A novel processing for multiple gases detection

Feng Chen1, Zonghai Chen1, Zheng Jiao2
1Department of Automation, University of Science and Technology, Hefei, Anhui, China
2Department of Chemistry, University of Science and Technology, Hefei, Anhui, China

Tóm tắt

It is difficult to detect multiple gases by single chemical sensor because of nonlinear and complicated relations between multiple gas and surface of sensitive materials. In this paper, the technology of multisensor data fusion is applied to detect multiple gases. It is presented a novel detection method based on multiobjective genetic algorithm(MOGA) for analyzing and distinguishing each component's concentration in multiple gases. The multigas detection is transformed to multiobjective optimization problem. In order to avoid premature convergence, sharing function is introduced to maintain the diversity of the population. The theory of multiple gases detection is described in detail. The experimental results are given and the results demonstrate the mechanism proposed in this paper is effective.

Từ khóa

#Gases #Chemical sensors #Gas detectors #Chemical technology #Genetic algorithms #Sensor phenomena and characterization #Neural networks #Intelligent sensors #Automation #Optimization methods

Tài liệu tham khảo

10.1016/0898-1221(92)90094-X holland, 1992, Adaptation in Nature and Artificial System, 10.7551/mitpress/1090.001.0001 hisashi, 1996, multi-objective optimization by genetic algorithms: a review, Proc of the 3rd ICEC, 517 davis, 1991, Handbook of Genetic Algorithm globerg, 1987, genetic algorithms with sharing for multi-modal function optimization, Proc 2nd Int Conf on Genetic Algorithms, 41 10.1162/evco.1994.2.3.221 kazimierz, 1998, An attempt to apply Elman's neural network to recognition of methane pulses, Sensors and Actuators B, 47, 231, 10.1016/S0925-4005(98)00028-8 syu, 1998, neural network signal detection of an SO2 electrode Sensors and Actuators B, 49, 186