Shuguang He

Tianjin University, T’ien-ching-shih, Tianjin Shi, China

Are you Shuguang He?

Claim your profile

Publications (12)4.58 Total impact

  • Shuguang He, Shijie Li, Zhen He
    [Show abstract] [Hide abstract]
    ABSTRACT: The Zero-inflated Poisson distribution (ZIP) is used to model the defects in processes with a large number of zeros. We propose a control charting procedure using a combination of two cumulative sum (CUSUM) charts to detect increases in the parameters of ZIP process, one is a conforming run length (CRL) CUSUM chart and another is a zero truncated Poisson (ZTP) CUSUM chart. The control limits of the control charts are obtained using both Markov chain-based methods and simulations. Simulation experiments show that the proposed method outperforms an existing method. Finally, a real example is presented.
    Communication in Statistics- Simulation and Computation 05/2014; 43(10). DOI:10.1080/03610918.2012.753082 · 0.29 Impact Factor
  • Source
    Min Zhang, G. Alan Wang, Shuguang He, Zhen He
    [Show abstract] [Hide abstract]
    ABSTRACT: The existing research of process capability indices of multiple quality characteristics mainly focuses on nonconforming of process output, the concept development of univariate process capability indices, quality loss function and various comprehensive evaluation methods. The multivariate complexity increases the computation difficulty of multivariate process capability indices(MPCI), which makes them hard to be used in practice. In this paper, a new PCA-based MPCI approach is proposed to assess the production capability of the processes that involve multiple product quality characteristics. This approach first transforms the original quality variables into standardized normal variables. MPCI measures are then provided based on the Taam index. Moreover, the statistical properties of these MPCIs, such as confidence intervals and lower confidence bound, are given to let the practitioners understand the capability indices as random variables instead of deterministic variables. A real manufacturing data set and a synthetic data set are used to demonstrate the effectiveness of the proposed method. An implementation procedure is also provided for quality engineers to apply our MPCI approach in their manufacturing processes. The case studies demonstrate the effectiveness and feasibility of this new kind of MPCI, which is easier to be used in production practice. The proposed research provides a novel approach of MPCI calculation.
    Chinese Journal of Mechanical Engineering 02/2014; 27(2). DOI:10.3901/CJME.2014.02.249 · 0.45 Impact Factor
  • Shuguang He, Zhen He, G. Alan Wang
    [Show abstract] [Hide abstract]
    ABSTRACT: A cumulative sum control chart for multivariate Poisson distribution (MP-CUSUM) is proposed. The MP-CUSUM chart is constructed based on log-likelihood ratios with in-control parameters, Θ0, and shifts to be detected quickly, Θ1. The average run length (ARL) values are obtained using a Markov Chain-based method. Numerical experiments show that the MP-CUSUM chart is effective in detecting parameter shifts in terms of ARL. The MP-CUSUM chart with smaller Θ1 is more sensitive than that with greater Θ1 to smaller shifts, but more insensitive to greater shifts. A comparison shows that the proposed MP-CUSUM chart outperforms an existing MP chart.
    Communication in Statistics- Theory and Methods 02/2014; 43(6). DOI:10.1080/03610926.2012.667484 · 0.28 Impact Factor
  • Source
    [Show abstract] [Hide abstract]
    ABSTRACT: Machine learning based algorithms, such as a decision tree (DT) classifier, have been applied to automated process monitoring and fault identification in manufacturing processes, however the current DT-based process control models employ a single DT classifier for both mean shift detection and fault identification. As many manufacturing processes use automated data collection for multiple process parameters, a DT classifier would have to handle a large number of classes. Previous research shows that a large number of classes can degrade the accuracy of a DT multiclass classifier. In this study we propose a new process monitoring model using multiple DT classifiers with each handling a small number of classes. Moreover, we not only detect mean shifts but also identify process variability levels that may cause out-of-control signals. Experimental results show that our proposed model achieves satisfactory performance in process monitoring and fault identification with various parameter settings. It achieves better ARL performance compared with the baseline method based on a single DT classifier.
    International Journal of Production Research 06/2013; 51(11). DOI:10.1080/00207543.2013.774474 · 1.32 Impact Factor
  • [Show abstract] [Hide abstract]
    ABSTRACT: A zero-inflated Poisson (ZIP) process is different from a standard Poisson process in that it results in a greater number of zeros. It can be used to model defect counts in manufacturing processes with occasional occurrences of non-conforming products. ZIP models have been developed assuming that random shocks occur independently with probability p, and the number of non-conformities in a product subject to a random shock follows a Poisson distribution with parameter λ. In our paper, a control charting procedure using a combination of two cumulative sum (CUSUM) charts is proposed for monitoring increases in the two parameters of the ZIP process. Furthermore, we consider a single CUSUM chart for detecting simultaneous increases in the two parameters. Simulation results show that a ZIP-Shewhart chart is insensitive to shifts in p and smaller shifts in λ in terms of the average number of observations to signal. Comparisons between the combined CUSUM method and the single CUSUM chart show that the latter's performance is worse when there are only increases in p, but better when there are only increases in λ or when both parameters increase. The combined CUSUM method, however, is much better than the single CUSUM chart when one parameter increases while the other decreases. Finally, we present a case study from the light-emitting diode packaging industry. Copyright © 2011 John Wiley & Sons, Ltd.
    Quality and Reliability Engineering 03/2012; 28(2):181 - 192. DOI:10.1002/qre.1228 · 0.99 Impact Factor
  • Shuguang He, Zhen He, Gang Alan Wang
    [Show abstract] [Hide abstract]
