Improvement of a cement rotary kiln performance using artificial neural network
- PDF / 3,030,087 Bytes
- 12 Pages / 595.276 x 790.866 pts Page_size
- 49 Downloads / 170 Views
ORIGINAL RESEARCH
Improvement of a cement rotary kiln performance using artificial neural network Hassan Aghdasinia1 · Seyed Sharif Hosseini1 · Jafar Hamedi1,2 Received: 23 April 2020 / Accepted: 27 August 2020 © Springer-Verlag GmbH Germany, part of Springer Nature 2020
Abstract In order to investigate the effect of parameters and system optimization, the processes must be modeled first. Cement rotary kiln systems are complex because of non-linear, time invariant and full of behavioral uncertainty where the mathematical modeling of the plant is impossible. Artificial neural network (ANN) is one of the best tools for improving the performance of such processes. In this study, the operational data from a cement factory are gathered and the relationships between variables analyzed via using ANN via MATLAB toolbox. ANN proposed 2.7 and 865 rpm for kiln and fan motor speed respectively and 4599.7 Ncm/h for total grate flowrate as optimum values. This research shows that using ANN for improving the performance of rotary kiln is effective and by optimization of operational parameters through ANN and applying them in the rotary kiln, higher production in the cement industry is accessible. Keywords Cement rotary kiln · Process control · Artificial neural network · Optimization
1 Introduction The cement plant is one of the most energy-intensive industries, and the rotary kiln consumes significant share of this energy and the amount of consumed fuel has a direct effect on the finished product price (Radwan 2012). The cement plants consume high quantities of power which shape approximately 40% of the total production cost (Chatterjee and Sui 2019; Zanoli et al. 2016b). This is why efficient energy utilization has always been a matter of priority in the cement industry. Hence, in order to manufacture more products at a lower price, the optimization and improvement of system performance has excellent potential. Over the past few decades, with the addition of new mills, more preheating towers or replacement of old furnaces with new ones, production of some cement plants has been increased. These kinds of changes require a lot of time, cost, and the payback period in capital budgeting is high. But it is also possible to reduce system energy consumption and improve
* Hassan Aghdasinia [email protected]; [email protected] 1
Faculty of Chemical and Petroleum Engineering, University of Tabriz, Tabriz, Iran
Ardebil Cement Factory, Ardebil, Iran
2
performance and efficiency by optimizing operation parameters. This approach requires less capital, has less risk compared to other approaches, and operates in a shorter time (Biernacki 2017; Lu et al. 2018; Pickl et al. 2019). Today nature-inspired and intelligent techniques in solving complex problems have tremendous capacity (Drewek-Ossowicka et al. 2020). The artificial neural network (ANN) is one of the most popular and effective one of these approaches, whose role in solving difficulties can never be ignored (Nikoo et al. 2015). ANNs construct of simple
Data Loading...
