1. School of Agricultural Engineering, Jiangsu University, Zhenjiang 212013, China
2. Key Laboratory of Modern Agricultural Equipment and Technology, Ministry of Education, Jiangsu University, Zhenjiang 212013, China
3. College of Mechanical and Electrical Engineering, Shihezi University, Shihezi 832003，China
Abstract：Agricultural biomass energy has gradually become one of the main clean energy sources in modern industry in China. Laser-induced breakdown spectroscopy (LIBS) was used to accurately evaluate the calorific value (CV) of straw charcoal in this paper. Due to the defects of the traditional X-independent variable feature extraction method in LIBS quantitative analysis of CV, an XY bivariate feature extraction method is proposed. Firstly, the correlation between CV and main elemental content was analyzed, and the Y-type sensitive variables with extremely significant correlation (p<0.01) were selected, which mainly obtained the analytical line broadening band of C, O, H and Na in the form of carbon, aromatic ring and a carboxyl group. Meanwhile, the X-type sensitive variables related to CV were obtained by screening the regression coefficient threshold of the partial least squares regression (PLSR) model. When the threshold is 4×10-5, the cross-validation root means square error (RMSECV) decreases to the lowest value, and its corresponding variables are the analytical line spectra of Ca, Cr, Mg and K that can participate in crop growth. The GA-BP-Adaboost model was then developed based on the XY double characteristic variables extracted. When the mutation probability, crossover probability and relative error rate (RE) are set to 0.1, 0.95 and 0.01 respectively, the average relative error (AREP) and relative standard deviation (RSDP) of the optimal model are 2.39% and 2.97% respectively, which is 0.82% and 0.91% lower than that of XY-PLSR model. The results show that the XY bivariate feature extraction method combined with the GA-BP-Adaboost model can be used to accurately and quantitatively predict the CV of biomass carbon in the industrial process.
