We are experiencing an explosion of predictive maintenance offerings where prognostics is often cited as integral to the solution.  Prognosis is the ability to predict when an asset is likely to fail with a measure of certainty.  Failure is losing the ability to function.  This period of time to functional failure is generally termed ‘remaining useful life’ (RUL).  Prognosis should ideally include what the consequences are when functions are lost, expressed in terms that are meaningful to any asset stakeholder who needs to take timely remedial actions.  An important consideration of consequences of failure will  include what the likely recovery time and effort will be to restore the asset functions.  The scope of work necessary will depend on when (timing) assets are decommissioned for recovery during the failure cycle.  As condition deteriorates over time, so recovery work may increase. Most predictive maintenance offerings do not deliver consequences and recovery information, and many offerings only have a one-dimensional approach to delivering estimates for RUL.

Therefore, a holistic and comprehensive approach to prognostics is necessary for users to either specify or evaluate predictive maintenance systems.

A predictive maintenance system delivers two basic levers that may be exercised to deliver business value:

  1. the depth of isolating fault conditions, so that the right components are identified that require remedial action.  This enables the right spare parts to be provided and the appropriate maintenance to be planned.  The diagnostic function of a predictive maintenance solution  delivers this lever
  2. The ability to deliver sufficient remaining useful life, to enable the most effective and efficient recovery possible that maintains safety, and minimises operational impact.  The prognostic function of a predictive maintenance solution delivers this lever

Successful diagnostics will be discussed in a separate post.

Charlie Dibsdale is co-founder and technical director at Ox Mountain, a start-up working to deliver predictive analytics to automate in-service support and maintenance to organizations that rely on complex and critical machinery assets. A seasoned electrical engineer with over 35 years in operating and maintaining submarines, nuclear propulsion plant, power plants and other assets, he was Chief Engineer and Global Head of Equipment Health Management at Rolls Royce and played a key role in developing that company’s renowned predictive maintenance capability that is important in it’s TotalCare (TM) service offerings. Charlie holds a BSc in Computer Science and an MSc in Information Systems from Open University (UK).

 

If you are a Service professional (manager, practitioner, consultant or academic) in an industrial setting join our group Service in Industry on Linkedin