Particle Swarm Optimization Algorithm and its Application in Parameter Identification of Generator Set Speed Regulation System

As one of the main systems for the control of generator sets, the regulation quality and dynamic characteristics of generator speed regulation system not only affect the economy and safety of the unit itself. The voltage recovery method only obtains the parameters of the generator set speed regulation system from the perspective of physical significance, ignores the influencing factors of the actual environment, and is easy to produce unstable parameter results. Therefore, this paper proposes a particle swarm improvement algorithm based on culture algorithm to identify the parameter values of the generator set speed regulation system. Firstly, based on the PMU data, the systematic deviation of the measurement data is taken as the value of the data to be identified, and the process of unified identification with other system parameters is carried out. Secondly, in order to obtain the optimal prediction value of system parameter identification, the particle swarm algorithm is improved based on the cultural algorithm, and the formal knowledge and normative knowledge in the cultural knowledge belief space are used to optimize the particle population, and the excellent particle individual information and particle population information are effectively retained, which improves the speed and stability of the algorithm for the parameter identification of the generator set speed regulation system. The MATLAB simulation results show that the particle swarm optimization algorithm identifies the parameters of the speed regulation system under the condition that the identification parameters are uniform Be better and better.