基于PSO-RBF神经网络的温度试验箱控制

For the temperature control systems of sealed high-low temperature test chamber have characteristics of Temperature and humidity strong coupling, controlling time-delay, parameter changes, etc. It needs using the radial basis function (RBF) neural network controller which is optimized by an improved particle swarm optimization (PSO) algorithm to improve the control accuracy of temperature control system. In the optimization of RBF neural network using particle swarm optimization algorithm, firstly, RBF neural network need to adjust the parameters as particles, based on the fast convergence and global search of the PSO algorithm; secondly, The optimized parameters use as the initial values of RBF'parameters need to adjust; lastly, the second time optimization was conducted to get the final value of the parameters. The simulation results show that the simulation results show that the method proposed here decreases the overshoot, shortens the response time, and the steady state error is small, which can fit the outputs of the reference model and is better than common PID control in control effects．