Articles
Composites Science and Technology (02663538)
This study presents an innovative application of the Taguchi design of experiment method to optimize the structure of an Artificial Neural Network (ANN) model for the prediction of elastic properties of short fiber reinforced composites. The main goal is to minimize the computational effort required for hyperparameter optimization while enhancing the prediction accuracy. By utilizing a robust experimental design framework, the structure of an ANN model is optimized. This approach involves identifying a combination of hyperparameters that provides optimal predictive accuracy with the fewest algorithmic runs, thereby significantly reducing the required computational effort. The results suggested that the Taguchi-based developed ANN model with three hidden layers, 20 neurons in each hidden layer, elu activation function, Adam optimizer, and a learning rate of 0.001 can predict the anisotropic elastic properties of short fiber reinforced composites with a prediction accuracy of 97.71 %. Then, external validation of the proposed ANN model was done using experimental data, and differences of less than 10 % were obtained, indicating an appropriate predictive performance of the proposed ANN algorithm. Our findings demonstrate that the Taguchi method not only streamlines the hyperparameter tuning process but also substantially improves the algorithm's performance. These results highlight the potential of the Taguchi method as a powerful tool for optimizing machine learning algorithms, especially in scenarios where computational resources are limited. The implications of this study are far-reaching, offering insights for future research in the optimization of different algorithms for improved accuracies and computational efficiencies. © 2024 The Authors
Progress in Additive Manufacturing (23639512)(4)
Material Extrusion (MEX) is the predominant technique in additive manufacturing of polymers, with Polylactic Acid (PLA) being the most commonly utilized material. Alongside the long list of advantages, MEX faces a major pitfall due to the mechanical weakness of parts. Moreover, accurately modeling the anisotropic failure of MEX specimens remains a persistent challenge. This paper, first, reviews the few previously established tensile strength prediction models to predict the mechanical behavior of PLA and meticulously analyzes their advantages and disadvantages. By phenomenologically exploring failure modes—specifically, the Layer Separation Mode (LSM) and the Layer Breakage Mode (LBM)—this study proposes a novel bilinear model to describe failure in MEX parts and predict the ultimate tensile strength of PLA in the conditions studied. The proposed bilinear model offers the advantage of simplicity and eliminates the need for assumptions regarding the shear strength and other complex performance factors. Experimental investigations were conducted with varying layer thicknesses (0.1 mm, 0.2 mm, and 0.3 mm) and printing angles (i.e., 0°, 15°, 30°, 45°, 60°, 75°, and 90°) were carried out, and a thorough comparison between the existing and the proposed models is made to strengthen the understanding of the behavior of PLA. In addition, three methods of deriving the shear strength are investigated for the first time, and the dependence of the models on this parameter is comprehensively explored. It was found that the established bilinear model performs exceptionally well in predicting the tensile strength, and its performance does not depend on other parameters such as shear strength. © The Author(s), under exclusive licence to Springer Nature Switzerland AG 2024.
