The Progressive Optimization Model on the Corrosion Rate of the Grounding Grid

Abstract:

Established a cross-validation of the model optimization algorithm in order to predict the corrosion rate of the grounding grid. Forward neural network input variables by principal component analysis to extract the main element, eliminating the correlation between variables; cross-validation method and change the termination of the neural network training conditions, the selection of network training model. The final simulation results show that, get a good grounding grid corrosion rate stability and generalization performance optimization prediction model can predict the corrosion rate of the grounding grid.

• Periodical: Advanced Materials Research (Volumes 712-715)
• Pages: 1090-1095
• DOI: https://doi.org/10.4028/www.scientific.net/AMR.712-715.1090
• Online since: June 2013
• Authors: Fen Lei Dai, Wen Qiang Xie
• Keywords: BP Neural Network (BPNN), Corrosion Rate Prediction, Cross-Validation, Model Optimization, Principal Component Analysis (PCA)

References

[1] Liu Liqiang, Luo Xianjue. Diagnosis grounding grid corrosion block hybrid optimization algorithm [J]. Electrical Engineering, 2009,29 (7) :33-38.

[2] Niu Tao, Luo Xianjue, Wang Sen.Fault diagnosis of grounding grid corrosion testability analysis [J]. Transactions of China Electrotechnical Society, 2010,25 (6) :192-198.

[3] Liu Jian,Wang Shuqi.Corrosion Diagnosis grounding grid testability [J] High Voltage Engineering, 2008,34 (1) :64-69.

[4] Zhao Bingjun, Zheng Hong-Wei. Hengshui area substation ground grid corrosion analysis [J]. Hebei Electric Power Technology, 2008,27 (6) :47-49.

[5] Fu Longhai,Wu Guangning. Qinghai-Tibet railway substation ground grid corrosion cracking point judgment [J] Electric Power System and Automation, 2006, 18 (1) :20-23.

[6] Liu Yugen,Wu Lixiang. Corrosion to optimize diagnostic utility analysis [J]. Chongqing University, 2008,31 (4) :417-420.

[7] Ma Wenjing,Zhang bo. Corrosion diagnosis method based on the regularization method of least squares base mesh research [J]. Heilongjiang Electric Power, 2012,34 (4) :278-284.

[8] Liu Yugen,Teng Yongxi. Grounding grid corrosion diagnosis research [J]. High Voltage Engineering, 2004,30 (6) :19-21.

[9] Wang Shuaihua,Qin Xiaoxia. MATLAB neural network in pipeline soil corrosion evaluation [J] Oil and gas storage and transportation, 2009,28 (11) :57-59.

[10] Wang Wan,Zhang Junming. Buried gas pipeline corrosion remaining life based on BP artificial neural network theory [J] Modern Machinery, 2010 (3) :44-46.

[11] Qu LiangShan, Li Xiaogang.By BP artificial neural network method build carbon steel Regional soil corrosion prediction model [J] Journal of Beijing University of Science and Technology, 2009,31 (12) :1569-1575.