Automatic Diagnosis Method and Device for Defects of Transmission Accessories Based on Fourier Transform Positioning

Abstract

The present invention relates to the technical field of power equipment detection, and discloses an automatic diagnosis method and device for defects of transmission accessories based on Fourier transform positioning. The present invention acquires visible light images and infrared images containing target transmission accessories; based on the regional position of the target transmission accessory in the visible light image, the regional position of the target transmission accessory in the infrared image is obtained, and then the regional image of the target transmission accessory is extracted; the regional image of the target transmission accessory is grayscale processed and two-dimensional Fourier transform is performed, the obtained spectrogram is projected and inverse Fourier transform is performed to obtain the corresponding brightness change curve; based on the brightness change curve, the target overheating area is determined; the relative temperature difference of the target overheating area is calculated, and the relative temperature difference is compared with a preset temperature difference threshold, so as to determine whether there are defects in the target transmission accessory. The present invention can realize the automatic diagnosis of defects of transmission accessories, effectively reduce the operation and maintenance labor cost and improve the operation and maintenance and repair efficiency of transmission accessories.

Description

Technical Field

[0001] The present invention relates to the technical field of power equipment detection, and particularly to an automatic diagnosis method and device for defects of transmission accessories based on Fourier transform positioning. Background Art

[0002] Transmission accessories are an important part of the transmission system and also a weak link in the transmission system. When there are defects in the transmission accessories, the temperature is often higher than that in the normal state. Therefore, in traditional technologies, defect diagnosis of transmission accessories is carried out based on infrared thermal imaging temperature measurement technology. However, the implementation of this method mainly relies on manpower, which not only consumes time and energy, but also relies too much on manual experience, which may lead to missed judgments and misjudgments.

[0003] Existing defect diagnosis schemes for transmission accessories generally achieve automatic diagnosis of transmission accessory defects based on artificial intelligence algorithms. The key to automatic diagnosis of transmission accessory defects lies in identifying the overheated areas of transmission accessories in infrared images. To identify the overheated areas, existing schemes generally use clustering algorithms to divide the grayscale infrared images of transmission accessories. However, the clustering algorithms adopted generally improve the accuracy of division through iterative clustering, which requires a large amount of computing resources and takes a long time, and it is difficult to reflect the defect diagnosis results of transmission accessories in a timely manner. Summary of the Invention

[0004] The present invention provides an automatic diagnosis method and device for defects of transmission accessories based on Fourier transform positioning, which solves the technical problem that the diagnosis efficiency of existing defect diagnosis schemes for transmission accessories needs to be improved.

[0005] In a first aspect of the present invention, an automatic diagnosis method for defects of transmission accessories based on Fourier transform positioning is provided, including:

[0006] Obtaining image information including a target transmission accessory; the image information includes a visible light image and an infrared image;

[0007] Detecting the visible light image to determine the regional position of the target transmission accessory in the visible light image;

[0008] According to the regional position of the target transmission accessory in the visible light image, using the corresponding relationship between the visible light image and the infrared image, determining the regional position of the target transmission accessory in the infrared image;

[0009] According to the regional position of the target transmission accessory in the infrared image, extracting a target transmission accessory regional image;

[0010] Gray-scale the image of the target transmission accessory area, perform two-dimensional Fourier transform on the obtained gray-scale image of the target transmission accessory area to obtain the corresponding frequency spectrum diagram, project and perform inverse Fourier transform on the frequency spectrum diagram to obtain the brightness change curve of the gray-scale image of the target transmission accessory area;

[0011] Perform brightness mutation detection on the brightness change curve to determine the target overheated area of the gray-scale image of the target transmission accessory area;

[0012] Calculate the relative temperature difference of the target overheated area;

[0013] Compare the obtained relative temperature difference with the preset temperature difference threshold, and determine whether there is a defect in the target transmission accessory according to the obtained comparison result.

[0014] According to an implementable manner of the first aspect of the present invention, the detecting the visible light image to determine the regional position of the target transmission accessory in the visible light image includes:

[0015] Detect the visible light image by using a preset deep learning-based transmission accessory target detection model, and output the regional position of the target transmission accessory in the visible light image.

[0016] According to an implementable manner of the first aspect of the present invention, the performing brightness mutation detection on the brightness change curve to determine the target overheated area of the gray-scale image of the target transmission accessory area includes:

[0017] Perform a difference operation on the brightness change curve to obtain a brightness difference function;

[0018] Determine the start mutation coordinate set and end mutation coordinate set of the brightness according to the brightness difference function;

[0019] Combine the start mutation coordinate set and the end mutation coordinate set to obtain the overheated area coordinates of the target overheated area.

