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 complete, and the feature importance can be selected. However, there may be some problems with the input data and the results are not as expected.



Haoyu seems to have misunderstood the direction of our study and his independent variables all become CH4/CO2 molar ratios


评论

发表评论

此博客中的热门博文

Week 2

  It's a new week and we've got reaction-related data, a total of 1180 entries, each with about 20 parameters. Through investigation and questioning we learned the direction of optimization, first we need to select a group of plasma combinations that make the conversion of CO2 and CH4 high, and then analyze the effect of other parameters on the reaction in the selected plasma combinations. So as a first step we want to find the plasma combination that we want to study by means of machine learning. At the same time, Zi'ao needs to find relevant literature to support our next choice of which parameters to explore for the effect on the reaction. For the machine learning models, we roughly determined that Qingyue is responsible for the random forest model, Siyuan builds a BP-neural network, and Haoyu prepares an SVM model.
阅读全文

Week1

图片
This week we had an initial look at plasma-catalyzed chemistry and divided up the work among each of us, with Zi'ao doing a survey of the chemistry and plasma-related literature and the rest of us considering which machine learning models to use to optimize the reactions.
阅读全文