This session will provide an introduction to the capabilities of STOCHOS Flow and demonstrate practical applications in the chemical industry. Topics include formulation development, process optimization, and the analysis of cause-and-effect relationships to better understand and improve complex systems and product performance.

Within the project, PI Probaligence GmbH developed the core AI technology for analyzing sensor-based data to enable early detection of critical pressure and stress patterns. The goal is to reduce the risk of amputations through more precise and continuous monitoring of high-risk patients.

Beyond developing the AI models, PI Probaligence was responsible for the full system integration, including implementation within a smartwatch for mobile data acquisition, an iPad application for nursing staff, and the secure server infrastructure for data processing.

Project partners included Niederrhein University of Applied Sciences, CID GmbH, and PI Probaligence GmbH. While the university and CID contributed clinical and medical technology expertise, PI Probaligence led the AI development, system integration, and technical architecture.

The award highlights the potential of probabilistic AI methods in safety-critical medical applications and demonstrates how advanced AI technology can address real societal healthcare challenges.

Build with an AI agent—not just chat with one.

Stochos Flow lets you describe what you want to build, and the agent does the work alongside you. It creates nodes, wires workflows, configures parameters, and helps debug directly on the canvas—so you can build AI models, run optimizations, generate data, connect simulation tools, and write custom scripts without friction.

Everything runs 100% locally. No cloud, no data leakage, no IP risk—designed for real engineering environments.

Stochos Flow is powered by RAG-based engineering knowledge, allowing you to teach the agent your internal standards, proprietary methods, solver APIs, and workflow documentation. Your knowledge becomes instantly accessible and actionable.

Built to extend—not constrain—Stochos Flow supports custom Python solver nodes, tool integrations via MCP servers, one-click export to web apps, and workflow export as standalone, production-ready Python code. Your workflows are never locked in.

The result: less infrastructure work, fewer brittle scripts, faster iteration, and more time focused on solving real problems.

Stochos Flow is where AI meets engineering intelligence.

We are proud to announce that PI Probaligence has achieved official ANSYS Technology Partner Status as of today!

Since the beginning of our partnership with ANSYS in 2022 we implemented and continuously are developing our AI algorithms for the ANSYS engineering solutions universe.

Best-In-Class Partner Experiences

ANSYS Technology Partners develop, test, integrate and validate solutions that integrate with industry-leading ANSYS technology. These collaborations provide our shared customers with opportunities to optimize product performance and improve product development processes. ANSYS is always evaluating new technology partner types and specializations that will create a best-in-class experience for their customers.

The entire PI Probaligence Team is looking very much forward to further boost the world of simulation all over the globe with our matchless ML algorithms for engineers!

GEMÜ is using the AI-driven capabilities of Stochos to make the verification process for metallic valve bodies more efficient and consistent.

GEMÜ develops and manufactures a broad range of metallic valve bodies, each requiring strength verifications in accordance with the Pressure Equipment Directive. In the past, this involved a considerable amount of manual modeling and data preparation.

With Stochos and in partnership with CADFEM, an automated workflow has been introduced that analyses CAD geometries, identifies relevant functional surfaces, and supports model setup and subsequent evaluation. These automated steps help increase process reliability and reduce repetitive manual tasks, resulting in

• Reliable detection of pressure-loaded and functional surfaces
• Standardized and reproducible workflows
• Reduced manual modeling effort

• More time for complex engineering tasks

Stochos supports GEMÜ in implementing verification processes more efficiently and consistently. We are happy to demonstrate how similar benefits can be achieved in other engineering environments.

Link to the full article:
https://www.konstruktionspraxis.vogel.de/machine-learning-automatisiert-aufwendige-nachweisfuehrungen-a-d7b98bc923f44587abf8d8e0d2ece3c7/?pt=691480251e776

GEMÜ Homepage: https://www.gemu-group.com/

Last week, Kevin Cremanns visited Singapore together with CADFEM South East Asia. The joint customer meetings again focused on advanced applications in engineering simulation.

 We were pleased to see that several customers in South East Asia are already using or evaluating our software STOCHOS. The discussions highlighted how STOCHOS unique methods can complement classical simulation workflows and lead to more efficient, reliable engineering decisions.

Many thanks to CADFEM South East Asia and all our partners for the insightful exchanges and their continued collaboration!

#AI #Engineering #Simulation #UncertaintyQuantification #MachineLearning #STOCHOS #DigitalEngineering #CADFEM

We participated in the GDCh Coatings Conference – with a presentation and an information booth on the use of AI in automated Design of Experiments (DoE) for coatings development. In addition, a research project on “Sustainable Coatings Industry through Digital Technologies for Climate and Environmental Protection” was presented.

Our talk highlighted how Artificial Intelligence opens new pathways in coatings development. With raw material variability, stricter environmental regulations, and the urgent need for sustainable processes, innovative approaches are essential.

AI-based methodology for adaptive experimental planning:

• Unlike classical, predefined experimental design, our approach enables dynamic, data-driven steering of experiments.

• Parameters from raw materials, application, and processes are integrated into probabilistic AI models (STOCHOS).

• The AI proposes targeted, optimal experiment combinations, reduces the number of trials, and avoids inefficient or incompatible setups.

The benefits:
Significantly lower resource consumption and time investment
Facilitated transition to sustainable raw materials
Prototype validation on high-throughput and industrial-scale equipment
Presentation of our software solution for AI-driven experimental planning

A special thank you to our project partners: AOM-Systems GmbH, Mankiewicz Gebr. & Co., Füll Lab Automation GmbH, HS Niederrhein, and Fraunhofer IFAM.

PI Probaligence auf der CADFEM Konferenz 2025 in Rapperswil 
Event-Link

Im Rahmen unseres Vortrags „Empowering Digital Engineering with AI“ haben wir von PI Probaligence aktuelle Entwicklungen vorgestellt:

• Generative AI für Engineering: Automatische Erzeugung möglicher Geometrien innerhalb definierter Parameterbereiche zur Unterstützung des Konstruktionsprozesses.

• Neue grafische Benutzeroberfläche (GUI): Erstmals präsentiert, mit geplanter Markteinführung in 2–3 Monaten.

Wir danken CADFEM sowie den Teilnehmenden für den fachlichen Austausch und freuen uns auf weitere Kooperationen.

#CADFEM #CAE #GenerativeDesign #DigitalEngineering #EngineeringAI

PI Probaligence at the CADFEM Konferenz 2025 in Rapperswil 
Event link

Within our presentation “Empowering Digital Engineering with AI”, we at PI Probaligence introduced our latest developments:

• Generative AI for Engineering: Automated generation of possible geometries within defined parameter ranges to support the design process.

• New graphical user interface (GUI): Presented for the first time, with a market launch planned in 2–3 months.

We thank CADFEM and all participants for the valuable technical exchange and look forward to further collaborations.

#CADFEM2025 #CAE #GenerativeDesign #DigitalEngineering #EngineeringAI