共查询到20条相似文献,搜索用时 203 毫秒
1.
对非线性连续一离散系统的极大似然参数估计方法导出了一种递推计算灵敏度的新算
式.该算式借助二水平正交表的性质,避免了原灵敏度递推算式中的矩阵求逆运算.仿真实
例验证了该算法的实用性和有效性. 相似文献
2.
3.
4.
为了发掘嵌入在人脸样本的非线性结构信息,把核方法和基向量正交化思想引入局部敏感分析算法中,提出一种新的人脸识别算法-核正交局部敏感辨别分析(Kernel based Orthogonal Locality Sensitive Discriminant Analysis).并给出了算法的推导过程及计算步骤.首先用核方法提取人脸样本的非线性信息,并将其投影至高维非线性空间,然后采用局部敏感辨别分析做线性映射,最后采用施密特正交化方法得到正交的基向量,从而使算法更好地描述人脸非线性流形结构特征.在ORL和YaleB人脸库的人脸识别实验证明了所提算法的有效性. 相似文献
5.
6.
为了提高红外CO2气体传感器的探测灵敏度和精度,首先研究了不同镀膜对非色散扁锥腔CO2气体传感器的红外吸收效率和灵敏度的影响.然后搭建了湿度实验平台,着重研究了环境湿度对气体浓度测量结果的影响.最后,采用遗传算法优化的BP神经网络算法(GA-BP)对传感器进行了湿度补偿.实验结果表明:在室温条件下、0~2000×10-6浓度范围内,镀金腔体的CO2传感器具有更高的红外吸收效率和灵敏度;在40%~80%湿度范围内,CO2气体传感器的测量误差与相对湿度密切相关,最高误差达645×10-6.采用GA-BP算法数据融合补偿后,传感器湿度漂移得到了较好抑制,整体平均误差小于±110×10-6,表明CO2气体传感器的测量精度得到了大幅提升. 相似文献
7.
求解全局优化问题的混合自适应正交遗传算法 总被引:3,自引:0,他引:3
提出了一种基于正交实验设计的混合自适应正交遗传算法(hybrid self-adaptive orthogonal genetic algorithm,简称HSOGA)以求解全局优化问题,此算法利用正交实验设计方法设计交叉算子,并提出一种自适应正交交叉算子.该自适应正交交叉算子根据父代个体的相似度自适应地调整正交表的因素个数和对父代个体进行因素分割的位置,生成具有代表性的子代个体,以更好地搜索空间.此外,新算法利用自适应正交交叉算子生成均匀分布的初始种群,以保证初始群体的多样性.同时引入了局部搜索策略以提高算法局部搜索能力和收敛速度.通过14个高维的Benchmark函数验证了算法的通用性和有效性. 相似文献
8.
为实现多输入多输出(MIMO)-正交频分复用(OFDM)系统相干检测,提出一种新的基于叠加正交训练序列的MIMO-OFDM信道估计.详细证明了算法的估计准则并说明了训练序列的构造.通过叠加与信息序列不相关的正交训练序列,快速有效地估计出信道的冲激响应,同时使得最小均方误差达到最小值.与最小二乘法比,该算法避免了复杂的矩阵求逆运算,降低了运算量,且通过叠加训练序列,没有带宽损失.通过计算机仿真证明了算法的有效性及高性能. 相似文献
9.
正交泛函网络函数逼近理论及算法 总被引:1,自引:1,他引:0
基于正交函数的概念和特性,提出一种正交泛函网络新模型,给出了正交泛函网络学习算法.该算法是借助于正交函数性质和Lagrange乘数法做辅助函数,对泛函参数学习过程归结为求解一组线性方程组的过程.最后,通过函数逼近算例计算机仿真结果表明,该算法十分有效,具有模型简单、逼近精度高等特点. 相似文献
10.
11.
12.
This paper proposes a differential evolution algorithm based on ε-domination and orthogonal design method (ε-ODEMO) to solve power dispatch problem considering environment protection and saving energy. Besides the operation costs of thermal power plant, contaminative gas emission is also optimized as an objective. In the proposed algorithm, ε-dominance is adopted to make genetic algorithm obtain a good distribution of Pareto-optimal solutions in a small computational time, and the orthogonal design method can generate an initial population of points that are scattered uniformly over the feasible solution space, these modify the differential evolution algorithm (DE) to make it suit for multi-objective optimization (MOO) problems and improve its performance. A test hydrothermal system is used to verify the feasibility and effectiveness of the proposed method. Compared with other methods, the results obtained demonstrate the effectiveness of the proposed algorithm for solving the power environmentally-friendly dispatch problem. 相似文献
13.
