CNN-Based Fault Detection for Smart Manufacturing
A smart factory is a highly digitized and networked production facility based on smart manufacturing. A smart manufacturing plant is the result of intelligent systems deployed in the factory. Smart factories have higher production volumes and are prone to machine failures when operating in almost al...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2021-12-01
|
| Series: | Applied Sciences |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2076-3417/11/24/11732 |
| _version_ | 1797506781229875200 |
|---|---|
| author | Dhiraj Neupane Yunsu Kim Jongwon Seok Jungpyo Hong |
| author_facet | Dhiraj Neupane Yunsu Kim Jongwon Seok Jungpyo Hong |
| author_sort | Dhiraj Neupane |
| collection | DOAJ |
| description | A smart factory is a highly digitized and networked production facility based on smart manufacturing. A smart manufacturing plant is the result of intelligent systems deployed in the factory. Smart factories have higher production volumes and are prone to machine failures when operating in almost all applications on a daily basis. With the growing concept of smart manufacturing required for Industry 4.0, intelligent methods for detecting and classifying bearing faults have become a subject of scientific research and interest. In this paper, a deep learning-based 1-D convolutional neural network is proposed using the time-sequence bearing data from the Case Western Reserve University (CWRU) bearing database. Four different sets of data are used. The proposed method achieves state-of-the-art accuracy even with a small amount of training data. For the sensitivity analysis of the proposed method, metrics such as precision, recall, and f-measure are determined. Next, we compare the proposed method with a 2-D CNN that uses two-dimensional image illustrations of raw data as input. This method shows the effectiveness of using 1-D CNNs over 2-D CNNs for time-sequence data. The proposed method is computationally inexpensive and outperforms the most complex and computationally intensive algorithms used for bearing fault detection and diagnosis. |
| first_indexed | 2024-03-10T04:37:22Z |
| format | Article |
| id | doaj.art-1f5d4031f3f647d5a4574706d0819add |
| institution | Directory Open Access Journal |
| issn | 2076-3417 |
| language | English |
| last_indexed | 2024-03-10T04:37:22Z |
| publishDate | 2021-12-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Applied Sciences |
| spelling | doaj.art-1f5d4031f3f647d5a4574706d0819add2023-11-23T03:37:29ZengMDPI AGApplied Sciences2076-34172021-12-0111241173210.3390/app112411732CNN-Based Fault Detection for Smart Manufacturing Dhiraj Neupane0Yunsu Kim1Jongwon Seok2Jungpyo Hong3Research and Development Department, IPCamp, Jinju-si 52818, KoreaDepartment of Information and Communication Engineering, Changwon National University, Changwon-si 51140, KoreaDepartment of Information and Communication Engineering, Changwon National University, Changwon-si 51140, KoreaDepartment of Information and Communication Engineering, Changwon National University, Changwon-si 51140, KoreaA smart factory is a highly digitized and networked production facility based on smart manufacturing. A smart manufacturing plant is the result of intelligent systems deployed in the factory. Smart factories have higher production volumes and are prone to machine failures when operating in almost all applications on a daily basis. With the growing concept of smart manufacturing required for Industry 4.0, intelligent methods for detecting and classifying bearing faults have become a subject of scientific research and interest. In this paper, a deep learning-based 1-D convolutional neural network is proposed using the time-sequence bearing data from the Case Western Reserve University (CWRU) bearing database. Four different sets of data are used. The proposed method achieves state-of-the-art accuracy even with a small amount of training data. For the sensitivity analysis of the proposed method, metrics such as precision, recall, and f-measure are determined. Next, we compare the proposed method with a 2-D CNN that uses two-dimensional image illustrations of raw data as input. This method shows the effectiveness of using 1-D CNNs over 2-D CNNs for time-sequence data. The proposed method is computationally inexpensive and outperforms the most complex and computationally intensive algorithms used for bearing fault detection and diagnosis.https://www.mdpi.com/2076-3417/11/24/11732bearing faultsmart manufacturingCWRU datasetdeep learningconvolutional neural networkraw vibration data |
| spellingShingle | Dhiraj Neupane Yunsu Kim Jongwon Seok Jungpyo Hong CNN-Based Fault Detection for Smart Manufacturing Applied Sciences bearing fault smart manufacturing CWRU dataset deep learning convolutional neural network raw vibration data |
| title | CNN-Based Fault Detection for Smart Manufacturing |
| title_full | CNN-Based Fault Detection for Smart Manufacturing |
| title_fullStr | CNN-Based Fault Detection for Smart Manufacturing |
| title_full_unstemmed | CNN-Based Fault Detection for Smart Manufacturing |
| title_short | CNN-Based Fault Detection for Smart Manufacturing |
| title_sort | cnn based fault detection for smart manufacturing |
| topic | bearing fault smart manufacturing CWRU dataset deep learning convolutional neural network raw vibration data |
| url | https://www.mdpi.com/2076-3417/11/24/11732 |
| work_keys_str_mv | AT dhirajneupane cnnbasedfaultdetectionforsmartmanufacturing AT yunsukim cnnbasedfaultdetectionforsmartmanufacturing AT jongwonseok cnnbasedfaultdetectionforsmartmanufacturing AT jungpyohong cnnbasedfaultdetectionforsmartmanufacturing |