Application of particle swarm optimization-based BP neural network PID controller in spray humidification

Abstract To enhance the spray pressure control capability of the spray humidification control system, a back-propagation neural network PID controller optimized using the particle swarm optimization algorithm was developed. Simulations and physical experiments were conducted with PSO-BP PID and BP PID as control groups. The simulation results indicate a 68.52% reduction in response time and a 15.7% decrease in overshoot. The physical experiment results reveal a 29.44% increase in response time, with the former demonstrating more stable control than the latter. The discrepancies between the simulation and physical experiment results are also analyzed.