GERİ BESLEMELİ VE İLERİ BESLEMELİ SİNİR AĞI KULLANILARAK DMMP VE CHCL3 GAZ KARIŞIMLARININ MİKTARSAL SINIFLANDIRILMASI

Abstract

Bu çalışmada, gaz karışımlarında gaz konsantrasyonlarının (DMMP and CHCl₃) miktarsal olarak tanımlanması için ileri beslemeli sinir ağı (FFNN) kullanılmış ve Elman geri beslemeli sinir ağı (RNN) önerildi. Phthalocyanine kaplamalı kuartz kristal mikrodenge (QCM) gaz sensörü olarak kullanıldı. Kalibreli bir kütle akış kontrolörü, taşıyıcı gaz, DMMP ve CHCl₃ gaz karışım  buharlarının akış miktarının kontrol edilmesi için kullanıldı.  Algılayıcının cevapları IEEE 488 kart vasıtasıyla toplandı. İkili karışımdaki bileşenler, QCM sensör dizisinden alınan sensör cevapları ileri beslemeli sinir ağı ve Elman geri beslemeli sinir ağına  giriş olarak uygulanma ile miktarsal olarak belirlendi. İki gizli katmanlı Elman geri beslemeli sinir ağı ile en iyi sonuç elde edildi. DMMP and CHCl₃ gaz karışımlarının miktarsal sınıflandırılması için diğer sinir ağlarının da uygulanabilirliği görüldü.

Keywords

• Gazların Miktarsal Sınıflandırılması,İleri Beslemeli Sinir Ağı,Elman Geri Beslemeli Sinir Ağı

QUANTITATIVE CLASSIFICATION OF DMMP AND CHCL3 GAS MİXTURES USING RECURRENT AND FEED FORWARD NEURAL NETWORKS

Abstract

In this study, the feed forward neural networks (FFNN) were used and Elman’s recurrent neural networks (RNN) were proposed for quantitative identification of individual gas concentrations (DMMP and CHCl₃) in their gas mixtures. The phthalocyanine coated quartz crystal microbalance (QCM) type sensors were used as gas sensors. A calibrated mass flow controller was used to control the flow rates of carrier gas and DMMP and CHCl₃ gas mixtures streams. Sensor responses were collected via an IEEE 488 card. The components in the binary mixture were quantified applying the sensor responses from the QCM sensor array as inputs to the feed forward and Elman’s recurrent neural networks. The results of the Elman’s recurrent neural network with two hidden layer was the best. The other neural networks are also applicable to the quantitative classification of DMMP and CHCl₃ gas mixtures.

Keywords

• Quantitive Classification of Gases,Feed Forward Neural,Network,Elman's Recurrent Neural Network

References

1. D. Rebiere, C. Dejeoue, J. Pistre, R. Planade, J.F. Lipsker, P. Robin , Surface acustic wave detection of organophosphorus compounds with flouropolyol coatings, Sensors and actuators B, Vol. 43 (1997) 34-39
2. M.S. Nieuwenhuizen, J.L.N. Harteveld, Studies on a surface acoustic wave (SAW) dosimeter sensor for organophosporous nerve agents, Sensors and actuators B, Vol. 40 (1997) 167-173
3. M.H. Ho, G.G. Gullbault, B. Rietz, Continuos Detection of Toluene in Ambient Air with a Coated Piezoelectric Crystal, Anal. Chem., Vol. 52(9), (1980)
4. F.Temurtas, C.Tasaltin, H.Temurtas, N. Yumusak, Z.Z: Ozturk, Fuzzy Logic and Neural Network Applicationns on the Gas Sensor Data: Concentration estimation, ISCIS’03, Antalya, LNCS (November 2003)178-185
5. A. Szczurek, P.M. Szecowka, B.W. Licznerski, Application of sensor array and neural networks for quantification of organic solvent vapours in air, , Sensors and Actuators B, Vol. 58 (1999) 427-432
6. S. Vaihinger, W. Gopel, Multi - Component Analysis in Chemical Sensing in Sensors: A Comprehensive Survery Ed. W. Gopel, S. Hense, S.N. Zemel, VCH. Weinhe, New York, Vol. 2(1) (1991) 192
7. M. Pardo, G. Faglia, G. Sberveglieri, M. Corte, F. Masulli, M. Riani, A time delay neural network for estimation of gas concentrations in a mixture, Sensors and Actuators B, 65 (2000) 267–269
8. H.W. King, Piezoelectric Sorption Detector, Anal. Chem., Vol. 36 (1964) 1735-1739

9. J. Riddick, and A. Bunger, in A. Weissberger, (ed.), Organic Solvents’ in Techniques of Chemistry, Vol. 2, Wiley Interscience, (1970)
10. M.M. Abdelhameed, F.F. Tolbah, A recurrent neural network based sequential controller for manufacturing automated systems, Vol. 12, (2002) 617-633
11. S. Haykin, Neural Networks, A Comprehensive Foundation, Macmillan Publishing Company, Englewood Cliffs, N.J. (1994)