Skip to main content
. 2026 Oct 28;18(21):2678. doi: 10.3390/polym18212678
Algorithm 2: DBN-GJO-PI-RNN Multi-Target Prediction
Input:
    Preprocessed dataset D
    Six target variables Y = {y1, y2, …, y6}
    Optimal hyperparameters H*
Output:
    Predicted responses and evaluation metrics
1: Train the DBN using the input features
2: Extract high-level latent representations Z
3: for j = 1 to 6 do
4:     Select target variable yj
5:     Combine Z with the corresponding physical and loading information
6:     Initialize the PI-RNN using H∗
7:     Train the PI-RNN using the data and PI constraints
8:     Generate predictions y^j for target yj
9:     Calculate MAE, MSE, RMSE, and R2
10:    Store predictions and evaluation metrics for yj
11: end for
12: Aggregate the target-wise prediction results
13: Perform failure assessment using the predicted mechanical responses
14: Return all predictions, evaluation metrics, and failure-assessment results