CN110796206A - A data enhancement method and device for partial discharge map - Google Patents

Abstract

The invention proposes a data enhancement method and device for partial discharge atlas. On the basis of adding common noises such as mobile phone interference, radar interference, and microwave sulfur lamp interference, the Gaussian blurring method is applied to randomly perturb RGB pixels for the purpose of Train a network that generalizes better. By using background noise coupling and Gaussian blur to preprocess the partial discharge map, one map can generate multiple maps, and a large number of labeled samples can be generated with a small amount of calculation, which solves the problem of the high cost of obtaining labeled samples and the need for training. The problem of insufficient data; on the basis of the original data samples, the common disturbance on the site is considered, and the real field data is simulated to increase the anti-interference ability of the training model; the diversity of the training data is expanded, and the model is trained with the expanded training data. , to avoid overfitting of the model.

Description

A data enhancement method and device for partial discharge map

technical field

The present invention relates to the field of partial discharge detection, and more particularly, to a data enhancement method for partial discharge maps.

Background technique

With the development of smart grids, the demand for data diagnostics is increasing. Machine learning diagnosis is an alternative to manual diagnosis. When building a machine learning model to train and verify data, how to quickly, efficiently and conveniently obtain a large number of labeled training samples is an urgent problem to be solved.

Partial discharge pattern recognition requires a large number of labeled training samples. The collection process of labeled samples is expensive, and it is often difficult to quickly accumulate enough samples to support training for the low-frequency partial discharge phenomenon. In traditional partial discharge data enhancement methods, simple processing methods such as translation, rotation, and scaling are generally used. The graph data processed in these ways: 1) The possible interference of the data in the real business situation is not considered; 2) The data enhancement method based on shape processing does not expand the data pixels, and the trained model is only suitable for the specified color and specification. images, which generalize poorly to data from different sources.

SUMMARY OF THE INVENTION

In order to overcome the defects in the prior art, the present invention uses methods such as background noise coupling and Gaussian blur to preprocess the partial discharge atlas, so that one atlas can generate multiple atlases. The method that can solve the problem of insufficient data in the identification of partial discharge maps can increase the number of samples and avoid overfitting by generating multiple maps from one map.

The invention designs a data enhancement method and device based on noise disturbance and Gaussian blurring. The Gaussian blurring method is applied on the basis of adding common noises such as mobile phone interference, radar interference, and microwave sulfur lamp interference to randomly disturb RGB pixels. It is used to train a network with stronger generalization ability.

Specifically, the data enhancement method for partial discharge atlas of the present invention utilizes background noise coupling and Gaussian blurring to preprocess the partial discharge atlas, so that one atlas can generate multiple atlas, including the following steps:

S1: Perform noise coupling on the original data of partial discharge to generate image files;

S2: The image file after noise coupling is further processed by the Gaussian blur method;

S3: Combine noise-coupling, Gaussian blurred samples and original samples for training of deep learning network models.

The first step specifically includes:

S11: Use the original partial discharge data collected by the collection front end as input data;

S12: Convert the input data into three-dimensional data;

S13: According to the data characteristics of noise interference, generate three-dimensional data corresponding to each noise respectively;

S14: Accumulate the input data and the noise data to obtain the noise-coupled data;

S15: Convert the noise-coupled data into a picture file.

further,

The three-dimensional data takes the phase as the x-axis, the period as the y-axis, and the amplitude as the z-axis.

further,

The noise interference includes radar noise, mobile phone noise, and microwave sulfur lamp interference.

Further, step 2 specifically includes:

S21: The image file after noise coupling in step 1 is used as input data;

S22: Extract the RGB (Red, Green, Blue) values of the input image file;

S23: respectively take the center point of the picture in the picture file as the zero point, and draw the horizontal and vertical axes;

S24: Calculate the weight of each pixel in the image with a two-dimensional Gaussian distribution function to form a weight matrix;

S25: normalize the weight matrix;

S26: Update the RGB value of the image file with the normalized weight;

S27: Store the image file after updating the RGB value as a new sample.

further,

The two-dimensional Gaussian distribution function described in step S24 is as follows:

In the formula, x and y are the horizontal and vertical coordinates of each pixel in the figure from the zero point, G(x, y) is the weight value from the point to the zero point, π is the pi, e is the natural constant, and σ is the normal distribution. Standard deviation, σ usually ranges from 1 to 3, the larger the value, the smoother the image.

further,

In step S25, normalizing the weight matrix includes:

Calculate the sum m of all weight values in the weight matrix, multiply each weight value in the weight matrix by 1/m, and obtain the normalized weight matrix.

