The increasing complexity of modern manufacturing systems has amplified the need for intelligent energy monitoring solutions capable not only of visualizing consumption but also of detecting anomalies and predicting failures. Traditional monitoring applications provide real-time dashboards and performance indicators; however, they remain reactive and offer limited capacity for forecasting abnormal behaviors or guiding improvement initiatives. This research proposes an enhanced intelligent energy monitoring framework for smart factory environments, combining neural network modeling with a Six Sigma analytical approach to strengthen prediction accuracy and process stability. The study begins by examining the operational logic of conventional energy monitoring systems, highlighting their architecture, data flow mechanisms, and functional limitations. To address these gaps, a predictive model based on artificial neural networks is developed and trained using real production data to detect erroneous measurements, and predict potential failures related to equipment or data acquisition. Six Sigma methodology is integrated into the modeling process to structure the improvement cycle, refine parameter selection, evaluate statistical significance, and ensure robust model validation through performance metrics and process capability indices. The proposed solution is finalized through the design of a new application framework embedding the predictive model into the existing monitoring architecture. This intelligent platform enables continuous KPI tracking, automated alerts, and data-driven decision-making for proactive maintenance, process optimization, and energy efficiency. Results demonstrate that the integration of AI and Six Sigma improves monitoring intelligence, reduces reaction time, and strengthens operational reliability in Industry 4.0 environments. The findings confirm the potential of hybrid analytical approaches to transform energy monitoring from a descriptive system into a predictive and prescriptive decision-making tool.