Prediction of restrained shrinkage crack widths of slag mortar composites by Takagi and Sugeno ANFIS models

BİLİR T., GENÇEL O., TOPÇU İ. B.

NEURAL COMPUTING & APPLICATIONS, cilt.27, sa.8, ss.2523-2536, 2016 (SCI-Expanded) identifier identifier

  • Yayın Türü: Makale / Tam Makale
  • Cilt numarası: 27 Sayı: 8
  • Basım Tarihi: 2016
  • Doi Numarası: 10.1007/s00521-015-2022-9
  • Dergi Adı: NEURAL COMPUTING & APPLICATIONS
  • Derginin Tarandığı İndeksler: Science Citation Index Expanded (SCI-EXPANDED), Scopus
  • Sayfa Sayıları: ss.2523-2536
  • Anahtar Kelimeler: ANFIS, Composite, Modeling, Mortar, Prediction, Restrained shrinkage cracking, LIGHTWEIGHT AGGREGATE CONCRETE, BLAST-FURNACE SLAG, DRYING SHRINKAGE, CREEP, STRENGTH, ASH, DURABILITY, FIBERS, SIZE
  • Eskişehir Osmangazi Üniversitesi Adresli: Evet

Özet

Shrinkage is an important parameter affecting crack development of mortars and concrete. With the occurrence of shrinkage cracks, the concrete starts to be exposed to the corrosion which significantly decreases the durability of concrete or mortars. In this study, the results of free shrinkage tests determining the length changes and ring test determination of the restrained drying shrinkage cracks are used for predicting the crack widths of granulated blast furnace slag fine aggregate mortars using adaptive-network-based fuzzy inference system (ANFIS). Subsequently, replacement ratios, drying time and free shrinkage length changes are used as inputs and crack width as output in order to predict the shrinkage cracking of these mortar types. The experimental test and the prediction results from the ANFIS model are compared with each other. It is clear that ANFIS can be employed directly in the prediction or discussion of the drying shrinkage cracks.