New structure, new logo, new concept: the expert group “Machine Learning Clinic” is a unique pool of expert knowledge. Our last meeting aimed to connect experts willing to share their knowledge with companies in need of expertise to push AI-projects forward. Despite the hype around AI and deep learning of the last years, only a few deployed solutions are running in industry. Why is this? What are the missing bricks? One of the missions of the ML-Clinic is to overcome this gap between lab and real-world applications.

During registration we identified needs and experts on the following hot topics:

• Data Management
• Vision Inspection
• Cloud Integration
• Hardware / Edge-Processing

During a 90min virtual meeting we connected people, exchanged experience, and brainstormed about new ideas. With the new open-innovation initiative www.databooster.ch and the support from Innosuisse there are many possibilities to support companies on their ML-journey.

In a familiar round we discussed about real cases from Roche, Sulzer, SBB and others. One common issue is data quality, availability and working with rare scenarios. How to deal with missing, wrong or corrupted data. How to train robust neural networks based on such datasets. There is no easy solution but there are more and more ideas how to deal with these common industrial issues.

Beside the deep technology discussions another highlight was the “non-virtual apéro package” which all participants received before the event. Even though we only communicated through Bytes over a glass fibre everyone had a real chilled beer and some nuts in their hands – what beer would be better to stimulate the real neurons than the AI beer: DEEPER

Overall a successful event and we hope you tune in for the next get together of the ML-Clinic!

On February 10, 2021, NTN Innovationbooster databooster was officially kicked-off. The kick-off brought 34 participants to the online platform.

Jürgen Laubersheimer from Innosuisse started by presenting the NTN Innovation Booster program. The NTN Innovation Boosters foster a culture of open innovation, and the activities are open to all interested Swiss actors. They promote the transfer of knowledge between research, business and society and foster cooperation with partners along the entire value chain of a theme. In doing so, they create sustainable competitive advantages for Swiss SMEs in particular.

Then Gundula Heinatz presented the Databooster and the opportunities it brings for data-based value creation in Switzerland. The databooster is a community with an open innovation culture, in which key players around data-based value creation work together to develop innovation ideas and explore new business areas and approaches. In doing so, they give Swiss companies a decisive competitive advantage and create important added value for the Swiss economy and society. She also outlined the innovation process with its five phases: Scouting, Call, Shaping, Reshaping, Deep Dive.

The presentations were followed by informal discussion and networking on the online platform “Wonder”.

Thank you to everyone who took part in the event!

On February 4, 2021, the expert group Smart Services got together online for another successful event in the series “Service Lunch”. Dr. Nikola Pascher from Kistler Instrumente AG presented the the Kistler Innovation Lab as a powerful Digitization Booster. The talk was accompanied by lively discussions among the more than 50 participants. Please find a summary of the talk here:

Kistler is the global leader for providing modular solutions in dynamic measurement technology for pressure, force, torque and acceleration measurements. The company looks back on a continuously growing business, selling hardware and system solutions in various markets. Headquartered in Winterthur, Switzerland, and with various locations worldwide, Kistler’s next step is a digital transformation to maintain steady growth within the digital age. This involves the creation of the Kistler Innovation Lab as a powerful digitization booster.

The Innovation Lab follows the general vision “Turning data into value”. This means, that we build on the vast amounts of data created with Kistler’s sensor technology and create value by using digital methods, rooted in data science, mathematics and signal processing. Digital initiatives are pursued in a protected framework at a higher speed than possible in the general corporate context. To accomplish this, the Innovation Lab stands on three pillars: With the co-creation platform, we connect different fields of expertise, share knowledge and data and provide digital know-how. The digital technology incubator is a professional framework for quick experiments and ideas with the ultimate goal to pursue proof of concept projects for digital services and solutions based on Kistler sensor data. With the digital training center, we want to empower the Kistler team and our partners to identify digital business opportunities.

In the first part of this talk, we report on the general digital transformation mechanism at Kistler with a focus on the ramp-up of the Innovation Lab within the corporate context. Despite the challenges, which are imposed by the Covid-19 pandemic, the Innovation Lab turned out to be a powerful tool, delivering first proof of Kistler’s data-based capabilities and strengthening the credibility towards our team, customers and partners.

In the second part of the talk, we focus on technical aspects of data-based services and solutions. All initiatives build on a powerful and scalable technology stack, which allows the quick set-up and deployment of cloud-based APIs. We report on first projects within the co-creation platform and the digital technology incubator. These projects aim at the fast creation of data-based services and solutions. In a co-creation project with our in-house sensor production, we aimed at optimizing a metal machining process inside a turning lathe. Together with the Kistler-internal machine shop, we made an important step towards a predictive maintenance and quality forecasting service. In a second project, we analyzed data from our weigh in motion (WIM) systems and realized, that roughly 30% of all trucks are driving empty. With the help of a machine learning model, we can forecast the flows of empty and full trucks with high accuracy.