Bearing Capacity Modeling of Composite Pile Foundation Using Parameter-Optimized RBF Neural Networks

2006 ◽  
Author(s):  
Maosen Cao ◽  
Baosheng Su
Keyword(s):  
Neural Networks ◽  
Bearing Capacity ◽  
Pile Foundation ◽  
Rbf Neural Networks ◽  
Composite Pile ◽  
Capacity Modeling

scholarly journals Bearing Characteristics of Composite Pile Group Foundations with Long and Short Piles under Lateral Loading in Loess Areas

2018 ◽  
Vol 2018 ◽  
pp. 1-17 ◽  
Author(s):  
Tianzhong Ma ◽  
Yanpeng Zhu ◽  
Xiaohui Yang ◽  
Yongqiang Ling
Keyword(s):  
Bearing Capacity ◽  
Pile Foundation ◽  
Horizontal Displacement ◽  
Pile Group ◽  
Lateral Load ◽  
Test Model ◽  
Pile Head ◽  
Load Bearing ◽  
Composite Pile ◽  
Pile Length

It is very necessary to research the bearing characteristics of composite pile group foundations with long and short piles under lateral load in loess areas, because these foundations are used widely. But few people researched this problem in loess areas up to now worldwide. In this paper, firstly, an indoor test model of a composite pile foundation with long and short piles is designed and then employed to explore the vertical load bearing characteristics and load transfer mechanisms of a single pile, a four-pile group, and a nine-pile group under different lateral loads. Secondly, ANSYS software is employed to analyze the load-bearing characteristics of the test model, and for comparison with the experimental results. The results demonstrate the following. (1) The lateral force versus pile head displacement curves of the pile foundation exhibit an obvious steep drop in section, which is a typical feature of piercing damage. A horizontal displacement limit of the pile foundation is 10 mm and 6mm for the ones sensitive to horizontal displacement. (2) The axial force along a pile and frictional resistance do not coincide, due to significant variations and discontinuities in the collapsibility of loess; a pile body exhibits multiple neutral points. Therefore, composite pile groups including both long and short piles could potentially maximize the bearing capacity and reduce pile settlement. (3) The distribution of stress and strain along the pile length is mainly concentrated from the pile head to a depth of about 1/3 of the pile length. If the lateral load is too large, short piles undergo rotation about their longitudinal axis and long piles undergo flexural deformation. Therefore, the lateral bearing capacity mainly relies on the strength of the soil at the interface with the pile or the horizontal displacement of the pile head.

scholarly journals Calculation of Bearing Capacity and Deformation of Composite Pile Foundation with Long and Short Piles in Loess Areas

2020 ◽  
Vol 2020 ◽  
pp. 1-10
Author(s):  
Tianzhong Ma ◽  
Yanpeng Zhu ◽  
Xiaohui Yang
Keyword(s):  
Theoretical Calculation ◽  
Bearing Capacity ◽  
Pile Foundation ◽  
Frictional Resistance ◽  
Operating Conditions ◽  
Neutral Point ◽  
Pile Foundations ◽  
Single Pile ◽  
Deformation Control ◽  
Composite Pile

In order to calculate the bearing capacity and settlement deformation of composite pile foundations with long and short piles in collapsible loess areas, the theoretical approximate solution was used to obtain the location of the neutral point of single piles. Additionally, based on the equation to calculate the bearing capacity of multielement composite foundations, a method considering the negative frictional resistance was proposed for calculating the bearing capacity of composite pile foundations with long and short piles. Based on the shear displacement method and the principle of deformation control, an equation to calculate the displacement and deformation of a composite pile foundation was presented. A model test with different operating conditions, i.e., a single pile, four piles, and eight piles, was designed to verify the proposed calculation methods. The results show that the location of the neutral point has a significant influence on the single-pile negative frictional resistance, and the neutral point ratio of the calculation meets the value range of the practical project. When the load at the top of the pile is relatively small, the experimental curve is consistent with the theoretical calculation curve, whereas when the load is comparatively large, the theoretically calculated displacement increase at the top of the pile is greater than the measured one. Under the premise that the theoretical calculation is in good agreement with the results, the theoretical value is larger than the actual value. And it contributes to strengthening engineering safety.

scholarly journals Numerical analysis for the vertical bearing capacity of composite pile foundation system in liquefiable soil under sine wave vibration

PLoS ONE ◽  
2021 ◽  
Vol 16 (3) ◽  
pp. e0248502
Author(s):  
Huang Zhan-fang ◽  
Xiao-hong Bai ◽  
Chao Yin ◽  
Yong-qiang Liu
Keyword(s):  
Bearing Capacity ◽  
Pile Foundation ◽  
Water Pressure ◽  
Seismic Loading ◽  
Shaking Table ◽  
Pile Spacing ◽  
Liquefiable Soil ◽  
Composite Pile ◽  
Vertical Bearing ◽  
Vertical Bearing Capacity

