Prognostics, the science of being able to accurately forecast the Remaining Useful Life (RUL) of machinery is a key technique in forecasting machine failure. We believe that prognostics is one of the most important enablers of predictive maintenance yet a number of reasons have blocked it from widespread adoption:
It must be driven by condition monitoring data
Whilst condition monitoring is an effective way to monitor the current health of machinery, it does not scale. Automated condition monitoring is way to achieve scalability and uses the same data that is needed for an effective prognostics program. This data must exist somewhere (in a factory historian or IoT middleware layer) in the first place.
Learn about how we’re changing condition monitoring here.
It needs accurate degradation information
This can be captured in a number of ways but till recently, the most popular method has been to run assets to destruction and record their failure modes for incorporation into hard-coded models. Mainly for cost reasons this is obviously impractical in an industrial scenario, as such this technique has mostly been limited to the aerospace & defence industries.
At Senseye, we advocate using maintenance information to automatically build prognostics models. This maintenance information must be stored electronically in a maintenance management system or directly within the Senseye app to be of use.
To be effective, it must be automated
Like condition monitoring, prognostics driven by human calculation and interpretation cannot scale. The skills required typically involve a deep understanding of condition monitoring and data analysis techniques which usually come with quite a heavy price tag (~$40,000++). This may be fine for less than 50 assets but manual analysis quickly becomes unreasonably expensive if tied to human resources. Industries such as Aerospace & Defence can afford large numbers of human resources however it’s beyond most industrial companies to have a team of dedicated data scientists per group of assets.
Simple access to the kind of computational power needed to automate prognostics has been limited until the recent explosion of inexpensive cloud computing and the increasingly common use of machine learning techniques.
A reduction in downtime, improvement in OEE
For a hypothetical company operating at a respectable Overall Equipment Effectiveness (OEE) of 50% (85% Quality, 69% Availability, 85% Performance), an effective predictive maintenance program driven by automated condition monitoring and prognostics might expect to reduce downtime by 50% [McKinsey].
This could have an immediate effect of increasing OEE to a very respectable 61%, before taking into account the indirect improvements that will likely be seen to the Quality and Performance metrics.
Effective prognostics directly allows maintainers to improve OEE by dramatically reducing unplanned downtime; decreasing costs and improving profitability.
Free prognostics white paper
Our automated condition monitoring and prognostics software helps you to enable predictive maintenance and reduce unplanned downtime without having to be an expert data scientist. If you’d like to learn more we’ve put together a free white paper, download yours here: