System parameter identification method and device based on unsupervised learning

The invention discloses a system parameter identification method and device based on unsupervised learning, and the method comprises the steps: constructing a state-space equation representing a target system, the state-space equation comprises a state equation used for representing the relation between the input of the target system and a state variable, and the state equation is used for representing the relation between the input of the target system and the state variable; the observation equation is used for representing the relation between the state variable and the output of the target system, and the state equation comprises parameters to be identified; arranging the state-space equation as a first state-space equation which represents known parameters and contains to-be-identified parameters in a parameter separation form; matching with the first state-space equation, constructing a neural network model, the input and output of the neural network model corresponding to the input and output of the fi