Within the research, selected multilayer technological systems created as combinations of water-glass containing moulding sand with
foundry tooling, were characterised on the grounds of their electrical properties. By measuring resonance frequency and quality factor of a
waveguide resonance cavity, real component of permittivity εr′ and loss tangent tgδ were determined for multilayer foundry systems with
various qualitative and quantitative compositions. It was demonstrated that combination of a sandmix and foundry tooling with known
dielectric properties results in a system with different physico-chemical properties, whose relation to the parameters of individual
components of the system is undefined at this research stage. On the grounds of measurement results, theoretical value of microwave
heating power, dissipated in unit volume of the selected multilayer foundry system, was determined. Knowledge of theoretical heating
power and evaluation of physical, chemical and structural changes occurring in moulding sands exposed to microwaves in such a
technological system makes a ground for empirical modelling of the process of microwave heating of foundry moulds and cores.
Presented are results of a research on the possibility of using artificial neural networks for forecasting mechanical and technological
parameters of moulding sands containing water-glass, hardened in the innovative microwave heating process. Trial predictions were
confronted with experimental results of examining sandmixes prepared on the base of high-silica sand, containing various grades of
sodium water-glass and additions of a wetting agent. It was found on the grounds of obtained values of tensile strength and permeability
that, with use of artificial neural networks, it is possible complex forecasting mechanical and technological properties of these materials
after microwave heating and the obtained data will be used in further research works on application of modern analytic methods for
designing production technology of high-quality casting cores and moulds.