Real-time prediction of nuclear power plant parameter trends following operator actions

作者：

Highlights：

• Methodology to predict future NPP parameter trends following device control by operators.

• To find optimal model performance, nine candidate models composed by different multi-step prediction strategies and artificial neural networks was tested.

• The best prediction model achieves 95.4% Mostly Accurate predictions.

• Prediction model can be utilized as human error prevention, and as a detection system.

摘要

•Methodology to predict future NPP parameter trends following device control by operators.•To find optimal model performance, nine candidate models composed by different multi-step prediction strategies and artificial neural networks was tested.•The best prediction model achieves 95.4% Mostly Accurate predictions.•Prediction model can be utilized as human error prevention, and as a detection system.

论文关键词：Nuclear power plant safety,Operator support system,Time-series forecasting,Artificial neural network,Long short-term memory,Multi-step prediction strategy

论文评审过程：Received 27 November 2020, Revised 23 July 2021, Accepted 30 August 2021, Available online 3 September 2021, Version of Record 9 September 2021.

论文官网地址：https://doi.org/10.1016/j.eswa.2021.115848