Open AccessCompressive Creep Prediction of Corundum-Mullite Refractories Based on BP Neural Network
Author(s) -
Lina Deng,
Yi Shuai,
Luju Zeng,
Fei Xue,
Chuancai Pan,
Lin Guo-wei,
Yueqiang Liu,
Hang Zhang,
Xiaochen Liu,
Jinli Xie
Publication year - 2019
Publication title -
iop conference series. materials science and engineering
Language(s) - English
Resource type - Journals
eISSN - 1757-899X
pISSN - 1757-8981
DOI - 10.1088/1757-899x/678/1/012086
Subject(s) - corundum , mullite , creep , materials science , compressive strength , artificial neural network , refractory (planetary science) , composite material , metallurgy , computer science , machine learning , ceramic
Compressive creep of corundum-mullite refractories is an important performance to measure whether they can be used stably for a long time at high temperature. Therefore, a compressive creep prediction method of corundum-mullite refractory based on BP neural network is proposed. The inputs of the BP neural network are the content of Al 2 O 3 , SiO 2 , Fe 2 O 3 and the time of high temperature whereas creep rate is the output. The results show that the predicted results can correspond well with the experimental results. The developed BP neural network model can efficiently and accurately predict the creep rate of corundum-mullite refractories.