Publication detail

Comparison of Faults Classification in Vibrodiagnostics from Time and Frequency Domain Data

ZUTH, D. MARADA, T.

Original Title

Comparison of Faults Classification in Vibrodiagnostics from Time and Frequency Domain Data

Type

conference paper

Language

English

Original Abstract

The paper deals with the comparison of the success rate of classification models from Matlab Classification Learner app. Classification models will compare data from the frequency and time domain, the data source is the same. Both data samples are from real measurements on the vibrodiagnostics model. Five basic faults are recognized, namely, the static unbalances at two levels, the dynamic unbalances at two levels and the faultless state. The data is then processed and reduced for the use of the Matlab Classification Learner app, which creates a model for recognizing faults. The aim of the paper is to compare the success rate of classification models when the data source is dataset in time or frequency domain.

Keywords

Vibrodiagnostics, Neuron Network, Classification Learner app, Machine Learning, Matlab, Classification Model, Static Unbalance, Dynamic Unbalance

Authors

ZUTH, D.; MARADA, T.

Released

5. 12. 2018

ISBN

978-80-214-5543-6

Book

Mechatronika 2018

Pages from

482

Pages to

487

Pages count

6

BibTex

@inproceedings{BUT151762,
  author="Daniel {Zuth} and Tomáš {Marada}",
  title="Comparison of Faults Classification in Vibrodiagnostics from Time and Frequency Domain Data",
  booktitle="Mechatronika 2018",
  year="2018",
  pages="482--487",
  isbn="978-80-214-5543-6"
}