A cable production safety intelligent early warning method and system

Abstract

The present invention relates to the field of cable production, and more specifically, to a method and system for intelligent early warning of cable production safety. The method comprises: obtaining a plurality of grayscale images of cable combustion after preprocessing according to a preset sampling interval, constructing a grayscale atlas, and obtaining the pixels of the flame area in each grayscale image; respectively calculating the lateral spread factor and the longitudinal spread factor of the grayscale atlas to calculate the spread index of the grayscale atlas; collecting the smoke volume of each grayscale image, and calculating the smoke volume variance of the grayscale atlas, adding and normalizing the spread index and the smoke volume variance as the evaluation value of the cable flame retardancy, so as to complete the cable production safety early warning. Through the technical solution of the present invention, the accuracy of the cable production safety early warning can be improved, and through automated detection, the labor cost can be reduced and the production quality of the cable can be improved.

Description

Technical Field

[0001] The present invention relates to the field of cable production, and more specifically, to a cable production safety intelligent early warning method and system. Background Art

[0002] As an important carrier of power transmission and information communication, cables play an irreplaceable role in the construction of infrastructure in modern society. In the safety process of cable production, it is necessary to first prepare raw materials including metal conductors, insulating materials, flame retardants and refractory materials, and then in the extrusion and molding steps, the conductors, insulating layers, filling layers and protective sleeves are extruded into cables of specified diameter and shape. In order to ensure the flame retardant performance of the cable, the uniform distribution of flame retardants and refractory materials must be ensured during the production process. If these materials are unevenly distributed, the flame retardant performance of certain parts of the cable will be reduced, thereby increasing the risk of fire in actual use.

[0003] The existing Chinese patent application document with publication number CN111159960A discloses a numerical simulation method for cable fires caused by electrical faults in tunnels. The method includes: inputting a determined initial fire source model, the laying conditions of cables in the cable tunnel, etc. into a FLASH-CAT model to obtain a real-time heat release rate of the fire source in the tunnel, establishing a fire source model for the cable tunnel fire, and directly importing the fire source model into the fluid dynamics calculation software FDS. In FDS, the material properties and boundary conditions of the cable tunnel model are set, the grid is divided, and numerical calculations are performed to obtain the time-varying laws of the temperature, smoke concentration, flame spread, CO concentration, etc. in the cable tunnel, so as to realize the hazard assessment of the cable tunnel fire.

[0004] However, in combustion analysis, it is not accurate to rely solely on the flue gas volume to evaluate the efficiency and environmental impact of the combustion process. This is because the flue gas concentration cannot fully reflect the dynamic changes of the flame during the combustion process, such as the cable burning rate and temperature changes in different combustion stages. These factors have a direct impact on the combustion efficiency and pollutant generation, resulting in inaccurate early warning assessments. Summary of the invention

[0005] In order to solve the problem of inaccurate early warning evaluation, the present invention proposes a cable production safety intelligent early warning method and system.

[0006] In a first aspect, the present invention discloses an intelligent early warning method for cable production safety, comprising: obtaining a plurality of grayscale images of cable combustion after preprocessing according to a preset sampling interval, constructing a grayscale atlas, and obtaining the pixels of the flame area in each grayscale image; respectively calculating the lateral spread factor and the longitudinal spread factor of the grayscale atlas to calculate the spread index of the grayscale atlas; collecting the smoke volume of each grayscale image, and calculating the smoke volume variance of the grayscale atlas, adding and normalizing the spread index and the smoke volume variance as the evaluation value of the cable flame retardancy, so as to complete the cable production safety early warning; the spread index satisfies the relationship:

[0007] ,in, represents the spread index, represents the lateral spreading factor, represents the vertical spread factor, Represents an exponential function.

[0008] By obtaining multiple grayscale images at preset sampling intervals, the pixels in the flame area are accurately captured, and then the horizontal and vertical spread factors of the grayscale atlas are calculated to comprehensively calculate the spread index, so as to quantify the speed and trend of flame spread. At the same time, by collecting and analyzing the smoke volume, the smoke volume variance of the grayscale atlas is calculated to further evaluate the severity of combustion and potential risks. Combining the spread index with the smoke volume variance and normalizing it provides a comprehensive evaluation value, which fully reflects the flame retardant performance of the cable. It not only improves the accuracy and efficiency of the evaluation of the flame retardant performance of the cable, but also provides strong support for safety monitoring and early warning in the cable production process, which helps to timely discover and respond to potential fire risks, ensure production safety, and reduce the possibility of accidents.

