smart processes for a smarter factory

The challenge

In a context where the competitive advantage of companies is increasingly linked to the ability to innovate and attract talent, Gefran launches INNOWAY, the Gefran Innovation Experience.

INNOWAY is Gefran's innovation incubator, a real experience in which the company provides budgets, resources and know-how in order to transform a brilliant idea into a specific project.

If you are born between 1991 and 1997 and you are passionate about energy saving and predictive maintenance in the world of industrial automation, you are in the right place!

The challenge is structured in 2 phases:

UPLOADING

Each group (1 to 4 members) uploads its own idea to the portal, choosing between one of the two proposed themes.
Gefran will select the ideas that will be able to access the next phase on the basis of the following parameters: innovative content, response to initial requests and skills demonstrated by the team.

ELEVATION

Gefran will provide a tutor to support each selected group. The tutoring, managed online on the platform, aims to refine ideas by providing the group with the necessary insights to bring the idea closer to a specific production and application needs.
At the end of this phase, Gefran will select up to 3 winning groups, using the same criteria as in the previous phase. The winners will be admitted to the 1st edition of INNOWAY.

INNOWAY

In this phase, supported by a corporate tutor, you will be able to access:

• A budget of 15.000 euros to cover the development costs of the project
• Gefran resources (laboratories, instruments and materials)
• Gefran know-how (consulting and support from professionals)

The objective will be to develop the project, arriving at the first tangible results (prototyping, technical laboratory tests, or market tests, etc.).

The first Gefran Innovation Experience will end with an event in which the winning group will be elected and rewarded, with the opportunity to collaborate with Gefran to get the project off the ground.

REGULATION OF THE GEFRAN CHALLENGE

To sign up for the Gefran Challenge, you must accept the Regulationand sign a confidentiality agreement. In addition, in the case of PhD students, researchers and/or assignees, it will also be necessary to sign a self-declaration document in which is expressed the commitment to promote negotiation between the University of origin and Gefran, without any obligation of result.

The documents are available below for viewing for your information. They will then be available on the platform in the registration phase, during which you will be asked to:

• Read the regulation and flag the button "I declare that I have read the rules and accept the terms and conditions contained therein"
• Download, fill in and upload the signed confidentiality agreement
• For PhD students, researchers and/or assignees only, download, fill in and upload the signed self-declaration

Finally, for the winning groups of the Elevation phase, to access the Innoway program will be proposed the signing of a research and development contract with Gefran. An example of such a contract is included at the end of the Regulations document in two different versions: one for students and graduates (Annex 1); one for PhD students, researchers and assignees (Annex 2).

For further information or clarification, please send an email to innoway@gefran.com

• GEFRAN CHALLENGE REGULATION
• CONFIDENTIALITY AGREEMENT
• DECLARATION OF COMMITMENT

SMART PROCESS FOR A SMART FACTORY

Energy Saving

Research of innovative technical solutions capable of optimizing electricity consumption in industrial plants, through hardware solutions or dedicated algorithms.
The solution must be able to provide, in real time, an estimate of the amount of energy saved.

KEYWORDS: power controllers, regulation, real time energy saving, neural networks, machine learning, hardware optimization

Predictive Maintenance

Creation of a widespread network composed of sensors operating on separate machines but with the same process.
This network must allow the collection and analysis of data that the machinery can provide, with a view to predictive maintenance of the most sensitive elements of the sensor itself.

KEYWORDS: pressure sensors, sensor membrane, predictive maintenance, neural networks, machine learning, IoT, cloud computing/edge computing