Assignment And Optimization On Process Parameters Of Injection Agent In Refining

With the continuous growth of the national economy, China's demand of crude oil increases dramatically. Domestic crude oil cann't meet the need of development of economy. Because of the quality difference of the import crude oil compare greatly,the content of sulfur and acid Value are higher. Enterprises have to face new problem of equipment corrosion.In oil refining enterprises,crude oil is processed in atmospheric and vacuum distillation uint. It has occupied an important position in the total technological process.Corrosion and Protection is divided into two parts in uint:Process anti-corrosion and Equipment anti-corrosion.The former,"Desalting and three injections",is an available way to prevent corrosion at topping system of distillation towers in the crude distillation unit(CDU).the latter is, the protection for corrosion resistance materials, applied to high temperature systems.With complex technical process of refining,multi-points control and changing of the working condition constantly,Injections agent system is stayed on manual operation. Adjustment and period of injections agent system, the relation between adjustment and oil parameters may be further discovered. The paper discusses assignment and optimization on process parameters of injection Agent in both theory and practice. Attempt to find connotative rules and the optimum on process parameters.At present,according to the frequent change of oil and process data, statistical analysis methods cann't reflect the trend of change in process objectively.The paper puts forward fuzzy rules based on process input and output data to finding connotative rules in it.The method is a fuzzy classification theory of process parameters on the basis of fuzzy mathematics and fuzzy reasoning. It mainly provides support for analysising and optimizing process parameters by establishing fuzzy rules model.Using BP neural network build function among process parameters by the analysis and inspection on output parameters of fuzzy rules model.It makes the relationship of parameters distinct and accuracy.the BP neural network can reflect general law of parameters,but it cann't give the optimal results.We proposed to establishing 0-1 Integer Programming Model.Then, the output of model is optimized by using Genetic Algorithms and We are able to obtain optimal value of injections agent system under different work conditions. Practice test results show the feasibility by using artificial intelligence methods.