Gaussian Process Regression Technique to Estimate the Pile Bearing Capacity
- PDF / 1,546,500 Bytes
- 13 Pages / 595.276 x 790.866 pts Page_size
- 99 Downloads / 235 Views
RESEARCH ARTICLE-CIVIL ENGINEERING
Gaussian Process Regression Technique to Estimate the Pile Bearing Capacity Ehsan Momeni1 · Mohammad Bagher Dowlatshahi1 · Fereydoon Omidinasab1 · Harnedi Maizir2 · Danial Jahed Armaghani3 Received: 19 April 2020 / Accepted: 29 May 2020 © King Fahd University of Petroleum & Minerals 2020
Abstract A commonly-encountered problem in foundation design is the reliable prediction of the pile bearing capacity (PBC). This study is planned to propose a feasible soft computing technique in this field i.e.; the Gaussian process regression (GPR) for the PBC estimation. The established database includes 296 number of dynamic pile load test in the field where the most influential factors on the PBC were selected as input variables. Several GPR models were designed and built. These models were assessed using three performance indices namely value account for (VAF), coefficient of determination (R2) and system error. To have a comparison, a genetic algorithm-based artificial neural network (GA-based ANN) model was also employed. It was found that the GPR-based model with VAF value of 86.41%, R2 of 0.84 and system error of 0.2006 is capable enough to predict the PBC and outperforms the GA-based ANN model. The results showed that the GPR can be utilized as a practical tool for the PBC estimation. Keywords Pile bearing capacity · Pile driving analyzer · Gaussian process regression · Predictive model
1 Introduction Pile foundations are used when the soil beneath the superstructures does not have enough strength to carry the superstructure loads. These substructure elements transfer the applied loads to the deeper layers of soil. The load transfer mechanism is based on the provided resistances of pile toe * Ehsan Momeni [email protected] Mohammad Bagher Dowlatshahi [email protected] Fereydoon Omidinasab [email protected] Harnedi Maizir harnedi@sttp‑yds.ac.id Danial Jahed Armaghani [email protected] 1
Faculty of Engineering, Lorestan University, Khorramabad, Iran
2
Department of Civil Engineering, Sekolah Tinggi Teknologi Pekanbaru, Pekanbaru, Indonesia
3
Department of Civil Engineering, Faculty of Engineering, University of Malaya, 50603 Kuala Lumpur, Malaysia
and pile shaft [1]. Pile behavior under load is complicated due to the interaction between pile and supporting soil. However, there are a number of methods to determine the load carrying capacity of piles which is mainly related to the geotechnical and geometrical properties. The bearing capacity of piles can be determined based on conventional semi-empirical equations. In this regard, the Meyerhof equation is still well-respected [2]. In addition, there are some simple correlations between the bearing capacity of piles and in-situ tests (like cone penetration test, CPT or standard penetration test, SPT); however, some studies suggest that the aforementioned correlations overestimate the bearing capacity [3]. Furthermore, some other studies recommend the use of dynamic equations, which are based on the pile
Data Loading...
