Journal
CONSTRUCTION AND BUILDING MATERIALS
Volume 219, Issue -, Pages 164-175Publisher
ELSEVIER SCI LTD
DOI: 10.1016/j.conbuildmat.2019.05.113
Keywords
Stray current; DC corrosion; Subway; Q235A steel; Gas pipeline; Artificial neural network
Categories
Funding
- Future Scientists Program of Double First Rate of China University of Mining and Technology [2019WLKXJ029]
Ask authors/readers for more resources
Stray currents are widely presented in and around the DC transit system, which leads to serious electrochemical corrosion threat to buried gas pipelines passing through and around the system. The corrosive effect of stray current is a process that changes with corrosion time in the complex environment. For the first part of this paper, electrochemical corrosion of Q235A steel under the coupling of stray current and chloride ion was studied experimentally, and the electrochemical corrosion parameters were analyzed. In the second part, a fully connected artificial neural network with multiple inputs and multiple outputs was established based on the electrochemical experimental data. The model achieves good prediction accuracy for polarization curves, self-corrosion potential, corrosion current density and linear polarization resistance, which suggests that the ANN-based model may be a practical methodology to monitor the corrosion parameters of gas pipeline under coupling action of stray current and chloride ion. (C) 2019 Elsevier Ltd. All rights reserved.
Authors
I am an author on this paper
Click your name to claim this paper and add it to your profile.
Reviews
Recommended
No Data Available