Abstract Monitoring several correlated quality characteristics of a process is common in modern manufacturing and service industries. Although a lot of attention has been paid to monitoring the multivariate process mean, not many control charts are available for monitoring the covariance matrix. This paper presents a comprehensive overview of the literature on control charts for monitoring the covariance

Abstract In multistage manufacturing systems, modeling multiple quality indices based on the process sensing variables is important. However, the classic modeling technique predicts each quality variable one at a time, which fails to consider the correlation within or between stages. We propose a deep multistage multi-task learning framework to jointly predict all output sensing variables in a unified

Abstract Variational autoencoders have been recently proposed for the problem of process monitoring. While these works show impressive results over classical methods, the proposed monitoring statistics often ignore the inconsistencies in learned lower-dimensional representations and computational limitations in high-dimensional approximations. In this work, we first manifest these issues and then overcome

Abstract We propose a method for monitoring proportions when the in-control proportion and the sample sizes vary over time. Our approach is able to overcome some of the performance issues of other commonly used methods, as we demonstrate in this paper using analytical and numerical methods. The derivations and results are shown mainly for monitoring proportions, but we show how the method can be extended

Abstract Dynamic data detection is one of the main concerns in the statistical process control (SPC) field. Here we focus on monitoring parametric multivariate dynamic data streams using the ARMAX-GARCH model, which reflects both the influence of exogenous variables on the mean vector and the heterogeneity of the covariance matrix. A quasi maximum likelihood estimator is used to estimate the parameter

(2021). Next Editor of the Journal of Quality Technology: Dr. L. Allison Jones-Farmer. Journal of Quality Technology: Vol. 53, No. 2, pp. 217-217.

(2021). Correction. Journal of Quality Technology: Vol. 53, No. 2, pp. 218-218.

(2021). The Statistical Analysis of Multivariate Failure Time Data: A Marginal Modeling Approach. Journal of Quality Technology. Ahead of Print.

Abstract In this article, I provide a detailed discussion of the well-known fish patty experiment introduced in the literature by the late John A. Cornell in the first edition of his famous textbook on the design and analysis of mixture experiments. Cornell used the fish patty experiment as the motivating example for an article discussing that, for logistical reasons, many mixture-process variable

Abstract Big Data are huge amounts of digital information that rarely result from properly planned surveys; as a consequence they often contain redundant observations. When the aim is to answer particular questions of interest, we suggest selecting a subsample of units that contains the majority of the information to achieve this goal. Selection methods driven by the theory of optimal design incorporate

Abstract A manufacturing system collects big and heterogeneous data for tasks such as product quality modeling and data-driven decision-making. However, as the size of data grows, timely and effective data utilization becomes challenging. We propose an unsupervised data filtering method to reduce manufacturing big data sets with multi-variate continuous variables into informative small data sets. Furthermore

Abstract In experimental designs, it is usually assumed that the data follow normal distributions and the models have linear structures. In practice, experimenters may encounter different types of responses and be uncertain about model structures. If this is the case, traditional methods, such as the ANOVA and regression, are not suitable for data analysis and model selection. We introduce the random

Abstract Thermal fields exist widely in engineering systems and are critical for engineering operation, product quality and system safety in many industries. An accurate prediction of thermal field distribution, that is, acquiring any location of interest in a thermal field at the present and future time, is essential to provide useful information for the surveillance, maintenance, and improvement

(2020). Statistical Inference via Data Science: A Modern Dive into R and the Tidyverse. Journal of Quality Technology. Ahead of Print.

(2020). Correction. Journal of Quality Technology. Ahead of Print.

Abstract Since parameter estimation degrades chart performance, it is important to design a control chart correctly, that is, taking account of the estimation effects. To this end, two perspectives are available in the literature: the unconditional, which focuses on the unconditional in-control (IC) average run length ( ARL 0 ), and the conditional, which focuses on the IC run-length distribution conditioned

Abstract Models with ordinal outcomes are an important part of generalized linear models and design issues for them are less studied, especially when the model has discrete and continuous factors. We propose an effective and flexible Particle Swarm Optimization (PSO) algorithm for finding locally D-optimal approximate designs for experiments with ordinal outcomes modeled using the cumulative logit

Abstract Accelerated life testing (ALT) is a commonly used experiment in industries for assessing a product’s lifetime. Planning a proper test with consideration of possible constraints on randomization is important because the prediction accuracy highly depends on the test plan. In this article, an optimal ALT test plan with multiple sources of random effects is demonstrated. Specifically, we consider

Abstract User-generated content including both review texts and user ratings provides important information regarding the customer-perceived quality of online products and services. This article proposes a modeling and monitoring method for online user-generated content. A unified generative model is constructed to combine words and ratings in customer reviews based on their latent sentiment and topic

