skip to main content


Title: Multi-objective materials bayesian optimization with active learning of design constraints: Design of ductile refractory multi-principal-element alloys
Award ID(s):
2119103 2001333 1545403 1835690
NSF-PAR ID:
10343399
Author(s) / Creator(s):
; ; ; ; ;
Date Published:
Journal Name:
Acta Materialia
Volume:
236
Issue:
C
ISSN:
1359-6454
Page Range / eLocation ID:
118133
Format(s):
Medium: X
Sponsoring Org:
National Science Foundation
More Like this
  1. The design of optical devices is a complex and time-consuming process. To simplify this process, we present a novel framework of multi-fidelity multi-objective Bayesian optimization with warm starts, called Multi-BOWS. This approach automatically discovers new nanophotonic structures by managing multiple competing objectives and utilizing multi-fidelity evaluations during the design process. We employ our Multi-BOWS method to design an optical device specifically for transparent electromagnetic shielding, a challenge that demands balancing visible light transparency and effective protection against electromagnetic waves. Our approach leverages the understanding that simulations with a coarser mesh grid are faster, albeit less accurate than those using a denser mesh grid. Unlike the earlier multi-fidelity multi-objective method, Multi-BOWS begins with faster, less accurate evaluations, which we refer to as “warm-starting,” before shifting to a dense mesh grid to increase accuracy. As a result, Multi-BOWS demonstrates 3.2–89.9% larger normalized area under the Pareto frontier, which measures a balance between transparency and shielding effectiveness, than low-fidelity only and high-fidelity only techniques for the nanophotonic structures studied in this work. Moreover, our method outperforms an existing multi-fidelity method by obtaining 0.5–10.3% larger normalized area under the Pareto frontier for the structures of interest. 
    more » « less
  2. null (Ed.)
    Design optimization of metamaterials and other complex systems often relies on the use of computationally expensive models. This makes it challenging to use global multi-objective optimization approaches that require many function evaluations. Engineers often have heuristics or rules of thumb with potential to drastically reduce the number of function evaluations needed to achieve good convergence. Recent research has demonstrated that these design heuristics can be used explicitly in design optimization, indeed leading to accelerated convergence. However, these approaches have only been demonstrated on specific problems, the performance of different methods was diverse, and despite all heuristics being correct'', some heuristics were found to perform much better than others for various problems. In this paper, we describe a case study in design heuristics for a simple class of 2D constrained multiobjective optimization problems involving lattice-based metamaterial design. Design heuristics are strategically incorporated into the design search and the heuristics-enabled optimization framework is compared with the standard optimization framework not using the heuristics. Results indicate that leveraging design heuristics for design optimization can help in reaching the optimal designs faster. We also identify some guidelines to help designers choose design heuristics and methods to incorporate them for a given problem at hand. 
    more » « less
  3. null (Ed.)
    Chronic pain is a common disease and as a negative consequence can cause paralysis to an individual in the long run. Noninvasive brain stimulation is an effective method to reduce pain in the short term. However, for long-term treatment, neural data analysis along with the stimulation is highly desirable. In this work, a unique multilayer spiral coil with a total dimension of 500 μm×500 μm is designed in a 0.5 μm CMOS process to make it suitable for a fully implantable system. The electrical modeling of the coil is also analyzed and simulated using Keysight's Advanced Design System (ADS) software to compare the theoretical modeling results with the simulation results. The electromagnetic (EM) simulation to characterize the on-chip coil in-terms of scattering parameters (S-parameters), Q -factor, power transfer efficiency (PTE) is performed using the Ansys High-Frequency Structure Simulator (HFSS) software. The operating frequency of the WPT system is chosen to be within 402-405 MHz which is the Medical Implant Communication System (MICS) band. The simulated Q -factor of the proposed on-chip coil is approximately 15 at 402 MHz. The on-chip coil is integrated with an on-chip seven-stage rectifier and some commercial off-the-shelf (COTS) components such as a DC-DC converter and a μ LED to design the complete optogenetic neuro-stimulation system. A minimum power transfer efficiency (PTE) of 0.4% is achieved through a 16 mm thick tissue media using the proposed WPT system. With that efficiency, the proposed system is able to provide constant power to light up a μ LED and proves to be a good candidate for neuromodulation applications. 
    more » « less
  4. null (Ed.)
    Design optimization of metamaterials and other complex systems often relies on the use of computationally expensive models. This makes it challenging to use global multi-objective optimization approaches that require many function evaluations. Engineers often have heuristics or rules of thumb with potential to drastically reduce the number of function evaluations needed to achieve good convergence. Recent research has demonstrated that these design heuristics can be used explicitly in design optimization, indeed leading to accelerated convergence. However, these approaches have only been demonstrated on specific problems, the performance of different methods was diverse, and despite all heuristics being ``correct'', some heuristics were found to perform much better than others for various problems. In this paper, we describe a case study in design heuristics for a simple class of 2D constrained multiobjective optimization problems involving lattice-based metamaterial design. Design heuristics are strategically incorporated into the design search and the heuristics-enabled optimization framework is compared with the standard optimization framework not using the heuristics. Results indicate that leveraging design heuristics for design optimization can help in reaching the optimal designs faster. We also identify some guidelines to help designers choose design heuristics and methods to incorporate them for a given problem at hand. 
    more » « less