CN117593285A - Quality detection system and method for flexible mineral insulation flexible fireproof cable - Google Patents

Abstract

The invention relates to the technical field of cables, in particular to a quality detection system and a quality detection method of a flexible mineral insulation flexible fireproof cable, wherein the quality detection system comprises a matching layer, a comparison layer and a judgment layer; the invention collects the image data of the cable through the matching layer, completes the segmentation of the cable image in the matching layer to obtain sub-cable images, carries out the mutual matching of image comparison targets on the obtained sub-cable images, and receives the matched sub-cable images in real time.

Description

A quality inspection system and method for flexible mineral insulated flexible fireproof cables

Technical field

The invention relates to the technical field of cables, and in particular to a quality detection system and method for flexible mineral insulated flexible fireproof cables.

Background technique

Flexible fire-resistant cable is a cable with fire-resistant properties. It is usually used in places that require a high degree of fire protection, such as high-rise buildings, underground shopping malls, tunnels, etc. The difference between it and ordinary cables is that the conductor is wrapped with a layer of mica tape. This mica tape has good high temperature resistance and fire resistance, and can protect the cable from damage in the event of a fire.

The invention patent with application number 202310050627.7 discloses an early warning cable detection system, which is characterized in that it includes a node association unit, a data collection unit, an early warning analysis unit, a historical database, an early warning unit, and a processor: the node association unit and the processing unit The node association unit is also communicatively connected with the historical database, the early warning analysis unit is communicatively connected with the processor, the data acquisition unit is communicatively connected with the processor, the early warning unit is communicatively connected with the processor; node association Unit, the node association unit is used to perform node association according to the relationship between nodes, obtain the first-level association point, second-level association point, and third-level association point corresponding to each node according to the association result, and associate each node with The first-level association points, second-level association points and third-level association points are uploaded to the processor; the processor uploads the first-level association points, second-level association points and third-level association points corresponding to each node to the historical database: data Acquisition unit, the data acquisition unit is used to obtain the temperature and current of each node every preset time T1 and mark the obtained temperature and current of the node respectively and upload them to the processor. The processor will receive the temperature and current of the node. The temperature and current are uploaded to the historical database: the early warning analysis unit, which detects data along the way based on the correlation results and the temperature and current information of the nodes transmitted by the data collection unit, obtains abnormal nodes and locates the abnormal direction of the cable; the early warning analysis unit analyzes the abnormal nodes And the abnormal direction of the cable located is uploaded to the processor.

The application aims to solve the problem: "The existing technology lacks the accuracy of early warning of potential operational failures of the cable itself and the cable network."

However, for flexible fire-proof cables, the integrity of the mica tape wrapped on its surface is the key to reflecting the fire-proof performance of flexible fire-proof cables;

However, there is currently no system for quality inspection of the surface of flexible fire-resistant cables. This results in the surface quality inspection of flexible fire-resistant cables mostly relying on manual inspection, and its inspection efficiency and accuracy are relatively poor.

Contents of the invention

In view of the above-mentioned shortcomings of the prior art, the present invention provides a quality detection system and method for flexible mineral insulated flexible fireproof cables, which solves the technical problems raised in the above-mentioned background technology.

In order to achieve the above objectives, the present invention is achieved through the following technical solutions:

In the first aspect, a quality inspection system for flexible mineral insulated flexible fireproof cables includes a matching layer, a comparison layer and a judgment layer;

The image data of the cable is collected through the matching layer, and the cable image is segmented in the matching layer to obtain sub-cable images. The obtained sub-cable images are matched with each other by image comparison targets. The comparison layer receives the matched sub-cable images in real time. , analyze the image information symmetry and similarity of each group of matching sub-cable images, and the judgment layer receives the image information symmetry and similarity recognition results of the matching sub-cable images in the comparison layer, based on the images of each group of sub-cable images The information uniformity and similarity recognition results determine whether the cable from which the sub-cable image comes is qualified;

The comparison layer includes a receiving module, an analysis module and a storage module. The receiving module is used to receive the matched sub-cable images in the matching layer. The analysis module is used to analyze the image information of each set of matched sub-cable images received in the receiving module. For symmetry and similarity, the storage module is used to receive the image information symmetry and similarity of the matching sub-cable images analyzed in the analysis module, and store the image information symmetry and similarity of the matching sub-cable images;

The similarity of the matched sub-cable image data is calculated by the following formula:

