The flow stress of hot deformation about 0Cr13Mn stainless steel was experimentally studied by A Gleeble1500 thermo-mechanical simulator. The effects of deformed temperature, strain rate and strain to flow stress were analyzed. The prediction of RBF neural network with correlation between the flow stress and the chemical composition, deformed temperature, strain rate and strain, etc was established. Simulation data of the flow stress by RBF network with relationship between input and output for 0Cr13Mn stainless steel were stable. Accuracy of the prediction by RBF Neural network was higher than the regression precision by the multiple non-linear regression numerical models. Through a combination of the prediction by RBF neural network and numerical regression model of flow stress, the developing method of BPF neural network on-line calculation based on measured data of flow stress will be feasible under the condition of ensuring the accuracy of the premise.