Electricity generated by wind turbines (WT) is a pillar of the transition to renewable energy [1]. In order to
economically utilize WTs, operating and maintenance costs, which account for 25% of total electricity
generation costs in onshore WTs, are a focus of cost reduction activities [2]. A prescriptive maintenance
approach can support in achieving this goal. Prescriptive maintenance is a maintenance approach, where
asset condition data is collected and analyzed to recommend specific actions to prevent breakdowns and
reduce downtimes. However, the processing and analysis of data is quite complex. Especially unstructured
data (such as comments of service technicians in free text fields) is often left unused, as companies, mostly
SMEs lack the capacity to carry out these analyses. In this work we propose an approach to utilize the
information from service reports, maintenance reports as well as status records from SCADA systems for
the development of a prescriptive maintenance approach to onshore WTs. To achieve this, an ontology was
utilized in this approach to codify implicit knowledge of service technicians and aid in making unstructured
data usable for further analysis. The ontology was used to link historical service and maintenance reports
with status codes, thus enabling automated analysis. In interviews with WT topic experts and through further
research, damage mechanisms and corresponding maintenance measures were identified and a measure
catalogue was developed to support service and maintenance activities. The recognition of the root cause of
problems allows for a prescriptive maintenance approach that recommends targeted actions to reduce
downtimes and optimize maintenance activities, it also allows to effectively control the outcome of
maintenance activities and optimize their execution.
|