^{1}

^{1}

^{1}

^{1}

^{2}

^{1}

^{2}

Effectively extracting power transformer partial discharge (PD) signals feature is of great significance for monitoring power transformer insulation condition. However, there has been lack of practical and effective extraction methods. For this reason, this paper suggests a novel method for the PD signal feature extraction based on multidimensional feature region. Firstly, in order to better describe differences in each frequency band of fault signals, empirical mode decomposition (EMD) and Hilbert-Huang transform (HHT) band-pass filter wave for raw signal is carried out. And the component of raw signals on each frequency band can be obtained. Secondly, the sample entropy value and the energy value of each frequency band component are calculated. Using the difference of each frequency band energy and complexity, signals feature region is established by the multidimensional energy parameters and the multidimensional sample entropy parameters to describe PD signals multidimensional feature information. Finally, partial discharge faults are classified by sphere-structured support vector machines algorithm. The result indicates that this method is able to identify and classify different partial discharge faults.

Power transformer is one of the most critical and expensive electrical pieces of equipment in power system, whose safety and reliability are closely related to the operation condition of the whole system. Furthermore, in the process of actual operation, power transformer is unavoidable to subject to such outside factor influence as electricity, machinery and heat, and so forth further causing its winding insulation deterioration to produce partial discharge (PD) phenomena, threatening the safety of operation of the whole system. Therefore, it is essential to monitor the insulation condition and provide a proper maintenance action for in-service power transformers [

At present, various monitoring and diagnostic techniques have been adopted for power transformers such as visual inspection, infrared scanning,

Accordingly, this paper proposes a new method for power transformer partial discharge fault diagnosis. And this paper content is arranged as such. Section

Transformer PD signal is of strong nonlinearity and time-variation. And in the in situ detection, it is frequently subject to the overlap of many interference signals [

Up to now, feature extraction methods mainly concentrate on the analysis of statistic graphic spectrum and wave shapes [

Unlike classical time-frequency analysis methods using a series of sinusoidal functions to describe a signal, wavelet transform decomposes a signal into wavelet coefficients of various time scales. And it is considered as one of the most powerful techniques for faults signal denoising and extracting transient feature [

Because different insulation defect faults have different partial discharge principle and there are strong randomness and dispersion in its phase distribution, feature frequency, and pulse magnitude, those classical feature extraction methods are not well suitable for online PD faults diagnosis. Moreover, the same insulation defect fault has some similarities on its frequency spectrum envelop and the frequency band energy distribution, whose features have an obvious probability distribution in certain frequency band. So this frequency band can describe different faults signal feature. The magnitude of energy and the complexity of frequency components are two different parameters, which can represent one frequency band from different angles. And literature [

In order to better describe differences in each frequency band of fault signals, the frequency band component of raw signal should be extracted. Now, EMD and HHT band-pass filter are used to extract frequency band component.

EMD is served as a kind of self-adaptive decomposition algorithm without obtaining a priori knowledge of raw signals in advance. And it avoids the optimum base function selection problem of wavelet decomposition [

The algorithm flow process of EMD.

Analog signals given in literature [

The analog signals of PD.

It can be known from Figure

The PD analog signals of EMD decomposition results. Note: in the figure, the scale of the vertical axis

Analog signals served as single exponent attenuation type

Analog signals served as single exponent vibration type

The 2nd-order IMF component 3D time-frequency spectrum.

Analog signals served as single exponent attenuation type

Analog signals served as single exponent vibration type

It can be known from Figure

The order of IMF obtained from PD signals through EMD decomposition is closely related to partial discharge type. And even if they are at the same order of IMF, their frequency band still has the obvious differences.

