A method for infrared image recognition of cable accessories

Abstract

The present invention provides an infrared image recognition method for cable accessories, comprising obtaining current operating status parameters of the cable accessory under test, wherein the current operating status parameters of the cable accessory under test include at least the cable cross-sectional area, real-time operating current, and installation ambient temperature of the cable circuit under test; calculating the temperature value of the cable under test and its cable accessories based on the cable cross-sectional area, real-time operating current, and installation ambient temperature of the cable circuit under test; and inputting the temperature value of the cable and its cable accessories as input into a preset infrared image recognition model to obtain infrared image information of the cable circuit under test. The present invention implements infrared image diagnosis and recognition of crimped defective cable accessories, addressing the problems of poor accuracy and high misjudgment rate in conventional infrared image recognition of crimped defective cable accessories.

Description

Technical Field

[0001] The present invention relates to the technical field of infrared image recognition of cable accessories, and in particular to an infrared image recognition method for cable accessories. Background Art

[0002] In recent years, with the continuous expansion of urban distribution networks and the acceleration of undergrounding of overhead lines, the number of distribution cables has rapidly increased. The health and stability of these cables has become crucial for the safe and reliable operation of urban power grids. Due to the length of power cables and operational maintenance requirements, two cable segments are often connected using cable accessories. However, latent crimping defects caused by human factors on-site may only become apparent after prolonged operation and can be difficult to detect. Therefore, infrared image recognition technology for cable accessories, based on contact resistance and temperature changes, is being used for live detection of crimping defects in cable accessories.

[0003] Cable accessory crimping defects are the most common form of cable accessory defect. These defects are often caused by improper installation, and latent crimping defects are difficult to detect during post-installation testing. However, crimping defects increase the internal contact resistance of cable accessories. Under long-term, high-current operating conditions, the cable accessories experience significant temperature fluctuations, with a temperature difference between the cable accessory and the cable cable. Summary of the Invention

[0004] The purpose of the present invention is to propose an infrared image recognition method for cable accessories to solve the technical problems of poor accuracy and high misjudgment rate in the existing infrared image recognition of crimped defective cable accessories.

[0005] In one aspect, a method for infrared image recognition of cable accessories is provided, comprising:

[0006] Obtaining current operating state parameters of the cable accessory to be tested, wherein the current operating state parameters of the cable accessory include at least the cable cross-sectional area, real-time operating current, and laying environment temperature of the cable line to be tested;

[0007] Calculate the temperature value of the cable to be tested and its cable accessories according to the cable cross-sectional area, real-time operating current and laying environment temperature of the cable line to be tested;

[0008] The temperature values ​​of the cable and its cable accessories are input as input quantities into a preset infrared image recognition model to obtain infrared image information of the cable line to be tested.

[0009] Preferably, the calculating of the temperature value of the cable to be tested and its cable accessories specifically includes:

[0010] Calculate the theoretical temperature value of the cable under test and its accessories under the current operating state according to the cable cross-sectional area, real-time operating current and laying environment temperature of the cable line under test;

[0011] Periodically collecting the real-time operating current of the cable under test, and determining the current state and temperature state in the cable under test, wherein the current state includes stable operation and unstable operation, and the temperature state includes stable and unstable;

[0012] According to the current state and temperature state in the cable to be tested, a corresponding temperature rise model is selected to calculate the temperature rise of the surface temperature of the cable to be tested at the current moment;

[0013] The temperature values ​​of the cable to be tested and its cable accessories at the current moment are determined based on the theoretical temperature values ​​of the cable to be tested and its cable accessories and using the temperature rise of the surface temperature of the cable to be tested at the current moment as an increment.

[0014] Preferably, the theoretical temperature value of the cable to be tested and its cable accessories under the current operating state of the cable accessories to be tested is calculated according to the following formula:

[0015]

[0016] Where I is the current carrying capacity, θ c is the conductor operating temperature, θ a is the ambient temperature, R is the AC resistance of the conductor at the highest operating temperature, W d is the insulation loss around the conductor, λ1 is the metal sheath loss factor, λ2 is the armor loss factor, T1 is the insulation layer thermal resistance, T2 is the water barrier layer thermal resistance, T3 is the outer sheath thermal resistance, and T4 is the surrounding medium thermal resistance.

