Journal of Quality Technology - July 2019 - ASQ

Journal of Quality Technology - July 2019

Volume 51 ∙ Number 3

ARTICLES

  • Dynamic quality-process model in consideration of equipment degradation
    By Ran Jin, Xinwei Deng, Xiaoyu Chen, Liang Zhu & Jun Zhang
    In many manufacturing processes, equipment reliability plays a crucial role for product quality assurance. It is important to consider the effect of equipment degradation for the quality-process model. In this article, we propose a dynamic quality-process model to characterize the varying effects of a process to product quality due to equipment degradation. The proposed model considers the effects of process variables on product quality as piecewise linear functions with respect to the equipment degradation. It can automatically estimate the dynamic effects via a meaningful parameter regularization, leading to accurate parameter estimation and model prediction. The merits of the proposed method are illustrated by both simulations and a real case study in a crystal growth manufacturing process.
  • The design of order-of-addition experiments
    By Joseph G. Voelkel
    I introduce systematic methods to create optimal designs for order-of-addition (OofA) experiments, those that study the order in which m components are applied—for example, the order in which chemicals are added to a reaction or layers are added to a film. Full designs require m! runs, so I investigate design fractions. Balance criteria for creating such designs employ an extension of orthogonal arrays (OAs) to OofA–OAs. A connection is made between D-efficient and OofA–OA designs. Necessary conditions are found for the number of runs needed to create OofA–OAs of strengths 2 and 3. I create a number of new, optimal, designs: 12-run OofA–OAs in 4 and 5 components, 24-run OofA–OAs in 5 and 6 components, and near OofA–OAs in 7 components. I extend these designs to include (a) process factors and (b) the common case in which component orderings are restricted. I also suggest how such designs may be analyzed.
  • An adaptive thresholding-based process variability monitoring
    By Galal M. Abdella, Jinho Kim, Sangahn Kim, Khalifa N. Al-Khalifa, Myong K. (MK) Jeong, Abdel Magid Hamouda & Elsayed A. Elsayed
    In high-dimensional processes, monitoring process variability is considerably difficult due to the large number of variables and the limited number of samples. Monitoring changes in the covariance matrix of a multivariate process is often used for monitoring process variability under the assumption that only a few elements in the covariance matrix are changed simultaneously from the in-control values. The existing LASSO-based covariance monitoring charts in the high-dimensional settings provide good performance in detecting some shift patterns depending on the prespecified tuning parameter. In practice, control charts that perform reasonably well over various shift patterns are desired when shift patterns are unknown. In this article, we propose a control chart based on an adaptive LASSO-thresholding for monitoring changes in the covariance matrix. The performance of the proposed chart, which is called the ALT-norm chart, is evaluated for various shift patterns and compared with the existing penalized likelihood-based methods. The results show the effectiveness of the proposed chart. Finally, we illustrate the advantages of the ALT-norm chart through simulated and real data from both the semiconductor industry and a high-dimensional milling process.
  • Some simultaneous progressive monitoring schemes for the two parameters of a zero-inflated Poisson process under unknown shifts
    By Amitava Mukherjee & Athanasios C. Rakitzis
    The zero-inflated Poisson (ZIP) distribution has been extensively studied in the literature during recent years. It is one of the most appropriate models for overdispersed data with an excessive number of zeros. Data of this type frequently arise in manufacturing processes with a low fraction of defective items. A ZIP model has two parameters; one presents the probability of extra zeros and the other stands for the expected Poisson count. In this article, we propose and study three new single control charts for detecting changes in either of the two parameters of a ZIP process. The performance of the schemes is studied via numerical simulation based on Monte-Carlo. We outline that all the existing control charts for monitoring ZIP processes are based on individual observations and assume that the shift sizes in either or both parameters are known. Our proposed schemes do not need any prior information related to shift size and can be used both for individual observations and subgroup samples. The results reveal that they are very effective in the detection of small and moderate shifts in process parameters. Practical implementation of the proposed schemes is also illustrated through an interesting real industrial data set on light emitting diodes (LED).
  • Modeling memoryless degradation under variable stress
    By Edward V. Thomas, Ira Bloom, Jon P. Christophersen, David C. Robertson, Lee K. Walker, Chinh D. Ho & Vincent S. Battaglia
