CN106780357A - XLPE cable insulation degree of purity appraisal procedure based on image treating - Google Patents

Abstract

The invention relates to a method for evaluating the purity of XLPE cable insulation based on an image processing method, and its technical characteristics include the following steps: collecting microscopic images of XLPE cable test pieces; preprocessing the collected microscopic images, and using morphological The reconstruction method smoothes the image to remove noise; for the geometry of the surface of the XLPE cable insulation material, image segmentation based on the threshold method and the fuzzy c-mean method is used to extract the impurity particles in the microscopic image; the extracted impurity particles Carry out marking and geometric shape analysis, and accurately and quantitatively calculate the geometric shape characteristics of impurity particles in XLPE microscopic images. The invention realizes the accurate, fast and comprehensive quantitative detection function of the geometric shape information of particles such as impurities in the XLPE cable insulation, and can automatically segment, classify and identify specific particles such as impurities and air bubbles in the XLPE cable insulation, and has comparative advantages. High accuracy and strong robustness.

Description

Evaluation Method of XLPE Cable Insulation Purity Based on Image Processing Method

technical field

The invention belongs to the technical field of cross-linked polyethylene insulated power cables, in particular to an evaluation method for the purity of XLPE cable insulation based on an image processing method.

Background technique

At present, according to "GB/T 11017.1-2002 Rated Voltage 110kV XLPE Insulated Power Cable and Its Accessories Part 1: Test Methods and Requirements", "GB/Z 18890.1-2002 Rated Voltage 220kV (Um=252kV) XLPE Polyethylene insulated power cables and their accessories, Part 1: Test methods and requirements, the detection steps for impurities in the XLPE insulation layer are: 1. Cut 80 samples containing conductors in the radial direction from a cable core sample about 50mm long. Shielding, insulation and insulation shielding round or spiral thin test piece, the thickness of the test piece is about 0.4mm ~ 0.7mm; 2. Use transmitted light to generally check the micropores, impurities and translucent brown in the insulation of all 80 test pieces 3. Use a microscope with a minimum magnification of 15 times to detect all areas of the 20 consecutive test pieces that are suspicious in the above-mentioned general inspection, and mark all micropores that exceed the standard; 4. Use a microscope with a minimum magnification of 40 times Measuring microscope measures the size of micropores, impurities, etc. in the direction of their largest size; 5. Measure and calculate the total volume of insulation of 20 test pieces, and convert the statistical number of micropores and impurities into the number ^of insulation volumes per 10cm3 , the calculated value should be rounded to an integer. The above-mentioned detection method relies on the experience of the measurer using human eyesight, the measurement error is relatively large, the recognition speed of impurity particles is slow, the detection efficiency is low, and the test result data is single. , area, standard deviation and other statistics of shape geometric characteristic parameters.

Contents of the invention

The purpose of the present invention is to overcome the deficiencies of the prior art, and provide a method for evaluating the purity of XLPE cable insulation based on an image processing method with reasonable design, high accuracy and strong robustness.

The present invention solves its technical problem and realizes by taking the following technical solutions:

A method for evaluating the purity of XLPE cable insulation based on an image processing method, comprising the following steps:

Step 1, using microscopic image analysis equipment to collect microscopic images of XLPE cable test pieces;

Step 2. Preprocessing the collected microscopic image to enhance the image contrast and sharpen the edge of the image; use the morphological reconstruction method to smooth the image to remove noise and maintain the basic shape characteristics of the original microscopic image;

Step 3, for the geometric topography of the surface of the XLPE cable insulation material, image segmentation is performed based on the threshold method and the fuzzy c-mean method, and the impurity particles in the microscopic image are extracted;

Step 4. Mark the extracted impurity particles and perform geometric shape analysis, accurately and quantitatively calculate the geometric shape characteristics of the impurity particles in the XLPE microscopic image, and realize the quantitative evaluation function of the XLPE insulation purity.

