The application of the artificial neural network and hot probe method in thermal parameters determination of heat insulation materials Part 1 - thermal model consideration

Abstract

The article presents an idea of a measurement system with hot probe for testing thermal parameters of heat insulation materials. In comparison to the classical method of the line heat source (LHS) numerous assumptions about model of heat flow in the sample of material are not needed. The model of a nonstationary heat flow process in the sample of material with hot probe and an auxiliary thermometer is based on a two-dimensional heat-conduction model and includes heat capacity of probe handle. For solving the system of partial differential equations describing the model, the finite element method (FEM) was applied. Simulations of heat flow process were carried out in the Matlab environment and the results are presented in part 1 of the paper. Part 2 is concentrated on the usability of the artificial neural network in solving the inverse heat transfer problem in a sample of heat insulation material. The proposed method is suitable for immediate measurement in building site or factory.