(63c) Pyrolysis of Reed Canary Grass – ANFIS Modeling

The depletion of fossil fuel and the environmental impact of using fossil fuel as a main energy source have been subjects of intense research and policy interest in recent years. Pyrolysis of biomass to produce bio-energy is a promising process. However, with the resulting high cost, creating a cost effective chemical plant is very important. A comprehensive process model, which can be used to predict the production from pyrolysis of biomass, is therefore necessary. However, modeling is complex and challenging because of short reaction times, temperatures as high as a thousand degrees Celsius, and biomass of varying or unknown chemical compositions. As such a deterministic model is not capable of representing the pyrolysis reaction system. We propose a new kinetic reaction model, which would account for significant uncertainty. Specifically we have employed fuzzy modeling using the adaptive neuro-fuzzy inference system (ANFIS) in order to describe the pyrolysis of biomass. In this work, we firstly use this technique with Reed Canary grass. The resulting model has a good prediction of 99.8% of the pyrolysis yield at different temperatures. With this result, the pyrolysis yield can be predicted more accurate than the traditional deterministic model.