Analysis reveals machine learning predicts corrosion in buried gas pipelines, suggesting improved evaluation methods.
Purpose With the gradual expansion of the national gas pipeline network, leakage accidents on buried gas pipelines caused by corrosion were increasingly frequent. However, there is still a lack of scientific and comprehensive evaluation methods for pipeline corrosion under complex environmental conditions. Design/methodology/approach By using methods such as field testing, laboratory experiments and machine learning, the authors analyzed the corrosion potential, macroscopic morphology, corrosion products and machine learning corrosion prediction. Based on these analyses, a corrosion grading model for various service environments was established, leading to the development of a comprehensive evaluation method for buried pipeline corrosion. Findings Based on field corrosion data from buried pipelines, the actual service environments of pipelines were categorized into four types: natural environments, steady-state DC environments, dynamic DC environments and cathodic protection environments. The key influencing parameters and corrosion prediction models for each environment were investigated, resulting in the development of a comprehensive evaluation method for buried pipeline corrosion. Originality/value Based on corrosion data from actual service pipelines, a corrosion grading model for four types of service environments was established, leading to the development of a comprehensive evaluation method for buried gas pipeline corrosion.
No takes yet. Share an insight, caveat, or question.
Yin et al. (2025) studied this question.
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: