Application of Machine Learning Models with Numerical Simulations of an Experimental Microwave Induced Plasma Gasification Reactor
Abstract
Climate change continues to rage as an international and multi-faceted issue that requires immediate attention. Waste-to-energy technologies are one type of emerging solution that will help to mitigate several factors that contribute to climate change. These technologies can utilize municipal solid waste streams as a form of renewable energy while simultaneously reducing greenhouse gas emissions. One type of waste-to energy technology that is currently emerging as an efficient and viable option is microwave-induced plasma gasification. This thesis aims to contribute to the future development of this technology by providing an in-depth literature review of how this technology physically operates and can be numerically modeled. Additionally, this thesis reviews literature of machine learning models that have been applied to gasification to make accurate predictions regarding the system. Finally, this thesis provides a framework of how to numerically model an experimental plasma gasification reactor in order to inform a variety of machine learning models. The machine learning models were able to achieve a high degree of accuracy (MAE = 0.011) for predicting the proportion of the reactor that is greater than 2000K given the input variables of reactor geometry and plasma flame temperature.
Document Details
- Document Type
- Technical Report
- Publication Date
- Mar 01, 2022
- Accession Number
- AD1174728
Entities
People
- Owen D. Sedej
Organizations
- Air Force Institute of Technology