Deep reinforcement learning for heat exchanger shape optimization

Summary of the technology

oundary conditions are extremely important for simulating/optimizing fluid flow and heat transfer in heat exchanger designs. Improving performance of heat exchangers requires greater freedom in the design process, which is computationally demanding and imposes manufacturing challenges.

Conventional optimization methods, that keep the heat exchanger boundaries distinguishable, are based on pixel or voxel optimization which require high CPU time due to the complexity of multidimensionality. Additionally, as the conventional methods/software packages start from limited pre-defined heat sink fin geometries, the final design/output may face manufacturing challenges and/or optimality issues (i.e. may be a local optimum but not an absolute optimum).

University of Waterloo
University of Waterloo

Details of the Technology Offer

Researchers at the University of Waterloo have invented a fast and non-restrictive method for optimizing the shape of heat exchanger fins that reduces the dimension of the optimization problem without sacrificing manufacturability or freedom to change the heat exchanger design.

The methodology uniquely utilizes Deep Reinforcement Learning (Deep RL) and Boundary Representation (BREP) algorithms and automatically designs/simulates heat exchanger fins and layouts based on the “physics” of each use-case. The designer is only required to input/define the “design space”, i.e. the boundaries of heat exchanger’s solid components, and thermodynamic parameters, i.e. temperatures and heat flux. The system then optimizes the shape of heat exchanger fins for maximum heat transfer and minimum fluid pressure drop.

Advantages

  • Easy to use (convenient) and fast (is not computation intensive).
  • Provides customized optimal designs (is not a “one size fits all”).
  • 30% improved heat transfer and 60% reduction in pressure drop
  • Manufacturable designs
  • Seamless interaction with CAD software

Potential applications

The invention can potentially be used for designing/simulating any heat exchanger system, including for:

  • Consumer electronics
  • Data centers
  • HVAC systems
  • Electric Vehicles

Patent status

Patent issued

Stage of development

Lab prototype and ongoing research

Related Keywords

  • Data Protection, Storage Technology, Cryptography, Data Security
  • Construction Technology
  • Composite materials
  • Hybrid and Electric Vehicles
  • Manufacturing

About University of Waterloo

The University of Waterloo, renowned for its innovative spirit and co-op education model, excels in cutting-edge research across diverse fields, including advanced manufacturing, artificial intelligence, sustainability, and health technologies.

University of Waterloo

Never miss an update from University of Waterloo

Create your free account to connect with University of Waterloo and thousands of other innovative organizations and professionals worldwide

University of Waterloo

Send a request for information
to University of Waterloo

About Technology Offers

Technology Offers on Innoget are directly posted
and managed by its members as well as evaluation of requests for information. Innoget is the trusted open innovation and science network aimed at directly connect industry needs with professionals online.

Help

Need help requesting additional information or have questions regarding this Technology Offer?
Contact Innoget support