A study on the influence of particle size on the identification accuracy of coal and gangue

• Autorzy: Li Xin , Wang Shuang , He Lei , Luo Qisheng

Identyfikatory

DOI

10.24425/gsm.2023.144634

Warianty tytułu

PL

Badanie wpływu wielkości cząstek na dokładność identyfikacji węgla i skały płonnej

• Języki publikacji: EN

Abstrakty

EN

In order to explore the impact of coal and gangue particle size changes on recognition accuracy and to improve the single particle size of coal and gangue identification accuracy of sorting equipment, this study established a database of different particle sizes of coal and gangue through image gray and texture feature extraction, using a relief feature selection algorithm to compare different particle size of coal and gangue optimal features of the combination, and to identify the points and particle size of coal and gangue. The results show that the optimal features and number of coal and gangue are different with different particle sizes. Based on visible-light coal and gangue separation technology, the change of coal and gangue particle size cause fluctuations in the recognition accuracy, and the fluctuation of recognition accuracy will gradually decrease with increases in the number of features. In the process of particle size classification, if the training model has a single particle size range, the recognition accuracy of each particle size range is low, with the highest recognition accuracy being 98% and the average recognition rate being only 97.2%. The method proposed in this paper can effectively improve the recognition accuracy of each particle size range. The maximum recognition accuracy is 100%, the maximum increase is 4%, and the average recognition accuracy is 99.2%. Therefore, this method has a high practical application value for the separation of coal and gangue with single particle size.

PL

W celu zbadania wpływu zmian wielkości cząstek węgla i skały płonnej na dokładność rozpoznawania oraz poprawienia dokładności identyfikacji pojedynczych cząstek węgla i skały płonnej przez urządzenia sortujące, w ramach tej pracy utworzono bazę danych różnych rozmiarów cząstek węgla i skały płonnej za pomocą obrazów szarych i ekstrakcję cech tekstury przy użyciu algorytmu wyboru cech reliefowych w celu porównania różnych rozmiarów cząstek węgla i skały płonnej przy optymalnych cechach kombinacji oraz identyfikacji punktów i wielkości cząstek węgla i skały płonnej. Wyniki pokazują, że optymalne liczby cech węgla i skały płonnej są różne dla różnych rozmiarów cząstek. W oparciu o technologię separacji węgla i skały płonnej w świetle widzialnym, zmiana wielkości cząstek węgla i skały płonnej powoduje fluktuacje dokładności rozpoznawania, a te z kolei będą stopniowo zmniejszać się wraz ze wzrostem liczby cech. W procesie klasyfikacji wielkości cząstek, jeśli model uczący ma jeden zakres wielkości cząstek, dokładność rozpoznawania każdego zakresu wielkości cząstek jest niska, przy czym najwyższa dokładność rozpoznawania wynosi 98%, a średni wskaźnik rozpoznawania wynosi tylko 97,2%. Metoda zaproponowana w tym artykule może skutecznie poprawić dokładność rozpoznawania każdego zakresu wielkości cząstek. Maksymalna dokładność rozpoznawania wynosi 100%, maksymalny wzrost to 4%, a średnia dokładność rozpoznawania to 99,2%. Dlatego ta metoda ma dużą praktyczną wartość użytkową do oddzielania węgla i skały płonnej według rozmiaru pojedynczej cząstki.

Słowa kluczowe

EN

particle size; gray feature; texture feature; support vector machine; coal identification; gangue identification

PL

wielkość cząstek; cecha szarości; cecha tekstury; maszyna wektorów pomocniczych; identyfikacja węgla; identyfikacja skały płonnej

• Wydawca: Instytut Gospodarki Surowcami Mineralnymi i Energią PAN ; Komitet Zrównoważonej Gospodarki Surowcami Mineralnymi PAN
• Czasopismo: Gospodarka Surowcami Mineralnymi
• Rocznik: 2023
• Tom: T. 39, z. 1
• Strony: 109--129
• Opis fizyczny: Bibliogr. 28 poz., rys., tab., wykr.

