Zenon Waszczyszyn

A Fuzzy Neural Network for the Analysis of Experimental Structural Mechanics Problems

A simplified neuro-fuzzy network is formulated. The membership functions of the network weights are computed on the base of learning the single patterns. The network is applied to the interval analysis of two problems from experimental structural mechanics.

DEVELOPMENT OF A HYBRID SYSTEM FOR IDENTIFICATION OF ELASTIC MATERIAL IN COMPOSITE LAMINA: APPLICATION OF LAMB WAVES AND NEURAL NETWORKS

A new Hybrid Computational System is presented, developed for the identification of homogeneous, elastic, hexagonally orthotropic plate parameters. Attention is focused on the construction of dispersion curves, related to Lamb waves. The main idea of the hybrid system lies in the separation of two essential basic computational stages, corresponding to the direct and inverse analyses. In the frame of the first stage an experimental dispersion curve DCexp is constructed, applying Guided Wave Measurement technique. The other stage is supported on the application of artificial neural network trained ‘off line’. Two case studies are presented, corresponding either to pseudo-experimental computer simulations or to laboratory tests.

Neutral and Shakedown-Type Domains for Axisymmetric Plates and Shells under Cycles of Pressure and Temperature

Incremental equations for elastic-plastic material with combined isotropic-kinematic strain-hardening and equations of large deflections of shells of revolution are used. The shooting method is applied to integrate the equations along the Load Control Program /LCP/ path. Neutral Domain Curves/NDC/ are evaluated for prescribed points of LCP. by means of an approximate method of superposition of an elastic-plastic solution and elastic unloadings. Skakedown-type Domains /SD/ are calculated for the radial LCP paths.