The impurity extraction particles include the following characteristics: number of impurities, perimeter of impurities, area, maximum size, centroid, roundness, standard deviation, minimum rectangle containing impurities, length of an ellipse having the same standard second-order central moment as the impurity region Axis length, minor axis length, eccentricity of ellipse and a topological invariant in geometric topology—Euler number.

Advantage and positive effect of the present invention are:

The invention performs image processing on the microscopic image of the XLPE cable insulation sample based on the mathematical morphology method, based on the advanced data analysis technology, combined with the relevant theory of digital image processing, and realizes the detection of impurities in the XLPE cable insulation, etc. The accurate, rapid and comprehensive quantitative detection function of the geometric shape information of the particles can automatically segment, classify and identify specific particles such as impurities and air bubbles in the XLPE cable insulation. It has a high degree of automation, high accuracy and strong robustness. Rodness, which can accurately and quantitatively compare the purity of different XLPE samples; it is of great significance to improve the detection level of cable insulation purity, reduce manpower and material resources, shorten the purity detection time, and improve the quality level of cables.

detailed description

Embodiments of the present invention are described in further detail below:

A method for evaluating the purity of XLPE cable insulation based on an image processing method, comprising the following steps:

Step 1. Use a microscopic image analysis device to collect microscopic images of the XLPE cable test piece.

Step 2. Preprocessing the collected microscopic image, enhancing the image contrast, sharpening the image edge, and using the morphological reconstruction method to smooth the image, remove noise, and maintain the basic shape characteristics of the original microscopic image.

Step 3. For the geometric topography of the surface of the XLPE cable insulation material, image segmentation is performed based on the threshold method and the fuzzy c-mean method (FCM), and the impurity particles in the microscopic image are effectively extracted.

Step 4. Mark the extracted impurity particles and perform geometric shape analysis, and accurately and quantitatively calculate the geometric shape characteristics of the impurity particles in the XLPE microscopic image, so as to realize the quantitative evaluation function of the XLPE insulation purity.

In this step, the extracted impurity particles include the following characteristics: number of impurities, perimeter of impurities, area, maximum size, center of mass (center of gravity), roundness, standard deviation, smallest rectangle containing impurities, and the same standard as the impurity area The second-order central moment of the ellipse's major axis length (in the pixel sense), the minor axis length, the eccentricity of the ellipse, and a topological invariant in geometric topology—Euler number and other shape factor geometric features.

It should be emphasized that the embodiments described in the present invention are illustrative rather than restrictive, so the present invention includes and is not limited to the embodiments described in the specific implementation, and those skilled in the art according to the technology of the present invention Other implementations derived from the scheme also belong to the protection scope of the present invention.

Claims (2)

1. A method for evaluating the purity of XLPE cable insulation based on image processing method, is characterized in that comprising the following steps: Step 1, using microscopic image analysis equipment to collect microscopic images of XLPE cable test pieces; Step 2. Preprocessing the collected microscopic image to enhance the image contrast and sharpen the edge of the image; use the morphological reconstruction method to smooth the image to remove noise and maintain the basic shape characteristics of the original microscopic image; Step 3, for the geometric topography of the surface of the XLPE cable insulation material, image segmentation is performed based on the threshold method and the fuzzy c-mean method, and the impurity particles in the microscopic image are extracted; Step 4. Mark the extracted impurity particles and perform geometric shape analysis, accurately and quantitatively calculate the geometric shape characteristics of the impurity particles in the XLPE microscopic image, and realize the quantitative evaluation function of the XLPE insulation purity. 2. A method for evaluating the purity of XLPE cable insulation based on an image processing method, characterized in that: the impurity particles extracted include the following characteristics: number of impurities, perimeter of impurities, area, maximum size, centroid, roundness, standard deviation , the smallest rectangle containing impurities, the length of the major axis, the length of the minor axis of the ellipse that has the same standard second-order central moment as the impurity region, the eccentricity of the ellipse, and a topological invariant in geometric topology—Euler number.