Correlation Between Uniaxial Compressive and Shear Strength Data of Limestone Rocks by Regression Analysis and ANFIS Model

  • Masoud RashidiEmail author
  • Adel Asadi
  • Biltayib Misbah Biltayib
Conference paper
Part of the Advances in Science, Technology & Innovation book series (ASTI)


To determine rock mechanical properties like uniaxial compressive strength and shear strength accurately, it is required to put considerable time to find and collect suitable samples for laboratory testing. To improve the time and cost efficiency, many empirical relationships have been proposed in literature. The purpose of this study is to develop a model to correlate uniaxial compressive strength and shear strength data of intact rocks. In this study, two mathematical methods, adaptive neuro-fuzzy inference systems (ANFIS) and regression analysis, were used to correlate the uniaxial compressive and shear strength. A new approach based on artificial intelligence techniques is considered to develop and train UCS-τ data. A total of 40 sets of data were used to correlate UCS and τ data of limestone rocks. The resulted regression equation shows that the relationship between uniaxial compressive and shear strength has an acceptable determination coefficients of R2. Results of this research study has also indicated that, because of their acceptable accuracy in development of an efficient correlation between UCS and τ data, adaptive neuro-fuzzy inference systems are appropriate tools to correlate UCS-τ data, in addition to the regression model proposed in this paper.


Uniaxial compressive strength Shear strength Limestone rocks Adaptive neuro-fuzzy inference systems 


  1. 1.
    Asadi, A.: Application of adaptive neuro-fuzzy inference system for the assessment of excavation damaged zone using uniaxial compressive strength data. In: Schubert, W., Kluckner, A. (eds.) Proceedings of the ISRM Regional Symposium EUROCK 2015 & 64th Geomechanics Colloquium—Future Development of Rock Mechanics, pp. 291–296. Austrian Society for Geomechanics, Salzburg, 7–10 Oct 2015Google Scholar
  2. 2.
    Khanlari, G., Abdilor, Y.: Estimation of strength parameters of limestone using artificial neural networks and regression analysis. Aust. J. Basic Appl. Sci. 5(11), 1049–1053. ISSN 1991-8178 (2011)Google Scholar
  3. 3.
    Singh, M.: A document on: assessment of engineering properties of rock mass in civil engineering applications. In: IGS Working group on Rock Mechanics and TunnelingGoogle Scholar

Copyright information

© Springer Nature Switzerland AG 2019

Authors and Affiliations

  • Masoud Rashidi
    • 1
    Email author
  • Adel Asadi
    • 2
  • Biltayib Misbah Biltayib
    • 1
  1. 1.Petroleum Engineering DepartmentCollege of Engineering, Australian College of KuwaitKuwait CityKuwait
  2. 2.Department of Petroleum Engineering, Science and Research BranchIslamic Azad UniversityTehranIran

Personalised recommendations