Exploratory Semantic Reliability Analysis of Wind Turbine Maintenance Logs using Large Language Models

A wealth of operational intelligence is locked within the unstructured free-text of wind turbine maintenance logs, a resource largely inaccessible to traditional quantitative reliability analysis. While machine learning has been applied to this data, existing approaches typically stop at classification, categorising text into predefined labels. This paper addresses the gap in leveraging modern large language models (LLMs) for more complex reasoning tasks. We introduce an exploratory framework that uses LLMs to move beyond classification and perform deep semantic analysis. We apply this framework to a large industrial dataset to execute four analytical workflows: failure mode identification, causal chain inference, comparative site analysis, and data quality auditing. The results demonstrate that LLMs can function as powerful "reliability co-pilots," moving beyond labelling to synthesise textual information and generate actionable, expert-level hypotheses. This work contributes a novel and reproducible methodology for using LLMs as a reasoning tool, offering a new pathway to enhance operational intelligence in the wind energy sector by unlocking insights previously obscured in unstructured data.

Analysis and Control of Acoustic Emissions from Marine Energy Converters

This study investigates the mitigation of acoustic emissions from tidal current converters (TCCs) through optimized control strategies to enhance power generation efficiency while minimizing environmental impacts on marine life. A MATLAB/Simulink-based model of a Tidal Current Conversion System (TCCS) was developed to simulate the effects of variable control parameters, including switching frequencies, maximum power point tracking (MPPT) coefficients, and the elimination of the gearbox, on underwater noise levels. Acoustic emissions were quantified in terms of sound pressure levels (SPLs), and their potential impacts on marine mammals and fish were evaluated against species-specific auditory thresholds for temporary and permanent hearing threshold shifts. The results indicate that adjusting control parameters can significantly reduce SPLs, with the removal of the gearbox yielding the greatest noise reduction. The study identifies operational conditions under which marine species are at risk of auditory damage and proposes control strategies to mitigate these risks without compromising energy output. These findings contribute to the understanding of how control system modifications can balance the efficiency of marine energy systems with ecological considerations, offering guidance for the design and operation of environmentally compliant TCCs.