Search results for "multilayer"
showing 10 items of 141 documents
Two multilayered plate models with transverse shear warping functions issued from three dimensional elasticity equations
2014
Abstract A multilayered plate theory which uses transverse shear warping functions is presented. Two methods to obtain the transverse shear warping functions from three-dimensional elasticity equations are proposed. The warping functions are issued from the variations of transverse shear stresses computed at specific points of a simply supported plate. The first method considers an exact 3D solution of the problem. The second method uses the solution provided by the model itself: the transverse shear stresses are computed integrating equilibrium equations. Hence, an iterative process is applied, the model is updated with the new warping functions, and so on. Once the sets of warping functio…
Conflict resolution in the multi-stakeholder stepped spillway design under uncertainty by machine learning techniques
2021
Abstract The optimal spillway design is of great significance since these structures can reduce erosion downstream of the dams. This study proposes a risk-based optimization framework for a stepped spillway to achieve an economical design scenario with the minimum loss in hydraulic performance. Accordingly, the stepped spillway was simulated in the FLOW-3D® model, and the validated model was repeatedly performed for various geometric states. The results were used to form a Multilayer Perceptron artificial neural network (MLP-ANN) surrogate model. Then, a risk-based optimization model was formed by coupling the MLP-ANN and NSGA-II. The concept of conditional value at risk (CVaR) was utilized…
Some Examples for Solving Clinical Problems Using Neural Networks
2001
In this paper neural networks are presented for solving some pharmaceutical problems. We have predicted and prevented patients with potential risk of post-Chemotherapy Emesis and potentially intoxicated patients treated with Digoxin. Neural networks have been also used for predicting Cyclosporine A concentration and Erythropoietin concentrations. Several neural networks (multilayer perceptron for classification tasks and Elman and FIR networks for prediction) and classical methods have been used. Results show how neural networks are very suitable tools for classification and prediction tasks, outperforming the classical methods. In a neural approach it is not strictly necessary to assume a …
Therapeutic Drug Monitoring of Kidney Transplant Recipients Using Profiled Support Vector Machines
2007
This paper proposes a twofold approach for therapeutic drug monitoring (TDM) of kidney recipients using support vector machines (SVMs), for both predicting and detecting Cyclosporine A (CyA) blood concentrations. The final goal is to build useful, robust, and ultimately understandable models for individualizing the dosage of CyA. We compare SVMs with several neural network models, such as the multilayer perceptron (MLP), the Elman recurrent network, finite/infinite impulse response networks, and neural network ARMAX approaches. In addition, we present a profile-dependent SVM (PD-SVM), which incorporates a priori knowledge in both tasks. Models are compared numerically, statistically, and in…
Ranking of Brain Tumour Classifiers Using a Bayesian Approach
2009
This study presents a ranking for classifers using a Bayesian perspective. This ranking framework is able to evaluate the performance of the models to be compared when they are inferred from different sets of data. It also takes into account the performance obtained on samples not used during the training of the classifiers. Besides, this ranking assigns a prior to each model based on a measure of similarity of the training data to a test case. An evaluation consisting of ranking brain tumour classifiers is presented. These multilayer perceptron classifiers are trained with 1H magnetic resonance spectroscopy (MRS) signals following a multiproject multicenter evaluation approach. We demonstr…
A finite element formulation for large deflection of multilayered magneto-electro-elastic plates
2014
An original finite element formulation for the analysis of large deflections in magneto-electro-elastic multilayered plates is presented. The formulation is based on an equivalent single-layer model in which first order shear deformation theory with von Karman strains and quasi-static behavior for the electric and magnetic fields are assumed. To obtain the plate model, the electro-magnetic state is firstly determined and condensed to the mechanical primary variables, namely the generalized displacements. In turn, this result is used to obtain laminate effective stiffness coefficients that allow to express the plate mechanical stress resultants in terms of the generalized displacements and a…
Heterogeneous structures studied by an interphase elasto-plastic damaging model
2013
Heterogeneous materials present a mechanical response strongly dependent on the static and kinematic phenomena occurring in the constituents and at their joints. At the mesoscopic level the interaction between the units is simulated by mean of apposite mechanical devices such as the zero thickness interface model where contact tractions and displacement discontinuities are the primary static and kinematic variables respectively. In heterogeneous materials the response also depends on joint internal stresses. The introduction of internal stresses brings to the interphase model or an enhancement of the classical zero-thickness interface. With the term 'interphase' we shall mean a layer separa…
A discontinuous Galerkin formulation for nonlinear analysis of multilayered shells refined theories
2023
A novel pure penalty discontinuous Galerkin method is proposed for the geometrically nonlinear analysis of multilayered composite plates and shells, modelled via high-order refined theories. The approach allows to build different two-dimensional equivalent single layer structural models, which are obtained by expressing the covariant components of the displacement field through-the-thickness via Taylor’s polynomial expansion of different order. The problem governing equations are deduced starting from the geometrically nonlinear principle of virtual displacements in a total Lagrangian formulation. They are addressed with a pure penalty discontinuous Galerkin method using Legendre polynomial…
A comparison between models for the study of static and dynamic behavior of heterogeneous multilayer composite plates
2013
In composite plate structures, it is common to combine different materials with very different Young's moduli and densities. Damping treatments can also be added to prevent high levels of vibration. For discretized problems, the static and dynamic behavior of such heterogeneous structures can be carried out with the 3D elasticity theory but this often leads to very large systems. Therefore, plate theories and particularly equivalent single layer models are often preferred. Classical plate theories have then been adapted to these particular structures using shear correction factors. Higher order shear deformation theories, and more recently transverse shear warping functions, have been propo…
Variable kinematics equivalent single layer theories for magneto-electro-elastic multilayered plates
2014
In recent years, the employment of smart materials able to provide multi-functional capabilities, besides the traditional structural functions, has been gaining attention in several technological fields (automotive, aerospace, biomedical, robotics, etc.). This possibility of coupling different physical fields can be and it has been exploited in transducer applications, structural health monitoring, vibration control, energy harvesting and other applications. In this framework, magneto-electro-elastic (MEE) materials are attracting increasing consideration from academic and industrial audiences: MEE materials have the ability to couple mechanical, electrical and magnetic fields and this make…