A Multi-Index Generative Adversarial Network for Tool Wear Detection with Imbalanced Data
The scarcity of abnormal data leads to imbalanced data in the field of monitoring tool wear conditions. In this paper, a novel multi-index generative adversarial network (MI-GAN) is proposed to detect the tool wear conditions subject to imbalanced signal data. First, the generator in the MI-GAN is t...
Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Wiley
2020-01-01
|
| Series: | Complexity |
| Online Access: | http://dx.doi.org/10.1155/2020/5831632 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832560204005244928 |
|---|---|
| author | Guokai Zhang Haoping Xiao Jingwen Jiang Qinyuan Liu Yimo Liu Liying Wang |
| author_facet | Guokai Zhang Haoping Xiao Jingwen Jiang Qinyuan Liu Yimo Liu Liying Wang |
| author_sort | Guokai Zhang |
| collection | DOAJ |
| description | The scarcity of abnormal data leads to imbalanced data in the field of monitoring tool wear conditions. In this paper, a novel multi-index generative adversarial network (MI-GAN) is proposed to detect the tool wear conditions subject to imbalanced signal data. First, the generator in the MI-GAN is trained to produce fake normal signals, and the discriminator computes scores of testing signals and generated signals. Next, the generator detects abnormal signals based on the performance of imitating testing signals, and the discriminator will compute the scores of testing signals and generated signals. Subsequently, two indexes, i.e., L2-norm and temporal correlation coefficient (CORT), are put forward to measure the similarity between generated signals and testing signals. Finally, our decision-making function further combines L2-norm and CORT with two discriminator scores to determine the tool conditions. Experimental results show that our method obtains 97% accuracy in tool wear detection based on imbalanced data without manual feature extraction, which outperforms traditional machine learning methods. |
| format | Article |
| id | doaj-art-b5ccc0cdf5484fdcb787aa74789e5cdd |
| institution | Kabale University |
| issn | 1076-2787 1099-0526 |
| language | English |
| publishDate | 2020-01-01 |
| publisher | Wiley |
| record_format | Article |
| series | Complexity |
| spelling | doaj-art-b5ccc0cdf5484fdcb787aa74789e5cdd2025-02-03T01:28:14ZengWileyComplexity1076-27871099-05262020-01-01202010.1155/2020/58316325831632A Multi-Index Generative Adversarial Network for Tool Wear Detection with Imbalanced DataGuokai Zhang0Haoping Xiao1Jingwen Jiang2Qinyuan Liu3Yimo Liu4Liying Wang5School of Optical-Electrical and Computer Engineering, University of Shanghai for Science and Technology, Shanghai, ChinaDepartment of Computer Science and Technology, Tongji University, Shanghai, ChinaTechnology Transformation Center, Shanghai Electric Group Co., Ltd. Central Academe, Shanghai, ChinaDepartment of Computer Science and Technology, Tongji University, Shanghai, ChinaSchool of Software, Tongji University, Shanghai, ChinaShanghai Leosue Network Technology Co., Ltd., Shanghai, ChinaThe scarcity of abnormal data leads to imbalanced data in the field of monitoring tool wear conditions. In this paper, a novel multi-index generative adversarial network (MI-GAN) is proposed to detect the tool wear conditions subject to imbalanced signal data. First, the generator in the MI-GAN is trained to produce fake normal signals, and the discriminator computes scores of testing signals and generated signals. Next, the generator detects abnormal signals based on the performance of imitating testing signals, and the discriminator will compute the scores of testing signals and generated signals. Subsequently, two indexes, i.e., L2-norm and temporal correlation coefficient (CORT), are put forward to measure the similarity between generated signals and testing signals. Finally, our decision-making function further combines L2-norm and CORT with two discriminator scores to determine the tool conditions. Experimental results show that our method obtains 97% accuracy in tool wear detection based on imbalanced data without manual feature extraction, which outperforms traditional machine learning methods.http://dx.doi.org/10.1155/2020/5831632 |
| spellingShingle | Guokai Zhang Haoping Xiao Jingwen Jiang Qinyuan Liu Yimo Liu Liying Wang A Multi-Index Generative Adversarial Network for Tool Wear Detection with Imbalanced Data Complexity |
| title | A Multi-Index Generative Adversarial Network for Tool Wear Detection with Imbalanced Data |
| title_full | A Multi-Index Generative Adversarial Network for Tool Wear Detection with Imbalanced Data |
| title_fullStr | A Multi-Index Generative Adversarial Network for Tool Wear Detection with Imbalanced Data |
| title_full_unstemmed | A Multi-Index Generative Adversarial Network for Tool Wear Detection with Imbalanced Data |
| title_short | A Multi-Index Generative Adversarial Network for Tool Wear Detection with Imbalanced Data |
| title_sort | multi index generative adversarial network for tool wear detection with imbalanced data |
| url | http://dx.doi.org/10.1155/2020/5831632 |
| work_keys_str_mv | AT guokaizhang amultiindexgenerativeadversarialnetworkfortoolweardetectionwithimbalanceddata AT haopingxiao amultiindexgenerativeadversarialnetworkfortoolweardetectionwithimbalanceddata AT jingwenjiang amultiindexgenerativeadversarialnetworkfortoolweardetectionwithimbalanceddata AT qinyuanliu amultiindexgenerativeadversarialnetworkfortoolweardetectionwithimbalanceddata AT yimoliu amultiindexgenerativeadversarialnetworkfortoolweardetectionwithimbalanceddata AT liyingwang amultiindexgenerativeadversarialnetworkfortoolweardetectionwithimbalanceddata AT guokaizhang multiindexgenerativeadversarialnetworkfortoolweardetectionwithimbalanceddata AT haopingxiao multiindexgenerativeadversarialnetworkfortoolweardetectionwithimbalanceddata AT jingwenjiang multiindexgenerativeadversarialnetworkfortoolweardetectionwithimbalanceddata AT qinyuanliu multiindexgenerativeadversarialnetworkfortoolweardetectionwithimbalanceddata AT yimoliu multiindexgenerativeadversarialnetworkfortoolweardetectionwithimbalanceddata AT liyingwang multiindexgenerativeadversarialnetworkfortoolweardetectionwithimbalanceddata |