Digital Oracle for Ultra-Low Temperature Freezers

Wiebke Brix Markussen

Your Contact

Contact me

Indtast venligst et validt navn
Or your phone number
Thank you for your message
Vi beklager

På grund af en teknisk fejl kan din henvendelse desværre ikke modtages i øjeblikket. Du er velkommen til at skrive en mail til Send e-mail eller ringe til +45 72 20 21 79.

Illustration af det digitale orakel

Digital Oracle for Ultra-Low Temperature Freezers

Project start August 2021. Expected completion date November 2024.

Purpose of project
The project will develop a cloud-based surveillance software model for Ultra-Low Temperature Freezers – also called a Digital Oracle – that can convert large amounts of temperature and electricity data into simple recommendations in order to save energy, avoid inappropriate use of the freezers, or detect the need for proactive maintenance.

The Digital Oracle will be developed for Ultra-Low Temperature Freezers used in i.e. pharmaceutical companies and in biobanks. A surveillance model for Ultra-Low Temperature Freezers is extremely relevant, since this kind of freezers is characterized by having a significant energy consumption and since the value of the contents of the freezer is usually very high. Thus, there are large energy savings to be achieved and a need for high security.

Project objectives
The underlying machine learning algorithms of the Digital Oracle will be researched and developed by DTU Compute and Danish Technical Institute by utilizing the learnings from a previous project on walk-in cold rooms as well as from new analyses conducted on ULT-freezers in both a controlled environment and in operation in the field. By using state of the art machine learning technology and expert know-how on refrigeration systems, the Digital Oracle will provide significant end-user value by providing increased surveillance compared to existing systems and by providing recommendations for advantageous changes in operation and maintenance.


The project is divided into the following phases:

  1. Definition of a framework for the Digital Oracle and preparation of hardware and software
  2. Performance characterization of pilot ULT-freezers
  3. Development of data-driven models
  4. Development of methods for fault detection and performance diagnosis for ULT-freezers
  5. Demonstration and application to field installations
  6. Dissemination of results.


  1. Danish Technological Institute (Project manager – Per Henrik Pedersen)
  2. DTU Compute
  3. Statens Serum Institut, Danish National Biobank
  4. Biobank of Region Zealand (Region Sjællands Biobank)
  5. Elcold Frysere Hobro
  6. Schneider Electric Denmark
  7. Novo Nordisk
  8. LH Laboratorie Service.

The project is funded by EUDP.