ARTIFICIAL NEURAL NETWORK MODELS IN ACOUSTIC DIAGNOSTICS OF STRAIGHT STRAIGHT-TOOTHED GEARS AS PART OF MULTI MULTI-SHAFT DRIVES
DOI:
https://doi.org/10.36773/1818-1112-2022-128-2-100-104Keywords:
gear wheel, defect, diagnostics, artificial neural network, architectureAbstract
The article considers a neural network approach for monitoring the monitoring of the technical condition of gears as part of a multi-shaft drive, based on the synthesis of spectral analysis of an acoustic signal and algorithms for processing information by artificial neural network models. Various variants of classical architectures of neural networks used to solve classification problems are presented. Sufficiently high efficiency and accuracy of detecting a local defect in a gear wheel of a multi-shaft drive during CIP diagnostics is shown.
Downloads
Published
How to Cite
Issue
Section
License
Copyright (c) 2022 Brest State Technical University
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.
The work is provided under the terms of Creative Commons public license Attribution-NonCommercial 4.0 International (CC BY-NC 4.0). This license allows an unlimited number of persons to reproduce and share the Licensed Material in all media and formats. Any use of the Licensed Material shall contain an identification of its Creator(s) and must be for non-commercial purposes only. Users may not prevent other individuals from taking any actions allowed by the license.
