Design of a neural network controller for the electrode control system in the electric arc furnace

Design of a neural network controller for the electrode control system in the electric arc furnace

Mina KoochakiMehri Lotfi 

Department of Electrical Engineering Khomeinishahr Branch, Islamic Azad University, Khomeinishahr/Isfahan, Iran

Corresponding Author Email: 
mina.koochaki@iaukhsh.ac.ir
Page: 
299-311
|
DOI: 
https://doi.org/10.3166/JESA.50.299-311
| |
Published: 
31 August 2017
| Citation

OPEN ACCESS

Abstract: 

The significance of steel making in the modern world has made the development of electric arc furnaces one of the top priorities in researches. The goal of this thesis is to design an artificial neural network in order to optimize the function of electric arc furnaces. At first the current loop of electrode control system has been simulated in MATLAB Simulink for Cassie-Mayr mathematical model of electric arc furnace. In this case, the input of the system is constant impedance set-points which are implemented by operators. So, change of conditions and output of the furnace do not affect the system input. Then, by using the output data from two different steel complexes of Iran, an artificial neural network has been designed for simulating a compensator system. Considering the RMS data achieved by the transformers, the RMS of input current is used as input current of EAF. By implementing this system on the current loop as the external loop, which includes furnace related inputs, a coefficient factor is created. By this factor, the constant impedances are corrected and optimized. In addition, it is observed that the impedance error of the new system significantly decreased compared to the impedance error of the simulation of the current system.

Keywords: 

electric arc furnace (EAF), electrode control system, neural energy control (NEC)

1. Introduction
2. Electric arc furnace, mathematical model and simulation
3. Artificial neural network, design and simulation of NEC
4. Simulation of the control loop
5. Conclusion
  References

Awagan G. R., Thosar A. G. (2016). Mathematical modeling of electric arc furnace to study the flicker. International Journal of Scientific & Engineering Research, Vol. 7, No. 5, pp. 684-695. 

Cano-Plata E. A., Ustariz-Frfan A. J., Soto-Marin O. J. (2015). Electric arc furnace model in distribution systems. IEEE Transactions on Industry Applications, Vol. 51, No. 5, pp. 4313-4320. 

Chang G. W., Chen C. I., and. Liu Y. J. (2010). A neural-network-based method of modeling electric arc furnace load for power engineering study. IEEE Transactions on Power Systems, Vol. 25, No. 1, pp. 138-146. http://dx.doi.org/10.1109/TPWRS.2009.2036711

Guan P., Li J. C., He L. X. (2009). Direct adaptive fuzzy sliding mode control of arc furnace electrode regulator system. Chinese Control & Decision Conference, pp. 2776-2781. http://dx.doi.org/10.1109/CCDC.2009.5194960 

Wang H. J., Li Y. W., Yue Y. J. (2011). Application of BP neural network intelligent PID controller based on GA in electrode regulator systems of electric arc furnace. 2011 IEEE 3rd Int. Conf. Commun. Softw. Networks. ICCSN 2011, pp. 198-202. http://dx.doi.org/10.1109/ICCSN.2011.6014422

Ismail M. J., Ibrahim R., and Ismail I. (2011). Development of neural network prediction model of energy consumption. Gas, Vol. 1, No. 1, pp. 0–1. 

Janabi-Sharifi F. and Jorjani G. (2009). An adaptive system for modelling and simulation of electrical arc furnaces. Control Engineering Practice, Vol. 17, No. 10, pp. 1202-1219. http://dx.doi.org/10.1016/j.conengprac.2009.05.006

Kiyoumarsi A., Ataei M. (2011). Effects of electrical, magnetic, and thermal parameters on refractory materials corrosion on the walls of arc furnaces. Technical report, Mobarakeh Steel Company. 

Li L., Mao Z. Z. (2012). Neurocomputing. A direct adaptive controller for EAF electrode regulator system using neural networks, Neurocomputing, Vol. 82, pp. 91-98. http://dx.doi.org/10.1016/j.neucom.2011.10.020

Moghadasian M., Alenasser E. (2011). Modelling and artificial intelligence-based control of electrode system for an electric arc furnace. Journal of Electromagnetic Analysis and Applications, Vol. 3, No. 2, Article ID: 4123. http://dx.doi.org/10.4236/jemaa.2011.32009

Mokhtari H., Hejri M. (2002). A new three phase time-domain model for electric arc furnaces using MATLAB. IEEE/PES Transmission and Distribution Conference and Exhibition, Vol. 3, No. i, pp. 2078-2083. http://dx.doi.org/10.1109/TDC.2002.1177781

Samet H., Ghanbari T., Ghaisari J. (2015). Maximum performance of electric arc furnace by optimal setting of the series reactor and transformer taps using a nonlinear model. IEEE Transactions on Power Delivery, Vol. 30, No. 2, pp. 764-772. http://dx.doi.org/10.1109/TPWRD.2014.2336693

Seker M., Memmedov A. (2014). Investigation of voltage quality in electric arc furnace with Matlab/Simulink. Int. J. Eng. Tech. Res., Vol. 2, No. 11, pp. 274-284.

SIMELT. (2006). Operation Manual AC/NEC, pp. 1-49.

Zhao H., Tang W., Yue Y. (2010). Simulations on harmonic analysis of arc furnace electrical arc model. 2010 2nd International Conference on Information Engineering and Computer Science. http://dx.doi.org/10.1109/ICIECS.2010.5678403

Zheng T., Makram E. (2000). IEEE Trans. power Deliv. An adaptive arc furnace model.