Estimation of dissolved oxygen via PLS and neural networks

Dissolved oxygen is one of the most important dependent factors in the process of aquaculture. In this article, a new on-line soft sensing method is proposed for estimation of dissolved oxygen in aquaculture. Based on the characters of process data, two advance techniques are used which is PLS (Partial Least Squares) and neural networks. With this method, real-time control and optimization can be realized in aquaculture. An industrial experimental study is described, and the results show that the proposed soft sensing algorithm is effective.

[1]  HE You-yuan.  Prediction Model of Dissolved Oxygen Fuzzy System in Aquaculture Pond Based on Neural Network , 2010 .

[2]  Ying Zhao,et al.  Water quality forecast through application of BP neural network at Yuqiao reservoir , 2007 .

[3]  S. Wold,et al.  PLS-regression: a basic tool of chemometrics , 2001 .

[4]  Changhui Deng,et al.  Soft sensing of dissolved oxygen in fishpond via extreme learning machine , 2014, Proceeding of the 11th World Congress on Intelligent Control and Automation.

[5]  Changhui Deng,et al.  Application of Neural Network Based on PSO Algorithm in Prediction Model for Dissolved Oxygen in Fishpond , 2006, 2006 6th World Congress on Intelligent Control and Automation.

[6]  William E. Grant,et al.  Fish bioenergetics and growth in aquaculture ponds: II. Effects of interactions among, size, temperature, dissolved oxygen, unionized ammonia and food on growth of individual fish , 1985 .

[7]  A. J. Morris,et al.  Non-linear projection to latent structures revisited (the neural network PLS algorithm) , 1999 .

[8]  Daoliang Li,et al.  A hybrid approach of support vector regression with genetic algorithm optimization for aquaculture water quality prediction , 2013, Math. Comput. Model..

[9]  Xuemei Hu,et al.  The Soft Measure Model of Dissolved Oxygen Based on RBF Network in Ponds , 2011, 2011 Fourth International Conference on Information and Computing.

[10]  D. Secor,et al.  Dissolved oxygen, temperature and salinity effects on the ecophysiology and survival of juvenile Atlantic sturgeon in estuarine waters: II. Model development and testing. , 2009 .

[11]  Yanping Gao,et al.  A Hybrid Neural Network and Genetic Algorithm Model for Predicting Dissolved Oxygen in an Aquaculture Pond , 2010, 2010 International Conference on Web Information Systems and Mining.

[12]  Bernhard H. Schmid,et al.  Artificial Neural Network Modeling of Dissolved Oxygen in a Wetland Pond: The Case of Hovi, Finland , 2006 .