Prediction of crucial nuclear power plant parameters using long short‐term memory neural networks

Lei, Jichong; Ren, Changan; Li, Wei; Fu, Liming; Li, Zhicai; Ni, Zining; Li, Yukun; Li, Chengwei; Zhang, Huajian; Chen, Zhenping; Yu, T.

doi:10.1002/er.7873

Cited by 16 publications

(7 citation statements)

References 25 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The forget gate controls memory capabilities: when the forget gate determines that new information does not require long‐term memory, the memory cell will preserve past features and cause the new information to be used in the current time step. This design efficiently captures the dependent relationships among longer time steps in a time series 45 …”

Section: Methodsmentioning

confidence: 99%

See 1 more Smart Citation

Metaheuristics‐optimized deep learning to predict generation of sustainable energy from rooftop plant microbial fuel cells

Chou

Cheng

Liu

et al. 2022

Intl J of Energy Research

View full text Add to dashboard Cite

Plant microbial fuel cells (PMFCs) are an emergent green-energy technology that continuously converts solar energy into electricity. Placing PMFCs on the roofs of urban buildings can help to create green urban environments even as they generate power. The power generation performance of PMFCs is affected by a range of environmental factors, so their power generation capacity is difficult to estimate. To develop an artificial intelligence model to forecast PMFC power generation accurately, relevant results obtained using shallow and deep learning techniques are compared for the first time. Once deep learning techniques had been identified as superior for this purpose, they were used with a bio-inspired optimization algorithm to dynamically setting the model hyperparameters. The developed model can also be applied to estimate the power generation capacity of PMFC devices in the future. The model was trained using data collected from sensors in a site experiment that was carried out using PMFCs embedded with Chinese pennisetumin (Pennisetum alopecuroides), narrowleaf cattail (Typha angustifolia), dwarf rotala (Rotala rotundifolia), and no plant as a control group. The original data of device parameters, environmental parameters, and the measured power generation of PMFCs in numerical form were applied to train shallow learning and time-series deep learning models. Meanwhile, the state-of-the-art sliding window technique was used to establish a numerical matrix, which was converted into a 2D image-like format to represent inputs for deep convolutional neural network (CNN) models. The accuracy in predicting the power generation capacity of PMFC devices showed that EfficientNet, an advanced type of CNN, was the best model among the shallow and deep learning techniques. These analytical results demonstrate the superior performance of deep CNNs in learning image features and their consequent suitability for constructing PMFC power generation forecasting models. To enhance the generalization performance of CNN, a

show abstract

Section: Methodsmentioning

confidence: 99%

“…This design efficiently captures the dependent relationships among longer time steps in a time series. 45…”

Section: Long Short-term Memorymentioning

confidence: 99%

Metaheuristics‐optimized deep learning to predict generation of sustainable energy from rooftop plant microbial fuel cells

Chou

Cheng

Liu

et al. 2022

Intl J of Energy Research

View full text Add to dashboard Cite

show abstract

“…These sophisticated algorithms can handle very complex machine learning tasks that are characterized by nonlinear relationships and interactions between features with a large number of inputs. Long Short-Term Memory (LSTM), first proposed in 1997 7 – 9 , is a neural network specifically proposed to solve the problem of long-term dependence in general recurrent neural networks.…”

Section: Lstm Neural Networkmentioning

confidence: 99%

Neutron transport calculation for the BEAVRS core based on the LSTM neural network

Ren,

He,

Lei

et al. 2023

Sci Rep

Self Cite

View full text Add to dashboard Cite

With the rapid development of computer technology, artificial intelligence and big data technology have undergone a qualitative leap, permeating into various industries. In order to fully harness the role of artificial intelligence in the field of nuclear engineering, we propose to use the LSTM algorithm in deep learning to model the BEAVRS (Benchmark for Evaluation And Validation of Reactor Simulations) core first cycle loading. The BEAVRS core is simulated by DRAGON and DONJON, the training set and the test set are arranged in a sequential fashion according to the evolution of time, and the LSTM model is constructed by changing a number of hyperparameters. In addition to this, the training set and the test set are retained in a chronological order that is different from one another throughout the whole process. Additionally, there is a significant pattern that is followed when subsetting both the training set and the test set. This pattern applies to both sets. The steps in this design are very carefully arranged. The findings of the experiments suggest that the model can be altered by making use of the appropriate hyperparameters in such a way as to bring the maximum error of the effective multiplication factor keff prediction of the core within 2.5 pcm (10–5), and the average error within 0.5266 pcm, which validated the successful application of machine learning to transport equations.

show abstract

“…Gong et al [ 29 ] introduced a zigmoid-based LSTM method for the time series prediction of an LOCA. Lei et al [ 30 ] developed a prediction model for key parameters affected by sensor failures during nuclear power plant accidents by using LSTM and historical key parameter operation sequences. The proposed model successfully predicted parameters including the pressurizer pressure, pressurizer water level, and steam generator water level, etc.…”

Section: Related Workmentioning

confidence: 99%

An Interpretable Time Series Data Prediction Framework for Severe Accidents in Nuclear Power Plants

Zhang

Xiao³

et al. 2023

Entropy

View full text Add to dashboard Cite

Accurately predicting severe accident data in nuclear power plants is of utmost importance for ensuring their safety and reliability. However, existing methods often lack interpretability, thereby limiting their utility in decision making. In this paper, we present an interpretable framework, called GRUS, for forecasting severe accident data in nuclear power plants. Our approach combines the GRU model with SHAP analysis, enabling accurate predictions and offering valuable insights into the underlying mechanisms. To begin, we preprocess the data and extract temporal features. Subsequently, we employ the GRU model to generate preliminary predictions. To enhance the interpretability of our framework, we leverage SHAP analysis to assess the contributions of different features and develop a deeper understanding of their impact on the predictions. Finally, we retrain the GRU model using the selected dataset. Through extensive experimentation utilizing breach data from MSLB accidents and LOCAs, we demonstrate the superior performance of our GRUS framework compared to the mainstream GRU, LSTM, and ARIMAX models. Our framework effectively forecasts trends in core parameters during severe accidents, thereby bolstering decision-making capabilities and enabling more effective emergency response strategies in nuclear power plants.

show abstract

Prediction of crucial nuclear power plant parameters using long short‐term memory neural networks

Cited by 16 publications

References 25 publications

Metaheuristics‐optimized deep learning to predict generation of sustainable energy from rooftop plant microbial fuel cells

Metaheuristics‐optimized deep learning to predict generation of sustainable energy from rooftop plant microbial fuel cells

Neutron transport calculation for the BEAVRS core based on the LSTM neural network

An Interpretable Time Series Data Prediction Framework for Severe Accidents in Nuclear Power Plants

Contact Info

Product

Resources

About