Based on a self-organized probabilistic neural network (PNN) paradim, a parallel network can be used to sort data parameters into classes with high sorting accuracy and fragmentation. The PNN implements the statistical Bayesian strategy by computing a joint probability density over all input parameters to match a group of candidate data classes, the sorting is accomplished by assigning the inputs to most likely group with highest probabílity density estimate. Then the prospect of applying the self-organized PNN to ESM pulse data sorting will be shown，and a system including self-organized PNN and pulse repeating interval sorting will be discussed under the limited conditions of the sorting after lots of emulated experiments.