A hybridized intelligence model to improve the predictability level of strength index parameters of rocks
- PDF / 1,989,984 Bytes
- 14 Pages / 595.276 x 790.866 pts Page_size
- 13 Downloads / 179 Views
(0123456789().,-volV)(0123456789(). ,- volV)
ORIGINAL ARTICLE
A hybridized intelligence model to improve the predictability level of strength index parameters of rocks Abbas Abbaszadeh Shahri1
•
Reza Asheghi1 • Mohammad Khorsand Zak2
Received: 9 October 2019 / Accepted: 17 July 2020 Ó Springer-Verlag London Ltd., part of Springer Nature 2020
Abstract In the current paper, the uniaxial compressive strength (UCS) and Young modulus (E) of rocks were predicted using a hybridized intelligence method. The model was developed using an optimum multi-objective generalized feedforward neural network (GFFN) incorporated with an imperialist competitive metaheuristic algorithm (ICA) and managed using 208 datasets of different physical and mechanical quarries from almost all over of Iran. Rock class, density, porosity, Pwave velocity, point load index and water absorption were datacenter components. The predictability and accuracy performance of the hybrid ICA-GFFN model were discussed using different error criteria and confusion matrixes. The observed 5.4% and at least 32% improvement in hybrid ICA-GFFN than GFFN and multivariate regression (MVR) demonstrated feasible and accurate enough tools that can effectively be applied for multi-objective prediction purposes. The influence of inputs on predicted outputs was also identified using two different sensitivity analyses. Keywords Hybrid model Sensitivity analysis Metaheuristic algorithm Strength index parameters Predictability level
1 Introduction The real-world complicated problems due to nonlinear constraints, interdependencies among variables and large solution spaces need to be optimized using capable techniques. Optimization, as a core component in problem solving, refers to find the best value of a set of variables for an objective function subject to a given set of constraints. The performances, benefits and great successes of such processes have widely been notified in the literature [10, 22, 48]. A design problem in rock engineering using uniaxial compressive strength (UCS) and elasticity modulus (E) usually involves many parameters of which some are highly sensitive. These two strength index properties of rocks have significantly been quoted in design approaches of civil, mining and construction engineering-oriented & Abbas Abbaszadeh Shahri [email protected] 1
Department of Civil Engineering, Roudehen Branch, Islamic Azad University, Tehran, Iran
2
Department of Applied Mathematics, Aligoudarz Branch, Islamic Azad University, Aligudarz, Iran
applications (e.g., tunneling, dam design, rock blasting, slope stability, rock mass classification, rock failure criteria, foundation engineering, underground excavation). Concerning approved and recognized difficulties in direct measurements of these parameters in both economical aspects and significant technical challenges in weak or highly weathered rocks [2, 4, 14, 16, 31, 37], producing optimized models that can provide more accurate results is demanded. From a practical perspective, a variety of pre
Data Loading...
