Case Study: Experimental Design in a Pet Food Manufacturing Company

Prat, Albert; Tort, Xavier

doi:10.1080/08982119008918838

Cited by 3 publications

(3 citation statements)

References 4 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…To apply DoE, it is necessary to adopt a standard procedure that allows randomization, replication and blocking. Santos et al (2018), Dean et al (2017), Politis et al (2017), Montgomery (2013), Freeman et al (2013), Carpinetti (2000), Coleman and Montgomery (1993) and Prat and Tort (1990) gather recommendations and phases on the planning, validation, and execution, analysis and optimization of industrial experiments and among the main aspects highlighted in the proposed phases are:…”

Section: Methodsmentioning

confidence: 99%

Thermal treatment process of PET bottles filaments using industrial design of experiments

Cotrim

Machado

Leal

et al. 2021

IJPPM

View full text Add to dashboard Cite

PurposeThe purpose of this paper is to present the application of Design of Experiments techniques for the analysis of operating parameters of an industrial oven for the heat treatment process of polyethylene terephthalate (PET) bottle filaments.Design/methodology/approachThe focus is on evaluating new ways of operating the transformation process. The main issue is to raise what are the variables interfering with the performance of the oven. The complete 2k factorial for three factors of control was used to analyze the behavior of these variables and their relationships in the specific response parameter for the process.FindingsThe results presented in this work allow the company to have greater knowledge about the operation of the equipment. The study showed possibilities of 14.8% energy reduction.Research limitations/implicationsThe heat treatment activity was characterized as a critical point in the production process, and techniques with empirical approaches, based on statistical techniques, was an opportunity that the company has to improve the execution of activities without major investments for the quality of the final product. The application of statistical quality techniques showed to be very promising.Originality/valueThe fact that the study was conducted using subjective quality performance makes this work different from others presented in the literature, showing the possibility to apply Design of Experiments using main control factors based on the opinion of experienced personnel involved in the process analyzed.

show abstract

Section: Methodsmentioning

confidence: 99%

Thermal treatment process of PET bottles filaments using industrial design of experiments

Cotrim

Machado

Leal

et al. 2021

IJPPM

View full text Add to dashboard Cite

show abstract

“…On the basis of the data published by Prat and Tort‐Martorell, 2 Box et al 3 present a 2 3 design carried out in a pet food factory (p. 194). Several responses are analyzed, but we consider only the amount of product obtained (yield).…”

Section: Situations With Factors Of Borderline Influence: Examplesmentioning

confidence: 99%

“…When carrying out an experimental plan in an industrial environment, if the person in charge of the process is asked which of the following errors they would rather commit- (1) considering that a factor influences the response when in fact it does not or (2) ignoring the influence of a factor that actually has an effect-they will generally choose the first. Although it is indeed true that arriving at the erroneous conclusion that factor A affects the response-when in fact it does not-can lead to controlling A unnecessarily and even to make an unnecessary investment, the quality of the final product will nevertheless not be affected.…”

Section: Introductionmentioning

confidence: 99%

Selecting relevant effects in factorial designs

Cintas

Rodero

Tort‐Martorell

2020

Quality & Reliability Eng

View full text Add to dashboard Cite

Industrial contexts tend to be as much or more concerned about the probability of ignoring an effect when its influence on the response is relevant (Type II error) than about the probability of considering an effect to be active when in fact, it is not (Type I error). Here, we present a methodology for taking into account both types of error by fixing an effect value that is considered large enough to control the probability of it going unnoticed. In addition, we propose a plot to visualize the results obtained.

show abstract