Water quality Prediction Model Based on fuzzy neural network

DOI

10.2991/mmebc-16.2016.127How to use a DOI?

Keywords

water quality of aquaculture; dissolved oxygen prediction; principle component analysis; differential evolution algorithm; FNN

Abstract

This article proposes a dissolved oxygen prediction model for water quality about aquaculture to solve the problems like low accuracy and poor robustness of traditional prediction methods about water quality based on principal component analysis (PCA), fuzzy neural network(FNN), and differential evolution combined with BP algorithm (DEBP). This model can establish nonlinear dissolved oxygen prediction model of water quality about aquaculture though collecting principle components about indicators of aquatic ecological environment based on PCA, reducing the vector dimension as input in the model, using differential evolution algorithm to optimize the weighting parameters of FNN, and automatically acquiring optimal parameters. Based on this model, we conducted the prediction analysis about online water quality data of a shrimp culture pond in Zhanjiang from December 1 to December 12 in 2015, and the results of the trial indicates that: this model achieves a good predictive effect, compared with the BP-FNN model, the absolute error of 95.8% of tested samples of the PCA-FNN-DEBP model is less than 20% and the maximum error is 0.22 mg/L, both of these two parameters are better than BP-FNN prediction model. The PCA-FNN-DEBP algorithm is not only fast and accurate, but also able to provide decision basis for adjustment and management of water quality in shrimp culture industry.

Copyright

© 2016, the Authors. Published by Atlantis Press.

Open Access

This is an open access article distributed under the CC BY-NC license (http://creativecommons.org/licenses/by-nc/4.0/).

Download article (PDF)

TY  - CONF
AU  - Fan Liao
AU  - Chunxia Zhao
PY  - 2016/06
DA  - 2016/06
TI  - Water quality Prediction Model Based on fuzzy neural network
BT  - Proceedings of the 2016 6th International Conference on Machinery, Materials, Environment, Biotechnology and Computer
PB  - Atlantis Press
SP  - 592
EP  - 595
SN  - 2352-5401
UR  - https://doi.org/10.2991/mmebc-16.2016.127
DO  - 10.2991/mmebc-16.2016.127
ID  - Liao2016/06
ER  -