Centrifugal pump fault diagnosis method based on complete ensemble empirical mode decomposition and random forest
An overall empirical mode and random forest technology, applied in pump control, mechanical equipment, non-variable pumps, etc., can solve the problem of few applications in the field of fault diagnosis, avoid modal aliasing and endpoint effects, and improve classification The effect of accuracy rate and small amount of calculation
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
Embodiment Construction
[0021] The present invention will be further described below in conjunction with the accompanying drawings and specific embodiments.
[0022] Such as figure 1 Shown, a kind of centrifugal pump fault diagnosis method flow process based on the random forest of CEEMD-SampEn of the present invention is introduced as follows:
[0023] The method is mainly divided into three parts: (1) use CEEMD to decompose the centrifugal pump vibration signal obtained by the sensor into a series of IMF classifications; (2) use the sample entropy of the IMF classification as the feature vector of the signal; (3) use CEEMD- The feature vector obtained from the sample entropy is used as the input of the random forest classifier for fault diagnosis. The method flow is as follows:
[0024] 1. Feature extraction process based on CEEMD-SampEn
[0025] 1.1 CEEMD method
[0026] CEEMD is an improved method based on the EMD algorithm. EMD is to use the local characteristics of the signal to adaptively...
PUM
Abstract
Description
Claims
Application Information
- R&D Engineer
- R&D Manager
- IP Professional
- Industry Leading Data Capabilities
- Powerful AI technology
- Patent DNA Extraction
Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic, Popular Technical Reports.
© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com