    Accelerated degradation tests can be used as the basis for predicting the performance or state of health of products and materials at use conditions over time. Measurements acquired at accelerated levels of stress are used to develop models that relate to the degradation of one or more performance measures. Frequently, products/materials of interest are subjected to variable stress levels during their lifetimes. However, testing is usually performed only at a few fixed stress levels. In such cases, cumulative degradation models are developed and assessed by using data acquired under those fixed stress conditions. The degradation rate at any stress condition within the range of the model can be estimated by the derivative of the cumulative model at that stress condition. It follows that, to predict cumulative degradation over variable use conditions, one might integrate the fluctuating degradation rate over time. Existing approaches for doing this consider degradation rates that depend only on the current stress level. Here, we propose to allow the degradation rate to also depend on the current state of health as indicated by the associated performance measure(s). The resulting modeling approach is capable of portraying a broader range of degradation behavior than existing approaches. The assertion of memoryless degradation by using this or any other approach should be assessed experimentally with data acquired under variable stress in order to increase confidence that the integrated rate model is accurate. In this article, we demonstrate the additional capability of the proposed approach by developing empirical memoryless rate-based degradation models to predict resistance increase and capacity decrease in lithium-ion cells that are being evaluated for use in electric vehicles. We then assess the plausibility of these models.
  • Modeling memoryless degradation under variable stress
    By Edward V. Thomas, Ira Bloom, Jon P. Christophersen, David C. Robertson, Lee K. Walker, Chinh D. Ho & Vincent S. Battaglia
    Accelerated degradation tests can be used as the basis for predicting the performance or state of health of products and materials at use conditions over time. Measurements acquired at accelerated levels of stress are used to develop models that relate to the degradation of one or more performance measures. Frequently, products/materials of interest are subjected to variable stress levels during their lifetimes. However, testing is usually performed only at a few fixed stress levels. In such cases, cumulative degradation models are developed and assessed by using data acquired under those fixed stress conditions. The degradation rate at any stress condition within the range of the model can be estimated by the derivative of the cumulative model at that stress condition. It follows that, to predict cumulative degradation over variable use conditions, one might integrate the fluctuating degradation rate over time. Existing approaches for doing this consider degradation rates that depend only on the current stress level. Here, we propose to allow the degradation rate to also depend on the current state of health as indicated by the associated performance measure(s). The resulting modeling approach is capable of portraying a broader range of degradation behavior than existing approaches. The assertion of memoryless degradation by using this or any other approach should be assessed experimentally with data acquired under variable stress in order to increase confidence that the integrated rate model is accurate. In this article, we demonstrate the additional capability of the proposed approach by developing empirical memoryless rate-based degradation models to predict resistance increase and capacity decrease in lithium-ion cells that are being evaluated for use in electric vehicles. We then assess the plausibility of these models.
  • Imperfect inspection with directional information: A general failure probability model
    By Young H. Chun
    Suppose that the entire sequence of items produced is divided into a stream of nondefective items, followed by a stream of defective items. We propose a sequential inspection procedure for the production process that has a general failure probability–increasing, constant, or decreasing failure patterns. We also consider the inspector’s classification errors as well as the costs of inspection and misclassifications. In numerical analysis, we show that other inspection models are special cases of our general model and analyze the effects of failure patterns on the inspection cost for various combinations of the type I and II errors.
  • Statistical inference for a class of startup demonstration tests
    By Serkan Eryilmaz
    In this article, we develop a general statistical inference procedure for the probability of successful startup p in the case of startup demonstration tests when only the number of trials until termination of the experiment are observed. In particular, we define a class of startup demonstration tests and present expectation-maximization (EM) algorithm to get the maximum likelihood estimate of p for this class. Most of well-known startup testing procedures are involved in this class. Extension of the results to Markovian startups is also presented.

 

Featured advertisers


ASQ is a global community of people passionate about quality, who use the tools, their ideas and expertise to make our world work better. ASQ: The Global Voice of Quality.