Determination of Poisson's ratio by spherical indentation using neural networks - Part II: Identification method

In a previous paper it has been shown that the load and the unloading stiffness are, among others, explicit functions of the Poisson's ratio, Efa spherical indenter is pressed into a metal material. These functions can be inverted by using neural networks in order to determine the Poisson 's ratio as a function of the load and the unloading stiffness measured at different depths. Also, the inverse function possesses as an argument the ratio of the penetration depth and that depth, at which plastic yield occurs for the first time. The latter quantity cannot be measured easily. In the present paper same neural networks are developed in order to identify the value of Poisson 's ratio, After preparing the input darn appropriately, two neural networks are trained, the first one being related to Set 2 of the previous paper: In order to avoid an explicit measurement of the yield depth, the second neural network has to be trained in such a way, that its solution intersects with that of Set 2 at the correct value of Poisson 's ratio. This allows to identify, Poisson's ratio with high accuracy within the domain of finite element data.