NPP-GPT: Forecasting nuclear power plants operating parameters using pre-trained large language model

Key Points

• Forecasting of operating parameters shows enhanced accuracy using the large language model, indicating effective prediction capabilities.
• Achieving up to 15% improvement in forecasting accuracy compared to conventional methods, highlighting significant performance gains.
• This analysis utilized a pre-trained large language model on extensive operational datasets from multiple power plants.
• Results indicate a need for further real-world testing to validate the model's performance in continuous operations.