Resumen de Non‐destructive testing of layered structures using generalised radial basis function networks trained by the orthogonal least squares learning algorithm

I.T. Rekanos, T.V. Yioultsis, T. D. Tsiboukis

• The evaluation of the conductivity profile of layered metallic structures is performed via the inversion of the impedance of a circular air cored probe coil of rectangular cross section. The inversion approach is based on the implementation of generalised radial basis function neural networks. The choice of the size of the network and the evaluation of its weights are handled by the orthogonal least squares learning algorithm. The merits of the proposed method are illustrated in the light of two examples concerning non‐destructive testing applications.