Machine Learning-Based Prediction of Mechanical and Thermal Properties of Nickel/Cobalt/Ferrous and Dried Leaves Fiber-Reinforced Polymer Hybrid Composites

Abstract

Dried leaves are the outstanding origin of cellulosic plant matter, and it is securing reputation as a renewable resource. Dried leaves fiber is suggested to possess the capability to substitute synthetic fibers in polymer laminates as a reinforcing component. The novelty of the present study reveals the effect of dried leaves fiber, cobalt, nickel, and ferrous reinforcement on the physical, mechanical, and thermal characteristics of epoxy, vinyl-ester, and polyester polymers using artificial neural network (ANN) technique. These composites were fabricated using ultrasonication bath-assisted wet layup method under ambient condition. The outcomes of this research exhibit that the dried leaves-cobalt fillers reinforced in all three polymers possess higher mechanical and thermal stability characteristics when compared with other samples. The reason may be assigned to producing novel hydroxyl functional groups and strong interfacial bonding of fillers within the matrix as observed from Fourier-transform infrared (FTIR) spectra and scanning electron microscope (SEM) micrographs, respectively. Moreover, as observed from the thermogravimetric analysis, the dried leaves-ferrous filler-reinforced polymer hybrid composites provided higher thermal stability. Statistical analysis was performed using the one-way ANOVA technique and found that outcomes were significant statistically under the confidence level of 95%. Hence, this investigation not only emphasize the significance of investigating new polymer composites but also highlight the benefits of engaging advanced modeling to forecast the material characteristics precisely.