Autonomous Optimization of Fluid Systems at Varying Length Scales

• URL: http://arxiv.org/abs/2105.13553v1
• Date: Fri, 28 May 2021 02:08:03 GMT
• Title: Autonomous Optimization of Fluid Systems at Varying Length Scales
• Authors: Alexander E. Siemenn, Evyatar Shaulsky, Matthew Beveridge, Tonio Buonassisi, Sara M. Hashmi, Iddo Drori
• Abstract summary: We propose a computer vision-driven Bayesian optimization framework to discover the precise hardware conditions that generate uniform droplets. This framework is validated on two fluid systems, at the micrometer and millimeter length scales, using microfluidic and inkjet systems.
• Score: 55.41644538483948
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Autonomous optimization is a process by which hardware conditions are discovered that generate an optimized experimental product without the guidance of a domain expert. We design an autonomous optimization framework to discover the experimental conditions within fluid systems that generate discrete and uniform droplet patterns. Generating discrete and uniform droplets requires high-precision control over the experimental conditions of a fluid system. Fluid stream instabilities, such as Rayleigh-Plateau instability and capillary instability, drive the separation of a flow into individual droplets. However, because this phenomenon leverages an instability, by nature the hardware must be precisely tuned to achieve uniform, repeatable droplets. Typically this requires a domain expert in the loop and constant re-tuning depending on the hardware configuration and liquid precursor selection. Herein, we propose a computer vision-driven Bayesian optimization framework to discover the precise hardware conditions that generate uniform, reproducible droplets with the desired features, leveraging flow instability without a domain expert in the loop. This framework is validated on two fluid systems, at the micrometer and millimeter length scales, using microfluidic and inkjet systems, respectively, indicating the application breadth of this approach.

Related papers

• Generative AI for fast and accurate Statistical Computation of Fluids [21.820160898966055]
  We present a generative AI algorithm for addressing the challenging task of fast, accurate and robust statistical computation. Our algorithm, termed as GenCFD, is based on a conditional score-based diffusion model.
  arXiv  Detail & Related papers  (2024-09-27T00:26:18Z)
• Regulating Model Reliance on Non-Robust Features by Smoothing Input Marginal Density [93.32594873253534]
  Trustworthy machine learning requires meticulous regulation of model reliance on non-robust features. We propose a framework to delineate and regulate such features by attributing model predictions to the input.
  arXiv  Detail & Related papers  (2024-07-05T09:16:56Z)
• A Universal Framework for Quantum Dissipation:Minimally Extended State Space and Exact Time-Local Dynamics [5.221249829454763]
  dynamics of open quantum systems is formulated in a minimally extended state space. Time-local evolution equation is created in a mixed Liouville-Fock space.
  arXiv  Detail & Related papers  (2023-07-31T15:57:10Z)
• A Physics-informed Deep Learning Approach for Minimum Effort Stochastic Control of Colloidal Self-Assembly [9.791617215182598]
  The control objective is formulated in terms of steering the state PDFs from a prescribed initial probability measure towards a prescribed terminal probability measure with minimum control effort. We derive the conditions of optimality for the associated optimal control problem. The performance of the proposed solution is demonstrated via numerical simulations on a benchmark colloidal self-assembly problem.
  arXiv  Detail & Related papers  (2022-08-19T07:01:57Z)
• Physics-informed machine learning with differentiable programming for heterogeneous underground reservoir pressure management [64.17887333976593]
  Avoiding over-pressurization in subsurface reservoirs is critical for applications like CO2 sequestration and wastewater injection. Managing the pressures by controlling injection/extraction are challenging because of complex heterogeneity in the subsurface. We use differentiable programming with a full-physics model and machine learning to determine the fluid extraction rates that prevent over-pressurization.
  arXiv  Detail & Related papers  (2022-06-21T20:38:13Z)
• On optimization of coherent and incoherent controls for two-level quantum systems [77.34726150561087]
  This article considers some control problems for closed and open two-level quantum systems. The closed system's dynamics is governed by the Schr"odinger equation with coherent control. The open system's dynamics is governed by the Gorini-Kossakowski-Sudarshan-Lindblad master equation.
  arXiv  Detail & Related papers  (2022-05-05T09:08:03Z)
• Visual-tactile sensing for Real-time liquid Volume Estimation in Grasping [58.50342759993186]
  We propose a visuo-tactile model for realtime estimation of the liquid inside a deformable container. We fuse two sensory modalities, i.e., the raw visual inputs from the RGB camera and the tactile cues from our specific tactile sensor. The robotic system is well controlled and adjusted based on the estimation model in real time.
  arXiv  Detail & Related papers  (2022-02-23T13:38:31Z)
• Online Preconditioning of Experimental Inkjet Hardware by Bayesian Optimization in Loop [62.997667081978825]
  We develop a computer vision-driven Bayesian optimization framework for optimizing the deposited droplet structures from an inkjet printer. We demonstrate convergence on optimum inkjet hardware conditions in 10 minutes using our framework.
  arXiv  Detail & Related papers  (2021-05-06T17:46:16Z)
• Multi-fidelity Generative Deep Learning Turbulent Flows [0.0]
  In computational fluid dynamics, there is an inevitable trade off between accuracy and computational cost. In this work, a novel multi-fidelity deep generative model is introduced for the surrogate modeling of high-fidelity turbulent flow fields. The resulting surrogate is able to generate physically accurate turbulent realizations at a computational cost magnitudes lower than that of a high-fidelity simulation.
  arXiv  Detail & Related papers  (2020-06-08T16:37:48Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.