ABSTRACT
Detecting manufacturing defects is vital for quality and cost efficiency. The use of artificial neural networks (ANNs) to enhance defect detection procedures is explored in this research. Preprocessing data and utilizing the Adam optimizer to train a multi-layered ANN are the two main tasks of the project. The findings show that, in comparison to conventional techniques, ANNs greatly improve accuracy, precision, and recall in fault detection. The results highlight how artificial neural networks (ANNs) have the potential to transform manufacturing quality control by offering more dependable and precise detection capabilities. The study indicates that fault detection efficiency can be further increased by investigating more sophisticated ANN structures and real-time data processing. In order to fully utilize ANNs in manufacturing settings, future research will concentrate on these areas with the goal of achieving even higher gains in operational effectiveness and quality control.
