Abstract: In order to accurately predict the corrosion rate of oil and gas pipelines, a prediction model based on the improved Sparrow Search Algorithm(ISSA) optimized by Support Vector Regression(SVR) was established. Firstly, ISSA was obtained by adjusting the position update formulas of various sparrows of the traditional sparrow search algorithm(SSA).By comparing the iterative results of the two algorithms before and after the improvement, it is found that the convergence speed of ISSA has been greatly improved. Then, the penalty factor and kernel parameters of the SVR model are optimized through the ISSA to improve the prediction accuracy and generalization ability of the model. The prediction performance of the ISSA-SVR model is verified by using 50 sets of pipeline corrosion data of the South China Sea oilfield pipeline. The results show that compared with the unoptimized SVR model, the prediction results of the ISSA-SVR model manifest less error and higher correlation, which indicate that the ISSA-SVR prediction model can provide accurate data support for the corrosion rate assessment of oil and gas pipelines.