Dong-Sheng Jeng

Neural network and neuro-fuzzy assessments for scour depth around bridge piers

The mechanism of flow around a pier structure is so complicated that it is difficult to establish a general empirical model to provide accurate estimation for scour. Interestingly, each of the proposed empirical formula yields good results for a particular data set. Hence, in this study, alternative approaches, artificial neural networks (ANNs) and adaptive neuro-fuzzy inference system (ANFIS), are proposed to estimate the equilibrium and time-dependent scour depth with numerous reliable data base. Two ANN models, multi-layer perception using back-propagation algorithm (MLP/BP) and radial basis using orthogonal least-squares algorithm (RBF/OLS), were used. The equilibrium scour depth was modeled as a function of five variables; flow depth, mean velocity, critical flow velocity, mean grain diameter and pier diameter. The time variation of scour depth was also modeled in terms of equilibrium scour depth, equilibrium scour time, scour time, mean flow velocity and critical flow velocity. The training and testing data are selected from the experimental data of several valuable references. Numerical tests indicate that MLP/BP model provide a better prediction of scour depth than RBF/OLS and ANFIS models as well as the previous empirical approaches. Finally, sensitivity analysis shows that pier diameter has a greater influence on equilibrium scour depth than the other independent parameters.

Application of artificial neural networks in tide-forecasting

An accurate tidal forecast is an important task in determining constructions and human activities in ocean environments. Conventional tidal forecasting has been based on harmonic analysis using the least squares method to determine harmonic parameters. However, a large number of parameters are required for the prediction of a long-term tidal level with harmonic analysis. Unlike conventional harmonic analysis, this paper presents an artificial neural network (ANN) model for forecasting the tidal-level using the short term measuring data. The ANN model can easily decide the unknown parameters by learning the input-output interrelation of the short-term tidal records. Three field data with three types of tides will be used to test the performance of the proposed ANN model. The numerical results indicate that the hourly tidal levels over a long duration can be predicted using a short-term hourly tidal record.

Wave-induced seabed instability in front of a breakwater

The wave-induced soil response in a porous seabed has become an important factor for the stability of offshore facilities, because many marine structures may have failed due to seabed instability and concomitant subsidence. An analytical solution is presented for the wave-induced soil response under the action of a three-dimensional wave system. Based on this general solution, the mechanism of seabed instability is then investigated. The general solutions for pore pressure and effective stresses are readily reducible to two dimensions for progressive waves, and are compared to theoretical and experimental work available. Some dominant factors affecting the wave-induced seabed instability are discussed; including permeability, seabed thickness and degree of saturation.

Analytical solution for tidal propagation in a coupled semi-confined/phreatic coastal aquifer

An analytical solution is derived for tidal fluctuations in a coupled coastal aquifer system consisting of a semi-confined aquifer, a thin semi-permeable layer and a phreatic aquifer. Based on the solution, we study the interactions (via leakage) between the confined and unconfined aquifers in response to tides. The results show that, under certain conditions, leakage from the confined aquifer can affect considerably the tidal water table fluctuation in the phreatic aquifer and vice versa. Ignoring these effects could lead to errors in estimating aquifer properties based on tidal signals.

NEURAL NETWORK MODELING FOR ESTIMATION OF SCOUR DEPTH AROUND BRIDGE PIERS

It is essential to predict the scour depth around bridge piers for hydraulic engineers involved in the economical design of bridge pier foundation. Conventional investigations have long been of the opinion that empirical scour prediction equations based on laboratory data over predict scour depths. In this article, the Back-Propagation Neural Network (BPN) was applied to predict the scour depth in order to overcome the problem of exclusive and the nonlinear relationships. The observations obtained from thirteen states in USA was verified by the present model. From the comparison with conventional experimental methods, it can be found that the scour depth around bridge piers can be efficiently predicted using the BPN.

