English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Tools annual

Global: Zendy Free Plan

Global: Zendy Tools monthly

Global: Zendy Plus monthly

Based on the research of particle swarm optimization, fuzzy neural network (FNN) and PID algorithm, this paper presents a solution to apply the improved fuzzy neural network PID algorithm to the pressure control system of flash tank. Particle swarm optimization is used to optimize the initial weights of the fuzzy neural network offline. The optimal weights of the fuzzy neural network are obtained to tune the PID parameters on-line and realize the real-time pressure control of the flash tank. The simulation results show that the improved Fuzzy Neural Network PID algorithm has shorter adjustment time, faster response and less overshoot than other advanced PID algorithms, and the control effect is better. There has been a great improvement in both speed and speed. Introduction Flash tank is a chemical unit which optimizes the complex industrial production process. Flash tank has the characteristics of fast speed, high energy efficiency and strong separation ability. It has been widely used in chemical manufacturing and pollutant recovery. Most of the domestic hydrocracking units being built or rebuilt are equipped with pre-flash tanks in front of the feed furnace of the atmospheric pressure fractionation tower [1] . It is generally believed that the flash tank can reduce the load of the heating furnace and the fractionation tower. The PID controller realizes control by proportional, integral and differential according to the difference between the system set value and the actual measured value [2] . It has better control effect for industrial process with simple system structure and production process. However, as the control precision of the system becomes higher and higher, it is difficult for the PID algorithm to meet the control requirements of the complex industrial system with non-linearity and large time-delay. In view of this, a solution which combines the PID algorithm, the fuzzy theory and the neural network model into the pressure control system of the flash tank is proposed. The improved particle swarm optimization algorithm is used to optimize the weight of the fuzzy neural network, and the improved fuzzy neural network PID algorithm is used to control the pressure of the flash tank. Pressure Control Principle of Flash Tank The mixture of gas and liquid produced by industry enters the flash tank for distillation and separation. The air in the flash tank is pumped out by vacuum pump, and the negative pressure environment in the tank is manufactured to achieve the purpose of gas-liquid separation. When the pressure in the flash tank changes, the pressure sensor will measure the real-time pressure in the tank. At the same time, the pressure setting value will be different from the measured value. The difference value and the change rate of the difference value will be input into the fuzzy neural network PID controller. The opening of the pneumatic valve will be controlled by the fuzzy neural network PID controller to realize the pressure control and ensure that the flash tank is in the normal pressure range. To improve the separation effect of materials.

Application of Improved Fuzzy Neural Network PID Algorithms in Pressure Control of Flash Tank