Due to varying burial conditions and service environments, concrete pipes exhibit complex mechanical behavior. Existing theoretical, simulation, and test methods for determining the maximum stress of pipes have significant limitations, including excessive assumptions, low efficiency, and restricted applicable conditions. Therefore, there is an urgent need to propose a multi-factor associated method for pipe stress prediction. This paper proposed an innovative approach to finely simulate the mechanics response for concrete pipes under the coupling action of stress-seepage-fluid fields. The accuracy of this numerical simulation method was validated through full-scale test. Sensitivity analysis based on Morris sensitivity analysis theory was conducted on traffic load magnitude and speed, buried depth, groundwater table, fluid height and velocity, bedding strength, backfill strength, and pipe diameter. A dataset of “physical variables - maximum stress” for concrete pipes was established. A multi-factor-correlated prediction model of maximum stress for concrete pipe was proposed using XGBoost machine learning method optimized by Particle Swarm Optimization (PSO) algorithm. The results indicate that pipe diameter is highly sensitive; buried depth and traffic load magnitude are sensitive; groundwater table, bedding strength, and backfill strength are moderately sensitive; while fluid height, traffic speed, and flow velocity are insensitive. The XGBoost-PSO model demonstrates the highest accuracy and lowest error compared to BP, RF, and XGBoost models, with improvements in prediction accuracy of 59.6 %, 23.8 %, and 8.6 %, respectively. The model achieves RMSE of 0.118 and MAE of 0.213, demonstrating the suitability of the XGBoost-PSO model for predicting maximum stress for concrete pipes.