High-speed train model prediction control method based on Koopman operator

The invention discloses a high-speed train model prediction control method based on a Koopman operator, and the method specifically comprises the steps: carrying out the input and output data collection through control input capable of exciting the dynamic characteristics of a high-speed train, and building a data set according to the generated output data and the control input data; according to the Koopman operator theory, a high-dimensional linear model corresponding to the high-speed train is established in an off-line mode by using an extended dynamic mode decomposition EDMD method; designing a model prediction controller according to the reference speed and the high-dimensional linearization model of the train at the current moment; the train high-dimensional linear model is updated online, the updated model is used for calculating the optimal control sequence meeting the constraint at the k + 1 moment, the first solution of the optimal control sequence serves as the control quantity to act on the high-