Oil and gas pipelines are affected by many factors, such as pipe wall thinning and pipeline rupture. Accurate prediction of failure pressure of oil and gas pipelines can provide technical support for pipeline safety management. Aiming at the shortcomings of the BP Neural Network (BPNN) model, such as low learning efficiency, sensitivity to initial weights, and easy falling into a local optimal state, an Improved Sparrow Search Algorithm (ISSA) is adopted to optimize the initial weights and thresholds of BPNN, and an ISSA-BPNN failure pressure prediction model for corroded pipelines is established. Taking 61 sets of pipelines blasting test data as an example, the prediction model was built and predicted by MATLAB software, and compared with the BPNN model, GA-BPNN model, and SSA-BPNN model. The results show that the MAPE of the ISSA-BPNN model is 3.4177%, and the R 2 is 0.9880, both of which are superior to its comparison model. Using the ISSA-BPNN model has high prediction accuracy and stability, and can provide support for pipeline inspection and maintenance.
KEYWORDSOil and gas pipeline; corrosion defect; failure pressure prediction; sparrow search algorithm; BP neural network; logistic chaotic map
Nomenclature
P FExperimental value of pipeline failure pressure PF Predicted value of pipeline failure pressure R eRelative error