A5077474190- Additive Manufacturing and 3D Printing Technologies
- Manufacturing Process and Optimization
- Machine Learning in Materials Science
- Software Engineering Research
- Data Visualization and Analytics
- Injection Molding Process and Properties
- Advanced Multi-Objective Optimization Algorithms
- Chemical Synthesis and Analysis
- Optimal Experimental Design Methods
- Gaussian Processes and Bayesian Inference
- 3D Shape Modeling and Analysis
Massachusetts Institute of Technology
2021-2022
Machine learning can aid the discovery of useful 3D printing material formulations.
Abstract Polymers are widely studied materials with diverse properties and applications determined by molecular structures. It is essential to represent these structures clearly explore the full space of achievable chemical designs. However, existing approaches cannot offer comprehensive design models for polymers because their inherent scale structural complexity. Here, a parametric, context‐sensitive grammar designed specifically (PolyGrammar) proposed. Using symbolic hypergraph...
We present AutoOED, an Optimal Experiment Design platform powered with automated machine learning to accelerate the discovery of optimal solutions. The solves multi-objective optimization problems in time- and data-efficient manner by automatically guiding design experiments be evaluated. To automate process, we implement several Bayesian algorithms state-of-the-art performance. AutoOED is open-source written Python. codebase modular, facilitating extensions tailoring code, serving as a...
Polymers are widely-studied materials with diverse properties and applications determined by different molecular structures. It is essential to represent these structures clearly explore the full space of achievable chemical designs. However, existing approaches unable offer comprehensive design models for polymers because their inherent scale structural complexity. Here, we present a parametric, context-sensitive grammar designed specifically representation generation polymers. As...
Enabling additive manufacturing to employ a wide range of novel, functional materials can be major boost this technology. However, making such printable requires painstaking trial-and-error by an expert operator, as they typically tend exhibit peculiar rheological or hysteresis properties. Even in the case successfully finding process parameters, there is no guarantee print-to-print consistency due material differences between batches. These challenges make closed-loop feedback attractive...
Additive manufacturing has become one of the forefront technologies in fabrication, enabling new products impossible to manufacture before. Although many materials exist for additive manufacturing, they typically suffer from performance trade-offs preventing them replacing traditional techniques. Current are designed with inefficient human-driven intuition-based methods, leaving short optimal solutions. We propose a machine learning approach accelerate discovery mechanical performance. A...