Further, in step S26,

For the weight matrix of each zero point, the weight value of each normalized weight matrix is multiplied by the pixel value of the weight value position, and the sum is used as the new pixel value of the zero point. The RGB values are updated respectively to obtain the updated three-color pixel values.

The present invention also provides a data enhancement device for partial discharge atlas, including:

A noise coupling module, a Gaussian blurring module and a sample generating module, wherein the output of the noise coupling module is connected with the input of the Gaussian blurring module, the output of the Gaussian module is connected with the sample generating module, and the partial discharge map is performed by using the background noise coupling and the Gaussian blurring method. Preprocessing enables one map to generate multiple maps.

further,

The noise coupling module includes a data input module, a 3D data generation module, a data coupling module and a picture conversion module, wherein the output of the data input module is connected with the input of the 3D data generation module, and the output of the 3D data generation module is connected with the input of the data coupling module. The output of the data coupling module is connected with the input of the picture conversion module.

further,

The data input module inputs the original partial discharge data collected by the collection front end.

further,

The three-dimensional data generation module converts the input data into three-dimensional data with the phase as the x-axis, the period as the y-axis, and the amplitude as the z-axis; and according to the data characteristics of radar noise, mobile phone noise, and microwave sulfur lamp interference, respectively 3D data corresponding to each noise.

further,

The data coupling module accumulates the three-dimensional data of the input data and the noise data to obtain noise-coupled data.

further,

The picture conversion module converts the noise-coupled data into a picture file.

further,

The Gaussian blurring module includes a pixel extraction module, a weight matrix generation module, a weight update module and a file generation module, wherein the output of the picture conversion module is connected to the input of the pixel extraction module, and the output of the pixel extraction module is connected to the weight matrix to generate The input of the module and the output of the weight matrix generation module are connected to the input of the weight update module, and the output of the weight update module is connected to the input of the file generation module to perform Gaussian blurring on the noise-coupled picture.

Further, the pixel extraction module inputs a picture file converted by the picture conversion module, and extracts RGB (Red, Green, Blue) values of the picture file.

further,

The weight matrix generation module takes the center point of the picture in the picture file as the zero point, respectively, and draws the horizontal and vertical axes;

Calculate the weight of each pixel in the picture with a two-dimensional Gaussian distribution function, form a weight matrix, and further obtain a normalized weight matrix.

further,

The two-dimensional Gaussian distribution function is as follows:

In the formula, x and y are the horizontal and vertical coordinates of each pixel in the figure from the zero point, G(x, y) is the weight value from the point to the zero point, π is the pi, e is the natural constant, and σ is the normal distribution. Standard deviation, σ usually ranges from 1 to 3, the larger the value, the smoother the image.

further,

The normalized weight matrix specifically includes:

Calculate the sum m of all weight values in the weight matrix, multiply each weight value in the weight matrix by 1/m, and obtain the normalized weight matrix.

further,

The weight updating module updates the RGB value of the picture file with the weight.

further,

Updating the RGB values of the image with weights specifically includes:

For the weight matrix of each zero point, the weight value of each normalized weight matrix is multiplied by the pixel value of the weight value position, and the sum is used as the new pixel value of the zero point. The RGB values are updated respectively to obtain the updated three-color pixel values.

further,

The file generation module stores the image file after updating the RGB value as a new sample.

further,

The sample generation module combines the noise-coupling, Gaussian blurred samples and the original samples for training of the deep learning network model.

Compared with directly using samples as training data, the method described in the present invention has the following advantages:

(1) Generate a large number of labeled samples with less computation, which solves the problems of high cost of obtaining labeled samples and insufficient training data;

(2) On the basis of the original data samples, the common disturbances in the field are considered, the real field data is simulated, and the anti-interference ability of the training model is increased;

(3) Expand the diversity of training data, from basic samples to multi-pixel and multi-shape samples. Training the model with the expanded training data can avoid overfitting of the model.

