神经网络进行优化,实现输变电工程造价的稳定有效评价。在Matlab环境下进行了仿真,并与传统的神经网络进行了比较。结果表明,遗传算法改进后的神经网络模型在实际应用中取得了较好的效果,可以指导工程造价管理。     

基于遗传算法和BP神经网络的电价预测

给出了一个发电例竞价模型中应用遗传算法与BP算法结合进行市场出清价预测的实例。与使用传统BP神经网络预测的方法进行比较，结果表明，该方法具有更高的预测精度，并总能收敛于全局最优解。     

人工神经网络在混合智能故障诊断技术中的应用研究

故障诊断的关键是寻找一种使诊断结果更为有效的方法。人工神经网络作为一种新兴的故障诊断方法，越来越受到人们的关注。然而，对于复杂的系统，单一的传统神经网络很难给出理想的结果。本文重点对神经网络与其它诊断方式融合的混合智能技术，即神经网络与专家系统、模糊控制、小波分析和遗传算法的结合以及集成神经网络等在故障诊断中的应用进行了综述。这些方法已应用到实践中，并取得了一定的成果。     

基于改进遗传算法优化的小波神经网络短期负荷预测模型

针对传统小波神经网络在电力系统短期负荷预测中存在预测结果的精确度依赖初始网络参数的问题,提出了一种基于改进遗传算法优化的小波神经网络短期负荷预测模型。为了保证神经网络在训练过程中,各个层的权值和阈值按最优方向变化,将遗传算法引入小波神经网络,利用遗传算法寻优能力指导权值和阈值进行优化。将概率分布策略用于遗传算法的种群交叉和变异过程,解决遗传算法在中后期搜索精度差,收敛速度慢等问题。应用结果表明,与基本的小波神经网络的预测模型相比,在只考虑短期负荷历史数据的情况下,通过均方根误差计算比较,基于改进遗传算法优化的小波神经网络短期负荷预测模型具有更高的预测精度。     

Application of a Genetic Algorithm for Thermal Design of Fin-and-Tube Heat Exchangers

Instead of the traditional trial-and-error process, a genetic algorithm (GA) is successfully applied to thermal design of fin-and-tube heat exchangers (FTHEs). The design method uses a GA to search and optimize structure sizes of FTHEs. The minimum total weight or total annual cost of FTHEs is taken as the objective function in the GA, respectively. Seven design parameters are varied for the optimization objectives. The implementation of the design method consists of a GA routine and a thermal design routine. In the GA routine, binary coding for tournament selection, uniform crossover, and one-point mutation is adopted. In the thermal design routine, thermal design of the FTHE is carried out according to the conditions of the structure sizes that the genetic algorithm generated, and the log-mean temperature difference method is used to determine the heat transfer area under the combined structure sizes for a given heat duty. Optimization shows that it is possible to achieve a great reduction in cost or weight, whenever such objectives have been chosen for minimization. The method is universal and may be used for thermal design and optimization of FTHEs under different specified duties.     

基于遗传算法的电力系统综合负荷模型的建模与仿真

遗传算法是一种具有全局寻优能力的随机搜索算法,但其本身存在收敛速度慢和易早熟的缺陷。为此,引入一种改进的遗传算法用于电力负荷综合建模。该算法具有克服早熟、避免近亲繁殖和自适应的优良特性。应用建模实例表明,遗传算法辨识所得负荷模型的描述精度很高,其模型参数呈现很好的稳健性,从而有效地克服了传统优化方法的模型参数分散性。     

二倍体遗传算法求解梯级水电站日优化调度问题

应用二倍体遗传算法（ＤＧＡ）对梯级水电站日优化调度问题求解,其算法采用了两条等长度的二进制码表示个体,借助于基因显性机制,将个体基因码链与梯级系统日调度计划联系起来．基因显性机制采用一种简便的布尔函数关系实现．杂交算子采用个体基因链交换与重组方式实现,具有一致杂交算子的效果．仿真计算结果验证了算法的有效性     

基于GA-LMBP神经网络模型的大坝渗流压力预报分析

为克服传统BP神经网络在渗流压力预测过程中收敛慢、计算量大和易陷入局部极小等缺陷,依据渗流压力的影响因素,研究了模型的结构和输入输出因子,建立了基于遗传算法和LM算法相结合的GA-LMBP神经网络的大坝渗流压力预测模型,即通过遗传算法(GA)的选择、交叉和变异操作得到BP网络的一组全局最优近似解(即网络的初始权值和阈值),再以该近似解为初值,利用LM算法对BP网络进行优化训练,将训练好的网络用于渗流压力的预测。实例应用结果表明,在相同精度的要求下,GA-LMBP神经网络模型收敛速度快、预测精度高,对大坝渗流压力的预测效果更佳,是值得采用的一种模型。     

