Hydro power operators face a number of challenges due to the introduction of stochastic energy providers like wind and solar. They are switching from baseload to more flexible power production, which introduces stochastic usage and operations pattern. At the same time availability and efficiency must be improved. Static wear and operations models of the core assets, e.g. turbines, pumps et al., don’t suffice any longer, intelligent AI driven condition monitoring and diagnostics promise remedy.
LexaTexer provides an Enterprise AI platform to support the energy value chain with prebuilt, configurable AI applications addressing CAPEX intense hydro assets like Francis and Pelton turbines and pumps.
In this project we combined a) our proprietary enterprise AI platform and b) data from real world operations to model the remaining useful life (RUL) of Pelton turbines based on real-world operational and environmental data. Thus, increasing RUL, efficiency and availability significantly. We have model build AI driven models that support answering two fundamental questions of turbine operators: a) given the current usage pattern, for how long can I operate my turbine until the end of life, i.e. maintenance shutdown, b) how do I have to parametrize the operational data to extent the remaining useful life.