Pressure Prediction in Natural Gas Desulfurization Process Based on PCA and SVR

Abstract:

Pressure monitoring is an important means to reflect the running status of the natural gas desulphurization process. By using the data mining technology, the interaction relationships between the pressure and other monitoring parameters are analyzed in this paper. A pressure trend prediction model is established to show the pressure status in the natural gas desulfurization process. Firstly, the theory of Principal Component Analysis (PCA) is used to reduce the dimensions of measured data from traditional Supervisory Control and Data Acquisition (SCADA) system. Secondly the principal components are taken as input data into the pressure trend prediction model based on multiple regression theory of Support Vector Regression (SVR). Finally the accuracy and the generalization ability of the model are tested by the measured data obtained from SCADA system. Compared with other prediction models, pressure trend prediction model based on PCA and SVR gets smaller MSE and higher correlation. The pressure trend prediction model gets better generalization ability and stronger robustness, and is an effective complement to SCADA system in the natural gas desulphurization process.

• Periodical: Advanced Materials Research (Volumes 962-965)
• Pages: 564-569
• DOI: https://doi.org/10.4028/www.scientific.net/AMR.962-965.564
• Online since: June 2014
• Authors: Yan Chao Shao*, Liang Jun Xu, Yan Zhu Hu, Xin Bo Ai
• Keywords: Desulfurization Process, Multiple Regression, PCA, Pressure Prediction, SVR

References

[1] Yu Yanqiu, Zhang Xiaogang, Lin Hongqing, Liu Xinling, Zhang Xiaoyan, Safety monitoring and control technology of a high H2S natural gas purificationplant: A case study from thePuguang Gas Field, Sichuan Basin, NATUR. GAS IND. VOLUME 34, ISSUE 3, pp.1-5, 3/25/(2014).

[2] Xia Taiwu, Yuan Shuhai, Song Bin, Zhang Wei, Application of Safety Integrity Level (SIL) and the Hazard and Operability Analysis (HAZOP) in a natural gas purification, NATUR. GAS IND. VOLUME 31, ISSUE 3, pp.1-5, 03/(2011).

[3] Wang Zhengquan, Wang Yao, Gao Chao, Xi Hongzhi, Wang Yi, KuangGuozhu, Adaptive Analog Calculation of Gas Desulfurization Unit, CHEMICAL ENGINEERING OF OIL & GAS. Vol. 39, NO. 3, pp.204-209, 03/07/(2010).

[4] Zhao Guangshe, Zhang XiRen, SVM Classification Method Based on Principal Component Analysis, Computer Engineering & Applications. NO. 03, pp.37-38, 03/(2004).

[5] Vapnik V, Golowich S, Smola A, Support vector method for function approximation, regression estimation, and signal processing. In: Mozer M, Jordan M, PetscheT (eds). Neural Information Processing Systems, MIT Press, 1997, 9.

[6] Ma W T．Gas emission forecast based on wavelet transform and genetic least square support vector machine[J]. Journal of Mining and Safety Engineering, 2009, 26(4): 524 528.

[7] Shen Z X, Huang X Y, Ma X X. Fault diagnosis method based on empirical mode decomposition and support vector machine[J]. Control and Decision, 2009, 24(6): 889-893.

[8] Zhang M G, Short-term load forecasting based on support vector machine regression[C]. 4th IntConf on Machine Learning and Cyberntics, Guangzhou, 2005: 4310-4314.

DOI: 10.1109/icmlc.2005.1527695

[9] Chih-Chung Chang, Chih-Jen Lin, LIBSVM: A library for support vector machines, ACM Transactions on Intelligent Systems and Technology (TIST), volume. 2, Issue 3, April 2011, Article No. 27, doi: 10. 1145/1961189. 1961199.

DOI: 10.1145/1961189.1961199