Abstract: As an important component to ensure the normal operation of urban rail transit power supply system, UPS (uninterruptable power system) equipment affects the normal operation of the power supply system with working status and performance. Taking the accumulated historical data of Shanghai rail transit power supply system UPS equipment as basis, a status evaluation system of the equipment is designed. By adopting the BP neural network intelligent algorithm, the evaluation system rule scoring optimization and fault prediction are studied. The system has the function of accurately assessing the health status and predicting the hidden dangers of UPS equipment.