Unsupervised detection of anomalous sounds for machine condition monitoring
In an era of explosive machine applications , abnormal sound detection is gaining increasing attention from machine learning engineers. This report presents a novel solution to monitoring abnormal machine sounds by ensemble of models. Dense autoencoder and convolutional autoencoder were ensemb...
Saved in:
Main Author: | |
---|---|
Other Authors: | |
Format: | Final Year Project |
Language: | English |
Published: |
Nanyang Technological University
2022
|
Subjects: | |
Online Access: | https://hdl.handle.net/10356/158025 |
Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
Institution: | Nanyang Technological University |
Language: | English |
id |
sg-ntu-dr.10356-158025 |
---|---|
record_format |
dspace |
spelling |
sg-ntu-dr.10356-1580252023-07-07T19:29:25Z Unsupervised detection of anomalous sounds for machine condition monitoring Xie, Yonggang Gan Woon Seng School of Electrical and Electronic Engineering EWSGAN@ntu.edu.sg Engineering::Electrical and electronic engineering::Computer hardware, software and systems In an era of explosive machine applications , abnormal sound detection is gaining increasing attention from machine learning engineers. This report presents a novel solution to monitoring abnormal machine sounds by ensemble of models. Dense autoencoder and convolutional autoencoder were ensembled with self-supervised classifiers which output the confidence for machine-type predictions. In the datastet, six types of machines, containing around 20,000 pieces of normally operating recordings were used in the project. Time-series recordings were processed as mel spectrograms to be fed in the models. Competitive results were achieved by the ensembled system of dense autoencoder and self-supervised model using ResNet50V2 as the backbone. On average, the self-supervised model achieved a classification accuracy of 99 percent, and the ensemble system reached a prediction accuracy of 80 percent. In conclusion, this paper presents designs of dense autoencoder , self-supervised model using transfer learning and an ensemble method between dense autoencoder and self supervised classifiers. Further exploratory attempts on Generative Adversarial Network (GAN) and different feature extraction techniques could be researched for better generalization and performance Bachelor of Engineering (Electrical and Electronic Engineering) 2022-05-27T01:34:01Z 2022-05-27T01:34:01Z 2022 Final Year Project (FYP) Xie, Y. (2022). Unsupervised detection of anomalous sounds for machine condition monitoring. Final Year Project (FYP), Nanyang Technological University, Singapore. https://hdl.handle.net/10356/158025 https://hdl.handle.net/10356/158025 en A3104-221 application/pdf Nanyang Technological University |
institution |
Nanyang Technological University |
building |
NTU Library |
continent |
Asia |
country |
Singapore Singapore |
content_provider |
NTU Library |
collection |
DR-NTU |
language |
English |
topic |
Engineering::Electrical and electronic engineering::Computer hardware, software and systems |
spellingShingle |
Engineering::Electrical and electronic engineering::Computer hardware, software and systems Xie, Yonggang Unsupervised detection of anomalous sounds for machine condition monitoring |
description |
In an era of explosive machine applications , abnormal sound detection is gaining
increasing attention from machine learning engineers. This report presents a novel
solution to monitoring abnormal machine sounds by ensemble of models. Dense
autoencoder and convolutional autoencoder were ensembled with self-supervised
classifiers which output the confidence for machine-type predictions. In the datastet,
six types of machines, containing around 20,000 pieces of normally operating
recordings were used in the project. Time-series recordings were processed as mel spectrograms to be fed in the models. Competitive results were achieved by the
ensembled system of dense autoencoder and self-supervised model using ResNet50V2
as the backbone. On average, the self-supervised model achieved a classification
accuracy of 99 percent, and the ensemble system reached a prediction accuracy of 80
percent.
In conclusion, this paper presents designs of dense autoencoder , self-supervised model
using transfer learning and an ensemble method between dense autoencoder and self supervised classifiers. Further exploratory attempts on Generative Adversarial
Network (GAN) and different feature extraction techniques could be researched for
better generalization and performance |
author2 |
Gan Woon Seng |
author_facet |
Gan Woon Seng Xie, Yonggang |
format |
Final Year Project |
author |
Xie, Yonggang |
author_sort |
Xie, Yonggang |
title |
Unsupervised detection of anomalous sounds for machine condition monitoring |
title_short |
Unsupervised detection of anomalous sounds for machine condition monitoring |
title_full |
Unsupervised detection of anomalous sounds for machine condition monitoring |
title_fullStr |
Unsupervised detection of anomalous sounds for machine condition monitoring |
title_full_unstemmed |
Unsupervised detection of anomalous sounds for machine condition monitoring |
title_sort |
unsupervised detection of anomalous sounds for machine condition monitoring |
publisher |
Nanyang Technological University |
publishDate |
2022 |
url |
https://hdl.handle.net/10356/158025 |
_version_ |
1772828316069265408 |