A5048468661- Manufacturing Process and Optimization
- Metallurgy and Material Forming
- Material Properties and Failure Mechanisms
- Fatigue and fracture mechanics
- Robot Manipulation and Learning
- Additive Manufacturing and 3D Printing Technologies
- Simulation and Modeling Applications
- Human Motion and Animation
- Composite Structure Analysis and Optimization
- Augmented Reality Applications
- Numerical methods in engineering
- Natural Language Processing Techniques
- Concrete and Cement Materials Research
- Model Reduction and Neural Networks
- EFL/ESL Teaching and Learning
- Composite Material Mechanics
- Laser and Thermal Forming Techniques
- Structural Health Monitoring Techniques
- Mechanical Behavior of Composites
- Vibration and Dynamic Analysis
- Machine Learning in Materials Science
- Probabilistic and Robust Engineering Design
- Hand Gesture Recognition Systems
- Topology Optimization in Engineering
- Concrete Properties and Behavior
Northwestern University
2021-2024
This paper presents the concept of reduced order machine learning finite element (FE) method. In particular, we propose an example such method, proper generalized decomposition (PGD) hierarchical deeplearning neural networks (HiDeNN), called HiDeNN-PGD. We described first HiDeNN interface seamlessly with current commercial and open source FE codes. The proposed method can reduce significantly degrees freedom for physics based modeling is able to deal high dimensional problems. found more...
Prediction of the autogenous shrinkage referred to as reduction apparent volume concrete under seal and isothermal conditions is great significance in service life analysis design durable structures, especially with increasing use low water-to-cement ratios. However, due highly complex mechanism shrinkage, it hard accurate mechanistic models for it. Existing state-of-the-art do not perform well several reasons such being able capture faster change at early ages (swelling), coefficients used...
The English wheel is a highly flexible traditional metalworking tool. Currently, wheeling manual manufacturing process that allows skilled craftsmen/smiths to form compound curves. geometric accuracy and repeatability of the forming pieces are heavily influenced by human factors. Consequently, its applications in modern production industries limited due mechanism. This paper presents application single-robot automation system (i.e., robot forming). reads simulation-based toolpaths or...
Concurrent analysis of composite materials can provide the interaction among scales for better design, analysis, and performance prediction. A data-driven concurrent n-scale modeling theory ($\textrm{FExSCA}^\textrm{n-1}$) is proposed in this paper utilizing a mechanistic reduced order model (ROM) called self-consistent clustering (SCA). We demonstrated with $\textrm{FExSCA}^2$ approach to study 3-scale woven carbon fiber reinforced polymer (CFRP) laminate structure. significantly expensive...