Aiming at the problem of phased array radar recognition, a recognition method based on particle swarm optimization extreme learning machine (PSO-KELM) is proposed. On the basis of kernel extreme learning machine (KELM), particle swarm optimization (PSO) algorithm is introduced to obtain the optimal solution of kernel function parameters and improve the recognition accuracy of phased array radar. By constructing radar database, the method of particle swarm optimization extreme learning machine is used to identify radar data under different noise conditions, and compared with kernel function extreme learning machine, kernel support vector machine (KSVM) and semi-supervised and transfer learning(SSTL). The simulation results show that the recognition accuracy of this method is higher than other methods under different radar types and different noises.