Published Paper Details:

The mechanical properties of aluminum wire rods--such as conductivity, elongation, and ultimate tensile strength--play a vital role in various industrial applications. However, traditional methods for assessing these properties can be time-intensive and require complex experimental setups. To address this, our research introduces a predictive model powered by Artificial Neural Networks (ANNs) to estimate these properties based on three key parameters: cooling temperature, casting speed, and rolling speed. By training the ANN model with an extensive dataset of experimental measurements, we were able to capture the intricate nonlinear relationships between the processing conditions and the resulting material properties. The model proved to be highly accurate and reliable in predicting conductivity, elongation, and tensile strength, offering a practical and efficient alternative to conventional testing methods. Adopting this predictive model in industrial settings has the potential to transform operations, improve efficiency, reduce costs, and streamline quality control. This study highlights the value of machine learning in metallurgy, opening the door to smarter and more automated manufacturing processes. Moving forward, we aim to refine the model further, expand the dataset to include a wider range of processing scenarios and integrate the model into real-time monitoring systems to optimize operational performance.