Imbalanced classification in faulty turbine data: New proximal policy optimisation

Abstract

AbstractIn industrial and real‐world systems, recognising errors and adopting the best approaches are gaining relevance. The authors’ goal is to identify artificial intelligence apps that provide the most reliable and valuable data‐based fault detection techniques. A system for fault identification is presented based on reinforcement learning and proximal policy optimisation (PPO). Due to the lack of fault data, one of the key issues with the standard policy is its inability to recognise fault classes; this issue was resolved by modifying the cost equation. Using improved PPO, the authors can improve performance, address data imbalances, and forecast possible failures more accurately. The approach utilises policy‐based optimisation, which offers several advantages. Firstly, it directly optimises the advantage quantity, and secondly, it ensures the stability of function approximation. The authors have studied two different turbines in Iran and collected data from them separately when a fault occurred. To demonstrate the efficiency of our algorithm, the authors have included the third and fourth datasets as cyber attack benchmarks. When the authors’ proposed policy is adopted, all evaluation metrics will improve by 3%–4% as compared to the previous policy in the first benchmark, between 20% and 55% in the second benchmark, between 6% and 14% in the third benchmark, and between 4% and 5% in the fourth benchmark, with improved results and prediction times compared to existing studies.