An Intelligent Framework for Fault Diagnosis of Centrifugal Pump Leveraging Wavelet Coherence Analysis and Deep Learning
This paper proposes an intelligent framework for the fault diagnosis of centrifugal pumps (CPs) based on wavelet coherence analysis (WCA) and deep learning (DL). The fault-related impulses in the CP vibration signal are often attenuated due to the background interference noises, thus affecting the s...
Main Authors: | , , , , , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
MDPI AG
2023-10-01
|
Series: | Sensors |
Subjects: | |
Online Access: | https://www.mdpi.com/1424-8220/23/21/8850 |
_version_ | 1797631257389039616 |
---|---|
author | Niamat Ullah Zahoor Ahmad Muhammad Farooq Siddique Kichang Im Dong-Koo Shon Tae-Hyun Yoon Dae-Seung Yoo Jong-Myon Kim |
author_facet | Niamat Ullah Zahoor Ahmad Muhammad Farooq Siddique Kichang Im Dong-Koo Shon Tae-Hyun Yoon Dae-Seung Yoo Jong-Myon Kim |
author_sort | Niamat Ullah |
collection | DOAJ |
description | This paper proposes an intelligent framework for the fault diagnosis of centrifugal pumps (CPs) based on wavelet coherence analysis (WCA) and deep learning (DL). The fault-related impulses in the CP vibration signal are often attenuated due to the background interference noises, thus affecting the sensitivity of the traditional statistical features towards faults. Furthermore, extracting health-sensitive information from the vibration signal needs human expertise and background knowledge. To extract CP health-sensitive features autonomously from the vibration signals, the proposed approach initially selects a healthy baseline signal. The wavelet coherence analysis is then computed between the healthy baseline signal and the signal obtained from a CP under different operating conditions, yielding coherograms. WCA is a signal processing technique that is used to measure the degree of linear correlation between two signals as a function of frequency. The coherograms carry information about the CP vulnerability towards the faults as the color intensity in the coherograms changes according to the change in CP health conditions. To utilize the changes in the coherograms due to the health conditions of the CP, they are provided to a Convolution Neural Network (CNN) and a Convolution Autoencoder (CAE) for the extraction of discriminant CP health-sensitive information autonomously. The CAE extracts global variations from the coherograms, and the CNN extracts local variations related to CP health. This information is combined into a single latent space vector. To identify the health conditions of the CP, the latent space vector is classified using an Artificial Neural Network (ANN). The proposed method identifies faults in the CP with higher accuracy as compared to already existing methods when it is tested on the vibration signals acquired from real-world industrial CPs. |
first_indexed | 2024-03-11T11:21:17Z |
format | Article |
id | doaj.art-500be07ebfc14b3b9fe9fc77380c81d7 |
institution | Directory Open Access Journal |
issn | 1424-8220 |
language | English |
last_indexed | 2024-03-11T11:21:17Z |
publishDate | 2023-10-01 |
publisher | MDPI AG |
record_format | Article |
series | Sensors |
spelling | doaj.art-500be07ebfc14b3b9fe9fc77380c81d72023-11-10T15:12:21ZengMDPI AGSensors1424-82202023-10-012321885010.3390/s23218850An Intelligent Framework for Fault Diagnosis of Centrifugal Pump Leveraging Wavelet Coherence Analysis and Deep LearningNiamat Ullah0Zahoor Ahmad1Muhammad Farooq Siddique2Kichang Im3Dong-Koo Shon4Tae-Hyun Yoon5Dae-Seung Yoo6Jong-Myon Kim7Department of Electrical, Electronics, and Computer Engineering, University of Ulsan, Ulsan 44610, Republic of KoreaDepartment of Electrical, Electronics, and Computer Engineering, University of Ulsan, Ulsan 44610, Republic of KoreaDepartment of Electrical, Electronics, and Computer Engineering, University of Ulsan, Ulsan 44610, Republic of KoreaICT Convergence Safety Research Center, University of Ulsan, Ulsan 44610, Republic of KoreaElectronics and Telecommunications Research Institute (ETRI), Daejeon 34129, Republic of KoreaElectronics and Telecommunications Research Institute (ETRI), Daejeon 34129, Republic of KoreaElectronics and Telecommunications Research Institute (ETRI), Daejeon 34129, Republic of KoreaDepartment of Electrical, Electronics, and Computer Engineering, University of Ulsan, Ulsan 44610, Republic of KoreaThis paper proposes an intelligent framework for the fault diagnosis of centrifugal pumps (CPs) based on wavelet coherence analysis (WCA) and deep learning (DL). The fault-related impulses in the CP vibration signal are often attenuated due to the background interference noises, thus affecting the sensitivity of the traditional statistical features towards faults. Furthermore, extracting health-sensitive information from the vibration signal needs human expertise and