阅读说明：本技术 基于电缆涂层感温变色的电缆检测装置及其检测方法 (Cable detection device based on temperature-sensitive color change of cable coating and detection method thereof ) 是由 陈江 张继武 肖遥王戈 李迅 李智欣 朱程雯 于 2020-06-02 设计创作，主要内容包括：本发明公开了一种基于电缆涂层感温变色的电缆检测装置及其检测方法,装置中,包括：电缆涂层包括基于温度变化而变色的微胶囊,数据采集单元拍摄所述电缆涂层生成图像数据,神经网络训练单元连接所述数据采集单元以接收图像数据,所述神经网络单元建立神经网络模型以训练图像样本,相关性分析单元配置成生成颜色与电缆温度之间的相关系数,主成分分析单元提取图像数据的主要特征分量以降维生成主成分,训练单元基于所述主成分训练图像样本以得到电缆状态与温度的关系曲线,检测单元连接所述神经网络训练单元以基于所述相关系数和关系曲线得到电缆状态基于颜色的变化曲线。(The invention discloses a cable detection device based on temperature-sensitive discoloration of a cable coating and a detection method thereof, wherein the device comprises the following components: the cable coating comprises microcapsules changing colors based on temperature changes, a data acquisition unit shoots the cable coating to generate image data, a neural network training unit is connected with the data acquisition unit to receive the image data, the neural network unit establishes a neural network model to train an image sample, a correlation analysis unit is configured to generate a correlation coefficient between the colors and the cable temperature, a principal component analysis unit extracts principal characteristic components of the image data to reduce the dimensions to generate principal components, the training unit trains the image sample based on the principal components to obtain a relation curve of the cable state and the temperature, and a detection unit is connected with the neural network training unit to obtain a change curve of the cable state based on the colors based on the correlation coefficient and the relation curve.)

1. A cable detection device based on temperature-sensing color change of a cable coating comprises,

cable coating comprising microcapsules which change color on the basis of a change in temperature,

a data acquisition unit that photographs the cable coating to generate image data,

a neural network training unit connected to the data acquisition unit to receive image data, the neural network unit building a neural network model to train image samples, comprising,

a correlation analysis unit configured to generate a correlation coefficient between the color and the cable temperature,

a principal component analysis unit that extracts principal feature components of the image data to generate principal components in a dimension reduction,

a training unit for training the image sample based on the principal component to obtain a cable state versus temperature curve,

and the detection unit is connected with the neural network training unit to obtain a cable state color-based change curve based on the correlation coefficient and the relation curve.

2. The cable detection device according to claim 1, wherein the data acquisition unit preferably comprises a color space transformation module configured to transform the input region image data from an RGB color space to an HSV color space, the image data comprising red R, green G, blue B, chromaticity H, saturation S, and luminance V parameters.

3. The cable detection apparatus of claim 1, wherein a histogram transformation module is disposed between the data acquisition unit and the neural network training unit, and retains image data related to the cable based on the received image data.

4. The cable detection device according to claim 1, wherein a region segmentation unit is provided between the data acquisition unit and the neural network training unit, and performs multichannel significance transformation on the image data to perform region segmentation, and removes part of edge background and other regions interfering with color identification so as to retain the image data of the cable fault coating color rendering region.

5. The cable detection apparatus according to claim 4, wherein the area division unit includes,

an R-channel saliency detection module that generates an R-channel saliency detection feature map based on the image data,

a G-channel saliency detection module that generates a G-channel saliency detection feature map based on the image data,

a B-channel saliency detection module that generates a B-channel saliency detection feature map based on the image data,

a multi-channel histogram transformation module that generates a histogram based on the image data,

a fusion selector that selects image data relating to the cable according to a saliency value range of the cable based on the multi-channel histogram transformation module, the G-channel saliency detection feature map, the B-channel saliency detection feature map, and the histogram,

a multi-channel fused feature module that generates a multi-channel fused feature map based on the selected cable-related image data fusion,

a binarization threshold selector that performs binarization processing based on the selected cable-related image data,

and the multi-channel detection module is connected with the multi-channel fusion feature module and the binarization threshold selector to generate regional image data representing the color of the cable coating failure main body based on the multi-channel detection module and the binarization result.

6. The cable detection device of claim 1, wherein the cable status of the sample is detected via a current detection device.

