Research on Optimization of Centrifugal Process Parameters Based on Support Vector Machine

The effect of centrifugal time, centrifugal temperature and centrifugal speed on the defective rate of dialyzer products in the process of dialyzer production was investigated by L
₂₅
(5
⁶
) orthogonal experimental design. The best combination parameters were obtained as 10 min, 65°C, 550 r/min. A predictive model of centrifugal processing technology based on support vector machine (SVM) was presented and the SVM algorithm was improved. Using the optimized support vector machine to establish the prediction model of the centrifugal process, compared with the current several main prediction modeling methods, it was found that the optimized support vector machine had better prediction accuracy. It shows that the research method has certain application value to the actual production of dialyzer centrifugation process.