Zastosowanie zaimplementowanej w FPAA kaskadowej sieci neuronowej do klasyfikacji jakości węgla w komorach spalania

• Autorzy: Suszyński R. , Marciniak J. , Wawryn K.

Identyfikatory

DOI

10.15199/48.2016.09.24

Warianty tytułu

EN

An application of the FPAA implemented cascaded neural network to the classification of coal fuel in combustion chambers

• Języki publikacji: PL

Abstrakty

PL

W pracy przedstawiono efektywny system klasyfikacji jakości paliwa w komorach spalania z wykorzystaniem sztucznej sieci neuronowej. Proponowany system wykorzystuje analizę pomierzonych parametrów procesu spalania w kotle. Parametry te wykorzystano do wytrenowania sieci ANN tj. do policzenia za pomocą programu MATLAB współczynników wagowych połączeń synaptycznych poszczególnych neuronów sieci. Otrzymane współczynniki zostały wykorzystane do skonfigurowania sieci ANN. Sieć ta została zaimplementowana w układzie FPAA i przetestowana na przykładach klasyfikacji paliwa dostarczanego do komory spalania. W pracy przedstawiono i omówiono wyniki badań.

EN

A hardware artificial neural network for classification a quality of a coal fuel in combustion chambers is presented in the paper. Proposed method is based on an analysis of measured combustion process parameters in the chamber by the feedforward artificial neural network. Measured parameters have been used to train neural network weights with a help of MATLAB program. Calculated weights have been used to determine the quality of the coal fuel loaded into the chamber. The ANN has been tested by the MATLAB program and the FPAA implemented network. Obtained results are presented and discussed.

Słowa kluczowe

PL

sztuczna sieć neuronowa; układ FPAA; proces spalania

EN

artificial neural network; FPAA device; combustion process

• Wydawca: Wydawnictwo SIGMA-NOT
• Czasopismo: Przegląd Elektrotechniczny
• Rocznik: 2016
• Tom: R. 92, nr 9
• Strony: 91--94
• Opis fizyczny: Bibliogr. 23 poz., rys., tab.

Twórcy

autor

Suszyński R.

• Politechnika Koszalińska, Wydział Elektroniki i Informatyki, ul. JJ Śniadeckich 2, 75-453 Koszalin

autor

Marciniak J.

• Politechnika Koszalińska, Wydział Elektroniki i Informatyki, ul. JJ Śniadeckich 2, 75-453 Koszalin

autor

Wawryn K.

• Politechnika Koszalińska, Wydział Elektroniki i Informatyki, ul. JJ Śniadeckich 2, 75-453 Koszalin

Bibliografia

• [1] Lou C., Zhou H., Yu P., and Jiang Z., Measurements of the flame emissivity and radiative properties of particulate medium in pulverized-coal-fired boiler furnaces by image processing of visible radiation, in Proc. of the Combustion Institute, vol. 31, (2007), 2771-2778
• [2] Gölles M., Reiter S., Brunner T., Dourdoumas N., and Obernberger I., Model based control of a small-scale biomass boiler, Control Engineering Practice, vol. 22, (2014), 94-102
• [3] Kalogirou S.A., Artificial intelligence for the modeling and control of combustion processes: a review, Progress in Energy and Combustion Science, vol. 29, (2003), 515-566
• [4] Hosovsky A., Genetic optimization of neural network structure for modeling of biomass-fired boiler emissions, Journal of applied science in the thermodynamics and fluid mechanics, vol. 9, no. 2, (2011), 1-6
• [5] Manke P., and Tembhurne S., Application of back propagation neural network to drum level control in thermal power plants, International Journal of Computer Science, (2012), 520-526
• [6] Ye H., and Ni W., Static and transient performance prediction for CFB boilers using a Bayesian-Gaussian Neural Network, J. of Thermal Science, (1997), 141-148
• [7] Blasco J., Fueyo N., Dopazo C., and Chen J.Y., Selforganizing- map approach to chemistry representation in combustion applications, Combustion Theory and Modelling, vol. 4, no. 1, (2000), 61-76
• [8] Wang L., The apllication of fuzzy neural network to boiler steam presure control, International Journal of Computer Science, (2013), 704-707
• [9] Marciniak J., The detection of anomalies in controlling of the combustion process by using a genetic algorithm, Diagnostyka, vol. 17, no. 1, (2016), 21-26
• [10] Marciniak J., The detection of anomalies in controlling of the combustion process by using a negative selection algorithm, Diagnostyka, vol. 17, no. 1, (2016), 28-31
• [11] Znamirowski L., Palusinski O.A., and Vrudhula S.B.K., Programmable Analog/Digital Arrays in Control and Simulation, Analog Integrated Circuits and Signal Processing, vol. 39, (2004), 55-73
• [12] Balen T.R., Andrade A.Q., Azais F., Lubaszewski M., and Renovell M., Applying the Oscillation Test Strategy to FPAA’s Configurable Analog Blocks, Journal of Electronic Testing: Theory and Applications, vol. 21, (2005), 135-146
• [13] Widyantara H., Rivai M., and Purwanto D., Neural Network for Electronic Nose using Field Programmable Analog Arrays, Int. J. of Electrical and Computer Engineering (IJECE), vol. 2, no. 6, (2012), 739-747
• [14] Suszynski R., and Wawryn K., Rapid prototyping of algorithmic A/D converters based on FPAA devices, Bulletin of the Polish Academy of Sciences-Technical Sciences, vol. 61, no. 3, (2013), 691-696
• [15] Suszynski R., and Wawryn K., Prototyping of Higher Order Sigma Delta ADC Based on Implementation of a FPAA, In Proc. of the Int. Conf. on Signals and Electronic Systems (ICSES), (2012), 1-4
• [16] Żurada J.M., Introduction to Artificial Neural systems, West Publishing Company, 1992
• [17] Van der Smagt P.P., Minimization methods for training feedforward neural networks, Neural Networks, vol. 7, (1994), 1-11
• [18] Wawryn K., and Strzeszewski B., Current mode circuits for programmable WTA neural network, Analog Integrated Circuits and Signal Processing, vol. 27, no. 1-2, (2001), 49-69
• [19] Swietlicka A., Gugala K., Jurkowlaniec A., et al., The Stochastic, Markovian, Hodgkin-Huxley Type of Mathematical Model of The Neuron, Neural Network World, vol. 25, no. 3, (2015), 219-239
• [20] Fletcher R., and Reeves C.M., Function minimization by conjugate gradients, Comput. J., vol. l, (1964), 149-154
• [21] Talaska T., and Dlugosz R., Analog Sorting Circuit for the Application in Self-Organizing Neural Networks Based on Neural Gas Learning Algorithm, (2015), 282-286
• [22] Wojtyna R., Analog low-voltage low-power CMOS circuit for learning Kohonen networks on silicon, Int. Conf. Mixed Design of Integrated Circuits and Systems, (MIXDES), (2010), 209-214
• [23] “AnadigmApex dpASP” Family User Manual. Anadigm. Inc.. 2005J. Clerk Maxwell. A Treatise on Electricity and Magnetism. 3rd ed.. vol. 2. Oxford: Clarendon. 1892. 68-73

Uwagi

Opracowanie ze środków MNiSW w ramach umowy 812/P-DUN/2016 na działalność upowszechniającą naukę.