Forecasting thermal parameters for ultra‐high voltage transformers using long‐ and short‐term time‐series network with conditional mutual information

Lin, Weiqing; Miao, Xin; Chen, Jing; Xiao, Shun; Lu, Yan; Jiang, Hao

doi:10.1049/elp2.12175

Cited by 14 publications

(4 citation statements)

References 65 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…On the one hand, the statistical vector auto-regressive algorithm (VAR) [ 5 ] and the Gaussian processes algorithm (GP) [ 6 ] are unable to explore non-linear relationships between variables. On the other hand, the LSTNet [ 7 , 8 ] and TPA-LSTM [ 9 ] methods, despite the fact that they can mine non-linear relationships, cannot explicitly determine the dependencies between any two variables. In the problem of time-series prediction, the method based on the graph neural network (GNN) [ 10 ] relies on a predefined graph structure and can obtain the relationships between variables.…”

Section: Introductionmentioning

confidence: 99%

Swing Trend Prediction of Main Guide Bearing in Hydropower Units Based on MFS-DCGNN

Li,

Xu,

Guo

2024

Sensors

View full text Add to dashboard Cite

Hydropower units are the core equipment of hydropower stations, and research on the fault prediction and health management of these units can help improve their safety, stability, and the level of reliable operation and can effectively reduce costs. Therefore, it is necessary to predict the swing trend of these units. Firstly, this study considers the influence of various factors, such as electrical, mechanical, and hydraulic swing factors, on the swing signal of the main guide bearing y-axis. Before swing trend prediction, the multi-index feature selection algorithm is used to obtain suitable state variables, and the low-dimensional effective feature subset is obtained using the Pearson correlation coefficient and distance correlation coefficient algorithms. Secondly, the dilated convolution graph neural network (DCGNN) algorithm, with a dilated convolution graph, is used to predict the swing trend of the main guide bearing. Existing GNN methods rely heavily on predefined graph structures for prediction. The DCGNN algorithm can solve the problem of spatial dependence between variables without defining the graph structure and provides the adjacency matrix of the graph learning layer simulation, avoiding the over-smoothing problem often seen in graph convolutional networks; furthermore, it effectively improves the prediction accuracy. The experimental results showed that, compared with the RNN-GRU, LSTNet, and TAP-LSTM algorithms, the MAEs of the DCGNN algorithm decreased by 6.05%, 6.32%, and 3.04%; the RMSEs decreased by 9.21%, 9.01%, and 2.83%; and the CORR values increased by 0.63%, 1.05%, and 0.37%, respectively. Thus, the prediction accuracy was effectively improved.

show abstract

Section: Introductionmentioning

confidence: 99%

Swing Trend Prediction of Main Guide Bearing in Hydropower Units Based on MFS-DCGNN

Li,

Xu,

Guo

2024

Sensors

View full text Add to dashboard Cite

show abstract

“…Due to the intermittent and irregular characteristics of wind and solar power, most of the existing power prediction methods are based on time-series data with nonlinear network prediction models [7][8][9]. Te long-and short-term time-series network (LSTNet) uses the convolutional neural network (CNN) and the recurrent neural network (RNN) to extract short-term local dependency patterns among variables and discover long-term patterns for time-series trends.…”

Section: Introductionmentioning

confidence: 99%

Short‐Term Wind and Solar Power Prediction Based on Feature Selection and Improved Long‐ and Short‐Term Time‐Series Networks

Wang

et al. 2023

Mathematical Problems in Engineering

View full text Add to dashboard Cite

In terms of the problems of high feature dimension and large data redundancy in the wind and solar power prediction method, an improved prediction model is proposed by combining feature selection methods with the long- and short-term time-series network (LSTNet). The long short-term memory (LSTM) unit in the LSTNet model is replaced with the bidirectional long short-term memory (BiLSTM), which enables recursive response training for the states of hidden layers at the start and end of the sequence. For feature selection, both feature screening and dimension reduction methods are considered, including random forest (RF), grey relational analysis (GRA), and principal component analysis (PCA). Finally, based on wind and solar power data, the effectiveness of the proposed methods is verified, where the RF-LSTNet performs the best. For wind power prediction, the mean absolute percentage error is reduced by 29.7% and root mean square error is reduced by 24.1% compared with the traditional LSTNet model, and for solar power prediction, the MAPE is reduced by 12.9% and RMSE is reduced by 3.8%.

show abstract

“…As one of the most important equipment in UHV-DC transmission, converter transformers' safe operation is crucial. The temperature distribution of converter transformer is a key limiting variable that affects its service life, allowable load and safe operation [2][3][4][5].…”

Section: Introductionmentioning

confidence: 99%

High proportion and large value harmonic current influence on the magnetic field, loss and temperature distribution for ultrahigh voltage converter transformer

Liu,

Hao,

Liao

et al. 2023

IET Electric Power Appl

View full text Add to dashboard Cite

The temperature distribution of ultrahigh voltage (UHV) converter transformer is the key to its service life, allowable load and safe operation. The influence of a high‐proportion and large‐value harmonic current on the magnetic field, loss and temperature distribution of a UHV converter transformer is studied. A new calculation method is proposed to determine the winding temperature under the combined actions of multiple key factors. First, the skin effect of UHV converter transformer winding under high proportion and high current harmonics is analysed extensively. It is found that the increase of harmonic current frequency leads to exponential increase of winding loss and temperature by changing skin depth. Second, based on the superposition principle, a calculation method for winding loss considering harmonic current and different load rates is developed. The temperature distribution under different harmonic current frequencies and contents is obtained. The winding losses and temperature under different harmonic currents are quantified. Finally, a new calculation method is proposed for the converter transformer winding temperature, considering the combined actions of factors such as load rate, cooling oil inlet rate and temperature, harmonic current frequency and content. Experimental verification showed an error of only 0.58 K in the actual transformer hotspot temperature, confirming the effectiveness of this method. This method is of great significance for temperature control and safe operation of UHV converter transformers.

show abstract

Forecasting thermal parameters for ultra‐high voltage transformers using long‐ and short‐term time‐series network with conditional mutual information

Cited by 14 publications

References 65 publications

Swing Trend Prediction of Main Guide Bearing in Hydropower Units Based on MFS-DCGNN

Swing Trend Prediction of Main Guide Bearing in Hydropower Units Based on MFS-DCGNN

Short‐Term Wind and Solar Power Prediction Based on Feature Selection and Improved Long‐ and Short‐Term Time‐Series Networks

High proportion and large value harmonic current influence on the magnetic field, loss and temperature distribution for ultrahigh voltage converter transformer

Contact Info

Product

Resources

About