On the exponentially weighted moving variance

MacGregor and Harris (J Quality Technol 25 (1993) 106–118) proposed the exponentially weighted mean squared deviation (EWMS) and the exponentially weighted moving variance (EWMV) charts as ways of monitoring process variability. These two charts are particularly useful for individual observations where no estimate of variability is available from replicates. However, the control charts derived by using the approximate distributions of the EWMS and EWMV statistics are difficult to interpret in terms of the average run length (ARL). Furthermore, both control charting schemes are biased procedures. In this article, we propose two new control charts by applying a normal approximation to the distributions of the logarithms of the weighted sum of chi squared random variables, which are respectively functions of the EWMS and EWMV statistics. These new control charts are easy to interpret in terms of the ARL. On the basis of the simulation studies, we demonstrate that the proposed charts are superior to the EWMS and EWMV charts and they both are nearly unbiased for the commonly used smoothing constants. We also compare the performance of the proposed charts with that of the change point (CP) CUSUM chart of Acosta‐Mejia (1995). The design of the proposed control charts is discussed. An example is also given to illustrate the applicability of the proposed control charts. © 2009 Wiley Periodicals, Inc. Naval Research Logistics, 2009     

Performance analysis of queue length monitoring of M/G/1 systems

This study investigates the statistical process control application for monitoring queue length data in M/G/1 systems. Specifically, we studied the average run length (ARL) characteristics of two different control charts for detecting changes in system utilization. First, the nL chart monitors the sums of successive queue length samples by subgrouping individual observations with sample size n. Next is the individual chart with a warning zone whose control scheme is specified by two pairs of parameters, (upper control limit, d_u) and (lower control limit, d_l), as proposed by Bhat and Rao (Oper Res 20 (1972) 955–966). We will present approaches to calculate ARL for the two types of control charts using the Markov chain formulation and also investigate the effects of parameters of the control charts to provide useful design guidelines for better performance. Extensive numerical results are included for illustration. © 2011 Wiley Periodicals, Inc. Naval Research Logistics, 2011     

Monitoring poisson count data with probability control limits when sample sizes are time varying

This article considers the problem of monitoring Poisson count data when sample sizes are time varying without assuming a priori knowledge of sample sizes. Traditional control charts, whose control limits are often determined before the control charts are activated, are constructed based on perfect knowledge of sample sizes. In practice, however, future sample sizes are often unknown. Making an inappropriate assumption of the distribution function could lead to unexpected performance of the control charts, for example, excessive false alarms in the early runs of the control charts, which would in turn hurt an operator's confidence in valid alarms. To overcome this problem, we propose the use of probability control limits, which are determined based on the realization of sample sizes online. The conditional probability that the charting statistic exceeds the control limit at present given that there has not been a single alarm before can be guaranteed to meet a specified false alarm rate. Simulation studies show that our proposed control chart is able to deliver satisfactory run length performance for any time‐varying sample sizes. The idea presented in this article can be applied to any effective control charts such as the exponentially weighted moving average or cumulative sum chart. © 2013 Wiley Periodicals, Inc. Naval Research Logistics 60: 625–636, 2013     

Power approximations in the economic design of control charts

A new approximate method is proposed for the economic design of control charts based on an estimate of the power of the control chart at optimality. Multiple linear regression is employed for the derivation of the approximate formula expressing the power of the control chart as a function of the model parameters. A simple optimization procedure is then used to determine the economic design of the control chart for the predicted value of the chart's detection power. The application of the new approach is illustrated through Duncan's models for variables control charts for processes subject to single and multiple assignable causes. Evaluation of the performance of the approximate method indicates that the approximate control chart design is very close to the exact optimum while its implementation requirements are reduced.     

A spatial rank‐based multivariate EWMA control chart

Nonparametric control charts are useful in statistical process control when there is a lack of or limited knowledge about the underlying process distribution, especially when the process measurement is multivariate. This article develops a new multivariate self‐starting methodology for monitoring location parameters. It is based on adapting the multivariate spatial rank to on‐line sequential monitoring. The weighted version of the rank‐based test is used to formulate the charting statistic by incorporating the exponentially weighted moving average control scheme. It is robust to non‐normally distributed data, easy to construct, fast to compute and also very efficient in detecting multivariate process shifts, especially small or moderate shifts which occur when the process distribution is heavy‐tailed or skewed. As it avoids the need for a lengthy data‐gathering step before charting and it does not require knowledge of the underlying distribution, the proposed control chart is particularly useful in start‐up or short‐run situations. A real‐data example from white wine production processes shows that it performs quite well. © 2012 Wiley Periodicals, Inc. Naval Research Logistics 59: 91–110, 2012     

