A Defect Detection Method for a Boiler Inner Wall Based on an Improved YOLO-v5 Network and Data Augmentation Technologies
During the long-term operation of a coal-fired boiler, some defects of its inner wall are unavoidable. The traditional manual detecting method is time-consuming and not safe for maintenance engineers. In this paper, we propose an automatic detection method to deal with inner wall defects based on an...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2022-01-01
|
| Series: | IEEE Access |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/9880480/ |
| _version_ | 1798001119426772992 |
|---|---|
| author | Xiaoming Sun Xinchun Jia Yuqian Liang Meigang Wang Xiaobo Chi |
| author_facet | Xiaoming Sun Xinchun Jia Yuqian Liang Meigang Wang Xiaobo Chi |
| author_sort | Xiaoming Sun |
| collection | DOAJ |
| description | During the long-term operation of a coal-fired boiler, some defects of its inner wall are unavoidable. The traditional manual detecting method is time-consuming and not safe for maintenance engineers. In this paper, we propose an automatic detection method to deal with inner wall defects based on an improved YOLO-v5 network and data augmentation technologies. Specifically, some shallow features and original deep features are fused on the basis of the original YOLO-v5 network for the small objects. Meanwhile, a squeeze-excitation (SE) attention module is added behind the network’s backbone to improve the feature extraction efficiency of the network, and a varifocal loss function is adopted to make it easier for the network to detect those dense objects. Moreover, 176 images including four types of typical inner wall defects (castables falling off, anti-wear layer damage, perforation and bruise) are collected from a power plant boiler, and five data augmentation technologies are introduced to increase the number of samples. The experimental results demonstrate that the proposed method can effectively detect various defects of a boiler inner wall with a satisfactory accuracy, and bring a great facilitation to the maintenance of a power plant. |
| first_indexed | 2024-04-11T11:32:06Z |
| format | Article |
| id | doaj.art-116c27f76cf84e018834c0b82c71934c |
| institution | Directory Open Access Journal |
| issn | 2169-3536 |
| language | English |
| last_indexed | 2024-04-11T11:32:06Z |
| publishDate | 2022-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Access |
| spelling | doaj.art-116c27f76cf84e018834c0b82c71934c2022-12-22T04:26:06ZengIEEEIEEE Access2169-35362022-01-0110938459385310.1109/ACCESS.2022.32046839880480A Defect Detection Method for a Boiler Inner Wall Based on an Improved YOLO-v5 Network and Data Augmentation TechnologiesXiaoming Sun0Xinchun Jia1https://orcid.org/0000-0003-4272-5758Yuqian Liang2Meigang Wang3Xiaobo Chi4https://orcid.org/0000-0002-0455-5607School of Automation and Software Engineering, Shanxi University, Taiyuan, ChinaSchool of Automation and Software Engineering, Shanxi University, Taiyuan, ChinaSchool of Automation and Software Engineering, Shanxi University, Taiyuan, ChinaSchool of Automation and Software Engineering, Shanxi University, Taiyuan, ChinaSchool of Mathematical Sciences, Shanxi University, Taiyuan, ChinaDuring the long-term operation of a coal-fired boiler, some defects of its inner wall are unavoidable. The traditional manual detecting method is time-consuming and not safe for maintenance engineers. In this paper, we propose an automatic detection method to deal with inner wall defects based on an improved YOLO-v5 network and data augmentation technologies. Specifically, some shallow features and original deep features are fused on the basis of the original YOLO-v5 network for the small objects. Meanwhile, a squeeze-excitation (SE) attention module is added behind the network’s backbone to improve the feature extraction efficiency of the network, and a varifocal loss function is adopted to make it easier for the network to detect those dense objects. Moreover, 176 images including four types of typical inner wall defects (castables falling off, anti-wear layer damage, perforation and bruise) are collected from a power plant boiler, and five data augmentation technologies are introduced to increase the number of samples. The experimental results demonstrate that the proposed method can effectively detect various defects of a boiler inner wall with a satisfactory accuracy, and bring a great facilitation to the maintenance of a power plant.https://ieeexplore.ieee.org/document/9880480/Boiler inner wall defectsobject detectionimproved YOLO-v5 networkdata augmentation |
| spellingShingle | Xiaoming Sun Xinchun Jia Yuqian Liang Meigang Wang Xiaobo Chi A Defect Detection Method for a Boiler Inner Wall Based on an Improved YOLO-v5 Network and Data Augmentation Technologies IEEE Access Boiler inner wall defects object detection improved YOLO-v5 network data augmentation |
| title | A Defect Detection Method for a Boiler Inner Wall Based on an Improved YOLO-v5 Network and Data Augmentation Technologies |
| title_full | A Defect Detection Method for a Boiler Inner Wall Based on an Improved YOLO-v5 Network and Data Augmentation Technologies |
| title_fullStr | A Defect Detection Method for a Boiler Inner Wall Based on an Improved YOLO-v5 Network and Data Augmentation Technologies |
| title_full_unstemmed | A Defect Detection Method for a Boiler Inner Wall Based on an Improved YOLO-v5 Network and Data Augmentation Technologies |
| title_short | A Defect Detection Method for a Boiler Inner Wall Based on an Improved YOLO-v5 Network and Data Augmentation Technologies |
| title_sort | defect detection method for a boiler inner wall based on an improved yolo v5 network and data augmentation technologies |
| topic | Boiler inner wall defects object detection improved YOLO-v5 network data augmentation |
| url | https://ieeexplore.ieee.org/document/9880480/ |
| work_keys_str_mv | AT xiaomingsun adefectdetectionmethodforaboilerinnerwallbasedonanimprovedyolov5networkanddataaugmentationtechnologies AT xinchunjia adefectdetectionmethodforaboilerinnerwallbasedonanimprovedyolov5networkanddataaugmentationtechnologies AT yuqianliang adefectdetectionmethodforaboilerinnerwallbasedonanimprovedyolov5networkanddataaugmentationtechnologies AT meigangwang adefectdetectionmethodforaboilerinnerwallbasedonanimprovedyolov5networkanddataaugmentationtechnologies AT xiaobochi adefectdetectionmethodforaboilerinnerwallbasedonanimprovedyolov5networkanddataaugmentationtechnologies AT xiaomingsun defectdetectionmethodforaboilerinnerwallbasedonanimprovedyolov5networkanddataaugmentationtechnologies AT xinchunjia defectdetectionmethodforaboilerinnerwallbasedonanimprovedyolov5networkanddataaugmentationtechnologies AT yuqianliang defectdetectionmethodforaboilerinnerwallbasedonanimprovedyolov5networkanddataaugmentationtechnologies AT meigangwang defectdetectionmethodforaboilerinnerwallbasedonanimprovedyolov5networkanddataaugmentationtechnologies AT xiaobochi defectdetectionmethodforaboilerinnerwallbasedonanimprovedyolov5networkanddataaugmentationtechnologies |