Artificial intelligence for stable processes in industry
Bottle jams on the conveyor belt or overheated machines – such interruptions to production cost a lot of time and money. ETH spin-off Cerrion detects and analyses problems in the process automatically and in real time.
The example of a production facility for glass bottles shows how complex the process is and why the processes have to be perfectly coordinated: A production line transports thousands of bottles per minute. But suddenly, all goes wrong – the bottles jam. What happened? Currently, specialists are needed to monitor and analyse the processes to find out where and when errors occur in the process. If process deviations are not detected in time, they can lead to longer downtimes, machine damage, delays, employee accidents, and, consequently, high unplanned costs.
Our AI-based software can be integrated into any commercially available camera and provides reliable process insights in real-time.Karim Saleh, CEO and co-founder of Cerrion
Video-based process insights are generated in real time during operation
Cerrion's solution can be used in any manufacturing process where the process is visible. What makes it special is the combination of video technology, which can be integrated directly into existing processes, and state-of-the-art AI. This way it is possible to monitor new processes immediately without having to first import a lot of data into the system, as is often the case with conventional solutions. The AI-based computer vision technology learns what a process looks like in normal operation and can detect deviations in real time.
The AI-based software can be connected to a commercially available camera and instantly provides reliable process insights. The system helps to detect problems in the process at an early stage, i.e. before they arise and lead to failures or losses. The technology can be used for a wide range of applications. Cerrion has already gained experience in glass bottle production, plant and machine manufacturing, tool manufacturing, pharmaceutical packaging, and wood construction. The AI can detect and track problems in automated processes such as jams on the production line in real time. It can also analyse whether the assigned time for the manual assembly of a component is in line with planning or whether the defined process needs to be optimised. Hazards for employees and equipment can also be detected and eliminated at an early stage. This leads to more safety in operations.
The relevant events defined by the customer are aggregated in a central dashboard, which provides an instant overview of the processes. Each relevant event is detected in real time and provides information on when, where and for how long the event took place. In addition, an anonymised video clip of the event is provided so that the customer can carry out a root cause analysis within minutes.
Our self-learning AI automatically optimises for each process and requires minimal input from the person operating the system.Michael Gygli, CTO and co-founder of Cerrion
Cerrion works very closely with its customers and releases new product features every fortnight. Their next big feature is a so-called "no-code workflow", an application that allows users without programming experience to set up and use the solution within a few hours. The self-learning AI automatically optimises each process and requires minimal input from the person operating the system. Thus, Cerrion is developing the first agnostic (requiring no prior knowledge) video-based AI.
First paying customers are already using the plug-and-play solution
Cerrion was founded in December 2021 and already has paying customers in various countries who are successfully using the technology. Customers can use the software immediately and operate it themselves.
The team of powerful specialists from ETH would like to expand
The three founders gained their expertise at ETH Zurich and have previously been entrepreneurs in various fields. Karim Saleh has advised other start-ups in his position at Unicorn Labs and made the Forbes 30 under 30 list in 2020. Nikolay Kobyshev co-founded Europe's largest hackathon, Hack Zurich, as well as AI start-ups Spectando and Assaia. Michael Gygli has gained experience as an AI specialist at Google.
Due to growing demand, the start-up is currently expanding its team and looking for more talent in the field of computer vision and engineering. Explicitly, they would like to bring more diversity into the team, as they are convinced that only a diverse team can perform at its best.
ETH spin-offs: facts and figures
Since 1996, 496 spin-offs have been founded at ETH Zurich. ETH transfer, the technology transfer office at ETH Zurich, supports recognized ETH spin-offs in the founding process and in their first years of operation.
With the help of the Pioneer Fellowship Programme, funded by the ETH Foundation, young researchers can develop innovative products and services based on their scientific work at ETH Zurich. A Pioneer Fellowship is awarded to young ETH entrepreneurial minds intending to develop a highly innovative product or service to be exploited commercially and/or for the benefit of society.
Press release ETH spin-offs January 2022: "Battling climate change and the pandemic"