PRESSURE CONTROL OF FLASH TANK BASED ON SINGLE NEURON ADAPTIVE PSD-PID

Traditional material recovery technology of continuous process system will cause material waste and low output. The conventional PID control parameters cannot be adjusted online, and its control effect is difficult to meet the requirements. Combined with the advantages of PID control, this paper proposes a flash tank pressure control algorithm based on single neuron adaptive PSD-PID. The algorithm takes three input single neuron as the core to self-learn and tune the gain K, and the controlled object does not need to be accurately identified. The Matlab simulation results show that the proposed algorithm has superior response characteristics, better dynamic and static performance, and higher robustness. The experimental results on SMPT-1000 platform show that the proposed algorithm has fast speed and response and can effectively improve the utilization rate of material recovery and product yield. The effectiveness of PSD-PID algorithm is effectively verified by comparison.