background knowledge. To extract CP health-sensitive features autonomously from the vibration signals, the proposed approach initially selects a healthy baseline signal. The wavelet coherence analysis is then computed between the healthy baseline signal and the signal obtained from a CP under different operating conditions, yielding coherograms. WCA is a signal processing technique that is used to measure the degree of linear correlation between two signals as a function of frequency. The coherograms carry information about the CP vulnerability towards the faults as the color intensity in the coherograms changes according to the change in CP health conditions. To utilize the changes in the coherograms due to the health conditions of the CP, they are provided to a Convolution Neural Network (CNN) and a Convolution Autoencoder (CAE) for the extraction of discriminant CP health-sensitive information autonomously. The CAE extracts global variations from the coherograms, and the CNN extracts local variations related to CP health. This information is combined into a single latent space vector. To identify the health conditions of the CP, the latent space vector is classified using an Artificial Neural Network (ANN). The proposed method identifies faults in the CP with higher accuracy as compared to already existing methods when it is tested on the vibration signals acquired from real-world industrial CPs.https://www.mdpi.com/1424-8220/23/21/8850centrifugal pumpwavelet coherence analysisfault diagnosisconvolutional neural networkvibrational signals |
spellingShingle | Niamat Ullah Zahoor Ahmad Muhammad Farooq Siddique Kichang Im Dong-Koo Shon Tae-Hyun Yoon Dae-Seung Yoo Jong-Myon Kim An Intelligent Framework for Fault Diagnosis of Centrifugal Pump Leveraging Wavelet Coherence Analysis and Deep Learning Sensors centrifugal pump wavelet coherence analysis fault diagnosis convolutional neural network vibrational signals |
title | An Intelligent Framework for Fault Diagnosis of Centrifugal Pump Leveraging Wavelet Coherence Analysis and Deep Learning |
title_full | An Intelligent Framework for Fault Diagnosis of Centrifugal Pump Leveraging Wavelet Coherence Analysis and Deep Learning |
title_fullStr | An Intelligent Framework for Fault Diagnosis of Centrifugal Pump Leveraging Wavelet Coherence Analysis and Deep Learning |
title_full_unstemmed | An Intelligent Framework for Fault Diagnosis of Centrifugal Pump Leveraging Wavelet Coherence Analysis and Deep Learning |
title_short | An Intelligent Framework for Fault Diagnosis of Centrifugal Pump Leveraging Wavelet Coherence Analysis and Deep Learning |
title_sort | intelligent framework for fault diagnosis of centrifugal pump leveraging wavelet coherence analysis and deep learning |
topic | centrifugal pump wavelet coherence analysis fault diagnosis convolutional neural network vibrational signals |
url | https://www.mdpi.com/1424-8220/23/21/8850 |
work_keys_str_mv | AT niamatullah anintelligentframeworkforfaultdiagnosisofcentrifugalpumpleveragingwaveletcoherenceanalysisanddeeplearning AT zahoorahmad anintelligentframeworkforfaultdiagnosisofcentrifugalpumpleveragingwaveletcoherenceanalysisanddeeplearning AT muhammadfarooqsiddique anintelligentframeworkforfaultdiagnosisofcentrifugalpumpleveragingwaveletcoherenceanalysisanddeeplearning AT kichangim anintelligentframeworkforfaultdiagnosisofcentrifugalpumpleveragingwaveletcoherenceanalysisanddeeplearning AT dongkooshon anintelligentframeworkforfaultdiagnosisofcentrifugalpumpleveragingwaveletcoherenceanalysisanddeeplearning AT taehyunyoon anintelligentframeworkforfaultdiagnosisofcentrifugalpumpleveragingwaveletcoherenceanalysisanddeeplearning AT daeseungyoo anintelligentframeworkforfaultdiagnosisofcentrifugalpumpleveragingwaveletcoherenceanalysisanddeeplearning AT jongmyonkim anintelligentframeworkforfaultdiagnosisofcentrifugalpumpleveragingwaveletcoherenceanalysisanddeeplearning AT niamatullah intelligentframeworkforfaultdiagnosisofcentrifugalpumpleveragingwaveletcoherenceanalysisanddeeplearning AT zahoorahmad intelligentframeworkforfaultdiagnosisofcentrifugalpumpleveragingwaveletcoherenceanalysisanddeeplearning AT muhammadfarooqsiddique intelligentframeworkforfaultdiagnosisofcentrifugalpumpleveragingwaveletcoherenceanalysisanddeeplearning AT kichangim intelligentframeworkforfaultdiagnosisofcentrifugalpumpleveragingwaveletcoherenceanalysisanddeeplearning AT dongkooshon intelligentframeworkforfaultdiagnosisofcentrifugalpumpleveragingwaveletcoherenceanalysisanddeeplearning AT taehyunyoon intelligentframeworkforfaultdiagnosisofcentrifugalpumpleveragingwaveletcoherenceanalysisanddeeplearning AT daeseungyoo intelligentframeworkforfaultdiagnosisofcentrifugalpumpleveragingwaveletcoherenceanalysisanddeeplearning AT jongmyonkim intelligentframeworkforfaultdiagnosisofcentrifugalpumpleveragingwaveletcoherenceanalysisanddeeplearning |