Intelligent Maintenance and Operations Systems (IMOS)

Our research focuses on developing intelligent algorithms to improve performance, reliability and availability of complex industrial assets and making the maintenance more cost efficient. 

Intelligent Maintenance & Operations Systems

Our research  focuses on developing intelligent algorithms to improve performance, reliability and availability of complex industrial assets and making the maintenance more cost efficient.

The amount of measured and collected condition monitoring data for complex industrial assets has been recently increasing significantly due to falling costs, improved technology, and increased reliability of sensors and data transmission.

The measured condition monitoring signals of complex industrial assets are typically high dimensional, highly redundant, have several interdependencies and prevalent non-​linear relationships. The diversity of the fault types and operating conditions makes it often impossible to extract and learn the fault patterns of all the possible fault types affecting a system and to develop model-​based approaches. Even collecting a representative dataset with all possible operating conditions can be a challenging task (depending on the variability of the operating regimes of the assets) and may delay the implementation of data-​driven fault detection systems.

 

This mission involves tackling the following challenges (selected):

  • Fault Rarity: The rarity of abnormal and faulty events (particularly for safety critical and highly reliable systems) and the multitude of possible fault types (many of which may not be known before their occurrence) make it very challenging and sometimes even impossible to learn the fault signatures from the data.
  • Heterogeneous condition monitoring data: A large number and a large variety of sensors monitor industrial assets (temperature, pressure, vibration, video, status, operating condition,…). Data with different nature, precision and sampling frequencies need to be combined to extract the meaningful information.
  • Refurbishment: Industrial assets with a long lifespan were not designed for modern monitoring methods. Installed a-​posteriori the non-​invasive monitoring systems often lead to incomplete and less reliable information on the system.
  • Varying and evolving operating conditions: Industrial assets are operated in dynamic environments with a high variability that may additionally evolve gradually or abruptly. In addition, the operating conditions and regimes change over time. Consequently, algorithms can become unreliable on new data and can generate false alarms. It is therefore necessary to distinguish a change in environment or operating conditions from an abnormal event.
  • Aging: Industrial assets are operated over long periods and wear and degradation processes affect the behavior of the system and need to be distinguished from occurring faults with different dynamics.
  • Unit specificities in fleets: The specificities of each unit within the fleet of industrial assets: operating conditions, aging, monitoring equipment might vary from one unit to another making the development of monitoring solutions at the fleet level challenging.
  • Decision support: Decision making for effective maintenance of complex systems and fleets of systems is complex and requires an integration of several sources of information with different degrees of uncertainty: (a) the current health condition of each system, (b) predicted evolution of the system state condition including the uncertainty of the performed predictions (c) the scheduled maintenance plan, (d) scheduled production or operation plan, (e) anticipated future operating conditions, (f) costs of maintenance resources and unavailability, (g) restrictions of resource availability and (h) the system configuration and decision alternatives.