Study of the Fouling Characteristics of Arc Pipe Based on Principal Component Analysis and Partial Least Squares

Abstract:

An experimental platform of arc pipe was built to measure the corresponding parameters of fouling and the equation of fouling characteristics was built based on principal component analysis and partial least squares, in which there are several input variables such as input and output temperature, wall temperature, flow rate and so on, and there is only one output variables—fouling resistance. In order to compare with the five-input-variables equation, the six-input-variables equation was also built. The prediction results show the model built in this paper is reasonable and feasible.

• Periodical: Advanced Materials Research (Volumes 443-444)
• Pages: 731-737
• DOI: https://doi.org/10.4028/www.scientific.net/AMR.443-444.731
• Online since: January 2012
• Authors: Li Jing, Xiao Qiang Wen
• Keywords: Arc Pipe, Fouling Characteristic, PLS, Prediction, Principal Component

References

[1] Yang Shanrang, Xu Zhiming, Sun Lingfang, Heat transfer equipment, fouling and strategy, 2nd ed., Beijing: Science Press, 2004, pp.10-12.

[2] Fan Shaosheng, Wang Yaonan, Prediction of Fouling in Condenser Based on Multi-Model Combination, Chinese Journal of Sensors and Actuators, vol. 18, Feb. 2005, pp.225-229.

[3] Fan Shaosheng, Gray theory based prediction for condenser fouling, Journal of electric power science and technology, vol. 22, Feb. 2007, pp.12-15.

[4] Feng Dianyi, Fan Jia, Sun Shouren, Research on the Real-time Prediction of the Fouling Resistance of a Waste Heat Boiler, Journal of engineering for thermal energy and power, vol. 24, Feb. 2009, pp.196-199.

[5] Feng Dianyi, Fan Jia, Sun Shouren, Correction and application of on-line prediction model for fouling thermal resistance, Chemical engineering, vol. 37, Nov. 2009, pp.12-15.

[6] Heng Shiquan, Yang Guanghua, Wu Lifeng, Application of neural network in prediction thermal resistance of corrosion Fouling, Total corrosion control, vol. 18, Jan. 2004, pp.11-13.

[7] Zhang Ying, Wang Yao Nan, Prediction of condenser fouling based on locally weighted partial least squares regression algorithm, Chinese Journal of Scientific Instrument, vol. 31. Feb. 2010, pp.299-304.

[8] Zhao Bo, Yang Shanrang, Liu Fan, Experimental Study on Dynamic Simulation of Cooling Water Fouling Resistance Prediction by Support Vector Machine, vol. 30, Nov. 2010, pp.92-97.

[9] Xu Zhiming, Yang Shanrang, Sun Lingfang, Experimental investigation on the fouling characteristics of corrugated tube, Journal of engineering thermophysics, vol. 22, Mar. 2001, pp.477-480.

[1] 708.

77.

[1] 791.

[5] 67.

[1] 695.

[1] 638.

[1] 16.

[1] 634.

92.

[1] 619.

[1] 604.

[6] 19.

[1] 849.

[8] 13.

[1] 710.

[1] 712.

[2] 66.

[1] 867.

[6] 15.

[1] 759.

[1] 859.

16.

[2] 070.

[11] 53.

[1] 856.

[1] 674.

[2] 59.

[1] 982.

[15] 33.

[1] 719.

[1] 872.

[5] 85.

[1] 790.

[9] 98.

[1] 989 test pipe B.

[3] 066.

[6] 50.

[1] 875.

[34] 87.

[2] 879.

[3] 586.

[4] 14.

[3] 034.

[11] 89.

[3] 444.

[3] 233.

[6] 86.

[2] 487.

[17] 80.

[3] 026.

[3] 226.

[2] 83.

[2] 767.

[11] 80.

[3] 137.

[3] 643.

[3] 36.

[3] 309.

[6] 12.

[3] 525.

[3] 370.

[3] 43.

[2] 791.

[20] 02.

[3] 490.

[3] 835.

12.

[3] 297.

[14] 13.

[3] 840.