Roads and Bridges - Drogi i Mosty
9, 3, 2010, 39-54

Application of machine learning to determine properties of concretes modified with addition of coal ash

Maria Marks Mail
Instytut Podstawowych Problemów Techniki PAN, Warszawa

Abstract


In the paper two algorithms of the machine learning are used in order to determine the durability of concrete modified with circulating fluidized bed combustion (CFBC) ash from hard coal and from brown coal. The rapid chloride permeability test, according to Nordtest Method BUILD 492, was used for determining the chloride ions penetration in concrete. The frost salt scaling tests were performed according to the Swedish Standard method SS 137244. In both cases the performed tests provided databases used as training sets to generate the rules describing the relations between material composition and durability parameters. The rules generated by computer programs AQ21 and WEKA using J48 algorithm provided means for adequate categorization of plain concrete and concrete modified with CFBC fly ash as materials of good and acceptable resistance to chloride penetration as well as materials resistant or not resistant to the surface scaling caused by freezing cycles.

Full Text:

PDF

Application of machine learning to determine properties of concretes modified with addition of coal ash

  
Marks, Maria. Application of machine learning to determine properties of concretes modified with addition of coal ash. Roads and Bridges - Drogi i Mosty, [S.l.], v. 9, n. 3, p. 39-54, apr. 2010. ISSN 2449-769X. Available at: <>. Date accessed: 22 Sep. 2019.