Chemical Drying Classification Model Based on Knowledge-Improved Cultural Algorithm

Abstract

The drying of PVC is a complex operation, and the moisture content of the product is affected by several parameters. In order to monitor and evaluate the quality of PVC drying products in chemical plants in real time, this paper uses the knowledge-improved cultural algorithm(CA) to construct a chemical drying classification model, and uses the model to predict the moisture content of PVC. The CA optimized by genetic algorithm makes the population space evolve and avoids the algorithm falling into local optimum in the process of target optimization. In the PVC fluidized drying experiment, the classification model constructed in this paper is used to predict the drying moisture content and quality of PVC products, and the actual production data is compared with the predicted data. The comparison results show that the predicted value is not much different from the actual value, which proves that the model has good prediction accuracy.