|
Descripción
|
|
|---|---|
| Today, accurate fault detection and prediction in modern industrial assets machinery is a key issue raised by maintenance. In particular, automatically modeling the normal behaviour of the assets from monitoring sensor data is probably one of the most challenging problems, specially in industrial scenarios in which there is limited information of real faults and conservative strategies are commonly adopted. To this aim, a novel methodology based on a workflow that combines a set of Machine Learning based methods is proposed. It can be efficiently used to generate normality and behaviour models that are able to predict potential failures in an online fashion, preventing costly corrective interventions. In order to illustrate its applicability, the proposed methodology has been integrated in a CBM+ (CBM+RCM+AI) platform and a NAVANTIA MTU 12V-396 auxiliary diesel engine has been analyzed. Experimental results show promising advantages over traditional strategies, detecting deviation patterns and degradation symptoms at an early stage. Therefore, critical faults can be anticipated and serious damages can be avoided, improving reliability and availability of the assets. | |
|
Internacional
|
No |
|
Entidad
|
U. ETSII, Industriales Research Meeting |
|
Lugar
|
ETSI Industriales, Madrid, 2016 |
|
Páginas
|
|
|
Referencia/URL
|
http://oa.upm.es/40073/ |
|
Tipo de publicación
|
Póster |