The paper discusses some considerations about the effect of characteristics of tri-axial accelerometers and of data processing on the results of Neural Networks (NN) algorithms, which are used for both classification and prediction in Condition Monitoring (CM) applications. Type of accelerometer, type of feature for monitoring, position and orientation of the accelerometers themselves are studied, in order to evaluate their effect on the robustness of results. Preliminary results are obtained and some little, even though interesting, difference is found.
Effect of Vibration Measurement Uncertainty on Condition Monitoring of Complex Industrial Components: Transducer and Data Processing Issues
Antonella Gaspari;
2017-01-01
Abstract
The paper discusses some considerations about the effect of characteristics of tri-axial accelerometers and of data processing on the results of Neural Networks (NN) algorithms, which are used for both classification and prediction in Condition Monitoring (CM) applications. Type of accelerometer, type of feature for monitoring, position and orientation of the accelerometers themselves are studied, in order to evaluate their effect on the robustness of results. Preliminary results are obtained and some little, even though interesting, difference is found.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.
