RRBM-YOLO: Research on Efficient and Lightweight Convolutional Neural Networks for Underground Coal Gangue Identification

Coal gangue identification is the primary step in coal flow initial screening, which mainly faces problems such as low identification efficiency, complex algorithms, and high hardware requirements. In response to the above, this article proposes a new “hardware friendly” coal gangue image recognitio...

Full description

Saved in:
Bibliographic Details
Main Authors: Yutong Wang, Ziming Kou, Cong Han, Yuchen Qin
Format: Article
Language:English
Published: MDPI AG 2024-10-01
Series:Sensors
Subjects:
Online Access:https://www.mdpi.com/1424-8220/24/21/6943
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850192985173524480
author Yutong Wang
Ziming Kou
Cong Han
Yuchen Qin
author_facet Yutong Wang
Ziming Kou
Cong Han
Yuchen Qin
author_sort Yutong Wang
collection DOAJ
description Coal gangue identification is the primary step in coal flow initial screening, which mainly faces problems such as low identification efficiency, complex algorithms, and high hardware requirements. In response to the above, this article proposes a new “hardware friendly” coal gangue image recognition algorithm, RRBM-YOLO, which is combined with dark light enhancement. Specifically, coal gangue image samples were customized in two scenarios: normal lighting and simulated underground lighting with poor lighting conditions. The images were preprocessed using the dim light enhancement algorithm Retinexformer, with YOLOv8 as the backbone network. The lightweight module RepGhost, the repeated weighted bi-directional feature extraction module BiFPN, and the multi-dimensional attention mechanism MCA were integrated, and different datasets were replaced to enhance the adaptability of the model and improve its generalization ability. The findings from the experiment indicate that the precision of the proposed model is as high as 0.988, the mAP@0.5(%) value and mAP@0.5:0.95(%) values increased by 10.49% and 36.62% compared to the original YOLOv8 model, and the inference speed reached 8.1GFLOPS. This indicates that RRBM-YOLO can attain an optimal equilibrium between detection precision and inference velocity, with excellent accuracy, robustness, and industrial application potential.
format Article
id doaj-art-d298d95aa77f40be96b08dea176fee96
institution OA Journals
issn 1424-8220
language English
publishDate 2024-10-01
publisher MDPI AG
record_format Article
series Sensors
spelling doaj-art-d298d95aa77f40be96b08dea176fee962025-08-20T02:14:23ZengMDPI AGSensors1424-82202024-10-012421694310.3390/s24216943RRBM-YOLO: Research on Efficient and Lightweight Convolutional Neural Networks for Underground Coal Gangue IdentificationYutong Wang0Ziming Kou1Cong Han2Yuchen Qin3School of Mechanical Engineering, Taiyuan University of Technology, Taiyuan 030024, ChinaSchool of Mechanical Engineering, Taiyuan University of Technology, Taiyuan 030024, ChinaSchool of Mechanical Engineering, Taiyuan University of Technology, Taiyuan 030024, ChinaSchool of Mechanical Engineering, Taiyuan University of Technology, Taiyuan 030024, ChinaCoal gangue identification is the primary step in coal flow initial screening, which mainly faces problems such as low identification efficiency, complex algorithms, and high hardware requirements. In response to the above, this article proposes a new “hardware friendly” coal gangue image recognition algorithm, RRBM-YOLO, which is combined with dark light enhancement. Specifically, coal gangue image samples were customized in two scenarios: normal lighting and simulated underground lighting with poor lighting conditions. The images were preprocessed using the dim light enhancement algorithm Retinexformer, with YOLOv8 as the backbone network. The lightweight module RepGhost, the repeated weighted bi-directional feature extraction module BiFPN, and the multi-dimensional attention mechanism MCA were integrated, and different datasets were replaced to enhance the adaptability of the model and improve its generalization ability. The findings from the experiment indicate that the precision of the proposed model is as high as 0.988, the mAP@0.5(%) value and mAP@0.5:0.95(%) values increased by 10.49% and 36.62% compared to the original YOLOv8 model, and the inference speed reached 8.1GFLOPS. This indicates that RRBM-YOLO can attain an optimal equilibrium between detection precision and inference velocity, with excellent accuracy, robustness, and industrial application potential.https://www.mdpi.com/1424-8220/24/21/6943coal gangue recognitionYOLOv8lightweight module RepGhostattention mechanism MCAlow light enhancement
spellingShingle Yutong Wang
Ziming Kou
Cong Han
Yuchen Qin
RRBM-YOLO: Research on Efficient and Lightweight Convolutional Neural Networks for Underground Coal Gangue Identification
Sensors
coal gangue recognition
YOLOv8
lightweight module RepGhost
attention mechanism MCA
low light enhancement
title RRBM-YOLO: Research on Efficient and Lightweight Convolutional Neural Networks for Underground Coal Gangue Identification
title_full RRBM-YOLO: Research on Efficient and Lightweight Convolutional Neural Networks for Underground Coal Gangue Identification
title_fullStr RRBM-YOLO: Research on Efficient and Lightweight Convolutional Neural Networks for Underground Coal Gangue Identification
title_full_unstemmed RRBM-YOLO: Research on Efficient and Lightweight Convolutional Neural Networks for Underground Coal Gangue Identification
title_short RRBM-YOLO: Research on Efficient and Lightweight Convolutional Neural Networks for Underground Coal Gangue Identification
title_sort rrbm yolo research on efficient and lightweight convolutional neural networks for underground coal gangue identification
topic coal gangue recognition
YOLOv8
lightweight module RepGhost
attention mechanism MCA
low light enhancement
url https://www.mdpi.com/1424-8220/24/21/6943
work_keys_str_mv AT yutongwang rrbmyoloresearchonefficientandlightweightconvolutionalneuralnetworksforundergroundcoalgangueidentification
AT zimingkou rrbmyoloresearchonefficientandlightweightconvolutionalneuralnetworksforundergroundcoalgangueidentification
AT conghan rrbmyoloresearchonefficientandlightweightconvolutionalneuralnetworksforundergroundcoalgangueidentification
AT yuchenqin rrbmyoloresearchonefficientandlightweightconvolutionalneuralnetworksforundergroundcoalgangueidentification