Description

The production of materials, components and final products can be energy- and resource-intensive and lead to significant amounts of waste. Digital tools can optimize processes by preventing waste and emissions and reducing energy and resource consumption, both during production and the use-phase. Digital twin, a digital replica of a physical entity, provides both the elements and the dynamics of how an Internet of things device operates and lives throughout its life cycle. It is the idea to set a digital twin already at design phase and use it for assisting towards more sustainable/circular products over its full life span. 

Also during use phase, the product is still connected with the digital twin. So that real life data produced by the sensors are processed. For the company, it is essential to keep track of the usage-history and performance of the leased items, or performance of some essential components, for a few reasons:

- Correct misuse: misuse can result in early defects and increased costs for the leasing company. Examples of misuse are putting too much clothes in a washing machine or using too much detergent;
- Anticipated replacements: some components need to be replaced once they are used a number of times in order to avoid defects of these components, and possibly collateral damage to other components. E.g. replace a washing machine’s suspension after YY washing rounds.
- In case of an unexpected defect, data-based decisions can best determine whether it is worthwhile to repair the leased items, or instead replace them.
Real-time, and on-distance, monitoring of the usage, and the performance of the items (components) can help to determine the optimal timing for the replacement of essential components. Machine learning algorithms can provide economic gains for the leasing companies in case they can further optimize the process of anticipated replacements, and determine the correct use pattern for the leased items. In the end, this must increase the lifetime of the leased items. In case of defects, the monitoring of the usage history, and track record of potential other defects, can assist in the complex repair or replace decisions to be made. Also in this case, the goal is to extend the items’ lifetime keeping in mind the profitability of the leasing companies. 

This operation model can only function optimally in a service-oriented business models such as product service systems. In private lease, the leasing company (which potentially, but not necessarily, is also the producer of the appliance/vehicle) remains owner of the appliance.
Expectations:
In close collaboration with the leasing company and the partners, the post doc will:

- Develop a digital twin for a product at design phase
- Identify what information needs to be monitored during the use phase in order to harness data at the source of data
- Develop AI methods for detecting misuse or automotive and predictive maintenance
- Translate information monitoring into useful advice for technicians in the field and towards service-oriented business models, including potential end-of-life decisions (e.g. repair a broken device or dispose, dismantle and recover materials and components)
- Derive learning and compare with case 2 outcomes, for example by means of a twin network to create a valuable ecosystem.
As such, the post doc aims to contribute to the further digitization of the design of products and circular decision making concerning the future destination of products. 


With this call, we invite researchers to submit their resumé (including track-record) and a one-page project description, that will be the basis for selecting candidates with whom we will collaborate for developing competitive MSCA-IF proposals. 
 

• Deadline application to VITO
Interested candidates should submit their resume (incl. track record) and a one-page note describing the project for which a Marie Curie grant will be applied, before Friday 17 April 2020 17h Brussels time.


• Deadline MSCA-IF 2020
Wednesday 9 September 2020 17h Brussels time.
 

Qualification

We invite applicants to propose a more detailed and focused research approach within the scope of this MSCA-IF Fellowship as a part of their application. We are primarily looking for experienced researchers who wish to use this period as an opportunity to further develop their research, and to develop longer-term research collaborations with VITO and other institutions conducting research in the field.
The candidates as in principle must be eligible for a Marie Curie Individual Fellowship – please refer to the conditions set-out in the H2020 MSCA Work Programme.

The following assets will be advantageous:

  • An excellent track record in research, necessary for being able to develop a competitive Marie Curie Fellowship application;
  • An open and cooperation-oriented nature, but with strong abilities for independent research work;
  • Thorough knowledge of data science techniques in areas such as machine learning, reinforcement learning and statistical methods such as regression and clustering analysis;
  • Hands-on experience with R or Python and flexible in working with other data science setups, especially with a focus on connectiveness;
  • Believe that data science is an important asset for a more sustainable and circular economy;
  • Communicate smoothly and able to present ideas to persons with different backgrounds;
  • highly proficient in spoken and written English.
Offer
Initially, we offer assistance in developing competitive Marie Curie Individual Fellowship proposals.

Then, to successful applicants to the Marie Curie program, we offer;

  • An exciting opportunity at VITO, the independent Flemish research organisation in the area of cleantech and sustainable development. Our goal? To accelerate the transition to a sustainable world;
  • Participation in a dynamic professional research & innovation community;
  • Flexible working conditions;
  • An inclusive and friendly work environment;
  • On-boarding assistance and other services.

 

 

Requisition

Location: 
Mol
Jobfield: 
Postdoc
ID: 
29360