[0009] Preferably, the flame area pixel points include: for any grayscale image, pixels with grayscale values ​​less than or equal to 128 are eliminated, the mode of the grayscale values ​​of the remaining pixels is used as the reference grayscale value, a window is constructed with the reference grayscale value as the center and a preset length as the size, and the pixels with grayscale values ​​within the window are used as flame area pixels.

[0010] By eliminating pixels with grayscale values ​​less than or equal to 128, low grayscale noise and background information in the image are removed. Then, the grayscale value mode of the remaining pixels is calculated and used as the reference grayscale value, which helps to determine the typical grayscale characteristics of the flame area.

[0011] Preferably, the lateral spread factor includes: for any grayscale image, constructing a coordinate system, each horizontal coordinate corresponds to a number of vertical coordinates, for the same horizontal coordinate, selecting the pixel point corresponding to the maximum value of the vertical coordinate as the flame edge pixel point, traversing all vertical coordinates, and obtaining a number of flame edge pixel points; calculating the local chaos degree of the flame edge pixel point, taking the mean of all local chaos degrees in the grayscale image as the overall chaos degree, and obtaining the overall chaos degree sequence of the grayscale atlas; subtracting the overall chaos degrees of two consecutive grayscale images in the grayscale atlas to construct a difference sequence, and normalizing the mean and the sum of the variance of the difference sequence as the lateral spread factor.

[0012] By constructing a coordinate system and selecting the maximum vertical coordinate pixel corresponding to each horizontal coordinate, the flame edge pixels are intelligently identified, which helps capture the contour changes of the flame. By calculating the local chaos degree of these flame edge pixels, the scheme evaluates the irregularity and dynamic changes of the flame morphology.

[0013] Preferably, the local disorder degree satisfies the relationship:

[0014] ,in, Indicates The local disorder degree of each flame edge pixel, Indicates The gray value of the flame edge pixel, Indicates The mean gray value of the 8-neighborhood pixel of the flame edge, Indicates The gradient value of the flame edge pixel, Indicates The mean gradient value of the 8-neighborhood pixel of the flame edge, Represents the normalization function.

[0015] Preferably, the lateral spread factor also includes: for any grayscale image, constructing a coordinate system, each horizontal coordinate corresponds to a number of vertical coordinates, for the same horizontal coordinate, selecting the pixel point corresponding to the minimum value of the vertical coordinate as the burning edge pixel point, traversing all vertical coordinates, and obtaining a number of burning edge pixel points; for the same grayscale image, calculating the Euclidean distance between two consecutive edge pixels, taking the cumulative value of all Euclidean distances in the grayscale image as the burning trajectory value of the grayscale image, and traversing to obtain the burning trajectory value of each grayscale image; subtracting the burning trajectory values ​​of two consecutive grayscale images in the grayscale image set and accumulating them to obtain the cumulative difference, and normalizing the ratio of the cumulative difference to the sampling time of the grayscale image set as the lateral spread factor.

[0016] Constructing a coordinate system and selecting the minimum vertical coordinate pixel corresponding to each horizontal coordinate helps capture the boundary of the flame burning. By calculating the Euclidean distance between consecutive edge pixels in the grayscale image and accumulating these distances, the scheme obtains the burning trajectory value of each grayscale image. This metric reflects the diffusion path and range of the flame in the image.

[0017] Preferably, the longitudinal spread factor includes: for any grayscale image, taking the number of pixels in the flame area as the flame area of ​​the grayscale image; obtaining the maximum Euclidean distance of the horizontal coordinates of any two pixels in the flame area in the grayscale image, and constructing a rectangular frame with the maximum Euclidean distance as the length and the maximum horizontal coordinates of all pixels in the flame area as the width; calculating the absolute value of the first difference between the area of ​​the rectangular frame and the flame area, and normalizing the absolute value of the first difference as the irregularity; and taking the average of the irregularity of each grayscale image in the grayscale image set as the longitudinal spread factor.

