Nowadays, many companies heavily invest in instrumenting and connecting their equipment and products. Large amounts of data on how assets are performing in the field are available, but are still not exploited to their full potential. Many industrial players are looking into innovative ways to exploit field data and maximize the insights that can be derived from it. For instance, identifying anomalous behaviour or rare faulty events is essential for optimizing asset operations in the field.
To inspire and encourage our EluciDATA Community Members to fully exploit usage data from their assets in the field, we are focusing this year’s EluciDATA Tech Talk on product-usage analytics. The EluciDATA Tech Talks are yearly events addressing the industrial deployment of data innovation and AI, showcasing recent success stories and realised proof-of-concepts on real-world use cases, and exchanging technological know-how and business insights with peers.
During this year’s event, you will:
- learn about the opportunities of product-usage analytics in industrial contexts;
- get inspired via real-world use cases;
- be able to discuss with peers the challenges related to industrial product-usage analytics;
- have the opportunity to get in touch and ask your questions to experts;
- network with peers.
13:00 - 13:10: Welcome & introduction
13:10 - 13:50: Inspirational industrial use cases
Leveraging machine learning to become the factory of the future - Karel Flere, Industrial IT Engineer at Duracell Batteries BV
Through the years companies have accumulated huge amounts of data. This has come to a point where it isn’t viable anymore to perform manual analysis of it. Numerous contextual factors affect the data in their own way. The challenge now lies in making sense of and learning from the data that is available, taking into account the contextual factors.Machine learning technology has matured and can help us in order to so. During this presentation machine learning and data analysis implementations within Duracell are presented.
Data analytics at Renson - From airflows to dataflows - Dr. Steven Delrue, R&D Manager Data Anlytics at Renson
Renson (company focusing on ventilation, sunprotection and outdoor solutions) has started investing in the development of connected devices for the HVAC industry in 2016. In the meantime, Renson has over ten thousand installed devices that stream live data related to indoor air quality and indoor comfort to the Renson cloud. This data is used to strengthen Renson's product leadership position in the market and prepare for product-service offerings. During the presentation, some use cases from Renson’s data analytics team will be discussed.
13:50 - 14:00: Q&A
14:00 - 14:15: In the lab vs. in the field data analytics: two paradigms that complement each other - Dr. Elena Tsiporkova, Head of EluciDATA Lab at Sirris
Data analysis is not new to industrial R&D, typically referring to statistical and physics-based modelling methods applied to experimental data collected in the lab. Recently, a gradual transition to employing also more advanced ML and AI approaches by industry is taking place. This is due mostly to more and more data being collected from the assets in the field. However, it is unknown how much of this field data finds its way back into R&D? When researchers study a specific phenomenon in the lab, they typically aim at extending their domain knowledge using dedicated and precise data generated in a controlled experimental environment. Whereas real-world data collected in the field is usually considered as an opportunity for creating additional revenue streams via the development of novel data services. At first sight, these appear to be two parallel worlds, having different goals and mindsets. In this presentation, our intention is to convince you that both approaches are very complementary and can impact and benefit from one another.
14:15 - 14:30: Break
14:30 - 15:30: Testimonials and approaches
Making the transition data-driven maintenance is far from trivial even for innovative production businesses! - Frank Matthijs, Project Lead at Van Hoecke and Kevin Van Vaerenbergh, Data Scientist at Sirris
The advantages of data-driven maintenance are well known and widely promoted by technology suppliers. However, arriving at that point is not a one-time switch, but rather a lengthy and bumpy transition process. It can take a lot of effort and requires dealing with and resolving many recurring issues independent from the type of industry, e.g., enabling and sustaining continuous data capturing, guaranteeing consistent recording, and tracing of maintenance interventions, moderating and scoping management expectations, etc. And it is also not only about technical challenges, but very often about mindset and company culture. In this presentation, Van Hoecke, a multiple time winner of the “Factory of the future” award manufacturer, will share the challenges and issues they have encountered in this process so far. The initial results of the data analysis realized in collaboration with Sirris will be also presented. The aim is to demonstrate that even very preliminary data analysis can contribute to deriving valuable insights about the machine operation and performance.
Exploiting multi-source mobility data - Geert Vanstraelen, Head of R&D at Macq and Michiel Dhont, Data Scientist at Sirris
Macq is a well-established Brussels-based family company existing for almost 100 years and counting more than 130 employees. Nowadays, Macq provides solutions around two main areas: industrial automation and smart mobility. While the former represents the historical market targeted by Macq, smart mobility has become the largest activity domain of the company in the last years and drives many of Macq's research activities. In that domain, Macq offers a wide range of products (sensor solutions for traffic monitoring, controllers for traffic light management at road intersections…), that give access to a large amount of mobility data from different sources. To expand its Macq Mobility Manager (M3) platform, which provides a traffic monitoring service to police, national authorities… Macq is now looking into further exploiting this mobility data together with Sirris and the VUB in the framework of an industrial PhD project. In this pair of talks, Macq and Sirris will present the opportunities and challenges related to analyzing data coming from various sources (e.g., data from inductive loops, FCD and ANPR data). Additionally, some results and their approach will be presented.
15:30 - 15:45: Expert Talk
From sensor data to actionable insights - Erik Laurijssen, Founder and CEO at Datylon
Airmatics from CMC is a cloud based air compressor monitoring solution that provides real-time data, analytics and insights at the push of a button. This bespoke IoTplatform connects 24/7 with air compressors world-wide and provides insights to all stakeholders involved. Sensor data is analyzed at the edge and relevant data sent to and stored in the cloud ready for real-time analytics and automated generation of actionable reports. We'll give an overview how sensor data traveling through the data pipeline is turned into insights for improving service actions, energy monitoring and overall operations.
15:45 - 16:00: Q&A
16:00 - 16:15: Concluding remarks
16:15 - 17:00: Networking (if possible)
- online via a TEAMS Connection.
Conditions & Price:
- Free for EluciDATA Community members
- Non-member companies: 150 EUR
- Participation to the event is subject to the signature of an NDA
If you are interested in becoming a member of the EluciDATA Community and/or attending this event, please contact us as firstname.lastname@example.org
If you are a Flemish SME you can also make use of the kmo-portefeuille (the kmo-portefeuille should be requested at latest 14 days after the course has taken place). (Erkenningsnr. Sirris: DV.O105154). Please note that if you do not apply in time your request will be declined.
Our general terms and conditions:
Any cancellation has to be done by e-mail (email@example.com). Cancellations made more than 3 business days before the event are free of charge. After this deadline, 50% of the participation fee will be charged (incl. VAT). In case of cancellation on the day of the event, the full amount of the registration will be due. In case of "no-show" the full amount of the registration fee will be due as well. Replacement by a colleague is always possible if notified in advance by e-mail (firstname.lastname@example.org).