Article history: A multi-layer perceptron neural network (MLPNN) model with Levenberg–Marquardt learning algo- Received 1 September 2015 rithm were applied to model CO capture by a novel amine solution called 4-diethylamino-2-butanol Received in revised form 11 February 2016 (DEAB). The MLPNN model predicted the CO concentration and temperature proﬁles along the height Accepted 12 February 2016 of the packed column as the model output. Inlet feed conditions of the absorber column (ﬂue gas and Available online 27 February 2016 amine) were selected as the inputs of the MLPNN model. Experimental data about random and structured packed columns were extracted from the literature and used to train the MLPNN model. In addition, a Keywords: systematic procedure, i.e. Taguchi method, was applied to obtain the signiﬁcant sequence of process Packed column parameters affecting CO removal efﬁciency and to optimize the variables in the absorber column. Five MLPNN model levels of ﬁve variables, including lean amine temperature, amine concentration, CO loading of amine, Taguchi method gas temperature, and amine ﬂow rate, were used for the optimization of the absorber column. The DEAB CO removal efﬁciency average absolute relative deviations (AARD) between the predicted results and the experimental data suggested that our MLPNN
International Journal of Greenhouse Gas Control – Elsevier
Published: Jun 1, 2016
It’s your single place to instantly
discover and read the research
that matters to you.
Enjoy affordable access to
over 12 million articles from more than
10,000 peer-reviewed journals.
All for just $49/month
It’s easy to organize your research with our built-in tools.
All the latest content is available, no embargo periods.
“Whoa! It’s like Spotify but for academic articles.”@Phil_Robichaud