PREDICTION OF CEMENT DEGREE OF HYDRATION USING ARTIFICIAL NEURAL NETWORKS

This paper presents the development of a computer model for the prediction of cement degree of hydration. The model is established by incorporating large experimental data sets using the neural networks (NNs) technology. NNs are computational paradigms, primarily based on the structural formation and the knowledge processing faculties of the human brain. Initially, the degree of hydration was estimated in the laboratory by preparing portland cement paste with the water-cement ratio ranging from 0.2 to 0.6, curing times from 0.25 days to 90 days, and subjected to curing temperatures from 3 deg C (37 deg F) to 43 deg C (109 deg F). A total of 390 specimens were tested, producing 195 data points divided into five sets. The networks were trained using data in Sets 1, 2, and 3. Once the NNs were fully trained, verification of the performance was carried out using Sets 4 and 5 of the experimental data. Results indicate that the NNs are very efficient in predicting concrete degree of hydration with great accuracy using minimal processing of data.

• Record URL:
  • http://www.concrete.org/Publications/InternationalConcreteAbstractsPortal.aspx.aspx?m=details&i=441
• 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:
  • BASMA, A A
  • Barakat, S A
  • Al-Oraimi, S
• Publication Date: 1999-3

Language

• English

Media Info

• Features: Figures; References; Tables;
• Pagination: p. 167-172
• Serial:
  • ACI Materials Journal
  • Volume: 96
  • Issue Number: 2
  • Publisher: American Concrete Institute (ACI)
  • ISSN: 0889-325X
  • Serial URL: https://www.concrete.org/publications/acimaterialsjournal.aspx

Subject/Index Terms

• TRT Terms: Cement; Cement paste; Concrete curing; Hydration; Mathematical models; Mathematical prediction; Neural networks; Portland cement; Water in concrete
• Subject Areas: Data and Information Technology; Highways; Materials; I32: Concrete;

Filing Info

• Accession Number: 00764913
• Record Type: Publication
• Contract Numbers: MSS-9257344
• Files: TRIS
• Created Date: Jun 7 1999 12:00AM