[0018] By calculating the absolute value of the first difference between the rectangular frame area and the flame area and normalizing it, the irregularity is obtained, which reflects the difference between the flame area and the ideal rectangular frame, quantifies the shape irregularity of the flame area, and can comprehensively consider the size, shape and longitudinal spread characteristics of the flame area.

[0019] Preferably, the longitudinal spread factor also includes: calculating the second absolute value of the difference between the maximum horizontal coordinate value and the mean horizontal coordinate value of all pixels in the flame area, normalizing the sum of the first absolute value of the difference and the second absolute value of the difference as the irregularity; and taking the mean value of the irregularity of each grayscale image in the grayscale image set as the longitudinal spread factor.

[0020] In a second aspect, the present invention discloses a cable production safety intelligent early warning system, comprising: a processor; and a memory, wherein the memory stores computer instructions, and when the computer instructions are executed by the processor, the system executes the above-mentioned cable production safety intelligent early warning method.

[0021] Beneficial effects of the present invention:

[0022] 1. The grayscale image collected by the present invention at preset time intervals can not only capture the subtle changes in the flame area, but also comprehensively evaluate the horizontal and vertical spread of the flame through the calculation of the spread index. This multi-dimensional analysis method enables the early warning system to more accurately identify and predict the trend of flame spread, and further improve the accuracy of analyzing the flame retardant effect of the cable and the production quality through the flame.

[0023] 2. The normalized evaluation value takes the spread index and smoke volume variance into consideration, providing an intuitive flame retardant performance evaluation index, enabling relevant personnel to make quick judgments and responses, significantly improving the efficiency and accuracy of cable flame retardant performance evaluation, and reducing labor costs and improving cable production quality through automated testing, thereby reducing the occurrence of fire accidents, protecting personnel safety and reducing property losses. BRIEF DESCRIPTION OF THE DRAWINGS

[0024] By reading the following detailed description with reference to the accompanying drawings, the above and other objects, features and advantages of the exemplary embodiments of the present invention will become readily understood. In the accompanying drawings, several embodiments of the present invention are shown in an exemplary and non-limiting manner, and the same or corresponding reference numerals represent the same or corresponding parts, wherein:

[0025] Figure 1 It is a flow chart of an intelligent early warning method for cable production safety according to an embodiment of the present invention. DETAILED DESCRIPTION

[0026] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative work are within the scope of protection of the present invention.

[0027] It should be understood that when the terms "first", "second", etc. are used in the claims, descriptions, and drawings of the present invention, they are only used to distinguish different objects, rather than to describe a specific order. The terms "include" and "comprise" used in the description and claims of the present invention indicate the presence of the described features, wholes, steps, operations, elements, and / or components, but do not exclude the presence or addition of one or more other features, wholes, steps, operations, elements, components, and / or their collections.

[0028] The present invention provides a cable production safety intelligent early warning method. Figure 1 As shown, a cable production safety intelligent early warning method includes steps S1 to S3, which are described in detail below.

[0029] S1, obtaining multiple grayscale images of cable burning after preprocessing according to a preset sampling interval, constructing a grayscale atlas, and obtaining the pixels of the flame area in each grayscale image.

[0030] In one embodiment, when the cable is subjected to a combustion test, an industrial camera is fixed to shoot the cable to ensure that the entire process of the cable combustion can be captured. The leftmost end of the test cable is ignited, and the flame burns from the leftmost end to the rightmost end.

[0031] A plurality of RGB (Red Green Blue) images of the cable burning after preprocessing are acquired according to a preset sampling interval. The exemplary preset sampling interval is set to 1 second, which can be specifically set by a person skilled in the art. A grayscale atlas is constructed.

[0032] Crop to remove irrelevant background, convert RGB images into grayscale images, reduce the amount of data in the image, and simplify subsequent processing. Use contrast enhancement algorithms to adjust the visual effect of grayscale images to make the details in grayscale images clearer, use Gaussian filtering algorithms to remove noise in images, and use Sobel operators to enhance the edge details of grayscale images.

