Based on machine learning prediction and experimental verification: The optimization of NH3-SCR performance on
Yue Zhu1, Fengyu Gao1, Yaxin Niu1
1School of Energy and Environmental Engineering, University of Science and Technology Beijing, Beijing 100083, China.
None:
To meet non-power industries like cement and glass urgent low-temperature denitrification demand address conventional Mn-based catalysts insufficient water-sulfur resistance and ternary systems low trial-and-error research and development efficiency this study used machine learning-experimental validation closed-loop strategy to optimize Ce/Co-modified MnNi-based NH3-SCR catalysts and clarify mechanisms. Based on 1064 Mn-based catalyst data nine algorithms were compared to build optimal XGBR model with R2= 0.88 RMSE= 6.90 realizing dual-target prediction of wide-temperature activity and water-sulfur stability for Mn-based ternary SCR catalysts with < 8 % error in low-to-medium temperature range. Due to ionic radius differences and thermodynamic synchrony, Ce forms discrete fluorite-phase CeO2 to preferentially adsorb SO2 protect Mn active sites Co promotes CoMnO3 solid solution for cross-metal electron cycling. MnNiCo retains 85 % NOx conversion after 60 h test at 200°C with 10 vol% H2O and 150 ppm SO2. Machine learning accurately captures performance trends under synergistic water-sulfur conditions. The study confirms catalyst poisoning universality and specificity are jointly determined by phase structure active site protection mechanisms and reaction conditions lattice interactions follow the Hume-Rothery rule and machine learning enables elemental ratio and temperature regulation to reduce activity loss.
More Related Videos
10:57Synthesis and Performance Characterizations of Transition Metal Single Atom Catalyst for Electrochemical CO2 Reduction
Published on: April 10, 2018
08:13Chemical Precipitation Method for the Synthesis of Nb2O5 Modified Bulk Nickel Catalysts with High Specific Surface Area
Published on: February 19, 2018
Related Concept Videos
02:17Reduction of Alkenes: Asymmetric Catalytic Hydrogenation
The metal catalyst used can be either heterogeneous or homogeneous. When hydrogenation of an alkene generates a chiral center, a pair of enantiomeric products is expected to form. However, an enantiomeric excess of one of the products can be facilitated using an enantioselective reaction or an...
00:55Nitriles to Amines: LiAlH4 Reduction
As shown below, the mechanism involves three steps. Firstly, the hydride ion acting as a nucleophile attacks the nitrile carbon to form an anion. In the second step, a second equivalent of the hydride ion attacks the anion to...
01:202° Amines to N-Nitrosamines: Reaction with NaNO2
01:13Preparation of Amines: Reduction of Amides and Nitriles
Amides can be reduced to primary, secondary, and tertiary amines using catalytic hydrogenation, active metals like Fe,...
01:20Amides to Amines: LiAlH4 Reduction
Amide reduction requires two equivalents of the reducing agent, acting as a source of hydride ions. As shown in the figure, the reaction is initiated with a nucleophilic attack by the hydride ion at the carbonyl carbon to form a tetrahedral intermediate.
01:30Preparation of Amines: Alkylation of Ammonia and Amines
Each alkylation step makes the nitrogen center more nucleophilic, which triggers successive alkylations until a quaternary ammonium salt is formed. Considering...