| Title: | Prediction of heel build-up on activated carbon using machine learning |
| Author(s): | Rahmani K; Mamaghani AH; Hashisho Z; Crompton D; Anderson JE; |
| Address: | "University of Alberta, Department of Civil and Environmental Engineering, Edmonton, AB T6G 1H9, Canada. University of Alberta, Department of Civil and Environmental Engineering, Edmonton, AB T6G 1H9, Canada. Electronic address: hashisho@ualberta.ca. Ford Motor Company, Environmental Quality Office, Dearborn, MI 48126, USA. Ford Motor Company, Research & Advanced Engineering, Dearborn, MI 48121, USA" |
| DOI: | 10.1016/j.jhazmat.2022.128747 |
| ISSN/ISBN: | 1873-3336 (Electronic) 0304-3894 (Linking) |
| Abstract: | "Determining the long-term performance of adsorbents is crucial for the design of air treatment systems. Heel buildup i.e., the accumulation of non-desorbed/ non-desorbable adsorbates and their reaction byproducts, on the surface/pores of the adsorbent is a primary cause of adsorption performance deterioration. However, due to the complexity of heel buildup mechanisms, theoretical models have yet to be developed to map the extent of heel buildup to the adsorption/desorption parameters. In this work, two machine learning (ML) algorithms (XGBoost and neural network (NN)) were applied to predict volatile organic compounds (VOCs) cyclic heel buildup on activated carbons (ACs) by considering the adsorbent characteristics, adsorbate properties and regeneration conditions. The NN algorithm showed better performance in prediction of cyclic heel buildup (R(2) = 0.94) than XGBoost (R(2) = 0.81). To analyze interaction between heel buildup and adsorbent characteristics, adsorbate properties, and regeneration conditions, partial dependency plots were generated. The proposed ML-based heel prediction methods can be ultimately used to: (i) optimize adsorption/desorption operating conditions to minimize heel buildup on activated carbon in cyclic adsorption/desorption processes and (ii) quickly screen various adsorbents for efficient adsorption/desorption of a particular family of VOCs by excluding adsorbents prone to high heel formation" |
| Keywords: | Adsorption *Charcoal Machine Learning *Volatile Organic Compounds Abraham descriptors Activated carbon Heel buildup Irreversible adsorption Neural Network; |
| Notes: | "MedlineRahmani, Keivan Mamaghani, Alireza Haghighat Hashisho, Zaher Crompton, David Anderson, James E eng Research Support, Non-U.S. Gov't Netherlands 2022/04/02 J Hazard Mater. 2022 Jul 5; 433:128747. doi: 10.1016/j.jhazmat.2022.128747. Epub 2022 Mar 25" |
