Design Optimisation/Simulation TRIZ Cases
- Human Motion Simulation Using Relative Joint Angle Changes
Computerized human movement simulation adapts empirical data to arbitrary postures using relative joint angle changes.
- Graph Neural Network Mesh Simulation for Computational Efficiency
Segmenting meshes by resolution reduces computational resource requirements while maintaining high simulation accuracy.
- Machine Learning Model for NMR Porosity Prediction
A machine learning model generates petrophysical analysis data from standard well logs.
- FEM Mesh Group Scheme for Stamped Sheet Metal Surface Imperfections
A finite element mesh uses a group-to-group scheme to create smooth surface representations from shell elements and nodes.
- Meshfree Simulation of Brittle Material Cracks Using Strain Regularization
A meshfree model segments particles into damage zones and applies a morphing function to the strain field for accurate brittle material simulation.
- Simulation Grid Depth-to-Size Ratio for Fluid Rendering
A simulation grid uses a consistent depth-to-size ratio from the camera perspective to distribute fluid motion data across cells.
- PCB Simulation via Segmented Finite Element Modeling
Segmenting PCB simulation into independent finite element models reduces computational complexity while maintaining thermal stress analysis accuracy.
- Stiffened Composite Panel Weight Optimization via Iterative Simulation
Iterative simulation of stiffened composite panels adjusts design variables to reduce structural mass.
- Dynamic Computing Resource Availability Rating via Probability Models
A server computing device generates application session data matrices and derives component signature blocks to identify resource dependencies.
- Modular Tensegrity Design Engine for Complex Structures
A modular tensegrity design engine lets users assemble virtual building blocks and optimize force networks to stabilize complex structures.
- ML Sequence Generation Ecosystem for IC Design Verification
Online inference reinforcement learning discovers new states to automate test sequence generation and reduce human error in verification.