Artificial Neural Network and Optimization and Neural Network Approach for Al 7072 Alloy Reinforced with Nanoparticles of Tungsten Carbide

Abstract

Aluminium 7072 has a broad variety of uses in aviation, fences, hydraulic pipelines, and navy structures because to its excellent stability, lesser mass, increased strength- ratio, low cost, and high toughness. A survey of the literature revealed that no experiments on the Al 7072 alloy were conducted to enhance its wear behaviour. Because of its great wear resistance, tungsten carbide (WC) is frequently used in the manufacturing of machining tools, shielding coverings, and carbide tools. The wear resistance property of the Al 7072 alloy was studied by adding increasing weight percentages of stir-cast tungsten carbide nanoparticles (2%, 4%, and 6%). Taguchi L27 orthogonal arrays were used in this work. Dry sliding wear behaviour is evaluated using pin-on-disc wear testing equipment. Frictional coefficient (fc) and rate wear (We) are the responses, whereas the process parameters include nanoparticle composition (Cp), disc rotation speed (Ds), load (L), and sliding distance (Ds). The Taguchi optimisation was utilised to discover the ideal combination for lowering the CoF and rate of wear. Under varied parametric conditions, the findings reveal that tungsten carbide reinforcement with 6% nanoparticles reduces CoF and specific wear rates. An artificial neural network model is also built to anticipate the answers.