Artificial neural network-based fault diagnosis of gearbox using empirical mode decomposition from vibration response

This paper presents a gearbox defect diagnosis based on vibration behaviour. In order to record the vibration response under various circumstances, an industrial gearbox was used as the basis for an experimental setup. The signals resulting from gear wear were processed using an empirical mode decom...

Full description

Bibliographic Details
Main Authors: Mutra, R. R., Reddy, D. M., Amarnath, M., M. N., Abdul Rani, M. A., Yunus, M. S. M., Sani
Format: Article
Language:English
Published: Universiti Malaysia Pahang 2023
Subjects:
Online Access:http://umpir.ump.edu.my/id/eprint/38981/1/Artificial%20Neural%20Network%20Based%20Fault%20Diagnosis%20of%20Gearbox.pdf
_version_ 1825815213072449536
author Mutra, R. R.
Reddy, D. M.
Amarnath, M.
M. N., Abdul Rani
M. A., Yunus
M. S. M., Sani
author_facet Mutra, R. R.
Reddy, D. M.
Amarnath, M.
M. N., Abdul Rani
M. A., Yunus
M. S. M., Sani
author_sort Mutra, R. R.
collection UMP
description This paper presents a gearbox defect diagnosis based on vibration behaviour. In order to record the vibration response under various circumstances, an industrial gearbox was used as the basis for an experimental setup. The signals resulting from gear wear were processed using an empirical mode decomposition for two operating time intervals (zero-hour running time and thirty-hour running time). The first three intrinsic mode functions and the corresponding frequency response were detected. The ten statistical parameters most sensitive to gear wear were selected using an evaluation method based on Euclidean distance. Using the identified features, an artificial neural network (ANN) was trained to track the gearbox for the selected future data set. The neural network received its input from the statistical parameters, and its output was the number of gearbox running hours. To achieve faster convergence, the radial basis function and the backpropagation neural network were compared. The superiority of the proposed strategy is demonstrated by comparing the performance of ANN. For monitoring the condition of industrial gears, the proposed strategy is found to be effective and trustworthy.
first_indexed 2024-03-06T13:10:09Z
format Article
id UMPir38981
institution Universiti Malaysia Pahang
language English
last_indexed 2024-03-06T13:10:09Z
publishDate 2023
publisher Universiti Malaysia Pahang
record_format dspace
spelling UMPir389812023-10-23T08:01:27Z http://umpir.ump.edu.my/id/eprint/38981/ Artificial neural network-based fault diagnosis of gearbox using empirical mode decomposition from vibration response Mutra, R. R. Reddy, D. M. Amarnath, M. M. N., Abdul Rani M. A., Yunus M. S. M., Sani TJ Mechanical engineering and machinery This paper presents a gearbox defect diagnosis based on vibration behaviour. In order to record the vibration response under various circumstances, an industrial gearbox was used as the basis for an experimental setup. The signals resulting from gear wear were processed using an empirical mode decomposition for two operating time intervals (zero-hour running time and thirty-hour running time). The first three intrinsic mode functions and the corresponding frequency response were detected. The ten statistical parameters most sensitive to gear wear were selected using an evaluation method based on Euclidean distance. Using the identified features, an artificial neural network (ANN) was trained to track the gearbox for the selected future data set. The neural network received its input from the statistical parameters, and its output was the number of gearbox running hours. To achieve faster convergence, the radial basis function and the backpropagation neural network were compared. The superiority of the proposed strategy is demonstrated by comparing the performance of ANN. For monitoring the condition of industrial gears, the proposed strategy is found to be effective and trustworthy. Universiti Malaysia Pahang 2023-10 Article PeerReviewed pdf en cc_by_nc_4 http://umpir.ump.edu.my/id/eprint/38981/1/Artificial%20Neural%20Network%20Based%20Fault%20Diagnosis%20of%20Gearbox.pdf Mutra, R. R. and Reddy, D. M. and Amarnath, M. and M. N., Abdul Rani and M. A., Yunus and M. S. M., Sani (2023) Artificial neural network-based fault diagnosis of gearbox using empirical mode decomposition from vibration response. International Journal of Automotive and Mechanical Engineering (IJAME), 20 (3). pp. 10695-10709. ISSN 2229-8649 (Print); 2180-1606 (Online). (Published) https://doi.org/10.15282/ijame.20.3.2023.12.0826 https://doi.org/10.15282/ijame.20.3.2023.12.0826
spellingShingle TJ Mechanical engineering and machinery
Mutra, R. R.
Reddy, D. M.
Amarnath, M.
M. N., Abdul Rani
M. A., Yunus
M. S. M., Sani
Artificial neural network-based fault diagnosis of gearbox using empirical mode decomposition from vibration response
title Artificial neural network-based fault diagnosis of gearbox using empirical mode decomposition from vibration response
title_full Artificial neural network-based fault diagnosis of gearbox using empirical mode decomposition from vibration response
title_fullStr Artificial neural network-based fault diagnosis of gearbox using empirical mode decomposition from vibration response
title_full_unstemmed Artificial neural network-based fault diagnosis of gearbox using empirical mode decomposition from vibration response
title_short Artificial neural network-based fault diagnosis of gearbox using empirical mode decomposition from vibration response
title_sort artificial neural network based fault diagnosis of gearbox using empirical mode decomposition from vibration response
topic TJ Mechanical engineering and machinery
url http://umpir.ump.edu.my/id/eprint/38981/1/Artificial%20Neural%20Network%20Based%20Fault%20Diagnosis%20of%20Gearbox.pdf
work_keys_str_mv AT mutrarr artificialneuralnetworkbasedfaultdiagnosisofgearboxusingempiricalmodedecompositionfromvibrationresponse
AT reddydm artificialneuralnetworkbasedfaultdiagnosisofgearboxusingempiricalmodedecompositionfromvibrationresponse
AT amarnathm artificialneuralnetworkbasedfaultdiagnosisofgearboxusingempiricalmodedecompositionfromvibrationresponse
AT mnabdulrani artificialneuralnetworkbasedfaultdiagnosisofgearboxusingempiricalmodedecompositionfromvibrationresponse
AT mayunus artificialneuralnetworkbasedfaultdiagnosisofgearboxusingempiricalmodedecompositionfromvibrationresponse
AT msmsani artificialneuralnetworkbasedfaultdiagnosisofgearboxusingempiricalmodedecompositionfromvibrationresponse