scholarly journals Ensuring timely repair of power transformers based on data of complex diagnostics

2021 ◽  
Vol 288 ◽  
pp. 01034
Author(s):  
Makhsud Sultanov ◽  
Elena Zenina ◽  
Peter Shamigulov ◽  
Valentina Lunenko ◽  
Olga Zhelyaskova
Keyword(s):  
Neural Network ◽  
Life Cycle ◽  
Power System ◽  
Neural Network Model ◽  
Power Transformers ◽  
Power Equipment ◽  
Reliable Operation ◽  
Safe Operation ◽  
Power Stations ◽  
Initial Stage

Timely diagnosis of power transformers is an essential component of ensuring reliable and safe operation of power stations and substations, on which the reliability of the power system depends. Detection of defects in the initial stage allows to maintain reliable operation of transformers, helps to define the "life cycle" and simplify the planning of their replacement. The paper presents an analysis of existing approaches to the creation of power equipment diagnostics systems using the example of power transformers. A neural network model has been developed, demonstrating the possibility of using power transformers to estimate the current residual resource based on the analysis of available diagnostic data.

scholarly journals A Short-Term Load Forecasting Method Based on GRU-CNN Hybrid Neural Network Model

2020 ◽  
Vol 2020 ◽  
pp. 1-10 ◽  
Author(s):  
Lizhen Wu ◽  
Chun Kong ◽  
Xiaohong Hao ◽  
Wei Chen
Keyword(s):  
Neural Network ◽  
Power System ◽  
Network Model ◽  
Neural Network Model ◽  
Feature Vector ◽  
Load Forecasting ◽  
Percentage Error ◽  
Short Term ◽  
Hybrid Neural Network ◽  
Short Term Load Forecasting

Short-term load forecasting (STLF) plays a very important role in improving the economy and stability of the power system operation. With the smart meters and smart sensors widely deployed in the power system, a large amount of data was generated but not fully utilized, these data are complex and diverse, and most of the STLF methods cannot well handle such a huge, complex, and diverse data. For better accuracy of STLF, a GRU-CNN hybrid neural network model which combines the gated recurrent unit (GRU) and convolutional neural networks (CNN) was proposed; the feature vector of time sequence data is extracted by the GRU module, and the feature vector of other high-dimensional data is extracted by the CNN module. The proposed model was tested in a real-world experiment, and the mean absolute percentage error (MAPE) and the root mean square error (RMSE) of the GRU-CNN model are the lowest among BPNN, GRU, and CNN forecasting methods; the proposed GRU-CNN model can more fully use data and achieve more accurate short-term load forecasting.

Week-ahead Forecasting of Household Energy Consumption Using CNN and Multivariate Data

2021 ◽  
Vol 20 ◽  
pp. 182-188
Author(s):  
Vanita Agrawal ◽  
Pradyut K. Goswami ◽  
Kandarpa K. Sarma
Keyword(s):  
Neural Network ◽  
Energy Consumption ◽  
Power System ◽  
Convolutional Neural Network ◽  
Network Model ◽  
Neural Network Model ◽  
Smart Grids ◽  
Smart Meters ◽  
Household Energy ◽  
Household Energy Consumption

Short-Term Load Forecasting for buildings has gained a lot of importance in recent times due to the ongoing penetration of renewable energy and the upgradation of power system networks to Smart Grids embedded with smart meters. Power System expansion is not able to keep pace with the energy consumption demands. In this scenario, accurate household energy forecasting is one of the key solutions to managing the demand side energy. Even a small percentage of improvement in forecasting error, translates to a lot of saving for both producers and consumers. In this paper, it was found out that Aggregated 1-Dimensional Convolutional Neural Networks can be effectively modeled to predict the household consumption with greater accuracy than a basic 1-Dimensional Convolutional Neural Network model or a classical Auto Regressive Integrated Moving Average model. The proposed Aggregated Convolutional Neural Network model was tested on a 4 year household energy consumption dataset and gave very promising Root Mean Square Error reduction

Prediction of Insulator's Equivalent Salt Deposit Density in Power System

2013 ◽  
Vol 385-386 ◽  
pp. 987-990
Author(s):  
Li Ai ◽  
Jia Tang Cheng
Keyword(s):  
Neural Network ◽  
Power System ◽  
Network Model ◽  
Neural Network Model ◽  
Meteorological Factors ◽  
Data Series ◽  
Salt Deposit ◽  
Changing Trend ◽  
Deposit Density ◽  
Main Basis

The equivalent salt deposit density (ESDD) of insulator in power system is the main basis of defining pollution classes and mapping pollution areas. However, The meteorological factors on it is complex, using traditional methods is difficult to establish accurate mathematical model to express the relationship, In this paper, the gray theory and neural network model to reflect the changing trend of data series on the apparent effect, Gray neural network model used to predict the insulators ESDD under certain meteorological factors, and to design a neural network compensator correction on the predicted results. The simulation results show that the model has higher prediction accuracy, better than a simple gray neural network model, and have certain theoretical value and practical application value.

scholarly journals Condition assessment of power transformers status based on moisture level using fuzzy logic techniques

2018 ◽  
Vol 9 (1) ◽  
pp. 17 ◽  
Author(s):  
Vezir Rexhepi ◽  
Petar Nakov
Keyword(s):  
Fuzzy Logic ◽  
Power System ◽  
Electrical Breakdown ◽  
Power Transformer ◽  
Condition Assessment ◽  
The State ◽  
Moisture Level ◽  
Power Transformers ◽  
Safe Operation ◽  
Fuzzy Logic Technique

Power transformers are one of the most expensive components; therefore the focus on their status and its continuous operation is the primary task. In the power systems, condition assessment of performance and reliability is based on the state of components, measurements, testing and maintenance as well as their diagnosis. Hence, condition assessment of power transformer parameters is the most important regarding their status and finding incipient failures. Among many factors, the most factors that affects the safe operation and life expentancy of the transformer is the moisture in oil. It is known that the low moisture oil in power transformers causes many problems including electrical breakdown, increase the amount of partial discharge, decreases the dielectric withstand strength and other phenomena. Thus, knowledge about the moisture concentration in a power transformer is significantly important for safe operation and lifespan. In this study, moisture level in oil is estimated and its status classification is proposed by using fuzzy logic techniques for the power transformer monitoring and condition assessment. Moreover, the goal of the study is to find methods and techniques for the condition assessment of power transformers status based on the state of moisture in oil using the fuzzy logic technique. These applied techniques increase the power system reliability, help to reduce incipient failures, and give the better maintenance plan using an algorithm based on logic rules. Also, by using the fuzzy logic techniques, it is easier to prevent failures which may have consequences not only for transformers but also for the power system as a whole.

Sign in / Sign up

Export Citation Format

Share Document