7. The cable detection device of claim 1, wherein the microcapsule encapsulates the invisible dye, the color former, and the temperature control agent.

8. The cable detection apparatus according to claim 1, wherein the correlation analysis unit includes a Pearson correlation coefficient module.

9. A method of testing a cable testing device according to any one of claims 1 to 8, comprising the steps of,

the cable is coated with a cable coating comprising microcapsules that change color based on a change in temperature,

the data acquisition unit shoots the cable coating to generate image data,

a region division unit region-divides the image data to generate image data,

the neural network unit establishes a neural network model to train an image sample, wherein the correlation analysis unit generates a correlation coefficient between color and cable temperature, the principal component analysis unit extracts principal characteristic components of image data to reduce dimensions and generate principal components, the training unit trains the image sample based on the principal components to obtain a relation curve between the cable state and the temperature,

and the detection unit obtains a change curve of the cable state based on the color based on the correlation coefficient and the relation curve.

Technical Field

The invention belongs to the technical field of cable detection, and particularly relates to a cable detection device based on temperature-sensitive color change of a cable coating and a detection method thereof.

Background

With the development of social economy, in recent years, the power load is continuously increased, however, due to the limitation of factors such as economic cost, social environment, project cycle and the like, the updating speed of the distribution network equipment cannot catch up with the increasing speed of the power load, so that the overload use condition of the power equipment is increasingly frequent, the safety accidents on the distribution network side frequently occur, the potential safety hazards are increasingly increased, and higher requirements are provided for the safe and reliable operation of the distribution network. Due to the limitation of geographical conditions and misunderstanding of electromagnetic radiation by people, the capacity expansion of a power system is difficult, and the power supply pressure is high during the summer period of the peak-to-peak degree. Through actual research and analysis, among numerous potential safety hazards, the insulation problem of distribution network equipment, the high temperature rise of the whole switch cabinet caused by the heating of contacts in the switch cabinet, the easy condensation of the switch cabinet and the like are main factors of failure occurrence.

At present, distribution network equipment mainly adopts an insulating sleeve made of silica gel materials to insulate an incoming and outgoing line, and the traditional sleeve has the problems of poor hydrophobicity, untight combination with the incoming and outgoing line and the like, so that the insulating effect is easily lost. It mainly shows that: (1) poor heat conduction performance causes a heat aging problem, leads to cracking of the insulating sheath, and introduces potential safety hazards; (2) the self-cleaning performance is poor, so that dust is adsorbed electrostatically, the hydrophobicity of the material is reduced, and the insulation problem is caused; (3) the maintainability is poor. Although the problem can be partially solved by adopting the insulating coating, the material is volatile and ineffective, and the problem of insulating damage in a distribution network is difficult to visually find. When operation and maintenance personnel carry out field maintenance, the fault phenomenon and the fault position are monitored mainly by a temperature measuring instrument, however, the traditional temperature measuring instrument has high equipment cost and low reliability. There is a lack of means for the maintenance personnel to visually detect the failure in the first place, and therefore it is urgent to develop an overall solution to the problem.

This information disclosed in the background section is only for enhancement of understanding of the background of the invention and therefore it may contain information that does not form the prior art that is already known in this country to a person of ordinary skill in the art.

Disclosure of Invention

The invention provides a cable detection device based on temperature-sensitive color change of a cable coating and a detection method thereof, aiming at the problems in the prior art, the cable coating is a solvent-free composite material with functions of corrosion resistance, hydrophobicity, insulation and color change indication, and is applied to a cable insulation layer of main equipment of a distribution network. The novel insulating material who uses can show different colours according to equipment temperature, has realized the visual monitoring of intelligence to the equipment state, improves the safe and reliable economic nature of joining in marriage net operation, has wide market perspective.

The invention aims to realize the purpose through the following technical scheme, and the cable detection device based on the temperature-sensing color change of the cable coating comprises:

cable coating comprising microcapsules which change color on the basis of a change in temperature,

a data acquisition unit that photographs the cable coating to generate image data,

a neural network training unit connected to the data acquisition unit to receive image data, the neural network unit building a neural network model to train image samples, comprising,

a correlation analysis unit configured to generate a correlation coefficient between the color and the cable temperature,

a principal component analysis unit that extracts principal feature components of the image data to generate principal components in a dimension reduction,

a training unit for training the image sample based on the principal component to obtain a cable state versus temperature curve,

and the detection unit is connected with the neural network training unit to obtain a cable state color-based change curve based on the correlation coefficient and the relation curve.

