The invention relates to the technical field of power system automation, and aims to provide a transient stability prevention and control method for a power system embedded with a deep belief network.The method comprises the following steps: S1, determining an active output fluctuation range and a load fluctuation range of a generator, generating N generator active output samples, obtaining a large amount of initial state data, and performing time domain simulation calculation on the initial state data to generate sample data; S2, establishing the deep belief network, training the deep beliefnetwork by using the sample data, and fitting the active power output of the generator and the transient stability of the system to generate a transient stability evaluator of the power system; S3, adding a cost constraint, a power flow constraint and a stable operation constraint to the NSGA-II algorithm based on a transient stability constraint condition, and building an NSGA-II evolutionary algorithm model; and S4, obtaining a generator output fluctuation range and a load fluctuation range of transient instability under a fault, performing iterative optimization on the NSGA-II evolutionaryalgorithm model and solving a prevention and control strategy.