RBFNN-based hole identification system in conducting plates

A neural-based signal processing system that exploits radial basis function neural network (RBFNN) is proposed to solve the problem of detecting and locating circular holes in conducting plates by means of nondestructive eddy currents testing. The capabilities of basic multilayer perceptron and radial basis function (RBF) schemes are first investigated. Since the achieved performance revealed insufficient, a two-step procedure is then analyzed: in the first step, an RBFNN is used to estimate the distances between the hole's center and the eddy current magnetic sensors; a least square algorithm is then exploited in order to locate the hole starting from the previously estimated distances. The performance of the proposed system are tested on a database of simulated experiments based on the a priori knowledge of the corresponding boundary value direct problem solution, by taking advantage of the closed-form analytical expression of the solution in order to generate a wide range of possible sensor-hole configurations. Both noiseless and noisy measurements are taken into account for assessing the system robustness. The main result achieved is discussed.