Hybrid intelligent control of continual carbonation
decomposition process
1.College of Automation Engineering, Nanjing University of Aeronautics and Astronautics, Nanjing, Jiangsu 210016, China; 2.School of Physics and Electronics, Central South University, Changsha, Hunan 410083, China; 3.School of Information Science and Engineering, Central South University, Changsha, Hunan 410083, China
Abstract：Due to the long timedelay and complex industrial process of continual carbonation decomposition, the optimal control was difficult to be described by mathematical models. To control the optimal resolution ratio and the last decomposition ratio, the intelligent control system with considerations of expert control and predictive control strategies was proposed for continual carbonation decomposition process of sodium aluminate solutions. The principle knowledge and expert experience was applied to establish expert knowledge bases to deal with fluctuations in operating conditions and equipment faults, and to output the fourth and the fifth control valves to realize stable control in normal operational conditions by slurry composition for every cell. A neural network predicting model was set up to forecast the next output of system and feedback to modify the output of expert control model. The practical results show that eligible ratio of decomposition ratio is increased by 4% with increased average value of decomposition ratio by 0.95%. The influence of long timedelay is conquered effectively, and the process of continual carbonation decomposition is optimally controlled by the proposed method.
2014, Vol. 35 
