Abstract:

Researchers are using different statistical techniques for process optimisation and product development both in academia and industries. Similarly, several statistical tools are being employed in the textile industry for process optimisation during the manufacturing of different products. The purpose of this study was to analyse different Taguchi-based techniques in the multi-response optimisation of selected industrial processes and then to generalise the outcomes. Herein, six different Taguchi-based multi-response optimisation techniques, including grey relational analysis (GRA), the weighted signal-to-noise (WSN) ratio, principal component analysis, VIKOR (VlseKriterijumska Optimizacija I Kompromisno Resenje), the multiple response signal-to-noise ratio, and Fuzzy logic were compared against three data sets of industrial processes. The researchers herein optimised cotton dyeing, the finishing of textile to make them oleo-hydrophobic, and the production of rhamnolipids (bio-surfactants). The results demonstrated that the Fuzzy logic-based Taguchi method gave the best optimisation amongst all the other approaches, followed by GRA and WSN for all the selected processes. The said statistical techniques were applied to specific textile and biotechnological processes. The outcomes of this study can help researchers in practical implementation in industrial sectors. In this study, a comparative analysis of the performances of six Taguchi-based multi-response optimisation techniques was conducted for potential industrial processes, particularly textile processing .