Particle-reinforced metal matrix composites, while having space and automotive industries as their main application area, provide very high strength, toughness, and wear resistance properties but are still facing problem of low toughness which is mainly due to the stiff reinforcements, agglomeration, and the interfacial problems. The research is investigated in terms of perfect dispersion, combined reinforcements, and sophisticated treatment to attain best strength-toughness ratio. The current research is focused on exploring mechanical features and machinability of new hybrid composite consisting of Magnesium-Calcium (Mg-Ca) alloy that is in turn reinforced with Hydroxyapatite (HA) and Carbon Nanofibers (CNFs). The composite is manufactured utilizing the stir casting technique, which aided the even distribution of reinforcements within the metal matrix, enhancing structural uniformity and mechanical properties in the process. To characterize the mechanical properties of hybrid composites, tensile strength, hardness, and compressive strength are determined. In addition, the Light Multi-head Attention Gannet Convolutional Neural Network (LMGCNN)-based predictor of the behaviour of the composite in use and machine also further enhances the effectiveness of the model with Clan Coordination-Based Owl Search Algorithm (CCBOSA). The performance of the proposed model is evaluated in MATLAB platform and compared with different composites. The composite under consideration shows outstanding characteristics such as highest elastic modulus of 170 GPa, Young’s modulus of 175 GPa, and yield stress of 380 MPa compared to Brass, Duralumin, Fe–C, and Cu–Sn alloys. Moreover, it has the lowest magnetization value of 0.3, which suggests better mechanical performance as well as lower magnetic response.
Khan et al. (Fri,) studied this question.