Machine learning prediction of higher heating value of biomass

Recently, biomass sources are important for energy applications. There is need for analyzing of the biomass model based on different components such as carbon, ash, and moisture content since the biomass sources are important for energy applications. In this paper, an extreme learning machine (ELM) is used to estimate efficiency. ELM was implemented for single-layer feed-forward neural network (SLFN) architectures. Because biomass modeling could be a very challenging task for conventional mathematical, it is suitable to apply machine learning models which could overcome nonlinearities of the process. The main attempt in this study was to develop a machine learning model for prediction of the higher heating values of biomass based on proximate analysis. According the prediction accuracy (coefficient of determination and root mean square error) of the higher heating value of the biomass, the inputs' influence was determined on the higher heating value. According to the obtained results, fixed carbon has less moderate coefficient, ash has less correlation coefficient, and volatile matter has the most correlation coefficient. Therefore, the volatile matter percentage weight has the highest relevance on the higher heating value of the biomass. On the contrary, the ash has the smallest relevance on the higher heating value of the biomass based on machine learning approach.

Automated summary

The study developed a machine learning model for predicting the higher heating values of biomass based on proximate analysis. The input variables' influence on the higher heating value was determined based on prediction accuracy. Results showed that volatile matter had the highest correlation coefficient, while ash had the smallest relevance on the higher heating value of biomass.