Statistical analysis of the results of mechanical tests of metal and pipes of trunk pipelines

Abstract

Modern approaches to processing large bulk of data accumulated as a result of mechanical testing, based on statistical analysis and machine learning methodology are discussed. The factors affecting the strength and durability of pipe products are considered. The stages of the initial data preparation are analyzed and the main steps of basic statistical processing, correlation and variance analyses, approaches to grouping and ranking of test data are discussed. The results of the developed approaches are demonstrated by the example of constructing a classification by steel grades and technical conditions of the pipe production according to the actual mechanical characteristics of the pipe metal. The real effect is shown on the example of the estimating the number of pipe defects that require priority to repair. The presented algorithms can be used as the elements of the formed information base and data banks in the field of pipeline transportation of oil and oil products. The developed approaches require a comprehensive testing and further development towards taking into account the actual loading of the pipe and assessing the failure probability.