    ABSTRACT: The zero-inflated Poisson (ZIP) model is an extension of the standard Poisson distribution. It is often used to describe a near zero-defect process with occasional occurrences of non-conforming products. In the past, research on the control charts for ZIP process has concentrated on univariate ZIP process where there is only one type of defect. However, it is common in some high quality processes that there are several types of defects to be considered and the count variables are correlated. It is not appropriate to monitor the process using independent univariate ZIP based control charts. In this paper, a control charting procedure using a combination of two cumulative sum charts is proposed for monitoring shifts in a bivariate ZIP (BZIP) process, which is a special case of the multivariate ZIP model. We use simulations to obtain the upper control limit of the control charts based on a specified in-control average number of observations to signal. We also use simulations to evaluate the control charting procedure in three situations: shifts only in the $p$ -set parameters; shifts only in the $\lambda$-set parameters; and shifts in all the parameters. The simulation results show that the proposed control charts are effective in detecting shifts in the parameters of a BZIP process. Finally, we present an application of our proposed method in the light emitting diode packaging industry.
    IEEE Transactions on Components, Packaging, and Manufacturing Technology 01/2012; 2(1). DOI:10.1109/TCPMT.2011.2176948 · 1.24 Impact Factor
  • Shuguang He, Chenghang Xiao
    [Show abstract] [Hide abstract]
    ABSTRACT: process monitoring and other p (p is the number of the variables) DT classifiers for fault identification. The Mahalanobis distance contours based method for selecting model training samples is proposed to decrease the number of training samples. Numerical experiments based on bivariate process show that the proposed model works well in different conditions considered. The results also show that the sample sizes have obvious effect on the performance of the model. The correlation coefficients have nearly no effects on the performance of the DT classifier for process monitoring, while have obvious effects on the performance of the DT classifiers for fault identification.
  • [Show abstract] [Hide abstract]
    ABSTRACT: The central composite design in the modeling and optimization of catalytic dehydration of ethanol to ethylene was performed to improve the ethylene yield. A total of 20 experiments at random were conducted to investigate the effect of reaction temperature, Si/Al ratios of H-ZSM-5 catalyst and liquid hourly space velocity (LHSV) on the ethylene yield. The results show that the relationship between ethylene yield and the three significant independent variables can be approximated by a nonlinear polynomial model, with R-squared of 99.9% and adjusted R-squared of 99.8%. The maximal response for ethylene yield is 93.4% under the optimal condition of 328 °C, Si/Al ratio 85, and LHSV 3.8 h−1.
    Transactions of Tianjin University 10/2009; 15(5):366-370. DOI:10.1007/s12209-009-0064-8
  • Li Li, Shuguang He, E.-S. Qi
    [Show abstract] [Hide abstract]
    ABSTRACT: In the course of software development, the requirements often change significantly. Based on the analysis of software requirement variations, we introduce a new approach to measurement of requirement changes based on the six-sigma methods. The framework of GQM (Goal-Question-Metric) and the process of DMAIC (Define-Measurement-Analysis- Improvement-Control) in six-sigma were combined for application in the management of software projects. The change metrics are presented based on GQM, and the requirement changes are classified according to their effect in project quality. Further, statistical methods were used in the analysis and the control of these requirement changes. Finally, we illustrate our approach with a business case.
    Advanced Management of Information for Globalized Enterprises, 2008. AMIGE 2008. IEEE Symposium on; 10/2008
  • Shuguang He, Li Li, Ershi Qi
    [Show abstract] [Hide abstract]
    ABSTRACT: Compared with other manufacturing processes, the process of semiconductor assembly has several particular characteristics: highly automated manufacturing processes, high manufacturing speed and multivariate critical quality characteristics. Based on the requirements of continuous quality improvement in semiconductor assembly processes, a method of material quality tracking and controlling with SPC chart was put forward. With this method, the sampling program can be adjusted according to the quality record of a supplier. And then a framework of 3-layer SPC was put forward. In this framework, the CTQ, qualification rate of processes, and qualification rate of final products can be controlled by proper SPC chart in different layer and this method is helpful to avoid unqualified products effectively. Furthermore, a model of quality improvement in semiconductor assembly with SPC and data mining was studied. This model can be used for improving the ability of process diagnosing and shortening the diagnosing time. At last, a structure of an integrated quality information system for semiconductor assembly was put forward. The result of this paper may be helpful for the continuous quality improvement in semiconductor assembly processes and it can also be used in other similar processes.
    Technology and Innovation Conference, 2006. ITIC 2006. International; 12/2006
  • [Show abstract] [Hide abstract]
    ABSTRACT: Listed park companies are special colony of Chinese economic structure after reform and opening up. This paper takes listed park companies into account and studies the service styles and payoff patterns in listed companies. At the beginning, the listed park companies and their characteristics are analyzed by taking Company X as example. Then the main service styles are brought forward after a contrast analysis between ten of main companies. At the end, a payoff pattern for listed companies currently is discussed by research on Company X
    Service Operations and Logistics, and Informatics, 2006. SOLI '06. IEEE International Conference on; 07/2006
  • Zhen He, Qing'an Cui, Shuguang He
    [Show abstract] [Hide abstract]
    ABSTRACT: Based on the extensive literature review and the philosophy of integration of quality tools, the paper develops integrated quality information system (IQIS) software, and applies it to a manufacturing company. The software integrates the quality tools as well as the process quality information. It provides guidance for locating bottleneck process through integrated data analysis and also supports six sigma process improvement. The result shows that the application of IQIS can optimize the process of design and manufacturing, shorten the cycle time of product, reduce the cost, and realize quality improvement continuously
    Management of Innovation and Technology, 2006 IEEE International Conference on; 07/2006