Surrogate model development for H2 separation via pressure swing
adsorption: evaluation of machine learning algorithms
Abstract
Within complex chemical engineering applications, subsystems or
technologies have to be pre-selected and evaluated, without being an
expert in each technology. In such cases, a surrogate model can help, if
it can be set up with easily available reliable tools and data from
publications. Here, a pressure swing adsorption (PSA) surrogate model
for hydrogen separation was developed. Therefore, 90 published data sets
were chosen for training and five different machine learning algorithms
were tested. For these data sets a random forest regression yielded the
best results when 80 % of the data was used for training and 20 % for
testing. The predicted hydrogen recovery deviated from the true value by
6.6 %. The procedure of the surrogate development and analysis is
described in this work as a transferable methodology to other scientific
questions, not limited to PSA applications.