An official website of the United States government
Additive manufacturing (AM) enables the fabrication of complex, highly customized geometries. However, the design and fabrication of structures with advanced functionalities, such as multistability and fail-safe mechanism, remain challenging due to the significant time and costs required for high-fidelity simulations and iterative prototyping. In this study, we investigate the application of Bayesian Optimization (BO), an advanced machine learning framework, to accelerate the discovery of optimal AM compatible designs with such advanced properties. BO uses a probabilistic surrogate to strategically balances the exploration of design space with few test designs and the exploitation of design space near current best performing designs, thereby reducing the number of design simulations needed. While existing studies have demonstrated the potential of BO in AM, most have focused on static or simple designs. Here, we target multistable structures that can reconfigure among multiple stable states in response to external conditions. Since mechanical performance (e.g., strength) is configuration-dependent, our goal is to identify high performing designs while ensuring that strength in all stable configurations exceeds a prescribed threshold for structural robustness.
more »
« less
A Bayesian experimental autonomous researcher for mechanical design
While additive manufacturing (AM) has facilitated the production of complex structures, it has also highlighted the immense challenge inherent in identifying the optimum AM structure for a given application. Numerical methods are important tools for optimization, but experiment remains the gold standard for studying nonlinear, but critical, mechanical properties such as toughness. To address the vastness of AM design space and the need for experiment, we develop a Bayesian experimental autonomous researcher (BEAR) that combines Bayesian optimization and high-throughput automated experimentation. In addition to rapidly performing experiments, the BEAR leverages iterative experimentation by selecting experiments based on all available results. Using the BEAR, we explore the toughness of a parametric family of structures and observe an almost 60-fold reduction in the number of experiments needed to identify high-performing structures relative to a grid-based search. These results show the value of machine learning in experimental fields where data are sparse.
more »
« less
- Award ID(s):
- 1661412
- PAR ID:
- 10186120
- Date Published:
- Journal Name:
- Science Advances
- Volume:
- 6
- Issue:
- 15
- ISSN:
- 2375-2548
- Page Range / eLocation ID:
- eaaz1708
- Format(s):
- Medium: X
- Sponsoring Org:
- National Science Foundation
More Like this
-
-
An autonomous experimentation platform in manufacturing is supposedly capable of conducting a sequential search for finding suitable manufacturing conditions by itself or even for discovering new materials with minimal human intervention. The core of the intelligent control of such platforms is a policy to decide where to conduct the next experiment based on what has been done thus far. Such policy inevitably trades off between exploitation and exploration. Currently, the prevailing approach is to use various acquisition functions in the Bayesian optimization framework. We discuss whether it is beneficial to trade off exploitation versus exploration by measuring the element and degree of surprise associated with the immediate past observation. We devise a surprise-reacting policy using two existing surprise metrics, known as the Shannon surprise and Bayesian surprise. Our analysis shows that the surprise-reacting policy appears to be better suited for quickly characterizing the overall landscape of a response surface under resource constraints. We do not claim that we have a fully autonomous experimentation system but believe that the surprise-reacting capability benefits the automation of sequential decisions in autonomous experimentation.more » « less
-
Additive manufacturing (AM) is a disruptive technology with a unique capability in fabricating parts with complex geometry and fixing broken supply chains. However, many AM techniques are complicated with their processing features due to complex heating and cooling cycles with the melting of feedstock materials. Therefore, it is quite challenging to directly apply the materials design and processing optimization method used for conventional manufacturing to AM techniques. In this viewpoint paper, we discuss some of the ongoing efforts of high-throughput (HT) experimentation, which can be used for materials development and processing design. Particularly, we focus on the beam- and powder-based AM techniques since these methods have demonstrated success in HT experimentation. In addition, we propose new opportunities to apply AM techniques as the materials informatic tools contributing to materials genome.more » « less
-
This paper presents a framework based on either iterative simulation or iterative experimentation for constructing an optimal, open-loop maneuver to regulate the aerodynamic force on a wing in the presence of a known flow disturbance. The authors refer to the method as iterative maneuver optimization and apply it in this paper to regulate lift on a pitching wing during a transverse gust encounter. A candidate maneuver is created by performing an optimal control calculation on a surrogate model of the wing–gust interaction. Execution of the proposed maneuver in a high-fidelity simulation or experiment provides an error signal based on the difference between the force predicted by the surrogate model and the measured force. The error signal provides an update to the reference signal used by the surrogate model for tracking. A new candidate maneuver is calculated such that the surrogate model tracks the reference force signal, and the process repeats until the maneuver adequately regulates the force. The framework for iterative maneuver optimization is tested on a discrete vortex model as well as in experiments in a water towing tank. Experimental results show that the proposed framework generates a maneuver that reduces the magnitude of lift overshoot by 92% for a trapezoidal gust with peak velocity equal to approximately 0.7 times the freestream flow speed.more » « less
-
Batch Bayesian optimization has been shown to be an efficient and successful approach for black-box function optimization, especially when the evaluation of cost function is highly expensive but can be efficiently parallelized. In this paper, we introduce a novel variational framework for batch query optimization, based on the argument that the query batch should be selected to have both high diversity and good worst case performance. This motivates us to introduce a variational objective that combines a quantile-based risk measure (for worst case performance) and entropy regularization (for enforcing diversity). We derive a gradient-based particle-based algorithm for solving our quantile-based variational objective, which generalizes Stein variational gradient descent (SVGD). We evaluate our method on a number of real-world applications and show that it consistently outperforms other recent state-of-the-art batch Bayesian optimization methods. Extensive experimental results indicate that our method achieves better or comparable performance, compared to the existing methods.more » « less
- Free Publicly Accessible Full Text
-
Accepted Manuscript1.0
- Journal Article:
- https://doi.org/10.1126/sciadv.aaz1708
