Intelligent Fault Diagnosis of Rolling Element Bearings Based on Modified AlexNet
The reliable and safe operation of industrial systems needs to detect and diagnose bearing faults as early as possible. Intelligent fault diagnostic systems that use deep learning convolutional neural network (CNN) techniques have achieved a great deal of success in recent years. In a traditional CN...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2023-09-01
|
| Series: | Sensors |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1424-8220/23/18/7764 |
| _version_ | 1797577018581188608 |
|---|---|
| author | Mohammad Mohiuddin Md. Saiful Islam Shirajul Islam Md. Sipon Miah Ming-Bo Niu |
| author_facet | Mohammad Mohiuddin Md. Saiful Islam Shirajul Islam Md. Sipon Miah Ming-Bo Niu |
| author_sort | Mohammad Mohiuddin |
| collection | DOAJ |
| description | The reliable and safe operation of industrial systems needs to detect and diagnose bearing faults as early as possible. Intelligent fault diagnostic systems that use deep learning convolutional neural network (CNN) techniques have achieved a great deal of success in recent years. In a traditional CNN, the fully connected layer is located in the final three layers, and such a layer consists of multiple layers that are all connected. However, the fully connected layer of the CNN has the disadvantage of too many training parameters, which makes the model training and testing time longer and incurs overfitting. Additionally, because the working load is constantly changing and noise from the place of operation is unavoidable, the efficiency of intelligent fault diagnosis techniques suffers great reductions. In this research, we propose a novel technique that can effectively solve the problem of traditional CNN and accurately identify the bearing fault. Firstly, the best pre-trained CNN model is identified by considering the classification’s success rate for bearing fault diagnosis. Secondly, the selected CNN model is modified to effectively reduce the parameter quantities, overfitting, and calculating time of this model. Finally, the best classifier is identified to make a hybrid model concept to achieve the best performance. It is found that the proposed technique performs well under different load conditions, even in noisy environments, with variable signal-to-noise ratio (SNR) values. Our experimental results confirm that this proposed method is highly reliable and efficient in detecting and classifying bearing faults. |
| first_indexed | 2024-03-10T22:02:58Z |
| format | Article |
| id | doaj.art-0ec211c5c31444ac8bb539ef7bf94004 |
| institution | Directory Open Access Journal |
| issn | 1424-8220 |
| language | English |
| last_indexed | 2024-03-10T22:02:58Z |
| publishDate | 2023-09-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Sensors |
| spelling | doaj.art-0ec211c5c31444ac8bb539ef7bf940042023-11-19T12:53:51ZengMDPI AGSensors1424-82202023-09-012318776410.3390/s23187764Intelligent Fault Diagnosis of Rolling Element Bearings Based on Modified AlexNetMohammad Mohiuddin0Md. Saiful Islam1Shirajul Islam2Md. Sipon Miah3Ming-Bo Niu4Department of Electronics and Telecommunication Engineering, Chittagong University of Engineering and Technology (CUET), Chittagong 4349, BangladeshDepartment of Electronics and Telecommunication Engineering, Chittagong University of Engineering and Technology (CUET), Chittagong 4349, BangladeshDepartment of Electronics and Telecommunication Engineering, Chittagong University of Engineering and Technology (CUET), Chittagong 4349, BangladeshDepartment of Information and Communication Technology, Islamic University, Kushtia 7003, BangladeshIVR Low-Carbon Research Institute, School of Energy and Electrical Engineering, Chang’an University, Xi’an 710064, ChinaThe reliable and safe operation of industrial systems needs to detect and diagnose bearing faults as early as possible. Intelligent fault diagnostic systems that use deep learning convolutional neural network (CNN) techniques have achieved a great deal of success in recent years. In a traditional CNN, the fully connected layer is located in the final three layers, and such a layer consists of multiple layers that are all connected. However, the fully connected layer of the CNN has the disadvantage of too many training parameters, which makes the model training and testing time longer and incurs overfitting. Additionally, because the working load is constantly changing and noise from the place of operation is unavoidable, the efficiency of intelligent fault diagnosis techniques suffers great reductions. In this research, we propose a novel technique that can effectively solve the problem of traditional CNN and accurately identify the bearing fault. Firstly, the best pre-trained CNN model is identified by considering the classification’s success rate for bearing fault diagnosis. Secondly, the selected CNN model is modified to effectively reduce the parameter quantities, overfitting, and calculating time of this model. Finally, the best classifier is identified to make a hybrid model concept to achieve the best performance. It is found that the proposed technique performs well under different load conditions, even in noisy environments, with variable signal-to-noise ratio (SNR) values. Our experimental results confirm that this proposed method is highly reliable and efficient in detecting and classifying bearing faults.https://www.mdpi.com/1424-8220/23/18/7764CNN modeldiscrete wavelet transformglobal average poolingintelligent fault diagnosisvibration image |
| spellingShingle | Mohammad Mohiuddin Md. Saiful Islam Shirajul Islam Md. Sipon Miah Ming-Bo Niu Intelligent Fault Diagnosis of Rolling Element Bearings Based on Modified AlexNet Sensors CNN model discrete wavelet transform global average pooling intelligent fault diagnosis vibration image |
| title | Intelligent Fault Diagnosis of Rolling Element Bearings Based on Modified AlexNet |
| title_full | Intelligent Fault Diagnosis of Rolling Element Bearings Based on Modified AlexNet |
| title_fullStr | Intelligent Fault Diagnosis of Rolling Element Bearings Based on Modified AlexNet |
| title_full_unstemmed | Intelligent Fault Diagnosis of Rolling Element Bearings Based on Modified AlexNet |
| title_short | Intelligent Fault Diagnosis of Rolling Element Bearings Based on Modified AlexNet |
| title_sort | intelligent fault diagnosis of rolling element bearings based on modified alexnet |
| topic | CNN model discrete wavelet transform global average pooling intelligent fault diagnosis vibration image |
| url | https://www.mdpi.com/1424-8220/23/18/7764 |
| work_keys_str_mv | AT mohammadmohiuddin intelligentfaultdiagnosisofrollingelementbearingsbasedonmodifiedalexnet AT mdsaifulislam intelligentfaultdiagnosisofrollingelementbearingsbasedonmodifiedalexnet AT shirajulislam intelligentfaultdiagnosisofrollingelementbearingsbasedonmodifiedalexnet AT mdsiponmiah intelligentfaultdiagnosisofrollingelementbearingsbasedonmodifiedalexnet AT mingboniu intelligentfaultdiagnosisofrollingelementbearingsbasedonmodifiedalexnet |