With the rapid development of urban rail transit and the continuous improvement of intelligent requirements, and in order to promote the transformation of the maintenance mode of urban rail vehicle traction drive systems from "planned repair"and"trouble repair" to "condition repair", the vehicle-ground integrated system solutions of urban rail vehicle condition repair was proposed. Then, intelligent operation and maintenance platform of FORESEE was created. Focusing on key components such as traction motors, converters, high-voltage parts, and running parts, a series of multi-information fusion online fault detection and status assessment methods that maximized the use of existing control signals were proposed, as well as prediction technology combined with degradation mechanism models and large data mining component life, and related technology were applied and verified, which could realize active and accurate maintenance of equipment, ensure the safety of urban rail vehicles and improve the economy of maintenance.