Flow regime recognition in spouted bed based on recurrence plot method

Recurrence plot and recurrence quantification analysis was applied into the analysis of the pressure fluctuation signals in spouted bed, and some parameters including recurrence rate, determinism, laminarity, averaged diagonal line length, trapping time and entropy were extracted from recurrence plots. Based on these characteristic parameters, least square support vector machine was applied to recognize the flow regimes, and parameters in least square support vector machine were optimized by adaptive genetic optimization algorithm. The recognition accuracies of packed bed, stable spouting, bubbly fluidized bed and slugging bed could reach 85%, 85%, 80% and 90% respectively.