ID | 原文 | 译文 |
8024 | 研究结果表明,选择性维修可有效解决多资源约束情况下面向任务的装备战场抢修决策问题; | The results show that the selective maintenance can effectively solve the resource constraint conditions more task oriented equipment battlefield repair decision problems; |
8025 | 通过优化抢修任务分工,可缩短装备抢修时间,能有效提高资源利用率和装备任务可靠度。 | By optimizing the repair task division of labor, equipment repair can shorten the time and task can effectively improve the utilization rate of resources and equipment reliability. |
8026 | 为改善常见的多目标分布估计算法在求解多目标优化问题的过程中存在的不足,即:对问题的规则特性考虑不够,对种群中异常解的处理不当,种群多样性容易丢失,过多的计算开销用于构建最优概率模型,提出一种基于聚类的新型多目标分布估计算法(clustering-based multi-objective estimation of distribution algorithm,CEDA)。 | To improve common multi-objective distribution estimation algorithm in solving multi-objective optimization problems in the process of the deficiencies, i.e., the property is not enough, the rules for the problem of the improper handling the exception in a population, species diversity easy to lose, too much computational overhead used to construct the optimal probability model, in this paper, a new multi-objective distribution estimation algorithm based on clustering (clustering -based multi - objective estimation of distribution algorithm, CEDA). |
8027 | CEDA在每一代运用凝聚层次聚类算法发掘种群个体的邻近结构,基于此结构,为每个个体构建一个多元高斯模型逼近种群结构并抽样产生新个体。 | CEDA condensation of every generation to use hierarchical clustering algorithm to discover individual species of adjacent structure, based on this structure, build a multivariate gaussian model approximation for each individual population structure and sampling to produce new individual. |
8028 | 为了降低建模计算开销,邻近个体共享相同的协方差矩阵建立高斯模型。 | Modeling in order to reduce the computational overhead, neighboring individuals share the same covariance matrix gaussian model is set up. |
8029 | 基于标准测试题的对比实验表明CEDA能够解决复杂的多目标优化问题。 | Based on the standard test of hcho CEDA can solve complex multi-objective optimization problem. |
8030 | 基于齿轮减速器优化设计的实际应用表明CEDA同样具有良好的实用性和优越性。 | Based on the practical application of gear reducer design optimization show that CEDA also has a good practicability and superiority. |
8031 | 针对雷达导引头机电结构组成复杂、性能指标测试数据信息利用率不足、使用传统基于数据驱动的状态预测方法精度不高的问题,借鉴相关向量机(relevance vector machine,RVM)和Dempster-Shafer(D-S)证据理论,提出了一种基于证据融合和改进局域RVM的状态预测方法。 | For radar seeker of complex mechanical structure, the performance test data information utilization is insufficient, the use of traditional state prediction method based on data driven precision is not high question, reference to relevance vector machine (relevance vector machine, RVM) and Dempster Shafer (D S) evidence theory, this paper proposes a fusion based on evidence and improve the local state of RVM prediction method. |
8032 | 首先,对标准RVM回归模型进行改进,通过构建方差高斯核函数(variance Gauss kernel function,VGKF)来提高核函数的全局性能和泛化能力; | First of all, to improve the standard RVM regression model, by building the variance of gaussian kernel function (variance Gauss kernel function, VGKF) to improve the global performance and generalization ability of the kernel function; |
8033 | 然后通过借鉴混沌序列局域预测法中邻近点个数的选取方法,利用Hannan-Quinn(H-Q)准则对训练空间预测嵌入维数进行优化,避免了主观选取的盲目性,完成了改进局域相关向量机模型(local relevance vector machine,LRVM)的构建; | Then through using the chaos sequence number of the adjacent point in local prediction method selection method, using kerri Hannan - Quinn (H, Q) guidelines for training space prediction embedding dimension optimization, avoid the blindness of subjective selection, completed the local relevance vector machine model (local relevance vector machine, LRVM) to build; |