Porous models for wave-seabed interactions

Wave-Induced Seabed Response in an Isotropic Seabed.- Wave-Induced seabed Instability.- Cross-Anisotropic Soil Behavior.- Non-Homogeneous Seabed.- Wave-Driven Seepage flux in Marine Sediments.- Dynamic Analysis for Wave-Seabed Interactions.- Wave-Induced Pore Pressure Accumulation in Marine Sediments.- Dynamic Analysis for Wave-Seabed Interactions.- Dynamic Analysis for Wave-Seabed Interactions.- Wave Propagation over Coulomb-Damped Seabed.- Wave-Induced Pore Pressure Accumulation in Marine Sediments.- Random wave-induced seabed response 295.- Wave-Induced Progressive liquefaction in a porous seabed.- Poro-Elastoplastic model for Wave-Seabed Interactions.- Response of Seabed to Combined Wave and Current Loading.- ANN model for Wave-Induced Liquefaction 341.- Models for Wave-Seabed-Structure Interaction.

Bayesian neural networks for prediction of equilibrium and time-dependent scour depth around bridge piers

Abstract The physical process of scour around bridge piers is complicated. Despite various models presented to predict the equilibrium scour depth and its time variation from the characteristics of the current and sediment, scope exists to improve the existing models or to provide alternatives to them. In this paper, a neural network technique within a Bayesian framework, is presented for the prediction of equilibrium scour depth around a bridge pier and the time variation of scour depth. The equilibrium scour depth was modeled as a function of five variables; flow depth and mean velocity, critical flow velocity, median grain diameter and pier diameter. The time variation of scour depth was also modeled in terms of equilibrium scour depth, equilibrium scour time, scour time, mean flow velocity and critical flow velocity. The Bayesian network predicted equilibrium and time-dependent scour depth much better when it was trained with the original (dimensional) scour data, rather than using a non-dimensional form of the data. The selection of water, sediment and time variables used in the models was based on conventional scour depth data analysis. The new models estimate equilibrium and time-dependent scour depth more accurately than the existing expressions. A committee model, developed by averaging the predictions of a number of individual neural network models, increased the reliability and accuracy of the predictions. A sensitivity analysis showed that pier diameter has a greater influence on equilibrium scour depth than the other independent parameters.

Effects of dynamic soil behavior and wave non-linearity on the wave-induced pore pressure and effective stresses in porous seabed

Most previous investigations for the wave-induced soil response have only considered the quasi-static soil behavior under linear wave loading. However, it is expected that the dynamic soil behavior and wave non-linearity will play an important role in the evaluation of wave-induced seabed response. In this paper, we include dynamic soil behavior and wave non-linearity into new analytical models. Based on the analytical solution derived, the effects of wave non-linearity on the wave-induced seabed response with dynamic soil behavior are examined. Numerical results demonstrate the significant effects of wave non-linearity and dynamic soil behavior on the wave-induced effective stresses. The applicable range of dynamic and quasi-static approximations is also clarified for engineering practice.

Finite element modeling for the mechanical behavior of dowel-type timber joints

The mechanical performances of timber joints are particularly important for timber engineers involved in the design of the wood structures. In general, joints are often one of the weakest points in a timber structure. However, to simplify the problem, most previous investigations have considered the effects of individual parameters on the mechanical behavior of timber joints. Thus, it is difficult to undertake an analytical study due to interactions among parameters. In this paper, a finite element model for a dowel-type timber joint is proposed to investigate the mechanical performance of un-reinforced and reinforced timber joints affected by the various parameters. Moreover, a stress-interaction based failure criterion is proposed to predict the strength of such joints. The numerical prediction of the proposed finite element method model overall agrees with the experimental results of mechanical testing.

Finite element modelling for water waves-soil interaction

The soil permeability and shear modulus of many marine sediments vary with depth because of consolidation under overburden pressure. However, conventional theories for wave-induced soil response have assumed a homogeneous porous seabed, with constant soil permeability and shear modulus. This paper presents a finite element model for the wave-induced soil response in a porous seabed, with variable permeability and shear modulus as a function of burial depth. The soil matrix considered here is unsaturated and hydraulically anisotropic, and subjected to a three-dimensional short-crested wave system. The present finite element formulation is established by using a combination of semi-analytical techniques and the Galerkin method. The nodal effective stresses directly derived from the governing equations can be calculated accurately in the present model. Verification is available through the reduction to the simple case of homogeneous seabed. Three typical marine materials, course, fine sand and gravel, are considered in this study. The numerical results indicate that the soil permeability affects the wave-induced seabed response significantly especially for gravelled seabed, as does the soil shear modulus for sandy seabed.