[0020] According to an implementable manner of the first aspect of the present invention, the determining the start mutation coordinate set and end mutation coordinate set of the brightness according to the brightness difference function includes:

[0021] Compare each brightness difference function value of the brightness difference function with a mutation threshold;

[0022] Take the coordinates corresponding to the brightness difference function values not less than the mutation threshold as start mutation coordinates to obtain a start mutation coordinate set;

[0023] Take the coordinates corresponding to the brightness difference function values less than the mutation threshold as end mutation coordinates to obtain an end mutation coordinate set.

[0024] According to an implementable manner of the first aspect of the present invention, calculating the relative temperature difference of the target overheated area includes:

[0025] Based on the mapping relationship between the gray value and the temperature, obtain the temperature values corresponding to all pixel points within the target overheated area;

[0026] Average the temperature values corresponding to all the pixel points to obtain the average temperature of the target overheated area;

[0027] Obtain the normal operating temperature and the ambient temperature of the target transmission accessory;

[0028] Calculate the relative temperature difference of the target overheated area according to the average temperature, the normal operating temperature, and the ambient temperature.

[0029] According to an implementable manner of the first aspect of the present invention, comparing the obtained relative temperature difference with a preset temperature difference threshold, and determining whether there is a defect in the target transmission accessory according to the obtained comparison result includes:

[0030] If the obtained relative temperature difference exceeds the preset temperature difference threshold, it is determined that the target transmission accessory has a defect.

[0031] According to an implementable manner of the first aspect of the present invention, the method further includes:

[0032] If the target transmission accessory has a defect, calculate the difference between the relative temperature difference and the preset temperature difference threshold;

[0033] Determine the defect level of the target transmission accessory according to the magnitude of the difference.

[0034] The second aspect of the present invention provides an automatic diagnosis device for transmission accessory defects based on Fourier transform positioning, including:

[0035] An acquisition module, configured to acquire image information including a target transmission accessory; the image information includes a visible light image and an infrared image;

[0036] A detection module, configured to detect the visible light image to determine the regional position of the target transmission accessory in the visible light image;

[0037] A position determination module, configured to determine the regional position of the target transmission accessory in the infrared image according to the regional position of the target transmission accessory in the visible light image and by using the corresponding relationship between the visible light image and the infrared image;

[0038] An extraction module, configured to extract a target transmission accessory region image according to the regional position of the target transmission accessory in the infrared image;

[0039] A curve determination module, configured to perform grayscale processing on the target transmission accessory region image, perform two-dimensional Fourier transform on the obtained grayscale image of the target transmission accessory region to obtain a corresponding spectrogram, perform projection and inverse Fourier transform on the spectrogram, and obtain a brightness change curve of the grayscale image of the target transmission accessory region;

[0040] An overheated region determination module, configured to perform brightness mutation detection on the brightness change curve to determine the target overheated region of the grayscale image of the target transmission accessory region;

[0041] A first calculation module, configured to calculate the relative temperature difference of the target overheated region;

[0042] A defect diagnosis module, configured to compare the obtained relative temperature difference with a preset temperature difference threshold, and determine whether there is a defect in the target transmission accessory according to the obtained comparison result.

[0043] According to an implementable manner of the second aspect of the present invention, the detection module includes:

[0044] A detection unit, configured to detect the visible light image by using a preset transmission accessory target detection model based on deep learning, and output the regional position of the target transmission accessory in the visible light image.

[0045] According to an implementable manner of the second aspect of the present invention, the overheated region determination module includes:

[0046] An operation unit, configured to perform a difference operation on the brightness change curve to obtain a brightness difference function;

[0047] A coordinate determination unit, configured to determine a start mutation coordinate set and an end mutation coordinate set of the brightness according to the brightness difference function;

[0048] A combination unit, configured to combine the start mutation coordinate set and the end mutation coordinate set to obtain the overheated region coordinates of the target overheated region.

[0049] According to an implementable manner of the second aspect of the present invention, the coordinate determination unit includes:

[0050] A comparison subunit, configured to compare each brightness difference function value of the brightness difference function with a mutation threshold;

[0051] A first coordinate determination subunit, configured to use the coordinates corresponding to the brightness difference function values not less than the mutation threshold as start mutation coordinates to obtain a start mutation coordinate set;

[0052] A second coordinate determination subunit, configured to use the coordinates corresponding to the luminance difference function values less than the mutation threshold as the end mutation coordinates, and obtain an end mutation coordinate set.

[0053] According to an implementable manner of the second aspect of the present invention, the first calculation module includes:

[0054] A first acquisition unit, configured to obtain the temperature values corresponding to all pixel points within the target overheated area based on the mapping relationship between the grayscale value and the temperature;

[0055] A first calculation unit, configured to calculate the average of the temperature values corresponding to all the pixel points to obtain the average temperature of the target overheated area;

[0056] A second acquisition unit, configured to obtain the normal operating temperature and the ambient temperature of the target transmission accessory;

[0057] A second calculation unit, configured to calculate the relative temperature difference of the target overheated area based on the average temperature, the normal operating temperature, and the ambient temperature.

[0058] According to an implementable manner of the second aspect of the present invention, the defect diagnosis module includes:

[0059] A defect determination unit, configured to determine that the target transmission accessory has a defect if the obtained relative temperature difference exceeds the preset temperature difference threshold.

[0060] According to an implementable manner of the second aspect of the present invention, the device further includes:

[0061] A second calculation module, configured to calculate the difference between the relative temperature difference and the preset temperature difference threshold if the target transmission accessory has a defect;

[0062] A defect level determination module, configured to determine the defect level of the target transmission accessory according to the magnitude of the difference.

[0063] The third aspect of the present invention provides an automatic diagnosis device for transmission accessory defects based on Fourier transform positioning, including:

[0064] A memory, configured to store instructions; wherein, the instructions are used to implement the automatic diagnosis method for transmission accessory defects based on Fourier transform positioning as described in any of the above implementable manners;

[0065] A processor, configured to execute the instructions in the memory.

[0066] In a fourth aspect of the present invention, a computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, it implements the automatic defect diagnosis method for transmission accessories based on Fourier transform positioning described in any one of the above-mentioned implementable manners.

[0067] As can be seen from the above technical solutions, the present invention has the following advantages:

[0068] The present invention acquires visible light images and infrared images containing target transmission accessories; detects the visible light images to determine the regional position of the target transmission accessories in the visible light images; determines the regional position of the target transmission accessories in the infrared images according to this regional position, and then extracts the regional images of the target transmission accessories; performs grayscale processing on the regional images of the target transmission accessories, performs two-dimensional Fourier transform on the obtained grayscale images of the target transmission accessories to obtain corresponding spectrograms, projects and performs inverse Fourier transform on the spectrograms to obtain the brightness change curve of the grayscale images of the target transmission accessories; performs brightness mutation detection on the brightness change curve to determine the target overheated area of the grayscale images of the target transmission accessories; calculates the relative temperature difference of the target overheated area; compares the obtained relative temperature difference with a preset temperature difference threshold, and determines whether there are defects in the target transmission accessories according to the obtained comparison result; the present invention can realize the automatic diagnosis of transmission accessory defects, effectively reduce the operation and maintenance labor cost, and the process of realizing the identification of the overheated area does not require iterative optimization, which can effectively improve the identification speed of the overheated area, thereby effectively improving the operation and maintenance and repair efficiency of transmission accessories. Description of the Drawings

[0069] In order to more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the following will briefly introduce the drawings required for use in the description of the embodiments or the prior art. Obviously, the following drawings are only some embodiments of the present invention. For those of ordinary skill in the art, without creative efforts, other drawings can also be obtained according to these drawings.

[0070] Figure 1 It is a flowchart of an automatic defect diagnosis method for transmission accessories based on Fourier transform positioning provided by an optional embodiment of the present invention;

[0071] Figure 2 It is a flowchart of an automatic defect diagnosis method for transmission accessories based on Fourier transform positioning provided by another optional embodiment of the present invention;

[0072] Figure 3 It is a structural connection block diagram of an automatic defect diagnosis device for transmission accessories based on Fourier transform positioning provided by an optional embodiment of the present invention;

[0073] Figure 4 The structural connection block diagram of an automatic diagnosis device for transmission accessory defects based on Fourier transform positioning provided by another alternative embodiment of the present invention.

[0074] Reference numerals:

[0075] 1 - Acquisition module; 2 - Detection module; 3 - Position determination module; 4 - Extraction module; 5 - Curve determination module; 6 - Overheating area determination module; 7 - First calculation module; 8 - Defect diagnosis module; 9 - Second calculation module; 10 - Defect level determination module. Specific embodiments

[0076] The embodiments of the present invention provide an automatic diagnosis method and device for transmission accessory defects based on Fourier transform positioning, which are used to solve the technical problem that the diagnosis efficiency of existing transmission accessory defect diagnosis schemes needs to be improved.