[0017] Preferably, the step of selecting a corresponding temperature rise model according to the current state in the cable to be tested to calculate the temperature rise of the surface temperature of the cable to be tested at the current moment specifically includes:

[0018] When the current in the cable under test is in a stable state, the temperature rise of the cable surface under test at the current moment is calculated according to the following formula:

[0019] θ c (t) = W c [T a (1-e -at )+T b (1-e -bt )]

[0020] Among them, θ c (t) is the temperature rise of the cable surface temperature at the time of operation t, W c is the power loss per unit length of conductor, T aCalculate the heat loss of the conductor in the equivalent thermal circuit for the transient temperature rise of the cable, T b Calculate the additional heat loss generated by the conductor in the equivalent thermal circuit for the transient temperature rise of the cable. a and b are the calculation coefficients for the transient temperature rise of the cable.

[0021] Preferably, the step of selecting a corresponding temperature rise model according to the current state in the cable to be tested to calculate the temperature rise of the surface temperature of the cable to be tested at the current moment specifically includes:

[0022] When the current state in the cable under test is unstable and the temperature state is unstable, calculate the temperature rise of the surface temperature of the cable under test at the current moment according to the following formula:

[0023]

[0024] in, is the temperature rise of the conductor relative to the cable surface temperature at time t2, that is, the temperature rise of the cable surface temperature at the next moment after time t1; The inverse function of conductor temperature rise is the standard of the basic algorithm; It is the temperature rise of the conductor relative to the cable surface temperature at time t1.

[0025] Preferably, the step of selecting a corresponding temperature rise model according to the current state in the cable to be tested to calculate the temperature rise of the surface temperature of the cable to be tested at the current moment specifically includes:

[0026] When the current state in the cable under test is unstable and the temperature state is stable, the temperature rise of the surface temperature of the cable under test at the current moment is calculated according to the following formula:

[0027]

[0028]

[0029] Among them, t * is the temperature saturation count variable; C XPLE For the hot melt of the cable insulation layer, C Cond is the thermal melting of the cable conductor; θ c2 (∞) is the steady-state temperature rise of the conductor to the skin when the operating current changes; is the temperature rise of the conductor at time t-1; is the temperature rise of the conductor at time t-2.

[0030] Preferably, the preset infrared image recognition model determines the infrared image information of the cable line to be tested through the following steps:

[0031] Determine the temperature gradient scalar value of the image according to the temperature values ​​of the cable to be tested and its cable accessories;

[0032] Set the standard distance parameters and determine the equivalent relationship between the surface temperature of the cable and its accessories at different shooting distances based on the preset relationship between the infrared detector's radiation intensity and the test distance;

[0033] According to the equivalent relationship of the surface temperature of the cable and its cable accessories at different shooting distances, the temperature gradient scalar value of the image is converted into the temperature of the image corresponding to the cable to be tested and its cable accessories detected by the infrared detector, and the brightness characteristics of the infrared image of the cable line are determined according to the temperature of the image corresponding to the cable to be tested and its cable accessories.

[0034] Preferably, determining the temperature gradient scalar value of the image specifically includes:

[0035]

[0036]

[0037] Where |f'(x,y)| is the temperature gradient scalar value of the image at the x,y coordinate position; is the temperature gradient of the image in the x direction; Δx is the temperature change value of the image in the x direction within the range of two adjacent steps; Δt is the step size of the image in the x direction; is the temperature gradient of the image in the y direction; Δy is the temperature change value of the image in the y direction within the range of two adjacent steps; Δt is the step size of the image in the y direction; t i+1 represents the time i+1; t i represents time i; x i+1 Indicates the temperature value in the x direction at time i+1; i Indicates the temperature value in the x direction at time i; y i+1 Indicates the temperature value in the y direction at time i+1; i Indicates the temperature value in the y direction at time i.

