Process monitoring for correlated gamma‐distributed data using generalized‐linear‐model‐based control charts

Jearkpaporn, Duangporn; Montgomery, Douglas C.; Runger, George C.; Borror, Connie M.

doi:10.1002/qre.521

Cited by 60 publications

(38 citation statements)

References 10 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Skinner et al (2003) e Jearkpaporn et al (2003) propuseram o uso de gráficos de controle para resíduos deviance dos MLGs no monitoramento de contagem de não-conformidades com distribuição Poisson e Gama, respectivamente. Russo et al (2008) usou o MLG para o monitoramento do número de não-conformidades em tecidos, seguindo uma distribuição Poisson.…”

Section: Modelos De Regressão Linear Múltiplaunclassified

Gráfico ewmareg aplicado no monitoramento de processos industriais

Pedrini

Santana

Caten

2011

Revista PO: R. Eletr. de Eng. de Produção e Correlatas

View full text Add to dashboard Cite

Resumo: Quando as características de qualidade do processo são dependentes das variáveis de controle e estas variam durante a execução do processo, violam-se as suposições necessárias à implementação dos gráficos de controle tradicionais. Se os valores das variáveis de controle do processo são conhecidos, é possível aplicar gráficos de controle de regressão. Um dos mais recentes gráficos desta linha é o EWMAREG, que consiste no monitoramento dos resíduos padronizados do modelo de regressão via gráfico de controle de médias móveis exponencialmente ponderadas. O presente trabalho tem como objetivo apresentar uma sistemática para a aplicação do gráfico de controle EWMAREG no monitoramento de um processo simulado de uma indústria química. A característica monitorada foi a taxa de corrosão de tubos de aço, em função de quatro variáveis de controle. A ferramenta aplicada demonstrou elevado potencial de detectar alteração no comportamento da taxa de corrosão, garantindo a estabilidade do processo.Palavras-chave: EWMAREG. Resíduos padronizados. Modelos de Regressão. Taxa de corrosão. Abstract:If the process quality characteristics are dependent of control variables, and these vary during the process operation, the basic assumptions of control charts are violated. If the values of the control variables are known, it's possible to apply the regression control chart. One of the most recent works in this area is the EWMAREG chart, which is the monitoring of the standardized residuals using exponentially weighted moving average control chart. In this paper, we present a systematic application of the EWMAREG control chart in monitoring a simulated process of chemical industry. The process characteristic monitored was the corrosion rate of steel pipe in function of four process control variables. The tool applied demonstrated high potential to detect change in surveillance of corrosion rate, ensuring stability process. Tal suposição é violada quando ocorrem alterações frequentes nas variáveis de controle do processo, causando a alteração na média dos dados monitorados. PalavrasEm outra situação, quando uma variável de controle é propositalmente ajustada para um valor extremo, a característica de qualidade pode assumir um valor diferente de seu comportamento usual, não havendo, no entanto, nenhuma falha no processo.Em ambos os casos, a característica de qualidade de um produto ou processo pode ser representada pelo seu relacionamento com as variáveis de controle, sendo possível o uso do gráfico de controle de regressão (JACOBI et al., 2002;LOREDO et al., 2002; SHU et al., 2007).

show abstract

Section: Modelos De Regressão Linear Múltiplaunclassified

Gráfico ewmareg aplicado no monitoramento de processos industriais

Pedrini

Santana

Caten

2011

Revista PO: R. Eletr. de Eng. de Produção e Correlatas

View full text Add to dashboard Cite

show abstract

“…In this context, various approaches have been proposed by researchers for constructing of control charts for autocorrelated data [10,11,12,13,14]. Alwan and Roberts [15] propose a univariate control chart for autocorrelated data.…”

Section: Introductionmentioning

confidence: 99%

MCEWMA control chart to detect small shift for autocorrelated water treatment process responses

Bardhan

Mukherjee

Pal³

2011

2011 IEEE International Conference on Quality and Reliability

View full text Add to dashboard Cite

Statistical process control (SPC) chart for individual observation helps to understand the state of control, stability, and capability of a process. However, most of the typical control chart suggested for individual observation is primarily based on the assumption that the process data are independent and normally distributed. This assumption of independency and normality is generally violated in many chemical processes. Response characteristic or output may have autocorrelation (or data are time dependent), and traditional control chart becomes practically unsuitable for such situations. A two-stage time series modelling and monitoring of residual approach by using control chart or using variable control limit-based MCEWMA is generally recommended. These charts can detect small shift for autocorrelated individual responses. In this paper, the usefulness of MCEWMA chart to detect small shift for autocorrelated mineral water treatment process is verified. The ARL values for MCEWMA are also proposed based on simulation results. The case study results confirms the suitability of ECWMA and is recommended as an alternative to the two-stage time series model and residual special control chart approach.

show abstract

“…Generalized linear models (GLMs) are effective in analyzing attribute data and have been applied to monitor processes, e.g., Hansen and Thyregod 21 , Jearkpaporn et al 22 , Tu and Piegorsch 23 and Skinner et al 24,25 . Such a wide application indicates that GLM can enhance the effectiveness of gauge capability analysis in environments in which variables are exponential family distributions.…”

Section: Introductionmentioning

confidence: 99%

Gauge capability studies for attribute data

Lyu

Chen

2007

Quality & Reliability Eng

View full text Add to dashboard Cite

A gauge repeatability and reproducibility (R&R) method is developed to assess the capability of a measurement system. Although gauge capability studies have received substantial attention, few studies have investigated attribute data despite their wide application in industry. The primary aim of this research is to develop a procedure, based on the generalized linear model, to evaluate the R&R of a measurement system for attribute data. To calculate repeatability of a system, the procedure integrates the iterative weighted least squares (IWLS) method and deviance analysis. The proposed procedure is applied to an inclusion measurement system to verify its adequacy to model the process capability.

show abstract

Process monitoring for correlated gamma‐distributed data using generalized‐linear‐model‐based control charts

Cited by 60 publications

References 10 publications

Gráfico ewmareg aplicado no monitoramento de processos industriais

Gráfico ewmareg aplicado no monitoramento de processos industriais

MCEWMA control chart to detect small shift for autocorrelated water treatment process responses

Gauge capability studies for attribute data

Contact Info

Product

Resources

About