In the formula: χ (a, b) is the similarity between sub-cable image data a and sub-cable image data b in the matched sub-cable image data; ξ _a is the image information uniformity of sub-cable image data a; ξ _b is the sub-cable image data a. Image information symmetry of cable image data b; α, β, γ are weights; d _color is the color similarity of the matching sub-cable image data; d _shape is the shape similarity of the matching sub-cable image data; d _texture is the matching Texture similarity of sub-cable image data;

Among them, when χ (a, b) is obtained, the image information symmetry of the two sets of sub-cable image data in the matching sub-cable image data is first obtained. The sub-cable image data with the smaller image information symmetry is used as in the formula a. Sub-cable image data with large image information uniformity is used as b in the formula. The sum of α, β, and γ is 1, α>γ>β.

Furthermore, the matching layer includes a collection module, a segmentation module and a configuration module. The collection module is used to collect cable image data, and the segmentation module is used to receive the cable image data collected by the collection module, and identify the cable image in the cable image data. Perform image segmentation processing on the recognized cable image, and the configuration module is used to receive several groups of sub-cable images obtained by segmentation processing in the segmentation module, and configure the sub-cable images with each other;

Among them, the cable is output from the output end of the cable production equipment, transported by the conveyor belt, and is rolled and received by the winding equipment. The acquisition of cable image data in the acquisition module is completed during the transportation stage of the cable on the conveyor belt. The surface color of the conveyor belt It is a solid color and is different from the color of the cable surface. The cable image data collected by the acquisition module is the cable image data with the conveyor belt as the background and only includes the conveyor belt and cable images.

Furthermore, the recognition result of the cable image in the cable image data in the segmentation module is output by the following formula;

p _residue = p _all -p _Del-obj ;

In the formula: p _residue is the remaining cable image; p _all is the original cable image; p _Del-obj is the target image area to be reduced in the original cable image;

Among them, the p _residue , p _all and p _Del-obj are all expressed in the form of a set of pixel blocks. Before obtaining the remaining cable image p _residue , the color entropy of each pixel block in the original cable image p _all is calculated. The target image area p _Del-obj to be reduced in the cable image is the background image in the cable image data. The color entropy of all pixel blocks in the background image in the cable image data is the same. The remaining cable image p _residue is the cable image in the cable image data.

Furthermore, the color entropy of the pixel block is calculated by the following formula:

In the formula: H is the color entropy of the pixel block; k is the number of color bits in the pixel block; p _i is the probability of the i-th color value in the pixel block;

Among them, p _all and p _Del-obj are determined by the color entropy calculation results of pixel blocks. The pixel blocks applied in the cable image output formula in the cable image data are equal in size, and their expressions are composed of x×x pixels. matrix, x is the number of pixels in the vertical and horizontal directions that make up the matrix of pixels. The smaller the pixel block applied in the cable image output formula in the cable image data, the better the accuracy of the remaining cable image p _residue .

Furthermore, after the segmentation module recognizes the cable image in the cable image data, it sets the segmentation logic based on the density of the mica tape wrapped around the cable surface and the size ratio of the cable image to the actual cable specification parameters. The segmentation logic is expressed as:

In the formula: L is the segmentation span of the cable image; W _Cov is the overlap width of the mica tape wrapped on the cable; f _pic is the length of the cable in the cable image; f _real is the actual length of the electric power;

Among them, the cable image is divided into several groups of equal-length cable segment images based on the cable image segmentation span L. The cable segment images are sub-cable image data, and the cable segment images are marked sequentially based on the cable conveyor belt transportation direction. The marking logic is: 1 , 2, 3, 4, 5, 6, ..., the configuration module configures the cable segment images based on the marking results of the cable segment images. The configuration logic is expressed as: the cable segment image corresponding to mark 1 and the cable corresponding to mark 2 The segment images are configured with each other, the cable segment image corresponding to mark 2 and the cable segment image corresponding to mark 3 are configured with each other, the cable segment image corresponding to mark 3 is configured with the cable segment image corresponding to mark 4, and so on.

Furthermore, in the similarity calculation formula of the matched sub-cable image data, the calculation logic of d _color , d _shape and d _texture includes:

In the formula: k is the number of color bits in the sub-cable image data; H _a [c] is the color histogram of the color channel value of the cable image data a in the c bit; H _b [c] is the cable image data b in the c bit The color histogram in the color channel value; H _a,o is the o-th component of cable image data a based on Hu moment; H _b,o is the o-th component of cable image data b based on Hu moment; C _a,c is The cable image data a is based on the element of row c and column c of GLCM in the c-bit color channel value; C _{b, c} is the element of the cable image data v based on the row c and column c of GLCM in the c-bit color channel value. .

