Abstract: Flexible cables, widely used in dynamic scenarios such as industrial automation and marine engineering, are susceptible to fatigue failure due to cyclic bending, stretching, and twisting, leading to cumulative damage in internal conductors and insulation layers, reduced service life, and threats to equipment stability and personnel safety. By predicting the fatigue life of flexible cables, potential failures can be identified early, the normal operation of automated equipment can be ensured, and economic losses can be reduced. Fatigue life prediction methods for flexible cables are systematically summarized in this review. Methods based on finite element simulation (model construction and life model analysis) are subject to high model dependency and insufficient adaptability to complex operating conditions. Significant advantages in handling nonlinear complex operating conditions and improving prediction accuracy are shown by artificial intelligence methods, represented by neural networks, but challenges in correlating with real-time operating conditions are faced by them. The integration of digital twin frameworks and intelligent algorithms, enabling full-cycle prediction of dynamic life through real-time data acquisition and dynamic model calibration, is expected to be the mainstream trend in this field.