Composite pile foundation has been widely used in ground engineering. This composite pile foundation system has complex pile-soil interactions under seismic loading. The calculation of vertical bearing capacity of composite pile foundation is still an unsolved problem if the soil around piles is partially or completely liquefied under seismic loading. We have completed indoor shaking table model tests to measure the vertical bearing capacity in a liquefiable soil foundation under seismic loading. This paper will use a numerical approach to analyze the change of this vertical bearing capacity under seismic loading. Firstly, the Goodman contact element is improved to include the Rayleigh damping. Such an improvement can well describe the reflection and absorption of seismic waves at the interface of soil and piles. Secondly, the Biot’s dynamic consolidation theory incorporated an elastoplastic model is applied to simulate the soil deformation and the generation and accumulation of pore water pressure under seismic loading. Thirdly, after verification with our indoor shaking table test data, this approach is used to investigate the effects of pile spacing on liquefaction resistance of the composite pile foundation in liquefiable soil. The time histories of pore water pressure ratio (PPR′) are calculated for the liquefiable soil and the vertical bearing capacity in partially liquefied soil is calculated and compared with our indoor shaking table test data at the 3D, 3.5D, 4D, 5D and 6D cases (D is the pile diameter). It is found that the pile spacing has some influence on the extent of soil liquefaction between piles. The vertical bearing capacity varies with liquefaction extent of inter-pile soil. The optimization of pile spacing varies with liquefaction extent. These results may provide some reference for the design of composite pile foundation under seismic loading.

scholarly journals Hardware implementation of radial-basis neural networks with Gaussian activation functions on FPGA

2021 ◽  
Author(s):  
Volodymyr Shymkovych ◽  
Sergii Telenyk ◽  
Petro Kravets
Keyword(s):  
Neural Networks ◽  
Hardware Implementation ◽  
Gaussian Function ◽  
Activation Function ◽  
Rbf Neural Networks ◽  
Activation Functions ◽  
Rbf Network ◽  
Combination Scheme ◽  
Radial Basis ◽  
Hidden Layer

AbstractThis article introduces a method for realizing the Gaussian activation function of radial-basis (RBF) neural networks with their hardware implementation on field-programmable gaits area (FPGAs). The results of modeling of the Gaussian function on FPGA chips of different families have been presented. RBF neural networks of various topologies have been synthesized and investigated. The hardware component implemented by this algorithm is an RBF neural network with four neurons of the latent layer and one neuron with a sigmoid activation function on an FPGA using 16-bit numbers with a fixed point, which took 1193 logic matrix gate (LUTs—LookUpTable). Each hidden layer neuron of the RBF network is designed on an FPGA as a separate computing unit. The speed as a total delay of the combination scheme of the block RBF network was 101.579 ns. The implementation of the Gaussian activation functions of the hidden layer of the RBF network occupies 106 LUTs, and the speed of the Gaussian activation functions is 29.33 ns. The absolute error is ± 0.005. The Spartan 3 family of chips for modeling has been used to get these results. Modeling on chips of other series has been also introduced in the article. RBF neural networks of various topologies have been synthesized and investigated. Hardware implementation of RBF neural networks with such speed allows them to be used in real-time control systems for high-speed objects.

scholarly journals Task-space regulation of rigid-link electrically-driven robots with uncertain kinematics using neural networks

2021 ◽  
Vol 54 (1-2) ◽  
pp. 102-115
Author(s):  
Wenhui Si ◽  
Lingyan Zhao ◽  
Jianping Wei ◽  
Zhiguang Guan
Keyword(s):  
Neural Networks ◽  
Asymptotic Stability ◽  
Control Method ◽  
Joint Space ◽  
Robot Kinematics ◽  
Rbf Neural Networks ◽  
Task Space ◽  
Actuator Dynamics ◽  
Rigid Link ◽  
On Line

Extensive research efforts have been made to address the motion control of rigid-link electrically-driven (RLED) robots in literature. However, most existing results were designed in joint space and need to be converted to task space as more and more control tasks are defined in their operational space. In this work, the direct task-space regulation of RLED robots with uncertain kinematics is studied by using neural networks (NN) technique. Radial basis function (RBF) neural networks are used to estimate complicated and calibration heavy robot kinematics and dynamics. The NN weights are updated on-line through two adaptation laws without the necessity of off-line training. Compared with most existing NN-based robot control results, the novelty of the proposed method lies in that asymptotic stability of the overall system can be achieved instead of just uniformly ultimately bounded (UUB) stability. Moreover, the proposed control method can tolerate not only the actuator dynamics uncertainty but also the uncertainty in robot kinematics by adopting an adaptive Jacobian matrix. The asymptotic stability of the overall system is proven rigorously through Lyapunov analysis. Numerical studies have been carried out to verify efficiency of the proposed method.

Decentralized adaptive tracking control for high-order interconnected stochastic nonlinear time-varying delay systems with stochastic input-to-state stable inverse dynamics by neural networks

2019 ◽  
Vol 41 (13) ◽  
pp. 3612-3625 ◽  
Author(s):  
Wang Qian ◽  
Wang Qiangde ◽  
Wei Chunling ◽  
Zhang Zhengqiang
Keyword(s):  
Neural Networks ◽  
Tracking Control ◽  
Large Scale ◽  
Inverse Dynamics ◽  
Small Neighborhood ◽  
High Order ◽  
Interconnected Systems ◽  
Delay Systems ◽  
Rbf Neural Networks ◽  
Stochastic Input

The paper solves the problem of a decentralized adaptive state-feedback neural tracking control for a class of stochastic nonlinear high-order interconnected systems. Under the assumptions that the inverse dynamics of the subsystems are stochastic input-to-state stable (SISS) and for the controller design, Radial basis function (RBF) neural networks (NN) are used to cope with the packaged unknown system dynamics and stochastic uncertainties. Besides, the appropriate Lyapunov-Krosovskii functions and parameters are constructed for a class of large-scale high-order stochastic nonlinear strong interconnected systems with inverse dynamics. It has been proved that the actual controller can be designed so as to guarantee that all the signals in the closed-loop systems remain semi-globally uniformly ultimately bounded, and the tracking errors eventually converge in the small neighborhood of origin. Simulation example has been proposed to show the effectiveness of our results.

Sign in / Sign up

Export Citation Format

Share Document