Minor fault diagnosis of transformer winding using polar plot based on frequency response analysis

Li, Zihao; He, Yigang; Xing, Zhikai; Chen, Mingyun

doi:10.1016/j.ijepes.2023.109173

Cited by 5 publications

(2 citation statements)

References 29 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Still, a long time in the fault state of operation will gradually affect the power grid's power supply, leading to widespread power outages and severe economic losses [6][7][8]. Therefore, effective fault diagnosis technology to improve the level of operation and maintenance is of vital significance [9][10][11].…”

Section: Introductionmentioning

confidence: 99%

Transformer Fault Diagnosis Method Based on TimesNet and Informer

Zhang,

Yang,

Zheng

2024

Actuators

View full text Add to dashboard Cite

Since the traditional transformer fault diagnosis method based on dissolved gas analysis (DGA) is challenging to meet today’s engineering needs, this paper proposes a multi-model fusion transformer fault diagnosis method based on TimesNet and Informer. First, the original TimesNet structure is improved by adding the MCA module to the Inception structure of the original TimesBlock to reduce the model complexity and computational burden; second, the MUSE attention mechanism is introduced into the original TimesNet to act as a bridge, so that associations can be carried out effectively among the local features, thus enhancing the modeling capability of the model; finally, when constructing the feature module, the TimesNet and Informer multilevel parallel feature extraction modules are introduced, making full use of the local features of the convolution and the global correlation of the attention mechanism module for feature summarization, so that the model learns more time-series information. To verify the effectiveness of the proposed method, the model is trained and tested on the public DGA dataset, and the model is compared and experimented with classical models such as Informer and Transformer. The experimental results show that the model has a strong learning ability for transformer fault data and has an advantage in accuracy compared with other models, which can provide a reference for transformer fault diagnosis.

show abstract

Section: Introductionmentioning

confidence: 99%

Transformer Fault Diagnosis Method Based on TimesNet and Informer

Zhang,

Yang,

Zheng

2024

Actuators

View full text Add to dashboard Cite

show abstract

“…The studies referenced in Refs. [18][19][20][21][22][23][24][25][26][27][28][29] elaborate on the representation of FRA for a power transformer's magnetic core and winding structure. This representation involves a sophisticated electrical network that includes series resistances, self-inductances, mutual inductance between sections, ground capacitances, capacitance between windings, and series capacitances.…”

mentioning

confidence: 99%

Derivation of transformer winding equivalent circuit by employing the transfer function obtained from frequency response analysis data

Zhang

2024

IET Electric Power Appl

View full text Add to dashboard Cite

Precisely interpreting frequency response analysis (FRA) curves is crucial when investigating mechanical malfunctions in power transformer windings (TWs). However, many conventional explanations of FRA features cannot be validated by an equivalent circuit (EC) that represents winding structures using resistance, inductance, and capacitance components in a ladder network. Incorrect interpretation can lead to misdiagnosis and confusion in asset management. Previous ECs are often proposed by analysing winding structures without rigorous verification compared to the corresponding FRA data. The specific EC is acquired using the transfer function (TF) derived from the measured FRA data. This allows for the establishment of the relationship between TW FRA curves, TF equations, and EC topologies. The precise interpretation of FRA curves can be achieved by closely observing the FRA curves created from TFs and ECs. The remarkable similarity between the measured and modelled FRA curves verifies the authenticity of the derived ECs. This significant achievement clarifies many misunderstandings regarding FRA and represents a substantial advancement in FRA technology.

show abstract