Equipment detection method and device based on joint learning
The invention relates to the technical field of joint learning, and provides an equipment detection method and device based on joint learning. The method comprises the following steps: collecting and selecting parameter data of equipment, and determining an original vibration signal in the parameter...
Gespeichert in:
1. Verfasser: | |
---|---|
Format: | Patent |
Sprache: | chi ; eng |
Schlagworte: | |
Online-Zugang: | Volltext bestellen |
Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
Zusammenfassung: | The invention relates to the technical field of joint learning, and provides an equipment detection method and device based on joint learning. The method comprises the following steps: collecting and selecting parameter data of equipment, and determining an original vibration signal in the parameter data; carrying out modal analysis on the original vibration signal to obtain modal data corresponding to a plurality of frequencies; performing Hilbert transformation on the modal data to obtain a Hilbert boundary spectrum; performing feature extraction according to the Hilbert boundary spectrum and the plurality of frequencies to obtain frequency features corresponding to the plurality of frequencies; generating a residual service life model through frequency characteristic training; and issuing the residual service life model to each participant to enable the participant to train the residual service life model in a combined learning form. The vibration signals are subjected to modal analysis and Hilbert transfo |
---|