Description of drawings

Fig. 1 is a flow chart of a data enhancement method based on noise disturbance and Gaussian blur of the present invention.

FIG. 2 is a schematic diagram of a data enhancement device based on noise disturbance and Gaussian blur according to the present invention.

Figure 3 is an unprocessed 3D image of the raw data.

Figure 4 is the image file after the noise is superimposed.

Figure 5 is the image file after superimposed Gaussian blur.

Detailed ways

In order to make the purpose, technical solutions and advantages of the embodiments of the present invention clearer, the technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings of the embodiments of the present invention. Obviously, the described embodiments are some, but not all, embodiments of the present invention. Based on the described embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art fall within the protection scope of the present invention.

Referring to the flowchart shown in FIG. 1 , the technical solution adopted in the present invention is a data enhancement method based on noise disturbance and Gaussian blurring for partial discharge maps, comprising the following steps:

(1) Noise coupling

①The input data is the original partial discharge data collected by the front-end;

② Convert the input data into three-dimensional data with the phase as the x-axis, the period as the y-axis, and the amplitude as the z-axis;

③ According to the data characteristics of radar noise, mobile phone noise, and microwave sulfur lamp interference, generate three-dimensional data corresponding to each noise respectively;

④ Accumulate the three-dimensional data of the input data and the noise data to obtain the data after noise coupling;

⑤ Convert the noise-coupled data into image files.

(2) Gaussian blur

①The input data is the image file after noise coupling;

② Extract the RGB (Red, Green, Blue) values of the input image file;

③ Take the center point of the picture in the picture file as the zero point, and draw the horizontal and vertical axes; calculate the weight matrix of each pixel in the picture with the two-dimensional Gaussian distribution function, and the two-dimensional Gaussian distribution is as follows:

In the formula, x and y are the horizontal and vertical coordinates of each pixel in the figure from the zero point, G(x, y) is the weight value from the point to the zero point, π is the pi, e is the natural constant, and σ is the normal distribution. Standard deviation, σ usually takes between 1 and 3, the larger the value, the smoother the image;

Taking an image of 3*3 pixels as an example, when the point in the image is zero, the (x, y) values of each point are shown in the following table:

(-1, 1) (0,1) (1,1) (-1, 0) (0,0) (1,0) (-1, -1) (0, -1) (1, -1)

Take σ as 1.5, and calculate the weights for each group (x, y). The results are shown in the following table:

0.04535 0.05664 0.04535 0.05664 0.07074 0.05664 0.04535 0.05664 0.04535

④ Normalize the weight matrix: calculate the sum m of all weight values in the weight matrix, multiply each weight value in the weight matrix by 1/m, and obtain the normalized weight matrix;

⑤Update the RGB value of the image file with the weight:

For the weight matrix of each zero point, the weight value of each normalized weight matrix is multiplied by the pixel value of the weight value position, and the sum is used as the new pixel value of the zero point. The RGB values are updated respectively to obtain the updated three-color pixel values;

⑥ Store the image file after updating the RGB value as a new sample.

(3) Combine the noise coupling, Gaussian blurred samples and the original samples into a new sample set for training the deep learning network model.

Referring to FIG. 2, the present invention also proposes a data enhancement device based on noise disturbance and Gaussian blurring, including: a noise coupling module, a Gaussian blurring module and a sample generation module.

The noise coupling module includes a data input module, a three-dimensional data generation module, a data coupling module and a picture conversion module.

Data input module, input the original partial discharge data collected by the front-end;

The three-dimensional data generation module converts the input data into three-dimensional data with the phase as the x-axis, the period as the y-axis, and the amplitude as the z-axis; and according to the data characteristics of radar noise, mobile phone noise, and microwave sulfur lamp interference, each noise is generated separately. Corresponding 3D data;

The data coupling module accumulates the input data and the noise data to obtain the data after noise coupling;

The image conversion module converts the noise-coupled data into image files.

The Gaussian Blur module includes:

Pixel extraction module, input the image file after noise coupling, and extract the RGB (Red, Green, Blue) value of the input image file;

The weight matrix generation module takes the center point of the picture in the picture file as the zero point, and draws the horizontal and vertical axes; calculates the weight of each pixel in the picture with a two-dimensional Gaussian distribution function, forms a weight matrix, and further obtains the normalized weight matrix.

