Fault risk prediction system for curtain door of train platform

The invention discloses a fault risk prediction system for a curtain door of a train platform. The fault risk prediction system comprises a plurality of sensors arranged at a plurality of preset positions of the curtain door and used for collecting real-time data; the gateway is positioned near the sensor and is used for transmitting the data acquired by the sensor to edge equipment; the edge device is used for processing the data transmitted by the gateway and transmitting the processed data to a server, the processing comprises performing fault risk prediction on the curtain door by using a deep learning model, and the processed data comprises a fault risk prediction result; the server is used for storing data and training the deep learning model; wherein the deep learning model performs fault risk prediction on the curtain door according to the log data of the curtain door, the environment data of the curtain door and the operation data of the curtain door, and the operation data of the curtain door is acq