Prediction of corrosion failure probability of buried oil and gas pipeline based on an RBF neural network

Risk assessment is critical to ensure the safe operation of oil and gas pipeline systems. The core content such risk determine failure probability pipelines quantitatively accurately. Hence, this study combines MATLAB neural network toolbox adopts an Radial Basis Functions (RBF) with a strong non-linear mapping relationship build corrosion prediction model for buried gathering transmission pipelines. Based on hazard identification failure, summarizes causes determines input output vectors based fault tree. According selected learning samples, through design training parameters, RBF that can predict system finally obtained. Taking 30 groups high-pressure storage as example, capability inputting bottom event outputting top demonstrated data. Our results show calculated tree analysis consistent predicted model. shown be reliable in predicting