High-speed train axle temperature dynamic alarm threshold setting method based on monitoring data

The invention discloses a high-speed train axle temperature dynamic alarm threshold setting method based on monitoring data. The method is concretely implemented according to the following steps that step 1, the monitoring data of a train are preprocessed; step 2, an axle temperature prediction model is established; and step 3, a hot axle discrimination model is established. An axle temperature prediction value T' is obtained according to the axle temperature prediction model, and a relative error value R is obtained according to a real axle temperature value. The hot axle discrimination model can be established based on the prediction value. If the difference between the prediction value and the actual value suddenly increases, a hot axle fault possibly occurs so that a vehicle can be inspected in advance, and the fault caused by the hot axle of the vehicle can be prevented. The dynamic threshold of the hot axle level is defined according to the actual situation, and the hot axle discrimination standard is s