How to perform a simultaneous optimization with several response variables

Abstract

A problem facing the product development community is developing simultaneous solutions of response variables (to several properties) that depends on a number of independent variables or sets of responses. Harrington, among others, addressed this problem and presented a desirability function with a functional approach. Derringer and Suich altered their approach and illustrated how multiple variables can be transformed into a convenience function. This work redid the calculation performed by them using another software and made a comparative discussion of the results found.

Scientific research trends about metaheuristics in process optimization and case study using the desirability function

“…Its goal is to find the operating conditions that ensure that the criteria of all involved responses are met and, at the same time, provide the best value trade-offs in the desirable joint response. Furthermore, its easy interpretation and implementation motivated the method to be described and its performance (Cardoso et al, 2023;Gunst et al, 1996Gunst et al, , 2011Vera Candioti et al, 2014).…”

“…A viable explanation for this fact is that this combination is present in the Minitab® software's Optimizer function, which would facilitate the execution of this method (Cardoso et al, 2023;Gomes, Pereira, Marins, et al, 2019). DOE is a structured and organized method used to determine the relationship between different process input and output factors, involving the definition of the set of experiments, in which all relevant factors are systematically varied.…”

Statistics as a tool for decision making in agricultural and environmental experiments

“…The strong competitiveness, the diffusion of technology, and the competence and responsibility of researchers make these procedures impractical. Such ideas are applicable to the optimization of the production of products that are already on the market and to their suitability for consumer preference (Cardoso, Reis, Silva, Almeida, et al, 2023;Morais et al, 2005).…”

“…DOE é um método estruturado e organizado utilizado para se obter a relação entre diferentes fatores de entrada e saída do processo, envolvendo a definição do conjunto de experimentos, em que todos os fatores relevantes são sistematicamente variados. Analisando os resultados obtidos, um pode determinar o grau de influência sobre a variável de resposta de cada fator utilizado, assim como as interações entre os fatores e as condições ótimas (Cardoso, Reis, Silva, Almeida, et al, 2023;Cardoso, Reis, Silva, Barros, et al, 2023;Korolchenko & Minaylov, 2020). Currently, metaheuristic algorithms inspired by nature are used to solve problems that are difficult to solve, and it has been shown that metaheuristics are very efficient (Askarzadeh, 2016).…”