The paper presents and analyzes critically a theoretical and experimental methodology, able to define and characterize features for condition monitoring of mechatronic systems. A kinematic and dynamic model of the whole mechatronic system is realized, allowing us to identify the phases of the operating cycle, which are the most meaningful from the condition monitoring point of view. Furthermore, it allows us to evaluate a set of quantities of interest throughout the whole chain, when both the measured quantity and the monitoring point are changed along the kinematic chain, from the motor to the end effector. The analysis is carried on in order to evaluate the most reliable configuration as for measuring point and quantity for condition monitoring. Selectivity and repeatability of features are evaluated experimentally, when operating conditions of the systems are changed, in order to realize the best features database for a possible processing by Artificial Neural Network.

Sensor fusion for more accurate features in condition monitoring of mechatronic systems

Gaspari A.;
2019

Abstract

The paper presents and analyzes critically a theoretical and experimental methodology, able to define and characterize features for condition monitoring of mechatronic systems. A kinematic and dynamic model of the whole mechatronic system is realized, allowing us to identify the phases of the operating cycle, which are the most meaningful from the condition monitoring point of view. Furthermore, it allows us to evaluate a set of quantities of interest throughout the whole chain, when both the measured quantity and the monitoring point are changed along the kinematic chain, from the motor to the end effector. The analysis is carried on in order to evaluate the most reliable configuration as for measuring point and quantity for condition monitoring. Selectivity and repeatability of features are evaluated experimentally, when operating conditions of the systems are changed, in order to realize the best features database for a possible processing by Artificial Neural Network.
2019 IEEE International Instrumentation and Measurement Technology Conference, I2MTC 2019
978-1-5386-3460-8
File in questo prodotto:
Non ci sono file associati a questo prodotto.

I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.

Utilizza questo identificativo per citare o creare un link a questo documento: http://hdl.handle.net/11589/239170
Citazioni
  • Scopus 10
  • ???jsp.display-item.citation.isi??? 4
social impact