Intelligent Evaluation Model for Cementing Quality Based on PSO-SVM and Application


Article Preview

The cementing quality is directly related to the normal operation of the gas well, therefore, the evaluation of cementing quality is key to the correctly use the gas well as well as to take measures to protect the gas well. In this paper, four first wave amplitudes at the same depth point when using the borehole compensated sonic logger with double transceiver technique to carry out the acoustic amplitude log operation are served as the discriminant factors to evaluate the cementing quality. Taking the engineering actual measured data as the learning samples and using the particle swarm optimization to optimize the parameters of support vector machine, this paper established the intelligent evaluation model for cementing quality based on particle swarm optimization (PSO) and support vector machine (SVM). The model employs the excellent characteristic of SVM which has high speed of solving and could describe nonlinear relation as well as the characteristic of PSO which has global optimization. Through test of engineering samples, the research result showed that this model has fast astringency and high precision, providing a new method and approach for the fast and accurate evaluation of the well cementing quality.



Edited by:

Dongye Sun, Wen-Pei Sung and Ran Chen




J. C. Liu et al., "Intelligent Evaluation Model for Cementing Quality Based on PSO-SVM and Application", Applied Mechanics and Materials, Vols. 71-78, pp. 4293-4299, 2011

Online since:

July 2011




[1] Chu Zehan. Sonic logging Priciple[M]. Beijing: Petroleum Industry Press, (1987).

[2] Liu Yufeng, Zhao Yafeng, Liu Xingbin, etal. Surveys no cement bond quality of well logging technology [J]. Oi1-gasfield Surface Engineering, 2004, 23(8): 61.

[3] Liu Xianjun, Liu Tangyan, Liu Shiqiong. We11 logging theory and its engineering applications[M]. Beijing: Petroleum Industry Press, (2006).

[4] Zhang Q, Benvenise A. Wavelet networks[J]. IEEE Transactions on Neural Network, 1992, 3(6): 889-898.

[5] Zhang J, Walter GG, Miao Y, etal. Wavelet neural netwokrs for function learing [J]. IEEE Transactions on Signal Processing, 1995, 43(6): 1485-1497.

[6] ZHANG Wei, SHI Yibing, ZHOU Longfu, LU Tao. An Intelligent Evaluation Method Based on Improved PSO-WNN for Cement Bond Quality[J]. Information an d Control, 2010, 39(3): 276-282.

[7] Vapnik V N. Statistical Learning Theory[M]. New York:John and Wiley, (1998).

[8] Cortes C, Vapnik V. Support-vector networks[J]. Machine Learning, 1995, (20): 273-297.

[9] JIANG An-nan, LIANG Bing. Feedback identifying seepage parameters of 3D aquifer based on particle swarm optimization and support vector machine[J]. Rock and Soil Mechanics, 2009, 30(5): 1527-1531.

[10] DU Xiao-kai, REN Qing-wen , ZHENG Zhi, et al. Back analysis of rock mechanic parameters based on coupling algorithm of adaptive particle awarm optimization and back-propagation neural network [J]. Journal of China Coal Society, 2009, 34 (12): 1610-1615.

[11] Chih-Chung Chang, Chih-Jen Lin. LIBSVM: a library for support vector machines[DB/OL]. http: /www. csie. ntu. edu. tw/~cj-lin / libsvm/ index. html, 2009-02-27.


Fetching data from Crossref.
This may take some time to load.