A Radial Basis Function Method with Improved Accuracy for Fourth Order Boundary Value Problems

Accurately approximating higher order derivatives is an inherently difficult problem. It is shown that a random variable shape parameter strategy can improve the accuracy of approximating higher order derivatives with Radial Basis Function methods. The method is used to solve fourth order boundary value problems. The use and location of ghost points are examined in order to enforce the extra boundary conditions that are necessary to make a fourth-order problem well posed. The use of ghost points versus solving an overdetermined linear system via least squares is studied. For a general fourth-order boundary value problem, the recommended approach is to either use one of two novel sets of ghost centers introduced here or else to use a least squares approach. When using either ghost centers or least squares, the random variable shape parameter strategy results in significantly better accuracy than when a constant shape parameter is used.

Mathematical modeling of fractional derivatives for magnetohydrodynamic fluid flow between two parallel plates by the radial basis function method

Investigations into the magnetohydrodynamics of viscous fluids have become more important in recent years,owing to their practical significance and numerous applications in astro-physical and geo-physical phenomena.In this paper,the radial base function was utilized to answer fractional equation associated with fluid flow passing through two parallel flat plates with a magnetic field.The magnetohydrodynamics coupled stress fluid flows between two parallel plates,with the bottom plate being stationary and the top plate moving at a persistent velocity.We compared the radial basis function approach to the numerical method(fourth-order Range-Kutta)in order to verify its validity.The findings demonstrated that the discrepancy between these two techniques is quite negligible,indicating that this method is very reliable.The impact of the magnetic field parameter and Reynolds number on the velocity distribution perpendicular to the fluid flow direction is illustrated.Eventually,the velocity parameter is compared for diverse conditionsα,Reynolds and position(y),the maximum of which occurs atα=0.4.Also,the maximum velocity values occur inα=0.4 and Re=1000 and the concavity of the graph is less forα=0.8.

A data-derived soft-sensor method for monitoring effluent total phosphorus

The effluent total phosphorus(ETP) is an important parameter to evaluate the performance of wastewater treatment process(WWTP). In this study, a novel method, using a data-derived soft-sensor method, is proposed to obtain the reliable values of ETP online. First, a partial least square(PLS) method is introduced to select the related secondary variables of ETP based on the experimental data. Second, a radial basis function neural network(RBFNN) is developed to identify the relationship between the related secondary variables and ETP. This RBFNN easily optimizes the model parameters to improve the generalization ability of the soft-sensor. Finally, a monitoring system, based on the above PLS and RBFNN, named PLS-RBFNN-based soft-sensor system, is developed and tested in a real WWTP. Experimental results show that the proposed monitoring system can obtain the values of ETP online and own better predicting performance than some existing methods.

NUMERICAL APPROXIMATION OF THE SMOLUCHOWSKI EQUATION USING RADIAL BASIS FUNCTIONS

The goal of this paper is to present a numerical method for the Smoluchowski equation,a drift-diffusion equation on the sphere,arising in the modelling of particle dynamics.The numerical method uses radial basis functions(RBF).This is a relatively new approach,which has recently mainly been used for geophysical applications.For a simplified model problem we compare the RBF approach with a spectral method,i.e.the standard approach used in related physical applications.This comparison as well as our other accuracy studies show that RBF methods are an attractive alternative for these kind of models.

The prediction of external flow field and hydrodynamic force with limited data using deep neural network

Predicting the external flow field with limited data or limited measurements has attracted long-time interests of researchers in many industrial applications.Physics informed neural network(PINN)provides a seamless framework for combining the measured data with the deep neural network,making the neural network capable of executing certain physical constraints.Unlike the data-driven model to learn the end-to-end mapping between the sensor data and high-dimensional flow field,PINN need no prior high-dimensional field as the training dataset and can construct the mapping from sensor data to high dimensional flow field directly.However,the extrapolation of the flow field in the temporal direction is limited due to the lack of training data.Therefore,we apply the long short-term memory(LSTM)network and physics-informed neural network(PINN)to predict the flow field and hydrodynamic force in the future temporal domain with limited data measured in the spatial domain.The physical constraints(conservation laws of fluid flow,e.g.,Navier-Stokes equations)are embedded into the loss function to enforce the trained neural network to capture some latent physical relation between the output fluid parameters and input tempo-spatial parameters.The sparsely measured points in this work are obtained from computational fluid dynamics(CFD)solver based on the local radial basis function(RBF)method.Different numbers of spatial measured points(4–35)downstream the cylinder are trained with/without the prior knowledge of Reynolds number to validate the availability and accuracy of the proposed approach.More practical applications of flow field prediction can compute the drag and lift force along with the cylinder,while different geometry shapes are taken into account.By comparing the flow field reconstruction and force prediction with CFD results,the proposed approach produces a comparable level of accuracy while significantly fewer data in the spatial domain is needed.The numerical results demonstrate that the proposed approach with a specific deep neural network configuration is of great potential for emerging cases where the measured data are often limited.

Numerical prediction of effective wake field for a submarine based on a hybrid approach and an RBF interpolation

A hybrid approach coupled with a surface panel method for the propeller and a Reynolds averaged Navier-Stokes（RANS） model for the hull with the propeller body forces are presented for predicting the self-propulsion performance and the effective wake field of underwater vehicles. To achieve a high accuracy and simplicity, a radial basis function（RBF） based approach is proposed for mapping the force field from the blade surface panels to the RANS model. The effective wake field is evaluated in two ways, i.e., by extrapolation from the flat planes upstream of the propeller disk, and by direct computation in a curved surface upstream of and parallel to the blade leading edges. The hull-propeller system of a real propeller geometry is further simulated with the sliding mesh model to numerically verify the hybrid approach. Numerical simulations are conducted for the fully appended SUBOFF submarine model. The high accuracy of the RBF-based interpolation scheme is confirmed, and the effective wake fraction predicted by the hybrid approach is found consistent with that obtained by the sliding mesh model. The effective wake fractions predicted by the two methods are, respectively, 4.6% and 3% larger than the nominal one.