Enhancing Condition Monitoring: Operational Mode Classification for Crew Transfer Vessels

The expected growth of new offshore wind turbine installations necessitates effective Operation and Maintenance strategies to ensure wind farm reliability. Key to these strategies is optimizing operational uptime for Crew Transfer Vessels (CTVs), which transport technicians to wind farms. CTVs operate in hostile environments demanding intricate manoeuvers, which often necessitate corrective maintenance approaches to ensure continuous operation. Moreover, the execution of complex manoeuvres results in deterioration that surpasses standard expectations. Transitioning towards a condition-based maintenance strategy potentially yields lowered maintenance costs while maximizing operational uptime. At the core of this strategy is condition monitoring technology, aiming at identifying deviations from normal operating conditions on rotary components. However, its application in CTVs is challenged by the diverse operational conditions encountered, ultimately hampering the definition of normal operating conditions. This study addresses this challenge by focusing on classifying operational modes of a CTV. Striving to balance simplicity and accuracy, the study utilizes a Random Forest model with data from the CTV’s Automatic Identification System. While the Random Forest model demonstrates high accuracy in this regard, future potential limitations emerged, prompting considerations for future improvements.