Posters
Come meet the poster presenters to ask them questions and discuss their work
We would like to invite you to come and see the posters at our upcoming conference. The posters will showcase a diverse range of research topics, and will give delegates an opportunity to engage with the authors and learn more about their work. Whether you are a seasoned researcher or simply curious about the latest developments in your field, we believe that the posters will offer something of interest to everyone. So please join us at the conference and take advantage of this opportunity to learn and engage with your peers in industry and the academic community.
PO501: Bayesian Survival Models Reveal Wind-Driven Reliability Patterns in Turbines
Clément Jacquet, Senior Researcher - Wind Farm Optimization, EPRI
Abstract
Accurate prediction of wind turbine component failures is essential, as operation and maintenance (O&M) costs can account for 25–30% of the levelized cost of energy (LCOE). Reliable forecasts support preconstruction cost assessments, helping evaluate project economic viability, and enable optimized maintenance planning, including efficient inventory management and scheduling. By reducing unexpected downtime and production losses, such predictions directly lower O&M expenses and improve the financial performance of wind energy projects. A major challenge in reliability assessment is the effect of environmental conditions, particularly wind speed, on component lifetimes. Individual wind farms rarely have enough turbines or operational history to generate statistically meaningful insights or perform robust site-by-site comparisons. To address this, we applied a Bayesian survival analysis framework using Markov Chain Monte Carlo (MCMC) to a dataset of over 3,000 turbines across roughly 40 sites in the U.S. and Canada. A two-parameter Weibull model estimated failure probabilities for major drivetrain components, while an Accelerated Failure Time (AFT) approach captured the influence of site-level wind speed. This framework leverages the full dataset to produce robust estimates while naturally incorporating covariate effects. Posterior distributions from MCMC provide credible intervals rather than single-point estimates, offering a rigorous quantification of uncertainty. Results indicate a clear negative impact of higher average wind speeds on gearbox reliability, with expected failure rates approximately doubling between 6 m/s and 9 m/s. These findings highlight the potential of Bayesian methods to improve turbine reliability assessment and guide maintenance strategies. The approach can be extended to other components and environmental or operational factors, providing a versatile, data-driven tool for O&M planning. This study represents a first step toward more comprehensive and robust decision-making, supporting the development of efficient, cost-effective wind energy operations.
No recording available for this poster.
