Generic compressive strength prediction model applicable to multiple lithologies based on a broad global database
نویسندگان
چکیده
In this study, we present a global database of ten parameters, which include measurements rock index properties, strength stiffness and dynamic properties. Hoek-Brown constant mi, is included, was estimated, using Hoek Brown proposed guidelines for determining mi values different types that can be used preliminary design when triaxial tests are not available. This broad compiled from 96 studies labelled as “ROCK/10/4025”, to describe the type geomaterial, number data samples included. It consists 35.4 % igneous, 54.8 sedimentary, 9.2% metamorphic rocks. The purpose paper propose generic soft computing model applicable multiple lithologies, become more reliable perhaps suitable specific site study in order densify often limited similar site-specific data. To end four were selected, served training sets developed machine learning models, develop compression prediction lithologies. suggested algorithms Back – Propagation Artificial Neural Networks, Neuro-Fuzzy Inference Systems, Support Vector Machines, Nearest Neighbour classifiers Ensemble Bagged Trees. According findings artificial neuro-fuzzy inference systems performance found marginally superior, while back propagation neural networks, support vector machines ensemble bagged trees models have good performance. Constant seems important parameter predictive centred on As result, suggest these powerful tools allow estimation compressive strength, based indicators. 70%–82% problem approached classification (that successful class very weak strong), 80%–96% solved function approximation problem.
منابع مشابه
Prediction of Lightweight Aggregate Concrete Compressive Strength
Nowadays, the better performance of lightweight structures during earthquake has resulted in using lightweight concrete more than ever. However, determining the compressive strength of concrete used in these structures during their service through a none-destructive test is a popular and useful method. One of the main methods of non-destructive testing in the assessment of compressive strength...
متن کاملmortality forecasting based on lee-carter model
over the past decades a number of approaches have been applied for forecasting mortality. in 1992, a new method for long-run forecast of the level and age pattern of mortality was published by lee and carter. this method was welcomed by many authors so it was extended through a wider class of generalized, parametric and nonlinear model. this model represents one of the most influential recent d...
15 صفحه اولGenetic Programming Based Formulation to Predict Compressive Strength of High Strength Concrete
This study introduces, two models based on Gene Expression Programming (GEP) to predict compressive strength of high strength concrete (HSC). Composition of HSC was assumed simplified, as a mixture of six components (cement, silica fume, super-plastisizer, water, fine aggregate and coarse aggregate). The 28-day compressive strength value was considered the target of the prediction. Data on 159...
متن کاملPrediction of Human Vertebral Compressive Strength Using Quantitative Computed Tomography Based Nonlinear Finite Element Method
Introduction: Because of the importance of vertebral compressive fracture (VCF) role in increasing the patients’ death rate and reducing their quality of life, many studies have been conducted for a noninvasive prediction of vertebral compressive strength based on bone mineral density (BMD) determination and recently finite element analysis. In this study, QCT-voxel based nonlinear finite eleme...
متن کاملThe prediction of compressive strength of travertines with special reference to laminae-orientation using index tests
In this research, different experimental techniques have been used to determine the strength of four types of travertines, selected from Hamedan and Markazi Provinces, west and central parts of Iran respectively. For this purpose, after sample preparation and assessment of mineral properties, the selected samples were subjected to physical and mechanical tests with special reference to two majo...
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
ژورنال
عنوان ژورنال: Probabilistic Engineering Mechanics
سال: 2023
ISSN: ['1878-4275', '0266-8920']
DOI: https://doi.org/10.1016/j.probengmech.2022.103400