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.

Recurrence plot method was used to extract the characteristic parameters from the pressure fluctuation signals in the spouted bed. Based on these characteristic parameters, least square support vector machine was applied to recognize the flow regimes, and adaptive genetic algorithm was used to optimize the parameters in support vector machine.Figure optionsDownload as PowerPoint slideHighlights
► Nonlinear phenomenon in spouted bed was presented by recurrence plot.
► Recurrence quantification analysis was used for pressure fluctuation signals.
► Least square support vector machine was used to recognize the flow regimes.