A deep learning method based on multi-scale fusion for noise-resistant coal-gangue recognition
Abstract Coal-gangue recognition technology plays an important role in the intelligent realization of integrated working faces and coal quality improvement. However, the existing methods are easily affected by high dust, noise, and other disturbances, resulting in unstable recognition results that m...
Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Nature Portfolio
2025-01-01
|
| Series: | Scientific Reports |
| Subjects: | |
| Online Access: | https://doi.org/10.1038/s41598-024-83604-z |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1841559613360570368 |
|---|---|
| author | Qingjun Song Shirong Sun Qinghui Song Bingrui Wang Zihao Liu Haiyan Jiang |
| author_facet | Qingjun Song Shirong Sun Qinghui Song Bingrui Wang Zihao Liu Haiyan Jiang |
| author_sort | Qingjun Song |
| collection | DOAJ |
| description | Abstract Coal-gangue recognition technology plays an important role in the intelligent realization of integrated working faces and coal quality improvement. However, the existing methods are easily affected by high dust, noise, and other disturbances, resulting in unstable recognition results that make it difficult to meet the needs of industrial applications. To realize accurate recognition of coal-gangue in noisy environments, this paper proposes an end-to-end multi-scale feature fusion convolutional neural network (MCNN-BILSTM) based gangue recognition method, which can automatically learn and fuse complementary information from multiple signal components of vibration signals. It combines traditional filtering methods and the idea of multi-scale learning, which can expand the breadth and depth of the feature learning process. the breadth and depth of the feature learning process. Moreover, to strengthen the expression of key features, a feature weighting method based on the attention mechanism is combined to give adaptive weights to different features. Finally, the experimental platform of a tail beam of coal-gangue impact hydraulic support is built, and several comparative experiments are carried out. The comprehensive comparison experiments show that the method shows strong adaptability, robustness, and noise resistance under various complex noise environments, and is suitable for complex practical industrial sites. |
| format | Article |
| id | doaj-art-a31e151208f34fdfad6f037b045b141f |
| institution | Kabale University |
| issn | 2045-2322 |
| language | English |
| publishDate | 2025-01-01 |
| publisher | Nature Portfolio |
| record_format | Article |
| series | Scientific Reports |
| spelling | doaj-art-a31e151208f34fdfad6f037b045b141f2025-01-05T12:20:30ZengNature PortfolioScientific Reports2045-23222025-01-0115111810.1038/s41598-024-83604-zA deep learning method based on multi-scale fusion for noise-resistant coal-gangue recognitionQingjun Song0Shirong Sun1Qinghui Song2Bingrui Wang3Zihao Liu4Haiyan Jiang5College of Intelligent Equipment, Shandong University of Science and TechnologyCollege of Intelligent Equipment, Shandong University of Science and TechnologyCollege of Intelligent Equipment, Shandong University of Science and TechnologyCollege of Intelligent Equipment, Shandong University of Science and TechnologyCollege of Intelligent Equipment, Shandong University of Science and TechnologyCollege of Intelligent Equipment, Shandong University of Science and TechnologyAbstract Coal-gangue recognition technology plays an important role in the intelligent realization of integrated working faces and coal quality improvement. However, the existing methods are easily affected by high dust, noise, and other disturbances, resulting in unstable recognition results that make it difficult to meet the needs of industrial applications. To realize accurate recognition of coal-gangue in noisy environments, this paper proposes an end-to-end multi-scale feature fusion convolutional neural network (MCNN-BILSTM) based gangue recognition method, which can automatically learn and fuse complementary information from multiple signal components of vibration signals. It combines traditional filtering methods and the idea of multi-scale learning, which can expand the breadth and depth of the feature learning process. the breadth and depth of the feature learning process. Moreover, to strengthen the expression of key features, a feature weighting method based on the attention mechanism is combined to give adaptive weights to different features. Finally, the experimental platform of a tail beam of coal-gangue impact hydraulic support is built, and several comparative experiments are carried out. The comprehensive comparison experiments show that the method shows strong adaptability, robustness, and noise resistance under various complex noise environments, and is suitable for complex practical industrial sites.https://doi.org/10.1038/s41598-024-83604-zCoal–gangue recognitionvibration signalMulti-scale parallel neural networkattention mechanism |
| spellingShingle | Qingjun Song Shirong Sun Qinghui Song Bingrui Wang Zihao Liu Haiyan Jiang A deep learning method based on multi-scale fusion for noise-resistant coal-gangue recognition Scientific Reports Coal–gangue recognition vibration signal Multi-scale parallel neural network attention mechanism |
| title | A deep learning method based on multi-scale fusion for noise-resistant coal-gangue recognition |
| title_full | A deep learning method based on multi-scale fusion for noise-resistant coal-gangue recognition |
| title_fullStr | A deep learning method based on multi-scale fusion for noise-resistant coal-gangue recognition |
| title_full_unstemmed | A deep learning method based on multi-scale fusion for noise-resistant coal-gangue recognition |
| title_short | A deep learning method based on multi-scale fusion for noise-resistant coal-gangue recognition |
| title_sort | deep learning method based on multi scale fusion for noise resistant coal gangue recognition |
| topic | Coal–gangue recognition vibration signal Multi-scale parallel neural network attention mechanism |
| url | https://doi.org/10.1038/s41598-024-83604-z |
| work_keys_str_mv | AT qingjunsong adeeplearningmethodbasedonmultiscalefusionfornoiseresistantcoalganguerecognition AT shirongsun adeeplearningmethodbasedonmultiscalefusionfornoiseresistantcoalganguerecognition AT qinghuisong adeeplearningmethodbasedonmultiscalefusionfornoiseresistantcoalganguerecognition AT bingruiwang adeeplearningmethodbasedonmultiscalefusionfornoiseresistantcoalganguerecognition AT zihaoliu adeeplearningmethodbasedonmultiscalefusionfornoiseresistantcoalganguerecognition AT haiyanjiang adeeplearningmethodbasedonmultiscalefusionfornoiseresistantcoalganguerecognition AT qingjunsong deeplearningmethodbasedonmultiscalefusionfornoiseresistantcoalganguerecognition AT shirongsun deeplearningmethodbasedonmultiscalefusionfornoiseresistantcoalganguerecognition AT qinghuisong deeplearningmethodbasedonmultiscalefusionfornoiseresistantcoalganguerecognition AT bingruiwang deeplearningmethodbasedonmultiscalefusionfornoiseresistantcoalganguerecognition AT zihaoliu deeplearningmethodbasedonmultiscalefusionfornoiseresistantcoalganguerecognition AT haiyanjiang deeplearningmethodbasedonmultiscalefusionfornoiseresistantcoalganguerecognition |