Design an intelligent calibration technique using optimized GA-ANN for liquid flow control system

Design an intelligent calibration technique using optimized GA-ANN for liquid flow control system

Pijush DuttaAsok Kumar

Research scholar, Mewar University, Rajasthan 213901, India

Department of Electronics & Communication Engineering, GIMT, Nadia741102, India

Department of Electronics & Communication Engineering, Asansol Engineering College, Asansol 713305, India

Corresponding Author Email: 
pijushdutta009@gmail.com
Page: 
449-470
|
DOI: 
https://doi.org/10.3166/JESA.50.449-470
| | | | Citation

OPEN ACCESS

Abstract: 

Designing a highly accurate model for liquid flow process industry and controlling the liquid flow rate from experimental data is an important task for engineers due to its non-linear characteristics. Efficient optimization techniques are essential to accomplish this task. In most of the process control industry flow rate depends on a multiple number of parameters like sensor output, pipe diameter, liquid conductivity, liquid viscosity & liquid density etc. In traditional optimization technique its very time consuming for obtaining the optimum flow rate which is manually controlled in the process. Hence the different computational optimization processes are utilized by using different intelligence techniques. In this paper three different selection of hybrid Genetic Algorithm- Neural network model is proposed & tested against the present liquid flow process. Equations for neural network are being used as non-linear model and these models are optimized using the proposed different selection of Genetic optimization techniques which is based on mimic of the genetic evolution of species that allow the consecutive generations in population to adapt their environment. From the numerical result it is observed that among the three different selection rank selected hybrid Genetic Algorithm- Neural network (GA-ANN) model is better than the other two selections (Tournament & Roulette wheel) in terms of the accuracy (98.42%) of final solutions, minimum absolute error (0.6463), computational time, and stability.

Keywords: 

liquid flow control process, anemometer type flow sensor, modelling, genetic algorithm, neural network model

1. Introduction
2. Flow sensor
3. Experimental setup
4. Proposed methods for modeling and optimization
5. Mathematical description of the problem
6. Results and discussion
7. Conclusions
  References

Amin N. A. S. (2006). Hybrid artificial neural network−genetic algorithm technique for modelling & optimization of plasma reactor. Industrial & Engineering Chemistry Research, Vol. 45, No. 20, pp. 6655-6664. http://dx.doi.org/10.1021/ie060562c 

Bera S. C., Chakraborty B., Kole D. N. (2007). Study of a modified anemometer type flow meter. Sensors & Transducers Journal, Vol. 83, No. 9, September, pp. 1521-1526.

Bera S. C., Roy J. K. (2001). An approach to the design and fabrication of a micro processor based flow meter using resistance and semiconductor probe. IETE Technical Review, Vol. 18, No. 5, pp. 355-360. http://dx.doi.org/10.1080/02564602.2001.11416983

Chaki S., Ghosal S. (2015). A GA–ANN hybrid model for prediction & optimization for CO2 Laser MIG Hybrid welding process. International Journal of Automotive and Mechanical Engineering, Vol. 11, pp. 2458-2470. http://dx.doi.org/10.15282/ijame.11.2015.26.0207

Chau K. W. (2007). Reliability and performance-based design by artificial neural network. Advances in Engineering Software, Vol. 38, No. 3, pp. 145-149. http://dx.doi.org/10.1016/j.advengsoft.2006.09.008

Chen G., Zhu M., Yu H., Li Y. (2007). Application of neural network in image definition recognization. IEEE International Conference on Signal Processing & Communications, pp. 1207-1210. http://dx.doi.org/10.1109/ICSPC.2007.4728542

Cook D. F., Ragsdale C., Major R. (2000). Combining a neural network with a genetic algorithm for process parameter optimization. Engineering Applications of Artificial Intelligence, Vol. 13, No. 4, pp. 391-396. http://dx.doi.org/10.1016/S0952-1976(00)00021-X

De Jong K. A., Spears W. M., Gordon D. F. (1993). Using genetic algorithms for concept learning. Machine Learning, Vol. 13, pp. 161-188. http://dx.doi.org/10.1007/BF00993042

Goldberg E. E. (1989). Genetic algorithm in searching, optimization, and machine learning. Reading MA: Addison-Wesley.

Griva I., Nash S., Sofer A. (2009). Linear and nonlinear optimization, Springer Science.

Grzesiak L., Meganck V., Sobolewski J., Ufnalski B. (2007). Genetic algorithm for parameters optimization of ANN based speed controller. The International Conference on "Computer as a Tool", pp. 1700-1705. http://dx.doi.org/10.1109/EURCON.2007.4400689 

Kulaksiz A. A., Akkaya R. (2012). Training data optimization for ANNs using genetic algorithm to enhance MPPT efficiency of a stand-alone PV system. Turkish Journal of Electrical Engineering & Computer Sciences, Vol. 20, No. 2, pp. 241-254. http://dx.doi.org/10.3906/elk-1101-1051

Leung C., Member C. (1994). A hybrid global learning algorithm based on global search and least squares techniques for back propagation neural network Networks. International Conference on Neural Networks, pp. 1890-1895. http://dx.doi.org/10.1109/ICNN.1997.614187

Moazenzadeh R., Mohammadi B., Shamshirband S., Chau K. (2018). Coupling a firefly algorithm with support vector regression to predict evaporation in Northern Iran. Engineering Applications of Computational Fluid Mechanics, Vol. 12, No. 1, pp. 584-597. http://dx.doi.org/10.1080/19942060.2018.1482476

Moh’d S., Ahmed A. S. (2006). Optimization of hot wire thermal flow sensor based on neural net model. Applied Thermal Engineering, Vol. 26, No. 8-9, pp. 948-955. http://dx.doi.org/10.1016/j.applthermaleng.2005.08.004

Nakawiro W., Erlich I. (2009). A combined GA-ANN strategy for solving optimal power flow with voltage security constraint. Power and Energy Engineering Conference, pp. 1-4. http://dx.doi.org/10.1109/APPEEC.2009.4918036

Sardiñas R. O., Rivas Santana M., Brindis E. A. (2006). Genetic algorithm-based multi-objective optimization of cutting parameters in turning processes. Engineering Applications of Artificial Intelligence, Vol. 19, No. 2, pp. 127. http://dx.doi.org/10.1016/j.engappai.2005.06.007

Satish C. B., Samik M. (2012). Study of a simple linearization technique of a P-N junction type anemometer flow sensor. IEEE Transaction Instrumentation and Measurement, Vol. 61, No. 9, pp. 545-552.

Taormina R., Chau K., Sivakumar B. (2015). Neural network river forecasting through baseflow separation and binary-coded swarm optimization. Journal of Hydrology, Vol. 529, No. 3, pp. 1788-1797. http://dx.doi.org/10.1016/j.jhydrol.2015.08.008

Venkata S. K., Roy B. K. (2012). An intelligent flow measurement technique using ultrasonic flow meter with optimized neural network. International Journal of Control and Automation, Vol. 5, No. 4, pp. 185-196. http://dx.doi.org/10.2316/P.2012.769-033

Wu C. L., Chau K. W. (2011). Rainfall-Runoff modeling using artificial neural network coupled with singular spectrum analysis. Journal of Hydrology, Vol. 399, No. 3-4, pp. http://dx.doi.org/10.1016/j.jhydrol.2011.01.017