Advanced structural health monitoring strategies for condition-based maintenance planning of offshore wind turbine support structures

Condition-based maintenance strategies need to be adopted as distance-to-shore and water depth increase in the offshore wind industry. The aim of the research presented herein is to develop advance structural health monitoring strategies that enhance the condition-based maintenance of offshore wind turbine support structures. The focus is on the selection of technologies, the implementation process, the analysis of the asset’s structural response under complex loading, the economic justification for structural health monitoring implementation and the effective structural health monitoring data analysis. Research activities consist of the provision of a comprehensive study for structural health monitoring technologies’ utilisation in the offshore wind industry. This is followed by parametric structural modelling, simulation and validation of an operational offshore wind turbine tower, support structure and soil-structure interaction, using commercial software. The evaluation of the asset’s response under complex loading subject to design changes and failure mechanisms is also undertaken. A combination of existing and newly developed methodologies is deployed for the effective data management of structural health monitoring systems and validated with industrial data for the case of strain monitoring. These include unsupervised learning algorithms (neural networks), deterministic and probabilistic methods for noise cleansing and missing data imputation. Guidelines for the structural health monitoring implementation from design stage of a wind farm are proposed and applied to a baseline scenario. This is utilised to assess the economic impact that structural health monitoring has in the lifecycle of the assets. The achieved results show that the implementation of structural health monitoring in offshore wind turbine following the Statistical Pattern Recognition paradigm and the proposed guidelines has the potential to reduce the Operational Expenditure. This reduction is much greater than the cost associated with the implementation of these systems. Monitoring from the commissioning of the assets is crucial for the system’s calibration and establishing thresholds. The developed noise cleansing and missing data imputation methodologies can successfully be employed together to produce more complete low-disturbed datasets.