Prediction Model of Aerosol Fire Extinguishing Agent Performance Based on Combination of Genetic Algorithm and Back-Propagation Neural Network

Abstract:

The aerosol fire extinguishing agent is a complex pyrotechnic composition, and the extinguishing efficiency need a series of experiments to identify. A method is put forward out based on combining back-propagation neural network and genetic algorithm (BP-GA) in this paper, and then the performance of aerosol fire extinguishing agent can be predicted in advance by the formulation. In the method, back-propagation (BP) algorithm was proposed to map the complex relationship between additive components and quality indexes of formulation. The genetic algorithm was employed to optimize the BP neural network weight and threshold. The results showed that the prediction display a satisfied consistence with the test and the error is less than 5%, and also indicated that the combining BP-GA method was an effective tool to predict the performance of aerosol fire extinguishing agent by the formulation designed.

• Periodical: Advanced Materials Research (Volumes 989-994)
• Pages: 2629-2633
• DOI: https://doi.org/10.4028/www.scientific.net/AMR.989-994.2629
• Online since: July 2014
• Authors: Zhi Jie Chen*, Chen Guang Zhu, Zi Hao Zhang
• Keywords: Aerosol Fire Extinguishing Agent, BP Neural Network (BPNN), Genetic Algorithm (GA)

References

[1] Guo hong-bao, Yue da-ke. Aerosol fire extinguishing technology [M]. Beijing, Chemical Industry Press, 2005, 4.

[2] Li min-qiang. The basic theory and application of genetic algorithm [M]. Beijing, Science Press, (2002).

[3] O P Korobeinichev, A. G. Shmakov. Fire suppression by low-volatile chemically active fire suppressants using aerosol technology [J]. Fire Safety Journal, 2012, 51, 102–109.

DOI: 10.1016/j.firesaf.2012.04.003

[4] Venkatesan D, Kannan K, Saravanan R. A genetic algorithm-based artificial neural network model for the optimization of machining processes[J]. Neural Computing and Applications 2008, 18(2): 135-140.

DOI: 10.1007/s00521-007-0166-y

[5] Ehsani M. R, Bateni H, Parchikolaei G R. Modeling the oxidative coupling of methane using artificial neural network and optimizing of its operational conditions using genetic algorithm[J]. Korean Journal of Chemical Engineering 2012, 29 (7): 855-861.

DOI: 10.1007/s11814-011-0250-y

[6] Gurunathan B, Sahadevan R. Design of experiments and artificial neural network linked genetic algorithm for modeling and optimization of L-asparaginase production by Aspergillus terreus MTCC 1782 [J]. Biotechnology and Bioprocess Engineering 2011, 16 (1): 50-58.

DOI: 10.1007/s12257-010-0119-7