This study aims to study the safety of oil and gas pipelines under stress corrosion conditions and grasp the corrosion damage situation timely and accurately. Consequently, a non-destructive testing method combining magnetic flux leakage testing technology and a kernel function extreme learning machine improved by genetic algorithm (GA-KELM) is proposed. Firstly, the variation of the corrosion defect dimension and profile with time is obtained by numerical simulation. At the same time, the distribution of the magnetic flux leakage signal under different defect conditions is analyzed and studied. Finally, feature selection is carried out on the magnetic flux leakage signal distribution curve, and GA-KELM is used to predict the depth and length of corrosion defects so as to realize the non-destructive testing of the pipeline defects. The results show that different geometric features result in different magnetic flux leakage signal distributions. There is a corresponding relationship between the defect dimension and extreme value, area, and peak width of the magnetic flux leakage signal distribution curve. The GA-KELM prediction model can effectively predict the depth and length of corrosion defects, and the prediction accuracy is better than the traditional extreme learning machine prediction model.

It is well known that the safety and reliability of pipeline transportation are crucial. We are aiming at the problem that the residual life and residual strength of the defective elbow pipes are difficult to predict and usually need to be obtained through experiments. Consequently, a combined method of numerical simulation technology combined with a genetic algorithm to optimize neural network extreme learning machine (GA-ELM) is proposed. Firstly, the erosion characteristics of elbow pipes with different defects under the conditions of different impurity particle flow rates, particle sizes, and mass flow rates are analyzed by numerical simulation. At the same time, the effects of erosion defects of different sizes on the equivalent stress and residual strength of elbow pipes are also studied. Based on numerical simulation data, the extreme learning machine prediction model optimized by a genetic algorithm is used to predict the erosion rate, residual life, and residual strength and compared with the traditional ELM network model. The results show that residual strength of the elbow pipes with the increase of the depth and length of the defect, and increases with the increase of the width of the defect; the GA-ELM model can not only effectively predict the erosion rate, residual life and residual strength of defective elbow pipes, moreover its prediction accuracy is better than the traditional ELM model.