Rapid identification of elastic modulus of the interface tissue on dental implants surfaces using reduced-basis method and a neural network

This paper proposes a rapid inverse analysis approach based on the reduced-basis method (RBM) and neural network (NN) to identify the “unknown” elastic modulus (Young's modulus) of the interfacial tissue between a dental implant and the surrounding bones. In the present RBM–NN approach, a RBM model is first built to compute displacement responses of dental implant-bone structures subjected to a harmonic loading for a set of “assumed” Young's moduli. The RBM model is then used to train a NN model that is used for actual inverse analysis in real-time. Actual experimental measurements of displacement responses are fed into the trained NN model to inversely determine the “true” elastic modulus of the interfacial tissue. As an example, a physical model of dental implant-bone structure is built and inverse analysis is conducted to verify the present RBM–NN approach. Based on numerical simulation and actual experiments, it is confirmed that the identified results are very accurate, reliable, and the computational saving is very significant. The present RBM–NN approach is found robust and efficient for inverse material characterizations in noninvasive and/or nondestructive evaluations.