Furthermore, the image information symmetry is obtained by the following formula:

In the formula: M, N are the width and height of the image; X _xy is the gray value of the image at (x, y); is the average gray value of the image;

Among them, ξ∈[0, 1]. The larger the ξ value, the better the image information symmetry of the image. On the contrary, it means the worse the image information symmetry of the image.

Furthermore, the determination layer includes a setting module and a determination module. The setting module is used to receive the image information uniformity and similarity of the matching sub-cable images stored in the storage module, and to set the cable qualification threshold, and determine The module is used to determine whether the image information uniformity and similarity of the sub-cable image are within the cable qualification threshold;

Among them, there are two sets of qualified judgment thresholds set in the setting module, which are respectively applied to the qualified judgment of the image information uniformity of the sub-cable image, and the qualified judgment of the similarity of the sub-cable image. The uniformity of the image information of the sub-cable image is When the sub-cable image is determined to be qualified, and in the similarity determination result of the sub-cable image, the sub-cable image data that is determined to be qualified is not less than 99% of the total amount of sub-cable image data, the cable from which the sub-cable image is derived is determined to be qualified, and the cable When it is judged to be unqualified, the judgment module synchronously obtains the marks of the sub-cable images corresponding to the uniformity and similarity of the image information that is judged to be unqualified, and sends the obtained sub-cable image marks to the storage module in the comparison layer. The system-side user reads the tag of the sub-cable image data in the storage module.

Furthermore, the receiving module is interactively connected to an analysis module and a storage module through a wireless network, the receiving module is interactively connected to a configuration module through a wireless network, and the configuration module is interactively connected to a segmentation module and a collection module through the wireless network, so The storage module is interactively connected to a setting module through a wireless network, and the setting module is interactively connected to a determination module through a wireless network.

In the second aspect, a quality inspection method for flexible mineral insulated flexible fireproof cables includes the following steps:

Step 1: Collect cable image data and segment the cable image data;

Step 11: Recognition stage of cable image in cable image data;

Step 12: Setting stage of cable image data segmentation processing logic;

Step 2: Obtain the sub-cable image data obtained by segmentation processing, and configure the sub-cable image data;

Step 21: Marking stage of sub-cable image data;

Step 3: Compare the image information uniformity and similarity of the configured sub-cable image data;

Step 31: The setting stage of the image information uniformity and similarity comparison logic of the sub-cable image data;

Step 4: Obtain the image information uniformity and similarity comparison results of the configured sub-cable image data, set the qualification threshold, and apply the qualification threshold to determine whether the cable corresponding to the sub-cable image data is qualified;

Step 5: Based on the marking of the sub-cable image data, capture the unqualified sub-cable image data in the sub-cable image data of the cable.

Compared with the known public technology, the technical solution provided by the present invention has the following features:

Beneficial effects:

1. The present invention provides a quality detection system for flexible mineral insulated flexible fireproof cables. During operation, the system performs image analysis on the cable by collecting image data of the cable, and during the process of analyzing the image of the cable, The cable image is segmented, so that the segmented cable image provides the system with more data support for cable qualification determination, making the power qualification detection and determination process more refined.

2. During the operation of the system in the present invention, while using the power image data as the basis for analysis, it also analyzes the symmetry and similarity of the image information based on the cable image data to determine whether the source cable of the cable image is qualified. The analysis data applied to the obtained results is more comprehensive, thereby improving the system's further detection and determination results based on the analysis results to be more accurate and reliable.

3. After collecting the cable image data, the system in the present invention performs segmentation processing on the cable image data. Through the set segmentation logic, when the system is applied to cable qualification detection, the system can further improve the system by controlling the segmentation accuracy. It brings a certain degree of control effect to the detection efficiency and detection accuracy of cable qualification detection, so that the adaptability of the system can be more conveniently controlled by users.

4. The present invention provides a quality detection method for flexible mineral insulated flexible fireproof cables. Through the execution of the steps in the method, the stability of the system operation can be further maintained, and during the execution of the steps of the method, the system can further be provided. Stable operating logic ensures that the technical solution composed of this method and system is more stable and reliable in the specific implementation stage.

Description of drawings

In order to more clearly explain the embodiments of the present invention or the technical solutions in the prior art, the drawings needed to describe the embodiments or the prior art will be briefly introduced below. Obviously, the drawings in the following description are only some embodiments of the present invention. For those of ordinary skill in the art, other drawings can be obtained based on these drawings without exerting creative efforts.

