Wear debris which contain multiple degrading information are of great interest to the running machines' health management. Among the several kinds of debris detection methods, inductive sensors have shown great potential for the online monitoring applications, along with which the superimposed voltage caused by the debris with short distances becomes a major factor influencing the accuracy of the detection. An improved convolutional neural network (CNN) combined with degenerate unmixing estimation technique (DUET) is proposed in the paper which offers an online solution for the inductive aliasing signal separation. The experimental result shows that the proposed method is effective and provides an alternative online approach of the original two-dimensional weighted histogram method.
Aliasing signal separation for superimposition of inductive debris detection using CNN-Based DUET
Zio E.;Shi J.;
2019-01-01
Abstract
Wear debris which contain multiple degrading information are of great interest to the running machines' health management. Among the several kinds of debris detection methods, inductive sensors have shown great potential for the online monitoring applications, along with which the superimposed voltage caused by the debris with short distances becomes a major factor influencing the accuracy of the detection. An improved convolutional neural network (CNN) combined with degenerate unmixing estimation technique (DUET) is proposed in the paper which offers an online solution for the inductive aliasing signal separation. The experimental result shows that the proposed method is effective and provides an alternative online approach of the original two-dimensional weighted histogram method.File | Dimensione | Formato | |
---|---|---|---|
31) Li, T., Wang, S., Zio, E., Shi, J., Yang, Z.Aliasing signal separation for superimposition of inductive debris detection using CNN-Based DUET.pdf
Accesso riservato
:
Pre-Print (o Pre-Refereeing)
Dimensione
747.42 kB
Formato
Adobe PDF
|
747.42 kB | Adobe PDF | Visualizza/Apri |
I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.