Aiming at this phenomenon, it is here that HHT band passing filter is adopted to solve the problem. The concrete procedures are as follows:

Sampling frequency of signals

Zero set all the instant amplitude values on the Hilbert time-frequency spectrum except for frequency band

Zero set the IMF component point values which is corresponding to the instant amplitude value being set as zero in

Each IMF component treated using the filter can be reconstructed to obtain signals

As to the rest of frequency bands, the above procedures are repeated. That is, signals

Signals

Different insulation defect faults have different partial discharge principle. And their discharge pulse has obvious difference on the wave shape and the frequency band energy distribution, while the same insulation defect fault has strong similarity on the wave shape and the frequency band energy distribution [

Each row datum of time-frequency matrix

Energy value

The multidimensional energy parameters of PD signals obtained from the above steps are marked as

Sample entropy algorithm is a kind of theory originating from nonlinear dynamics [

Sample entropy of each row datum in time-frequency matrix

It is necessary to determine the dimensional number

where

The maximum difference value between the corresponding elements from

According to the given threshold

where

Take the average of

Change the embedding dimension from

The sample entropy of this row data in the time-frequency matrix

Repeating Step (1) to Step (6) for the rest of other row data in the time-frequency matrix

where

A feature plane is established to describe the PD signals feature from different dimensions. This feature plane consists of the multidimensional energy parameters and the multidimensional sample entropy parameters.

The energy parameter

Finding a minimum circle

The calculation process of feature region.

The feature region of signals.

Support vector machine algorithm is a new machine learning method developed on the statistical study theory. It avoids the network structure selection, overlearning and underlearning, and other problems in artificial neural network algorithm. However, standard SVM is a binary classifier so that it cannot effectively solve multiclass classification [

One multiclassification problem is expressed as follows:

In order to avoid some rough points impact on the algorithm, it is just here that a slack variable

The objective function of the above-mentioned problems should be defined as

Each classification can be described as similar to the quadratic programming problem. Solving this quadratic programming problem can obtain one sphere. And this sphere represents this class. Points on the spherical surface play a key role in spherical determination, called the support vector, as shown in Figure

The sketch of spherical classification.

One set

Firstly, it is necessary to calculate

For

For

For

All spheres including sample

Compare the magnitude of

The schematic diagram of spherical structure classification.

Based on power transformer structure and the different discharge forms of the different insulation defect, transformer partial discharge forms can be divided into the following three types: insulation internal defect (e.g., there are bubbles in insulating oil), surface discharge (e.g., the insulator surface flashover phenomenon), and electrode tip discharge (e.g., the winding tip discharge). The in situ data of 330 kV transformer stations in Gansu province, China, are taken as a real example for carrying out the analysis. Figure

The in situ condition. Note: power transformer (SSP-360 MVA/330 kV) and the UHF sensor parameters: detection sensitivity (−80 dBm~−35 dBm), working voltage (8 V~15 V), working current (120 mA), and output voltage (100 mV~3 V).

Different defect UHF PD sample signals.

The PD signals after filtering and reconstruction.

Since the strongest noise in transformers station mainly concentrates into 10 kHz, the transformers iron-core magnetic noise mainly concentrates into the range of 10–70 kHz [

The feature region within 90% confidence interval of different UHF PD signals.

It can be seen from Figure

Identification results.

Types | Maximum error rate | Average identifying rate |
---|---|---|

Surface discharge | 4.5% | 97.8% |

Electrode tip discharge | 6% | 95.3% |

Insulation internal defect | 4.3% | 96.1% |

It can be seen from Table

Then, two popular approaches of faults classification [

As one can notice from Table

The contrast analysis.

Fault types | Fault classification accuracy (%) | ||
---|---|---|---|

PCA-SVM | Wavelet-SVM | The approach proposed in this paper | |

Surface discharge | 88.7 | 95.9 | 97.8 |

Electrode tip discharge | 88.1 | 97.1 | 95.3 |

Insulation internal defect | 90 | 94.2 | 96.1 |

Power transformer PD signals contain a large amount of insulation state information of power transformer. Effectively extracting signals feature information is of great significance for power transformer insulation online monitoring. In order to effectively extract PD signals feature, this paper suggests a new method. Firstly, using UHF PD signals, different frequency band components construct the time-frequency matrix. And then signals feature region is established by multidimensional energy parameters and multidimensional sample entropy parameters. It is confirmed in Section

The authors declare there are no competing interests regarding the publication of this paper.

This work was supported by the National Natural Science Foundation of China (no. 51279161). Furthermore, the authors are grateful for the staff of China Electric Power Research Institute and State Grid Gansu Province Electric Power Research Institute.