Rotating Machinery Fault Detection Using Support Vector Machine via Feature Ranking

Artificial intelligence has succeeded in many different areas in recent years. Especially the use of machine learning algorithms has been very popular in all areas, including fault detection. This paper explores a case study of applying machine learning techniques and neural networks to detect ten d...

Full description

Saved in:
Bibliographic Details
Main Authors: Harry Hoa Huynh, Cheol-Hong Min
Format: Article
Language:English
Published: MDPI AG 2024-10-01
Series:Algorithms
Subjects:
Online Access:https://www.mdpi.com/1999-4893/17/10/441
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850205084227469312
author Harry Hoa Huynh
Cheol-Hong Min
author_facet Harry Hoa Huynh
Cheol-Hong Min
author_sort Harry Hoa Huynh
collection DOAJ
description Artificial intelligence has succeeded in many different areas in recent years. Especially the use of machine learning algorithms has been very popular in all areas, including fault detection. This paper explores a case study of applying machine learning techniques and neural networks to detect ten different machinery fault conditions using publicly available data sets collected from a tachometer, two accelerometers, and a microphone. Ten different conditions were classified using machine learning algorithms. Fifty-eight different features are extracted from time and frequency by applying the Short-Time Fourier Transform to the data with the window size of 1000 samples with 50% overlap. The Support Vector Machine models provided fault classification with 99.8% accuracy using all fifty-eight features. The proposed study explores the dimensionality reduction of the extracted features. Fifty-eight features were ranked using the Decision Tree model to identify the essential features as the classifier predictors. Based on feature extraction and raking, eleven predictors were extracted leading to reduced training complexity, while achieving a high classification accuracy of 99.7% could be obtained in less than half of the training time.
format Article
id doaj-art-b06da2ec513444cca6bcd6cf59683ed8
institution OA Journals
issn 1999-4893
language English
publishDate 2024-10-01
publisher MDPI AG
record_format Article
series Algorithms
spelling doaj-art-b06da2ec513444cca6bcd6cf59683ed82025-08-20T02:11:11ZengMDPI AGAlgorithms1999-48932024-10-01171044110.3390/a17100441Rotating Machinery Fault Detection Using Support Vector Machine via Feature RankingHarry Hoa Huynh0Cheol-Hong Min1Electrical and Computer Engineering, University of St. Thomas, St. Paul, MN 55105, USAElectrical and Computer Engineering, University of St. Thomas, St. Paul, MN 55105, USAArtificial intelligence has succeeded in many different areas in recent years. Especially the use of machine learning algorithms has been very popular in all areas, including fault detection. This paper explores a case study of applying machine learning techniques and neural networks to detect ten different machinery fault conditions using publicly available data sets collected from a tachometer, two accelerometers, and a microphone. Ten different conditions were classified using machine learning algorithms. Fifty-eight different features are extracted from time and frequency by applying the Short-Time Fourier Transform to the data with the window size of 1000 samples with 50% overlap. The Support Vector Machine models provided fault classification with 99.8% accuracy using all fifty-eight features. The proposed study explores the dimensionality reduction of the extracted features. Fifty-eight features were ranked using the Decision Tree model to identify the essential features as the classifier predictors. Based on feature extraction and raking, eleven predictors were extracted leading to reduced training complexity, while achieving a high classification accuracy of 99.7% could be obtained in less than half of the training time.https://www.mdpi.com/1999-4893/17/10/441artificial intelligencemachine learningfault detectionsupport vector machine (SVM)feature extractiondecision tree
spellingShingle Harry Hoa Huynh
Cheol-Hong Min
Rotating Machinery Fault Detection Using Support Vector Machine via Feature Ranking
Algorithms
artificial intelligence
machine learning
fault detection
support vector machine (SVM)
feature extraction
decision tree
title Rotating Machinery Fault Detection Using Support Vector Machine via Feature Ranking
title_full Rotating Machinery Fault Detection Using Support Vector Machine via Feature Ranking
title_fullStr Rotating Machinery Fault Detection Using Support Vector Machine via Feature Ranking
title_full_unstemmed Rotating Machinery Fault Detection Using Support Vector Machine via Feature Ranking
title_short Rotating Machinery Fault Detection Using Support Vector Machine via Feature Ranking
title_sort rotating machinery fault detection using support vector machine via feature ranking
topic artificial intelligence
machine learning
fault detection
support vector machine (SVM)
feature extraction
decision tree
url https://www.mdpi.com/1999-4893/17/10/441
work_keys_str_mv AT harryhoahuynh rotatingmachineryfaultdetectionusingsupportvectormachineviafeatureranking
AT cheolhongmin rotatingmachineryfaultdetectionusingsupportvectormachineviafeatureranking