Mathematical Validation of Experimentally Optimised Parameters Used in a Vibration-Based Machine-Learning Model for Fault Diagnosis in Rotating Machines
Mathematical models have been widely used in the study of rotating machines. Their application in dynamics has eased further research since they can avoid time-consuming and exorbitant experimental processes to simulate different faults. The earlier vibration-based machine-learning (VML) model for f...
Main Authors: | , |
---|---|
Format: | Article |
Language: | English |
Published: |
MDPI AG
2021-08-01
|
Series: | Machines |
Subjects: | |
Online Access: | https://www.mdpi.com/2075-1702/9/8/155 |
_version_ | 1797523233319157760 |
---|---|
author | Natalia Espinoza-Sepulveda Jyoti Sinha |
author_facet | Natalia Espinoza-Sepulveda Jyoti Sinha |
author_sort | Natalia Espinoza-Sepulveda |
collection | DOAJ |
description | Mathematical models have been widely used in the study of rotating machines. Their application in dynamics has eased further research since they can avoid time-consuming and exorbitant experimental processes to simulate different faults. The earlier vibration-based machine-learning (VML) model for fault diagnosis in rotating machines was developed by optimising the vibration-based parameters from experimental data on a rig. Therefore, a mathematical model based on the finite-element (FE) method is created for the experimental rig, to simulate several rotor-related faults. The generated vibration responses in the FE model are then used to validate the earlier developed fault diagnosis model and the optimised parameters. The obtained results suggest the correctness of the selected parameters to characterise the dynamics of the machine to identify faults. These promising results provide the possibility of implementing the VML model in real industrial systems. |
first_indexed | 2024-03-10T08:39:32Z |
format | Article |
id | doaj.art-e530732dfb044e3889285b1757fa3264 |
institution | Directory Open Access Journal |
issn | 2075-1702 |
language | English |
last_indexed | 2024-03-10T08:39:32Z |
publishDate | 2021-08-01 |
publisher | MDPI AG |
record_format | Article |
series | Machines |
spelling | doaj.art-e530732dfb044e3889285b1757fa32642023-11-22T08:24:29ZengMDPI AGMachines2075-17022021-08-019815510.3390/machines9080155Mathematical Validation of Experimentally Optimised Parameters Used in a Vibration-Based Machine-Learning Model for Fault Diagnosis in Rotating MachinesNatalia Espinoza-Sepulveda0Jyoti Sinha1Dynamics Laboratory, Department of MACE, The University of Manchester, Manchester M13 9PL, UKDynamics Laboratory, Department of MACE, The University of Manchester, Manchester M13 9PL, UKMathematical models have been widely used in the study of rotating machines. Their application in dynamics has eased further research since they can avoid time-consuming and exorbitant experimental processes to simulate different faults. The earlier vibration-based machine-learning (VML) model for fault diagnosis in rotating machines was developed by optimising the vibration-based parameters from experimental data on a rig. Therefore, a mathematical model based on the finite-element (FE) method is created for the experimental rig, to simulate several rotor-related faults. The generated vibration responses in the FE model are then used to validate the earlier developed fault diagnosis model and the optimised parameters. The obtained results suggest the correctness of the selected parameters to characterise the dynamics of the machine to identify faults. These promising results provide the possibility of implementing the VML model in real industrial systems.https://www.mdpi.com/2075-1702/9/8/155rotating machinerotor faultsfault diagnosisfinite-element modelmathematical simulationmachine learning |
spellingShingle | Natalia Espinoza-Sepulveda Jyoti Sinha Mathematical Validation of Experimentally Optimised Parameters Used in a Vibration-Based Machine-Learning Model for Fault Diagnosis in Rotating Machines Machines rotating machine rotor faults fault diagnosis finite-element model mathematical simulation machine learning |
title | Mathematical Validation of Experimentally Optimised Parameters Used in a Vibration-Based Machine-Learning Model for Fault Diagnosis in Rotating Machines |
title_full | Mathematical Validation of Experimentally Optimised Parameters Used in a Vibration-Based Machine-Learning Model for Fault Diagnosis in Rotating Machines |
title_fullStr | Mathematical Validation of Experimentally Optimised Parameters Used in a Vibration-Based Machine-Learning Model for Fault Diagnosis in Rotating Machines |
title_full_unstemmed | Mathematical Validation of Experimentally Optimised Parameters Used in a Vibration-Based Machine-Learning Model for Fault Diagnosis in Rotating Machines |
title_short | Mathematical Validation of Experimentally Optimised Parameters Used in a Vibration-Based Machine-Learning Model for Fault Diagnosis in Rotating Machines |
title_sort | mathematical validation of experimentally optimised parameters used in a vibration based machine learning model for fault diagnosis in rotating machines |
topic | rotating machine rotor faults fault diagnosis finite-element model mathematical simulation machine learning |
url | https://www.mdpi.com/2075-1702/9/8/155 |
work_keys_str_mv | AT nataliaespinozasepulveda mathematicalvalidationofexperimentallyoptimisedparametersusedinavibrationbasedmachinelearningmodelforfaultdiagnosisinrotatingmachines AT jyotisinha mathematicalvalidationofexperimentallyoptimisedparametersusedinavibrationbasedmachinelearningmodelforfaultdiagnosisinrotatingmachines |