Global electricity consumption has continued to grow rapidly. This growth of consumption shows that energy will be one of the major problems in the future. Maintenance of the energy supply is essential, as the interruption of this service leads to higher expenses, representing substantial monetary losses and even legal penalties for the power generation company (Azam et al,2021). Hydroelectricity is the basis of the Brazilian energy matrix. Therefore, it is clear the need to maintain the availability and operational reliability of hydroelectric plants, so as not to compromise the continuity and conformity (quality) of the electrical energy supply to the end consumer. Ensuring availability along with the reliability of hydroelectric plants can be maintained by employing appropriate maintenance policies that reduce the likelihood of failure or even eliminate its root causes, preventing failure from occurring. The aim of this paper is presenting a proposed smart maintenance system model that integrates Natural Language Processing (NLP) algorithm and FMECA (Failure Mode, Effects & Criticality Analysis) database automated by Power BI® for the development of consistent maintenance plans for hydrogenerators assets. This integrated innovative tool can identify the operational subsystem chronic failure modes supporting industrial managers to incorporate tasks aimed at strengthening and increasing the maintenance plan consistency in blocking failure modes before them occurrences. This work was applied to a case study in a 525 Kv transformer of a hydrogenerator unit type Francis to demonstrate its use and contribute to its understanding.