Intelligent Asset Maintenance

Statistically, less than 20% of compression equipment failures are a function of age or normal wear and tear.  The other 80% can be traced back to operating conditions, such as equipment operated outside of design tolerances, friction, vibration, etc. 

Condition-Based Maintenance (CBM) is a strategy used to predict upcoming equipment failure so maintenance can be proactively scheduled when it is needed – and not before.  An evidence-based concept that has been successfully applied to maintenance programs on complex systems in the manufacturing sector for years, CBM:

  • Monitors key asset and operational indicators to decide what maintenance needs to be done;
  • Prescribes maintenance procedures only when certain key indicators show signs of decreasing performance or upcoming failure.

Cycorp’s Cognitive Conditions-Based Equipment Maintenance application complements statistical/machine-learning based predictive maintenance applications with contextually- and situationally-aware human-like expert reasoning, and transparent, plain-language explanations.  A cognitive equipment maintenance application also works in areas machine-learning applications do not, such as when data is untrusted, inadequate, or unavailable.

Benefits of implementing a Cognitive equipment maintenance application include:

  • Reduction or elimination of unplanned failures, and a subsequent reduction in emergency responses required by field service personnel
  • Rightsized staffing and optimized scheduling – right maintenance personnel with the requisite skills available when and where needed
  • Improved inventory control – right parts in the right place at the right time
  • Optimized maintenance intervals can extend equipment run-life and delay CAPEX
  • A faster path to improved MX procedures – A byproduct of a more precise understanding of condition-specific drivers of run life often leads to improved maintenance procedures.
  • Optimized equipment or system design and configuration – A granular understanding of condition-specific drivers of run life enable the development of optimal mechanical configurations for specific environments.
  • Optimized run-time parameters:  A granular understanding of condition-specific drivers of run life enable the development of optimal run-time parameters for given operating conditions.  Parameters can be adjusted in real time as conditions change.

7000 North Mopac Expressway, Suite #200
Austin, TX 78731, USA