Michael Klingel: Network state estimation for the renewable energy transition

The energy transition is taking place - through the expansion of renewable energies and the market ramp-up of electromobility - in the distribution grid. As a result, power generation is increasingly migrating to medium and low voltage. This dynamic is accompanied by new challenges for distribution network operators: they have to deal with bidirectional power flows and enormous peak loads - and all this with huge network areas. This is only possible with innovative approaches and the inclusion of artificial intelligence!

Dr. Cyrille Waguet: AI for resilient infrastructures

Timely maintenance of railway tracks is crucial for resilience, comfort and safety in rail traffic. It increases the acceptance of rail transport and its sustainability. incontext.technology developed a smart monitor for rails which identifies and categorises anomalies on railway tracks by analysing sensor data based on daily train operations. Connected to the operator’s business processes, the resulting digital twin of the tracks keeps the maintenance teams up to date about the rail conditions and their expected evolution.

Stéphane Canu: French Strategy on artificial intelligence

French-German cooperation and its implementation modalities, in particular via calls for projects already implemented or to be implemented in the future will be presented.

Lisa Kratochwill: Artificial Intelligence – from Hype to Reality for the Energy Industry

Looking at artificial intelligence as hyped technology no longer seems to be appropriate - it has already penetrated most sectors as a key technology. Especially in the energy sector the high efficiency potential of AI has been very well received - much faster than expected. In dena’s new AI-analysis the most promising fields of application for AI in the energy industry are classified and an initial assessment is carried out to examine the opportunities and challenges.

Prof. Dr.-Ing. Gisela Lanza: Artificial Intelligence - The new production manager

The possible industrial applications of artificial intelligence (AI) are manifold. There are AI systems that perform quality inspection more reliably than humans as well as systems that support engineers in the design phase. Thus, will entire factories soon be managed by AI? Practical examples demonstrate what AI systems can already do, where they are already applied and what limits prevail. Altogether, the new role of production managers will be projected.

Dr. Hannes Sieling: AI-Enabled Price Markdowns for Groceries in Real-Time

AI allows retailers to translate business decisions at scale with a high degree of automation. As grocery retailers experience intensifying competition, they need to manage pricing processes for expiring products to balance profitability and waste. Learn how AI enables the full utilization of intraday POS data and real-time decision making to manage markdowns. Markdown pricing contributes to sustainability goals by minimising and controlling waste based on the retailer’s business strategy.

Guillaume Cazenave: Computer Vision for gains in efficiency and cost saving

There are a growing number of Computer Vision (CV) use cases for increasing efficiency and cost savings of organisations. Prior the Edge AI CV revolution, cameras were used by agents for limited visual monitoring actions. Most of the time, agents could at best see an incident at it was occurring or investigate after it happened. With the implementation of Edge AI CV, a single agent can monitor multiple sites remotely and leverage camera infrastructure and AI to prevent incidents and take proactive decisions. This result in significant improvement in business process and reduction in product loss for an increase in ROI of organisations.

Sébastien Picardat: The challenges of AI and data in agriculture

Decision tools used in precision agriculture and integrating AI are designed using useful digital agricultural data. These data come from the many connected objects in place in farms: weather sensors, drones, electronic loops, etc. By relying on reliable data, exchanged with the consent of farmers, AI can make a major contribution to the sustainability of the agricultural sector.

Dr.-Ing. Robin Hirt:

AI will open up remarkable opportunities by learning from our data. However, we need to ensure that this exact data is kept safe during the process.

Thomas Mann:

AI is the driver of progress of this century - the automation of processes, enabling opportunities for more sustainable prosperity.

Katia Hilal:

The industry desperately lacks historical failure data to train Machine Learning algorithms. Blind failure prediction means we predict equipment failures without historical failure data. Magical? No, we invented scientific methods to generate highly discriminant health indicators from industrial time series.