[0038] Preferably, the relationship between the radiation intensity of the infrared detector and the test distance specifically includes:

[0039]

[0040] Where E′(λ) represents the radiation intensity of the infrared detector, τ0(λ) is the transmittance of the optical system at wavelength λ, λ represents the wavelength, f′ represents the focal length, D represents the diameter, d represents the distance between the target and the infrared detector, and s represents the object distance.

[0041] Preferably, determining the brightness characteristics of the infrared image of the cable line specifically includes:

[0042] Calculate the variance, standard deviation, kurtosis and entropy of the corresponding pixel grayscale values ​​according to the temperature of the image corresponding to the cable to be tested and its cable accessories; and determine the pixel grayscale value of the mean pixel;

[0043] The brightness characteristics of the infrared image of the cable line are calculated according to the following formula:

[0044] Homo(x,y)=1-E(x,y)×V(x,y)

[0045]

[0046]

[0047] Among them, Homo(x,y) represents the brightness characteristics of the infrared image of the cable line, v x,y and e x,y They represent the standard deviation and mean of the grayscale value in the 5×5 area near the temperature gradient scalar value (x, y).

[0048] In summary, the implementation of the embodiments of the present invention has the following beneficial effects:

[0049] The infrared image recognition method for cable accessories provided by the present invention determines the basic operating conditions of the cable line to be tested, such as the cable cross-sectional area, real-time operating current, and laying environment temperature, and obtains the theoretical temperature values ​​of the cable and its cable accessories under the current operating state of the cable accessories to be tested. The distance relationship between the position of the cable line to be tested and the infrared camera point is determined, and the equivalent relationship of the surface temperature of the cable to be tested and its cable accessories under different shooting distances of the infrared camera is obtained. The infrared spectrum information of the cable line to be tested is determined, and the spatial statistical information characteristic laws such as the surface temperature gradient and grayscale, variance, standard deviation, kurtosis, entropy and homogeneity of the infrared image of the cable to be tested and its cable accessories are obtained. The infrared image diagnosis and recognition of crimped defective cable accessories is realized, and the problems of poor accuracy and high error rate in the traditional infrared image recognition of crimped defective cable accessories are solved. BRIEF DESCRIPTION OF THE DRAWINGS

[0050] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, without paying any creative work, other drawings obtained based on these drawings still fall within the scope of the present invention.

[0051] Figure 1 The figure is a schematic diagram of the main process of a method for infrared image recognition of cable accessories in an embodiment of the present invention. DETAILED DESCRIPTION

[0052] In order to make the objectives, technical solutions and advantages of the present invention more clear, the present invention will be described in further detail below with reference to the accompanying drawings.

[0053] like Figure 1 FIG. 1 is a schematic diagram of an embodiment of an infrared image recognition method for cable accessories provided by the present invention. In this embodiment, the method includes the following steps:

[0054] Obtain the current operating status parameters of the cable accessories to be tested, wherein the current operating status parameters of the cable accessories include at least the cable cross-sectional area, real-time operating current, and laying ambient temperature of the cable line to be tested; that is, the basic operating conditions such as the cable cross-sectional area, real-time operating current, and laying ambient temperature of the cable line to be tested are collected through different collection methods. The collection methods of these parameters are conventional settings in this field and will not be repeated here.

[0055] Furthermore, the temperature values ​​of the cable to be tested and its cable accessories are calculated based on the cable cross-sectional area, real-time operating current, and laying environment temperature of the cable line to be tested; that is, based on the basic operating conditions such as the cable cross-sectional area, real-time operating current, and laying environment temperature of the cable line to be tested, the theoretical temperature values ​​of the cable and its cable accessories under the current operating state of the cable accessories to be tested are obtained.

[0056] In this embodiment, the theoretical temperature values ​​of the cable under test and its cable accessories under the current operating state of the cable under test are calculated based on the cable cross-sectional area of ​​the cable under test, the real-time operating current, and the laying environment temperature of the cable under test. It is understandable that the maximum current carrying capacity allowed for long-term operation of the cable under test can be calculated based on the cable cross-sectional area of ​​the cable under test, the laying environment, and the external ambient temperature. Specifically, the theoretical temperature values ​​of the cable under test and its cable accessories under the current operating state of the cable under test are calculated according to the following formula:

[0057]

[0058] Where I is the current carrying capacity, λ c is the conductor operating temperature, θ a is the ambient temperature, R is the AC resistance of the conductor at the highest operating temperature, W d is the dielectric loss around the conductor, λ1 is the metal sheath loss factor, λ2 is the armor loss factor, T1 is the insulation layer thermal resistance, T2 is the water barrier layer thermal resistance, T3 is the outer sheath thermal resistance, and T4 is the surrounding medium thermal resistance. Since the above formula requires the conductor operating temperature, the ideal conductor operating temperature can be calculated based on other parameters, that is, the theoretical temperature value of the cable under test and its cable accessories.

[0059] The real-time operating current of the cable to be tested is collected periodically, and the current state and temperature state in the cable to be tested are determined, wherein the current state includes stable operation and unstable operation, and the temperature state includes stable and unstable; according to the current state and temperature state in the cable to be tested, a corresponding temperature rise model is selected to calculate the temperature rise of the surface temperature of the cable to be tested at the current moment; it is understandable that according to different current states and temperature states, it can be determined that the temperature change mode of the cable to be tested and its cable accessories is different, and different calculations need to be performed for different situations.

[0060] In this embodiment, when the current state in the cable to be tested is stable, the temperature rise of the surface temperature of the cable to be tested at the current moment is calculated according to the following formula:

[0061] θ c (t) = W c [T a (1-e -at )+T b (le -bt )]

[0062] Among them, θ c (t) is the temperature rise of the cable surface temperature at the time of operation t, W c is the power loss per unit length of conductor, T a Calculate the heat loss of the conductor in the equivalent thermal circuit for the transient temperature rise of the cable, T b The additional heat loss generated by the conductor in the equivalent thermal path is calculated for the transient temperature rise of the cable, where a and b are the coefficients for calculating the transient temperature rise of the cable. This calculation method can be understood to address the temperature rise of the cable conductor relative to the cable surface as a function of the operating time t under a certain stable operating current. However, in a real-time monitoring system, this basic algorithm is no longer applicable when the operating current of the cable line under test changes.

[0063] When the current state in the cable under test is unstable and the temperature state is unstable, calculate the temperature rise of the surface temperature of the cable under test at the current moment according to the following formula:

[0064]

[0065] in, is the temperature rise of the conductor relative to the cable surface temperature at time t2, that is, the temperature rise of the cable surface temperature at the next moment after time t1; The inverse function of conductor temperature rise is the standard of the basic algorithm; =T1 is the temperature rise of the conductor relative to the cable surface temperature. It can be understood that by periodically collecting the real-time operating current of the cable under test and the temperature of the cable surface under test, the current state in the cable system under test can be determined. If I tIf the temperature of the cable conductor under test has not reached the steady-state temperature, the above formula will be used to calculate the temperature rise of the surface temperature of the cable under test.

[0066] When the current state in the cable under test is unstable and the temperature state is stable, the temperature rise of the surface temperature of the cable under test at the current moment is calculated according to the following formula:

[0067]

[0068]

[0069] Among them, t * is the temperature saturation count variable; C XPLE For the hot melt of the cable insulation layer, C Cond is the thermal melting of the cable conductor; θ c2 (∞) is the steady-state temperature rise of the conductor to the skin when the operating current changes; is the temperature rise of the conductor at time t-1; is the temperature rise of the conductor at time t-2. It is understandable that if I t If the temperature of the cable conductor under test has reached the steady-state temperature, the above formula will be used to calculate the temperature rise of the surface temperature of the cable under test; It is not the temperature rise of the conductor at the previous moment, but is calculated by the formula of the previous situation (the current state in the cable to be tested is unstable and the temperature state is unstable).

