Monitoring & metering


begun before the outbreak of the COVID-19 pandemic, but has gathered significant momentum since. The bearing specialist is changing from a company that sells products to one that, in effect, sells performance through its REP contracts. Through these, SKF’s customers pay a monthly fee and, should their KPIs be met, bonus payments. Any risks associated with the implementation of digital technologies are therefore shared, but then so too are the rewards.


ArtificiAl intelligence


The new strategy is encouraging every part of SKF to rethink the way it works, including its core research and development functions. In particular, it is striving to making better use of the huge quantities of data generated by modern machinery. As we have seen, bearings can be equipped with sensors, and connected machines and digital management tools can generate detailed records of the way equipment is used and maintained, but using data from potentially millions of bearings to create machines that run and run remains a significant challenge—one that can can only be met with artificial intelligence (AI). With that in mind, the SKF AI group contacted Presenso, a start-up based in Israel, which was working on the application of automated machine-learning technologies for improving industrial reliability. The match turned out so well that SKF acquired the company in October 2019. SKF industrial customers are already


benefitting directly from Presenso technology,


which can automatically sift through the data generated by a factory and can flag-up issues and improvement opportunities. The real power of this AI-driven approach, however, will come from its application to the aggregated data SKF collects from thousands of customer sites. By analysing big populations of bearings in the field, AI technology can identify the specific issues associated with higher rates of failure, helping it to fine tune its research, and making customers’ machines perform better.


A BrAVe Venture


SKF is also building a testing facility at its Research and Technology Development (RTD) centre in Houten, The Netherlands, where it hopes it will be able to gather data that will support its development of AI and machine- learning techniques that can be used to predict or improve the performance of its bearings. When attempting to predict how, and perhaps more importantly when, a bearing will fail, a huge number of variables must be considered, including the application for which it will be used, the environment in which it will operate, the lubricants used and the loads to which it will be subjected, to name but a few. As such, when developing new bearings, verifying their performance and for how long they will last can be a slow, expensive and complex process. BRAVE will be used to increase SKF’s


knowledge of the mechanisms that cause bearings to fail. It will feature a number of rigs specifically designed and tailored to meet SKF


specifications that will be used by researchers to develop and experimentally verify bearing failure models. The functions of these rigs will be categorised as ‘contaminate’, ‘initiate’ and ‘propagate’, and they will be often used in sequence. In this way, SKF researchers can screen many different variants of bearings very quickly to determine the best solution for a given application. Test procedures will be developed, controlled and monitored closely, and all of the data, regarding things such as vibration, temperature and load history will be recorded. This data can then be analysed in detail during or after the experiments.


BeAring fruit


This new approach is already bearing significant fruit, both for SKF and its partners. Big River Steel (BRS) of Osceola, Arkansas, for instance, is the newest and most technologically advanced steel mill in the USA, but it recognised early on that there were aspects of its operations – including parts inventory, condition monitoring and predictive maintenance – where specialist expertise would be of significant benefit. As such, it entered into an REP partnership with SKF, the first of its kind in the USA. The partnership is focused entirely on results—in this case, producing more steel. Through it, SKF helps BRS monitor its new equipment and devises strategies for getting the most from it. SKF engineers work hand-in-hand with those from BRS, becoming part of the team. Initially, the partners established a performance baseline for the new equipment so any problems with it could be identified early. They use the data collected through this process – and ongoing monitoring activities – to gain an understanding of why a piece of equipment might be deteriorating, and how to solve the problem with new installations. The data is also used to predict when replacement parts are likely to be needed so that other maintenance activities can be scheduled around this work—enabling any downtime to be compressed. Where unscheduled failure might necessitate five hours of downtime, planned-for failures might only require two hours. The partners are supported in this work remotely by engineers at SKF's Rotating Equipment Centres. The initial results achieved through the


partnership are highly encouraging. BRS set a first-month production record for a new steel facility in terms of the tonnes of metal that it produced and, with support from SKF, it says that it is manufacturing products that would typically take a mill 4–6 years to achieve.


DigitAl help


Overall, assets perform better with digital help, but the right digital approaches need to be applied at the right time. With programmes such as REP, SKF is helping many businesses take the next step along their digitisation journey in a manageable way.


SKF Instrumentation Monthly April 2021 www.skf.co.uk 21


Page 1  |  Page 2  |  Page 3  |  Page 4  |  Page 5  |  Page 6  |  Page 7  |  Page 8  |  Page 9  |  Page 10  |  Page 11  |  Page 12  |  Page 13  |  Page 14  |  Page 15  |  Page 16  |  Page 17  |  Page 18  |  Page 19  |  Page 20  |  Page 21  |  Page 22  |  Page 23  |  Page 24  |  Page 25  |  Page 26  |  Page 27  |  Page 28  |  Page 29  |  Page 30  |  Page 31  |  Page 32  |  Page 33  |  Page 34  |  Page 35  |  Page 36  |  Page 37  |  Page 38  |  Page 39  |  Page 40  |  Page 41  |  Page 42  |  Page 43  |  Page 44  |  Page 45  |  Page 46  |  Page 47  |  Page 48  |  Page 49  |  Page 50  |  Page 51  |  Page 52  |  Page 53  |  Page 54  |  Page 55  |  Page 56  |  Page 57  |  Page 58  |  Page 59  |  Page 60  |  Page 61  |  Page 62  |  Page 63  |  Page 64  |  Page 65  |  Page 66  |  Page 67  |  Page 68  |  Page 69  |  Page 70  |  Page 71  |  Page 72  |  Page 73  |  Page 74