1. MMC
  2. All Volumes and Issues
  3. Volume 2, Number 1, 2015
  4. Optical combustion sensor data interpretation using hybrid negative selection algorithm with artificial immune networks

Optical combustion sensor data interpretation using hybrid negative selection algorithm with artificial immune networks

MMC.
2015;
Volume 2, Number 1
: pp. 58-70
https://doi.org/10.23939/mmc2015.01.058
Received: February 25, 2015

Math. Model. Comput. Vol. 2, No. 1, pp. 58-70 (2015)

Authors:
  1. V. I. Lytvynenko
  2. A. Smolarz
  3. W. Wójcik
  4. J. Ballester
  5. O. Kozhukhovskaya
  6. K. Gromaszek
1
Kherson National Technical University, Kherson, Ukraine
2
Lublin University of Technology
3
Lublin University of Technology
4
University of Zaragoza
5
Cherkasy State Technological University
6
Lublin University of Technology

In most extended in Poland PC burners an individual air excess ratio rules an amount of pollution generated, yet there is a lack of method that allows measurement of output parameters. It is therefore necessary to use indirect methods, which could primarily include acoustic, and optical methods. These methods are non-invasive and can provide virtually not delayed and additionally spatially selective information about the combustion process but they are really difficult in interpretation. The article shows application of relatively new class of classification methods – the artificial immunology algorithms to the combustion process diagnostics consisting in detection of incorrect air excess in pulverised coal burner on the basis of signals acquired from optical sensor.

optical industrial systems
industrial diagnostics
pulverised coal burner
artificial immune network
Negative Selection Algorithm
  1. Komada P. and Cieszczyk S. Application of Multiple Line Integrated Spectroscopy on CO Concentration Measurement. Elektronika ir Elektrotechnika. 19(9), 46–49 (2013).
  2. Komada P., Cieszczyk S. and Wójcik W. Influence of gas concentration inhomogeneity on measurement accuracy in absorption spectroscopy. Przegląd Elektrotechniczny. 88(8), 36–38 (2012).
  3. Wójcik W., Surtel W., Smolarz A., Kotyra A., Komada P. Optical fiber system for combustion quality analysis in power boilers. Proceedings of SPIE 4425, 517–522 (2001).
  4. De Castro L. N. and Timmis J. Artificial Immune Systems: A New Computational Intelligence Approach. Springer, London, England. 1–357 (2002).
  5. Forrest S., Perelson A. S., Allen L. and Cherukuri R. Self-nonself discrimination in a computer. Proceedings of the Symposium IEEE Computer Society on Research in Security and Privacy, May 16–18, IEEE Xplore Press, Oakland, CA., USA. 202–212 (1994).
  6. Lytvynenko V. I. Comparative experimental study of a modified negative selection algorithm and clonal selection algorithm negative for solving classification. Vestnik Kherson National Technical University. 4(33), 7–11 (2008). (In Russian).
  7. Dasgupta D. Advances in Artificial Immune Systems. IEEE Computational Intelligence Magazine. 1(4), 40–49 (2006).
  8. Bidyuk P. I., Lytvynenko V. I. and Fefelov A. O. Formalizatsiya metodiv pobudovi shtuchnix imunnih systems. Naukovi Visti Natsionalnogo tehnichnogo universitetu Ukraine Kiivsky politehnichny institut. 1/2007, 29–41 (2007).
  9. Lytvynenko V., Bidjuk P. and Myrgorod V. Application of the method and combined algorithm on the basis of immune network and negative selection for identification of turbine engine surging. 2nd International Conference on Inductive Modelling. Kyiv, Ukraine. 116–123 (2008).
  10. Fefelov A. A., Litvinenko V. I. and Bidjuk P. I. Modification of algorithm of negative selection on the basis of mechanisms artificial immune sets for the decision of problems of detection of anomalies. The Collection of scientific jobs in five volumes of the second international scientific conference Intellectual systems of decision-making and applied aspects of information technologies. Evpatoria, 19–22 May, 2007. 3, 73–78 (2007).
  11. Lytvynenko V. Classification systems based on negative selection mechanism. III International Scientific and Practical Conference Trends in Research. Dnipropetovsk, 21–30 June 2004. 34–36 (2004).
  12. Ding C. H. Q. and Dubchak I. Multi-class protein fold recognition using support vector machines and neural networks. Bioinformatics. 17(4), 349–358 (2004).
  13. Rifkin R. and Klautau A. Parallel networks that learn to pronounce English text. Journal of Machine Learning Research. 5, 101–141 (2004).
  14. Aly M. Survey on Multi-Class Classification Methods. Technical Report, Caltech, USA (2005).
  15. Smolarz A. Optical methods in diagnostics of combustion process of gaseous fuels, pulverized coal and its blends with biomass. Wydawnictwo Politechniki Lubelskiej. Lublin, Poland. 99–100 (2013). (In Polish).