Technical Diagnostics of Industrial Robots Using Vibration Signals: Case Study on Detecting Base Unfastening

In the domain of modern manufacturing digitalization, artificial intelligence tools are increasingly employed for condition monitoring and technical diagnostics. However, the majority of existing methodologies primarily concentrate on the technical diagnosis of rotating machines, with a noticeable l...

Full description

Saved in:
Bibliographic Details
Main Authors: Daria Fedorova, Vladimír Tlach, Ivan Kuric, Tomáš Dodok, Ivan Zajačko, Karol Tucki
Format: Article
Language:English
Published: MDPI AG 2024-12-01
Series:Applied Sciences
Subjects:
Online Access:https://www.mdpi.com/2076-3417/15/1/270
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1841549420705873920
author Daria Fedorova
Vladimír Tlach
Ivan Kuric
Tomáš Dodok
Ivan Zajačko
Karol Tucki
author_facet Daria Fedorova
Vladimír Tlach
Ivan Kuric
Tomáš Dodok
Ivan Zajačko
Karol Tucki
author_sort Daria Fedorova
collection DOAJ
description In the domain of modern manufacturing digitalization, artificial intelligence tools are increasingly employed for condition monitoring and technical diagnostics. However, the majority of existing methodologies primarily concentrate on the technical diagnosis of rotating machines, with a noticeable lack of research addressing these issues in sequential machines. In this paper, we deal with the selection of suitable vibration signal characteristics for the detection of an industrial robot’s release from its base during a handling operation. Statistical methods, including one-way ANOVA and <i>t</i>-tests, were used to identify the most significant features, which allowed us to isolate vibration metrics with significant predictive potential. These selected features were then used as inputs to various machine learning models to evaluate the hypothesis that these parameters can reliably indicate fastening releasing events. The results show that the optimized parameters significantly improve the detection accuracy, thus providing a reliable basis for future applications in predictive maintenance and monitoring. The findings represent an advance in robotic condition monitoring, providing a structured approach to feature selection that improves the reliability of disconnection detection in automated systems with potential applicability in various industrial environments.
format Article
id doaj-art-e7955cf7be9943c39c1cdb647f29ba64
institution Kabale University
issn 2076-3417
language English
publishDate 2024-12-01
publisher MDPI AG
record_format Article
series Applied Sciences
spelling doaj-art-e7955cf7be9943c39c1cdb647f29ba642025-01-10T13:14:59ZengMDPI AGApplied Sciences2076-34172024-12-0115127010.3390/app15010270Technical Diagnostics of Industrial Robots Using Vibration Signals: Case Study on Detecting Base UnfasteningDaria Fedorova0Vladimír Tlach1Ivan Kuric2Tomáš Dodok3Ivan Zajačko4Karol Tucki5Department of Automation and Production Systems, Faculty of Mechanical Engineering, University of Zilina, Univerzitna 8215/1, 010 26 Zilina, SlovakiaDepartment of Automation and Production Systems, Faculty of Mechanical Engineering, University of Zilina, Univerzitna 8215/1, 010 26 Zilina, SlovakiaDepartment of Automation and Production Systems, Faculty of Mechanical Engineering, University of Zilina, Univerzitna 8215/1, 010 26 Zilina, SlovakiaDepartment of Automation and Production Systems, Faculty of Mechanical Engineering, University of Zilina, Univerzitna 8215/1, 010 26 Zilina, SlovakiaDepartment of Automation and Production Systems, Faculty of Mechanical Engineering, University of Zilina, Univerzitna 8215/1, 010 26 Zilina, SlovakiaInstitute of Mechanical Engineering, Department of Production Engineering, Warsaw University of Life Sciences, Nowoursynowska 164, 02-787 Warszawa, PolandIn the domain of modern manufacturing digitalization, artificial intelligence tools are increasingly employed for condition monitoring and technical diagnostics. However, the majority of existing methodologies primarily concentrate on the technical diagnosis of rotating machines, with a noticeable lack of research addressing these issues in sequential machines. In this paper, we deal with the selection of suitable vibration signal characteristics for the detection of an industrial robot’s release from its base during a handling operation. Statistical methods, including one-way ANOVA and <i>t</i>-tests, were used to identify the most significant features, which allowed us to isolate vibration metrics with significant predictive potential. These selected features were then used as inputs to various machine learning models to evaluate the hypothesis that these parameters can reliably indicate fastening releasing events. The results show that the optimized parameters significantly improve the detection accuracy, thus providing a reliable basis for future applications in predictive maintenance and monitoring. The findings represent an advance in robotic condition monitoring, providing a structured approach to feature selection that improves the reliability of disconnection detection in automated systems with potential applicability in various industrial environments.https://www.mdpi.com/2076-3417/15/1/270vibrodiagnosticsdetectionfeature extractionfeature selectionensemble modelneural network
spellingShingle Daria Fedorova
Vladimír Tlach
Ivan Kuric
Tomáš Dodok
Ivan Zajačko
Karol Tucki
Technical Diagnostics of Industrial Robots Using Vibration Signals: Case Study on Detecting Base Unfastening
Applied Sciences
vibrodiagnostics
detection
feature extraction
feature selection
ensemble model
neural network
title Technical Diagnostics of Industrial Robots Using Vibration Signals: Case Study on Detecting Base Unfastening
title_full Technical Diagnostics of Industrial Robots Using Vibration Signals: Case Study on Detecting Base Unfastening
title_fullStr Technical Diagnostics of Industrial Robots Using Vibration Signals: Case Study on Detecting Base Unfastening
title_full_unstemmed Technical Diagnostics of Industrial Robots Using Vibration Signals: Case Study on Detecting Base Unfastening
title_short Technical Diagnostics of Industrial Robots Using Vibration Signals: Case Study on Detecting Base Unfastening
title_sort technical diagnostics of industrial robots using vibration signals case study on detecting base unfastening
topic vibrodiagnostics
detection
feature extraction
feature selection
ensemble model
neural network
url https://www.mdpi.com/2076-3417/15/1/270
work_keys_str_mv AT dariafedorova technicaldiagnosticsofindustrialrobotsusingvibrationsignalscasestudyondetectingbaseunfastening
AT vladimirtlach technicaldiagnosticsofindustrialrobotsusingvibrationsignalscasestudyondetectingbaseunfastening
AT ivankuric technicaldiagnosticsofindustrialrobotsusingvibrationsignalscasestudyondetectingbaseunfastening
AT tomasdodok technicaldiagnosticsofindustrialrobotsusingvibrationsignalscasestudyondetectingbaseunfastening
AT ivanzajacko technicaldiagnosticsofindustrialrobotsusingvibrationsignalscasestudyondetectingbaseunfastening
AT karoltucki technicaldiagnosticsofindustrialrobotsusingvibrationsignalscasestudyondetectingbaseunfastening