Imagine if every machine in a factory had its own tiny brain that learned how it was being used without sending private data to a central server. Instead of one giant brain in the cloud trying to understand every machine, these tiny brains share their 'lessons' to create a master guide for everyone. It's like a group of students studying separately but sharing their best notes to help the whole class improve.
OEMs cannot improve their products because operational data is confidential or too large to send to the cloud. This prevents the use of AI for predictive maintenance in real-world industrial settings.
The Synthesis system, a platform for managing machine-learning models on distributed devices that uses federated learning to keep data at the edge.
If you are a vehicle component OEM dealing with restricted access to customer operational data — this project developed Synthesis that enables per-device maintenance and optimization without transferring raw data. This allows you to improve product reliability while respecting client confidentiality.
If you are a thermal energy provider dealing with high downtime in distributed heating systems — this project developed a system that automatically detects under-performing devices at the edge. This leads to reduced downtime and more informed operational decision-making.
If you are a smart sensor manufacturer dealing with the high cost of streaming all data to the cloud — this project developed Edge Intelligence that conducts learning on sensor-sized devices. This enables a transition from simple connected devices to truly smart units.
Based on available project data, specific pricing or cost structures for the Synthesis product are not disclosed.
Yes, the system is designed with a scalable interface capable of handling thousands of models in real time across diverse deployments.
Based on available project data, the technology is developed by Ekkono Solutions AB, but specific licensing terms are not provided.
The system integrates directly on distributed, sensor-sized devices, allowing learning to happen at the edge rather than requiring a cloud-only setup.
The project period runs from 2023-05-01 to 2025-12-31, indicating the development and validation phase is currently active.
The project is led by a single Swedish SME, Ekkono Solutions AB, with a 100% industry ratio. This lean structure suggests a highly focused commercial drive, leveraging 7 years of prior research to move directly into industrial application without academic overhead.
Contact EKKONO SOLUTIONS AB in Sweden
Contact us to explore licensing or partnership opportunities with Ekkono Solutions.
