Research on neural network predictive control scheme of industrial solid waste pyrolysis kettle

The thermal pyrolysis process of industrial solid waste involves characteristics such as nonlinearity, uncertainty, and high inertia, making traditional control methods difficult to apply effectively. To optimize the control performance of the thermal pyrolysis of industrial solid waste, a study was conducted on the current state of intelligent control research, and a predictive control strategy based on the Grey Wolf Optimizer (GWO) algorithm optimized Back Propagation (BP) neural network was proposed to improve the control performance of the thermal pyrolysis process of industrial solid waste. The GWO algorithm was used to improve the BP neural network, enhancing the accuracy of the predictive model. This improved model was then combined with Model Predictive Control (MPC) to achieve temperature control in the pyrolysis process. Comparative simulations between the GB-MPC control algorithm and the traditional PID controller showed that the GB-MPC model converged faster, exhibited smaller temperature fluctuations, and had less overshoot. The control effectiveness of GB-MPC was superior to that of the traditional PID control, significantly enhancing the control performance and stability of the industrial solid waste pyrolysis process. This research provides a reference for the further development of industrial solid waste pyrolysis.