Research on the Fouling Prediction Based on Hybrid Kernel Function Relevance Vector Machine

Abstract:

The research on the fouling prediction of heat exchanger is significantly to improve operational efficiency and economic benefits of the plants. Based on the relevance vector machine with Gaussian kernel function, polynomial kernel function and hybrid kernel function, simulation research on the fouling prediction was introduced. We construct a six-inputs and one-output network model according to the fouling monitor principle and parameters with MATLAB, all training data came from the Automatic Dynamic Simulator of Fouling and input the network after normalized processing and reclassification. Simulations show that the root mean square error of fouling prediction with hybrid kernel function is less than simple kernel function, and has the better prediction precision.

• Periodical: Advanced Materials Research (Volumes 204-210)
• Pages: 31-35
• DOI: https://doi.org/10.4028/www.scientific.net/AMR.204-210.31
• Online since: February 2011
• Authors: Ling Fang Sun, Hong Gang Xie, Li Hong Qiao
• Keywords: Fouling Thermal Resistance, Hybrid Kernel Function, Prediction, Relevance Vector Machine

References

[1] Steinhagen R, Steinhagen H M, Maani K. Problems and Costs due to Heat Exchanger Fouling in New Zealand Industries. Heat Transfer Engineering, Vol. 14(1993), pp.19-30.

DOI: 10.1080/01457639308939791

[2] Shanran Yang, Zhiming Xu, Lingfang Sun. Heat Exchanger Fouling and Its Countermeasure, 2nd Ed, Science Press, Beijing, (2004).

[3] Epstein N. Thinking about Heat Transfer Fouling: A 5×5Matrix. Heat Transfer Engineering, Vol. 4(1983), pp.43-56.

DOI: 10.1080/01457638108939594

[4] Zhimin Yang, Guangli Liu. Uncertainly Principle and Application of Support Vector Machine, Science Press, Beijing (2007).

[5] Xiao Huang. The Study on Kernels in Support Vector Machine, [Master Thesis], Soochow University, Su Zhou(2008).

[6] Tipping M E. The Relevance Vector Machine/Proc. of Advances in Neural Information Processing Systems. Cambridge, Mass: MIT Press(2000).

[7] Tzikas D G, Likas A, Galatsanos N P, et al. Relevance Vector Machine Analysis of Functional Neuroimages. Arlington, VA: IEEE(2004).

DOI: 10.1109/isbi.2004.1398710

[8] Nikolaev N. Sequential Relevance Vector Machine Learning from Time Series. Proceedings of International Joint Conference on Neural Networks. Montreal, Canada(2005).

DOI: 10.1109/ijcnn.2005.1556043

[9] Lingfang Sun , Shanyang Yang, Yukun Qin, Zhiming Xu. Evaluation of Antifouling Performance for Ion-rod Water Treater with Automatic Dynamic Simulator of Fouling, Journal of chemical industry and Engineering, Vol. 56(2005), pp.668-671.