NEURAL NETWORK MODEL FOR PREFORMED-FOAM CELLULAR CONCRETE

Cellular concrete (CC) is a lightweight material consisting of portland cement paste or mortar with a homogeneous void or cell structure created by introducing air or gas in the form of small bubbles during the mixing process. A major concern with CC production is achieving product consistency and predictability of performance. CC producers have generated much experimental data over the years, but the analysis of such data using traditional statistical tools has not produced reliable predictive models. This research studies the use of artificial neural networks (ANN) to predict the performance of CC mixtures. The ANN method can capture complex interactions among input/output variables in a system without any prior knowledge of the nature of these interactions and without having to explicitly assume a model form, which is generated by the data points themselves. The database assembled, the selection and training process of the ANN model, and its validation are described. Results show that production yield, foamed and unfoamed density, and compressive strength of CC mixtures can be predicted much more accurately using the ANN method compared to existing parametric methods.

• Availability:
  • Find a library where document is available. Order URL: http://worldcat.org/oclc/13846872
• Corporate Authors:

  American Concrete Institute (ACI)

  38800 Country Club Drive
  Farmington Hills, MI  United States  48331
• Authors:
  • Nehdi, M
  • Djebbar, Y
  • Khan, A B
• Publication Date: 2001-9

Language

• English

Media Info

• Features: Figures; References; Tables;
• Pagination: p. 402-409
• Serial:
  • ACI Materials Journal
  • Volume: 98
  • Issue Number: 5
  • Publisher: American Concrete Institute (ACI)
  • ISSN: 0889-325X
  • Serial URL: https://www.concrete.org/publications/acimaterialsjournal.aspx

Subject/Index Terms

• TRT Terms: Admixtures; Artificial intelligence; Cellular concrete; Compressive strength; Neural networks; Porous pavements; Portland cement concrete
• Uncontrolled Terms: Concrete performance
• Subject Areas: Highways; Materials; I32: Concrete;

Filing Info

• Accession Number: 00818409
• Record Type: Publication
• Files: TRIS
• Created Date: Oct 13 2001 12:00AM