Offshore Wind turbines predicative maintenance

The project successfully tested CarbonLnk and IoT sensors on a wind turbine in Levenmouth over three months. Despite initial connectivity issues with the main sensors, backup systems ensured uninterrupted data collection. The sensors proved durable and reliable in real-world conditions, and remote re-establishment of connectivity demonstrated cost-effectiveness by reducing the need for on-site visits.  
 

Predictive AI and data analytics were applied to historical data (received late), revealing anomalies, energy surges, and inefficiencies, which can inform maintenance and operational improvements. 

A real-time carbon avoidance dashboard was developed, and 15,618.31 LnkCoins were issued, linking renewable energy data to a decentralized financial system. Marketing efforts included social media updates and professional visuals, with a case study pending ORE approval. API access for research partners was deferred due to budget constraints, requiring a separate business case. 

Overall, the project demonstrated the technical viability, resilience, and commercial potential of CarbonLnk, laying the groundwork for future scalability and market engagement.