Integrating Wide and Deep Neural Networks with Squeeze-and-Excitation Blocks for Multi-Target Property Prediction in Additively Manufactured Fiber Reinforced Composites

TL;DR

This paper presents a novel multi-input, multi-target neural network model that efficiently predicts multiple properties of additively manufactured fiber-reinforced composites, reducing experimental testing and aiding process optimization.

Contribution

It introduces an integrated approach combining Latin Hypercube Sampling with a squeeze-and-excitation wide and deep neural network for multi-property prediction in CFRC-AM.

Findings

The model achieved a MAPE of 12.33% on test data.

It outperformed traditional machine learning models significantly.

SHAP analysis identified reinforcement strategy as key to mechanical performance.

Abstract

Continuous fiber-reinforced composite manufactured by additive manufacturing (CFRC-AM) offers opportunities for printing lightweight materials with high specific strength. However, their performance is sensitive to the interaction of process and material parameters, making exhaustive experimental testing impractical. In this study, we introduce a data-efficient, multi-input, multi-target learning approach that integrates Latin Hypercube Sampling (LHS)-guided experimentation with a squeeze-and-excitation wide and deep neural network (SE-WDNN) to jointly predict multiple mechanical and manufacturing properties of CFRC-AMs based on different manufacturing parameters. We printed and tested 155 specimens selected from a design space of 4,320 combinations using a Markforged Mark Two 3D printer. The processed data formed the input-output set for our proposed model. We compared the results with those from commonly used machine learning models, including feedforward neural networks, Kolmogorov-Arnold networks, XGBoost, CatBoost, and random forests. Our model achieved the lowest overall test error (MAPE = 12.33%) and showed statistically significant improvements over the baseline wide and deep neural network for several target variables (paired t-tests, p <= 0.05). SHapley Additive exPlanations (SHAP) analysis revealed that reinforcement strategy was the major influence on mechanical performance. Overall, this study demonstrates that the integration of LHS and SE-WDNN enables interpretable and sample-efficient multi-target predictions, guiding parameter selection in CFRC-AM with a balance between mechanical behavior and manufacturing metrics.