This paper proposes a novel prognostics-driven approach to optimize
operations and maintenance (Ô&M) décisions dans les systèmes hydroélectriques. Our approach
harnesses the insights from sensor data to accurately predict the remaining
lifetime distribution of critical generation assets in hydropower systems,
c'est-à-dire, butées, and use these predictions to optimally schedule O&M
actions for a fleet of hydro generators. We consider complex interdependencies
across hydro generator failure risks, reservoir, production, and demand
management decisions. We propose a stochastic joint O&M scheduling model to
tackle the unique challenges of hydropower O&M including the interdependency of
generation capacities, the nonlinear nature of power production, operational
exigences, and uncertainties. We develop a two-level decomposition-based
solution algorithm to effectively handle large-scale cases. The algorithm
incorporates a combination of Benders optimality cuts and integer cuts to solve
the problem in an efficient manner. We design an experimental framework to
evaluate the proposed prognostics-driven O&M scheduling framework, using
real-world condition monitoring data from hydropower systems, historical market
prices, and water inflow data. The developed framework can be partially
implemented for a phased-in approach. Our experiments demonstrate the
significant benefits of the sensor-driven O&M framework in improving
reliability, availability, effective usage of resources, and system
profitability, especially when gradually shifting from traditional time-based
maintenance policies to condition-based prognostics-driven maintenance
policies.

Cet article explore les excursions dans le temps et leurs implications.

Télécharger PDF: