ID 原文 译文
12074 根据控制变量的变化趋势,可进一步分析保障系统能力跃变的发生情况,从而为实现其过程控制奠定方法基础。 ‭According to the trend of the control variables can be further analysis support system and the ability to jump method basis to realize the process control.
12075 最后给出了相应的算例,表明了论文方法的有效性。 ‭Finally the corresponding example is given, which indicates that the validity of the method of the thesis. ‭
12076 Wiener过程广泛用于产品的性能退化建模,为了便于Bayesian统计推断大都采用随机参数的共轭先验分布。 Wiener process is widely used in product performance degradation model, in order to facilitate the Bayesian statistical inference are mostly adopt the conjugate prior distribution of random parameters.
12077 针对目前的二步法得到的超参数先验估计值精度不高的问题,研究了最大期望(expectation maximization,EM)算法在Wiener过程超参数先验估计中的应用。 Super parameter in two steps to get a priori estimate accuracy is not high, the maximum expected (expectation maximization, EM) algorithm in the application of super Wiener process parameters a priori estimates.
12078 EM算法将随机参数作为隐含变量对先验信息进行整体处理,利用随机参数的期望值代替其估计值,通过Expectation和Maximization组成的递归迭代过程寻找超参数的估计值。 EM algorithm is a random parameter as the hidden variables to the whole processing of a priori information, instead of using random parameter expectations of its estimate, through the Expectation and Maximization of recursive iteration process for super parameter estimates.
12079 仿真实验表明,EM算法相比于二步法提高了估计精度,特别是在采样数量较少时EM算法具有较大的精度优势。 Simulation results show that the EM algorithm compared to the two steps to improve the estimation precision, especially in the periods of low sampling number EM algorithm has higher precision.
12080 GaAs激光器实例应用表明EM算法不但具备很好的收敛性而且有良好的工程应用价值。 GaAs laser application instances show that the EM algorithm not only has good convergence and good engineering application value.
12081 为了促使Ad-hoc网络中的"自私"节点进行合作,提出了一种基于博弈论和粒子群优化的协作算法(Nash Bargaining of game theory and particle swarm optimization,NGPSO)。 In order to encourage "selfish" node in Ad hoc network, this paper proposes a collaborative algorithm based on game theory and particle swarm optimization (Nash Bargaining of game going and particle swarm optimization, NGPSO).
12082 在算法的第一阶段,源节点通过对中继节点转发的数据进行价格补偿,从而达到使中继节点参与合作的目的。 In the first phase of the algorithm, the source node to relay node forward price compensation data, so as to achieve the aim of the relay nodes to cooperate.
12083 将源节点的最优出价归结为纳什谈判问题,得到具有帕累托最优的激励价格,保证源节点和中继节点在合作中同时获得最佳收益;‭ ‭To attribute the source node, the optimal bid for Nash negotiations, with the pareto optimal incentive price, ensure that the source node and relay node at the same time get the best benefits in cooperation;