Research on Dissolve Oxygen Modeling Based on Neural Network

Abstract:

The structure, characteristics and principles of BP neural network model are described in this paper. First, three impact factors of the dissolved oxygen are selected as the sample input of network, and then the parameters of BP neural network are selected, such as network structure, learning algorithm, output layer transfer function, learning rate and so on. Finally, the BP neural network model is established and trained, in order to approach compensate the effects of improves non-linearity. The simulation results show that BP neural network is practical and dependable in the field of dissolved oxygen modeling and has nice applied prospect.

• Periodical: Advanced Materials Research (Volumes 287-290)
• Pages: 2640-2643
• DOI: https://doi.org/10.4028/www.scientific.net/AMR.287-290.2640
• Online since: July 2011
• Authors: Guo Dong Gao, Wen Xiao Zhang, Gong Zhi Yu, Jiang Hua Sui
• Keywords: BP Neural Network (BPNN), Dissolved Oxygen (DO), Forecast, Model, Simulation

References

[1] Maged M. Hamed and Manar Z. EL-Beshry: submitted to Journal of Environmental Management (2004)

[2] Qinqi Wu and Yanxia Zhao: submitted to Journal of Zhanjiang Ocean University (1997). In Chinese

[3] Ling Zhang and Bo Zhang: Theory and Application of Artificial Neural Networks (Zhejiang Science and Technology Publications, Zhejiang 1997). In Chinese

[4] Xin Wen, Lu Zhou and Xiang Li: Simulation and application of MATLAB neural networks (Science Publications, Beijing 2003). In Chinese

[5] Jingle Fan: Detailed explanation of Matlab simulation application (Posts & Telecom Publications, Beijing 2003). In Chinese

[6] Huiqiang Zhi, Liang Tian and Zengjun Yang: submitted to Journal of Bulletin of Science and Technology (2005). In Chinese