Leveraging explainable Artificial Intelligence for real-time detection of tidal blade damage

Fossil fuels are the main cause of global warming and threaten our survival. Tidal turbines can supply renewable energy and fight climate change. Whereas large scale of installation will lower the levelized cost of tidal energy to EUR100/MWh, making ocean energy competitive with other renewable energy sources like offshore wind. To achieve the target, increased performance and reliability of tidal energy devices are required. Tidal turbine blades are one of the primary component of tidal turbines, and can experience complex non-linear damage modes. Tidal blades can fail catastrophically due to impact damage, delamination, matrix crack, fibre breakage or rupture, and others in harsh marine environments. Thus, tidal energy companies must ensure blade health and performance. In the sea, fault diagnosis and maintenance are difficult, and if left unattended, the tidal energy system may fail. Therefore, we proposed real-time and reliable structure health monitoring (SHM) tidal blades. We addressed the trustworthiness of system decisions made with explainable artificial intelligence (XAI), which is recommended approach by EU for utilization of AI. This paper presents a real-time damage detection framework, ICT-based infrastructure for real-time monitoring, and a novel model to classify/detect blade structure damages. Testing and evaluation of proposed approach in laboratory and operational settings is the future concern of this study.