[0070] The temperature values ​​of the cable to be tested and its cable accessories at the current moment are determined based on the theoretical temperature values ​​of the cable to be tested and its cable accessories and using the temperature rise of the surface temperature of the cable to be tested at the current moment as an increment.

[0071] Furthermore, the temperature values ​​of the cable and its accessories are input into a pre-set infrared image recognition model to obtain infrared image information of the cable line under test. Specifically, based on the distance relationship between the location of the cable line under test and the infrared camera position, the equivalent relationship between the surface temperature of the cable and its accessories under different infrared camera shooting distances is obtained. Based on the infrared spectrum information of the cable line under test, the infrared spectrum cable line temperature, temperature gradient, and spatial statistical information characteristics are obtained.

[0072] In this embodiment, the image's temperature gradient scalar value is determined based on the temperature values ​​of the cable under test and its cable accessories. Understandably, to make even slightly varying physical quantities more prominent and intuitive, differential numerical processing methods are often employed to perform differential or gradient processing on these slightly varying physical quantities. The idea is to extract and filter data information through the differential relationship between two variables. Therefore, using the temperature gradient result provides a more sensitive reflection of the temperature status of cable accessories. The core algorithm formula is as follows:

[0073]

[0074] in, is the temperature gradient of the image in the x direction; Δx is the temperature change value of the image in the x direction within the range of two adjacent steps; Δt is the step size of the image in the x direction.

[0075]

[0076] in, is the temperature gradient of the image in the y direction; Δy is the temperature change value of the image in the y direction within the range of two adjacent steps; Δt is the step size of the image in the y direction.

[0077]

[0078] Where |f'(x,y)| is the temperature gradient scalar value of the image at the x,y coordinate position; t i+1 represents the time i+1; t i represents time i; x i+1 Indicates the temperature value in the x direction at time i+1; i Indicates the temperature value in the x direction at time i; y i+1 Indicates the temperature value in the y direction at time i+1; i Indicates the temperature value in the y direction at time i.

[0079] Set the standard distance parameters and determine the equivalent relationship between the surface temperature of the cable and its cable accessories at different shooting distances based on the relationship between the preset infrared detector's radiation intensity and the test distance. It is understandable that the temperature measurement principle of the infrared thermal imager is mainly to judge the temperature of the object by sensing the radiation transmitted by the object itself. In the actual temperature measurement process, the amount of radiation received by the infrared thermal imaging instrument includes the energy of the object itself and the energy reflected by the surrounding environment.

[0080] L λ =ε λ L bλ (T0)+ρ λ L bv (T U )

[0081] =ε λ L bλ (T0)+(Ia λ )L bλ (T U )

[0082] It can be seen that the first part is the surface spectral radiance, and the second part is the reflected ambient spectral radiance. T0 is the surface temperature of the object being measured; TU is the ambient temperature; ε λ is the surface emissivity; ρ λ is the surface reflectivity; α λ is the surface absorption rate. When the detector is working, it can convert the radiation energy into an electrical signal proportional to the energy. The radiation illumination of the thermal imager is represented by E:

[0083] E=A0d -2 [σ aλ ε λ L bλ (T0)+τ aλ (1-α λ )L bλ (T U )+ε aλ L bλ (T a )]

[0084] Among them, A0 is the visible area of ​​the target corresponding to the thermal imager; d is the distance between the target and the measuring instrument, A0d -2 Generally a constant value; aλ is the surface emissivity; τ aλ is the spectral transmittance of the atmosphere; ε aλ is the atmospheric emissivity.

[0085] Since the black body is the target to be measured, its emissivity is about 1, and it basically does not reflect radiation from other objects. Therefore, for the target to be measured that does not reflect radiation, the radiation intensity is expressed by the following equation:

[0086] E′(λ)=πτ0(λ)εL e (T 0b ,λ)sin 2 u′ m

[0087] Where τ0(λ) is the transmittance of the optical system at wavelength λ; L e (T 0b ,λ) represents wavelength λ, temperature T 0b The brightness of the object when ε is 1, which means the emissivity of the object; sinu′ m is the image-side numerical aperture.

