Modeling and optimization of activated carbon carbonization process based on support vector machine

• Autorzy: Liu Gangyang , Zhang Chunlong , Dou Dongyang , Wei Yinghua

Identyfikatory

DOI

10.37190/ppmp/133057

• Języki publikacji: EN

Abstrakty

EN

Product prediction and process parameter optimization in the production process of activated carbon are very important for production. It can stabilize product quality and improve the economic efficiency of enterprises. In this paper, three process parameters of a carbonization furnace, namely feeding rate, rotation speed, and carbonization temperature, were adopted to build a quality optimization model for carbonized materials. First, an orthogonal test was designed to obtain the preliminary relationship between the process parameters and the quality indicators of a carbonized material and prepare data for modeling. Then, an improved SVR model was developed to establish the relationship between product quality indicators and process parameters. Finally, through the singlefactor experiments and the Monte Carlo method, the process parameters affecting the quality of a carbonized material were determined and optimized. This showed that a high-quality carbonized material could be obtained with a smaller feeding rate, larger rotation speed, and higher carbonization furnace temperature. The quality of activated carbon reached its maximum when the feeding rate was 1.0 t/h, the rotation speed was 90 r/h, and the temperature was 836°C. It can effectively improve the quality of carbonized materials.

Słowa kluczowe

EN

carbonization process; optimization; modeling; support vector machine

• Wydawca: Oficyna Wydawnicza Politechniki Wrocławskiej
• Czasopismo: Physicochemical Problems of Mineral Processing
• Rocznik: 2021
• Tom: Vol. 57, iss. 2
• Strony: 131--143
• Opis fizyczny: Bibliogr. 35 poz., rys.

Twórcy

autor

Liu Gangyang

• School of Chemical Engineering and Technology, China University of Mining and Technology, Xuzhou 221116, P. R. China

autor

Zhang Chunlong

• School of Chemical Engineering and Technology, China University of Mining and Technology, Xuzhou 221116, P. R. China

autor

Dou Dongyang

• Key Laboratory of Coal Processing and Efficient Utilization of Ministry of Education, China University of Mining and Technology, Xuzhou 221116, P. R. China

autor

Wei Yinghua

• Coal Preparation Center, Ningxia Coal Industry Co., Ltd., Shizuishan 753000, P. R. China