In the cable detection device, the data acquisition unit comprises a color space transformation module which is configured to transform input area image data from an RGB color space to an HSV color space, wherein the image data comprises red R, green G, blue B, chroma H, saturation S and brightness V parameters.

In the cable detection device, a histogram transformation module is arranged between a data acquisition unit and a neural network training unit and used for retaining image data related to a cable based on the received image data.

In the cable detection device, an area segmentation unit is arranged between a data acquisition unit and a neural network training unit and is used for performing multichannel significance transformation on image data to segment the area, and removing partial edge background and other areas interfering with color identification so as to retain the image data of a cable fault coating color development area.

In the cable detection device, the area dividing unit comprises,

an R-channel saliency detection module that generates an R-channel saliency detection feature map based on the image data,

a G-channel saliency detection module that generates a G-channel saliency detection feature map based on the image data,

a B-channel saliency detection module that generates a B-channel saliency detection feature map based on the image data, a multi-channel histogram transformation module that generates a histogram based on the image data,

a fusion selector that selects image data relating to the cable according to a saliency value range of the cable based on the multi-channel histogram transformation module, the G-channel saliency detection feature map, the B-channel saliency detection feature map, and the histogram,

a multi-channel fused feature module that generates a multi-channel fused feature map based on the selected cable-related image data fusion,

a binarization threshold selector that performs binarization processing based on the selected cable-related image data,

and the multi-channel detection module is connected with the multi-channel fusion feature module and the binarization threshold selector to generate regional image data representing the color of the cable coating failure main body based on the multi-channel detection module and the binarization result.

In the cable detection device, the cable state of the sample is detected by a current detection device.

In the cable detection device, the microcapsule coats the invisible dye, the color forming agent and the temperature control agent.

In the cable detection device, the correlation analysis unit comprises a Pearson correlation coefficient module.

According to another aspect of the present invention, a method for testing a cable testing device includes the steps of coating a cable with a cable coating including microcapsules that change color based on a change in temperature,

the data acquisition unit shoots the cable coating to generate image data,

a region division unit region-divides the image data to generate image data,

the neural network unit establishes a neural network model to train an image sample, wherein the correlation analysis unit generates a correlation coefficient between color and cable temperature, the principal component analysis unit extracts principal characteristic components of image data to reduce dimensions and generate principal components, the training unit trains the image sample based on the principal components to obtain a relation curve between the cable state and the temperature,

and the detection unit obtains a change curve of the cable state based on the color based on the correlation coefficient and the relation curve.

Compared with the prior art, the invention has the following advantages:

the invention overcomes the problem that factors such as image background, non-fault color area of cable coating and the like influence the accuracy of positioning and segmentation, and the condition that dust accumulation of the cable year round and color disintegration caused by coating oxidation and color change under different illumination and the like cause the difficulty of the discrimination of various color categories to be increased, so that a classification recognition algorithm can not play a good role, the invention leads to a neural network training unit to establish a neural network model to train an image sample, a correlation analysis unit generates a correlation coefficient between color and cable temperature, a principal component analysis unit extracts the principal characteristic component of image data to reduce the dimension to generate a principal component, a training unit trains the image sample based on the principal component to obtain a relation curve between the cable state and the temperature, a detection unit obtains a change curve of the cable state based on the color based on the correlation coefficient and the relation curve, research is carried out on data input processing and model output selection, and feature extraction and detection of color images are carried out, so that the identification precision and the detection efficiency are obviously improved.

Drawings

Various other advantages and benefits of the present invention will become apparent to those of ordinary skill in the art upon reading the following detailed description of the preferred embodiments. The drawings are only for purposes of illustrating the preferred embodiments and are not to be construed as limiting the invention. It is obvious that the drawings described below are only some embodiments of the invention, and that for a person skilled in the art, other drawings can be derived from them without inventive effort. Also, like parts are designated by like reference numerals throughout the drawings.

In the drawings:

fig. 1 is a schematic structural diagram of a cable detection device based on cable coating thermochromic according to an embodiment of the invention.

The invention is further explained below with reference to the figures and examples.

