本文在Blasone研究工作的基础上,进一步提出了基于马尔科夫链-蒙特卡洛算法的改进通用似然不确定性估计方法(Markov Chain-Monte Carlo based Modified Generalized Likelihood Uncertainty Estimation,MMGLUE)。该方法结合近年来被广...本文在Blasone研究工作的基础上,进一步提出了基于马尔科夫链-蒙特卡洛算法的改进通用似然不确定性估计方法(Markov Chain-Monte Carlo based Modified Generalized Likelihood Uncertainty Estimation,MMGLUE)。该方法结合近年来被广泛用于推求参数后验分布的MCMC方法,对基于Monte Carlo随机取样方法的传统GLUE方法进行改进,并以预测区间性质最优为标准,对可行参数组阈值进行判断与选择,提出了衡量预测区间对称性的标准,并就预测区间性质与可行参数组个数的相关关系进行了探索。在汉江玉带河流域的实例研究证明,MMGLUE方法较传统的GLUE方法能够推求出性质更为优良的预测区间,从而更真实合理地反映水文模型的不确定性。展开更多
炉次计划是炼钢-连铸批量计划的关键计划之一,主要功能是考虑如何充分利用转炉容量及板坯属性使用最少的炉次组织生产,其编制的好坏直接影响后续计划制定及各工序生产节奏.基于目前炉次计划模型存在无法分辨板坯宽度区间相交程度、炉容...炉次计划是炼钢-连铸批量计划的关键计划之一,主要功能是考虑如何充分利用转炉容量及板坯属性使用最少的炉次组织生产,其编制的好坏直接影响后续计划制定及各工序生产节奏.基于目前炉次计划模型存在无法分辨板坯宽度区间相交程度、炉容量利用效率及炉次内板坯间关系的不足及一维装箱理论没有考虑剩余箱子容量及箱子内物品间关系的问题,将炉次计划归结为考虑炉次剩余容量及板坯间关系的一维装箱问题,并建立数学规划模型.基于炉次计划模型解矩阵的特点及迭代局部搜索(iterated local search,ILS)和变邻域搜索(variable neighborhood search,VNS)的优点,提出了将VNS算法作为ILS算法中局部搜索的混合算法.最后利用现场实际数据对模型和算法的有效性进行了对比验证,结果表明炉次计划模型及混合算法是有效的.展开更多
A Poisson distribution is well used as a standard model for analyzing count data. Most of the usual constructing confidence intervals are based on an asymptotic approximation to the distribution of the sample mean by ...A Poisson distribution is well used as a standard model for analyzing count data. Most of the usual constructing confidence intervals are based on an asymptotic approximation to the distribution of the sample mean by using the Wald interval. That is, the Wald interval has poor performance in terms of coverage probabilities and average widths interval for small means and small to moderate sample sizes. In this paper, an approximate confidence interval for a Poisson mean is proposed and is based on an empirically determined the tail probabilities. Simulation results show that the pro- posed interval outperforms the others when small means and small to moderate sample sizes.展开更多
In this paper, a novel hybrid method is presented for finding global optimization of an objective function. Based on the interval computation, this hybrid method combines interval deterministic method and stochastic e...In this paper, a novel hybrid method is presented for finding global optimization of an objective function. Based on the interval computation, this hybrid method combines interval deterministic method and stochastic evolution method. It can find global optimization quickly while ensuring the deterministic and stability of the algorithm. When using interval computation, extra width constraints accuracy of interval computation results. In this paper, a splitting method to reduce the extra width is introduced. This method is easy and it can get a more precise interval computation result. When finding the global optimization, it can increase the efficiency of pruning. Several experiments are given to illustrate the advantage of the new hybrid method.展开更多
A study of the evolution of the pulse width in homogeneous dielectric barrier dis- charge at atmospheric pressure with helium as the working gas is reported by using a one- dimensional fluid model. In this paper, a ne...A study of the evolution of the pulse width in homogeneous dielectric barrier dis- charge at atmospheric pressure with helium as the working gas is reported by using a one- dimensional fluid model. In this paper, a new computational method is presented to estimate the pulse width through calculating the time interval between the breakdown voltage and the extinguishing voltage. The effects on the discharge characteristics of the applied voltage and exci- tation frequency are studied based on the computational data. The results of the simulation show that the pulse width is observed to be narrower and the time intervals between two consecutive current pulses decrease with increasing amplitude and excitation frequency, which indicates that the homogeneous discharge is susceptible to the filamentary mode. The simulation results support the conclusion that in order to restrain the transition from the glow mode to filamentary mode, the applied voltage and excitation frequency should be kept within an appropriate range.展开更多
