Real-Time Fault Detection in Electrical Systems Using Machine Learning and Big Data Analytics

This research explores the application of machine learning and big data analytics for real-time fault detection in electrical systems across multiple industries, including finance, healthcare, and retail. The study evaluates several models, including Artificial Neural Networks (ANN), Support Vector Machines (SVM), Random Forest (RF), and Convolutional Neural Networks (CNN), to detect electrical faults based on parameters such as voltage, current, and power. Descriptive and inferential statistical methods were applied to understand the data distribution and identify key fault indicators. The CNN model demonstrated superior performance with an accuracy of 95%, surpassing other models in detecting non-linear patterns and anomalies in electrical data. Key evaluation metrics, including precision, recall, F1 score, confusion matrix, and ROC-AUC, confirmed the robustness of the model. This study illustrates the significant potential of leveraging machine learning for enhancing system reliability, and suggests further research into integrating these models with emerging sensor technologies for improved real-time monitoring.