In this paper, a new localized radial basis function (RBF) method based on partition of unity (PU) is proposed for solving boundary and initial-boundary value problems. The benefits from direct discretization approach called the “direct RBF (D-RBF-PU)” method. Thanks to avoiding all derivatives PU weight functions as well lower local approximants, faster simpler than standard RBF-PU Besides, di...

In this paper, learning algorithms for radial basis function (RBF) networks are discussed. Whereas multilayer perceptrons (MLP) are typically trained with backpropagation algorithms, starting the training procedure with a random initialization of the MLP's parameters, an RBF network may be trained in many different ways. We categorize these RBF training methods into one-, two-, and three-phase ...

We present a generalization of the RBF-FD method that allows full control of the overlap between RBF-FD stencils. We accomplish this by introducing a continuous overlap parameter δ ∈ [0, 1] such that δ = 1 recovers the standard RBF-FD method and δ = 0 results in a full decoupling of the RBF-FD stencils. We show with a simple example that global interpolation with both RBFs and RBFs augmented wi...

The current fault diagnosis methods based on conventional BP neural network and RBF neural network exist long training time, slow convergence speed and low judgment accuracy rate and so on. In order to improve the ability of fault diagnosis, this paper puts forward a kind of fault diagnosis method based on RBF Neural Network improved by PSO algorithm. By using particle swarm algorithm’s heurist...

We present a generalization of the RBF-FD method that allows full control of the overlap between RBF-FD stencils. We accomplish this by introducing a continuous overlap parameter δ ∈ [0, 1] such that δ = 1 recovers the standard RBF-FD method and δ = 0 results in a full decoupling of the RBF-FD stencils. We show with a simple example that global interpolation with both RBFs and RBFs augmented wi...