Coal-gangue recognition via multi-branch convolutional neural network based on MFCC in noisy environment
Abstract Traditional coal-gangue recognition methods usually do not consider the impact of equipment noise, which severely limits its adaptability and recognition accuracy. This paper mainly studies the more accurate recognition of coal-gangue in the noise site environment with the operation of shea...
| Main Authors: | , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Nature Portfolio
2023-04-01
|
| Series: | Scientific Reports |
| Online Access: | https://doi.org/10.1038/s41598-023-33351-4 |
| _version_ | 1797841059299983360 |
|---|---|
| author | HaiYan Jiang DaShuai Zong QingJun Song KuiDong Gao HuiZhi Shao ZhiJiang Liu Jing Tian |
| author_facet | HaiYan Jiang DaShuai Zong QingJun Song KuiDong Gao HuiZhi Shao ZhiJiang Liu Jing Tian |
| author_sort | HaiYan Jiang |
| collection | DOAJ |
| description | Abstract Traditional coal-gangue recognition methods usually do not consider the impact of equipment noise, which severely limits its adaptability and recognition accuracy. This paper mainly studies the more accurate recognition of coal-gangue in the noise site environment with the operation of shearer, conveyor, transfer machine and other device in the process of top coal caving. Mel Frequency Cepstrum Coefficients (MFCC) smoothing method was introduced to express the intrinsic feature of sound pressure more clearly in the coal-gangue recognition site. Then, a multi-branch convolution neural network (MBCNN) model with three branches was developed, and the smoothed MFCC feature was incorporated into this model to realize the recognition of falling coal and gangue in noisy environment. The sound pressure signal datasets under the operation of different device were constructed through a great deal of laboratory and site data acquisition. Comparative experiments were carried out on noiseless dataset, single noise dataset and simulated site dataset, and the results show that our method can provide higher correct recognition accuracy and better robustness. The proposed coal-gangue recognition approach based on MBCNN and MFCC smoothing can not only recognize the state of falling coal or gangue, but also recognize the operational state of site device. |
| first_indexed | 2024-04-09T16:24:51Z |
| format | Article |
| id | doaj.art-1cca168068684c2b89b262bb10e9657e |
| institution | Directory Open Access Journal |
| issn | 2045-2322 |
| language | English |
| last_indexed | 2024-04-09T16:24:51Z |
| publishDate | 2023-04-01 |
| publisher | Nature Portfolio |
| record_format | Article |
| series | Scientific Reports |
| spelling | doaj.art-1cca168068684c2b89b262bb10e9657e2023-04-23T11:13:55ZengNature PortfolioScientific Reports2045-23222023-04-0113111210.1038/s41598-023-33351-4Coal-gangue recognition via multi-branch convolutional neural network based on MFCC in noisy environmentHaiYan Jiang0DaShuai Zong1QingJun Song2KuiDong Gao3HuiZhi Shao4ZhiJiang Liu5Jing Tian6Department of Intelligent Equipment, Shandong University of Science & TechnologyDepartment of Intelligent Equipment, Shandong University of Science & TechnologyDepartment of Intelligent Equipment, Shandong University of Science & TechnologyShandong Province Key Laboratory of Mine Mechanical Engineering, Shandong University of Science & TechnologyHong Kong Baptist UniversityDepartment of Intelligent Equipment, Shandong University of Science & TechnologyTaihe Electric Power Co. LtdAbstract Traditional coal-gangue recognition methods usually do not consider the impact of equipment noise, which severely limits its adaptability and recognition accuracy. This paper mainly studies the more accurate recognition of coal-gangue in the noise site environment with the operation of shearer, conveyor, transfer machine and other device in the process of top coal caving. Mel Frequency Cepstrum Coefficients (MFCC) smoothing method was introduced to express the intrinsic feature of sound pressure more clearly in the coal-gangue recognition site. Then, a multi-branch convolution neural network (MBCNN) model with three branches was developed, and the smoothed MFCC feature was incorporated into this model to realize the recognition of falling coal and gangue in noisy environment. The sound pressure signal datasets under the operation of different device were constructed through a great deal of laboratory and site data acquisition. Comparative experiments were carried out on noiseless dataset, single noise dataset and simulated site dataset, and the results show that our method can provide higher correct recognition accuracy and better robustness. The proposed coal-gangue recognition approach based on MBCNN and MFCC smoothing can not only recognize the state of falling coal or gangue, but also recognize the operational state of site device.https://doi.org/10.1038/s41598-023-33351-4 |
| spellingShingle | HaiYan Jiang DaShuai Zong QingJun Song KuiDong Gao HuiZhi Shao ZhiJiang Liu Jing Tian Coal-gangue recognition via multi-branch convolutional neural network based on MFCC in noisy environment Scientific Reports |
| title | Coal-gangue recognition via multi-branch convolutional neural network based on MFCC in noisy environment |
| title_full | Coal-gangue recognition via multi-branch convolutional neural network based on MFCC in noisy environment |
| title_fullStr | Coal-gangue recognition via multi-branch convolutional neural network based on MFCC in noisy environment |
| title_full_unstemmed | Coal-gangue recognition via multi-branch convolutional neural network based on MFCC in noisy environment |
| title_short | Coal-gangue recognition via multi-branch convolutional neural network based on MFCC in noisy environment |
| title_sort | coal gangue recognition via multi branch convolutional neural network based on mfcc in noisy environment |
| url | https://doi.org/10.1038/s41598-023-33351-4 |
| work_keys_str_mv | AT haiyanjiang coalganguerecognitionviamultibranchconvolutionalneuralnetworkbasedonmfccinnoisyenvironment AT dashuaizong coalganguerecognitionviamultibranchconvolutionalneuralnetworkbasedonmfccinnoisyenvironment AT qingjunsong coalganguerecognitionviamultibranchconvolutionalneuralnetworkbasedonmfccinnoisyenvironment AT kuidonggao coalganguerecognitionviamultibranchconvolutionalneuralnetworkbasedonmfccinnoisyenvironment AT huizhishao coalganguerecognitionviamultibranchconvolutionalneuralnetworkbasedonmfccinnoisyenvironment AT zhijiangliu coalganguerecognitionviamultibranchconvolutionalneuralnetworkbasedonmfccinnoisyenvironment AT jingtian coalganguerecognitionviamultibranchconvolutionalneuralnetworkbasedonmfccinnoisyenvironment |