Reliability Analysis of Settlement of Pile Group in Clay Using LSSVM, GMDH, GPR
- PDF / 1,060,732 Bytes
- 14 Pages / 547.087 x 737.008 pts Page_size
- 60 Downloads / 163 Views
(0123456789().,-volV) ( 01234567 89().,-volV)
ORIGINAL PAPER
Reliability Analysis of Settlement of Pile Group in Clay Using LSSVM, GMDH, GPR Manish Kumar . Pijush Samui
Received: 8 August 2019 / Accepted: 6 July 2020 Springer Nature Switzerland AG 2020
Abstract Robust and reliable design at certain levels of safety has earned lot of attention in recent. To build over the limitations of FOSM based reliability analysis, the paper proposes least square support vector machine (LSSVM), The Group Method of Data Handling (GMDH) and Gaussian process regression (GPR) based reliability analysis of pile group resting on cohesive soil. LSSVM is an improvement over support-vector machines (SVM) which uses linear systems instead of complex quadratic equations. GMDH is a self-organized neural network capable of solving complex non-linear problems. GPR is an effective Bayesian tool of machine learning the performance of the developed models is ascertained using various statistical parameters and Taylor curves. The reliability indices of the simulated values are compared to that of the actual values obtained from FOSM. The results show that all the models are applicable for reliability analysis of settlement of pile group. Keywords Pile foundation Reliability FOSM LSSVM GMDH GPR
M. Kumar P. Samui (&) Department of Civil Engineering, NIT Patna, Bihar, India e-mail: [email protected] M. Kumar e-mail: [email protected]
1 Introduction In the conventional design of pile group resting on a cohesive frictional soil, allowable settlement is calculated using Equivalent Raft Approach. However, for serviceability credentials, we need to ensure safe limit of safety of settling of the foundation. Inherent inevitable variability is associated with soil data. The uncertainties involved can be classified into three categories: Inherent variability, Measurement variability and transformation uncertainties (Phoon and Kulhawy 1999; Cherubini et al. 1993). Inherent variability is related to material parameters of the soil e.g. void ratio, density etc. Each parameter is probable to vary appreciably owing to soil being Isotropic and heterogeneous and discontinuity in geology. Measurement Variability is related to equipment errors and errors in sampling and testing. Errors in hypothesis and simplifications in the solution model are categorized into transformation uncertainties. All models of soil behavior are derived by assuming some ideal behavior of real situations. The necessity to assess calculated risk has been proposed long back (Casagrande 1965). Factor of safety (FS) approach has been used traditionally which is based on past experience. On one hand, FS approach leads to conservative analysis and hence high cost; on the other hand, it has been found to possess significant probability of failure (Hoeg and Murarka 1974). To overcome these shortcomings of FS approach,
123
Geotech Geol Eng
Reliability analysis method have been proposed. Reliability is defined as capability to carry out its proposed function effectively on
Data Loading...
