Modelling of the Flexural Strength of Low Flow Polypropylene Talc/Colemanite Hybrid Composite Materials with Taguchi and ANFIS Methods

摘要

In this experimental study, Taguchi experiment design and Adaptive Neuro-Fuzzy Inference System (ANFIS) methods were used to optimize the flexural strength of polypropylene/talc/colemanite hybrid composite materials depending on their production parameters and hybrid filler ratios in different percentages by weight. It is known, that in most sectors today, for example, in the automotive industry, weight reduction efforts are under way. However, there is currently no published scientific and/or experimental studies on the three point bending properties of polypropylene/talc/colemanite hybrid composite materials. On the other hand, it is also known that the three point bending properties of thermoplastic composites are influenced by injection molding parameters and that these characteristic features influenced by injection molding parameters can not be predicted and/or determined, for example from flow analysis and/or computer-aided design programs. In this context, in the first phase of the study, the predicted boundary conditions of the design parameters such as hybrid filler ratio and injection parameters such as nozzle temperature, injection speed and mold temperature were determined, which can influence the three-point bending properties and also increase and/or decrease the flexural strength. In the second phase of the study, three-point bending tests were performed on talc (TC) and colemanite (GC) filled polypropylene (LPPH) hybrid composite materials according to ISO 178, and the ANFIS method was used to model the flexural strengths of LPPH/TC/GC hybrid composite materials. The results obtained were compared with the ANOVA results obtained with the Taguchi experiment design method. It was found that the ANFIS method provided satisfactory results.