Water quality evaluation model based on hybrid PSO-BP neural network

A hybrid neural network algorithm, aims at evaluating water quality, based on particle swarm optimization (PSO) algorithm, which has a keen ability in global search and back propagation (BP) algorithm that has a strong ability in local search. Heuristics has been proposed to optimize the number of neurons in the hidden layer. The comparison with the traditional BP NN shows the advantage of the proposed method with high precision and good correlation. The values of average absolute deviation (AAD), standard deviation error (SDE) and squared correlation coefficient (R 2 ) are 0.0072, 0.0208 and 0.98845, respectively. The results show that the hybrid PSO-BP NN has a good predictal ability of evaluating water quality; it is a practical and efficacious method to evaluate water quality. DOI : http://dx.doi.org/10.11591/telkomnika.v12i2.3190

[1]  P. Asokan,et al.  SURFACE ROUGHNESS PREDICTION USING HYBRID NEURAL NETWORKS , 2007 .

[2]  Li Jia-ke.  The Application of RBF Neural Network in Water Quality Evaluation , 2003 .

[3]  Yousef Bakhbakhi,et al.  Neural network modeling of ternary solubilities of 2-naphthol in supercritical CO2: A comparative study , 2012, Math. Comput. Model..

[4]  Li Ya-wei.  Water quality evaluation based on fuzzy artificial neural network , 2005 .

[5]  José O. Valderrama,et al.  Thermodynamic consistency test for high pressure gas–solid solubility data of binary mixtures using genetic algorithms , 2006 .

[6]  Zhou Wenbin,et al.  Status of nitrogen and phosphorus in waters of Lake Poyang Basin , 2008 .

[7]  Xuesong Yan,et al.  Orthogonal Particle Swarm Optimization Algorithm and Its Application in Circuit Design , 2013 .

[8]  T. Khayamian,et al.  Prediction of solubility for polycyclic aromatic hydrocarbons in supercritical carbon dioxide using wavelet neural networks in quantitative structure property relationship , 2004 .

[9]  Aboozar Khajeh,et al.  Prediction of solubility of gases in polystyrene by Adaptive Neuro-Fuzzy Inference System and Radial Basis Function Neural Network , 2010, Expert Syst. Appl..

[10]  Seyed Taghi Akhavan Niaki,et al.  A hybrid method of artificial neural networks and simulated annealing in monitoring auto-correlated multi-attribute processes , 2011 .

[11]  M. Ahmadi.  Neural network based unified particle swarm optimization for prediction of asphaltene precipitation , 2012 .

[12]  Huang Shen-wei.  Application of BF Network to Evaluate Water Quality , 2003 .

[13]  Juan A. Lazzús,et al.  Estimation of solid vapor pressures of pure compounds at different temperatures using a multilayer network with particle swarm algorithm , 2010 .

[14]  Cheng Jilin.  Application of main component analysis method in comprehensive evaluation for water conservancy modernization in Jiangsu Province , 2010 .

[15]  Vladan Babovic,et al.  Multi-step-ahead model error prediction using time-delay neural networks combined with chaos theory , 2010 .

[16]  Gu Li.  Application of improved LM-BP neural network in water quality evaluation , 2008 .

[17]  K. Movagharnejad,et al.  A comparative study between LS-SVM method and semi empirical equations for modeling the solubility of different solutes in supercritical carbon dioxide , 2011 .

[18]  M. Lashkarbolooki,et al.  Comparison the capability of artificial neural network (ANN) and EOS for prediction of solid solubil , 2011 .

[19]  Holger R. Maier,et al.  The effect of internal parameters and geometry on the performance of back-propagation neural networks: an empirical study , 1998 .

[20]  Kenneth R. Hall,et al.  An algebraic method that includes Gibbs minimization for performing phase equilibrium calculations for any number of components or phases , 2003 .