Prediction of thermal insulation performance of vacuum glass based on extreme random forest model

Abstract

For the prediction of the U value of the heat transfer coefficient of vacuum glass, a new method is proposed in this paper. By constructing a prediction model of vacuum glass heat transfer coefficient based on extreme random forest and random forest algorithm, the prediction of U value of heat transfer coefficient is realized. This paper measures the excellence of the prediction model by using the MAE, MSE and 𝑅ଶ squared value parameters and plotting the observed curve between the predicted value and the actual value. Finally, the evaluation values of extreme forest are 0.0458, 0.0050, 0.9784, and the prediction curves are very consistent, which proves that the extreme forest prediction model has a good U value prediction ability. At the same time, by introducing the RMSE image curve, it is observed that compared with random forest, extreme forest has better generalization ability under smaller data. Aiming at the difficulty of collecting vacuum glass data sets, this paper introduces the feature importance analysis method, and the correlation between the temperature change rate and the heat transfer coefficient U is as high as 0.9882. It provides a new idea for further reducing the size of the dataset.

Prediction of insulation performance of vacuum glass based on cascade forest model

“…Unlike random forests, extreme random forests generally do not use random sampling and utilize the original training set of each decision tree. At the same time, in the key feature division stage, different from random forest, extreme random forest will randomly split at nodes, instead of selecting the optimal split attribute and threshold [17] . In general, extreme random forest is more excellent than random forest in terms of classification accuracy and training time.…”

Prediction of heat transfer performance of vacuum glass based on extreme gradient boosting algorithm

“…The regression prediction based on small sample data is poor using the usual algorithms based on large amount of data, and often faces overfitting problems, For example, the heat transfer process modeling of vacuum glass based on LSSVM. [5] In this paper, on top of the GBDT, XGBoost algorithm after optimization is used and evaluated by criteria such as MAE and R2, in which the R2 score reaches 99.83%,Nested cross-loop validation of the samples is performed, which effectively solves the problem of validation set for small sample data.…”