Abstract
Knowledge advancement in artificial intelligence and blockchain technologies provides new potential predictive reliability for biomass energy value chain. However, for the prediction approach against experimental methodology, the prediction accuracy is expected to be high in order to develop a high fidelity and robust software which can serve as a tool in the decision making process. The global standards related to classification methods and energetic properties of biomass are still evolving given different observation and results which have been reported in the literature. Apart from these, there is a need for a holistic understanding of the effect of particle sizes and geospatial factors on the physicochemical properties of biomass to increase the uptake of bioenergy. Therefore, this research carried out an experimental investigation of some selected bioresources and also develops high-fidelity models built on artificial intelligence capability to accurately classify the biomass feedstocks, predict the main elemental composition (Carbon, Hydrogen, and Oxygen) on dry basis and the Heating value in (MJ/kg) of biomass...
Ph.D. (Mechanical Engineering Science)