2021 IEEE 15th International Symposium on Applied Computational Intelligence and Informatics (SACI) | 2021

Comparison of Full Factorial DoE and SSTE®

 
 

Abstract


Understanding the behavior of industrial operations require complex resource needs, such as budget, operation downtime to perform experiments, and so on. Engineers and scientists mainly use Design of Experiment to understand the effects of the observed factors. In specific cases, these experiments require increased calculation power, due to the rise of the measured records and factors. The results are often questioned, because interpreting them requires an expert in any topic. This study aims to determine, if there is a faster, more cost effective alternative method, with lower need of calculation power, within the same complexity of a model. In this context, the Full Factorial Design of Experiment method was compared with the Secondary Substitution Transfer Equation practice. The results showed many differences between the two methods, reflecting the accuracy of the prediction, the calculation power need, the file size, ease of use, and last, but not least, the file sizes. These results suggest that, the Secondary Substitution Transfer Equation method is a comparative alternative, especially in complex cases, where the observed factors do not behave linearly. It also requests less resource, which can make this practice an easy to use and cost effective way in the experiments.

Volume None
Pages 000211-000214
DOI 10.1109/SACI51354.2021.9465612
Language English
Journal 2021 IEEE 15th International Symposium on Applied Computational Intelligence and Informatics (SACI)

Full Text