Figure 1 is a schematic structural diagram of a quality inspection system for flexible mineral insulated flexible fireproof cables;

Figure 2 is a schematic flow chart of a quality inspection method for flexible mineral insulated flexible fireproof cables;

Figure 3 is a schematic diagram showing the logic of system placement in the present invention;

Figure 4 is a schematic diagram showing the process of obtaining sub-cable images from cable image data in the present invention;

Figure 5 is a statistical diagram of the results of similarity calculation of the neutron cable image data of the present invention.

Detailed ways

In order to make the purpose, technical solutions and advantages of the embodiments of the present invention more clear, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are some, but not all, of the embodiments of the present invention. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without making creative efforts fall within the scope of protection of the present invention.

The present invention will be further described below in conjunction with examples.

Example 1:

A quality inspection system for flexible mineral insulated flexible fireproof cables in this embodiment, as shown in Figure 1, includes a matching layer, a comparison layer and a judgment layer;

The image data of the cable is collected through the matching layer, and the cable image is segmented in the matching layer to obtain sub-cable images. The obtained sub-cable images are matched with each other by image comparison targets. The comparison layer receives the matched sub-cable images in real time. , analyze the image information symmetry and similarity of each group of matching sub-cable images, and the judgment layer receives the image information symmetry and similarity recognition results of the matching sub-cable images in the comparison layer, based on the images of each group of sub-cable images The information uniformity and similarity recognition results determine whether the cable from which the sub-cable image comes is qualified;

The comparison layer includes a receiving module, an analysis module and a storage module. The receiving module is used to receive the matched sub-cable images in the matching layer. The analysis module is used to analyze the image information symmetry of each set of matched sub-cable images received in the receiving module. and similarity, the storage module is used to receive the image information symmetry and similarity of the matching sub-cable images analyzed in the analysis module, and store the image information symmetry and similarity of the matching sub-cable images;

The similarity of the matching sub-cable image data is calculated by the following formula:

In the formula: χ (a, b) is the similarity between sub-cable image data a and sub-cable image data b in the matched sub-cable image data; ξ _a is the image information uniformity of sub-cable image data a; ξ _b is the sub-cable image data a. Image information symmetry of cable image data b; α, β, γ are weights; d _color is the color similarity of the matching sub-cable image data; d _shape is the shape similarity of the matching sub-cable image data; d _texture is the matching Texture similarity of sub-cable image data;

Among them, when χ (a, b) is obtained, the image information symmetry of the two sets of sub-cable image data in the matching sub-cable image data is first obtained. The sub-cable image data with the smaller image information symmetry is used as in the formula a, sub-cable image data with large image information uniformity is used as b in the formula, the sum of α, β, and γ is 1, α>γ>β;

The matching layer includes an acquisition module, a segmentation module and a configuration module. The acquisition module is used to collect cable image data. The segmentation module is used to receive the cable image data collected by the acquisition module, identify the cable image in the cable image data, and identify the cable image. Perform image segmentation processing, and the configuration module is used to receive several groups of sub-cable images obtained by segmentation processing in the segmentation module, and configure the sub-cable images with each other;

Among them, the cable is output from the output end of the cable production equipment, transported by the conveyor belt, and is wound and received by the winding equipment. The acquisition of cable image data in the acquisition module is completed during the transportation stage of the cable on the conveyor belt. The surface color of the conveyor belt is solid and distinct. Regarding the cable surface color, the cable image data collected by the acquisition module is the cable image data with the conveyor belt as the background and only includes the conveyor belt and cable images;

In the similarity calculation formula of matching sub-cable image data, the calculation logic of d _color , d _shape and d _texture includes:

In the formula: k is the number of color bits in the sub-cable image data; H _a [c] is the color histogram of the color channel value of the cable image data a in the c bit; H _b [c] is the cable image data b in the c bit The color histogram in the color channel value; H _a,o is the o-th component of cable image data a based on Hu moment; H _b,o is the o-th component of cable image data b based on Hu moment; C _a,c is The cable image data a is based on the element of row c and column c of GLCM in the c-bit color channel value; C _{b, c} is the element of the cable image data v based on the row c and column c of GLCM in the c-bit color channel value. ;

The symmetry of image information is calculated by the following formula:

In the formula: M, N are the width and height of the image; X _xy is the gray value of the image at (x, y); is the average gray value of the image;