文摘本文在Blasone研究工作的基础上,进一步提出了基于马尔科夫链-蒙特卡洛算法的改进通用似然不确定性估计方法(Markov Chain-Monte Carlo based Modified Generalized Likelihood Uncertainty Estimation,MMGLUE)。该方法结合近年来被广泛用于推求参数后验分布的MCMC方法,对基于Monte Carlo随机取样方法的传统GLUE方法进行改进,并以预测区间性质最优为标准,对可行参数组阈值进行判断与选择,提出了衡量预测区间对称性的标准,并就预测区间性质与可行参数组个数的相关关系进行了探索。在汉江玉带河流域的实例研究证明,MMGLUE方法较传统的GLUE方法能够推求出性质更为优良的预测区间,从而更真实合理地反映水文模型的不确定性。
文摘炉次计划是炼钢-连铸批量计划的关键计划之一,主要功能是考虑如何充分利用转炉容量及板坯属性使用最少的炉次组织生产,其编制的好坏直接影响后续计划制定及各工序生产节奏.基于目前炉次计划模型存在无法分辨板坯宽度区间相交程度、炉容量利用效率及炉次内板坯间关系的不足及一维装箱理论没有考虑剩余箱子容量及箱子内物品间关系的问题,将炉次计划归结为考虑炉次剩余容量及板坯间关系的一维装箱问题,并建立数学规划模型.基于炉次计划模型解矩阵的特点及迭代局部搜索(iterated local search,ILS)和变邻域搜索(variable neighborhood search,VNS)的优点,提出了将VNS算法作为ILS算法中局部搜索的混合算法.最后利用现场实际数据对模型和算法的有效性进行了对比验证,结果表明炉次计划模型及混合算法是有效的.
文摘A Poisson distribution is well used as a standard model for analyzing count data. Most of the usual constructing confidence intervals are based on an asymptotic approximation to the distribution of the sample mean by using the Wald interval. That is, the Wald interval has poor performance in terms of coverage probabilities and average widths interval for small means and small to moderate sample sizes. In this paper, an approximate confidence interval for a Poisson mean is proposed and is based on an empirically determined the tail probabilities. Simulation results show that the pro- posed interval outperforms the others when small means and small to moderate sample sizes.
基金Project supported by the Natural High-Technology Research and Development Program of China(Grant No.2009AA012201)the Major Technology Research and Development Program of Shanghai Municipality(Grant No.08DZ501600)the Shanghai Leading Academic Discipline Project(Grant No.J50103)
文摘In this paper, a novel hybrid method is presented for finding global optimization of an objective function. Based on the interval computation, this hybrid method combines interval deterministic method and stochastic evolution method. It can find global optimization quickly while ensuring the deterministic and stability of the algorithm. When using interval computation, extra width constraints accuracy of interval computation results. In this paper, a splitting method to reduce the extra width is introduced. This method is easy and it can get a more precise interval computation result. When finding the global optimization, it can increase the efficiency of pruning. Several experiments are given to illustrate the advantage of the new hybrid method.
基金supported by National Natural Science Foundation of China(No.51077089)
文摘A study of the evolution of the pulse width in homogeneous dielectric barrier dis- charge at atmospheric pressure with helium as the working gas is reported by using a one- dimensional fluid model. In this paper, a new computational method is presented to estimate the pulse width through calculating the time interval between the breakdown voltage and the extinguishing voltage. The effects on the discharge characteristics of the applied voltage and exci- tation frequency are studied based on the computational data. The results of the simulation show that the pulse width is observed to be narrower and the time intervals between two consecutive current pulses decrease with increasing amplitude and excitation frequency, which indicates that the homogeneous discharge is susceptible to the filamentary mode. The simulation results support the conclusion that in order to restrain the transition from the glow mode to filamentary mode, the applied voltage and excitation frequency should be kept within an appropriate range.
