A nonlinear programming solution to robust multi-response quality problem

Köksoy, Onur

doi:10.1016/j.amc.2007.06.023

Cited by 37 publications

(21 citation statements)

References 12 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…However, to use the most popular desirability function-based method, the so-called Derringer and Suich's method [6,7], the analyst needs to specify values to four types of shape parameters/weights. This is not a simple task and has impact on the method's solution [8,9]. Some authors, including Chiao and Hamada [10], also criticize this method arguing that the composite function value does not allow a clear interpretation except the principle that a higher value is preferred.…”

Section: Research Objectivesmentioning

confidence: 96%

Multiple response optimization: a global criterion‐based method

Costa

Pereira

2010

Journal of Chemometrics

View full text Add to dashboard Cite

Processes and products have by nature many quality characteristics that must be in some sense optimized simultaneously. With this aim, a method which can be used easily and efficiently by practitioners for optimizing multi-response problems is proposed. Implementation steps and considerations, in addition to optimization measures to assess method's solutions and guide the analyst in finding an effective compromise solution, are also presented. Three classical examples from the literature are used to assess the performance of several prominent methods in the response surface methodology (RSM) framework and help practitioners make a better-informed choice among them.

show abstract

Section: Research Objectivesmentioning

confidence: 96%

Multiple response optimization: a global criterion‐based method

Costa

Pereira

2010

Journal of Chemometrics

View full text Add to dashboard Cite

show abstract

“…Para múltiplas respostas, entretanto, duas estratégias podem ser adotadas: a) a aglutinação das equações do Erro Quadrático Médio de cada resposta através da sua soma ponderada; ou, b), a escolha da equação do Erro Quadrático Médio da resposta de maior importância como função objetivo, atribuindo às demais o caráter de restrições [5,11].…”

Section: Superfície De Resposta Dualunclassified

Otimização do processo de soldagem FCAW usando o erro quadrático médio multivariado

et al. 2010

View full text Add to dashboard Cite

ResumoEncontrar um conjunto ótimo de parâmetros para um processo de soldagem é uma tarefa pouco trivial, face às múltiplas características exigíveis ou desejáveis que devem ser analisadas. Além disso, a negligência da estrutura de variância-covariância Palavras-chave: Erro Quadrático Médio Multivariado (EQMM). FCAW. Projeto e Análise de Experimentos. Metodologia de Superfície de Respostas. Abstract: The optimization of welding processes is not a trivial task, mainly due to the great number of exigible and desirable characteristics that must be analyzed. Moreover, the optimization of a welding process with multiple characteristics without to consider the variance-covariance structure, may lead to inadequate optimum. To help in this task, a method of multiobjective optimization based in the Multivariate Mean Square Error applied in the study of multiple correlated characteristics of a FCAW (Flux Cored Arc Welding) welding process will be presented. This method characterized by a combined approach based in the Response Surface Methodology, Design of Experiments and Principal Components Analysis consisted in an attempt to achieve the nearest values to specific targets, for each studied characteristic (penetration, deposition rate, deposition efficiency, convexity index of the weld bead and dilution) considering the welding variables expressed in function of welding voltage (V), wire feed speed (Va) and the contact tip to workpiece distance (d). The results point out a good adequacy of the proposed method. Key-words: Multivariate Mean Square Error (MMSE); FCAW; Design of Experiments; Response Surface Methodology (RSM). IntroduçãoNum processo de soldagem é desejável que se determinem parâmetros adequados para sua realização, com a máxima acurácia possível. A busca por esses parâmetros, entretanto, passa por um processo de otimização de múltiplas variáveis, representando múltiplas características de qualidade, exigíveis ou desejáveis, para um determinado processo ou produto, constituindo-se em uma tarefa de difícil execução e de eficácia improvável.

show abstract

“…In this paper, it is assumed that there is no correlation between responses; a similar assumption is made in other studies, such as Koksoy (2008). However, by considering each response and using univariate M-estimators to estimate the coefficients, a problem could occur, and outlier detection is required to consider all of the responses simultaneously.…”

Section: Introductionmentioning

confidence: 99%

“…This methodology specifically utilizes both experimentation and optimization methods to determine the system's optimum operating conditions. Koksoy (2008Koksoy ( , 2006 presented MSE as a robust design criterion in multi-response problems. Additionally, genetic algorithms and generalized reduced gradients method were used in their solution stage.…”

Section: Introductionmentioning

confidence: 99%

Simultaneous robust estimation of multi-response surfaces in the presence of outliers

Bashiri

Moslemi

2013

J Ind Eng Int

View full text Add to dashboard Cite

A robust approach should be considered when estimating regression coefficients in multi-response problems. Many models are derived from the least squares method. Because the presence of outlier data is unavoidable in most real cases and because the least squares method is sensitive to these types of points, robust regression approaches appear to be a more reliable and suitable method for addressing this problem. Additionally, in many problems, more than one response must be analyzed; thus, multi-response problems have more applications. The robust regression approach used in this paper is based on M-estimator methods. One of the most widely used weighting functions used in regression estimation is Huber's function. In multi-response surfaces, an individual estimation of each response can cause a problem in future deductions because of separate outlier detection schemes. To address this obstacle, a simultaneous independent multi-response iterative reweighting (SIMIR) approach is suggested. By presenting a coincident outlier index (COI) criterion while considering a realistic number of outliers in a multi-response problem, the performance of the proposed method is illustrated. Two well-known cases are presented as numerical examples from the literature. The results show that the proposed approach performs better than the classic estimation, and the proposed index shows efficiency of the proposed approach.

show abstract

A nonlinear programming solution to robust multi-response quality problem

Cited by 37 publications

References 12 publications

Multiple response optimization: a global criterion‐based method

Multiple response optimization: a global criterion‐based method

Otimização do processo de soldagem FCAW usando o erro quadrático médio multivariado

Simultaneous robust estimation of multi-response surfaces in the presence of outliers

Contact Info

Product

Resources

About