SKF’s virtual technical press days took place on Oct. 7 and 8, 2020. Under the title of “Bearings 2.0: What the Future Holds,” the event featured expert speakers who addressed how SKF’s innovations in bearing and rotating machinery will change the way end-users and manufacturers operate.
Talks included keynote presentations on topics such as the future role of bearings in industrial applications, how digitalization is driving development around the rotating shaft and how these developments enable the growth of outcome-based business models. The roles of modeling, artificial intelligence and machine learning in enabling the improvement of bearing design, performance, lifespan and predictability were explored.
Among the event’s highlights was the presentation delivered by Victoria van Camp, CTO and President of Innovation & Business Development at SKF. During a lecture titled “AI, Agility and Accessibility: Customer-Driven R&D at SKF,” van Camp focused on how usability and customer needs are changing the way SKF conducts its R&D activities. “Our business is in the midst of a massive change: from a product-selling company to a function provider. We want to provide our customers with what they actually need. That is not lots of bearings, it is machines that run and run,” she said.
Van Camp explained that this shift in direction reflects wider changes in society, with industries from music retail to mobility all moving to models where customers pay only for the services they consume. The new strategy is encouraging every part of the company to rethink the way it works and that includes SKF’s core R&D functions, she elaborated. Becoming a service provider rather than a product manufacturer implies a completely different way of approaching R&D. “If you are responsible for the performance of a customer’s machine over its lifetime, you need a much deeper understanding of how your products are being used in that machine. Are they continually exposed to hot, corrosive chemicals? Are they being hit with a hammer during installation?” she offered.
Guillermo Morales-Espejel, Principal Scientist at SKF, explained that engineers had achieved a breakthrough in information concerning hybrid bearings. This type of bearings use ceramic silicon nitride rolling elements and steel rings. They have been the preferred choice for high-speed, high-precision equipment, such as machine tool spindles, and are currently finding many new applications, from electric vehicle powertrains to industrial pumps and compressors.
Engineers know from experience that hybrid bearings can perform extremely well in these applications, often lasting many times longer than their conventional all-steel counterparts. Yet, until recently, the design calculations used to estimate the operating life of bearings often gave the opposite result, Morales-Espejel said.
Morales-Espejel explained that faulty models for calculating the rating life of a bearing are the reason for that. As a result, SKF set out to do better. To create a new bearing life model they needed three things. “The first was a model of sub-surface fatigue within the material, which we already had. The second was a model for failure at the surface. The third was data from endurance tests that we could use to calibrate and validate our model.”
The effort was finally completed a year ago. The new model shows if a hybrid solution would offer a longer life on certain applications and will quantify the difference between a steel bearing and a hybrid. To show how big the difference can be, Morales-Espejel and his colleagues have run calculations for a number of representative real-world applications. In the case of a pump bearing running with oil-bath lubrication and diluted oil resulting in poor lubrication, the rating life of a hybrid bearing was eight times longer than a steel equivalent.
Eitan Vesely, SKF AI Offering Manager, delivered a presentation called “Machine Learning-Based Predictive Maintenance Changes the Game.” He explained how Automated Machine Learning (AutoML) is enabling a completely new way for machine and factory operators to approach performance and machine output. At the center of this development is the combined expertise resulting from SKF and an Israeli start-up which was acquired by the Swedish bearing manufacturer in 2019, Vesely said.
AutoML applies pre-trained algorithms to real-time process data to identify anomalous patterns and warn technicians of evolving asset failure. AI is responsible for choosing which machine learning models are applied and maintaining these models over time while they run in production. This capability enables quicker modeling and higher accuracy, Vesely pointed out. “What is really exciting about this development is that we are able to combine asset vibration data with temperature and other types of process data generated by the asset. Essentially, 2+2=5 in terms of extrapolating value from the combined data set and what it means in terms of actionable insights. For customers, this means earlier failure alerts and insights that provide maintenance technicians with the time and information they need to plan maintenance and establish a diagnosis before a machine breaks down,” he elaborated.