Supercritical Fluid Extraction Process Parameters Optimization And Its Control Method

Supercritical CO2 extraction is a special extraction and separation technique under normal temperature, which has high yield and purity, less power consumption, safety and recover able etc., meanwhile, Supercritical CO2 has dual characteristics of both liquid and gas with good solubility and mass transfer properties in the extraction process, especially suitable for sensitive instability and chemical separation of natural product. It has been widely used in many fields, including the extraction and separation of the active constituents from natural aroma chemicals and perfume and the Chinese traditional medicine, food industry, petrochemical industry and light industry.In this paper, during the extractions separation experiment, using Ructus schisandrae as experimental material in supercritical CO2 extraction device, The relationship between process parameters and the product index is graphically illustrated, which provides a superb discussion of these experimental results. In the article, the mathematical model that is about of process parameter of supercritical extraction and yield is built, and the forecasting model of product yield is built, meanwhile, optimized model of supercritical extraction conditions is built based on supportvectormachine(SVM)and genetic algorithm. The main work and research results are shown in the following:(1) Analysis and study of the principle of supercritical CO2 extraction technology, equipments and application. The experiment is designed by using the supercritical CO2 extraction device combined with main evaluation index of effecting supercritical extraction, which are the extraction pressure, the extraction temperature and CO2 flow. This article focuses on the issues of relationship between parameters and index based on the experimental data.(2) The fundamentals and training process of SVM were clarified. Aiming at the complexity of the supercritical CO2 extraction process, the global optimal, training based on SVM is the characteristics of high efficiency and global search ability of genetic algorithm, set up the prediction model based on genetic algorithm of SVM. On the basis of the prediction model, the establishment of the system parameters based on multi-objective genetic algorithm optimization model, to yield the weighted processing. Using the optimization model, to yield can be obtained for the optimization goal, optimization of process parameters, such as extraction pressure, extraction temperature and subsequent tests provide reasonable optimization strategy for the enterprise.(3) The article reaches the fuzzy control detail based on the self-regulation of the weighted factor and supercritical fluid extraction temperature fuzzy control is implemented. Based on the extraction temperature self-tuning system simulation model and the simulation results are analyzed, with supercritical fluid extraction temperature as input to hot oil machine as the controlled object, design the fuzzy control rules.