YOUR QUESTIONS ANSWERED
In this day and age, there is a wealth of information at our fingertips. Despite this wealth of knowledge, sometimes only 40 years’ of combined experience can answer a specific question. Below you can find a full list of FAQs from our time in the industry.
There are a number of key points here:
1) Senseye’s sweet spot is scale. It is optimised to automatically monitor hundreds or thousands of machines. And it will do this with minimal deployment effort and zero customisation. Actionable information is available from Day 14.
2) Senseye is the only product to offer prognostics at scale. Prognostics is the engineering discipline of providing the Remaining Useful Life (RUL) of a machine – i.e. an accurate forecast of when a machine will fail. No other product does this automatically – competitors require the development of customer and machine specific algorithms, significantly increasing cost and ROI and requiring constant modification as new machines are added or operating conditions change.
3) Senseye works out of the box. It’s a product not a platform, which means it doesn’t need to be deployed with a team of data scientists or consultants. This means there is no upfront cost and the ROI is usually proven within weeks.
4) Senseye has deep domain experience. It has been developed with industry know-how; we’re not just a software company. In contrast, analytics platforms are by definition broad and therefore lack the domain pedigree to really address complex problems.
Senseye has had over €8m of development invested into it and has been validated by some of the world’s largest organisations. For example, since 2016 a major automotive OEM has deployed Senseye across four production facilities across the world and proven it with over 2,000 machines. This makes Senseye the leading PdM product.
There are two major shortcomings with this approach.
1) It doesn’t scale. You cannot do manual diagnostics for more than a few dozen machines. To scale, you need automation.
2) Diagnostics is only able to provide a short time horizon of failure (less than a day or two) which is insufficient time to better plan maintenance, prevent delays on spare parts orders and cannot be used to underpin predictive maintenance regimes.
Traditional systems used rigid mathematical models to predict failure, which meant they were very expensive but also fragile to operating and environmental changes. Moreover, they could not evolve and identify new and emerging faults. Senseye is based on an entirely new machine learning approach drawing on over 40 years of experience within the aerospace sector.
Typically, they are, but not Senseye, which has been designed to be affordable and easy-to-use. Senseye works from day one and requires no or minimal customisation. And we certainly won’t bother you with consultants.