[0088] In the optical system, the symbol f′ represents the focal length, D represents the diameter, and s represents the object distance. The relationship between the test distance and the image side value can be obtained as follows:

[0089]

[0090] Combining the above equations, we can get the relationship between the detector radiation intensity and the test distance:

[0091]

[0092] Where E′(λ) represents the radiation intensity of the infrared detector, τ0(λ) is the transmittance of the optical system at wavelength λ, λ represents the wavelength, f′ represents the focal length, D represents the diameter, d represents the distance between the target and the infrared detector, and s represents the object distance.

[0093] Based on the equivalent relationship between the surface temperatures of cables and their accessories at different shooting distances, the image's temperature gradient scalar value is converted into the temperature of the image corresponding to the cable under test and its accessories, as detected by the infrared detector. The brightness characteristics of the cable line's infrared image are then determined based on the temperature of the image corresponding to the cable under test and its accessories. Specifically, the relationship between detector radiation intensity and test distance is used to set a standard distance parameter, and the detector radiation intensity is normalized. Based on the normalized detector radiation intensity, a grayscale processing method is used to obtain a unique characteristic of the cable line's infrared image brightness. Based on the infrared image characteristics of the cable under test, the temperature and grayscale data of the infrared image of the cable under test are acquired.

[0094] In this embodiment, the variance, standard deviation, kurtosis, and entropy of the corresponding pixel grayscale values ​​are calculated according to the temperature of the image corresponding to the cable to be tested and its cable accessories; and the pixel grayscale value of the mean pixel is determined;

[0095] The brightness characteristics of the infrared image of the cable line are calculated according to the following formula:

[0096] Homo(x,y)=1-E(x,y)×V(x,y)

[0097]

[0098]

[0099] Among them, Homo(x,y) represents the brightness characteristics of the infrared image of the cable line, v x,y and e x,y They represent the standard deviation and mean of the grayscale value in the 5×5 area near the temperature gradient scalar value (x, y).

[0100] Specifically, the grayscale results of the infrared image of the cable line under test are regarded as a two-dimensional random number matrix. The elements of the matrix correspond to the grayscale values ​​of the pixels. The matrix features extracted using spatial statistics can be used as the infrared image features of the cable line under test. In the infrared image recognition method of the cable line under test, three first-order statistical features, namely variance, standard deviation, and kurtosis, are extracted; and two second-order statistical features, namely entropy and homogeneity, are extracted. The calculation method of the infrared image variance statistical feature is:

[0101]

[0102] Variance represents the average of the sum of squares of the deviations between each value in a set of data and its arithmetic mean, reflecting the degree of dispersion or deviation trend between the grayscale values ​​of each pixel.

[0103] The calculation method of the standard deviation statistical characteristics of infrared images is:

[0104]

[0105] The standard deviation is the square root of the variance. Since there is a nonlinear transformation relationship between the variance and the standard deviation, the standard deviation and the variance are meaningful for the multilayer perceptron.

[0106] The calculation method of the infrared image kurtosis statistical characteristics is:

[0107]

[0108] Kurtosis indicates the steepness of the change in the grayscale distribution of an image, and can quickly understand the edge components in the image.

[0109] The calculation method of the statistical characteristics of infrared image entropy is:

[0110]

[0111] Entropy indicates the amount of average information in an image. The entropy of an infrared grayscale image is indirectly related to the average heat output. L is the total number of grayscale levels in the image, which is generally 0 to 255, a total of 256. i is the occurrence probability of gray level i.

[0112] The calculation method of the statistical characteristics of infrared image homogeneity is:

[0113] Homo(x,y)=1-E(x,y)×V(x,y)

[0114]

[0115]

[0116] Among them, v x,y and e x,y Represents the mean square error and mean of the grayscale values ​​within a 5×5 region around pixel (x,y), respectively. Homogeneity, also known as uniformity, reflects the consistency of the data region. In the image field, homogeneity is generally used as the basis for object segmentation algorithms.

