A Review on Data-driven Predictive Maintenance Approach for Hydro Turbines/Generators

Abstract

Abstract-Hydroelectricity as a renewable energy to respond the increasing population and environment crisis is widely used in the world. With the Hydro Turbines/Generators (HTG) being more and more complicated, the maintenance play a more and more important role in the production management in the hydro power plant. Many researches had concentrated on the predictive maintenance for the HTG in recent years. From the perspective of data-driven, this paper reviews and summarizes the key techniques regarding data acquisition, data processing, data analysis and data mining for the predictive maintenance of HTG. Especially, it place emphasis on the data-driven models for the diagnostics and prognostics. Finally, the paper concludes the current practices and presents a future research work.

Artificial intelligence based prognostic maintenance of renewable energy systems: A review of techniques, challenges, and future research directions

“…To this aim, several efforts have been made. 34,35 For instance, Liu et al 36 developed a graphical software-based condition monitoring system for a Francis turbine. Different variables that had a cumulative impact on one another and affected the turbine's performance were recorded in a database.…”

“…With the current pace of technological advancement resulting in more complex equipment, a global paradigm shift from conventional PM systems to more advanced diagnostic and prognostic maintenance systems is required. To this aim, several efforts have been made 34,35 . For instance, Liu et al 36 developed a graphical software‐based condition monitoring system for a Francis turbine.…”

“…A vast majority of the predictive maintenance solutions for hydropower projects rely on data‐driven methods. In Shewei et al, 35 several data‐driven predictive maintenance models for hydro turbines are analyzed and evaluated. The paper classifies the models into three categories, namely (a) physical models that analytically derived a relationship between the condition and performance of the system, (b) stochastic models that are based on probabilistic and statistical analysis, and (c) data‐mining models that utilize advanced ML algorithms, such as ANN, Composite Neural Networks, SVMs and Decision Trees for fault identification.…”

Artificial Intelligence Based Prognostic Maintenance of Renewable Energy Systems: A Review of Techniques, Challenges, and Future Research Directions

“…With the current pace of technological advancement resulting in more complex equipment, a global paradigm shift from conventional preventive maintenance systems to more advanced diagnostic and prognostic maintenance systems is required. To this aim, several efforts have been made [33], [34]. For instance, Liu et al [35] developed a graphical software-based condition monitoring system for a Francis turbine.…”

“…A vast majority of the predictive maintenance solutions for hydropower projects rely on data-driven methods. In [34], several data-driven predictive maintenance models for hydro turbines are analyzed and evaluated. The paper classifies the models into three categories, namely (i) physical models, that analytically derive the relationship between the system condition and system performance, (ii) stochastic models, that are based on probabilistic and statistical analysis, and (iii) data-mining models, that utilize advanced ML algorithms, such as ANN, Composite Neural Networks, SVMs and Decision Trees for fault identification.…”