[0077] In order to make the object, features, and advantages of the present invention more obvious and understandable, the technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present invention. Obviously, the embodiments described below are only a part of the embodiments of the present invention, rather than all the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative efforts shall fall within the protection scope of the present invention.

[0078] The present invention provides an automatic diagnosis method for transmission accessory defects based on Fourier transform positioning.

[0079] Please refer to Figure 1 , Figure 1 which shows the flowchart of an automatic diagnosis method for transmission accessory defects based on Fourier transform positioning provided by an embodiment of the present invention.

[0080] An automatic diagnosis method for transmission accessory defects based on Fourier transform positioning provided by an embodiment of the present invention includes steps S1 - S8.

[0081] Step S1, acquire image information including the target transmission accessory; the image information includes visible light images and infrared images.

[0082] Among them, the target transmission accessory in this embodiment is a transmission accessory that needs to be automatically diagnosed for defects, such as lightning arresters, circuit breakers, current transformers, capacitors, disconnect switches, and high - voltage bushings, etc.

[0083] Among them, the image information including the target transmission accessory can be collected by a hybrid thermal imaging camera, and then obtained by the execution device of the method described in this embodiment from the hybrid thermal imaging camera. To facilitate the collection of image information, the hybrid thermal imaging camera can be mounted on a drone, for example, mounted at the position of the lower gimbal of the drone. The execution device of the method described in this embodiment can be an embedded computer, and the embedded computer can be mounted under the drone when the hybrid thermal imaging camera is mounted on the drone.

[0084] As a specific implementation, to collect high-quality image information, the thermal imager used by the hybrid thermal imaging camera can be an infrared thermal imaging camera using a non-cooled vanadium oxide microbolometer. The resolution of the infrared thermal imaging camera is 640×512, the measurement temperature range is 40°C to 550°C, and the operating environment temperature range is -10°C to 40°C.

[0085] Step S2, detect the visible light image to determine the regional position of the target transmission accessory in the visible light image.

[0086] In a feasible implementation, a pre-set deep learning-based transmission accessory target detection model is used to detect the visible light image, and the regional position of the target transmission accessory in the visible light image is output.

[0087] In this embodiment, the transmission accessory target detection model is a pre-constructed detection model that can quickly identify transmission accessories, such as the YOLOv5 model. It should be noted that the transmission accessory target detection model can be constructed based on existing deep learning algorithms. As for the specific construction method, it is not limited in this embodiment of the present invention.

[0088] Step S3, according to the regional position of the target transmission accessory in the visible light image, use the correspondence between the visible light image and the infrared image to determine the regional position of the target transmission accessory in the infrared image.

[0089] As a specific implementation, the coordinate correspondence between the visible light image and the infrared image can be determined in advance, and then the regional position of the target transmission accessory in the infrared image is obtained by transformation according to this coordinate correspondence.

[0090] Step S4, extract the target transmission accessory regional image according to the regional position of the target transmission accessory in the infrared image.

[0091] Step S5, perform grayscale processing on the target transmission accessory area image, perform two-dimensional Fourier transform on the obtained grayscale image of the target transmission accessory area to obtain a corresponding spectrogram, project and perform inverse Fourier transform on the spectrogram to obtain the brightness change curve of the grayscale image of the target transmission accessory area.

[0092] Specifically, when implemented, assume that the obtained grayscale image of the target transmission accessory area is G = f(x, y), where f(x, y) is the pixel point with the position coordinates (x, y). After performing two-dimensional Fourier transform, a two-dimensional Fourier spectrogram I = F(u, v) can be obtained, where F(u, v) represents the brightness value of the pixel point with the position coordinates (u, v) in the spectrogram. Project the spectrogram I in the u and v dimensions respectively and perform inverse Fourier transform to obtain the brightness change curves of the grayscale image G on the x and y axes. The brightness change functions on the x and y axes are expressed as:

[0093] p(x) = IFT(F(u, 0)), p(y) = IFT(F(0, v))

[0094] In the formula, IFT(·) is the inverse Fourier transform function.

[0095] Step S6, perform brightness mutation detection on the brightness change curve to determine the target overheated area of the grayscale image of the target transmission accessory area.

[0096] In a realizable manner, the performing brightness mutation detection on the brightness change curve to determine the target overheated area of the grayscale image of the target transmission accessory area includes:

[0097] Perform a difference operation on the brightness change curve to obtain a brightness difference function;

[0098] Determine the start mutation coordinate set and end mutation coordinate set of the brightness according to the brightness difference function;

[0099] Combine the start mutation coordinate set and the end mutation coordinate set to obtain the overheated area coordinates of the target overheated area.

