ANALYSIS • NORDIC INNOVATION
Knut Ørbeck-Nilssen
DNV GL offers expert data analysis with Veracity
With today’s increased array of sensors and better ship-to-shore connectivity for the transfer of ‘big data’, increased uptake of predictive maintenance looks certain.
‘In the future, gradually more vessels will be fitted with sensors, and the amount of records that you could be receiving is in the range of billions,’ says DNV GL Maritime ceo Knut Ørbeck-Nilssen. ‘The possibilities of big data give us another set of glasses we can look through – not “why do things happen” but “what correlates with what”. This is the key ingredient – the ability to mine big data, but also the domain knowledge to find some relevance in that data.’
In a particular case on a drillship, on examining ‘one year of operational data’ DNV GL was able to make predictions about a piece of equipment likely to fail in the next three months. ‘It had a quite regular increase in temperature,’ says Ørbeck-Nilssen. ‘This usually indicates high friction for a certain time. The challenge was that this had very regular peaks. Through the combination of data scientists and domain knowledge, we are able to trace that back to a specific crew member on a certain shift.’
Visit:
seatrade-maritime.com
‘Using these techniques we can identify abnormalities before they happen,’ he adds, ‘but you have to do all the nitty-gritty work to enable that – make sure the data is good quality and that security of the data is maintained.’
DNV GL is in the process of launching a new platform, Veracity, for just this purpose. The system, based on Microsoft’s ultra-secure Azure software, is designed to streamline the process of collecting and leveraging big data.
While full details have yet to be released as the project is still in the research stage, the software is geared toward providing a service by which owners can upload, store and ‘combine their datasets’, Ørbeck- Nilssen indicates.
‘This platform in itself is not all that unique – there are others out there providing similar capabilities,’ he admits. ‘What is unique is the cross- industry knowledge platform DNV GL can bring which will serve these users.’
The Veracity platform will also be geared towards bringing teams of big data specialists to bear on the collected material, allowing much greater insights. ‘We have the
capability, if requested, to do a lot of data mining for owners, identify which datasets make sense to combine. To be able to do that you need data scientists, and the other is domain knowledge – you need to be able to know what’s relevant,’ says Ørbeck-Nilssen.
‘We will give owners the possibility to mine their own datasets and combine them with another – this is the area of the greatest potential,’ he continues. ‘For example, shipowners could combine their findings with oil majors, particularly in the Caspian domain, and identify cost efficiencies there.’
DNV GL is keen to emphasise that who owners decide to share their data with will be up to them, and even sharing it with – or being classed by – DNV GL will not be compulsory. An example might be sharing data with an engine manufacturer in order to optimise fuel consumption.’
Of course, DNV GL has extensive experience of analysing data – and also offers its own ECO Insight suite of fleet performance software (pictured) – and therefore can, if requested, carry out the data mining for owners and identify which datasets it make sense to combine. But ‘If you are not sure you can trust whether your data is safe this will not fly,’ DNV GL’s Maritime ceo concludes.
By Charlie Bartlett Seatrade Maritime Review • Quarterly Issue 2 • June 2017 35
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 |
Page 75 |
Page 76 |
Page 77 |
Page 78 |
Page 79 |
Page 80 |
Page 81 |
Page 82 |
Page 83 |
Page 84 |
Page 85 |
Page 86 |
Page 87 |
Page 88 |
Page 89 |
Page 90 |
Page 91 |
Page 92 |
Page 93 |
Page 94 |
Page 95 |
Page 96 |
Page 97 |
Page 98 |
Page 99 |
Page 100
