A novel method for evaluation of the maintenance impact in the health of industrial components
This study presents a novel method for evaluating maintenance effectiveness in industrial systems, built around the concept of “risk curves” as quantitative indicators of failure. By integrating Failure Mode and Effect Analysis (FMEA) with machine learning-based anomaly detection models, the propose...
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Elsevier
2025-09-01
|
| Series: | Results in Engineering |
| Subjects: | |
| Online Access: | http://www.sciencedirect.com/science/article/pii/S2590123025018808 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1849682784863387648 |
|---|---|
| author | F. Javier Bellido-Lopez Miguel A. Sanz-Bobi Antonio Muñoz Daniel Gonzalez-Calvo Tomas Alvarez-Tejedor |
| author_facet | F. Javier Bellido-Lopez Miguel A. Sanz-Bobi Antonio Muñoz Daniel Gonzalez-Calvo Tomas Alvarez-Tejedor |
| author_sort | F. Javier Bellido-Lopez |
| collection | DOAJ |
| description | This study presents a novel method for evaluating maintenance effectiveness in industrial systems, built around the concept of “risk curves” as quantitative indicators of failure. By integrating Failure Mode and Effect Analysis (FMEA) with machine learning-based anomaly detection models, the proposed approach constructs risk curves by aggregating normalized deviations from monitored variables. These curves reflect the progression of failure modes in real time and enable a quantitative and accurate assessment of the impact of maintenance actions.A key contribution of this research is the use of risk curves as an innovative method to continuously track the potential emergence of failure modes and quantify how maintenance actions contribute to reducing their associated risk. Applied to a feedwater pump in a combined-cycle power plant, these curves successfully detected critical failures, such as bearing wear and leaks, months in advance of traditional methods. Moreover, they provided a data-driven means to assess the effectiveness of maintenance actions, demonstrating their role as a determinant factor in improving component condition and mitigating failure risk.The findings highlight the potential of this methodology to enhance maintenance strategies, reduce downtime, and foster improved collaboration between operation and maintenance teams. This research represents a significant advancement in maintenance evaluation, offering a scalable and data-driven framework that bridges existing gaps in failure diagnostics and decision-making processes. |
| format | Article |
| id | doaj-art-3511ee4f5650423eb77ac2dfddcaf7ff |
| institution | DOAJ |
| issn | 2590-1230 |
| language | English |
| publishDate | 2025-09-01 |
| publisher | Elsevier |
| record_format | Article |
| series | Results in Engineering |
| spelling | doaj-art-3511ee4f5650423eb77ac2dfddcaf7ff2025-08-20T03:24:04ZengElsevierResults in Engineering2590-12302025-09-012710580910.1016/j.rineng.2025.105809A novel method for evaluation of the maintenance impact in the health of industrial componentsF. Javier Bellido-Lopez0Miguel A. Sanz-Bobi1Antonio Muñoz2Daniel Gonzalez-Calvo3Tomas Alvarez-Tejedor4Institute for Research in Technology, ICAI School of Engineering, Pontifical Comillas University, Rey Francisco 4, Madrid 28015, Spain; Corresponding author.Institute for Research in Technology, ICAI School of Engineering, Pontifical Comillas University, Rey Francisco 4, Madrid 28015, SpainInstitute for Research in Technology, ICAI School of Engineering, Pontifical Comillas University, Rey Francisco 4, Madrid 28015, SpainEnel Green Power and Thermal Generation, Endesa - Gas Maintenance Iberia, Ribera del Loira 60, Madrid 28042, SpainEnel Green Power and Thermal Generation, Endesa - Gas Maintenance Iberia, Ribera del Loira 60, Madrid 28042, SpainThis study presents a novel method for evaluating maintenance effectiveness in industrial systems, built around the concept of “risk curves” as quantitative indicators of failure. By integrating Failure Mode and Effect Analysis (FMEA) with machine learning-based anomaly detection models, the proposed approach constructs risk curves by aggregating normalized deviations from monitored variables. These curves reflect the progression of failure modes in real time and enable a quantitative and accurate assessment of the impact of maintenance actions.A key contribution of this research is the use of risk curves as an innovative method to continuously track the potential emergence of failure modes and quantify how maintenance actions contribute to reducing their associated risk. Applied to a feedwater pump in a combined-cycle power plant, these curves successfully detected critical failures, such as bearing wear and leaks, months in advance of traditional methods. Moreover, they provided a data-driven means to assess the effectiveness of maintenance actions, demonstrating their role as a determinant factor in improving component condition and mitigating failure risk.The findings highlight the potential of this methodology to enhance maintenance strategies, reduce downtime, and foster improved collaboration between operation and maintenance teams. This research represents a significant advancement in maintenance evaluation, offering a scalable and data-driven framework that bridges existing gaps in failure diagnostics and decision-making processes.http://www.sciencedirect.com/science/article/pii/S2590123025018808Maintenance effectivenessFailure indicatorPredictive maintenancePHMRCM |
| spellingShingle | F. Javier Bellido-Lopez Miguel A. Sanz-Bobi Antonio Muñoz Daniel Gonzalez-Calvo Tomas Alvarez-Tejedor A novel method for evaluation of the maintenance impact in the health of industrial components Results in Engineering Maintenance effectiveness Failure indicator Predictive maintenance PHM RCM |
| title | A novel method for evaluation of the maintenance impact in the health of industrial components |
| title_full | A novel method for evaluation of the maintenance impact in the health of industrial components |
| title_fullStr | A novel method for evaluation of the maintenance impact in the health of industrial components |
| title_full_unstemmed | A novel method for evaluation of the maintenance impact in the health of industrial components |
| title_short | A novel method for evaluation of the maintenance impact in the health of industrial components |
| title_sort | novel method for evaluation of the maintenance impact in the health of industrial components |
| topic | Maintenance effectiveness Failure indicator Predictive maintenance PHM RCM |
| url | http://www.sciencedirect.com/science/article/pii/S2590123025018808 |
| work_keys_str_mv | AT fjavierbellidolopez anovelmethodforevaluationofthemaintenanceimpactinthehealthofindustrialcomponents AT miguelasanzbobi anovelmethodforevaluationofthemaintenanceimpactinthehealthofindustrialcomponents AT antoniomunoz anovelmethodforevaluationofthemaintenanceimpactinthehealthofindustrialcomponents AT danielgonzalezcalvo anovelmethodforevaluationofthemaintenanceimpactinthehealthofindustrialcomponents AT tomasalvareztejedor anovelmethodforevaluationofthemaintenanceimpactinthehealthofindustrialcomponents AT fjavierbellidolopez novelmethodforevaluationofthemaintenanceimpactinthehealthofindustrialcomponents AT miguelasanzbobi novelmethodforevaluationofthemaintenanceimpactinthehealthofindustrialcomponents AT antoniomunoz novelmethodforevaluationofthemaintenanceimpactinthehealthofindustrialcomponents AT danielgonzalezcalvo novelmethodforevaluationofthemaintenanceimpactinthehealthofindustrialcomponents AT tomasalvareztejedor novelmethodforevaluationofthemaintenanceimpactinthehealthofindustrialcomponents |