Reducing NOx Emissions in Pyrolysis Machines for Biochar Production: A machine learning approach

Pyrolysis machines are commonly used in the production of biochar, but the combustion of
biomass during pyrolysis can lead to the emission of harmful nitrogen oxides (NOx).
In this talk, we will present a novel approach for minimizing NOx emissions using machine
learning and constraint optimization techniques.
We will first discuss the challenges of finding the optimal working points for a pyrolysis
machine, which can be a time-consuming and expert-driven process.
We will show how machine learning can be used to identify patterns in the data that are
difficult for humans to detect, allowing for more efficient identification of optimal operating
conditions.
Specifically, we will focus on how a machine learning algorithm can be used to model the
states of the pyrolysis machine, enabling us to predict NOx emissions for a given set of
inputs.
We will also discuss how constraint optimization techniques can be applied on top of the
learned model to minimize NOx emissions while ensuring that the pyrolysis machine
operates within its temperature and throughput limits.
Finally, we will evaluate our methods on an actual pyrolysis machine and demonstrate how
our approach can significantly reduce NOx emissions while maintaining high-quality biochar
production.
Our work has the potential to improve the sustainability of biochar production by reducing the
environmental impact of pyrolysis machines