[0033] For any grayscale image, remove pixels with grayscale values ​​less than or equal to 128, take the mode of the grayscale values ​​of the remaining pixels as the reference grayscale value, build a window with the reference grayscale value as the center and the preset length as the size, and take the pixels with grayscale values ​​within the window as the pixels of the flame area.

[0034] In one embodiment, the edge detection algorithm is used to obtain the flame edge, and the connected domain is extracted, and the pixel points located in the connected domain are the flame area pixel points.

[0035] S2, respectively calculates the horizontal spreading factor and the vertical spreading factor of the grayscale atlas to calculate the spreading index of the grayscale atlas.

[0036] In one embodiment, calculating the lateral spread factor includes: for any grayscale image, constructing a coordinate system, each horizontal coordinate corresponds to a plurality of vertical coordinates, for the same horizontal coordinate, selecting a pixel point corresponding to the maximum vertical coordinate as a flame edge pixel point, traversing all vertical coordinates, and obtaining a plurality of flame edge pixel points; calculating the local disorder degree of the flame edge pixel point, wherein the local disorder degree satisfies the relationship:

[0037] ,in, Indicates The local disorder degree of each flame edge pixel, Indicates The gray value of the flame edge pixel, Indicates The mean gray value of the 8-neighborhood pixel of the flame edge, Indicates The gradient value of the flame edge pixel, Indicates The mean gradient value of the 8-neighborhood pixel of the flame edge, Represents the normalization function.

[0038] The mean of all local disorder degrees in the grayscale image is taken as the overall disorder degree, and the overall disorder degree sequence of the grayscale atlas is obtained; the overall disorder degrees of two consecutive grayscale images in the grayscale atlas are subtracted to construct a difference sequence, and the sum of the mean and variance of the difference sequence is normalized as the lateral spread factor.

[0039] The calculation of the longitudinal spread factor includes: for any grayscale image, the number of pixels in the flame area is used as the flame area of ​​the grayscale image; the maximum value of the Euclidean distance between the horizontal coordinates of any two pixels in the flame area in the grayscale image is obtained, and a rectangular frame is constructed with the maximum value of the Euclidean distance as the length and the maximum value of the horizontal coordinates of all pixels in the flame area as the width; the absolute value of the first difference between the area of ​​the rectangular frame and the flame area is calculated, and the absolute value of the first difference is normalized as the irregularity, and the irregularity satisfies the relationship:

[0040] ,in, Indicates irregularity, represents the maximum value of the Euclidean distance, Indicates the maximum value of the horizontal coordinate of all pixels in the flame area. represents the flame area, Represents an exponential function. It represents the area of ​​the constructed rectangular box.

[0041] The mean value of the irregularity of each grayscale image in the grayscale image set is taken as the vertical spread factor.

[0042] It should be noted that the irregularity can reflect whether the shape of the flame in the grayscale image is close to a rectangle. If the difference between the area of ​​the rectangular frame and the area of ​​the flame is smaller, it means that the shape of the flame in the grayscale image is more rectangular and more regular, which can reflect that the flame burns more evenly and stably when the test cable is ignited. At the same time, considering the influence of the height of the flame on the flame retardant performance of the test cable, when the height of the flame in the grayscale image is higher, it can reflect that the flame retardancy of the test cable is poor.

[0043] The spread index of the grayscale atlas is calculated based on the horizontal spread factor and the vertical spread factor. The spread index satisfies the relationship:

[0044] ,in, represents the spread index, represents the lateral spreading factor, represents the vertical spread factor, Represents an exponential function.

[0045] In one embodiment, the lateral spread factor also includes: for any grayscale image, a coordinate system is constructed, each horizontal coordinate corresponds to a number of vertical coordinates, for the same horizontal coordinate, the pixel point corresponding to the minimum value of the vertical coordinate is selected as the burning edge pixel point, and all vertical coordinates are traversed to obtain a number of burning edge pixel points.

