Monitoring censored lifetime data with a weighted‐likelihood scheme

Lifetime experiments are common in many research areas and industrial applications. Recently, process monitoring for lifetime observations has received increasing attention. However, some existing methods are inadequate as neither their in control (IC) nor out of control (OC) performance is satisfactory. In addition, the challenges associated with designing robust and flexible control schemes have yet to be fully addressed. To overcome these limitations, this article utilizes a newly developed weighted likelihood ratio test, and proposes a novel monitoring strategy that automatically combines the likelihood of past samples with the exponential weighted sum average scheme. The proposed Censored Observation‐based Weighted‐Likelihood (COWL) control chart gives desirable IC and OC performances and is robust under various scenarios. In addition, a self‐starting control chart is introduced to cope with the problem of insufficient reference samples. Our simulation shows a stronger power in detecting changes in the censored lifetime data using our scheme than using other alternatives. A real industrial example based on the breaking strength of carbon fiber also demonstrates the effectiveness of the proposed method. © 2016 Wiley Periodicals, Inc. Naval Research Logistics 63: 631–646, 2017     

基于粗集和最大熵的模式识别方法

用基于属性约简的粗集理论找出条件属性的最小属性集。对属性间为不确定因果关系的模式,计算在最大熵情况下发生的概率,通过比较概率来进行模式识别,实例分析和结论部分说明这种方法是有效的。     

Discriminating between the Weibull and log‐normal distributions

Log‐normal and Weibull distributions are the most popular distributions for modeling skewed data. In this paper, we consider the ratio of the maximized likelihood in choosing between the two distributions. The asymptotic distribution of the logarithm of the maximized likelihood ratio has been obtained. It is observed that the asymptotic distribution is independent of the unknown parameters. The asymptotic distribution has been used to determine the minimum sample size required to discriminate between two families of distributions for a user specified probability of correct selection. We perform some numerical experiments to observe how the asymptotic methods work for different sample sizes. It is observed that the asymptotic results work quite well even for small samples also. Two real data sets have been analyzed. © 2004 Wiley Periodicals, Inc. Naval Research Logistics, 2004     

Properties of some stochastic orders: A unified study

The notions of the likelihood ratio order of degree s (s ≥ 0) are introduced for both continuous and discrete integer‐valued random variables. The new orders for s = 0, 1, and 2 correspond to the likelihood ratio, hazard rate, and mean residual life orders. We obtain some basic properties of the new orders and their up shifted stochastic orders, and derive some closure properties of them. Such a study is meaningful because it throws an important light on the understanding of the properties of the likelihood ratio, hazard rate, and mean residual life orders. On the other hand, the properties of the new orders have potential applications. © 2003 Wiley Periodicals, Inc. Naval Research Logistics, 2004.     

最大生存概率下的编队防空目标分配研究

为研究编队目标武器分配方法,分析了编队防空体系在作战过程中武器系统火力单元状态、分配决策矩阵和目标序列状态的动态更新形式,建立了以编队生存概率最大为最优函数的动态目标分配优化模型。描述了仿真环境,运用不确定目标序列对分配过程进行了仿真。结果表明,所建立的模型能够反映实际情况,得到的关于集火、转火射击和优先分配策略对模型的工程应用具有实际指导意义。     

Double Mover–Stayer model on customer switching in telecommunications industry

Customer acquisition and customer retention are the most important challenges in the increasingly competitive telecommunications industry. Traditional studies of customer switching always assume that customers are homogeneous, and thus that model customer switching behavior follows a Markov formulation. However, this postulation is obviously inappropriate in most instances. Blumen et al. (Cornell Studies of Industrial and Labor Relations, Cornell University Press, Ithaca, NY, 1955) developed the Mover–Stayer (MS) model, a generalization of the Markov chain model, to relax the requirement of homogeneity and allow the presence of heterogeneity with two different types of individuals—“stayers,” who purchase the same kinds of products or services throughout the entire observation period; and “movers,” who look for variety in products or services over time. There are two purpose of this article. First, we extend the MS model to a Double Mover‐Stayer (DMS) model by assuming the existence of three types of individuals in the market: (1) stable and loyal customers, who have stable usage within the same company; (2) instable but loyal customers, whose usage varies within the same company over time; and (3) disloyal customers, who switch from one company to another to seek for new experiences or/and benefits. We also propose an estimation method for the DMS model. Second, we apply the DMS model to telecommunications data and demonstrate how it can be used for pattern identification, hidden knowledge discovery, and decision making. © 2012 Wiley Periodicals, Inc. Naval Research Logistics, 2012     

多源信息的验前分布融合方法研究

验前分布的获取和表示是B ayes理论应用中的一个关键问题。针对目前多源验前信息融合中存在的过分依赖专家信息的问题,提出了一种基于第2类极大似然估计原理(M L-II)确定验前分布权重的方法,该方法将现场试验数据看作是由其边缘分布产生的样本,然后根据不同验前分布下现场样本似然性的大小来确定其在验前分布融合中的作用,并以此进一步确定不同验前分布的权重因子。最后通过算例证明了该方法比基于专家信息的融合方法更为合理和有效。     

机载雷达与地面雷达的最大似然配准算法

空、地多雷达配准是空地一体化预警的前提。通过建立空中运动雷达与地面静止雷达的配准模型,以最大似然算法为基础,导出其空间系统误差配准参数及目标运动状态估计的具体公式,并对系统误差估计值的卡拉美-罗界进行了讨论。仿真结果表明,该算法具有较快的迭代收敛速度和较好的配准效果。     

On‐line parameter estimation for a partially observable system subject to random failure

In this paper, we study the on‐line parameter estimation problem for a partially observable system subject to deterioration and random failure. The state of the system evolves according to a continuous time homogeneous Markov process with a finite state space. The system state is not observable, except for the failure state. The information related to the system state is available at discrete times through inspections. A recursive maximum likelihood (RML) algorithm is proposed for the on‐line parameter estimation of the model. The RML algorithm proposed in the paper is considerably faster and easier to apply than other RML algorithms in the literature, because it does not require projection into the constraint domain and calculation of the gradient on the surface of the constraint manifolds. The algorithm is illustrated by an example using real vibration data. © 2006 Wiley Periodicals, Inc. Naval Research Logistics, 2006     

基于GA-ML-PMHT的多基站无源协同定位方法

针对无源协同定位系统中低可观测目标的航迹初始及维持问题,提出一种基于遗传算法的极大似然概率多假设的多基站无源协同定位方法。首先,建立多基站无源协同定位系统数学模型。其次,提出基于极大似然概率多假设的无源协同定位航迹初始算法,并首次利用遗传算法解决极大似然概率多假设中的优化求解问题,以提高目标检测跟踪性能。最后,通过滑窗法实现航迹维持。仿真结果表明,所提方法能够有效解决多基站无源协同定位系统中低可观测目标的航迹初始及维持问题。