Among them, ξ∈[0, 1], the larger the ξ value, the better the image information symmetry of the image, and conversely, the worse the image information symmetry of the image;

The judgment layer includes a setting module and a judgment module. The setting module is used to receive the image information uniformity and similarity of the matching sub-cable images stored in the storage module, and set the cable qualification judgment threshold. The judgment module is used to judge the sub-cable. Whether the image information uniformity and similarity of the image are within the cable qualification threshold;

Among them, there are two sets of qualified judgment thresholds set in the setting module, which are respectively applied to the qualified judgment of the image information uniformity of the sub-cable image, and the qualified judgment of the similarity of the sub-cable image. The uniformity of the image information of the sub-cable image is When the sub-cable image is determined to be qualified, and in the similarity determination result of the sub-cable image, the sub-cable image data that is determined to be qualified is not less than 99% of the total amount of sub-cable image data, the cable from which the sub-cable image is derived is determined to be qualified, and the cable When it is judged to be unqualified, the judgment module synchronously obtains the marks of the sub-cable images corresponding to the uniformity and similarity of the image information that is judged to be unqualified, and sends the obtained sub-cable image marks to the storage module in the comparison layer. The system-side user reads the tag of the sub-cable image data in the storage module;

The receiving module is interactively connected to the analysis module and the storage module through the wireless network. The receiving module is interactively connected to the configuration module through the wireless network. The configuration module is interactively connected to the segmentation module and the acquisition module through the wireless network. The storage module is interactively connected to the setting module through the wireless network. , the setting module is interactively connected to the judgment module through the wireless network.

In this embodiment, the acquisition module runs to collect cable image data, and the segmentation module runs afterward to receive the cable image data collected by the acquisition module, identifies the cable image in the cable image data, performs image segmentation processing on the identified cable image, and configures The module synchronously receives several groups of sub-cable images obtained by segmentation processing in the segmentation module, and configures the sub-cable images with each other. The receiving module further operates to receive the matched sub-cable images in the matching layer, and the analysis module analyzes each group received in the receiving module in real time. The image information symmetry and similarity of the matched sub-cable images are synchronously received by the storage module and analyzed in the analysis module. The image information symmetry and similarity of the matched sub-cable images are analyzed. The similarity is stored, and finally the image information uniformity and similarity of the matching sub-cable image stored in the storage module are received through the setting module, and the cable qualification threshold is set, and the judgment module determines the uniformity of the image information of the sub-cable image. Whether the degree and similarity are within the cable qualification threshold;

See Figure 3, which can further assist system users to understand the position and posture of the system relative to the cable production equipment and cable winding equipment when the acquisition module in the matching layer in the system collects cable image data;

As shown in Figure 4, the upper part of the figure shows the cable image data, the middle part of the figure shows the cable image, and the lower part of the figure shows the sub-cable image data, which can also be called the cable segment image;

Refer to Figure 5, which further shows the similarity of the sub-cable image data obtained in the comparison layer in the system. The diagram is formed by the similarity of the sub-cable image data, which can further assist system end users with visual method to read the qualification test results of the cable.

Example 2:

At the specific implementation level, on the basis of Embodiment 1, this embodiment further explains in detail the quality detection system of a flexible mineral insulated flexible fireproof cable in Embodiment 1 with reference to Figure 1:

In the segmentation module, the recognition result of the cable image in the cable image data is output through the following formula;

p _residue = p _all -p _Del-obj ;

In the formula: p _residue is the remaining cable image; p _all is the original cable image; p _Del-obj is the target image area to be reduced in the original cable image;

Among them, p _residue , p _all and p _Del-obj are all expressed in the form of a set of pixel blocks. Before obtaining the remaining cable image p _residue , calculate the color entropy of each pixel block in the original cable image p _all . The original cable image The target image area p _Del-obj to be reduced is the background image in the cable image data. The color entropy of all pixel blocks in the background image in the cable image data is the same. The remaining cable image p _residue is the cable image in the cable image data;

The color entropy of a pixel block is calculated by the following formula:

In the formula: H is the color entropy of the pixel block; k is the number of color bits in the pixel block; p _i is the probability of the i-th color value in the pixel block;

Among them, p _all and p _Del-obj are determined by the color entropy calculation results of pixel blocks. The pixel blocks applied in the cable image output formula in the cable image data are equal in size, and their expressions are composed of x×x pixels. matrix, x is the number of pixels in the vertical and horizontal directions that make up the matrix of pixels. The smaller the pixel block applied in the cable image output formula in the cable image data, the better the accuracy of the remaining cable image p _residue ;

Through the above settings, the recognition logic of the matching layer segmentation module in the system when performing cable image recognition on cable image data is further limited.

