Possibilities of Application of Computational Intelligence in Monitoring of Heat Production and Supply

Abstract:

The article deals with on-line monitoring of heat sources with application of predictive system equipped with computational intelligence. In particular, an emphasis is given especially on efficiency, optimization of operation, predictability, and synergistic effects. The operation effectiveness will be evaluated from several perspectives such as the thermal properties of the objects, characteristics and properties of resources, and internal air quality. The proposed system based on the analytical/static approaches (e.g. heat loss models of heated objects) and applying the techniques of computational intelligence (e.g. artificial neural networks) creates a dynamic environment that can predict the amount of heat delivered not only on the basis of the energy requirements for the thermal balance of the heated objects and the current weather forecast, but the use of the data base and universal approximators in the field of computational intelligence on the behavior of objects in different operating conditions.

• Periodical: Key Engineering Materials (Volume 669)
• Pages: 560-567
• DOI: https://doi.org/10.4028/www.scientific.net/KEM.669.560
• Online since: October 2015
• Authors: Ivan Čorný*
• Keywords: Computational Intelligence, Heat Production, Heat Supply, Monitoring

References

[1] R. Eberhart, Y. Shi, Evolving Artificial Neural Networks, in: Proceedings of the International Conference on Neural Networks and Brain, 1998, pp. PL5–PL13.

[2] R. Eberhart, Y. Shi, Computational Intelligence Concepts to Implementations, 1st ed., Morgan Kaufmann/Elsevier, (2007).

[3] L. Gustavsson, A. Joelsson, Life cycle primary energy analysis of residential buildings, Energy and Buildings 42 (2010) 210–220.

DOI: 10.1016/j.enbuild.2009.08.017

[4] J. Jurko, A. Panda, M. Behún, Prediction of a new form of the cutting tool according to achieve the desired surface quality, Applied Mechanics and Materials 268 (2013) 473-476.

DOI: 10.4028/www.scientific.net/amm.268-270.473

[5] A. Hošovský et al., Model-based Evolution of a Fast Hybrid Fuzzy Adaptive Controller for a Pneumatic Muscle Actuator, International Journal of Advanced Robotic Systems 56 (2012) 1-11.

DOI: 10.5772/50347

[6] L. Straka, Operational Reliability of Mechatronic Equipment Based on Pneumatic Artificial Muscle, Applied Mechanics and Materials 460 (2014) 41-48.

DOI: 10.4028/www.scientific.net/amm.460.41

[7] B. Xing, W. -J. Gao, Innovative Computational Intelligence: A Rough Guide to 134 Clever Algorithms, Springer, Switzerland, (2014).

[8] M. Rimár, M. Fedák, Š. Kuna, Equation Model of Stabilization of Low Damped Astatic Systems, Applied Mechanics and Materials 415 (2013) 427-430.

DOI: 10.4028/www.scientific.net/amm.415.427

[9] T. Krenický, P. Jacko, Simultaneous Temperature Monitoring Using Virtualization, in: Scientific Papers: Operation and Diagnostics of Machines and Production Systems Operational States, RAM-Verlag, Lüdenscheid, 2009, pp.58-62.

[10] J. Wang et al., Computational Intelligence in Manufacturing Handbook, Boca Raton: CRC Press LLC, (2001).

[11] M. Rimár et al., Adaptive rejection filter for the drives stabilization of pressure die casting machines, Advances in Mechanical Engineering (2014) ID 453724, pp.1-10.

DOI: 10.1155/2014/453724

[12] L. Bičejová, S. Fabian, Analysis of technological head working pressure, tilt angle and shift impact to its vibrations using AWJ technology, Applied Mechanics and Materials 616 (2014) 159-166.

DOI: 10.4028/www.scientific.net/amm.616.159

[13] J. Piteľ, J. Mižák, Computational Intelligence and Low Cost Sensors in Biomass Combustion Process, in: Proceedings of the 2013 IEEE Symposium Series on Computational Intelligence (SSCI): 2013 IEEE Symposium on Computational Intelligence in Control and Automation (CICA), Singapore, April 16-19, 2013, IEEE, Singapore, 2013, pp.165-168.

DOI: 10.1109/cica.2013.6611681

[14] J. Mižáková, J. Piteľ, S. Hrehová, Some Simulation Results of Heat Transfer through the Wall Model, International Journal of Mathematical Models and Methods in Applied Sciences 8 (2014) 1-8.

[15] J. Piteľ, J. Mižáková, A. Hošovský, Biomass Combustion Control and Stabilization Using Low-Cost Sensors, Advances in Mechanical Engineering 5 (2013) ID 685157.

DOI: 10.1155/2013/685157

[16] I. Čorný, M. Fedák, M. Rimár, Chilled Ceiling Adaptive Control with Application of Parameters Gained from the Chilled Ceiling System Proposal Algorithm, Applied Mechanics and Materials 616 (2014) 317-324.

DOI: 10.4028/www.scientific.net/amm.616.317

[17] J. Boržíková, J. Mižák, J. Piteľ, Monitoring of Operational States of Biomass Combustion Process, Applied Mechanics and Materials 308 (2013) 153-158.

DOI: 10.4028/www.scientific.net/amm.308.153

[18] J. Piteľ, J Mižák, Cost Effective Biomass Combustion Process Control, in: Proceedings of the 8th PP&PSC (Power Plant and Power System Control) IFAC Symposium, Toulouse, France, September 02 – 05, 2012, 2012, pp.616-620.

DOI: 10.3182/20120902-4-fr-2032.00108

[19] V. Plaček, B. Šulc, S. Vrána, J. Hrdlička, J. Piteľ, Investigation in Control of Small-scale Biomass Boilers, in: Proceedings of the 2011 12th International Carpathian Control Conference (ICCC), Velké Karlovice, Czech Republic, 25 – 28 May 2011, IEEE, Ostrava, 2011, p.312.

DOI: 10.1109/carpathiancc.2011.5945869

[20] A. Hošovský, K. Židek, C. Oswald, Hybridized GA-optimization of Neural Dynamic Model for Nonlinear Process, in: Proceedings of the 13th International Carpathian Control Conference (ICCC 2012), Podbanské, Slovak Republic, IEEE, 2012, p.227 – 232.

DOI: 10.1109/carpathiancc.2012.6228644

[21] L. Straka, I. Čorný, J. Boržíková, Analysis of heat-affected zone depth of sample surface at electrical discharge machining with brass wire electrode, Strojarstvo: Journal for Theory and Application in Mechanical Engineering 51/6 (2009) 633-640.

[22] A. Vagaská et al., The Application of Neural Networks to Control Technological Process, in: Proceedings of the 2013 International Conference on Applied Mathematics and Computational Methods (AMCM 2013), Recent Advances in Applied Mathematics and Computational Methods, Venice, Italy, September 28-30, 2013, Metin Demiralp, Venice, 2013, pp.179-186.

[23] P. Michal, Comparison of Possibilities for Process Control Using Basic Neural Structures, in: Proceedings of CER Comparative European Research 2014, Research Track: 1st Biannual CER Comparative European Research Conference: International Scientific Conference for Ph.D. students of EU countries, March 17-21, 2014, London, Sciemcee Publishing, 2014, pp.113-116.