Stratio Concludes a Research Project on AI Models for Predictive Maintenance with the Support of ELISE

Reading Time: 2 minutes

 

 

We’re delighted to share that our research funded by the ELISE project has started to show results. We have deployed the first vehicle fault prediction model prototype that resulted from this collaboration!

About our project funded by ELISE

 

ELISE, the European Network of AI Excellence Centres, has been promoting our project to research a more efficient way of developing models used to predict upcoming vehicle failures. Specifically, the project tested a novel deep learning methodology on a vehicle’s cooling system, with the ambition to generalize the concept to other components.

This allows our research team to scale up the model development process, building a strong competitive advantage in this field and allowing us to deliver more value to our customers, faster. A model developed with this approach was deployed and further research will be done to optimize performance.

“Limiting the scope to only one vehicle subsystem increased our chances of getting results within the time frame of the project. Targeting a component that exists in all vehicles and has a relatively high likelihood of failure, such as the cooling system, guaranteed that we had plenty of examples to validate the strategy.” – Paulo Bajouco, CFO at Stratio. 

This project provides the Artificial Intelligence (AI) community with a good example of how machine learning techniques can be applied to solve today’s real-world problems. It identifies where existing methods are lacking and allows the research community to address the issues that prevent widespread adoption. 

 

What’s next?

 

Building on results from the ELISE project, we will continue to research and develop improved ways of solving our customers’ problems. ELISE provided the initial funding that allowed Stratio to explore a radically new approach, which our R&D team will continue to improve, both in-house and through future EU-funded research projects.

As AI and Machine Learning (ML) are at the core of our product offering, we intend to continue pursuing research and development and state-of-the-art advancements in this field, leveraging both public funding and private funding. Paulo explained: “Within the next 3-4 years we intend to have in production the results of R&D that enable us to develop robust ML models that are not so dependent on the existence of labels.”

Stratio will present the results of this project at the next European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases, which will be held in Grenoble, France, from the 19th to the 23rd of September 2022. This is Europe’s top machine learning and data mining conference, with over 20 years of successful events and conferences across the continent.

You can learn more about the project in the video below.

 

More about the ELISE 1st Open call and awarded companies is available here.