After the segmentation module recognizes the cable image in the cable image data, it sets the segmentation logic based on the density of the mica tape wrapped on the cable surface and the size ratio of the cable image to the actual cable specification parameters. The segmentation logic is expressed as:

In the formula: L is the segmentation span of the cable image; W _Cov is the overlap width of the mica tape wrapped on the cable; f _pic is the length of the cable in the cable image; f _real is the actual length of the electric power;

Among them, the cable image is divided into several groups of equal-length cable segment images based on the cable image segmentation span L. The cable segment images are sub-cable image data, and the cable segment images are marked sequentially based on the cable conveyor belt transportation direction. The marking logic is: 1 , 2, 3, 4, 5, 6, ..., the configuration module configures the cable segment images based on the marking results of the cable segment images. The configuration logic is expressed as: the cable segment image corresponding to mark 1 and the cable corresponding to mark 2 The segment images are configured with each other, the cable segment image corresponding to mark 2 and the cable segment image corresponding to mark 3 are configured with each other, the cable segment image corresponding to mark 3 is configured with the cable segment image corresponding to mark 4, and so on.

Through the above settings, the segmentation logic of the cable image by the segmentation module in the matching layer in the system is further defined.

Example 3:

At the specific implementation level, on the basis of Embodiment 1, this embodiment further explains in detail the quality detection system of a flexible mineral insulated flexible fireproof cable in Embodiment 1 with reference to Figure 2:

A quality inspection method for flexible mineral insulated flexible fireproof cables, including the following steps:

Step 1: Collect cable image data and segment the cable image data;

Step 11: Recognition stage of cable image in cable image data;

Step 12: Setting stage of cable image data segmentation processing logic;

Step 2: Obtain the sub-cable image data obtained by segmentation processing, and configure the sub-cable image data;

Step 21: Marking stage of sub-cable image data;

Step 3: Compare the image information uniformity and similarity of the configured sub-cable image data;

Step 31: The setting stage of the image information uniformity and similarity comparison logic of the sub-cable image data;

Step 4: Obtain the image information uniformity and similarity comparison results of the configured sub-cable image data, set the qualification threshold, and apply the qualification threshold to determine whether the cable corresponding to the sub-cable image data is qualified;

Step 5: Based on the marking of the sub-cable image data, capture the unqualified sub-cable image data in the sub-cable image data of the cable.

To sum up, during the operation of the system in the above embodiment, the cable image data is collected and the cable image is analyzed. In the process of cable image analysis, the cable image is segmented, so that the cable image is obtained through segmentation. The cable images provide the system with more data support for cable qualification determination, making the power qualification detection and determination process more refined; and during the operation of this system, the power image data is used as the basis for analysis. At the same time, based on the analysis of the symmetry and similarity of the image information of the cable image data, whether the source cable of the cable image is qualified or not makes the analysis data applied in the analysis results more comprehensive, thereby improving the system and further improving the system through the analysis results. The detection and determination results made are more accurate and reliable; at the same time, after the system collects the cable image data, it performs segmentation processing on the cable image data. Through the set segmentation logic, the system can be used for cable qualification inspection through segmentation. The precision control further enables the system to bring a certain degree of control effect on the detection efficiency and detection accuracy of cable qualification detection, so that the adaptability of the system can be more conveniently controlled by the user; at the same time, the embodiment can further maintain the operation of the system It is stable, and during the execution of the steps of the method, it can further provide stable operating logic of the system, ensuring that the technical solution composed of the method and the system is more stable and reliable in the specific implementation stage.

The above embodiments are only used to illustrate the technical solutions of the present invention, but not to limit them; although the present invention has been described in detail with reference to the foregoing embodiments, those of ordinary skill in the art should understand that they can still modify the technical solutions of the foregoing embodiments. Modifications may be made to the recorded technical solutions, or equivalent substitutions may be made to some of the technical features; however, these modifications or substitutions will not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of each embodiment of the present invention.