Performance and properties of Q‐Statistic monitoring schemes

In this article, we study the Shewhart chart of Q statistics proposed for the detection of process mean shifts in start‐up processes and short runs. Exact expressions for the run‐length distribution of this chart are derived and evaluated using an efficient computational procedure. The procedure can be considerably faster than using direct simulation. We extend our work to analyze the practice of requiring multiple signals from the chart before responding, a practice sometimes followed with Shewhart charts. The results show that waiting to receive multiple signals severely reduces the probability of quickly detecting shifts in certain cases, and therefore may be considered a risky practice. Operational guidelines for practitioners implementing the chart are discussed. © 2009 Wiley Periodicals, Inc. Naval Research Logistics, 2009     

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     

Kurtosis correction method for X̄ and R control charts for long‐tailed symmetrical distributions

This paper proposes a kurtosis correction (KC) method for constructing the X? and R control charts for symmetrical long‐tailed (leptokurtic) distributions. The control charts are similar to the Shewhart control charts and are very easy to use. The control limits are derived based on the degree of kurtosis estimated from the actual (subgroup) data. It is assumed that the underlying quality characteristic is symmetrically distributed and no other distributional and/or parameter assumptions are made. The control chart constants are tabulated and the performance of these charts is compared with that of the Shewhart control charts. For the case of the logistic distribution, the exact control limits are derived and are compared with the KC method and the Shewhart method. © 2007 Wiley Periodicals, Inc. Naval Research Logistics, 2007     

Combining standardized time series area and Cramér–von Mises variance estimators

We propose three related estimators for the variance parameter arising from a steady‐state simulation process. All are based on combinations of standardized‐time‐series area and Cramér–von Mises (CvM) estimators. The first is a straightforward linear combination of the area and CvM estimators; the second resembles a Durbin–Watson statistic; and the third is related to a jackknifed version of the first. The main derivations yield analytical expressions for the bias and variance of the new estimators. These results show that the new estimators often perform better than the pure area, pure CvM, and benchmark nonoverlapping and overlapping batch means estimators, especially in terms of variance and mean squared error. We also give exact and Monte Carlo examples illustrating our findings.© 2007 Wiley Periodicals, Inc. Naval Research Logistics, 2007     

Skewness correction X̄ and R charts for skewed distributions

This paper proposes a skewness correction (SC) method for constructing the and R control charts for skewed process distributions. Their asymmetric control limits (about the central line) are based on the degree of skewness estimated from the subgroups, and no parameter assumptions are made on the form of process distribution. These charts are simply adjustments of the conventional Shewhart control charts. Moreover, the chart is almost the same as the Shewhart chart if the process distribution is known to be symmetrical. The new charts are compared with the Shewhart charts and weighted variance (WV) control charts. When the process distribution is in some neighborhood of Weibull, lognormal, Burr or binomial family, simulation shows that the SC control charts have Type I risk (i.e., probability of a false alarm) closer to 0.27% of the normal case. Even in the case where the process distribution is exponential with known mean, not only the control limits and Type I risk, but also the Type II risk of the SC charts are closer to those of the exact and R charts than those of the WV and Shewhart charts. © 2003 Wiley Periodicals, Inc. Naval Research Logistics 50: 555–573, 2003     

Economic design of a two-stage control chart based on both performance and surrogate variables

The traditional approach to economic design of control charts is based on the assumption that a process is monitored using only a performance variable. If, however, the performance variable is costly to measure and a less expensive surrogate variable is available, the process may be more efficiently controlled by using both performance and surrogate variables. In this article we propose a model for economic design of a two-stage control chart which uses a highly correlated surrogate variable together with a performance variable. The process is assumed to be monitored by the surrogate variable until it signals out-of-control behavior, then by the performance variable until it signals out-of-control behavior or maintains in-control signals for a prespecified amount of time, and the two variables are used in alternating fashion. An algorithm based on the direct search method of Hooke and Jeeves [6] is used to find the optimum values of design parameters. The proposed model is applied to the end-closure welding process for nuclear fuel to compute the amount of reduction in cost compared with the current control procedure. © 1999 John Wiley & Sons, Inc. Naval Research Logistics 46: 958–977, 1999     

Approximate semieconomic design of control charts with multiple control limtis

Statistical quality control of complicated production processes subject to a multiplicity of assignable causes may require the utilization of control charts with multiple control limits. This article presents an approximate semieconomic design of such charts, which is easily implementable in practical situations. Evaluations of the semieconomic control chart design show that the proposed approximate method results in solutions that are very close to the true optima and can be obtained with minimal computational effort.     