Twórcy

autor

Li Xin

• School of Mechanical Engineering, Anhui University of Science and Technology, Huainan, China
• State Key Laboratory of Mining Response and Disaster Prevention and Control in Deep Coal Mines, Anhui University of Science and Technology, Huainan, China

• https://orcid.org/0000-0003-4334-3532

autor

Wang Shuang

• School of Mechanical Engineering, Anhui University of Science and Technology, Huainan, China
• State Key Laboratory of Mining Response and Disaster Prevention and Control in Deep Coal Mines, Anhui University of Science and Technology, Huainan, China

autor

He Lei

• School of Mechanical Engineering, Anhui University of Science and Technology, Huainan, China
• State Key Laboratory of Mining Response and Disaster Prevention and Control in Deep Coal Mines, Anhui University of Science and Technology, Huainan, China

autor

Luo Qisheng

• School of Mechanical Engineering, Anhui University of Science and Technology, Huainan, China
• State Key Laboratory of Mining Response and Disaster Prevention and Control in Deep Coal Mines, Anhui University of Science and Technology, Huainan, China

Bibliografia

• [1] Alpna. and Chand, S. 2020. An intelligent technique for the characterization of coal microscopic images using ensemble learning. Journal of Intelligent & Fuzzy Systems 38(5), pp. 6257-6267, DOI: 10.3233/JIFS-179707.
• [2] Ansari et al. 2017 – Ansari, M., Diksha, K. and Manish, D. 2017. A comprehensive analysis of image edge detection techniques. International Journal of Multimedia and Ubiquitous Engineering 12(11), pp. 1-12, DOI: 10.14257/ijmue.2017.12.11.01.
• [3] Dou et al. 2019 – Dou, D., Wu, W., Yang, J. and Zhang, Y. 2019. Classification of coal and gangue under multiple surface conditions via machine vision and relief-SVM. Powder Technology 356, pp. 1024-1028, DOI: 10.1016/j.powtec.2019.09.007.
• [4] Eshaq et al. 2020 – Eshaq, R., Hu, E., Li, M. and Alfarzaeai, M.S. 2020. Separation between coal and gangue based on infrared radiation and visual extraction of the YCbCr color space. Ieee Access 8, pp. 55204-55220, DOI: 10.1109/ACCESS.2020.2981534.
• [5] Haralick et al. 1973 – Haralick, R.M., Shanmugan, K. and Dinstein, I. 1973. Textural features for image classification. IEEE Transactions on systems, man, and cybernetics SMC-3(6), pp. 610-621.
• [6] He et al. 2022 – He, L., Wang, S., Guo, Y., Hu, K. and Cheng, G. 2022. Shape selection recognition and scattering distribution prediction of adhesion targets in multi-scale dual-energy X-ray images of coal and gangue. International Journal of Coal Preparation and Utilization. DOI: 10.1080/19392699.2022.2122453.
• [7] He et al. 2023 – He, L., Wang, S., Guo, Y., Hu, K., Cheng, G. and Wang, X. 2022. Study of raw coal identification method by dual-energy x-ray and dual-view visible light imaging. International Journal of Coal Preparation and Utilization 43(2), DOI: 10.1080/19392699.2022.2051013.
• [8] Hong, J. 1984. Gray Level-Gradient Cooccurrence Matrix Texture Analysis Method. Acta Automatica Sinica 10(1), pp. 22-25 (in Chinese).
• [9] Hu et al. 2022 – Hu, F., Zhou, M., Yan, P., Liang, Z. and Li, M. 2022. A Bayesian optimal convolutional neural network approach for classification of coal and gangue with multispectral imaging. Optics and Lasers in Engineering 156, DOI: 10.1016/j.optlaseng.2022.107081.
• [10] Kalbasi, M. and Nikmehr, H. 2020. Noise-Robust, Reconfigurable Canny Edge Detection and its Hardware Realization. IEEE ACCESS 99, pp. 39934-39945, DOI: 10.1109/ACCESS.2020.2976860.
• [11] Kazanin et al. 2021 – Kazanin, O., Sidorenko, A. and Drebenstedt, C. 2021. Intensive underground mining technologies: Challenges and prospects for the coal mines in Russia. Acta Montanistica Slovaca 26(1), pp. 60-69, DOI: 10.46544/AMS.v26i1.05.
• [12] Li, J. and Wang, J. 2019. Comprehensive utilization and environmental risks of coal and gangue: A review. Journal of Cleaner Production 239, DOI: 10.1016/j.jclepro.2019.117946.