The weight update module updates the RGB value of the image file with the weight;

For the weight matrix of each zero point, the weight value of each normalized weight matrix is multiplied by the pixel value of the weight value position, and the sum is used as the new pixel value of the zero point. The RGB values are updated respectively to obtain the updated three-color pixel values.

The file generation module stores the image file after updating the RGB value as a new sample.

The sample generation module combines noise-coupling, Gaussian blurred samples and original samples for training of deep learning network models.

Example

The method of the present invention is further described below with reference to FIGS. 3-5 given practical application data.

The data enhancement method based on noise disturbance and Gaussian blurring for a partially enlarged atlas according to the present invention includes:

A piece of PD raw data is collected, and its unprocessed 3D image is shown in Figure 3.

The original sample data is superimposed on the noise interference of lights, radar and mobile phones, and the data after the superimposed interference is three-dimensionally processed to obtain the image file after the noise is superimposed, as shown in Figure 4.

Take σ as 1.5, calculate the Gaussian weight matrix for the RGB three pigments of the image file after noise superposition, and superimpose the Gaussian blur to obtain the image file as shown in Figure 5.

Combine the Gaussian blurred image file and the original file into the sample library to complete a data enhancement based on noise superposition and Gaussian blurring.

It can be seen that, compared with directly using samples as training data, the present invention can generate a large number of labeled samples with less calculation amount, and on the basis of the original data samples, common disturbances in the field are considered, and the data in the identification of partial discharge maps can be solved. The insufficient method, by generating multiple maps from one map, increases the number of samples and avoids overfitting.

The applicant has described and described the embodiments of the present invention in detail with reference to the accompanying drawings, but those skilled in the art should understand that the above embodiments are only preferred embodiments of the present invention, and the detailed description is only to help readers better understand The spirit of the present invention is not intended to limit the protection scope of the present invention. On the contrary, any improvement or modification made based on the spirit of the present invention should fall within the protection scope of the present invention.

Claims (23)

1. A data enhancement method for a partial discharge map is characterized in that the partial discharge map is preprocessed by using a background noise coupling and Gaussian blur method, so that a plurality of maps can be generated by one map, and the method comprises the following steps:

s1: carrying out noise coupling on the partial discharge original data to generate a picture file;

s2: further processing the picture file after noise coupling by adopting a Gaussian blur method;

s3: and combining the samples subjected to noise coupling and Gaussian blur and the original samples for training the deep learning network model.

2. The method according to claim 1, wherein step one comprises in particular:

s11: taking the partial discharge original data acquired by the acquisition front end as input data;

s12: converting input data into three-dimensional data;

s13: respectively generating three-dimensional data corresponding to each noise according to the data characteristics of the noise interference;

s14: accumulating the input data and the noise data to obtain data after noise coupling;

s15: and converting the data after the noise coupling into a picture file.

3. The method of claim 2,

the three-dimensional data takes the phase as an x-axis, the period as a y-axis and the amplitude as a z-axis.

4. The method of claim 2,

the noise interference comprises radar noise, mobile phone noise and microwave sulfur lamp interference.

5. The method according to one of claims 1 to 4, characterized in that step two comprises in particular:

s21: taking the picture file after noise coupling in the step one as input data;

s22: extracting RGB (Red, Green, Blue) values of an input picture file;

s23: respectively taking the central point of the picture in the picture file as a zero point, and drawing horizontal and vertical coordinate axes;

s24: calculating the weight of each pixel point in the picture by using a two-dimensional Gaussian distribution function to form a weight matrix;

s25: carrying out normalization processing on the weight matrix;

s26: updating the RGB value of the picture file by the normalized weight;

s27: and storing the picture file with the updated RGB values as a new sample.

6. The method according to claim 5, wherein the two-dimensional Gaussian distribution function in step S24 is as follows:

in the formula, x and y are horizontal and vertical coordinates of each pixel point in the graph from a zero point, G (x and y) is a weight value from the point to the zero point, pi is a circumferential rate, e is a natural constant, sigma is a standard deviation of normal distribution, sigma is generally between 1 and 3, and the image is smoother when the value is larger.

