Transformer Condition Monitoring Based on Load-Varied Vibration Response and GRU Neural Networks

Hong, Kaixing; Jin, Ming

doi:10.1109/access.2020.3027834

Cited by 20 publications

(12 citation statements)

References 23 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In order to ensure the safety of the experiment, the input voltage should not exceed 48 V. During the experiment, the fifth coil was selected as point 1, and the symmetric 20-th coil was selected as point 2. According to the FEM simulation results in [14], the location of the measuring point has no effect on the natural frequency change of the obtained vibration. The impact hammer was used to excite the winding in the vertical direction.…”

Section: Methodsmentioning

confidence: 99%

“…However, the assumption that the windings are randomly excited by Gaussian white noise is impossible for field transformers. We have analyzed the influence of the electromagnetic force on the winding modal parameters through experiments and finite element simulation [14,15]. Therefore, it is important to understand the relationship between steady-state vibration and load current for operating transformers.…”

Section: Introductionmentioning

confidence: 99%

“…In our previous studies [14,15], the relationship between load current and natural frequency change under different clamping forces is obtained by finite element simulation and laboratory experiments. In this study, we focus on the amplitude change of the vibration response under harmonic excitations, and the related feature extraction procedure is proposed.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

The vibration response of transformer windings under harmonic excitations and its applications

Hong¹,

Qian²,

Yin³

et al. 2021

J. vibroeng.

Self Cite

View full text Add to dashboard Cite

The power transformer is a key device in the power grid systems. The mechanical degradation of windings represented by the clamping force looseness will cause the decline of the short circuit withstand ability, and cause further damages. This paper proposes a clamping force diagnosis method for operating windings based on the study of the vibration response. In the theory part, the influence of the load current on the natural frequency of windings is discussed, and the influence of the natural frequency change on the steady-state vibration response is studied to obtain the vibration feature related with the clamping force. The subspace method is used to fuse two vibration sequences with the same characteristics to eliminate the measurement error. In the experiment, the free vibration test was performed on a short circuit on-load winding structure. It was proved that the natural frequency change can be extracted from the relationship between the amplitude change of the 100 Hz component and the current change. In the field tests, the vibration sequences of two typical transformers were compared, and the results show that the vibration feature extracted from the relationship between the amplitude variation and the current change contains the structural information of windings.

show abstract

Section: Methodsmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

The vibration response of transformer windings under harmonic excitations and its applications

Hong¹,

Qian²,

Yin³

et al. 2021

J. vibroeng.

Self Cite

View full text Add to dashboard Cite

show abstract

“…Hong K proposed a winding condition evaluation model using vibration signals, which separates winding vibration signals from mixed signals using a fundamental frequency vibration analysis [ 14 ]. In addition, they used a gated recurrent unit (GRU) neural network to explore the relationship between the current sequence and the vibration sequence for operating transformers, suggesting that the electromagnetic force induced by the load current affects the vibration response of the winding structure, especially when the tightening force is significantly loose [ 15 ]. Wang et al obtained the vibration characteristics of winding under normal and loose conditions from the perspective of pad nonlinearity, and they found a correlation between the degree of winding looseness and the 100 Hz octave component in the vibration signal [ 16 ].…”

Section: Introductionmentioning

confidence: 99%

Defect Identification Method for Transformer End Pad Falling Based on Acoustic Stability Feature Analysis

Han

Wang²,

Liao

et al. 2023

Sensors

View full text Add to dashboard Cite

A transformer’s acoustic signal contains rich information. The acoustic signal can be divided into a transient acoustic signal and a steady-state acoustic signal under different operating conditions. In this paper, the vibration mechanism is analyzed, and the acoustic feature is mined based on the transformer end pad falling defect to realize defect identification. Firstly, a quality–spring–damping model is established to analyze the vibration modes and development patterns of the defect. Secondly, short-time Fourier transform is applied to the voiceprint signals, and the time–frequency spectrum is compressed and perceived using Mel filter banks. Thirdly, the time-series spectrum entropy feature extraction algorithm is introduced into the stability calculation, and the algorithm is verified by comparing it with simulated experimental samples. Finally, stability calculations are performed on the voiceprint signal data collected from 162 transformers operating in the field, and the stability distribution is statistically analyzed. The time-series spectrum entropy stability warning threshold is given, and the application value of the threshold is demonstrated by comparing it with actual fault cases.

show abstract

“…The recent research shows that the vibration of transformers is strongly related to the mechanical properties of windings [2]. Therefore, more attentions have been paid to transformers vibration signal analysis [3,4].…”

Section: Introductionmentioning

confidence: 99%

A Novel Feature Extraction Method for Power Transformer Vibration Signal Based on CEEMDAN and Multi-Scale Dispersion Entropy

Shang

et al. 2021

Entropy

View full text Add to dashboard Cite

Effective diagnosis of vibration fault is of practical significance to ensure the safe and stable operation of power transformers. Aiming at the traditional problems of transformer vibration fault diagnosis, a novel feature extraction method based on complete ensemble empirical mode decomposition with adaptive noise (CEEMDAN) and multi-scale dispersion entropy (MDE) was proposed. In this paper, CEEMDAN method is used to decompose the original transformer vibration signal. Additionally, then MDE is used to capture multi-scale fault features in the decomposed intrinsic mode functions (IMFs). Next, the principal component analysis (PCA) method is employed to reduce the feature dimension and extract the effective information in vibration signals. Finally, the simplified features are sent into density peak clustering (DPC) to get the fault diagnosis results. The experimental data analysis shows that CEEMDAN-MDE can effectively extract the information of the original vibration signals and DPC can accurately diagnose the types of transformer faults. By comparing different algorithms, the practicability and superiority of this proposed method are verified.

show abstract

Transformer Condition Monitoring Based on Load-Varied Vibration Response and GRU Neural Networks

Cited by 20 publications

References 23 publications

The vibration response of transformer windings under harmonic excitations and its applications

The vibration response of transformer windings under harmonic excitations and its applications

Defect Identification Method for Transformer End Pad Falling Based on Acoustic Stability Feature Analysis

A Novel Feature Extraction Method for Power Transformer Vibration Signal Based on CEEMDAN and Multi-Scale Dispersion Entropy

Contact Info

Product

Resources

About