Kassandra Hernandez
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Kassandra Hernandez has a total of 15 co-authors. Here are the top co-authors by number of shared publications:
- Devin J. Roach
School of Mechanical, Industrial, and Manufacturing Engineering Oregon State University Corvallis OR 97331 USA
2 shared publications - Aaron B. Hoskins
University of Maryland
1 shared publication - Adam Bischoff
School of Mechanical, Industrial, and Manufacturing Engineering Oregon State University Corvallis OR 97331 USA
1 shared publication - Andre Olarra
Phil and Penny Knight Campus for Accelerating Scientific Impact University of Oregon Eugene Oregon USA
1 shared publication Avijit Paul
Department of Electronics & Telecommunication Engineering Rajshahi University of Engineering & Technology Rajshahi Bangladesh
1 shared publicationElliot Yoo
School of Mechanical Industrial and Manufacturing Engineering Oregon State University Corvallis OR USA
1 shared publication
Latest Publications
- Open Access
- 17 September 2026
- Published by Wiley in SPE Polymers
- Vol. 7 (4) , e70068
Influence of 3D Printing Parameters on ULTEM 9085 Mechanical Properties Using Explainable Machine Learning
Fused filament fabrication (FFF) printed polyetherimide (PEI), commercially available as ULTEM 9085, is qualified by the Federal Aviation Administration for aerospace structural applications. Its mechanical performance depends strongly on printing parameters, including build orientation, number of contours, raster angle, and air gap, whose nonlinear interactions govern void formation, interlayer bonding, and ultimate strength. Prior work using artificial neural networks (ANNs) predicted ULTEM 9085 properties with under 5% error from a single data split, leaving two questions open: whether that accuracy holds across repeated splits, and whether the model's reasoning can be physically interpreted. This study addresses both gaps. Eight regression algorithms (Ridge, Decision Tree, Random Forest, Extra Trees, Gradient Boosting, XGBoost, K‐Nearest Neighbors, and Support Vector Regression) are benchmarked to jointly predict complete stress–strain curves and three scalar mechanical properties (tensile strength, elastic modulus, yield strength) from the four printing parameters, evaluated across five random data splits. SHAP and LIME are then applied to the best‐performing model to attribute its predictions to individual printing parameters. Extra Trees Regressor achieves the lowest and most stable test mean absolute error (MAE) of 0.162 ± 0.041 in scaled space across five seeds, with scalar property errors of 4.0% (tensile strength), 4.4% (elastic modulus), and 8.5% (yield strength), accuracy comparable to the ANN baseline at a fraction of the computational cost. SHAP and LIME attributions agree that the number of contours and build orientation are the dominant drivers of tensile strength, with air gap acting as a smaller, suppressive factor. These results support Extra Trees with SHAP/LIME explanation as a repeatable, interpretable, and computationally inexpensive surrogate for reducing the physical testing burden in aerospace qualification of 3D‐printed ULTEM 9085.
- 17 September 2026
- Published by Wiley in SPE Polymers
- Vol. 7 (4) , e70068
Open AccessInfluence of 3D Printing Parameters on ULTEM 9085 Mechanical Properties Using Explainable Machine Learning
Fused filament fabrication (FFF) printed polyetherimide (PEI), commercially available as ULTEM 9085, is qualified by the Federal Aviation Administration for aerospace structural applications. Its mechanical performance depends strongly on printing parameters, including build orientation, number of contours, raster angle, and air gap, whose nonlinear interactions govern void formation, interlayer bonding, and ultimate strength. Prior work using artificial neural networks (ANNs) predicted ULTEM 9085 properties with under 5% error from a single data split, leaving two questions open: whether that accuracy holds across repeated splits, and whether the model's reasoning can be physically interpreted. This study addresses both gaps. Eight regression algorithms (Ridge, Decision Tree, Random Forest, Extra Trees, Gradient Boosting, XGBoost, K‐Nearest Neighbors, and Support Vector Regression) are benchmarked to jointly predict complete stress–strain curves and three scalar mechanical properties (tensile strength, elastic modulus, yield strength) from the four printing parameters, evaluated across five random data splits. SHAP and LIME are then applied to the best‐performing model to attribute its predictions to individual printing parameters. Extra Trees Regressor achieves the lowest and most stable test mean absolute error (MAE) of 0.162 ± 0.041 in scaled space across five seeds, with scalar property errors of 4.0% (tensile strength), 4.4% (elastic modulus), and 8.5% (yield strength), accuracy comparable to the ANN baseline at a fraction of the computational cost. SHAP and LIME attributions agree that the number of contours and build orientation are the dominant drivers of tensile strength, with air gap acting as a smaller, suppressive factor. These results support Extra Trees with SHAP/LIME explanation as a repeatable, interpretable, and computationally inexpensive surrogate for reducing the physical testing burden in aerospace qualification of 3D‐printed ULTEM 9085.
- Open Access
- 5 January 2026
- Published by Wiley in Advanced Functional Materials
- Vol. 36 (33)
Spatially Tailorable Liquid Crystalline Elastomer Alignment During Digital Light Process 3D Printing
Liquid crystal elastomers (LCEs) are anisotropic polymeric smart materials with promise for soft robotic actuators, dampers, and adhesives. Realizing these applications requires precise 3D alignment of the polymer backbone, yet current manufacturing approaches struggle to produce complex spatial patterns in three dimensions. Here, we introduce a digital light processing (DLP) 3D printing strategy that enables voxel‐level control of LCE alignment domains. By integrating a rotatable magnetic array with DLP photomasking, we achieve spatially tunable structures at voxel resolutions. This approach allows freeform 180° alignment within individual voxels, generating highly nonlinear shape transformations in both 2D films and 3D architectures. Finite element modeling and inverse design guide the creation of multidomain alignment patterns that could achieve targeted nonlinear deformation behaviors. As a demonstration, multidomain LCE smart valves are fabricated that exhibit up to 70% improved flow control compared to monodomain analogues. This technique dramatically expands the design space of 3D programmable matter and establishes a pathway toward complex, application‐ready LCE systems.
- 5 January 2026
- Published by Wiley in Advanced Functional Materials
- Vol. 36 (33)
Open AccessSpatially Tailorable Liquid Crystalline Elastomer Alignment During Digital Light Process 3D Printing
Liquid crystal elastomers (LCEs) are anisotropic polymeric smart materials with promise for soft robotic actuators, dampers, and adhesives. Realizing these applications requires precise 3D alignment of the polymer backbone, yet current manufacturing approaches struggle to produce complex spatial patterns in three dimensions. Here, we introduce a digital light processing (DLP) 3D printing strategy that enables voxel‐level control of LCE alignment domains. By integrating a rotatable magnetic array with DLP photomasking, we achieve spatially tunable structures at voxel resolutions. This approach allows freeform 180° alignment within individual voxels, generating highly nonlinear shape transformations in both 2D films and 3D architectures. Finite element modeling and inverse design guide the creation of multidomain alignment patterns that could achieve targeted nonlinear deformation behaviors. As a demonstration, multidomain LCE smart valves are fabricated that exhibit up to 70% improved flow control compared to monodomain analogues. This technique dramatically expands the design space of 3D programmable matter and establishes a pathway toward complex, application‐ready LCE systems.
- Open Access
- 8 February 2024
- Published by Elsevier in Trees, Forests and People
- Vol. 15
Machine learning algorithms applied to wildfire data in California's central valley
- 8 February 2024
- Published by Elsevier in Trees, Forests and People
- Vol. 15
Open AccessMachine learning algorithms applied to wildfire data in California's central valley