Artificial neural network-based decision support tool for identifying operational causes of energy consumption anomalies in production lines

Energy management is a critical challenge for industries that rely on energy-intensive production lines, where inefficiencies can increase costs and waste. This study introduces a practical decision support tool, based on Artificial Neural Networks, designed to monitor energy consumption and identify the operational causes of anomalies. By analyzing data from production lines, the tool helps identify inefficiencies linked to factors like downtime, production speed, and defect rates. The proposed system has been tested on a real case study, showing the ability to detect different issues such as energy waste during unproductive periods or excessive consumption tied to high defect rates. Thus, it also highlights how managerial decisions, such as planned stoppages during cleaning or maintenance, can significantly affect energy efficiency. By making these insights clear, the system helps companies make smarter choices to optimize energy use and reduce waste.