Research On Coke Oven Collector Pressure Intelligent Control Based On Operation-pattern Optimization

The study of the complex coke oven collector pressure system is a long-term process with innovation. In recent years, in order to improve the performance of the coke oven and low energy consumption in the production process to get a high product quality, many new advanced control strategies came into being. These new theories have been applied to actual production where improve productivity effectively and enhance the market competitiveness of the enterprises. Coke oven collector pressure control system is a complicated control system with a multi-variable, uncertain, nonlinear and strong coupling. In this article, the study of the intelligent control system is based on the operation-pattern optimization.Firstly, on the basis of a brief description of the technological process of coke oven collector pressure, a regression prediction model of the coke oven gas mainly collector pressure based on support vector machine (SVM) method is proposed. The simulation results of the actual pressures and the predicted show that the proposed method has higher forecast accuracy, which provides bases on the real-time decoupling control and the set-point optimization based on the operation mode strategy of the coke oven collector pressure system.Secondly,on the basis of the collector pressure control characteristics, a large number of historical data in production process and operating experiences, an operation-pattern optimization method is proposed based on the subtractive clustering algorithm for controlling coke oven collector pressure. The subtractive clustering algorithm is used to realize the pattern discovery, the pattern rule extraction, eventually forming the optimized operation pattern database in order to optimize the pressure set-points. The pattern reconfiguration strategy based on the model migration ideological is used to carry out the operation pattern revision. The simulation results demonstrate the effectiveness of the proposed method.Finally,based on the mathematical model of coke oven collector pressure control system, a self-tuning PID decoupling controller optimized by the improved glowworm swarm optimization (GSO) algorithm was put forward to control the collector pressure. The diagonal matrix decoupling method is used to eliminate the coupling between the control loops to obtain two single-input-single-output (SISO) channels. Then the improved GSO was exploited to tune PID controller parameters. The congestion degree factor is introduced to enhance the local search ability of the GSO algorithm and avoid the local excessive congestion.Above shows the design of coke oven collector pressure intelligent control.This method could well meet the requirements of the production. We achieve an efficient production and improve the economic efficiency of enterprises in this way. Besides, enterprises improve the quality of the product, achieve lower pollution, and get the lowest consumption with minimum cost.