备件需求过程的MAP数据拟合算法研究

为了将备件需求过程表示为马尔可夫到达过程(Markovian arrival process, MAP)形式,设计了备件需求到达流的MAP拟合算法.首先,采用EM算法将备件需求到达间隔时间拟合成Hyper-Erlang分布形式,然后利用MAP性质和Bayes公式推导出生成元矩阵的计算公式;随后设计了一个完整的数据拟合流程,并通过实例对算法的效果和效率与已有研究进行了对比.结果表明,该算法在确保拟合效果的同时,能够有效提升拟合效率.     

考虑不完全维修的可修串联系统可用度模型

可用度是衡量系统可靠性、维修性水平的一个重要指标.提出一类基于gamma劣化过程的可修串联系统的可用度计算方法.该方法从构成系统部件的状态出发,用gamma过程刻画部件的退化失效规律,同时考虑系统维修效果的不完全性,在此基础上推导出系统可用度的表达式.最后用一个算例验证了研究模型的合理性.     

Quality control chart design under Jidoka

We consider design of control charts in the presence of machine stoppages that are exogenously imposed (as under jidoka practices). Each stoppage creates an opportunity for inspection/repair at reduced cost. We first model a single machine facing opportunities arriving according to a Poisson process, develop the expressions for its operating characteristics and construct the optimization problem for economic design of a control chart. We, then, consider the multiple machine setting where individual machine stoppages may create inspection/repair opportunities for other machines. We develop exact expressions for the cases when all machines are either opportunity‐takers or not. On the basis of an approximation for the all‐taker case, we then propose an approximate model for the mixed case. In a numerical study, we examine the opportunity taking behavior of machines in both single and multiple machine settings and the impact of such practices on the design of an X – Q C chart. Our findings indicate that incorporating inspection/repair opportunities into QC chart design may provide considerable cost savings. © 2009 Wiley Periodicals, Inc. Naval Research Logistics 2009     

Technical note: A computationally efficient algorithm for undiscounted Markov decision processes with restricted observations

We present a computationally efficient procedure to determine control policies for an infinite horizon Markov Decision process with restricted observations. The optimal policy for the system with restricted observations is a function of the observation process and not the unobservable states of the system. Thus, the policy is stationary with respect to the partitioned state space. The algorithm we propose addresses the undiscounted average cost case. The algorithm combines a local search with a modified version of Howard's (Dynamic programming and Markov processes, MIT Press, Cambridge, MA, 1960) policy iteration method. We demonstrate empirically that the algorithm finds the optimal deterministic policy for over 96% of the problem instances generated. For large scale problem instances, we demonstrate that the average cost associated with the local optimal policy is lower than the average cost associated with an integer rounded policy produced by the algorithm of Serin and Kulkarni Math Methods Oper Res 61 (2005) 311–328. © 2008 Wiley Periodicals, Inc. Naval Research Logistics 2009     

炮兵作战决策方案优选的方法

炮兵作战方案的选择,是炮兵作战指挥决策的关键环节,其合理与否,直接关系到炮兵作战效能的发挥和作战的成败.根据炮兵作战的实际,阐述了炮兵作战方案优选的依据,给出了运用层次分析法确定影响作战方案选择的各因素权重的方法步骤,在对优选依据的建模要素进行分析的基础上,构建了每个要素的效用函数计算模型,并给出了评估方案的计算方法,提供了模型应用的一般步骤.     

基于灰色关联法的飞行模拟器方案评估

对三个飞行训练模拟器方案进行灰色关联评估。根据装备效能分析原则,结合飞行训练模拟器组成结构的自身特点,确定了影响飞行训练模拟器效能的主要指标,建立了飞行模拟器效能评估体系,应用层次分析法,计算出各指标的权重,再利用灰色理论原理,对效能体系中主要指标进行了灰色综合评估,然后把灰色综合评估值与费用结合,确定评估矩阵,按照灰色关联法的步骤,计算出各方案与理想方案的关联度。结果是比较符合实际情况的,并且应用到某型飞行模拟器方案论证中。     

多决策目标排序的层次分析与灰色关联法

战争中对打击目标排序是下定作战决心的前提,是战场信息处理的重要内容.随着军事科技的发展和战术运用要求的提高,决定目标排序的因素不断增多,作战环境更加复杂,单一指标已不能满足需求.采用层次分析和灰色关联相结合的方法对多决策目标进行分析,为具有多决策因子目标提供了一种排序方法.灰色数据的白化和精确数据的直接使用提高了数据的效率,使得不同特点的目标具有可比性.实例表明,该方法行之有效.     

特殊半鞅的强大数定律

利用特殊半鞅的收敛定理和一般形式的Kronecker引理,给出了特殊半鞅和非负特殊半鞅强大数定律的一般形式,推广和完善了已有的结果.     

坦克发动机自行加温过程研究

为改进坦克发动机冷却系统,以12150L型坦克发动机为例,通过建立公式对发动机自行 加温过程进行了计算,得出不同条件下冷却液温度随时间的变化关系;并通过试验验证。由此为改进冷 却系统提供了理论依据。     

Optimal control policies in service systems with limited information on the downstream stage

Existing models in multistage service systems assume full information on the state of downstream stages. In this paper, we investigate how much the lack of such information impacts jobs' waiting time in a two‐stage system with two types of jobs at the first stage. The goal is to find the optimal control policy for the server at the first stage to switch between type‐1 and type‐2 jobs, while minimizing the long‐run average number of jobs in the system. We identify control policies and corresponding conditions under which having no or partial information, the system can still capture the most benefit of having full information.