Modeling of lime production process using artificial neural network
Author:
Daeichian Abolghasem12ORCID, Shahramfar Rana3, Heidari Elham4ORCID
Affiliation:
1. Department of Electrical Engineering , Faculty of Engineering, Arak University , 38156-8-8349 Arak , Iran 2. Research Institute of Renewable Energy , Arak University , 38156-8-8349 Arak , Iran 3. Department of Electrical Engineering , Payam Institute , Golpayegan , Isfahan , Iran 4. School of Chemical, Petroleum, and Gas Engineering, Iran University of Science and Technology , Tehran , Iran
Abstract
Abstract
Lime is a significant material in many industrial processes, including steelmaking by blast furnace. Lime production through rotary kilns is a standard method in industries, yet it has depreciation, high energy consumption, and environmental pollution. A model of the lime production process can help to not only increase our knowledge and awareness but also can help reduce its disadvantages. This paper presents a black-box model by Artificial Neural Network (ANN) for the lime production process considering pre-heater, rotary kiln, and cooler parameters. To this end, actual data are collected from Zobahan Isfahan Steel Company, Iran, which consists of 746 data obtained in a duration of one year. The proposed model considers 23 input variables, predicting the amount of produced lime as an output variable. The ANN parameters such as number of hidden layers, number of neurons in each layer, activation functions, and training algorithm are optimized. Then, the sensitivity of the optimum model to the input variables is investigated. Top-three input variables are selected on the basis of one-group sensitivity analysis and their interactions are studied. Finally, an ANN model is developed considering the top-three most effective input variables. The mean square error of the proposed models with 23 and 3 inputs are equal to 0.000693 and 0.004061, respectively, which shows a high prediction capability of the two proposed models.
Publisher
Walter de Gruyter GmbH
Subject
Modeling and Simulation,General Chemical Engineering
Reference53 articles.
1. Negi, AS, Faizan, M, Siddharth, DP, Singh, R. Soil stabilization using lime. Int J Innovat Res Sci Eng Technol 2013;2:448–53. 2. Ren, W, Zhou, Z, Jiang, L-M, Hu, D, Qiu, Z, Wei, H, et al.. A cost-effective method for the treatment of reject water from sludge dewatering process using supernatant from sludge lime stabilization. Separ Purif Technol 2015;142:123–8, https://doi.org/10.1016/j.seppur.2014.12.037. 3. Zhang, J, Yao, C, Zheng, P, Zang, L. Synergistic effects of anaerobic digestion from sewage sludge with lime mud. Int J Hydrogen Energy 2017;42:12022–31, https://doi.org/10.1016/j.ijhydene.2017.02.098. 4. Peray, KE, Waddell, JJ. The rotary cement kiln. New York: Edward Arnold; 1986. 5. Fan, X-h., Wang, Y, Chen, X-l. Mathematical models and expert system for grate-kiln process of iron ore oxide pellet production. Part II: rotary kiln process control. J Cent S Univ Technol 2012;19:1724–7, https://doi.org/10.1007/s11771-012-1199-7.
|
|