IMPROVING THE LEVEL OF PREDICTIVE MAINTENANCE MATURITY MATRIX IN INDUSTRIAL ENTERPRISE

Predictive maintenance is a maintenance strategy that applies advanced statistical methods and artificial intelligence to determine the appropriate maintenance time. The article focuses on future recommendations for industry and logistics to achieve a higher level of predictive maintenance maturity,...

Full description

Saved in:
Bibliographic Details
Published in:Acta logistica 2022-06, Vol.9 (2), p.183-193
Main Authors: Mesarosova, Jana, Martinovicova, Klaudia, Fidlerova, Helena, Hrablik Chovanova, Henrieta, Babcanova, Dagmar, Samakova, Jana
Format: Article
Language:English
Subjects:
Artificial intelligence
Case studies
Failure
Innovations
Logistics
Maintenance costs
Performance prediction
Predictive maintenance
Preventive maintenance
Production lines
Sensors
Statistical methods
Citations: Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Predictive maintenance is a maintenance strategy that applies advanced statistical methods and artificial intelligence to determine the appropriate maintenance time. The article focuses on future recommendations for industry and logistics to achieve a higher level of predictive maintenance maturity, which requires real-time monitoring of the state of the company's machinery and equipment. The article's main objective is to propose recommendations to increase effectiveness by improving the predictive maintenance maturity matrix from the current level to a higher level in the industrial enterprise. The current state of maturity has been indicated using the modified model of predictive maintenance and following recommendations from the document Manual for companies for the introduction of artificial intelligence. Simultaneously within the analysis, a predictive maintenance simulation was performed on a selected production line, including essential machines and equipment. The study also identified the individual assumptions (processes, data, infrastructure, personnel, applications, organization) necessary to implement predictive maintenance successfully. The presented case study results contribute to understanding how individual assumptions can be obtained for predictive maintenance improvement and how innovative solutions in the context of Industry 4.0 and Logistics 4.0 can be achieved in enterprises.
ISSN:1339-5629
1339-5629
DOI:10.22306/al.v9i2.292