Detailed Description

A specific embodiment of the present invention will be described in more detail below with reference to fig. 1. While specific embodiments of the invention are shown in the drawings, it should be understood that the invention may be embodied in various forms and should not be construed as limited to the embodiments set forth herein. Rather, these embodiments are provided so that this disclosure will be thorough and complete, and will fully convey the scope of the invention to those skilled in the art.

It should be noted that certain terms are used throughout the description and claims to refer to particular components. As one skilled in the art will appreciate, various names may be used to refer to a component. This specification and claims do not intend to distinguish between components that differ in name but not function. In the following description and in the claims, the terms "include" and "comprise" are used in an open-ended fashion, and thus should be interpreted to mean "include, but not limited to. The description which follows is a preferred embodiment of the invention, but is made for the purpose of illustrating the general principles of the invention and not for the purpose of limiting the scope of the invention. The scope of the present invention is defined by the appended claims.

For the purpose of facilitating understanding of the embodiments of the present invention, the following description will be made by taking specific embodiments as examples with reference to the accompanying drawings, and the drawings are not to be construed as limiting the embodiments of the present invention.

For better understanding, as shown in fig. 1, the cable sensing device based on the thermochromic change of the cable coating includes, a cable coating including microcapsules changing color based on a temperature change,

a data acquisition unit that photographs the cable coating to generate image data,

a neural network training unit connected to the data acquisition unit to receive image data, the neural network unit building a neural network model to train image samples, comprising,

a correlation analysis unit configured to generate a correlation coefficient between the color and the cable temperature,

a principal component analysis unit that extracts principal feature components of the image data to generate principal components in a dimension reduction,

a training unit for training the image sample based on the principal component to obtain a cable state versus temperature curve,

and the detection unit is connected with the neural network training unit to obtain a cable state color-based change curve based on the correlation coefficient and the relation curve.

The relation between the color data on the cable coating and the temperature of the cable coating is researched, the cable state is further evaluated by using the temperature, data processing is carried out on the basis of the color readings of the cable coating at different temperatures, the relation between the color readings and the cable temperature is determined, then multivariate linear fitting is carried out, the residual standard deviation S is selected for analysis, and the change curve of the cable state based on the color is obtained.

In a preferred embodiment of the cable detection device, the data acquisition unit includes a color space transformation module configured to transform input region image data from an RGB color space to an HSV color space, where the image data includes red R, green G, blue B, chromaticity H, saturation S, and brightness V parameters.

In a preferred embodiment of the cable detection apparatus, a histogram transformation module is disposed between the data acquisition unit and the neural network training unit, and retains image data related to the cable based on the received image data.

In the preferred embodiment of the cable detection device, an area segmentation unit is arranged between the data acquisition unit and the neural network training unit and is used for performing multichannel significance transformation on image data to segment the area, and removing partial edge backgrounds and other areas interfering with color identification to retain the image data of the cable fault coating color rendering area.

In a preferred embodiment of the cable inspection device, the area dividing unit includes,

an R-channel saliency detection module that generates an R-channel saliency detection feature map based on the image data,

a G-channel saliency detection module that generates a G-channel saliency detection feature map based on the image data,

a B-channel saliency detection module that generates a B-channel saliency detection feature map based on the image data, a multi-channel histogram transformation module that generates a histogram based on the image data,

a fusion selector that selects image data relating to the cable according to a saliency value range of the cable based on the multi-channel histogram transformation module, the G-channel saliency detection feature map, the B-channel saliency detection feature map, and the histogram,

a multi-channel fused feature module that generates a multi-channel fused feature map based on the selected cable-related image data fusion,

a binarization threshold selector that performs binarization processing based on the selected cable-related image data,

and the multi-channel detection module is connected with the multi-channel fusion feature module and the binarization threshold selector to generate regional image data representing the color of the cable coating failure main body based on the multi-channel detection module and the binarization result.

In a preferred embodiment of the cable detection device, the cable state of the sample is detected by a current detection device.

In the preferred embodiment of the cable detection device, the microcapsule coats the invisible dye, the color forming agent and the temperature control agent.

In a preferred embodiment of the cable detection apparatus, the correlation analysis unit includes a Pearson correlation coefficient module.

