Novel predictive model for metallic structure corrosion status in presence of stray current in DC mass transit systems

Abstract

The novel method to analyze metallic structure corrosion status was proposed in the presence of stray current in DC mass transit systems. Firstly, the characteristic parameter and the influence parameters for the corrosion status were determined. Secondly, an experimental system was established for simulating the corrosion process within the stray current interference. Then, a predictive model for the corrosion status was built, using a support vector machine (SVM) method and experimental data. The data were divided into two sets, including training set and testing set. The training set was used to generate the SVM model and the testing set was used to evaluate the predictive performance of the SVM model. The results show that the relationship between the characteristic parameter and the influence parameters is nonlinear and the SVM model is suitable for predicting the corrosion status.

Keywords

DC mass transit systems / stray current / corrosion / support vector machine (SVM)

References

[1] CottonI, CharalambousC, AylottP, ErnxtP. Stray current control in DC mass transit systems [J]. IEEE Transactions on Vehicular Technology, 2005, 54(2): 722-730

[2] DarowickiK, ZakowskiK. A new time-frequency detection method of stray current field interference on metal structures [J]. Corrosion Science, 2004, 46(5): 1061-1070

[3] ZhuQ J, CaoA, WangZ F, SongJ W, ChenS L. Stray current corrosion in buried pipeline [J]. Anti-Corrosion Methods and Materials, 2011, 58(5): 234-237

[4] CaoA L, ZhuQ J, ZhangS T, HouB R. BP neural network predictive model for stray current density of a buried metallic pipeline [J]. Anti-Corrosion Methods and Materials, 2010, 57(5): 234-237

[5] HernandezF, PlascenciaG, KochK. Rail base corrosion problem for north american transit systems [J]. Engineering Failure Analysis, 2009, 16(1): 281-294

[6] CharalambousC, CottonI. Influence of soil structures on corrosion performance of floating-DC transit systems [J]. IET Electric Power Applications, 2007, 1(1): 9-16

[7] BertoliniL, CarsanaM, PedeferriP. Corrosion behaviour of steel in concrete in the presence of stray current [J]. Corrosion Science, 2007, 49(3): 1056-1068

[8] ZakowskiK, DarowickiK. Potential changes in an electric field and electrolytic corrosion [J]. Anti-Corrosion Methods and Materials, 2003, 50(1): 25-33

[9] ZakowskiK, DarowickiK. Some aspects of potential measurements in a stray current field [J]. Corrosion Reviews, 2001, 19(1): 55-67

[10] LiWeiStray current corrosion monitoring and protection technology in DC mass transit systems [M], 2004, Xuzhou, China University of Mining and Technology Press

[11] LeeC H, WangH M. Effects of grounding schemes on rail potential and stray currents in Taipei rail transit systems [J]. IEE Proceedings-Electric Power Applications, 2001, 148(2): 148-154

[12] XuS Y, LiW, WangY Q. Effects of vehicle running mode on rail potential and stray current in DC mass transit systems [J]. IEEE Transactions on Vehicular Technology, 2013, 62(8): 3569-3580

[13] MandalS K, ChanF, TiwariM K. Leak detection of pipeline: An integrated approach of rough set theory and artificial bee colony trained SVM [J]. Expert Systems with Applications, 2012, 39(3): 3071-3080

[14] JiangX L, XiaY F, HuJ L, ZhangZ J, ShuL C, SunC X. An S-Transform and support vector machine (SVM)-based online method for diagnosing broken strands in transmission lines [J]. Energies, 2011, 4(9): 1278-1300

[15] CollobertR, BengioS. SVMTorch: Support vector machines for large-scale regression problems [J]. Journal of Machine Learning Research, 2001, 1(2): 143-160

[16] AndresE, Salcedo-sanzS, MongeF, Perez-BellidoA. Efficient aerodynamic design through evolutionary programming and support vector regression algorithms [J]. Expert Systems with Applications, 2012, 39(12): 10700-10708

[17] HeY X, HeH Y, WangY J, LuoT. Forecasting model of residential load based on general regression neural network and PSO-Bayes least squares support vector machine [J]. Journal of Central South University of Technology, 2011, 18(4): 1184-1192

[18] YangS X, CaoY, LiuD, HuangC F. RS-SVM forecasting model and power supply-demand forecast [J]. Journal of Central South University of Technology, 2011, 18(6): 2074-2079