Claims (10)

1. A quality inspection system for flexible mineral insulated flexible fireproof cables, which is characterized in that it includes a matching layer, a comparison layer and a judgment layer; The image data of the cable is collected through the matching layer, and the cable image is segmented in the matching layer to obtain sub-cable images. The obtained sub-cable images are matched with each other by image comparison targets. The comparison layer receives the matched sub-cable images in real time. , analyze the image information symmetry and similarity of each group of matching sub-cable images, and the judgment layer receives the image information symmetry and similarity recognition results of the matching sub-cable images in the comparison layer, based on the images of each group of sub-cable images The information uniformity and similarity recognition results determine whether the cable from which the sub-cable image comes is qualified; The comparison layer includes a receiving module, an analysis module and a storage module. The receiving module is used to receive the matched sub-cable images in the matching layer. The analysis module is used to analyze the image information of each set of matched sub-cable images received in the receiving module. For symmetry and similarity, the storage module is used to receive the image information symmetry and similarity of the matching sub-cable images analyzed in the analysis module, and store the image information symmetry and similarity of the matching sub-cable images; The similarity of the matched sub-cable image data is calculated by the following formula: In the formula: χ (a, b) is the similarity between sub-cable image data a and sub-cable image data b in the matched sub-cable image data; ξ _a is the image information uniformity of sub-cable image data a; ξ _b is the sub-cable image data a. Image information symmetry of cable image data b; α, β, γ are weights; d _color is the color similarity of the matching sub-cable image data; d _shape is the shape similarity of the matching sub-cable image data; d _texture is the matching Texture similarity of sub-cable image data; Among them, when χ (a, b) is obtained, the image information symmetry of the two sets of sub-cable image data in the matching sub-cable image data is first obtained. The sub-cable image data with the smaller image information symmetry is used as in the formula a. Sub-cable image data with large image information uniformity is used as b in the formula. The sum of α, β, and γ is 1, α>γ>β. 2. A quality detection system for flexible mineral insulated flexible fireproof cables according to claim 1, characterized in that the matching layer includes an acquisition module, a segmentation module and a configuration module, and the acquisition module is used to acquire cable image data, segmentation The module is used to receive the cable image data collected by the acquisition module, identify the cable images in the cable image data, and perform image segmentation processing on the recognized cable images. The configuration module is used to receive several groups of sub-cable images obtained by segmentation processing in the segmentation module. , mutually configure the sub-cable images; Among them, the cable is output from the output end of the cable production equipment, transported by the conveyor belt, and is rolled and received by the winding equipment. The acquisition of cable image data in the acquisition module is completed during the transportation stage of the cable on the conveyor belt. The surface color of the conveyor belt It is a solid color and is different from the color of the cable surface. The cable image data collected by the acquisition module is the cable image data with the conveyor belt as the background and only includes the conveyor belt and cable images. 3. A quality detection system for flexible mineral insulated flexible fireproof cables according to claim 1, characterized in that the recognition result of the cable image in the cable image data in the segmentation module is output by the following formula; p _residue = p _all -p _Del-obj ; In the formula: p _residue is the remaining cable image; p _all is the original cable image; p _Del-obj is the target image area to be reduced in the original cable image; Among them, the p _residue , p _all and p _Del-obj are all expressed in the form of a set of pixel blocks. Before obtaining the remaining cable image p _residue , the color entropy of each pixel block in the original cable image p _all is calculated. The target image area p _Del-obj to be reduced in the cable image is the background image in the cable image data. The color entropy of all pixel blocks in the background image in the cable image data is the same. The remaining cable image p _residue is the cable image in the cable image data. 4. A quality detection system for flexible mineral insulated flexible fireproof cables according to claim 3, characterized in that the color entropy of the pixel block is obtained by the following formula: In the formula: H is the color entropy of the pixel block; k is the number of color bits in the pixel block; p _i is the probability of the i-th color value in the pixel block; Among them, p _all and p _Del-obj are determined by the color entropy calculation results of pixel blocks. The pixel blocks applied in the cable image output formula in the cable image data are equal in size, and their expressions are composed of x×x pixels. matrix, x is the number of pixels in the vertical and horizontal directions that make up the matrix of pixels. The smaller the pixel block applied in the cable image output formula in the cable image data, the better the accuracy of the remaining cable image p _residue . 