In a preferred embodiment of the cable detection device, the principal characteristic components of the image data include red R, green G, blue B, chromaticity H, saturation S, and luminance V parameters, the principal component analysis unit establishes a component matrix to obtain principal components occupied by R red color values, the proportion occupied by the obtained R red color values is maximum, and then the data of the R red color values are removed; performing principal component analysis again by using the remaining five-dimensional data to obtain the maximum proportion of the G green color value; and then removing the G green color value, so that the proportion of the B blue color value is the maximum, and judging the significance before and after dimension reduction by adopting a dimension reduction method. The order of dimension reduction is: six-dimensional, five-dimensional (hue H removed), and four-dimensional (saturation S removed).

In the preferred embodiment of the cable detection device, the color-temperature curve and the temperature-state curve are prepared by the data of six color readings (red R, green G, blue B, chroma H, saturation S and brightness V) and the cable coating temperature color development in the RGB color space and the HSV color space at different temperatures.

In the preferred embodiment of the cable detection device, the neural network is used for learning the data of the coating color and the temperature to obtain a certain approximate linear relation between the coating color and the temperature.

In the preferred embodiment of the cable detection device, the correlation analysis unit analyzes two or more variable elements with correlation, and further measures the degree of closeness of correlation between the two variable elements. The degree of linear relationship between two variables is described by the correlation coefficient r: the change directions of x and y are consistent, for example, the relation between height and weight, and r is more than 0 and is positive correlation; r | ≧ 0.95 is significantly correlated; the | r | ≧ 0.8 is highly correlated; the absolute r is more than or equal to 0.5 and less than 0.8; low degree correlation of r < 0.5 more than or equal to 0.3; the relationship of r < 0.3 is very weak; inversely related, r is less than 0; wireless correlation: r is 0.

In one embodiment, based on Pearson correlation coefficients, the correlation coefficients between the cable temperature and the color can be obtained by performing correlation analysis on the colors at 10 different temperatures by using SPSS software, and the correlation coefficients have significant correlation.

In one embodiment, the model is optimized by eliminating collinearity through a principal component analysis method by using variance expansion factors (ViF) in the data multivariate linear regression, wherein the collinearity of the function is extremely strong, and each independent variable has interaction to influence the fitting accuracy.

In one embodiment, the principal component analysis unit converts a given set of correlated variables into another set of uncorrelated variables by linear transformation, and these new variables are arranged in order of decreasing variance, which can be used to extract the dominant feature components of data, which is often used for dimensionality reduction of high-dimensional data. The new variable is called the principal component and it retains the information contained in the original variable. PCA achieves the purpose of reducing the dimension mainly through translation and rotation of coordinates. Assuming a 2-dimensional data table, in which data are distributed in an elliptical shape, the center of gravity is the origin of coordinates, the coordinate system is rotated, the direction of the maximum data variation is the axis Y1, an orthogonal coordinate system Y1OY2 is obtained, and data points are projected on the axis Y1 ignoring the direction of the smaller data variation, i.e., the direction of the axis Y2. This reduces the problem of the original 2-dimensional data space to 1-dimensional data space for analysis. The principal component analysis unit selects the eigenvector corresponding to the larger eigenvalue, abandons the eigenvector corresponding to the small eigenvalue, and offsets the loss of the information quantity as much as possible. The dimension can determine the number of factors of the color, and the dimension is reduced from the reading of 10 groups of colors to 5 dimensions and then to 4 dimensions to study the fitting characteristics. From the principal component analysis, it is known that, among different colors, the three primary colors R, G, B and the luminance V play an important role, and the chromaticity and the saturation are relatively weak.

The detection method of the cable detection device comprises the following steps,

the cable is coated with a cable coating comprising microcapsules that change color based on a change in temperature,

the data acquisition unit shoots the cable coating to generate image data,

a region division unit region-divides the image data to generate image data,

the neural network unit establishes a neural network model to train an image sample, wherein the correlation analysis unit generates a correlation coefficient between color and cable temperature, the principal component analysis unit extracts principal characteristic components of image data to reduce dimensions and generate principal components, the training unit trains the image sample based on the principal components to obtain a relation curve between the cable state and the temperature,

and the detection unit obtains a change curve of the cable state based on the color based on the correlation coefficient and the relation curve.

Although the embodiments of the present invention have been described above with reference to the accompanying drawings, the present invention is not limited to the specific embodiments and the application fields, and the specific embodiments are illustrative, instructive, and not restrictive. Those skilled in the art, having the benefit of this disclosure, may effect numerous modifications thereto without departing from the scope of the invention as defined by the appended claims.