Indian Journal of Science and Technology

Open Access Open Access  Restricted Access Subscription Access

Improvement the Performance of Drum Boiler in Thermal Power Plant using Hybrid Model Through the Adaptive Neuro-Fuzzy Controller


Affiliations
1 Electromechanical Engineering Department, University of Technology, Baghdad, Iran, Islamic Republic of
 

Objectives: This Study tackles how the process of Neuro-fuzzy control that allows observing and controlling the steam pressure and temperature than conventional PI at drum boiler in the power station. It is used to increase the thermal efficiency of the boiler while it has helped to maintain the Turbine not to reach wet vapor which is considered the best method, more accurate compared to the basic conventional method of PI. Methods/Statistical Analysis: The method of hybrid control was used by Neuro-fuzzy in model design simulation by the Matlab program, which led to data training and testing. It is compared with conventional method of PI (Rise Time (sec) – Settling Time (sec) – Overshoot (%) Peak – Peak Time (sec)) by tracking the temperature, steam pressure and to reach the degree of vapor in less time and accuracy. Findings: ANFIS tracks the path of parameters (Temperature – Pressure) more accurately and superior than the traditional method PID and this leads to enhanced, improved and more thermal efficient performance in a drum of the boiler. It shows that the ratio of the overshoot in the PI is 15.68 for the temperature while in the steam for pressure 13.22 bars either in Neuro-fuzzy is in both parameters zero. Thus, ANFIS seems to be more accurate in tracking and shorter time and the absence of the ratio Overshoot compared to the basic conventional method of PI. Application/Improvements: Strategy is presented in the promotion and development of control of drum steam boilers through the simulations model, which was constructed using the hybrid theory and compared to the main theory PI as shown in the results.
User

  • Lucian M, Iosif O, Catalin D, DorinI. Neuro-fuzzy models of thermoelectric power station installations. International Conference on Computational Intelligence for Modeling, Control and Automation and International Conference on Intelligent Agents, Web Technologies and Internet Commerce; 2005. p. 899–904.

  • Nurnberger A, Nauck D, Kruse R, Merz L. A Neuro-fuzzy development tool for fuzzy controllers under MATLAB/ SIMULINK. Proceedings 5th European Congress on Intelligent Techniques and Soft Computing; 1997.

  • Kumar R, Kaushik S, Kumar A. Energy and exergy analysis of non-reheat thermal power plant. Proceedings of International Conference on Energy and Environment; 2009. p. 608–11.

  • Horikawa S, Furuhashi T, Uchikawa Y. A new type of fuzzy neural network for linguistic fuzzy modeling. Proceedings 2nd International Conference on Fuzzy Logic and Neural Networks; 1992. p. 1053–6.

  • Culliere T, Corrieu J. Neuro-fuzzy modeling of nonlinear systems for control purposes. Proceedings IEEE International Conference on Fuzzy Systems; 1995. p. 2009– 16. Crossref

  • Jang SRJ. ANFIS: Adaptive network based fuzzy inference system. IEEE Trans on Systems, Man and Cybernetics. 1993; 23(3):665–85. Crossref

  • Jang J. Neuro-fuzzy modeling: Architecture, Analyses and Applications. Berkeley, USA: University of California; 1992. p. 1-310.

  • Jang J, Sun C. Neuro-fuzzy modelling and control. Proceedings IEEE. 1995; 83(3):378–406. Crossref

  • Jang J, Sun C, Mizutani E. Neuro-Fuzzy and Soft Computing - A Computational Approach to Learning and Machine Intelligence. New Jersey: Prentice Hall; 1997. p. 1-640.

  • Ying B, Dali W. Advanced of fuzzy logic technologies in industrial application. Springer; 2006.

  • Rabah AC. Improved Controller for a thermal power plant [Thesis]. Institute de Genie Electrique; 2012.

  • Math Works. Fuzzy Logic Toolbox User’s Guide. The Math Works, Technical Report. 2014.


Abstract Views: 209

PDF Views: 0




  • Improvement the Performance of Drum Boiler in Thermal Power Plant using Hybrid Model Through the Adaptive Neuro-Fuzzy Controller

Abstract Views: 209  |  PDF Views: 0

Authors

Khalid Faisal Sultan
Electromechanical Engineering Department, University of Technology, Baghdad, Iran, Islamic Republic of
Hosham Salim Anead
Electromechanical Engineering Department, University of Technology, Baghdad, Iran, Islamic Republic of
Malak Moneeryounis
Electromechanical Engineering Department, University of Technology, Baghdad, Iran, Islamic Republic of

Abstract


Objectives: This Study tackles how the process of Neuro-fuzzy control that allows observing and controlling the steam pressure and temperature than conventional PI at drum boiler in the power station. It is used to increase the thermal efficiency of the boiler while it has helped to maintain the Turbine not to reach wet vapor which is considered the best method, more accurate compared to the basic conventional method of PI. Methods/Statistical Analysis: The method of hybrid control was used by Neuro-fuzzy in model design simulation by the Matlab program, which led to data training and testing. It is compared with conventional method of PI (Rise Time (sec) – Settling Time (sec) – Overshoot (%) Peak – Peak Time (sec)) by tracking the temperature, steam pressure and to reach the degree of vapor in less time and accuracy. Findings: ANFIS tracks the path of parameters (Temperature – Pressure) more accurately and superior than the traditional method PID and this leads to enhanced, improved and more thermal efficient performance in a drum of the boiler. It shows that the ratio of the overshoot in the PI is 15.68 for the temperature while in the steam for pressure 13.22 bars either in Neuro-fuzzy is in both parameters zero. Thus, ANFIS seems to be more accurate in tracking and shorter time and the absence of the ratio Overshoot compared to the basic conventional method of PI. Application/Improvements: Strategy is presented in the promotion and development of control of drum steam boilers through the simulations model, which was constructed using the hybrid theory and compared to the main theory PI as shown in the results.

References





DOI: https://doi.org/10.17485/ijst%2F2018%2Fv11i22%2F125191