English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

This research gauges the ability of deep reinforcement learning (DRL)techniques to assist the control of conjugate heat transfer systems governed bythe coupled Navier--Stokes and heat equations. It uses a novel, "degenerate"version of the proximal policy optimization (PPO) algorithm, intended forsituations where the optimal policy to be learnt by a neural network does notdepend on state, as is notably the case in optimization and open-loop controlproblems. The numerical reward fed to the neural network is computed with anin-house stabilized finite elements environment combining variationalmulti-scale (VMS) modeling of the governing equations, immerse volume method,and multi-component anisotropic mesh adaptation. Several test cases of naturaland forced convection in two and three dimensions are used as testbed fordeveloping the methodology. The approach successfully alleviates the naturalconvection induced enhancement of heat transfer in a two-dimensional,differentially heated square cavity controlled by piece-wise constantfluctuations of the sidewall temperature. It also proves capable of improvingthe homogeneity of temperature across the surface of two and three-dimensionalhot workpieces under impingement cooling. Various cases are tackled, in whichthe position of multiple cold air injectors is optimized relative to a fixedworkpiece position. The flexibility of the numerical framework makes ittractable to solve also the inverse problem, i.e., to optimize the workpieceposition relative to a fixed injector distribution. The obtained resultsshowcase the potential of the method for black-box optimization of practicallymeaningful computational fluid dynamics (CFD) conjugate heat transfer systems.

Deep reinforcement learning for the control of conjugate heat transfer with application to workpiece cooling