A neurocomputing model for the elastoplasticity (Q1968496)

Using the parametric variational principle for elastoplasticity, the authors propose a new variational principle called here ``two-type variable variational principle'', so that the neural networks theory can be used to solve the corresponding elastoplastic problem. For the two-type-variable minimum potential energy principle, the energy function and the constraint conditions of the neural networks are built up, and the structure and parameters are given. As an example, the authors consider the neurocomputation of a simple truss. It is shown that the neurocomputed conclusions are in good agreement with theoretical solutions. The elastoplastic solutions can be obtained within an elapsed nano-second-order time of the circuit time-constant.