Designation Of Expert System For Raw Mix Slurry Blending In Production Of Alumina

Aluminum industry has significance to science and technology, economy, national defense and people's daily life, and alumina is the raw material for electrolytic aluminum. Because of the characteristic of ore in country, sintering method and combination of sintering method are adopted as the main techniques of alumina production. The quality of raw slurry made up by blending, which is the first process of Alumina Production by Sintering Method, not only directly relates to the quality of the sintered grog, but also make great influence on the alkali and water balance in the whole system.However, because of the process of pulp in APSM, in which time-delay and many environment effects exists, is too difficult to describe with precise and analytic mathematical models, and it can not be controlled properly by traditional methods. Based on the analysis of pulp in APSM and long-period knowledge of expert experience, a blending expert system based on the predictive model of raw slurry quality that adapts productive features of pulp in APSM has been developed in this paper.On the background of production process of alumina in Shanxi Brach China Aluminum. Firstly, the key factors that influence the quality of raw slurry are acquired by analyzing the process of blending, then the multi-step modeling method is proposed. According to it, before the predictive model of quality for raw slurry is established, the predictive model of content for components of Ca-Al silicate slime and alkali liquor should be established. On the research mentioned above, based on the blending theory, the knowledge of experts'experience derived from. long-period blending production, the knowledge abstract method is described, the Backus-Naur Form (BNF) is adopted as the knowledge representation. According to the knowledge characteristic and the knowledge BNF, the inference engine is realized through the hybrid of Heuristic Search among the rule collection, Forward Chaining in the interior rule collection, which implements the match computation. Then the paper simulate the control effect of raw slurry blending expert system by the software MATLAB. The result shows that the expert system of raw slurry blending based on the predictive model of quality has the faster calculation speed and the higher passing rate. The system which the paper designs makes strong value in production of alumina.