Improving Reliability of Large Language Models for Nuclear Power Plant Diagnostics Technical Presentation
Large Language Models (LLMs) struggle out of the box when answering factually about detailed questions, especially in domains that are sparsely represented in their training data. This causes hallucinations and reduces reliability making it difficult for them to be used in practice. This work shows that using RAG techniques can improve factual accuracy and reliability, […]
Improving Reliability of Large Language Models for Nuclear Power Plant Diagnostics
Large Language Models (LLMs) struggle out of the box when answering factually about detailed questions, especially in domains that are sparsely represented in their training data. This causes hallucinations and reduces reliability making it difficult for them to be used in practice. This work shows that using RAG techniques can improve factual accuracy and reliability, […]
On-line monitoring of transformer health using gas analysis
On-line monitoring of transformer health using gas analysis presentation.
TRANSFORMER HEALTH MONITORING USING DISSOLVED GAS ANALYSIS
As integral components of any power plant, transformers supply the generated electricity to the grid. However, the transformer’s cellulose-based paper insulation and the mineral oil that it is immersed in break down over time, due to standard operating conditions—or more rapidly due to potential faults within the system. This technical brief exhibits a collection of […]
Verification and validation of developed short-term forecasting models
Recent advancements in machine learning (ML) and artificial intelligence (AI) technologies provide an opportunity for leveraging data-driven algorithms to predict future nuclear power plant (NPP) operating conditions by using recorded plant process data. Successfully implementing these models can lead to cost-reducing, conditioned-based predictive maintenance through optimized maintenance schedules and a reduction of unnecessary maintenance activities. […]
Development of Short-Term Forecasting Models Using Plant AssetData and Feature Selection
Nuclear power plants collect and store large volumes of heterogeneous data from various components and systems. With recent advances in machine learning (ML) techniques, these data can be leveraged to develop diagnostic and short-term forecasting models to better predict future equipment condition. Maintenance operations can then be planned in advance whenever degraded performance is predicted, […]