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

The Organic Rankine Cycle (ORC) is widely used in industrial waste heatrecovery due to its simple structure and easy maintenance. However, in thecontext of smart manufacturing in the process industry, traditional model-basedoptimization control methods are unable to adapt to the varying operatingconditions of the ORC system or sudden changes in operating modes. Deepreinforcement learning (DRL) has significant advantages in situations withuncertainty as it directly achieves control objectives by interacting with theenvironment without requiring an explicit model of the controlled plant.Nevertheless, direct application of DRL to physical ORC systems presentsunacceptable safety risks, and its generalization performance under model-plantmismatch is insufficient to support ORC control requirements. Therefore, thispaper proposes a Sim2Real transfer learning-based DRL control method for ORCsuperheat control, which aims to provide a new simple, feasible, anduser-friendly solution for energy system optimization control. Experimentalresults show that the proposed method greatly improves the training speed ofDRL in ORC control problems and solves the generalization performance issue ofthe agent under multiple operating conditions through Sim2Real transfer.

Surrogate Empowered Sim2Real Transfer of Deep Reinforcement Learning for ORC Superheat Control