A generalised intelligent bearing fault diagnosis model based on a two-stage approach
A generalised intelligent bearing fault diagnosis model based on a two-stage approach
This paper introduces a two-stage intelligent fault diagnosis model for rolling element bearings (REBs) aimed at overcoming the challenge of limited real-world vibration training data. In this study, bearing characteristic frequencies (BCFs) extracted from a novel hybrid method combining cepstrum pre-whitening (CPW) and high-pass filtering developed by the authors’ group are used as input features, and a two-stage approach is taken to develop an intelligent REB fault detect and diagnosis model. In the first stage, various machine learning (ML) methods, including support vector machine (SVM), multinomial logistic regressions (MLR), and artificial neural networks (ANN), are evaluated to identify faulty bearings from healthy ones. The best-performing ML model is selected for this stage. In the second stage, a similar evaluation is conducted to find the most suitable ML technique for bearing fault classification. The model is trained and validated using vibration data from an EU Clean Sky2 I2BS project (An EU Clean Sky 2 project ‘Integrated Intelligent Bearing Systems’ collaborated between Schaeffler Technologies and the University of Southampton. Safran Aero Engines was the topic manager for this project) and tested on datasets from Case Western Reserve University (CWRU) and the US Society for Machinery Failure Prevention Technology (MFPT). The results show that the two-stage model, using an SVM with a polynomial kernel function in Stage-1 and an ANN with one hidden layer and 0.05 dropout rate in Stage-2, can successfully detect bearing conditions in both test datasets and perform better than the results in literature without the requirement of further training. Compared with a single-stage model, the two-stage model also shows improved performance.
ANN, SVM, bearing characteristic frequencies, generalised fault diagnosis model, rolling element bearing, two-stage intelligent approach, vibration analysis, SVM and ANN
Kiakojouri, Amirmasoud
2a451714-d4fa-4ecc-9775-e828e975c884
Lu, Zudi
4aa7d988-ac2b-4150-a586-ca92b8adda95
Mirring, Patrick
7f50dd2b-912e-4994-aa2b-2a75befcc2cf
Powrie, Honor
81067bac-f71e-4bdb-b216-87f4f4da43de
Wang, Ling
67c7f78c-bd08-4935-8a68-c29dd49c9a2a
19 January 2024
Kiakojouri, Amirmasoud
2a451714-d4fa-4ecc-9775-e828e975c884
Lu, Zudi
4aa7d988-ac2b-4150-a586-ca92b8adda95
Mirring, Patrick
7f50dd2b-912e-4994-aa2b-2a75befcc2cf
Powrie, Honor
81067bac-f71e-4bdb-b216-87f4f4da43de
Wang, Ling
67c7f78c-bd08-4935-8a68-c29dd49c9a2a
Kiakojouri, Amirmasoud, Lu, Zudi, Mirring, Patrick, Powrie, Honor and Wang, Ling
(2024)
A generalised intelligent bearing fault diagnosis model based on a two-stage approach.
MDPI, 12 (1), [77].
(doi:10.3390/machines12010077).
Abstract
This paper introduces a two-stage intelligent fault diagnosis model for rolling element bearings (REBs) aimed at overcoming the challenge of limited real-world vibration training data. In this study, bearing characteristic frequencies (BCFs) extracted from a novel hybrid method combining cepstrum pre-whitening (CPW) and high-pass filtering developed by the authors’ group are used as input features, and a two-stage approach is taken to develop an intelligent REB fault detect and diagnosis model. In the first stage, various machine learning (ML) methods, including support vector machine (SVM), multinomial logistic regressions (MLR), and artificial neural networks (ANN), are evaluated to identify faulty bearings from healthy ones. The best-performing ML model is selected for this stage. In the second stage, a similar evaluation is conducted to find the most suitable ML technique for bearing fault classification. The model is trained and validated using vibration data from an EU Clean Sky2 I2BS project (An EU Clean Sky 2 project ‘Integrated Intelligent Bearing Systems’ collaborated between Schaeffler Technologies and the University of Southampton. Safran Aero Engines was the topic manager for this project) and tested on datasets from Case Western Reserve University (CWRU) and the US Society for Machinery Failure Prevention Technology (MFPT). The results show that the two-stage model, using an SVM with a polynomial kernel function in Stage-1 and an ANN with one hidden layer and 0.05 dropout rate in Stage-2, can successfully detect bearing conditions in both test datasets and perform better than the results in literature without the requirement of further training. Compared with a single-stage model, the two-stage model also shows improved performance.
Text
machines-12-00077-v2
- Version of Record
Text
machines-12-00077-manuscript
- Proof
More information
Accepted/In Press date: 17 January 2024
e-pub ahead of print date: 19 January 2024
Published date: 19 January 2024
Additional Information:
Publisher Copyright:
© 2024 by the authors.
Keywords:
ANN, SVM, bearing characteristic frequencies, generalised fault diagnosis model, rolling element bearing, two-stage intelligent approach, vibration analysis, SVM and ANN
Identifiers
Local EPrints ID: 486473
URI: http://eprints.soton.ac.uk/id/eprint/486473
PURE UUID: e94654d3-a8ac-4870-8acc-f377e75edf02
Catalogue record
Date deposited: 24 Jan 2024 17:32
Last modified: 12 Apr 2024 02:00
Export record
Altmetrics
Contributors
Author:
Amirmasoud Kiakojouri
Author:
Patrick Mirring
Author:
Honor Powrie
Author:
Ling Wang
Download statistics
Downloads from ePrints over the past year. Other digital versions may also be available to download e.g. from the publisher's website.
View more statistics