Strategic Study of CAE >> 2007, Volume 9, Issue 2
Study on the Purification of Wastewater in the Constructed Wetland Based on GA-BP Network
Department of Municipal Engineering, Southeast University, Nanjing 210096, China
Next Previous
Abstract
As a new type of ecological technique in wastewater treatmen t field, Constructed Wetland was gradually put into application and received growing attention. Since the wastewater purification process in constructed wetland was a complex and nonlinear state affected by many interactional factors, it was hard to establish exact mathematics model to carry out multi-factor analysis and determine best operation condition by traditional means. Based on plenty of reliable experimental data, genetic neural network was first tentatively utilized to simulate the pollutant removal system of wetland, and some key problems were discussed, such as how to determine optimally the topological structure, sample scale and unitary method for training data, etc. Optimized GA-BP network was established to simulate orthogonal test of wetland system. According to the results of orthogonal test, best operation condition was decided and the factors(e. g.water level, hydraulic retaining time, etc)were classified. Therefore, proper feasible methods of pollutant removal were put forward.
Keywords
constructed wetlands ; wastewater purification ; GA-BP network ; orthogonal test
References
[ 1 ] Michael C K .Subsurface flow constructed wetlands treating municipal wastewater for nitrogen transformation and removal [ J] . Water Environment Research , 1997 , 67 (7) :1254 ~ 1264 link1
[ 2 ] Gopal B .Natural and constructed wetlands for wastewater treatment : potentials and problems [J] . Water Science and Technology ,1999 ,40 :27 ~ 35 link1
[ 3 ] 张乃尧 ,阎平凡 .神经网络与模糊控制[M] .北京 : 清华大学出版社 ,1998
[ 4 ] Michale wicz Z . Genetic Algorithm + Data Struture = Evolution Programs , 2nd ed [M] . New York : Springer- Verlag ,1994
[ 5 ] Whiltley D , Dominic S , Das R . Genetic reinforcement learning for neurocontrol problem [J] .Machine Learning , 1993 ,13 :259 ~ 284 link1
[ 6 ] Koehn P . Combining Genetic Algorithms and Neural Networks: The Encoding Problem [D] . Knoxville : The University of Tennessee ,1994
[ 7 ] Ehrenfeuchi A , Detal H . A general lower bound on the number of example needed for learning[J] . Information and Computation ,1989 ,82(3) :247 ~ 251 link1