Solution of nonmonotone friction unilateral contact problems within a neural network environment

Abstract

A neural network approach for dealing with the solution of frictional contact problems is proposed. Such an approach permits the rational treatment of the aforementioned limit states. In particular, discretizing the structure by means of a suitable finite element scheme, the structural behavior is described by a discrete hemivariational inequality. An effective algorithm equivalently transforms the initial nonmonotone problem into a sequence of monotone, Coulomb friction problems. Then, a neural network computing system is applied in order to solve efficiently the arising optimization problems.