Global ETD Search
Search theses and dissertations gathered from participating repositories worldwide. Every result links back to the library that holds it. No account is needed.
Results
Showing 1 to 13 of 13 for “"physics-informed model"”.
-
Automated Materials Spectroscopy and Topology Optimizations Using Genetic Algorithms
… for specific spectra methods such as EXAFS, Astrophysics, Nano-Indentation, and many more. For GA implementation that relates to EXAFS, we have demonstrated the usage of GA to correctly identify chemical species presented, for Copper metal species, Technetium compounds, and in-situ of SnS2 …
-
Machine Learning in Conjunction with Molecular Simulations for Nanoporous Materials Discovery
… Then, Chapter 2 develops a machine learning model, named SorbNet, on the optimization of the desorptive drying process. SorbNet is trained using loss function based on statistical mechanics principles of Monte Carlo simulations. The prediction given by SorbNet is used to perform the design of …
-
Model Predictive Control for Dual Three-phase Interior Permanent Magnet Synchronous Motor Drives
… for DTP-PMSM drives. First, a finite-control-set model predictive control (FCS-MPC) strategy with an enhanced sector selection method is proposed for high-saliency DTP-PMSM drives. The proposed method improves tracking accuracy in the d-q subspace by reliably identifying the optimal virtual …
-
NOVEL ARCHITECTURE AND MACHINE LEARNING MODELS FOR SYSTEM PROGNOSTIC AND REMAINING USEFUL LIFE PREDICTION WITH UNCERTAINTY QUANTIFICATION
… prevalent challenges in data-driven prognostic models related to prediction accuracy and interoperability. This thesis first proposes a novel computational architecture for accurate prognostic and RUL prediction with uncertainty quantification. This computational architecture integrates signal …
-
Discovering tough and impact-resistant structures using a self-driving lab
… contacts make their performance difficult to model. Thus, physical experiments are often the only way to effectively evaluate the performance of a potential structure. To tackle this problem, we employ a self-driving lab comprised of an automated experimentation system guided by machine …
-
Optimizing Total Hip Arthroplasty using Predictive Dynamic Simulation of Human Sit-to-Stand Movement and Deep Learning for Flexible Spinopelvic Model Identification
… involves integrating an innovative deep learning model, LanDet—an anatomical landmark detection algorithm—with a predictive human dynamic model for surgical planning. This integration is crucial in considering the often-neglected aspects of spine stiffness, pelvic tilt, and spinopelvic measures, …
-
DIAGNOSIS AND PROGNOSIS OF USED LITHIUM-ION BATTERIES
… on rapid nondestructive measurements and physics-informed learning from limited data. The first part of the dissertation develops rapid state-of-health (SoH) diagnosis for used lithium-ion batteries. Mechanical expansion of pouch cells is measured using digital image correlation (DIC), and …
-
Advancing New Material and Process Capabilities for Multi-Material High Performance Thermoset Additive Manufacturing
… through the development of novel processes and physics-based predictive frameworks. A hybrid vat photopolymerization-direct ink write (VPP-DIW) process is introduced to enable high-resolution, continuous functional grading of high-viscosity thermoset resins. This is supported by a …
-
Explainable Physics-informed Deep Learning for Rainfall-runoff Modeling and Uncertainty Assessment across the Continental United States
Hydrologic models provide a comprehensive tool to calibrate streamflow response to environmental variables. Various hydrologic modeling approaches, ranging from physically based to conceptual to entirely data-driven models, have been widely used for hydrologic simulation. During the recent years, …
-
Physics-informed machine learning for structural dynamics: combining physics and data for offshore structures
Physics-Informed Machine Learning (PIML) aims to exploit the benefits of both physics and data-based modelling approaches; insight, structure and an enhanced ability to extrapolate are provided through physical knowledge, whilst a data-based component increases flexibility and allows for the …
-
Machine Learning Approaches for Understanding Water Droplet Erosion in Metals
… design. Traditional empirical and analytical models often struggle to capture the complex, non-linear interactions of material properties and impact conditions, limiting their predictive accuracy and generalizability. To overcome the limitations of existing models, this thesis introduces a …
-
Fault Detection and Diagnosis for Hairpin Windings in Electric Motors
… health condition of hairpin windings. Further, a model-based method based on the Equivalent Circuit Model (ECM) is built to characterize the frequency response of hairpin windings. It reflects the health status of hairpin windings through the variation of the extracted parameters in the …
-
A Virtual CO2 Sensor for Vehicle Cabins Using Deep Learning and Physics- Based Modelling
… the dependence on dedicated hardware. Three modelling approaches are developed and compared: a purely data-driven deep learning model, a physics-based mass-balance model, and a hybrid approach in which the physics model output is incorporated as an input feature to the data-driven model. …