Current Science

Open Access Open Access  Restricted Access Subscription Access

Optimization Algorithm-Based Elman Neural Network Controller for Continuous Stirred Tank Reactor Process Model


Affiliations
1 Department of Electrical and Electronics Engineering, KPR Institute of Engineering and Technology, Coimbatore 641 407, India
 

A continuous stirred tank reactor (CSTR) is a standout nonlinear system among the most essential units of chemical industries. In this article, an Elman neural network is designed to analyse the characteristics of nonlinear behaviour of the CSTR system. The data generated employing the state-space model of CSTR are used to train the designed Elman neural network controller and the controller parameters are optimally tuned by the proposed hybrid swarm intelligencebased optimization algorithm. Two different hybridizations have been developed, including DPSO, DGSA and hybrid DPSO–DGSA and successfully employed in controller tuning. The significance of the proposed controller is validated by a comparative analysis made with conventional methods and the performance is experimentally demonstrated using MATLAB software.

Keywords

Continuous Stirred Tank Reactor, Neural Network Controller, Nonlinear Behaviour, Optimization Algorithm, Process Control.
User
Notifications
Font Size

  • Baruah, S. and Dewan, L., A comparative study of PID based temperature control of CSTR using genetic algorithm and particle swarm optimization. In International Conference on Emerging Trends in Computing and Communication Technologies (ICETCCT), Dehradun, India, 2017, pp. 1–6; doi:10.1109/ICETCCT.2017.8280312.

  • Babushanmugham, S., Srinivasan, D. S. and Giriraj Kumar, S. M., Temperature control of a non-linear process using genetic algorithm. Int. J. Curr. Eng. Technol., 2017, 7(2), 585–589.

  • Salahshour, E., Malekzadeh, M., Gordillo, F. and Ghasemi, J., Quantum neural network-based intelligent controller design for CSTR using modified particle swarm optimization algorithm. Trans. Inst. Meas. Control, 2019, 41(2), 392–404.

  • Saini, P., Kumar, R., Sharma, P. and Rajput, N., Design and comparative analysis of controllers for continuous stirred tank reactor (CSTR). In Proceeding of International Conference on Intelligent Communication, Control and Devices, Springer, Singapore, 2017, pp. 351–365.

  • So, G. B. and Jin, G. G., Fuzzy-based nonlinear PID controller and its application to CSTR. Kor. J. Chem. Eng., 2018, 35(4), 819– 825.

  • Suvire, R. B., Serrano, M. E., Vega, J. R., Ortiz, O. A. and Scaglia, G. J. E., Nonlinear Controller for Trajectory Tracking of a Continuous Stirred Tank Reactor. CEAI, 2017, vol. 19, No. 4, pp. 112–121.

  • Bingi, K., Ibrahim, R., Karsiti, M. N. and Hassan, S. M., Fuzzy gain scheduled set-point weighted PID controller for unstable CSTR systems. In IEEE International Conference on Signal and Image Processing Applications (ICSIPA), IEEE, 2017, pp. 289–293.

  • Mungale, N. R., Upadhyay, A. and Pandian, B. J., Self-tuning regulator for an interacting CSTR process. In IOP Conference Series: Materials Science and Engineering, IOP Publishing, 2017, vol. 263, No. 5, p. 052012.

  • Feng, J., Cao, L., Ma, L., Zhao, D. and Spurgeon, S. K., Modelfree adaptive sliding mode control for continuous stirred tank reactor. In 37th Chinese Control Conference (CCC), IEEE, 2018, pp. 3035–3040.

  • Tripathi, S., Kaur, G. G. and Singla, S. G., Design of Intelligent Controller for Isothermal Continuous Stirred Tank Reactor System, 2017; http://tudr.thapar.edu:8080/jspui/bitstream/10266/4555/1/final_report_tripathi_done.pdf

  • Kavyarasan, K. and Bagyaveereswaran, V., Tuning of PID controller using optimization techniques for a MIMO process. IOP Conf. Ser.: Mater. Sci. Eng., 2017, 052019.

  • Luning, M., Ynag Xiao, Zhao Dong-ya and Spurgeon, S., Disturbance observer based sliding mode control for a continuous stirred tank reactor (CSTR). 36th Chinese Control Conference (CCC), 2017, pp. 3748–3753.

  • Taieb, A., Soltani, M. and Chaari, A., Parameter optimization of MIMO fuzzy optimal model predictive control by APSO. Complexity, 2017, 11; https://doi.org/10.1155/2017/5813192

  • Kantha, A. S., Utkarsh, A. and Jatoth, R. K., Hybrid genetic algorithmswarm intelligence-based tuning of temperature controller for continuously stirred tank reactor. Int. J. Model., Identif. Control, 25(3), 239–248.

