Prediction on the influence of ambient temperature and humidity to measuring instrument of thermal conductivity based on BP neural network

In order to break the limitations on field applications of steady-state thermal conductivity measurement techniques, a new measuring system using the method termed point-heating steady state thermal conductivity measurement method is developed in this work. A corresponding 3D thermal transport model has been built to correlate the surface temperature rise with the incident heat flux, sample's thermal conductivity, and the location for temperature probing. The surface temperature is monitored by an infrared camera, which is easily affected by ambient temperature and humidity. BP neural network model is then employed to predict the influence of ambient temperature and humidity on the measuring instrument of thermal conductivity. The generalization and robustness of the BP neural network model are further verified by comparison with outputs of linear fitting and nonlinear fitting. The prediction model of F (x, y, z) based on BP neural network has good accuracy, and the error is between -0.17 and +0.17, which also improves the speed of measuring the thermal conductivity of the measuring instrument.