Measurement and prediction of correction factors for very high core compressive strength by using the adaptive neuro-fuzzy techniques Traad Mohammed Al-zharani a , Ramazan Demirboga a,b , Waleed Hassan Khushefati a,⇑ , Osman Taylan a a King Abdulaziz University, Engineering Faculty, Civil Engineering Department, Jeddah, Saudi Arabia b Atatürk University, Engineering Faculty, Civil Engineering Department, Erzurum, Turkey highlights  Cores with different h/d were extracted from a slab block of HSC.  Molded samples from the same mixes were also prepared.  Correction factors were changed between 1.06 and 1.21 for slab.  A comparative study was made using the adaptive neuro-fuzzy techniques.  Outcomes were assessed statistically to evaluate the performance of ANFIS models. article info Article history: Received 13 April 2016 Received in revised form 6 June 2016 Accepted 9 June 2016 Keywords: Core slenderness High strength concrete Adaptive neuro-fuzzy Core compressive strength Correction factor abstract In this study the relationship between the core compressive strength with respect to reference samples and different core sizes with different slenderness ratio, length to diameter (L/D) were investigated. In addition, a comparative study was carried out by a hybrid neuro-fuzzy (ANFIS) technique, the core cor- rection factors were evaluated by statistical methods for comparing the performance of four different ANFIS approaches. The Gaussian membership functions were used for defining linguistic terms. The back propagation multi layer (BPML) and hybrid learning algorithms with grid partition were employed for the development of the ANFIS models. Experimental results showed that the core strength was increased with the decrease of slenderness ratio and have ranged between 0.95 and 1.21. The ANFIS model results showed that it could be used an efficient tool for the estimation of the core correction factor of very high strength concrete. The ANFIS model in the current study performs sufficiently in the estimation of core correction factor of high strength concrete, which particularly estimates closely following the actual val- ues. The ANFIS model with hybrid learning algorithm of grid partition was able to produce the most accu- rate model outcomes for estimating the correction factor among the examined models. Ó 2016 Elsevier Ltd. All rights reserved. 1. Introduction The compressive strength of concrete is a generally used an important criteria for the mix design of concrete. But, the compres- sive strength tests take time. In addition, it is impossible to correct even if tests result do not meet the design compressive strength, because the test is usually performed on the 7th and 28th day after placing of concrete into the form at construction site. That is why, realistic and precise strength estimation before casting of concrete are very significant, also for some structural cases, after long ser- vice life exposure to different environmental conditions, evalua- tion for concrete strength is needed. There are currently many methods used to estimate in-situ strength, each providing unique benefits such as economics, pre- vent delaying of estimation of strength, etc. However, many of these techniques can introduce all variables that affect accurate estimation. A simple method is presented for the determination of an equivalent specified strength of concrete, using a number of core tests, which can be substituted directly for the specified strength in conventional design equations to assess the safety of an existing structure. The method is developed from investigations concerned with the interpretation of core strength data and the strength of concrete in structures. High compressive strength of concrete ranges from 50 to 125 MPa is used in the construction of high- rise buildings and long span bridges in many parts of the world. There is great deal of differences in behavior between normal http://dx.doi.org/10.1016/j.conbuildmat.2016.06.019 0950-0618/Ó 2016 Elsevier Ltd. All rights reserved. ⇑ Corresponding author. E-mail address: wkhushefati@kau.edu.sa (W.H. Khushefati). Construction and Building Materials 122 (2016) 320–331 Contents lists available at ScienceDirect Construction and Building Materials journal homepage: www.elsevier.com/locate/conbuildmat