Prediction of The Uniaxial Compressive Strength of Rocks Materials

Prediction of The Uniaxial Compressive Strength of Rocks Materials

Nurcihan Ceryan (Balikesir University, Turkey) and Nuray Korkmaz Can (Istanbul University, Turkey)
DOI: 10.4018/978-1-5225-2709-1.ch002
OnDemand PDF Download:
List Price: $37.50


This study briefly will review determining UCS including direct and indirect methods including regression model soft computing techniques such as fuzzy interface system (FIS), artifical neural network (ANN) and least sqeares support vector machine (LS-SVM). These has advantages and disadvantages of these methods were discussed in term predicting UCS of rock material. In addition, the applicability and capability of non-linear regression, FIS, ANN and LS-SVM SVM models for predicting the UCS of the magnatic rocks from east Pondite, NE Turkey were examined. In these soft computing methods, porosity and P-durability secon index defined based on P-wave velocity and slake durability were used as input parameters. According to results of the study, the performanc of LS-SVM models is the best among these soft computing methods suggested in this study.
Chapter Preview

2. Background

Uniaxial compressive strength (UCS) of rock mass is very important parameter for the design of rock structures and can be measured directly and indirectly in laboratory.

Key Terms in this Chapter

Rock Material: A continium or polycrystalline solid between discontinuities consisting of an aggregate of minerals or grains. Its properties are governed by the physical properties of the materials of which it is composed of and the manner in which they are bonded to each other.

Least Squares Support Vector Machines (LS-SVM): It are least squares versions of support vector machines (SVM), which are a set of related supervised learning methods that analyze data and recognize patterns, and which are used for classification and regression analysis.

Soft Computing Methods: The guiding principle of soft computing is to exploit the tolerance for imprecision, uncertainty, approximate, reasoning and partial truth in order to close resemblance with human like decision making. Soft Computing is the fusion of methodologies for example fuzzy logic, artificial neural networks, and genetic algorithms, support vector machine and relevance vector machine, etc.

Fuzzy Interface System: Fuzzy inference is the process of formulating the mapping from a given input to an output using fuzzy logic. Then the mapping provides a basis from which decisions can be made, or patterns discerned.

Uniaxial Compressive Strength: The uniaxial compressive strength (UCS) is the maximum axial compressive stress that a right-cylindrical sample of material can withstand before failing. It is also known as the unconfined compressive strength of a material because confining stress is set to zero.

Porosity: Porosity (n) is ratio of void or pore volume to the total volume of rock sample. It is dimensionless and varies significantly for varies significantly for different rock types or even for the same rock type due to different factors.

Artificial Neural Network: Neural networks are a computational approach and based on massively parallel, distributed and adaptive systems, modeled on the general features of biological networks with the potential for ever improving performance through a dynamical learning process.

Regression: In statistical modeling, regression analysis is a statistical process for predicting the relationships among variables. It includes many techniques for modeling and analyzing several variables, when the focus is on the relationship between a dependent variable and one or more independent variables.

Complete Chapter List

Search this Book: