Prediction of ratio of mineral substitution in the production of low-clinker factored cement by artificial neural network

Canpolat F., Yilmaz K., Ata R., Köse M. M.

Mathematical and Computational Applications, vol.8, no.1-3, pp.209-216, 2003 (Scopus) identifier

  • Publication Type: Article / Abstract
  • Volume: 8 Issue: 1-3
  • Publication Date: 2003
  • Doi Number: 10.3390/mca8020209
  • Journal Name: Mathematical and Computational Applications
  • Journal Indexes: Scopus, TR DİZİN (ULAKBİM)
  • Page Numbers: pp.209-216
  • Keywords: Artificial neural networks, Blended cement, Mineral admixtures in cement, Civil engineering materials design and optimization, Natural zeolites, fly ash, coal bottom ash, volcanic ash
  • Yıldız Technical University Affiliated: No


Artificial Neural Networks (ANN) has been widely used to solve some of the problems in science and engineering, which requires experimental analysis. Use of ANN in civil engineering applications started in late eighties. One of the important features of the ANN is its ability to learn from experience and examples and then to adapt with changing situations. Engineers often deal with incomplete and noisy data, which is one of the areas where ANN can easily be applied. Dealing with incomplete and noisy data is the conceptual stage of the design process. This paper shows practical guidelines for designing ANN for civil engineering applications. ANN is in cement industry: in the production of low-clinker factored cement, and in the derivation of composition of natural and artificial puzzolans in the production of high performance cement and concrete. By using ANN, a study to find out the optimum ratio of substitution and compression strengths was carried out.