Week 3
In this week, we tried to analyze the data in some machine learning ways to get the best plasma - Dielectric barrier (dbd). During this week of working on the project, we encountered some problems. First, it became a bit confusing as to the purpose of this machine learning, not knowing whether we should derive a model from experimentally known datasets and then determine the combination of plasma with the highest conversion of reactants from a new set of datasets or fit several reaction conditions as a function of the conversion of the reaction and then compare it to the real results. Second, there are still some problems with our data pre-processing, if we force the control variables to be pursued and leave all other parameters constant, there will be very little data to use, and it will include some data with missing values. We determined 3 parameters which influent the chemical reaction which is “frequency”, “discharge power” and “CH4/CO2 molar ratio”. The RF code is almost co...