本文提出一种改进的免疫算法。该算法用正交交叉生成初始种群,用精英交叉来增加群体的优良模式,用混合变异提高局部和全局寻优能力。将该方法应用于墨西哥湾地区典型地层模型AVO弹性参数反演。数值试验结果表明,和传统免疫算法相比,改进算法在反演精度和收敛速度上都有了很大的提高。 相似文献
14.
《Advances in Engineering Software》2007,38(5):301-311
A method for the acceleration of a fully implicit solution of nonlinear unsteady boundary value problem is presented. The principle of acceleration is for provide to the inexact Newton backtracking method a better initial guess, for the current time step, than the conventional choice from the previous time step. This initial guess is built on the reduced model obtained by a proper orthogonal decomposition of solutions at the previous time steps. This approach is appealing to GRID computing: spare processors may help to improve the numerical efficiency and to manage the computing in a reliable way. 相似文献
15.
Yuqing Hao 《International journal of systems science》2017,48(4):738-749
This paper considers the problem of structured output-feedback controller synthesis with finite frequency specifications. Based on the orthogonal space information of input matrix, an improved parameter-dependent Lyapunov function method is first proposed. Then, a two-stage construction method is designed, which depends on an initial centralised controller. Corresponding design conditions for three types of output-feedback controllers are presented in terms of unified representations. Moreover, heuristic algorithms are provided to explore the desirable controllers. Finally, the effectiveness of these proposed methods is illustrated via some practical examples. 相似文献
16.
针对Scatter Search算法在初始种群的分布欠均匀,难以搜索到全局最优,目标函数评价次数多等方面的缺点,把正交设计方法同Scatter Search算法结合起来,提出了Orthogonal Scatter Search(OSS)算法,以改进其不足,满足实际工程的需要.实验证明OSS算法优于SS算法,不仅目标函数评价次数少,收敛速度快,而且易于搜索到全局最优或者非常接近于全局最优,尤其是高维空间效果更加明显. 相似文献
17.
18.
Immune algorithm with orthogonal design based initialization, cloning, and selection for global optimization 总被引:1,自引:0,他引:1
In this study, an orthogonal immune algorithm (OIA) is proposed for global optimization by incorporating orthogonal initialization,
a novel neighborhood orthogonal cloning operator, a static hypermutation operator, and a novel diversity-based selection operator.
The orthogonal initialization scans the feasible solution space once to locate good points for further exploration in subsequent
iterations. Meanwhile, each row of the orthogonal array defines a sub-domain. The neighborhood orthogonal cloning operator
uses orthogonal arrays to scan uniformly the neighborhood around each antibody. Then the new algorithm explores each clone
by using hypermutation. The improved maturated progenies are selectively added to an external population by the diversity-based
selection, which retains one and only one external antibody in each sub-domain. The OIA is unique in three aspects: First,
a new selection method based on orthogonal arrays is provided in order to preserve diversity in the population. Second, the
orthogonal design with a modified quantization technique is introduced to generate initial population. Third, the orthogonal
design is introduced into the cloning operator. The performance comparisons of OIA with two known immune algorithms and three
evolutionary algorithms in optimizing eight benchmark functions and six composition functions indicate that OIA is an effective
algorithm for solving global optimization problems. 相似文献
19.
为提高正交遗传算法收敛速度和搜索精度,在正交遗传算法的基础上引入局部搜索策略,提出一种新的聚类局部搜索算子。利用正交算子初始化种群,保证初始群体分布的均匀性和多样性。通过正交算子在全局范围内进行全局搜索,使算法能在全局范围内收敛。采用聚类局部搜索算子对群体进行局部搜索,以增强算法的收敛速度和搜索精度。对7个高维的Benchmark函数进行测试,仿真实验结果表明,与其他算法相比,该算法具有更好的搜索精度、收敛速度和全局寻优的能力。 相似文献
20.
提出在超分辨率复原中使用基于隐含重起Arnoldi过程来高效计算正则化参数的方法。通过隐含重起Arnoldi过程,可选择一个较好的初始向量。该方法将大型稀疏系统矩阵投影到Krylov子空间上并表达成一个小型稠密的Hessenberg矩阵。该方法可减少正则化参数的计算代价。 相似文献