The effect of process adjustment error on X̄ chart design

The existing literature on economic design of X̄ process control charts generally assumes perfect process adjustment, such that the process mean is returned to an exactly centered “in control” state following any real or false alarm control chart signal. This paper presents a model which demonstrates the effects of imperfect process adjustment on the economically designed control chart parameters. The model demonstrates that the optimal control limit width depends fundamentally on the precision with which the process can be adjusted. The greater the process adjustment error, all else constant, the wider will be the optimal control limits, in order to alleviate the potential for process overcontrol and tampering effects. By endogenously modeling these effects, the new model helps to rectify the problem of poor statistical properties for which the economic design approach has been criticized. © 1999 John Wiley & Sons, Inc. Naval Research Logistics 46: 597–612, 1999     

Stochastic framework for partially degradation systems with continuous component degradation‐rate‐interactions

Many conventional models that characterize the reliability of multicomponent systems are developed on the premise that for a given system, the failures of its components are independent. Although this facilitates mathematical tractability, it may constitute a significant departure from what really takes place. In many real‐world applications, system components exhibit various degrees of interdependencies, which present significant challenges in predicting degradation performance and the remaining lifetimes of the individual components as well as the system at large. We focus on modeling the performance of interdependent components of networked systems that exhibit interactive degradation processes. Specifically, we focus on how the performance level of one component affects the degradation rates of other dependent components. This is achieved by using stochastic models to characterize how degradation‐based sensor signals associated with the components evolve over time. We consider “Continuous‐Type” component interactions that occur continuously over time. This type of degradation interaction exists in many applications, in which interdependencies occur on a continuum. We use a system of stochastic differential equations to capture such “Continuous‐Type” interaction. In addition, we utilize a Bayesian approach to update the proposed model using real‐time sensor signals observed in the field and provide more accurate estimation of component residual lifetimes. © 2014 Wiley Periodicals, Inc. Naval Research Logistics 61: 286–303, 2014     

Exact expected values of variance estimators for simulation

We formulate exact expressions for the expected values of selected estimators of the variance parameter (that is, the sum of covariances at all lags) of a steady‐state simulation output process. Given in terms of the autocovariance function of the process, these expressions are derived for variance estimators based on the simulation analysis methods of nonoverlapping batch means, overlapping batch means, and standardized time series. Comparing estimator performance in a first‐order autoregressive process and the M/M/1 queue‐waiting‐time process, we find that certain standardized time series estimators outperform their competitors as the sample size becomes large. © 2007 Wiley Periodicals, Inc. Naval Research Logistics, 2007     

Signal‐to‐interference‐plus‐noise ratio estimation for wireless communication systems: Methods and analysis

The Signal‐to‐Interference‐plus‐Noise Ratio (SINR) is an important metric of wireless communication link quality. SINR estimates have several important applications. These include optimizing the transmit power level for a target quality of service, assisting with handoff decisions and dynamically adapting the data rate for wireless Internet applications. Accurate SINR estimation provides for both a more efficient system and a higher user‐perceived quality of service. In this paper, we develop new SINR estimators and compare their mean squared error (MSE) performance. We show that our new estimators dominate estimators that have previously appeared in the literature with respect to MSE. The sequence of transmitted bits in wireless communication systems consists of both pilot bits (which are known both to the transmitter and receiver) and user bits (which are known only by the transmitter). The SINR estimators we consider alternatively depend exclusively on pilot bits, exclusively on user bits, or simultaneously use both pilot and user bits. In addition, we consider estimators that utilize smoothing and feedback mechanisms. Smoothed estimators are motivated by the fact that the interference component of the SINR changes relatively slowly with time, typically with the addition or departure of a user to the system. Feedback estimators are motivated by the fact that receivers typically decode bits correctly with a very high probability, and therefore user bits can be thought of as quasipilot bits. For each estimator discussed, we derive an exact or approximate formula for its MSE. Satterthwaite approximations, noncentral F distributions (singly and doubly) and distribution theory of quadratic forms are the key statistical tools used in developing the MSE formulas. In the case of approximate MSE formulas, we validate their accuracy using simulation techniques. The approximate MSE formulas, of interest in their own right for comparing the quality of the estimators, are also used for optimally combining estimators. In particular, we derive optimal weights for linearly combining an estimator based on pilot bits with an estimator based on user bits. The optimal weights depend on the MSE of the two estimators being combined, and thus the accurate approximate MSE formulas can conveniently be used. The optimal weights also depend on the unknown SINR, and therefore need to be estimated in order to construct a useable combined estimator. The impact on the MSE of the combined estimator due to estimating the weights is examined. © 2004 Wiley Periodicals, Inc. Naval Research Logistics, 2004     