7. The method according to claim 5 or 6, wherein the step S25, the normalization of the weight matrix comprises:

and calculating the sum m of all weight values in the weight matrix, and multiplying each weight value in the weight matrix by 1/m to obtain the normalized weight matrix.

8. The method according to claim 7, wherein, in step S26,

and for the weight matrix of each zero point, multiplying the weight value of each normalized weight matrix by the pixel value at the position of the weight value, summing the pixel values to serve as a new pixel value of the zero point, and respectively updating the RGB values by the weight updating method to obtain an updated three-color pixel value.

9. A data enhancement apparatus for a partial discharge map, comprising:

the device comprises a noise coupling module, a Gaussian blur module and a sample generation module, wherein the output of the noise coupling module is connected with the input of the Gaussian blur module, the output of the Gaussian blur module is connected with the sample generation module, and a partial discharge map is preprocessed by using a background noise coupling and Gaussian blur method, so that a plurality of maps can be generated by one map.

10. The apparatus of claim 9,

the noise coupling module comprises a data input module, a three-dimensional data generation module, a data coupling module and a picture conversion module, wherein the output of the data input module is connected with the input of the three-dimensional data generation module, the output of the three-dimensional data generation module is connected with the input of the data coupling module, and the output of the data coupling module is connected with the input of the picture conversion module.

11. The apparatus of claim 10,

and the data input module is used for inputting the partial discharge original data acquired by the acquisition front end.

12. The apparatus of claim 11,

the three-dimensional data generation module converts input data into three-dimensional data with the phase as an x axis, the period as a y axis and the amplitude as a z axis; and respectively generating three-dimensional data corresponding to each noise according to the data characteristics of radar noise, mobile phone noise and microwave sulfur lamp interference.

13. The apparatus of claim 12,

and the data coupling module accumulates the three-dimensional data of the input data and the noise data to obtain data after noise coupling.

14. The apparatus of claim 13,

and the picture conversion module is used for converting the data after the noise coupling into a picture file.

15. The apparatus according to claim 14, wherein the gaussian blur module comprises a pixel extraction module, a weight matrix generation module, a weight update module and a file generation module, wherein an output of the picture conversion module is connected to an input of the pixel extraction module, an output of the pixel extraction module is connected to an input of the weight matrix generation module, an output of the weight matrix generation module is connected to an input of the weight update module, and an output of the weight update module is connected to an input of the file generation module, and is configured to perform gaussian blur processing on the noise-coupled picture.

16. The apparatus of claim 15,

the pixel extraction module inputs the picture file converted by the picture conversion module and extracts the RGB (Red, Green, Blue) value of the picture file.

17. The apparatus of claim 16,

the weight matrix generation module is used for respectively taking the central point of the picture in the picture file as a zero point and drawing a horizontal axis and a vertical axis; and calculating the weight of each pixel point in the picture by using a two-dimensional Gaussian distribution function to form a weight matrix, and further obtaining a normalized weight matrix.

18. The apparatus of claim 17,

the two-dimensional gaussian distribution function is as follows:

in the formula, x and y are horizontal and vertical coordinates of each pixel point in the graph from a zero point, G (x and y) is a weight value from the point to the zero point, pi is a circumferential rate, e is a natural constant, sigma is a standard deviation of normal distribution, sigma is generally between 1 and 3, and the image is smoother when the value is larger.

19. The apparatus of claim 18,

the obtaining of the normalized weight matrix specifically includes:

and calculating the sum m of all weight values in the weight matrix, and multiplying each weight value in the weight matrix by 1/m to obtain the normalized weight matrix.

20. The apparatus of claim 19,

and the weight value updating module updates the RGB value of the picture file by weight.

21. The apparatus of claim 20,

updating the RGB values of the picture with the weights specifically includes:

and for the weight matrix of each zero point, multiplying the weight value of each normalized weight matrix by the pixel value at the position of the weight value, summing the pixel values to serve as a new pixel value of the zero point, and respectively updating the RGB values by the weight updating method to obtain an updated three-color pixel value.

22. The apparatus of claim 21,

and the file generation module is used for storing the picture file with the updated RGB value as a new sample.

23. The apparatus of claim 22,

and the sample generation module is used for combining the noise-coupled and Gaussian-fuzzy sample and the original sample and is used for training the deep learning network model.

Images