Towards Fault Detection in Industrial Equipment through Energy Consumption Analysis: Integrating Machine Learning and Statistical Methods
Accurately forecasting the energy consumption of industrial equipment and linking these forecasts to equipment health has become essential in modern manufacturing. This capability is crucial for advancing predictive maintenance strategies to reduce energy consumption and greenhouse gas emissions. In...
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
EDP Sciences
2025-01-01
|
| Series: | E3S Web of Conferences |
| Subjects: | |
| Online Access: | https://www.e3s-conferences.org/articles/e3sconf/pdf/2025/01/e3sconf_icegc2024_00079.pdf |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832098579585433600 |
|---|---|
| author | Baddou Nada Dadda Afaf Rzine Bouchra Hmamed Hala |
| author_facet | Baddou Nada Dadda Afaf Rzine Bouchra Hmamed Hala |
| author_sort | Baddou Nada |
| collection | DOAJ |
| description | Accurately forecasting the energy consumption of industrial equipment and linking these forecasts to equipment health has become essential in modern manufacturing. This capability is crucial for advancing predictive maintenance strategies to reduce energy consumption and greenhouse gas emissions. In this study, we propose a hybrid model that combines Long Short-Term Memory (LSTM) for energy consumption prediction with a statistical change-point detection algorithm to identify significant shifts in consumption patterns. These shifts are then correlated with the equipment’s health status, providing a comprehensive overview of energy usage and potential failure points. In our case study, we began by evaluating the prediction model to confirm the performance of LSTM, comparing it with several machine learning models commonly used in the literature, such as Random Forest, Support Vector Machines (SVM), and GRU. After assessing different loss functions, the LSTM model achieved the strongest prediction accuracy, with an RMSE of 0.07, an MAE of 0.0188, and an R2 of 92.7%. The second part of the model, which focuses on detecting change points in consumption patterns, was evaluated by testing several cost functions combined with binary segmentation and dynamic programming. Applied to a real-world case, it successfully detected a change point two months before equipment failure, offering the potential to reduce energy consumption by 27,052 kWh. This framework not only clarifies the relationship between equipment health and CO2 emissions but also provides actionable insights into emission reduction, contributing to both economic and environmental sustainability. |
| format | Article |
| id | doaj-art-10a0467331bb4bc2ba452ac03d1ab791 |
| institution | Kabale University |
| issn | 2267-1242 |
| language | English |
| publishDate | 2025-01-01 |
| publisher | EDP Sciences |
| record_format | Article |
| series | E3S Web of Conferences |
| spelling | doaj-art-10a0467331bb4bc2ba452ac03d1ab7912025-02-05T10:46:25ZengEDP SciencesE3S Web of Conferences2267-12422025-01-016010007910.1051/e3sconf/202560100079e3sconf_icegc2024_00079Towards Fault Detection in Industrial Equipment through Energy Consumption Analysis: Integrating Machine Learning and Statistical MethodsBaddou Nada0Dadda Afaf1Rzine Bouchra2Hmamed Hala3LGM, Faculty of Science and Technology, Sidi Mohamed Ben Abdellah UniversityMathematical and Computer Modeling Laboratory, University moulay Ismail, ENSAMLGM, Faculty of Science and Technology, Sidi Mohamed Ben Abdellah UniversityMathematical and Computer Modeling Laboratory, University moulay Ismail, ENSAMAccurately forecasting the energy consumption of industrial equipment and linking these forecasts to equipment health has become essential in modern manufacturing. This capability is crucial for advancing predictive maintenance strategies to reduce energy consumption and greenhouse gas emissions. In this study, we propose a hybrid model that combines Long Short-Term Memory (LSTM) for energy consumption prediction with a statistical change-point detection algorithm to identify significant shifts in consumption patterns. These shifts are then correlated with the equipment’s health status, providing a comprehensive overview of energy usage and potential failure points. In our case study, we began by evaluating the prediction model to confirm the performance of LSTM, comparing it with several machine learning models commonly used in the literature, such as Random Forest, Support Vector Machines (SVM), and GRU. After assessing different loss functions, the LSTM model achieved the strongest prediction accuracy, with an RMSE of 0.07, an MAE of 0.0188, and an R2 of 92.7%. The second part of the model, which focuses on detecting change points in consumption patterns, was evaluated by testing several cost functions combined with binary segmentation and dynamic programming. Applied to a real-world case, it successfully detected a change point two months before equipment failure, offering the potential to reduce energy consumption by 27,052 kWh. This framework not only clarifies the relationship between equipment health and CO2 emissions but also provides actionable insights into emission reduction, contributing to both economic and environmental sustainability.https://www.e3s-conferences.org/articles/e3sconf/pdf/2025/01/e3sconf_icegc2024_00079.pdfmachine learningenergy savingearly failure predictioncarbone footprintpredictive maintenance |
| spellingShingle | Baddou Nada Dadda Afaf Rzine Bouchra Hmamed Hala Towards Fault Detection in Industrial Equipment through Energy Consumption Analysis: Integrating Machine Learning and Statistical Methods E3S Web of Conferences machine learning energy saving early failure prediction carbone footprint predictive maintenance |
| title | Towards Fault Detection in Industrial Equipment through Energy Consumption Analysis: Integrating Machine Learning and Statistical Methods |
| title_full | Towards Fault Detection in Industrial Equipment through Energy Consumption Analysis: Integrating Machine Learning and Statistical Methods |
| title_fullStr | Towards Fault Detection in Industrial Equipment through Energy Consumption Analysis: Integrating Machine Learning and Statistical Methods |
| title_full_unstemmed | Towards Fault Detection in Industrial Equipment through Energy Consumption Analysis: Integrating Machine Learning and Statistical Methods |
| title_short | Towards Fault Detection in Industrial Equipment through Energy Consumption Analysis: Integrating Machine Learning and Statistical Methods |
| title_sort | towards fault detection in industrial equipment through energy consumption analysis integrating machine learning and statistical methods |
| topic | machine learning energy saving early failure prediction carbone footprint predictive maintenance |
| url | https://www.e3s-conferences.org/articles/e3sconf/pdf/2025/01/e3sconf_icegc2024_00079.pdf |
| work_keys_str_mv | AT baddounada towardsfaultdetectioninindustrialequipmentthroughenergyconsumptionanalysisintegratingmachinelearningandstatisticalmethods AT daddaafaf towardsfaultdetectioninindustrialequipmentthroughenergyconsumptionanalysisintegratingmachinelearningandstatisticalmethods AT rzinebouchra towardsfaultdetectioninindustrialequipmentthroughenergyconsumptionanalysisintegratingmachinelearningandstatisticalmethods AT hmamedhala towardsfaultdetectioninindustrialequipmentthroughenergyconsumptionanalysisintegratingmachinelearningandstatisticalmethods |