Abstract: The backfilling material of pipe trenches is very important to ensure the safety of buried pipelines. Due to its small self-weight, controllable strength and self-compaction property, foam concrete is a preferred choice for backfilling buried pipe trenches. In order to study the protective effect of foam concrete on pipelines, buried pipe trenches crossing the oblique reverse faults were backfilled with foam concrete. Then, a nonlinear numerical model for buried pipelines crossing the faults in foam concrete/sand-pipeline-undisturbed soil structure was established through numerical simulation, so as to comparatively analyze the stress and strain of pipelines in the trenches backfilled with foam concrete and sand, respectively. Besides, the effect of the main performance parameters of foam concrete on pipeline strain was further analyzed. As shown by the results, compared with sand, the foam concrete backfilling buried pipe trenches could effectively reduce the stress and strain of pipelines under the dislocation of oblique reverse fault. Meanwhile, the great compressive strength of foam concrete has better effect on reducing the pipeline strain, while the friction coefficient of foam concrete and pipelines should not be too large but sufficient to ensure its friction with pipeline. Generally, the research results could provide reference for the application of foam concrete to backfill buried pipe trenches crossing the fault.In order to improve the prediction accuracy on internal corrosion rate of multiphase flow pipelines, the combined model of Improved Gravitational Search Algorithm (IGSA) and Random Forest Regression (RFR) was adopted, the number of decision trees and division characteristics of RFR model were optimized by IGSA, the influence of iteration times on prediction accuracy was discussed, the accuracy of model was verified by introducing the statistical indicators, and the characteristic variables affecting the corrosion rate were ranked. The results show that the variables other than pressure have great influence on the internal corrosion rate. The mean-square error of IGSA-RFR combined model in the same test set is 0.000 016 5, which is 2 orders of magnitude smaller than that of other models. Besides, its mean absolute percentage error is 0.524 1, which is 1 order of magnitude smaller than that of other models, and the coefficient of determination R2 is 0.999 6, which is the closest to 1 in all models. Hence, IGSA-RFR model is better than other models in terms of prediction accuracy and suitable for the research on prediction of internal corrosion rate of multiphase flow gathering pipelines.