Abstract: Abstract: Focused on the issue that the particle swarm optimization algorithm was prone to fall into the local optimal, the convergence accuracy was not high, and the convergence speed was slow, an improved particle swarm optimization algorithm based on hierarchical autonomous learning was proposed. Firstly, according to the particle fitness value and the number of iterations, the population was dynamically divided into three different classes. Then, according to the characteristics of different classes of particles, the local learning model, the standard learning model and the global learning model were respectively adopted to increase the particle diversity and reflect the effect of individual difference cognition on the performance of the algorithm, improved convergence speed and convergence precision of the algorithm. Finally, the HCPSO algorithm and the other three contrast algorithms were compared on 6 typical test functions respectively. The simulation results show that the convergence speed and convergence accuracy of the HCPSO algorithm were obviously improved, and the execution time of the algorithm and the time difference of the basic PSO algorithm were poor within 0.001 orders of magnitude. The algorithm performance was improved without increasing the complexity of the algorithm.