Corroded Subsea Pipelines Burst Pressure Prediction Utilizing Finite Element Data Using ANN

The Engineering industry is constantly exploring an effective and fast-solving method for complicated engineering problems. adaptation of artificial intelligent technology can diminish the time-consuming conventional analysis methods, especially in offshore engineering. For that reason, this study pursued to build a prediction model predict residual strength API 5L X42 subsea pipelines. An neural network used as analytical medium developing model. Three (3) physical shapes corrosion data with diverse level are designed input based on corroded pipelines true 2009 historical inspection South China Sea. output obtained from finite element produce burst pressure data. performance evaluated using mean squared error (MSE) absolute (MAE) which results 9.13 x 10-5 0.005499 respectively optimum predicted shows significant similarity line validation purposes. This expected provide quick reliability engineers reduce or eliminate massive work.