Improvement of radial basis function neural network with accelerated particle swarm optimization for corrosion rate prediction of 3C steel in seawater environment

Improvement of radial basis function neural network with accelerated particle swarm optimization for corrosion rate prediction of 3C steel in seawater environment

Qingping Jian 

Chengdu Vocational & Technical College of Industry, Equipment Manufacturing College, Chengdu 610218, China

Corresponding Author Email:
| |
| | Citation



For accurately prediction of 3C steel corrosion rate in seawater environment, this paper establishes a radial basis function neural network (RBFNN) and improves it with accelerated particle swarm optimization (APSO). Specifically, the centers, spreads and connection weights of each radial basis function (RBF) were automatically tuned by the APSO, and the number of RBFs in the RBFNN was minimized by choosing a special fitness function. The APSO-optimized RBFNN was proved through a case study to have good prediction accuracy and self-learning ability. The research findings provide an accurate, adaptive and easily-to-train prediction model for 3C steel corrosion rate in the seawater environment


radial basis function neural network (RBFNN), seawater environment, accelerated particle swarm optimization (APSO), prediction model, corrosion rate

1. Introduction
2. RBFNN structure
3. The APSO
4. Prediction model based on APSO-RBFNN
5. Conclusions

Bishop C. M. (1995). Neural networks for pattern recognition. Oxford: Oxford University Press.

Caceres L., Vargas T., Herrera L. (2007). Determination of electrochemical parameters and corrosion rate for carbon steel in un-buffered sodium chloride solutions using a superposition model. Corrosion Science, Vol. 49, No. 8, pp. 3168-3184.

Cao C. L., Cheng X. W., Zhang G. Y. (2012). Study on improving prediction accuracy of 3C steel corrosion rate. China Well and Rock Salt, Vol. 43, No. 5, pp. 25-28.

Feng H. M. (2006). Self-generation RBFNs using evolutional PSO learning. Neurocomputing, Vol. 70, No. 1, pp. 241-251.

Hajeeh M. (2003). Estimating corrosion: a statistical approach. Materials and Design, Vol. 24, No. 7, pp. 509-518.

Kennedy J., Eberhart R. C. (1995). Particle swarm optimization. Proceedings of the IEEE International Conference on Neural Networks, pp. 1942-1948.

Liu J. J., Lin Y. Z., Li X. Y. (2008). Numerical simulation for carbon steel flow-induced corrosion in high-velocity flow seawater. Anti-Corrosion Methods and Materials, Vol. 55, No. 2, pp. 66-72.

Liu X. Q., Tang X., Wang J. (2005). Correlation between seawater environmental factors and marine corrosion rate using artificial neural network analysis. J. Chin. Soc. Corros. Prot., Vol. 25, No. 2005, pp. 11–14.

Liu Y. X., Gao X. C., Zhang G. Y., Guo H. H. (2008). BP neural networks used in prediction and analyses of 3C steel corrosion function. Journal of Materials Science and Engineering, Vol. 26, No. 2008, pp. 94–97.

Paik J. K., Thayamballi A. K., Park Y. I., Hwang T. S. (2004). A time-dependent corrosion wastage model for seawater ballast tank structures of ships. Corrosion Science, Vol. 46, No. 2, pp. 471-486.

Samide A. P., Bibicu I., Agiu M., Preda M. (2008). Mossbauer spectroscopy study on the corrosion inhibition of carbon steel in hydrochloric acid solution. Materials Letters, Vol. 62, No. 2, pp. 320-322.

Schwenker F., Kestler H. A., Palm G. (2001). Three learning phases for radial-basis-function networks. Neural Networks, Vol. 14, No. 4-5, pp. 439-458.

Song W. W., Dong C. C., Zhang B. (2012). Application of artificial neural network to metal corrosion in seawater. Corrosion & Protection, Vol. 33, No. 8, pp. 668-671.

Srisuwan N., Ochoa N., Pebere N., Tribollet B. (2008). Variation of carbon steel corrosion rate with flow conditions in the presence of an inhibitive formulation. Corrosion Science, Vol. 50, No. 5, pp. 1245-1250.

Yang X. S. (2010). Engineering optimization: an introduction with metaheuristic appplications. John Wiley & Sons.