[0046] For the same grayscale image, the Euclidean distance between two consecutive edge pixels is calculated, and the cumulative value of all Euclidean distances in the grayscale image is used as the combustion trajectory value of the grayscale image. The combustion trajectory value of each grayscale image is traversed to obtain the combustion trajectory value of each grayscale image. The combustion trajectory values ​​of two consecutive grayscale images in the grayscale image set are subtracted and accumulated to obtain the cumulative difference. The ratio of the cumulative difference to the sampling time of the grayscale image set is normalized as the lateral spread factor.

[0047] In one embodiment, the longitudinal spread factor also includes: calculating the second absolute value of the difference between the maximum horizontal coordinate value and the mean horizontal coordinate value of all pixels in the flame area, normalizing the sum of the first absolute value of the difference and the second absolute value of the difference as the irregularity; and taking the mean of the irregularity of each grayscale image in the grayscale image set as the longitudinal spread factor.

[0048] S3, collects the smoke volume of each grayscale image, and calculates the smoke volume variance of the grayscale atlas. The spread index and the smoke volume variance are added and normalized to obtain the evaluation value of the cable flame retardancy to complete the cable production safety warning.

[0049] In one embodiment, a smoke sensor is installed at the exhaust port of the test cable for the combustion experiment, the smoke volume corresponding to the acquisition time of each grayscale image in the grayscale image set is obtained, and the smoke volume variance of all grayscale images is calculated.

[0050] Calculate the evaluation value of cable flame retardancy, the evaluation value of cable flame retardancy satisfies the relationship:

[0051] ,in, Indicates the evaluation value of cable flame retardancy. represents the flue gas volume variance, represents the spread index, Represents an exponential function.

[0052] The evaluation value of the flame retardancy of the cable is compared with the preset evaluation value threshold. When the evaluation value is less than or equal to the preset evaluation value threshold, a safety warning is issued to remind relevant technical personnel to inspect and recycle the cables of the batch to which the test cable belongs.

[0053] Exemplarily, the preset evaluation value threshold is set to 0.7, which can be specifically set by those skilled in the art.

[0054] An embodiment of the present invention further discloses a cable production safety intelligent early warning system, including a processor and a memory, wherein the memory stores computer program instructions, and when the computer program instructions are executed by the processor, a cable production safety intelligent early warning method according to the present invention is implemented.

[0055] The above system also includes other components well known to those skilled in the art, such as a communication bus and a communication interface, and their configuration and functions are known in the art, so they will not be described in detail here.

[0056] In the present invention, the aforementioned memory may be any tangible medium containing or storing a program, which may be used by or in combination with an instruction execution system, apparatus or device. For example, a computer-readable storage medium may be any appropriate magnetic storage medium or magneto-optical storage medium, such as a resistive random access memory RRAM (Resistive Random Access Memory), a dynamic random access memory DRAM (Dynamic Random Access Memory), a static random access memory SRAM (Static Random-Access Memory), an enhanced dynamic random access memory EDRAM (Enhanced Dynamic Random Access Memory), a high-bandwidth memory HBM (High-Bandwidth Memory), a hybrid memory cube HMC (Hybrid Memory Cube), etc., or any other medium that can be used to store the required information and can be accessed by an application, a module or both. Any such computer storage medium may be part of a device or accessible or connectable to a device.

[0057] Although this specification has shown and described a number of embodiments of the present invention, it will be apparent to those skilled in the art that such embodiments are provided by way of example only. Those skilled in the art will conceive of many modifications, changes and alternatives without departing from the ideas and spirit of the present invention. It should be understood that in the practice of the present invention, various alternatives to the embodiments of the present invention described herein may be employed.

[0058] The above are all preferred embodiments of the present invention, and are not intended to limit the protection scope of the present invention. Therefore, any equivalent changes made based on the structure, shape, and principle of the present invention should be included in the protection scope of the present invention.

Claims

1. A cable production safety intelligent early warning method, characterized in that: include: Acquire multiple grayscale images of cable burning after preprocessing according to a preset sampling interval, construct a grayscale atlas, and obtain the pixel points of the flame area in each grayscale image; Calculate the horizontal spreading factor and the vertical spreading factor of the grayscale atlas respectively to calculate the spreading index of the grayscale atlas; The smoke volume corresponding to the time of each grayscale image is collected, and the smoke volume variance of the grayscale image set is calculated. The spread index and the smoke volume variance are added and normalized as the evaluation value of the cable flame retardancy to complete the cable production safety early warning; The spreading index satisfies the relationship: ,in, represents the spread index, represents the lateral spreading factor, represents the vertical spread factor, Represents an exponential function.

