An EfficientNetv2-based method for coal conveyor belt foreign object detection
The detection and recognition of foreign objects on coal conveyor belts play a crucial role in coal production. This article proposes a foreign object detection method for coal conveyor belts based on EfficientNetv2. Since MBConv and Fused-MBConv structures in EfficientNetv2 employ information compr...
Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Frontiers Media S.A.
2025-01-01
|
| Series: | Frontiers in Energy Research |
| Subjects: | |
| Online Access: | https://www.frontiersin.org/articles/10.3389/fenrg.2024.1444877/full |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1841543680145489920 |
|---|---|
| author | Tao Hu Deyu Zhuang Jinbo Qiu |
| author_facet | Tao Hu Deyu Zhuang Jinbo Qiu |
| author_sort | Tao Hu |
| collection | DOAJ |
| description | The detection and recognition of foreign objects on coal conveyor belts play a crucial role in coal production. This article proposes a foreign object detection method for coal conveyor belts based on EfficientNetv2. Since MBConv and Fused-MBConv structures in EfficientNetv2 employ information compression and fusion strategies, which may lead to the loss of important information and affect the integrity of feature extraction, a hard shuffle attention (Hard-SA) mechanism is utilized to enhance the focus on important features and improve the representation ability of coal conveyor belts image features. To address the potential gradient disappearance issue during the backpropagation process of the network, an elastic exponential linear unit (EELU) activation function is introduced. Additionally, since the cross-entropy loss function may not be flexible enough to handle complex data distributions and may fail to fit the non-linear relationships between data well, a Polyloss function is adopted. Polyloss can better adapt to the complex data distribution and task requirements of coal mine images. The experimental results show that the proposed method achieves an accuracy of 93.02%, which is 2.39% higher than that of EfficientNetv2. It also outperforms some other state-of-the-art (SOTA) models and can effectively complete the detection of foreign objects on coal conveyor belts. |
| format | Article |
| id | doaj-art-4220147e68524e6b8beee9c1ecae0954 |
| institution | Kabale University |
| issn | 2296-598X |
| language | English |
| publishDate | 2025-01-01 |
| publisher | Frontiers Media S.A. |
| record_format | Article |
| series | Frontiers in Energy Research |
| spelling | doaj-art-4220147e68524e6b8beee9c1ecae09542025-01-13T06:11:07ZengFrontiers Media S.A.Frontiers in Energy Research2296-598X2025-01-011210.3389/fenrg.2024.14448771444877An EfficientNetv2-based method for coal conveyor belt foreign object detectionTao Hu0Deyu Zhuang1Jinbo Qiu2China Coal Technology and Engineering Group Shanghai Co., Ltd., Shanghai, ChinaChina Coal Technology and Engineering Group Shanghai Co., Ltd., Shanghai, ChinaState Key Laboratory of Intelligent Coal Mining and Strata Control, Shanghai, ChinaThe detection and recognition of foreign objects on coal conveyor belts play a crucial role in coal production. This article proposes a foreign object detection method for coal conveyor belts based on EfficientNetv2. Since MBConv and Fused-MBConv structures in EfficientNetv2 employ information compression and fusion strategies, which may lead to the loss of important information and affect the integrity of feature extraction, a hard shuffle attention (Hard-SA) mechanism is utilized to enhance the focus on important features and improve the representation ability of coal conveyor belts image features. To address the potential gradient disappearance issue during the backpropagation process of the network, an elastic exponential linear unit (EELU) activation function is introduced. Additionally, since the cross-entropy loss function may not be flexible enough to handle complex data distributions and may fail to fit the non-linear relationships between data well, a Polyloss function is adopted. Polyloss can better adapt to the complex data distribution and task requirements of coal mine images. The experimental results show that the proposed method achieves an accuracy of 93.02%, which is 2.39% higher than that of EfficientNetv2. It also outperforms some other state-of-the-art (SOTA) models and can effectively complete the detection of foreign objects on coal conveyor belts.https://www.frontiersin.org/articles/10.3389/fenrg.2024.1444877/fullforeign object detectionEfficientNetv2hard shuffle attention (Hard-SA)elastic exponential linear units (EELU)polyloss function |
| spellingShingle | Tao Hu Deyu Zhuang Jinbo Qiu An EfficientNetv2-based method for coal conveyor belt foreign object detection Frontiers in Energy Research foreign object detection EfficientNetv2 hard shuffle attention (Hard-SA) elastic exponential linear units (EELU) polyloss function |
| title | An EfficientNetv2-based method for coal conveyor belt foreign object detection |
| title_full | An EfficientNetv2-based method for coal conveyor belt foreign object detection |
| title_fullStr | An EfficientNetv2-based method for coal conveyor belt foreign object detection |
| title_full_unstemmed | An EfficientNetv2-based method for coal conveyor belt foreign object detection |
| title_short | An EfficientNetv2-based method for coal conveyor belt foreign object detection |
| title_sort | efficientnetv2 based method for coal conveyor belt foreign object detection |
| topic | foreign object detection EfficientNetv2 hard shuffle attention (Hard-SA) elastic exponential linear units (EELU) polyloss function |
| url | https://www.frontiersin.org/articles/10.3389/fenrg.2024.1444877/full |
| work_keys_str_mv | AT taohu anefficientnetv2basedmethodforcoalconveyorbeltforeignobjectdetection AT deyuzhuang anefficientnetv2basedmethodforcoalconveyorbeltforeignobjectdetection AT jinboqiu anefficientnetv2basedmethodforcoalconveyorbeltforeignobjectdetection AT taohu efficientnetv2basedmethodforcoalconveyorbeltforeignobjectdetection AT deyuzhuang efficientnetv2basedmethodforcoalconveyorbeltforeignobjectdetection AT jinboqiu efficientnetv2basedmethodforcoalconveyorbeltforeignobjectdetection |