Adaptive neural network PID controller design for temperature control in vacuum thermal tests

Temperature control is important for reliability testing of aerospace products in vacuum thermal environment. The traditional proportional-integral-derivative (PID) controller based closed-loop control system cannot guarantee the high precision requirements in the experiment temperature control. In this paper, an adaptive PID controller based on the radial basis function (RBF) neural network is designed to address the temperature control problem in the thermal vacuum tests. Simulation results show that the designed adaptive closed-loop control system can track the given references with better tracking performance, compared to the conventional PID control method.