5. A quality detection system for flexible mineral insulated flexible fireproof cables according to claim 1, characterized in that, after the segmentation module recognizes the cable image in the cable image data, it is based on the density of the mica tape wrapped on the surface of the cable and The size ratio between the cable image and the actual cable specification parameters sets the segmentation logic. The segmentation logic is expressed as: In the formula: L is the segmentation span of the cable image; W _Cov is the overlap width of the mica tape wrapped on the cable; f _pic is the length of the cable in the cable image; f _real is the actual length of the electric power; Among them, the cable image is divided into several groups of equal-length cable segment images based on the cable image segmentation span L. The cable segment images are sub-cable image data, and the cable segment images are marked sequentially based on the cable conveyor belt transportation direction. The marking logic is: 1 , 2, 3, 4, 5, 6, ..., the configuration module configures the cable segment images based on the marking results of the cable segment images. The configuration logic is expressed as: the cable segment image corresponding to mark 1 and the cable corresponding to mark 2 The segment images are configured with each other, the cable segment image corresponding to mark 2 and the cable segment image corresponding to mark 3 are configured with each other, the cable segment image corresponding to mark 3 is configured with the cable segment image corresponding to mark 4, and so on. 6. A quality detection system and method for flexible mineral insulated flexible fireproof cables according to claim 1, characterized in that in the similarity calculation formula of the matched sub-cable image data, d _color , d _shape and d _{The texture} acquisition logic includes: In the formula: k is the number of color bits in the sub-cable image data; H _a [c] is the color histogram of the color channel value of the cable image data a in the c bit; H _b [c] is the cable image data b in the c bit The color histogram in the color channel value; H _a,o is the o-th component of cable image data a based on Hu moment; H _b,o is the o-th component of cable image data b based on Hu moment; C _a,c is The cable image data a is based on the element of row c and column c of GLCM in the c-bit color channel value; C _{b, c} is the element of the cable image data v based on the row c and column c of GLCM in the c-bit color channel value. . 7. A quality detection system for flexible mineral insulated flexible fireproof cables according to claim 1, characterized in that the image information symmetry is obtained by the following formula: In the formula: M, N are the width and height of the image; X _xy is the gray value of the image at (x, y); is the average gray value of the image; Among them, ξ∈[0, 1]. The larger the ξ value, the better the image information symmetry of the image. On the contrary, it means the worse the image information symmetry of the image. 8. A quality inspection system for flexible mineral insulated flexible fireproof cables according to claim 1, characterized in that the determination layer includes a setting module and a determination module, and the setting module is used to receive the matching stored in the storage module. The image information uniformity and similarity of the sub-cable image are determined, and the cable qualification threshold is set. The determination module is used to determine whether the image information uniformity and similarity of the sub-cable image are within the cable qualification threshold; Among them, there are two sets of qualified judgment thresholds set in the setting module, which are respectively applied to the qualified judgment of the image information uniformity of the sub-cable image, and the qualified judgment of the similarity of the sub-cable image. The uniformity of the image information of the sub-cable image is When the sub-cable image is determined to be qualified, and in the similarity determination result of the sub-cable image, the sub-cable image data that is determined to be qualified is not less than 99% of the total amount of sub-cable image data, the cable from which the sub-cable image is derived is determined to be qualified, and the cable When it is judged to be unqualified, the judgment module synchronously obtains the marks of the sub-cable images corresponding to the uniformity and similarity of the image information that is judged to be unqualified, and sends the obtained sub-cable image marks to the storage module in the comparison layer. The system-side user reads the tag of the sub-cable image data in the storage module. 9. A quality detection system for flexible mineral insulated flexible fireproof cables according to claim 1, characterized in that the receiving module is interactively connected to an analysis module and a storage module through a wireless network, and the receiving module interacts through a wireless network A configuration module is connected to the configuration module. The configuration module is interactively connected to a segmentation module and a collection module through a wireless network. The storage module is interactively connected to a setting module through a wireless network. The setting module is interactively connected to a determination module through the wireless network. 10. A quality detection method for flexible mineral insulated flexible fireproof cables. The method is an implementation method of a quality detection system for flexible mineral insulated flexible fireproof cables as claimed in any one of claims 1 to 9, and its characteristics Yes, including the following steps: Step 1: Collect cable image data and segment the cable image data; Step 11: Recognition stage of cable image in cable image data; Step 12: Setting stage of cable image data segmentation processing logic; Step 2: Obtain the sub-cable image data obtained by segmentation processing, and configure the sub-cable image data; Step 21: Marking stage of sub-cable image data; Step 3: Compare the image information uniformity and similarity of the configured sub-cable image data; Step 31: The setting stage of the image information uniformity and similarity comparison logic of the sub-cable image data; Step 4: Obtain the image information uniformity and similarity comparison results of the configured sub-cable image data, set the qualification threshold, and apply the qualification threshold to determine whether the cable corresponding to the sub-cable image data is qualified; Step 5: Based on the marking of the sub-cable image data, capture the unqualified sub-cable image data in the sub-cable image data of the cable.