Abstract Recent advances in data acquisition and storage technologies have permitted the rapid collection of data over time at a relatively low cost. The implication of these advances to modern quality engineering is that many of today’s processes produce samples of individual observations that are grossly non-normal and, potentially, very highly autocorrelated. Consequently, the typical assumptions

Abstract In this case study, we demonstrate the use of multilevel process monitoring in quality control. Using high school data, we answer three research questions related to high school student progress during an academic year. The questions are (1) What determines student performance? (2) How can statistical process monitoring be used in monitoring student progress? (3) What method can be used for

(2020). The analytics lifecycle toolkit: A practical guide for an effective analytics capability. Journal of Quality Technology. Ahead of Print.

(2020). ASQ Membership. Journal of Quality Technology: Vol. 52, No. 4, pp. 431-431.

(2020). ASQ Books. Journal of Quality Technology: Vol. 52, No. 4, pp. 432-432.

The high-dimensionality and volume of large-scale streaming data has inhibited significant research progress in developing an integrated monitoring and diagnostics (M&D) approach. Such data streams are becoming common in various applications including manufacturing, healthcare, and web mining. In this article, we propose an integrated M&D approach for large-scale streaming data. Using principal component

Monitoring multivariate and high-dimensional data streams is often an essential requirement for quality management in manufacturing and service sectors in the Industry 4.0 era. Identifying a suitable distribution for a multivariate data set, especially when the number of variables is much larger than the sample size, is often challenging. Consequently, in a high-dimensional set-up, that is, when the

A new data fusion and network analytics framework is proposed that is based on the topology of large-scale networks and the stochastic dependencies between nodes, edges, and sensor data. The framework can transform real-time sensor data collected from disparate sources in a network to detect the location of anomalies and the nodes that are impacted by the detected anomalies. By intelligently fuzing

Directed graphical models aim to represent the probabilistic relationships between variables in a system. Learning a directed graphical model from data includes parameter learning and structure learning. Several methods have been developed for directed graphical models with scalar variables. However, the case in which the variables are infinite-dimensional has not been studied thoroughly. Nowadays

In functional sequential process monitoring, a process is characterized by sequences of observations called profiles which are monitored over time for stability. The goal is to halt a process when the process generating these observations deviates from a specified in control standard. We propose a Bayesian sequential process control (SPC) methodology which uses wavelets to monitor the functional responses

(2020). In memoriam: Raymond “Ray” Harold Myers (1937 – 2020) Journal of Quality Technology: Vol. 52, No. 3, pp. 327-327.

In applications, most processes for quality control and management are multivariate. Thus, multivariate statistical process control (MSPC) is an important research problem and has been discussed extensively in the literature. Early MSPC research is based on the assumptions that process observations at different time points are independent and they have a parametric distribution (e.g., Gaussian) when

Computer models with both quantitative and qualitative inputs frequently arise in science, engineering and business. Mixed-input Gaussian process models have been used for emulating such models. The key in building this emulator is to accurately estimate the covariance between different categorical levels of the qualitative inputs. This problem is challenging when the number of categorical levels is

(2020). Probability, Lawrence M. Leemis. Lighting Source, La Vergne, TN, 2017, 566 pp., $45.00, ISBN: 978-0982917473. Journal of Quality Technology. Ahead of Print.

To online monitor the longitudinal performance of processes and give early signals to processes with irregular patterns, a series of dynamic screening systems (DySS) have been proposed in the literature. Existing DySS methods are all based on estimation of the in-control (IC) mean and variance of processes with a regular longitudinal pattern. In this paper, a new DySS method is suggested, which is

(2020). Mathematical Statistics. Journal of Quality Technology. Ahead of Print.

The purpose of this article is to persuade experimenters to choose A-optimal designs rather than D-optimal designs for screening experiments. The primary reason for this advice is that the A-optimality criterion is more consistent with the screening objective than the D-optimality criterion. The goal of screening experiments is to identify an active subset of the factors. An A-optimal design minimizes

(2020). Surrogates: Gaussian process modeling, design, and optimization for the applied sciences. Journal of Quality Technology. Ahead of Print.

This paper investigates degradation modeling under dynamic conditions and its applications. Both univariate and multiple competing degradation processes are considered with individual degradation paths being described by Wiener processes. Parametric and non-parametric approaches are used to capture the effect of environmental conditions on process parameters. For competing degradation processes, we

In statistical process control (SPC), a proper Phase I analysis is essential to the success of Phase II monitoring. With recent advances in sensing technology and data acquisition systems, Phase I analysis of high-dimensional data is increasingly encountered. However, the high dimensionality presents a new challenge to the traditional Phase I techniques. A literature review reveals nearly no Phase

(2020). The Road to Quality Control: the Industrial Application of Statistical Quality Control. Journal of Quality Technology. Ahead of Print.

