Prediction Method for Sugarcane Syrup Brix Based on Improved Support Vector Regression

The brix of syrup is an important parameter in sugar production. To accurately measure brix, a novel measurement method based on support vector regression (SVR) presented. With the resonant frequency and quality factor as inputs output, mathematical model relationship between frequency, factor, established. Simultaneously, particle swarm optimization (PSO) algorithm used to optimize penalty coefficient radial basis kernel function SVR improve performance model. calculation trained tested using collected experimental data. results show that mean absolute error, percentage root square error improved can reach 0.74 °Bx, 2.24%, 0.90 respectively, while determination 0.9985. simulation online actual production process proves excellent prediction PSO–SVR model, which thus be predict brix.