2. The intelligent early warning method for cable production safety according to claim 1 is characterized in that: The flame area pixels include: For any grayscale image, remove pixels with grayscale values ​​less than or equal to 128, take the mode of the grayscale values ​​of the remaining pixels as the reference grayscale value, build a window with the reference grayscale value as the center and the preset length as the size, and take the pixels with grayscale values ​​within the window as the pixels of the flame area.

3. The intelligent early warning method for cable production safety according to claim 1 is characterized in that: The lateral spread factors include: For any grayscale image, a coordinate system is constructed, where each horizontal coordinate corresponds to several vertical coordinates. For the same horizontal coordinate, the pixel corresponding to the maximum vertical coordinate is selected as the flame edge pixel, and all vertical coordinates are traversed to obtain several flame edge pixels. Calculate the local disorder degree of the flame edge pixel points, take the average of all local disorder degrees in the grayscale image as the overall disorder degree, and obtain the overall disorder degree sequence of the grayscale atlas; The overall chaos degree of two consecutive grayscale images in the grayscale image set is subtracted to construct a difference sequence, and the sum of the mean and variance of the difference sequence is normalized as the horizontal spread factor.

4. The intelligent early warning method for cable production safety according to claim 3 is characterized in that: The local disorder degree satisfies the relationship: ,in, Indicates The local disorder degree of each flame edge pixel, Indicates The gray value of the flame edge pixel, Indicates The mean gray value of the 8-neighborhood pixel of the flame edge, Indicates The gradient value of the flame edge pixel, Indicates The mean gradient value of the 8-neighborhood pixel of the flame edge, Represents the normalization function.

5. The intelligent early warning method for cable production safety according to claim 1 is characterized in that: The lateral spread factors also include: For any grayscale image, a coordinate system is constructed, where each horizontal coordinate corresponds to several vertical coordinates. For the same horizontal coordinate, the pixel corresponding to the minimum vertical coordinate is selected as the burning edge pixel, and all vertical coordinates are traversed to obtain several burning edge pixels; For the same grayscale image, the Euclidean distance between two consecutive edge pixels is calculated, and the accumulated value of all Euclidean distances in the grayscale image is used as the combustion trajectory value of the grayscale image. The combustion trajectory value of each grayscale image is obtained by traversing. The combustion trajectory values ​​of two consecutive grayscale images in the grayscale atlas are subtracted and accumulated to obtain the cumulative difference, and the ratio of the cumulative difference to the sampling time of the grayscale atlas is normalized as the lateral spread factor.

6. The intelligent early warning method for cable production safety according to claim 1 is characterized in that: The vertical spread factors include: For any grayscale image, the number of pixels in the flame area is taken as the flame area of ​​the grayscale image; Obtain the maximum value of the Euclidean distance between the horizontal coordinates of any two pixels in the flame area in the grayscale image, and construct a rectangular frame with the maximum value of the Euclidean distance as the length and the maximum value of the horizontal coordinates of all pixels in the flame area as the width; Calculating the absolute value of the first difference between the area of ​​the rectangular frame and the area of ​​the flame, and normalizing the absolute value of the first difference as the irregularity; The mean value of the irregularity of each grayscale image in the grayscale image set is taken as the vertical spread factor.

7. The intelligent early warning method for cable production safety according to claim 6 is characterized in that: The vertical spread factor also includes: Calculate the second absolute value of the difference between the maximum value of the horizontal coordinate and the mean value of the horizontal coordinate of all the pixels in the flame area, and normalize the sum of the first absolute value of the difference and the second absolute value of the difference as the irregularity; The mean value of the irregularity of each grayscale image in the grayscale image set is taken as the vertical spread factor.

8. An intelligent early warning system for cable production safety, characterized in that: include: Processor; and A memory storing computer instructions, wherein when the computer instructions are executed by a processor, the system executes a cable production safety intelligent early warning method according to any one of claims 1 to 7.

Images