Parameter extraction of solar cell models based on adaptive differential evolution algorithm

In this paper, a new approach based on adaptive Differential Evolution Technique (DET) is used to extract the parameters of solar cell models accurately. The adaption is achieved through crossover and mutation factor. It is indicated that the optimization with an objective function can minimize the difference between the estimated and measured values. In order to verify the performance of the proposed system, three different solar cell models: single diode model, double diode model, and photovoltaic module are used to extract the parameters. The analysis is performed by using the voltage and current data sets. The result shows that the proposed DET outperforms these other methods: chaos particle swarm optimization (CPSO), genetic algorithm (GA), harmony search algorithm (HSA), and artificial bee swarm optimization (ABSO). Furthermore, the DET technique is practically validated by two different solar cell types such as monocrystalline and multi-crystalline and modules. The performance of solar cell models has been verified and the outcome shows that it is an optimal method which suits the parameter extraction of solar cells and modules.     

Application of genetic algorithm with a novel adaptive scheme for the identification of induction machine parameters

This work presents a powerful application of genetic algorithm (GA) for the identification of Park's model electric parameters of an induction machine. Such a model is used in control techniques for variable speed drives. GA is considered as the most recent product of the artificial intelligence techniques. By its evolutionary character, it solves efficient electrical engineering problems despite its relative slowness in its standard form. Such shortcoming has been dealt with by incorporating a novel adaptive scheme. The suggested adaptive GA aims at accurately solving a nonlinear fitting optimization problem within a reduced computing time. The yielded solution of parameters produces, according to the machine model, the closest possible curves to those of the references. Finally, for the purpose of validation, the obtained machine performances of the adaptive GA method are compared with both those of references and those of a near-least-square-error estimator using experimental variable load measurements.     

Power economic dispatch using a hybrid genetic algorithm

This letter outlines a hybrid genetic algorithm (HGA) for solving the economic dispatch problem. The algorithm incorporates the solution produced by an improved Hopfield neural network (NN) as a part of its initial population. Elitism, arithmetic crossover and mutation are used in the GAs to generate successive sets of possible operating policies. The technique improves the quality of the solution and reduces the computation time, and is compared with the classical optimization technique, an improved Hopfield NN approach (IHN), a fuzzy logic controlled GA and an improved GA     

Genetic algorithm based optimal chiller loading for energy conservation

This study employs genetic algorithm (GA) to solve optimal chiller loading (OCL) problem. GA overcomes the flaw that Lagrangian method is not suitable as there is non-convex kW-PLR function in a system. This study uses the part load ratios (PLR) of chiller units to binary code chromosomes, and execute reproduction, crossover and mutation operation. Since the semiconductor plant is the largest a/c load for power consumption, it is used as an example in this paper. After analysis and comparison of the case study, we are confident to say that this method not only solves the problem of Lagrangian method, but also produces results with high accuracy within a rapid timeframe. It can be perfectly applied to the operation of air conditioning systems.     

遗传算法的群体模式多样性与模式生长方程(Ⅰ)

引入个体平均相似度来衡量群体的基因模式多样性,分析讨论了遗传算子对个体平均相似度的影响．     

An Inverse Analysis for Parameter Estimation Applied to a Non-Fourier Conduction–Radiation Problem

Retrieval of parameters in a non-Fourier conduction and radiation heat transfer problem is reported. The direct problem is formulated using the lattice Boltzmann method (LBM) and the finite-volume method (FVM). The divergence of radiative heat flux is computed using the FVM, and the LBM formulation is employed to obtain the temperature field. In the inverse method, this temperature field is taken as exact. Simultaneous estimation of parameters, namely, the extinction coefficient and the conduction–radiation parameter, is done by minimizing the objective function. The genetic algorithm (GA) is used for this purpose. The accuracies of the estimated parameters are studied for the effects of measurement errors and genetic parameters such as the crossover and mutation probabilities, the population size, and the number of generations. The LBM-FVM in combination with GA has been found to provide a correct estimate of parameters.