Abstract: The oil-gas mixed transportation pipeline has a high internal corrosion rate. Hence, accurately predicting the internal corrosion rate of mixed transportation pipelines is of great significance to improve the integrity management of pipelines. In response to this problem, the evaluation index system and data set were constructed based on the field monitoring results at first, and the Kernel Principal Component Analysis(KPCA) was used for dimensionality reduction. Then, the Improved Grasshopper Optimization Algorithm(IGOA) was adopted to optimize the Extreme Learning Machine(ELM), the optimal network structure and the excitation function were determined, and the combined prediction model of KPCA-IGOA-ELM was proposed. With this model, prediction was performed based on 8 groups of data, and comparison was made with the results of other models to verify the prediction results. The results showed that three principal components were extracted by KPCA, and the network structure of ELM model was simplified. Among them, H₂S partial pressure, CO₂ partial pressure, calcium ion, chloride ion, temperature and flow rate have significant contribution to corrosion. In addition, the network structure of the optimal ELM model was determined as 3-32-1 by trial algorithm, and the excitation function was the Sigmoid function, having the minimum root mean square error. Moreover, the RMSE, MAPE and Theil IC of the KPCA-IGOA-ELM combined prediction model are 0.002 56, 2.458 34 and 1.113, respectively, and the average training time is 4.19 s, which are all superior to other models. It is proved that the KPCA-IGOA-ELM model is an excellent algorithm for oil-gas mixed transportation pipelines, which could be popularized and applied in practice.