• [13] Li et al. 2022 – Li, M., He, X., Duan, Y. and Yang, M. 2022. Experimental study on the influence of external factors on image features of coal and gangue. International Journal of Coal Preparation and Utilization 42(9), pp. 2770-2787, DOI: 10.1080/19392699.2021.1901692.
• [14] Luo et al. 2022 – Luo, Q., Wang, S., Li, X. and He, L. 2022. Recognition of coal and gangue based on multi-dimensional gray gradient feature fusion. Energy Sources, Part A: Recovery, Utilization, and Environmental Effects 44(3), pp. 8060-8076, DOI: 10.1080/15567036.2022.2119309.
• [15] Mallick et al. 2014 – Mallick, A., Roy, S., Chaudhuri, S. and Roy, S. 2014. Optimization of Laplace of Gaussian (LoG) filter for enhanced edge detection: A new approach. In Proceedings of the 2014 International Conference on Control, Instrumentation, Energy and Communication (CIEC), pp. 658-661.
• [16] Reddy, K. and Tripathy, D. 2013. Separation of gangue from coal based on histogram thresholding. International Journal of Technology Enhancements and Emerging Engineering Research 1(4), pp. 31-34.
• [17] Robben et al. 2020 – Robben, C., Condori, P., Pinto, A., Machaca, R. and Takala, A. 2020. X-ray-transmission based ore sorting at the San Rafael tin mine. Minerals Engineering 145, DOI: 10.1016/j.mineng.2019.105870.
• [18] Snehamoy, C. 2013. Vision-based rock-type classification of limestone using multi-class support vector machine. Applied intelligence 39(1), pp. 14-27, DOI: 10.1007/s10489-012-0391-7.
• [19] Sun et al. 2021 – Sun, Z., Huang, L. and Jia, R. 2021. Coal and gangue separating robot system based on computer vision. Sensors 21(4), DOI: 10.3390/s21041349.
• [20] Sun et al. 2022 – Sun, Z., Lu, W., Xuan, P., Li, H., Zhang, S., Niu, S. and Jia, R. 2019. Separation of gangue from coal based on supplementary texture by morphology. International Journal of Coal Preparation and Utilization 42(3), pp. 221-237, DOI: 10.1080/19392699.2019.1590346.
• [21] Tripathy, D. and Reddy, K. 2017. Novel Methods for Separation of Gangue from Limestone and Coal using Multispectral and Joint Color-Texture Features. Journal of The Institution of Engineers (India): Series D 98, pp. 109-117, DOI: 10.1007/s40033-015-0106-4.
• [22] Urbanowicz et al. 2018 – Urbanowicz, R., Meeker, M., La Cava, W., Olson, R. and Moore, J. 2018. Relief-based feature selection: Introduction and review. Journal of biomedical informatics 85, pp. 189-203, DOI: 10.1016/j.jbi.2018.07.014.
• [23] Wang et al. 2021 – Wang, X., Wang, S., Guo, Y., Hu, K. and Wang, W. 2021. Recognition of coal and gangue based on dielectric characteristics and geometric constraints under multi factors. Energy Sources, Part A: Recovery, Utilization, and Environmental Effects, DOI: 10.1080/15567036.2021.1968546.
• [24] Varnavskiy et al. 2022 – Varnavskiy, K., Nepsha, F. and Сhen, Q. 2022. The assessment of functional efficiency of technological structure for the coal mine working face–an application of IIIE. Journal of Industrial Information Integration 26, DOI: 10.1016/j.jii.2021.100262.
• [25] Zhang, N. and Liu, C. 2018. Radiation characteristics of natural gamma-ray from coal and gangue for recognition in top coal caving. Scientific Reports 8, DOI: 10.1038/s41598-017-18625-y.
• [26] Zhang et al. 2017 – Zhang, X., Cui, J., Wang, W. and Lin, C. 2017. A study for texture feature extraction of high-resolution satellite images based on a direction measure and gray level co-occurrence matrix fusion algorithm. Sensors 17(7), DOI: 10.3390/s17071474.
• [27] Zhang et al. 2021 – Zhang, J., He, G. and Yang, S. 2021. Controlling water temperature for efficient coal/gangue recognition. Materials Today Chemistry 22, DOI: 10.1016/j.mtchem.2021.100587.
• [28] Zou et al. 2020 – Zou, X., Tan, W., Huang, X., Nan, S., Bai, Y. and Fu, X. 2020. Imaging quality enhancement in binary ghost imaging using the Otsu algorithm. Journal of Optics 22(9), DOI: 10.1088/2040-8986/aba22e.

Uwagi

PL

Opracowanie rekordu ze środków MEiN, umowa nr SONP/SP/546092/2022 w ramach programu "Społeczna odpowiedzialność nauki" - moduł: Popularyzacja nauki i promocja sportu (2022-2023)