Improvement indicators for Total Productive Maintenance policy
Autor: | Avila Manuel, Kratz Frederic, Aggab Toufik, Vrignat Pascal, Duculty Florent |
---|---|
Přispěvatelé: | Laboratoire Pluridisciplinaire de Recherche en Ingénierie des Systèmes, Mécanique et Energétique (PRISME), Ecole Nationale Supérieure d'Ingénieurs de Bourges (ENSI Bourges)-Université d'Orléans (UO), Université d'Orléans (UO)-Ecole Nationale Supérieure d'Ingénieurs de Bourges (ENSI Bourges) |
Jazyk: | angličtina |
Rok vydání: | 2019 |
Předmět: |
0209 industrial biotechnology
Mean time between failures Planned maintenance Process (engineering) Computer science Applied Mathematics 020208 electrical & electronic engineering 02 engineering and technology Total productive maintenance Computer Science Applications 020901 industrial engineering & automation Work (electrical) Risk analysis (engineering) Control and Systems Engineering [INFO.INFO-AU]Computer Science [cs]/Automatic Control Engineering 0202 electrical engineering electronic engineering information engineering Information system Relevance (information retrieval) Electrical and Electronic Engineering Reliability (statistics) ComputingMilieux_MISCELLANEOUS |
Zdroj: | Control Engineering Practice Control Engineering Practice, Elsevier, 2019, 82, pp.86-96. ⟨10.1016/j.conengprac.2018.09.019⟩ |
ISSN: | 0967-0661 |
DOI: | 10.1016/j.conengprac.2018.09.019⟩ |
Popis: | Many papers have been written on financial indicators to assess the use of a maintenance policy based on Total Productive Maintenance, while others have compared results showing the impact of criteria such as the Mean Time Between Failures. This paper provides the maintenance managers indicators which can assess the relevance of the actions carried out as well as readjustment of the planned maintenance program. In long term, this indicators knowledge may lead them to review their maintenance policy. To reach this aim, we propose several indicators for reliability, diagnosis and prognosis to assess and improve the maintenance policy based on Total Productive Maintenance. Methods used to obtain these indicators are only based on operating maintenance activities. These latter were extracted from a database produced by a Computerized Maintenance Management Information System. This work focuses on a maintained process based on total productive maintenance in which available sensor data are not indicative of degradation level achieved by the system. Indicators presented were obtained using Survival Laws, Hidden Markov Model and Support Vector Machine. As a concrete case study, an alloy foundry process is used. |
Databáze: | OpenAIRE |
Externí odkaz: |