After completing the experimental runs of a screening design, the responses under study are analyzed by statistical methods to detect the active effects. To increase the chances of correctly identifying these effects, a good analysis method should provide alternative interpretations of the data, reveal the aliasing present in the design, and search only meaningful sets of effects as defined by user-specified

This study proposes an efficient approach to detect one or more change points for gamma distribution. We plug a closed-form estimator into the gamma log-likelihood function to obtain a sharp approximation to the maximum of log-likelihood. We further derive a closed form calibration of approximate likelihood which is asymptotically equivalent to the exact log-likelihood. This circumvents iterative optimization

Space-filling designs are a convenient and effective approach for exploring the input space for experiments. However, standard choices for these designs strive to provide uniform density of points throughout the region of interest. There are numerous situations where flexibility to adapt the density of points to match specific design objectives would be advantageous to maximize the efficiency of the

Effective process monitoring of high-dimensional data streams with embedded spatial structures has been an arising challenge for environments with limited resources. Utilizing the spatial structure is key to improve monitoring performance. This article proposes a correlation-based dynamic sampling technique for change detection. Our method borrows the idea of Upper Confidence Bound algorithm and uses

Stochastic textured surface (STS) data (e.g., material microstructure microscopy images) are increasingly common in many quality control settings. Because of their stochastic nature, performing statistical process control (SPC) for STS data without requiring advanced knowledge of abnormal behavior is challenging, and there is no existing SPC software available to solve this problem. This article introduces

Abstract Fully-sequential (i.e., with design points added one-at-a-time) space-filling designs are useful for global surrogate modeling of expensive computer experiments when the number of design points required to achieve a suitable accuracy is unknown in advance. We develop and investigate three fully-sequential space-filling (FSSF) design algorithms that are conceptually simple and computationally

(2021). Design of Experiments for Generalized Linear Models. Journal of Quality Technology: Vol. 53, No. 1, pp. 107-108.

Abstract In classical response surface methodology, the optimization step uses a small number of important factors. However, in practice, experimenters sometimes fit a second-order model without previous experimentation. In this case, the true model is uncertain and the full model may overfit. Here, we use an extensive simulation to evaluate several analysis strategies in terms of their optimum locating

(2020). Time series: a data analysis approach using R. Journal of Quality Technology. Ahead of Print.

Abstract Multivariate categorical quality characteristics, whose distribution can be displayed by a contingency table, are routinely encountered in many applications. When most of the cell entries in the contingency table are very small or zeros counts, which is so-called sparse contingency table in the literature, existing methods developed in the literature are often inadequate for use, due to the

Abstract Nonparametric control charts that can detect arbitrary distributional changes are highly desirable due to their flexibility to adapt to different distributional assumptions and changes. However, most of the nonparametric control charts in the literature either can only detect location changes, or involve intensive computation. In this article, we propose a new nonparametric adaptive CUSUM

Abstract In many applications of modern quality control, process monitoring involves a large number of process variables and quality characteristics. Practitioners are desired to attain complete information about the process in order to assure quick detection of shifts that may possibly occur at any variable. However, full information is not always available during online monitoring of big data streams

(2019). ASQ Books. Journal of Quality Technology: Vol. 51, No. 4, pp. (422)-(422).

(2019). ASQ Membership. Journal of Quality Technology: Vol. 51, No. 4, pp. (423)-(423).

(2020). Probability and Statistics for Data Sciences: Math + R + Data. Journal of Quality Technology: Vol. 52, No. 4, pp. 428-430.

(2021). Mixture Modeling for Medical and Health Sciences. Journal of Quality Technology: Vol. 53, No. 1, pp. 106-106.

(2020). Analysis of Integrated Data. Journal of Quality Technology: Vol. 52, No. 4, pp. 427-427.

Abstract Split-plot definitive screening and blocked definitive screening designs have been developed for detecting active main effects and second-order effects in screening experiments when split-plot and block structures exist. In the literature, multistage regression and forward stepwise regression methods were proposed for data analysis on the two types of designs. However, classical regression

Abstract The goal of this case study is to answer four research questions related to fatigue through features derived from wearable sensors to measure patterns in steps: (1) How do important gait parameters change over time? (2) How do these sensor-based changes relate to the participant's subjective fatigue ratings over time? (3) Are there consistent patterns in performance across different individuals

Abstract Parameter estimation has a large impact on control chart performance. Recently, widened control limits have been suggested to guarantee an acceptable in-control behavior. However, the consequence is a reduced ability to detect a real change in the process. In order to overcome this undesired effect, we explore an alternative design based on a delayed updating of parameter estimates. We consider