Abstract
The assessment of the remaining useful life due to fatigue in Francis turbine runners implies complex measurements with strain gauges that have to be installed in a submerged and rotating structure, which is excited with high pressure pulsations and strong turbulent flows. Furthermore, the conditioning, storage and transmission of these signals to the stationary frame involves complicated technical solutions. In order to avoid such complex and expensive measurements, in this paper we explore the feasibility of obtaining the strain on the runner with stationary sensors, which can be easily installed and used for a continuous monitoring of the machine. Based on the experimental strain tests performed in a Francis turbine unit, strain on the runner blade is correlated with relevant indicators obtained with stationary sensors. The correlation within indicators is obtained considering linear regression models and improved with artificial intelligence techniques.
Export citation and abstract BibTeX RIS
Content from this work may be used under the terms of the Creative Commons Attribution 3.0 licence. Any further distribution of this work must maintain attribution to the author(s) and the title of the work, journal citation and DOI.