Composite materials are extensively utilized across various industries due to their light-weight nature and superior mechanical properties. Enhancing and predicting the mechanical behaviour of these composites is crucial for optimizing their performance in various applications. This research investigates the prediction of load-bearing capacity in carbon-fiber laminates using Artificial Neural Networks (ANNs). The study involved experimental evaluation of the mechanical properties of the carbon metal composite materials, focusing on their behavior under tensile stress. The ANN model was trained on experimental data, including laminate dimensions, volume fraction, and applied load. Results showed the model’s robust performance in accurately predicting tensile stress and classifying samples across diverse data-sets, indicating high reliability and efficacy.
The study also highlights the potential of ANNs in modeling and predicting the mechanical behavior of composite materials, suggesting their usefulness in the design and analysis of carbon-fiber laminates. It recommends further optimization to improve the model’s accuracy and applicability in real-world scenarios. Overall, this research provides significant insights into the mechanical properties of composite materials and emphasizes the practical potential of ANN modeling in engineering applications.