Optimization of process parameters for anaerobic fermentation of corn stalk based on least squares support vector machine

Abstract

In order to improve the yield and efficiency of biogas produced from anaerobic fermentation of corn stalk, least squares support vector machine (LS-SVM) was used to optimize the pretreatment process parameters. Weight of corn stalk, ultrasonic duration time, alkali pretreatment (2% NaOH) time, and single/dual-frequency ultrasound were selected as the experimental factors of orthogonal experimental design (OED). A new modeling method combining LS-SVM and OED was proposed to establish the predictive model between cumulative biogas production (CBP) and pretreatment process parameters. The effect of experimental factors on CBP was analyzed by two-dimensional (2D) and three-dimensional (3D) contour maps of the predictive model. The optimum parameters for process pretreatment were as follows: weight of corn stalk 53 g, dual-frequency ultrasound, ultrasonic duration time 33 min, alkali pretreatment time 56 h. The CBP of the optimal conditions obtained was 22.69 L and was 14.13% higher than that of optimal conditions for OED.