  • Darius, E. M. and Sivagamasundari, D. S., Design and implementation of controllers for a CSTR process. Int. J. Emerg. Technol. Comput. Sci. Electron., 2016, 23(1), 175–183.

  • Kumar, S. S. and Shreesha, C., Design of robust PID controller for a CSTR plant with interval parametric uncertainty using Kharitonov theorem. In Computation of Power, Energy Information and Communication (ICCPEIC), International Conference on IEEE, 2016, pp. 430–433.

  • Saini, P., Gaba, S. K., Rajput, N. and Aggarwal, A., Design and analysis of controllers for continous stirred tank reactor (CSTR).

  • In 3rd International Conference on Computing for Sustainable Global Development (INDIACom), IEEE, 2016, pp. 2778–2784.

  • Sharma, R. S., Dewan, L. and Chatterji, S., Neural network-based fault diagnosis in CSTR. Leonardo Electron. J. Pract. Technol., 2018, 32, 193–214.

  • Han, Z., Cheng, B., Wang, C. and Yang, W., Identification of CSTR using extreme learning machine based Hammerstein– Wiener model. In Control Science and Systems Engineering (ICCSSE). 3rd IEEE International Conference on IEEE, 2017, pp. 733–736.

  • Tronci, S. and Baratti, R., A gain-scheduling PI control based on neural networks. Complexity, 2017, 8; https://doi.org/10.1155/2017/9241254.

  • Wong, W. C., Chee, E., Li, J. and Wang, X., Recurrent neural network-based model predictive control for continuous pharmaceutical manufacturing. Mathematics, 2018, 6(11), 242.

  • Sudhanan, R. M. and Poongodi, P., Comparative analysis of various control strategies for a nonlinear CSTR system. Int. J. Nonlinear Sci. Numer. Simul., 2017, 18(3–4), 269–276.

  • Bzioui, S. and Channa, R., Observer based tracking control for the isothermal CSTR. In International Conference on Control, Automation and Information Sciences (ICCAIS), IEEE, 2018, pp. 102–106.

  • Lin, W. M. and Hong, C. M., A new Elman neural network-based control algorithm for adjustable-pitch variable-speed wind-energy conversion systems. IEEE Trans. Power Electron., 2010, 26(2), 473–481.

  • Kennedy, J. and Eberhart, R. C., A discrete binary version of the particle swarm algorithm. Systems, Man, Cybernatics, IEEE International Conference on Computational Cybernetics and Simulation, 1997, vol. 5, pp. 4104–4108.

  • Rashedi, E., Nezamabadi-Pour, H. and Saryazdi, S., GSA: a gravitational search algorithm. Inf. Sci., 2009, 179(13), 2232–2248.

  • Gnana Sheela, K. and Deepa, S. N., Review on methods to fix number of hidden neurons in neural networks. Math. Prob. Eng., 2013, 11; https://doi.org/10.1155/2013/425740

  • Sundari, S. and Nachiappan, A., Design of optimal linear quadratic regulator for the stabilization of continuous stirred tank reactor (CSTR) process. Int. J. Pure Appl. Math., 2018, 118(24), 1–19.

  • Campos, J., Jaramillo, S., Morales, L., Camacho, O. and Chavez, D., PD+ I fuzzy controller optimized by PSO applied to a variable dead time process. In IEEE Third Ecuador Technical Chapters Meeting (ETCM), IEEE, 2018, pp. 1–6.


Abstract Views: 183

PDF Views: 77




  • Optimization Algorithm-Based Elman Neural Network Controller for Continuous Stirred Tank Reactor Process Model

Abstract Views: 183  |  PDF Views: 77

Authors

I. Baranilingesan
Department of Electrical and Electronics Engineering, KPR Institute of Engineering and Technology, Coimbatore 641 407, India

Abstract


A continuous stirred tank reactor (CSTR) is a standout nonlinear system among the most essential units of chemical industries. In this article, an Elman neural network is designed to analyse the characteristics of nonlinear behaviour of the CSTR system. The data generated employing the state-space model of CSTR are used to train the designed Elman neural network controller and the controller parameters are optimally tuned by the proposed hybrid swarm intelligencebased optimization algorithm. Two different hybridizations have been developed, including DPSO, DGSA and hybrid DPSO–DGSA and successfully employed in controller tuning. The significance of the proposed controller is validated by a comparative analysis made with conventional methods and the performance is experimentally demonstrated using MATLAB software.

Keywords


Continuous Stirred Tank Reactor, Neural Network Controller, Nonlinear Behaviour, Optimization Algorithm, Process Control.

References





DOI: https://doi.org/10.18520/cs%2Fv120%2Fi8%2F1324-1333