Ball Screw Fault Diagnosis Based on Wavelet Convolution Transfer Learning
The ball screw is the core component of the CNC machine tool feed system, and its health plays an important role in the feed system and even in the entire CNC machine tool. This paper studies the fault diagnosis and health assessment of ball screws. Aiming at the problem that the ball screw signal i...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2022-08-01
|
| Series: | Sensors |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1424-8220/22/16/6270 |
| _version_ | 1797431723208736768 |
|---|---|
| author | Yifan Xie Chang Liu Liji Huang Hongchun Duan |
| author_facet | Yifan Xie Chang Liu Liji Huang Hongchun Duan |
| author_sort | Yifan Xie |
| collection | DOAJ |
| description | The ball screw is the core component of the CNC machine tool feed system, and its health plays an important role in the feed system and even in the entire CNC machine tool. This paper studies the fault diagnosis and health assessment of ball screws. Aiming at the problem that the ball screw signal is weak and susceptible to interference, using a wavelet convolution structure to improve the network can improve the mining ability of signal time domain and frequency domain features; aiming at the challenge of ball screw sensor installation position limitation, a transfer learning method is proposed, which adopts the domain adaptation method as jointly distributed adaptation (JDA), and realizes the transfer diagnosis across measurement positions by extracting the diagnosis knowledge of different positions of the ball screw. In this paper, the adaptive batch normalization algorithm (AdaBN) is introduced to enhance the proposed model so as to improve the accuracy of migration diagnosis. Experiments were carried out using a self-made lead screw fatigue test bench. Through experimental verification, the method proposed in this paper can extract effective fault diagnosis knowledge. By collecting data under different working conditions at the bearing seat of the ball screw, the fault diagnosis knowledge is extracted and used to identify and diagnose the position fault of the nut seat. In this paper, some background noise is added to the collected data to test the robustness of the proposed network model. |
| first_indexed | 2024-03-09T09:50:25Z |
| format | Article |
| id | doaj.art-de0fffe63ce34c10b9549ead9cbc80b5 |
| institution | Directory Open Access Journal |
| issn | 1424-8220 |
| language | English |
| last_indexed | 2024-03-09T09:50:25Z |
| publishDate | 2022-08-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Sensors |
| spelling | doaj.art-de0fffe63ce34c10b9549ead9cbc80b52023-12-02T00:17:44ZengMDPI AGSensors1424-82202022-08-012216627010.3390/s22166270Ball Screw Fault Diagnosis Based on Wavelet Convolution Transfer LearningYifan Xie0Chang Liu1Liji Huang2Hongchun Duan3Key Laboratory of Advanced Equipment Intelligent Manufacturing Technology of Yunnan Province, Kunming University of Science & Technology, Kunming 650500, ChinaKey Laboratory of Advanced Equipment Intelligent Manufacturing Technology of Yunnan Province, Kunming University of Science & Technology, Kunming 650500, ChinaKey Laboratory of Advanced Equipment Intelligent Manufacturing Technology of Yunnan Province, Kunming University of Science & Technology, Kunming 650500, ChinaKey Laboratory of Advanced Equipment Intelligent Manufacturing Technology of Yunnan Province, Kunming University of Science & Technology, Kunming 650500, ChinaThe ball screw is the core component of the CNC machine tool feed system, and its health plays an important role in the feed system and even in the entire CNC machine tool. This paper studies the fault diagnosis and health assessment of ball screws. Aiming at the problem that the ball screw signal is weak and susceptible to interference, using a wavelet convolution structure to improve the network can improve the mining ability of signal time domain and frequency domain features; aiming at the challenge of ball screw sensor installation position limitation, a transfer learning method is proposed, which adopts the domain adaptation method as jointly distributed adaptation (JDA), and realizes the transfer diagnosis across measurement positions by extracting the diagnosis knowledge of different positions of the ball screw. In this paper, the adaptive batch normalization algorithm (AdaBN) is introduced to enhance the proposed model so as to improve the accuracy of migration diagnosis. Experiments were carried out using a self-made lead screw fatigue test bench. Through experimental verification, the method proposed in this paper can extract effective fault diagnosis knowledge. By collecting data under different working conditions at the bearing seat of the ball screw, the fault diagnosis knowledge is extracted and used to identify and diagnose the position fault of the nut seat. In this paper, some background noise is added to the collected data to test the robustness of the proposed network model.https://www.mdpi.com/1424-8220/22/16/6270transfer learningconvolutional neural networkadaptive batch normalization algorithmfault diagnosisball screw |
| spellingShingle | Yifan Xie Chang Liu Liji Huang Hongchun Duan Ball Screw Fault Diagnosis Based on Wavelet Convolution Transfer Learning Sensors transfer learning convolutional neural network adaptive batch normalization algorithm fault diagnosis ball screw |
| title | Ball Screw Fault Diagnosis Based on Wavelet Convolution Transfer Learning |
| title_full | Ball Screw Fault Diagnosis Based on Wavelet Convolution Transfer Learning |
| title_fullStr | Ball Screw Fault Diagnosis Based on Wavelet Convolution Transfer Learning |
| title_full_unstemmed | Ball Screw Fault Diagnosis Based on Wavelet Convolution Transfer Learning |
| title_short | Ball Screw Fault Diagnosis Based on Wavelet Convolution Transfer Learning |
| title_sort | ball screw fault diagnosis based on wavelet convolution transfer learning |
| topic | transfer learning convolutional neural network adaptive batch normalization algorithm fault diagnosis ball screw |
| url | https://www.mdpi.com/1424-8220/22/16/6270 |
| work_keys_str_mv | AT yifanxie ballscrewfaultdiagnosisbasedonwaveletconvolutiontransferlearning AT changliu ballscrewfaultdiagnosisbasedonwaveletconvolutiontransferlearning AT lijihuang ballscrewfaultdiagnosisbasedonwaveletconvolutiontransferlearning AT hongchunduan ballscrewfaultdiagnosisbasedonwaveletconvolutiontransferlearning |