Proactive Fleet Health Monitoring and Management

Achieving fleet-wide management and decision-making support raises challenges that still have to be addressed. Toward this end, new methodologies, methods and tools are required to identify the related health indicators, support continuous monitoring, enable predictive diagnosis, and provide suitable prognosis facilities in order to carry out proactive health management. In this paper, an approach to proactive fleet health monitoring and management is proposed. The underlying modeling methods are introduced as well as health monitoring facilities for proactively reacting to system performance drift.

[1]  Piero P. Bonissone,et al.  Predicting the Best Units within a Fleet: Prognostic Capabilities Enabled by Peer Learning, Fuzzy Similarity, and Evolutionary Design Process , 2005, The 14th IEEE International Conference on Fuzzy Systems, 2005. FUZZ '05..

[2]  Benoît Iung,et al.  Conceptual framework for e-Maintenance: Illustration by e-Maintenance technologies and platforms , 2009, Annu. Rev. Control..

[3]  Ajit Srividya,et al.  A systemic approach to integrated E-maintenance of large engineering plants , 2010, Int. J. Autom. Comput..

[4]  Piero P. Bonissone,et al.  Design of local fuzzy models using evolutionary algorithms , 2006, Comput. Stat. Data Anal..

[5]  R. Outbib,et al.  Damage trajectory analysis based prognostic , 2008, 2008 International Conference on Prognostics and Health Management.