A hybrid computing model to predict rock strength index properties using support vector regression
- PDF / 4,040,129 Bytes
- 16 Pages / 595.276 x 790.866 pts Page_size
- 84 Downloads / 219 Views
ORIGINAL ARTICLE
A hybrid computing model to predict rock strength index properties using support vector regression Abbas Abbaszadeh Shahri1 · Fardad Maghsoudi Moud2 · Seyed Poorya Mirfallah Lialestani3 Received: 1 January 2020 / Accepted: 26 May 2020 © Springer-Verlag London Ltd., part of Springer Nature 2020
Abstract The uniaxial compressive strength (UCS) and elasticity modulus (E) are two of the most quoted rock strength parameters in engineering application. Due to approved technical difficulties indirect measurements, the tendency for determining these parameters through predictive models using simpler and cheaper tests in practical oriented applications have widely been highlighted. In this paper, a new hybridized multi-objective support vector regression (MSVR) model integrated with the firefly metaheuristic algorithm (FMA) was developed to touch upon a computational method in rock engineering purposes. The optimum internal parameters were adjusted through parametric investigation using 222 physical and mechanical rock properties corresponding to a variety of quarried stones from all over Iran. The accuracy and robustness of models were evaluated using different error indices, the area under curve for receiver operation characteristics (AUCROC) and F1-score criteria. Comparing to MSVR, the predictability level of UCS and E showed 8.35% and 5.47% improvement in hybrid MSVR-FMA. The superior and more promising results imply that hybrid MSVR-FMA as a flexible alternative can be applied for rock strength prediction in designing of construction projects. Using tow sensitivity analyses, the point load index and P-wave velocity were distinguished as the main effective factors on predicted UCS and E. Keywords Hybrid model · Predictability level · Multi-objective · Quarried stone · Rock strength · Firefly algorithm
1 Introduction The natural stones as one of the efficient but oldest recognized materials provide many possibilities in different civil and construction applications (e.g., building industry, road base, paving, concrete, and asphalt). However, due to heterogeneity of these materials plethora and quite variable engineering characteristics can be observed. Strength properties, durability, attractiveness (appearance and color), cost, economy and quarrying susceptibility are the primary common criteria in selecting the appropriate building stones. In specific applications, some other * Abbas Abbaszadeh Shahri [email protected] 1
Department of Civil Engineering, Roudehen Branch, Islamic Azad University, Tehran, Iran
2
Department of Earth Systems Analysis, Geo‑Information Science and Earth Observation (ITC), University of Twente, Enschede, The Netherlands
3
Departmetn of Mining, Industrial and TIC Engineering, Universitat Politecnica de Catalunya, Barcelona, Spain
properties such as hardness, toughness, specific gravity, porosity and water absorption, dressing, seasoning, workability, fire, and chemical resistance also may need to be considered. Using laboratory tests suitability o
Data Loading...
