<p>The present work proposed a response surface method (RSM) based regression equation model and fuzzy logic inference system model (FIS) that can predict the wear performance of steel-embedded glass-epoxy polymer hybrid composite (SGFPC). The predictive model that defined the correlation between the inputs multivariate such as sliding distance, applied load, and sliding velocity and the outputs multivariate such as specific wear rate (SWR) and coefficient of friction (CoF) were derived. This was obtained by developing FIS models and the traditional RSM-regression equation method. The membership functions (MFs) and fuzzy rule bank built on the bases of designer experience, knowledge, and experimental results via MATLAB fuzzy logic toolbox. RSM-regression equation model was developed by using Minitab 19. The results show that the accuracy of the predicted value by the FIS model as compared to the RSM-regression equation model is very good as compared with the experiment results. A FIS and mathematical regression models are a build-up to predict the output within the defined ranges and judge against the experimental results and the most suitable model with most precision to predict the SWR and CoF is identified. The purpose of this work is not only modeling by FIS but also showing a comparison of two modeling methods like FIS and RSM regression method. It also shows the accuracy of the FIS model is approximately 98% as compared with experimental results and validation results. Lastly, a scanning electron microscope (SEM) was used to examine the hybrid composite’s worn surface. Weight loss happened from the hybrid composite’s worn surface developing shallow, thin grooves at low stress and massive cracks at high load.</p>