Abstract: Unlike aircraft where complex mechanical transmission devices can be used to determine the setpoint speed of an engine speed control system in a laboratory, this paper proposes a radial basis function (RBF) neural network algorithm for determining the setpoint speed of a turbofan engine based on the analysis of the influencing factors. An RBF neural network model for determining the setpoint speed of the engine is established using experimental data as training samples. Experimental results demonstrate that this method has the advantages of fast learning speed and high computational accuracy, making it effective for determining the setpoint speed of aero-engines. Keywords: RBF neural network, aero-engine, setpoint speed, fuel pump regulator 1. Introduction To study the working process of a turbofan engine's fuel control system and the fault mechanism of its field fuel control system, and to simulate field fault modes, an engine fuel integrated control laboratory was established with the fuel pump regulator and electronic integrated regulator as the core. However, in the laboratory, the engine's setpoint speed is unknown, and the engine's operating state cannot be determined. In an aircraft, the engine's setpoint speed is achieved through a complex mechanical transmission device, which is not feasible in a laboratory. Therefore, based on the analysis of the working principle of the speed control system of a certain turbofan engine, this paper, in the laboratory, measured the influencing factors of the engine's setpoint speed and determined the setpoint speed of the engine using the RBF network algorithm, thus solving the problem. For details, please click to download: Application of RBF Network in Determining the Setpoint Speed ​​of Aero-engines.