article · Applied Sciences
A decision-support framework was developed for smart factories to differentiate between high energy demand caused by production and poor energy performance. This interpretable system uses daily total energy consumption and product-referenced specific energy consumption (SEC) for three anonymised products. It analysed 401 valid daily energy records from a single manufacturing plant collected between 2019 and 2026. The framework employs chronological Q90 and Q95 thresholds, comparing them with other statistical limits. A rule matrix assigns four recommendation levels, and a robust score identifies unusual operating days. The system showed activation rates between 16.96% and 26.95%, Level 3 recommendations from 1.77% to 2.60%, and anomaly rates from 6.65% to 8.48%.
This research provides a clear method for factories to understand their energy use, helping them identify inefficiencies rather than simply high production-related consumption. This can lead to more effective energy management, cost savings, and improved operational sustainability.
This decision-support framework could be implemented as a software tool for energy managers and production supervisors in smart factories. It offers practical support for monitoring, inspecting, scheduling, and prioritising operational reviews related to energy use. The system appears to be an applied research outcome, potentially ready for integration into existing factory management systems or as a standalone energy optimisation tool.
AI-generated from the published abstract. Always read the original work before citing.
Smart factories need transparent methods that distinguish high energy demand caused by production from poor energy performance. This study presents an interpretable decision-support framework based on daily total energy consumption and product-referenced specific energy consumption (SEC) for three distinct anonymized products. The analysis used 436 daily records collected between 2019 and 2026 from a single manufacturing plant. After the data-quality audit, 401 valid energy records were retained. Normality was rejected in seven of the eight annual datasets. Chronological Q90 and Q95 thresholds were therefore used as the main approach and compared with limits based on the mean and standard deviation and on the median and MAD. A complete rule matrix assigned four recommendation levels, while a separate robust score identified unusual operating days. Across 907 evaluations, activation rates ranged from 16.96% to 26.95%, Level 3 recommendations from 1.77% to 2.60%, and anomaly rates from 6.65% to 8.48%. Confidence intervals and sensitivity analyses showed that the main conclusions remained stable across the analytical choices. The framework supports monitoring, inspection, scheduling, and prioritized operator review.
This page summarises published work. The authoritative version sits with the publisher.
DOI: 10.3390/app16178601
Is something wrong with this record? Report it or request removal.
Discussion
Have you built on this work, tried to replicate it, or seen it applied in practice? Share what you know. Verified researchers and MARATTO™ domain experts can open a discussion, and any member can reply. Contributions are reviewed before they appear.
No discussion yet. Open the first thread.
New to MARATTO™? Create a free account.
