During the regular heavy passenger flow periods in the morning peak of urban rail transit, stations become crowded, prompting managers to commonly adopt station flow restriction strategies, resulting in preference and heterogeneity in passenger travel behavior. In order to gain a deeper understanding of the travel time choice behavior of different passenger groups during the morning rush hour and the mechanism of flow restriction strategies, this paper considers individual attributes, travel characteristics, and attitudinal preferences. It designs a questionnaire on passengers" willingness to choose travel times, taking into account different planned travel times and commuting durations as scenarios. Based on the questionnaire survey results of Shanghai Metro, age, passenger expected arrival time elasticity, and congestion sensitivity were selected as characteristic variables reflecting passenger heterogeneity. Subsequently, a multinomial Logit model (MNL) for passenger travel time selection and a mixed Logit model (ML) considering passenger heterogeneity were constructed. The model parameters are estimated using Biogeme software. The results indicate that, among all characteristic variables, travel duration has the most significant impact on passengers" travel time choices. Passengers are more inclined to avoid flow restriction when their planned departure times are closer to the start or end of flow restriction periods and when their commuting durations are longer. The analysis of individual heterogeneity reveals that passengers with flexible arrival times are more willing to adjust their travel times to avoid flow restriction or train congestion. Passengers with higher congestion sensitivity and younger passengers pay more attention to the number of people waiting in line.