Zobraziť v EDS

Enhancing Predictive Maintenance of Industrial Assets Through Machine Diagnostic Parameter Grouping.

Uložené v:
Podrobná bibliografia
Názov: Enhancing Predictive Maintenance of Industrial Assets Through Machine Diagnostic Parameter Grouping.
Autori: LUŚCIŃSKI, Sławomir1 luscinski@tu.kielce.pl, BEDNAREK, Mariusz2,3, JABŁOŃSKI, Marek4
Zdroj: Management & Production Engineering Review (MPER). Sep2025, Vol. 16 Issue 3, p1-12. 12p.
Predmety: *INDUSTRIAL equipment, *DATA analysis, *INDUSTRIAL productivity, MACHINE learning, CONDITION-based maintenance, FAULT diagnosis
Abstrakt: This article examines the advancement of predictive maintenance (PdM) for industrial assets through an innovative methodology that categorises diagnostic parameters into coherent groups. Predictive maintenance constitutes a vital component in mitigating unforeseen downtime and improving operational efficiency within manufacturing settings. The authors recommend a centralised framework for PdM, effectively addressing the complexities arising from data saturation by numerous sensor nodes. The proposed methodology refines the predictive maintenance process by systematically organising diagnostic parameters based on their significance and interconnections, thereby enhancing its effectiveness and efficiency. The study utilises the KNIME software platform for comprehensive data analysis and validation of the proposed approach, demonstrating its practicality with datasets obtained from SCADA/MES systems. The results confirm the robustness and accessibility of the methodology, highlighting its potential applicability across various industrial sectors. Future research directions include the integration of advanced machine learning techniques and the exploration of the methodology's relevance in diverse industries. [ABSTRACT FROM AUTHOR]
Copyright of Management & Production Engineering Review (MPER) is the property of Polish Academy of Sciences and its content may not be copied or emailed to multiple sites without the copyright holder's express written permission. Additionally, content may not be used with any artificial intelligence tools or machine learning technologies. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)
Databáza: Business Source Index
Popis
Abstrakt:This article examines the advancement of predictive maintenance (PdM) for industrial assets through an innovative methodology that categorises diagnostic parameters into coherent groups. Predictive maintenance constitutes a vital component in mitigating unforeseen downtime and improving operational efficiency within manufacturing settings. The authors recommend a centralised framework for PdM, effectively addressing the complexities arising from data saturation by numerous sensor nodes. The proposed methodology refines the predictive maintenance process by systematically organising diagnostic parameters based on their significance and interconnections, thereby enhancing its effectiveness and efficiency. The study utilises the KNIME software platform for comprehensive data analysis and validation of the proposed approach, demonstrating its practicality with datasets obtained from SCADA/MES systems. The results confirm the robustness and accessibility of the methodology, highlighting its potential applicability across various industrial sectors. Future research directions include the integration of advanced machine learning techniques and the exploration of the methodology's relevance in diverse industries. [ABSTRACT FROM AUTHOR]
ISSN:20808208
DOI:10.24425/mper.2025.156149