A platform for research: civil engineering, architecture and urbanism
A platform for research: civil engineering, architecture and urbanism
Indirect measure of shale shear strength parameters by means of rock index tests through an optimized artificial neural network
Shear strength is one of the most important features in engineering design of geotechnical structures such as embankments, earth dams, tunnels and foundations. Shear strength parameters describe how rock material resists deformation induced by shear stress. Rock shear strength parameters are usually measured through laboratory tests, and these methods are destructive, time consuming and expensive. In addition, providing good-quality core samples is difficult especially in highly fractured and weathered rocks. This paper presents an indirect measure of shear strength parameters of shale by means of rock index tests. In this regard, 230 shale samples were collected from an excavation site in Malaysia and shear strength parameters of samples were obtained using triaxial compression test. Furthermore, rock index tests including dry density, point load index, Brazilian tensile strength, ultrasonic velocity, and Schmidt hammer test were conducted for each sample. A particle swarm optimization-artificial neural network (PSO-ANN) integrated model was developed by setting the results of rock index tests as inputs and shear strength parameters as outputs of the model. The obtained correlation of determination of 0.966 and 0.944 for training and testing datasets show the applicability of the proposed model to predict shale shear strength parameters with high accuracy.
Indirect measure of shale shear strength parameters by means of rock index tests through an optimized artificial neural network
Shear strength is one of the most important features in engineering design of geotechnical structures such as embankments, earth dams, tunnels and foundations. Shear strength parameters describe how rock material resists deformation induced by shear stress. Rock shear strength parameters are usually measured through laboratory tests, and these methods are destructive, time consuming and expensive. In addition, providing good-quality core samples is difficult especially in highly fractured and weathered rocks. This paper presents an indirect measure of shear strength parameters of shale by means of rock index tests. In this regard, 230 shale samples were collected from an excavation site in Malaysia and shear strength parameters of samples were obtained using triaxial compression test. Furthermore, rock index tests including dry density, point load index, Brazilian tensile strength, ultrasonic velocity, and Schmidt hammer test were conducted for each sample. A particle swarm optimization-artificial neural network (PSO-ANN) integrated model was developed by setting the results of rock index tests as inputs and shear strength parameters as outputs of the model. The obtained correlation of determination of 0.966 and 0.944 for training and testing datasets show the applicability of the proposed model to predict shale shear strength parameters with high accuracy.
Indirect measure of shale shear strength parameters by means of rock index tests through an optimized artificial neural network
Jahed Armaghani, Danial (author) / Hajihassani, Mohsen (author) / Yazdani Bejarbaneh, Behnam (author) / Marto, Aminaton (author) / Tonnizam Mohamad, Edy (author)
Measurement ; 55 ; 487-498
2014
12 Seiten, 63 Quellen
Article (Journal)
English
An Example of Artificial Neural Network (ANN) Application for Indirect Estimation of Rock Parameters
| British Library Online Contents | 2008
An Example of Artificial Neural Network (ANN) Application for Indirect Estimation of Rock Parameters
| Online Contents | 2007
An Example of Artificial Neural Network (ANN) Application for Indirect Estimation of Rock Parameters
| Online Contents | 2007
Investigation of Indirect Shear Strength of Black Shale for Urban Deep Excavation
| DOAJ | 2024
Optimized Analysis Method for Evaluating the Shear Strength Parameters of Rock Joint Surfaces
| DOAJ | 2020