Bibliografia

• ANDRE, H., ALLEMAND, F., KHELF, I., BOURDON, A., REMOND, D., 2020. Improving the monitoring indicators of a variable speed wind turbine using support vector regression. Appl. Acoust. 166, UNSP 107350.
• AWORN, A., THIRAVETYAN, P., NAKBANPOTE, W., 2008. Preparation and characteristics of agricultural waste activated carbon by physical activation having micro- and mesopores. Journal of Analytical and Applied Pyrolysis 82, 279–285.
• CORTES, C., VAPNIK, V., 1995. Support-vector networks. Mach Learn 20, 273–297.
• DOU, D., LIU, G., YANG, J., 2019a. Particle size-included partition curve model of dense medium cyclones. International Journal of Coal Preparation and Utilization 1–15. https://doi.org/10.1080/19392699.2019.1628026
• DOU, D., QIU, Z., YANG, J., 2020a. Parameter optimization of an industrial water injection hydrocyclone in the Taixi coal preparation plant. International Journal of Coal Preparation and Utilization 1–9.
• DOU, D., WU, W., YANG, J., ZHANG, Y., 2019b. Classification of coal and gangue under multiple surface conditions via machine vision and relief-SVM. Powder Technology 356, 1024–1028.
• DOU, D., YANG, J., LIU, J., ZHANG, Z., ZHANG, H., 2015. Soft-Sensor Modeling for Separation Performance of Dense-Medium Cyclone by Field Data. International Journal of Coal Preparation and Utilization 35, 155–164.
• DOU, D., ZHOU, D., YANG, J., 2020b. A new partition curve model of dense-medium cyclone based on process parameters. International Journal of Coal Preparation and Utilization 40, 459–472.
• DOU, D., ZHOU, D., YANG, J., ZHANG, Y., 2020c. Coal and gangue recognition under four operating conditions by using image analysis and Relief-SVM. International Journal of Coal Preparation and Utilization 40, 473–482.
• DOU, D., ZHOU, S., 2016. Comparison of four direct classification methods for intelligent fault diagnosis of rotating machinery. Applied Soft Computing 46, 459–468.
• JIANG, W., XING, X., LI, S., ZHANG, X., WANG, W., 2019. Synthesis, characterization and machine learning based performance prediction of straw activated carbon. Journal of Cleaner Production 212, 1210–1223.
• KALHORI, H., BAGHERPOUR, R., 2019. Prediction of shotcrete compressive strength using Intelligent Methods; Neural Network and Support Vector Regression. Cement Wapno Beton 24, 126.
• KEERTHI, S.S., LIN, C.-J., 2003. Asymptotic Behaviors of Support Vector Machines with Gaussian Kernel. Neural Computation 15, 1667–1689.
• KHOSLA, E., DHARAVATH, R., PRIYA, R., 2020. Crop yield prediction using aggregated rainfall-based modular artificial neural networks and support vector regression. Environ. Dev. Sustain. 22, 5687–5708.
• LIAO, M., KELLEY, S., YAO, Y., 2020. Generating Energy and Greenhouse Gas Inventory Data of Activated Carbon Production Using Machine Learning and Kinetic Based Process Simulation. ACS Sustainable Chem. Eng. 8, 1252–1261.
• LIAO, M., KELLEY, S.S., YAO, Y., 2019. Artificial neural network based modeling for the prediction of yield and surface area of activated carbon from biomass. Biofuels, Bioprod. Bioref. 13, 1015–1027. https://doi.org/10.1002/bbb.1991
• LINARES-SOLANO, A., MARTÍN-GULLON, I., SALINAS-MARTÍNEZ DE LECEA, C., SERRANO-TALAVERA, B., 2000. Activated carbons from bituminous coal: effect of mineral matter content. Fuel 79, 635–643.
• LOZANO-CASTELLÓ, D., LILLO-RÓDENAS, M.A., CAZORLA-AMORÓS, D., LINARES-SOLANO, A., 2001. Preparation of activated carbons from Spanish anthracite: I. Activation by KOH. Carbon 39, 741–749.
• MIANOWSKI, A., OWCZAREK, M., MARECKA, A., 2007. Surface Area of Activated Carbon Determined by the Iodine Adsorption Number. Energy Sources, Part A: Recovery, Utilization, and Environmental Effects 29, 839–850.
• NUNES, C.A., GUERREIRO, M.C., 2011. Estimation of surface area and pore volume of activated carbons by methylene blue and iodine numbers. Quím. Nova 34, 472–476.
• OSUNA, E., FREUND, R., GIROSI, F., 1997. An improved training algorithm for support vector machines, in: Neural Networks for Signal Processing VII. Proceedings of the 1997 IEEE Signal Processing Society Workshop. Presented at the Neural Networks for Signal Processing VII. Proceedings of the 1997 IEEE Signal Processing Society Workshop, pp. 276–285.
• QIU, Z., DOU, D., ZHOU, D., YANG, J., 2020. On-line prediction of clean coal ash content based on image analysis. Measurement 108663.
• REN, Y., CAO, G., ZHU, X., 2005. Predictive control of proton exchange membrane fuel cell (PEMFC) based on support vector regression machine, in: 2005 International Conference on Machine Learning and Cybernetics. Presented at the 2005 International Conference on Machine Learning and Cybernetics, pp. 4028-4031, Vol. 7.
• SHAMSUDDIN, M.S., YUSOFF, N.R.N., SULAIMAN, M.A., 2016. Synthesis and Characterization of Activated Carbon Produced from Kenaf Core Fiber Using H3PO4 Activation. Procedia Chemistry 19, 558–565.
• SMOLA, A.J., SCHÖLKOPF, B., 2004. A tutorial on support vector regression. Statistics and Computing 14, 199–222.
• SOLGI, M., NAJIB, T., AHMADNEJAD, S., NASERNEJAD, B., 2017. Synthesis and characterization of novel activated carbon from Medlar seed for chromium removal: Experimental analysis and modeling with artificial neural network and support vector regression. Resource-Efficient Technologies 3, 236–248.
• VAPNIK, V., 2013. The Nature of Statistical Learning Theory. Springer Science & Business Media.
• VAPNIK, V., LEVIN, E., CUN, Y.L., 1994. Measuring the VC-Dimension of a Learning Machine. Neural Computation 6, 851–876.
• WU, X., HE, S., 2004. Production and Development of Coal-based Activated Carbon. Coal Chemical Industry 37–39.
• XIE, Q., BIAN, B., 2002. Principles of control over coal carbonization its application in preparation of activated carbon. Xuzhou: China University of Mining and Technology Press.
• XIE, Q., CHEN, Q., 1996. Approaches to improve the quality of activated carbon from coal. Coal Conversion 46–52.
• XIE, Q., ZHANG, S., 2002. Theoretical foundation of preparation of high specific surface area coal-based activated carbon. Carbon Science and Technology 12, 24–29.
• XUE, Y., DOU, D., YANG, J., 2020. Multi-fault diagnosis of rotating machinery based on deep convolution neural network and support vector machine. Measurement 156, 107571.
• YAN, Q., WANG, G., 2009. Prediction Model of Alga’s Growth Based on Support Vector Regression, in: 2009 International Conference on Environmental Science and Information Application Technology. Presented at the 2009 International Conference on Environmental Science and Information Application Technology, pp. 673–675.
• ZHAO, C., JIANG, H., GUO, X., 2009. Application of Support vector machine in small sample prediction. Oil-Gas Field Surface Engineering 28, 21–23.

Uwagi

Opracowanie rekordu ze środków MNiSW, umowa Nr 461252 w ramach programu "Społeczna odpowiedzialność nauki" - moduł: Popularyzacja nauki i promocja sportu (2021).