[0117] In summary, the implementation of the embodiments of the present invention has the following beneficial effects:

[0118] The infrared image recognition method for cable accessories provided by the present invention determines the basic operating conditions of the cable line to be tested, such as the cable cross-sectional area, real-time operating current, and laying environment temperature, and obtains the theoretical temperature values ​​of the cable and its cable accessories under the current operating state of the cable accessories to be tested. The distance relationship between the position of the cable line to be tested and the infrared camera point is determined, and the equivalent relationship of the surface temperature of the cable to be tested and its cable accessories under different shooting distances of the infrared camera is obtained. The infrared spectrum information of the cable line to be tested is determined, and the spatial statistical information characteristic laws such as the surface temperature gradient and grayscale, variance, standard deviation, kurtosis, entropy and homogeneity of the infrared image of the cable to be tested and its cable accessories are obtained. The infrared image diagnosis and recognition of crimped defective cable accessories is realized, and the problems of poor accuracy and high error rate in the traditional infrared image recognition of crimped defective cable accessories are solved.

[0119] The above disclosure is merely a preferred embodiment of the present invention and certainly cannot be used to limit the scope of the present invention. Therefore, equivalent changes made according to the claims of the present invention are still within the scope of the present invention.

Claims

1. A method for infrared image recognition of cable accessories, characterized in that: include: Obtaining current operating state parameters of the cable accessory to be tested, wherein the current operating state parameters of the cable accessory include at least the cable cross-sectional area, real-time operating current, and laying environment temperature of the cable line to be tested; Calculate the temperature value of the cable to be tested and its cable accessories according to the cable cross-sectional area, real-time operating current and laying environment temperature of the cable line to be tested; Input the temperature values ​​of the cable and its cable accessories as input into a preset infrared image recognition model to obtain infrared image information of the cable line to be tested; The preset infrared image recognition model determines the infrared image information of the cable line to be tested through the following steps: Determine the temperature gradient scalar value of the image according to the temperature values ​​of the cable to be tested and its cable accessories; Set the standard distance parameters and determine the equivalent relationship between the surface temperature of the cable and its accessories at different shooting distances based on the preset relationship between the infrared detector's radiation intensity and the test distance; According to the equivalent relationship of the surface temperature of the cable and its cable accessories at different shooting distances, the temperature gradient scalar value of the image is converted into the temperature of the image corresponding to the cable to be tested and its cable accessories detected by the infrared detector, and the brightness characteristics of the infrared image of the cable line are determined according to the temperature of the image corresponding to the cable to be tested and its cable accessories.

2. The method according to claim 1, wherein The calculation of the temperature value of the cable to be tested and its cable accessories specifically includes: Calculate the theoretical temperature value of the cable under test and its accessories under the current operating state according to the cable cross-sectional area, real-time operating current and laying environment temperature of the cable line under test; Periodically collecting the real-time operating current of the cable under test, and determining the current state and temperature state in the cable under test, wherein the current state includes stable operation and unstable operation, and the temperature state includes stable and unstable; According to the current state and temperature state in the cable to be tested, a corresponding temperature rise model is selected to calculate the temperature rise of the surface temperature of the cable to be tested at the current moment; The temperature values ​​of the cable to be tested and its cable accessories at the current moment are determined based on the theoretical temperature values ​​of the cable to be tested and its cable accessories and using the temperature rise of the surface temperature of the cable to be tested at the current moment as an increment.

3. The method according to claim 2, wherein The theoretical temperature values ​​of the cable under test and its accessories under the current operating state are calculated according to the following formula: Where I is the current carrying capacity, θ c is the conductor operating temperature, θ a is the ambient temperature, R is the AC resistance of the conductor at the highest operating temperature, W d is the insulation loss around the conductor, λ1 is the metal sheath loss factor, λ2 is the armor loss factor, T1 is the insulation layer thermal resistance, T2 is the water barrier layer thermal resistance, T3 is the outer sheath thermal resistance, and T4 is the surrounding medium thermal resistance.

