Data-driven dynamic modeling and control of a surface aeration system

Abstract

In this study we have developed a support vector regression (SVR) based data-driven model for predicting two important design parameters of surface aerators, namely, the volumetric mass transfer coefficient (k_La) and fractional gas hold-up (ε _G). The dynamical state of the surface aerator system was captured by acquiring pressure fluctuation signals (PFSs) at various design and operating conditions. The most informative features from PFS were extracted using the chaos analysis technique, which includes estimation of Lyapunov exponent, correlation dimensions, and Kolmogorov entropy. At similar conditions the values of k_La and ε _G were also measured. Two different SVR models for predicting the volumetric mass transfer coefficient (k_La) and overall gas hold-up (ε _G) as a function of chaotic invariants, design parameters, and operating parameters were developed showing test accuracies of 98.8% and 97.1%, respectively. Such SVM based models for the surface aerator can be potentially useful on a commercial scale for online monitoring and control of desired process output variables.