Fault Classification in Diesel Engines Based on Time-Domain Responses through Signal Processing and Convolutional Neural Network

In today’s interconnected industrial landscape, the ability to predict and monitor the operational status of equipment is crucial for maintaining efficiency and safety. Diesel engines, which are integral to numerous industrial applications, require reliable fault detection mechanisms to reduce opera...

Full description

Saved in:
Bibliographic Details
Main Authors: Gabriel Hasmann Freire Moraes, Ronny Francis Ribeiro Junior, Guilherme Ferreira Gomes
Format: Article
Language:English
Published: MDPI AG 2024-09-01
Series:Vibration
Subjects:
Online Access:https://www.mdpi.com/2571-631X/7/4/46
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850239323684732928
author Gabriel Hasmann Freire Moraes
Ronny Francis Ribeiro Junior
Guilherme Ferreira Gomes
author_facet Gabriel Hasmann Freire Moraes
Ronny Francis Ribeiro Junior
Guilherme Ferreira Gomes
author_sort Gabriel Hasmann Freire Moraes
collection DOAJ
description In today’s interconnected industrial landscape, the ability to predict and monitor the operational status of equipment is crucial for maintaining efficiency and safety. Diesel engines, which are integral to numerous industrial applications, require reliable fault detection mechanisms to reduce operational costs, prevent unplanned downtime, and extend equipment lifespan. Traditional anomaly detection methods, such as thermometry, wear indicators, and radiography, often necessitate significant expertise, involve costly equipment shutdowns, and are limited by high usage costs and accessibility. Addressing these challenges, this study introduces a novel approach for fault detection in diesel engines by analyzing torsional vibration data in the time domain. The proposed method leverages short-term Fourier transform (STFT) and continuous wavelet transform (CWT) techniques, integrated with a convolutional neural network (CNN) to identify hidden patterns and diagnose engine conditions accurately. The method achieved a detection accuracy of 96.5% with STFT and 92.2% with CWT. To ensure robustness, the model was tested under various noise conditions, maintaining accuracies above 70% for noise levels up to 40%. This research provides a practical and efficient solution for real-time fault detection in diesel engines, offering a significant improvement over traditional methods in terms of cost, accessibility, and ease of implementation.
format Article
id doaj-art-3dc49f7eedaf4cf68b4c580e0617a199
institution OA Journals
issn 2571-631X
language English
publishDate 2024-09-01
publisher MDPI AG
record_format Article
series Vibration
spelling doaj-art-3dc49f7eedaf4cf68b4c580e0617a1992025-08-20T02:01:10ZengMDPI AGVibration2571-631X2024-09-017486389310.3390/vibration7040046Fault Classification in Diesel Engines Based on Time-Domain Responses through Signal Processing and Convolutional Neural NetworkGabriel Hasmann Freire Moraes0Ronny Francis Ribeiro Junior1Guilherme Ferreira Gomes2Mechanical Engineering Institute, Universidade Federal de Itajuba (UNIFEI), Itajuba 37500-903, BrazilMechanical Engineering Institute, Universidade Federal de Itajuba (UNIFEI), Itajuba 37500-903, BrazilMechanical Engineering Institute, Universidade Federal de Itajuba (UNIFEI), Itajuba 37500-903, BrazilIn today’s interconnected industrial landscape, the ability to predict and monitor the operational status of equipment is crucial for maintaining efficiency and safety. Diesel engines, which are integral to numerous industrial applications, require reliable fault detection mechanisms to reduce operational costs, prevent unplanned downtime, and extend equipment lifespan. Traditional anomaly detection methods, such as thermometry, wear indicators, and radiography, often necessitate significant expertise, involve costly equipment shutdowns, and are limited by high usage costs and accessibility. Addressing these challenges, this study introduces a novel approach for fault detection in diesel engines by analyzing torsional vibration data in the time domain. The proposed method leverages short-term Fourier transform (STFT) and continuous wavelet transform (CWT) techniques, integrated with a convolutional neural network (CNN) to identify hidden patterns and diagnose engine conditions accurately. The method achieved a detection accuracy of 96.5% with STFT and 92.2% with CWT. To ensure robustness, the model was tested under various noise conditions, maintaining accuracies above 70% for noise levels up to 40%. This research provides a practical and efficient solution for real-time fault detection in diesel engines, offering a significant improvement over traditional methods in terms of cost, accessibility, and ease of implementation.https://www.mdpi.com/2571-631X/7/4/46fault detectionSTFTwaveletconvolutional neural networkdiesel engines
spellingShingle Gabriel Hasmann Freire Moraes
Ronny Francis Ribeiro Junior
Guilherme Ferreira Gomes
Fault Classification in Diesel Engines Based on Time-Domain Responses through Signal Processing and Convolutional Neural Network
Vibration
fault detection
STFT
wavelet
convolutional neural network
diesel engines
title Fault Classification in Diesel Engines Based on Time-Domain Responses through Signal Processing and Convolutional Neural Network
title_full Fault Classification in Diesel Engines Based on Time-Domain Responses through Signal Processing and Convolutional Neural Network
title_fullStr Fault Classification in Diesel Engines Based on Time-Domain Responses through Signal Processing and Convolutional Neural Network
title_full_unstemmed Fault Classification in Diesel Engines Based on Time-Domain Responses through Signal Processing and Convolutional Neural Network
title_short Fault Classification in Diesel Engines Based on Time-Domain Responses through Signal Processing and Convolutional Neural Network
title_sort fault classification in diesel engines based on time domain responses through signal processing and convolutional neural network
topic fault detection
STFT
wavelet
convolutional neural network
diesel engines
url https://www.mdpi.com/2571-631X/7/4/46
work_keys_str_mv AT gabrielhasmannfreiremoraes faultclassificationindieselenginesbasedontimedomainresponsesthroughsignalprocessingandconvolutionalneuralnetwork
AT ronnyfrancisribeirojunior faultclassificationindieselenginesbasedontimedomainresponsesthroughsignalprocessingandconvolutionalneuralnetwork
AT guilhermeferreiragomes faultclassificationindieselenginesbasedontimedomainresponsesthroughsignalprocessingandconvolutionalneuralnetwork