A performance comparison of empirical Bayes and Bayes estimators of the Weibull and gamma scale parameters

A mean-squared error comparison of smooth empirical Bayes and Bayes estimators for the Weibull and gamma scale parameters is studied based on a computer simulation. The smooth empirical Bayes estimators are determined as functions of up to 15 past estimates of the parameter of interest. Results indicate that at best the mean-squared errors of the empirical Bayes estimators are about 20–40% larger than those of the corresponding squared-error optimal Bayes estimators.     

Maneuvering target tracking of UAV based on MN-DDPG and transfer learning

Tracking maneuvering target in real time autonomously and accurately in an uncertain environment is one of the challenging missions for unmanned aerial vehicles(UAVs).In this paper,aiming to address the control problem of maneuvering target tracking and obstacle avoidance,an online path planning approach for UAV is developed based on deep reinforcement learning.Through end-to-end learning powered by neural networks,the proposed approach can achieve the perception of the environment and continuous motion output control.This proposed approach includes:(1)A deep deterministic policy gradient(DDPG)-based control framework to provide learning and autonomous decision-making capa-bility for UAVs;(2)An improved method named MN-DDPG for introducing a type of mixed noises to assist UAV with exploring stochastic strategies for online optimal planning;and(3)An algorithm of task-decomposition and pre-training for efficient transfer learning to improve the generalization capability of UAV's control model built based on MN-DDPG.The experimental simulation results have verified that the proposed approach can achieve good self-adaptive adjustment of UAV's flight attitude in the tasks of maneuvering target tracking with a significant improvement in generalization capability and training efficiency of UAV tracking controller in uncertain environments.     

Choosing arrival process models for service systems: Tests of a nonhomogeneous Poisson process

Service systems such as call centers and hospital emergency rooms typically have strongly time‐varying arrival rates. Thus, a nonhomogeneous Poisson process (NHPP) is a natural model for the arrival process in a queueing model for performance analysis. Nevertheless, it is important to perform statistical tests with service system data to confirm that an NHPP is actually appropriate, as emphasized by Brown et al. [8]. They suggested a specific statistical test based on the Kolmogorov–Smirnov (KS) statistic after exploiting the conditional‐uniform (CU) property to transform the NHPP into a sequence of i.i.d. random variables uniformly distributed on [0,1] and then performing a logarithmic transformation of the data. We investigate why it is important to perform the final data transformation and consider what form it should take. We conduct extensive simulation experiments to study the power of these alternative statistical tests. We conclude that the general approach of Brown et al. [8] is excellent, but that an alternative data transformation proposed by Lewis [22], drawing upon Durbin [10], produces a test of an NHPP test with consistently greater power. We also conclude that the KS test after the CU transformation, without any additional data transformation, tends to be best to test against alternative hypotheses that primarily differ from an NHPP only through stochastic and time dependence. © 2014 Wiley Periodicals, Inc. Naval Research Logistics 61: 66–90, 2014     

Tests for homogeneity of distributions of component lifetimes from system lifetime data with known system signatures

In this article, we discuss the problem of testing the homogeneity of distributions of component lifetimes based on system lifetime data when the system signatures are known. Both parametric and nonparametric procedures are developed for this problem. For nonparametric testing, the Mann–Whitney‐type statistic is used, and its performance and limitations are discussed. Next, we assume the component lifetimes to follow exponential distributions and then develop different parametric tests. Exact and asymptotic methods are developed based on the method of moments estimators. A Monte Carlo simulation study is used to compare the performance of different parametric procedures with that of the nonparametric procedure. Based on the results of the simulation study, discussions and practical recommendations are made and finally some concluding remarks are provided. © 2015 Wiley Periodicals, Inc. Naval Research Logistics 62: 550–563, 2015