Research Article
Study of Measurement and Inverse Prediction Methods of Heat Storage Efficiency for the Wood Heating Floor
@INPROCEEDINGS{10.1007/978-3-030-82562-1_35, author={Guangyue Du}, title={Study of Measurement and Inverse Prediction Methods of Heat Storage Efficiency for the Wood Heating Floor}, proceedings={Multimedia Technology and Enhanced Learning. Third EAI International Conference, ICMTEL 2021, Virtual Event, April 8--9, 2021, Proceedings, Part I}, proceedings_a={ICMTEL}, year={2021}, month={7}, keywords={Wood floor Heat storage performance Heat transfer inverse problem Neural network}, doi={10.1007/978-3-030-82562-1_35} }- Guangyue Du
Year: 2021
Study of Measurement and Inverse Prediction Methods of Heat Storage Efficiency for the Wood Heating Floor
ICMTEL
Springer
DOI: 10.1007/978-3-030-82562-1_35
Abstract
Wood heating floor has been widely used today, but the performance evaluation system still needs to be further improved. The author's team developed the equipment for testing heat storage efficiency of wood floor. The basic principle is to calculate the heat storage efficiency of test samples by temperature field distribution which is measured by the sensor in closed cavity. Based on the study method for the inverse heat transfer problem, this paper proposed an inversion calculation method for the heat storage efficiency of the test sample according to the measured temperature field. BP neural network technique is adopted for the inversion calculation which is a nonlinear problem. Numerical model of the testing cavity is established with CFD software. The temperature field data of a single structure sample under different initial temperature range of 50 ℃ ~ 130 ℃ are obtained by simulation (different simulation conditions are divided by interval of 5 ℃). After repeated training, a better neural network model is obtained. The average values of the calculation error and the fitting degree of the testing set areMRE= 0.67%,MAE= 19.68%,MSE= 1.16%,R2= 0.97. It can be seen that, the well trained BP neural network model could predict out the heat storage of different wood floor samples, and provides support for the analysis of heat storage efficiency for wood heating floor.