4. The method according to claim 3, wherein The step of selecting a corresponding temperature rise model according to the current state in the cable to be tested to calculate the temperature rise of the surface temperature of the cable to be tested at the current moment specifically includes: When the current in the cable under test is in a stable state, the temperature rise of the cable surface under test at the current moment is calculated according to the following formula: θ c (t)=W c [T a (1-e -at )+T b (1-e -bt )] Among them, θ c (t) is the temperature rise of the cable surface temperature at the time of operation t, W c is the power loss per unit length of conductor, T a Calculate the heat loss of the conductor in the equivalent thermal circuit for the transient temperature rise of the cable, T b Calculate the additional heat loss generated by the conductor in the equivalent thermal circuit for the transient temperature rise of the cable. a and b are the calculation coefficients for the transient temperature rise of the cable.

5. The method according to claim 3, wherein The step of selecting a corresponding temperature rise model according to the current state in the cable to be tested to calculate the temperature rise of the surface temperature of the cable to be tested at the current moment specifically includes: When the current state in the cable under test is unstable and the temperature state is unstable, calculate the temperature rise of the surface temperature of the cable under test at the current moment according to the following formula: in, is the temperature rise of the conductor relative to the cable surface temperature at time t2, that is, the temperature rise of the cable surface temperature at the next moment after time t1; The inverse function of conductor temperature rise is the standard of the basic algorithm; It is the temperature rise of the conductor relative to the cable surface temperature at time t1.

6. The method according to claim 3, wherein The step of selecting a corresponding temperature rise model according to the current state in the cable to be tested to calculate the temperature rise of the surface temperature of the cable to be tested at the current moment specifically includes: When the current state in the cable under test is unstable and the temperature state is stable, calculate the temperature rise of the surface temperature of the cable under test at the current moment according to the following formula: Among them, t * is the temperature saturation count variable; C XPLE For the hot melt of the cable insulation layer, C Cond is the thermal melting of the cable conductor; θ c2 (∞) is the steady-state temperature rise of the conductor to the skin when the operating current changes; is the temperature rise of the conductor at time t-1; is the temperature rise of the conductor at time t-2.

7. The method according to claim 1, wherein Determining the temperature gradient scalar value of the image specifically includes: Where |f'(x,y)| is the temperature gradient scalar value of the image at the x,y coordinate position; is the temperature gradient of the image in the x direction; Δx is the temperature change value of the image in the x direction within the range of two adjacent steps; Δt is the step size of the image in the x direction; is the temperature gradient of the image in the y direction; Δy is the temperature change value of the image in the y direction within the range of two adjacent steps; Δt is the step size of the image in the y direction; t i+1 represents the time i+1; t i represents time i; x i+1 Indicates the temperature value in the x direction at time i+1; i Indicates the temperature value in the x direction at time i; y i+1 Indicates the temperature value in the y direction at time i+1; i Indicates the temperature value in the y direction at time i.

8. The method according to claim 1, wherein The relationship between the radiation intensity of the infrared detector and the test distance specifically includes: Where E′(λ) represents the radiation intensity of the infrared detector, τ0(λ) is the transmittance of the optical system at wavelength λ, λ represents the wavelength, f′ represents the focal length, D represents the diameter, d represents the distance between the target and the infrared detector, and s represents the object distance.

9. The method according to claim 1, wherein Determining the brightness characteristics of the infrared image of the cable line specifically includes: Calculate the variance, standard deviation, kurtosis and entropy of the corresponding pixel grayscale values ​​according to the temperature of the image corresponding to the cable to be tested and its cable accessories; and determine the pixel grayscale value of the mean pixel; The brightness characteristics of the infrared image of the cable line are calculated according to the following formula: Homo(x,y)=1-E(x,y)×V(x,y) Among them, Homo ( x,y ) represents the brightness characteristics of the infrared image of the cable line, v x,y and e x,y They represent the standard deviation and mean of the grayscale value in the 5×5 area near the temperature gradient scalar value (x, y).

Images