A neural network method for quantitative depth profiling of inhomogeneous materials with quasi-continuously varying electrical conductivity profiles is presented. The possibilities and limitations of eddy-current depth profiling are examined on the basis of insight into the physics of eddy currents and of the statistics of simulation results obtained for large sets of inversion examples. Neural network reconstructions of electrical conductivity profiles retrieved from experimental eddy-current data on artificial samples are discussed. The approach presented allows one to study the eddy-current inverse problem in a flexible way thanks to the combination of a versatile profile parametrization and the feasibility of fast neural network performance tests.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.