Knowledge‐based artificial neural network for power transformer protection

Li, Zongbo; Jiao, Zaibin; He, Anyang

doi:10.1049/iet-gtd.2020.0542

Cited by 16 publications

(10 citation statements)

References 53 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Stopping the network early has been utilized to prevent network overfitting and underfitting 129 . The optimal BPNN settings with the maximum precision, which is equivalent to the correlation coefficient ( R ), were obtained by modifying the number of hidden layers, the number of neurons, as well as the transfer functionality 108 , 130 . In this work, a two-layer system with 10-hidden layers and a 1-output layer was adopted for both BPNN algorithms.…”

Section: Methods Used To Investigate Transformers In-servicementioning

confidence: 99%

Application of back propagation neural network in complex diagnostics and forecasting loss of life of cellulose paper insulation in oil-immersed transformers

Ngwenyama,

Gitau

2024

Sci Rep

View full text Add to dashboard Cite

Oil-immersed transformers are expensive equipment in the electrical system, and their failure would lead to widespread blackouts and catastrophic economic losses. In this work, an elaborate diagnostic approach is proposed to evaluate twenty-six different transformers in-service to determine their operative status as per the IEC 60599:2022 standard and CIGRE brochure. The approach integrates dissolved gas analysis (DGA), transformer oil integrity analysis, visual inspections, and two Back Propagation Neural Network (BPNN) algorithms to predict the loss of life (LOL) of the transformers through condition monitoring of the cellulose paper. The first BPNN algorithm proposed is based on forecasting the degree of polymerization (DP) using 2-Furaldehyde (2FAL) concentration measured from oil samples using DGA, and the second BPNN algorithm proposed is based on forecasting transformer LOL using the 2FAL and DP data obtained from the first BPNN algorithm. The first algorithm produced a correlation coefficient of 0.970 when the DP was predicted using the 2FAL measured in oil and the second algorithm produced a correlation coefficient of 0.999 when the LOL was predicted using the 2FAL and DP output data obtained from the first algorithm. The results show that the BPNN can be utilized to forecast the DP and LOL of transformers in-service. Lastly, the results are used for hazard analysis and lifespan prediction based on the health index (HI) for each transformer to predict the expected years of service.

show abstract

Section: Methods Used To Investigate Transformers In-servicementioning

confidence: 99%

Application of back propagation neural network in complex diagnostics and forecasting loss of life of cellulose paper insulation in oil-immersed transformers

Ngwenyama,

Gitau

2024

Sci Rep

View full text Add to dashboard Cite

show abstract

“…It threatens the most expensive elements in electric power distribution, such as transformers [ 10 ]. A power transformer, is shown in Fig 1 is considered the backbone and most critical equipment in electrical power conversion, so it requires better stability and reliable protection [ 11 ].…”

Section: Introductionmentioning

confidence: 99%

Sustainable energy management using the Internet of Things (IoT)

Shah

Khan

et al. 2023

PLoS ONE

View full text Add to dashboard Cite

The world has a lot of want for energy due to the rapid pace of its consumption. The world’s energy resources, especially non-renewable sources, are vanishing by leaps and bounds. However, agencies like the Paris Climate Agreement and the United Nations Sustainable development have defined some preventive measures to consider while consuming energy. The main issue in Pakistan is that the consumer is not supplied with electric power in a managed way, and the way of installation causes a lot of impairment to the expensive tools in the power distribution system. The motivation of this research focuses on energy management, making the distribution authority more powerful, digitalization, and protection of expensive components in electrical power systems. The proposed methodology uses current and voltage sensors to remotely monitor the amount of power being supplied to the consumer continuously, along with a microcontroller responsible for activating the relay in case of over-consumption and the Global System for Mobile (GSM) network to warn the consumer and inform the authority. This research work prevents manual and laborious meter readings and protects electrical instruments. Further, this work can enable online billing, pre-paid billing, and energy saving and provide a base for power theft detection.

show abstract

“…In summary, to improve the generalizability of AIbased protection schemes, it is critical to decrease the data ergodicity requirement of AI. In this paper, a novel deep neural network called a denoising-classification neural network (DCNN) is proposed and used to develop an AI-based transformer protection scheme by identifying the exciting voltage-differential current curve (VICur) [27][28][29]. Typical VICurs are shown in Fig.…”

Section: Introductionmentioning

confidence: 99%

A denoising-classification neural network for power transformer protection

Jiao

et al. 2022

Prot Control Mod Power Syst

Self Cite

View full text Add to dashboard Cite

Artificial intelligence (AI) can potentially improve the reliability of transformer protection by fusing multiple features. However, owing to the data scarcity of inrush current and internal fault, the existing methods face the problem of poor generalizability. In this paper, a denoising-classification neural network (DCNN) is proposed, one which integrates a convolutional auto-encoder (CAE) and a convolutional neural network (CNN), and is used to develop a reliable transformer protection scheme by identifying the exciting voltage-differential current curve (VICur). In the DCNN, CAE shares its encoder part with the CNN, where the CNN combines the encoder and a classifier. Based on the interaction of the CAE reconstruction process and the CNN classification process, the CAE regards the saturated features of the VICur as noise and removes them accurately. Consequently, it guides CNN to focus on the unsaturated features of the VICur. The unsaturated part of the VICur approximates an ellipse, and this significantly differentiates between a healthy and faulty transformer. Therefore, the unsaturated features extracted by the CNN help to decrease the data ergodicity requirement of AI and improve the generalizability. Finally, a CNN which is trained well by the DCNN is used to develop a protection scheme. PSCAD simulations and dynamic model experiments verify its superior performance.

show abstract

Knowledge‐based artificial neural network for power transformer protection

Cited by 16 publications

References 53 publications

Application of back propagation neural network in complex diagnostics and forecasting loss of life of cellulose paper insulation in oil-immersed transformers

Application of back propagation neural network in complex diagnostics and forecasting loss of life of cellulose paper insulation in oil-immersed transformers

Sustainable energy management using the Internet of Things (IoT)

A denoising-classification neural network for power transformer protection

Contact Info

Product

Resources

About