[0100] In a realizable manner, the determining the start mutation coordinate set and end mutation coordinate set of the brightness according to the brightness difference function includes:

[0101] Compare each brightness difference function value of the brightness difference function with a mutation threshold;

[0102] Take the coordinates corresponding to the brightness difference function values not less than the mutation threshold as the start mutation coordinates to obtain the start mutation coordinate set;

[0103] Take the coordinates corresponding to the luminance difference function values less than the mutation threshold as the end mutation coordinates to obtain the set of end mutation coordinates.

[0104] Among them, the expression of the luminance difference function is:

[0105] d(x) = p(x) - p(x + 1), x ≥ 0, x ∈ N +

[0106] d(y) = p(y) - p(y + 1), y ≥ 0, y ∈ N +

[0107] In the formula, d(x) represents the luminance difference function value on the x-axis, d(y) represents the luminance difference function value on the y-axis, and N + represents an integer, p(x) represents the luminance value of the grayscale image G on the x-axis, p(y) represents the luminance value of the grayscale image G on the y-axis, p(x) represents the luminance value of the grayscale image G on the x + 1 axis, and p(y) represents the luminance value of the grayscale image G on the y + 1 axis.

[0108] Then the expression of the set of start mutation coordinates on the x-axis is:

[0109] X s = {x | d(x) ≥ α}

[0110] The expression of the set of start mutation coordinates on the y-axis is:

[0111] Y s = {y | d(y) ≥ β}

[0112] The expression of the set of end mutation coordinates on the x-axis is:

[0113] X e = {x | d(x) < -α}

[0114] The expression of the set of end mutation coordinates on the y-axis is:

[0115] Y e = {y | d(y) < -β}

[0116] In the formula, α and β are preset mutation thresholds;

[0117] Then the coordinates of the i-th overheating area are:

[0118] R i = (x s i , x e i , y s i , y e i )

[0119] where x s i is the i-th element of X s and x e i is also the i-th element of X e and y s i is the i-th element of Y s and y e i is also the i-th element of Y e in the i-th position.

[0120] Step S7: Calculate the relative temperature difference of the target overheated area.

[0121] In the above embodiments of the present invention, based on the idea of Fourier transform positioning, a two-dimensional Fourier transform is performed on the infrared image. According to the brightness characteristics of the overheated area in the spectrogram, the spectrogram is projected on the x and y axes and inverse Fourier transforms are performed separately. The brightness mutation area is detected and located, thereby realizing the identification of the overheated area. This process does not require iterative optimization, can effectively improve the identification speed of the overheated area, and further reduce the time cost of transmission accessory operation and maintenance.

[0122] In an implementable manner, the calculating the relative temperature difference of the target overheated area includes:

[0123] Based on the mapping relationship between the gray value and the temperature, obtain the temperature values corresponding to all pixel points within the target overheated area;

[0124] Average the temperature values corresponding to all pixel points to obtain the average temperature of the target overheated area;

[0125] Obtain the normal operating temperature and the ambient temperature of the target transmission accessory;

[0126] Calculate the relative temperature difference of the target overheated area according to the average temperature, the normal operating temperature and the ambient temperature.

[0127] As a specific implementation manner, the calculation formula for the relative temperature difference of the target overheated area can be:

[0128] δ=(T a -T b ) / (T a -T0)

[0129] where δ represents the relative temperature difference of the target overheated area, T a represents the average temperature, T b represents the normal operating temperature, and T0 represents the ambient temperature.

[0130] It should be noted that in other embodiments, in order to improve the calculation accuracy of the relative temperature difference, the above formula for calculating the relative temperature difference can also be appropriately adjusted and transformed. For example, a preset adjustment factor can be added to the calculation formula.

[0131] Step S8: Compare the obtained relative temperature difference with a preset temperature difference threshold, and determine whether there is a defect in the target transmission accessory according to the obtained comparison result.

[0132] In an implementable manner, if the obtained relative temperature difference exceeds the preset temperature difference threshold, it is determined that there is a defect in the target transmission accessory.

[0133] In another implementable manner, when the difference between the obtained relative temperature difference and the preset temperature difference threshold is greater than the difference threshold, it is determined that there is a defect in the target transmission accessory.

[0134] In this embodiment, the judgment process of the defect of the target transmission accessory can be made adjustable. Among them, the difference threshold can be set according to the actual situation.

[0135] In an implementable manner, on the basis of the method shown in Figure 1 As shown in Figure 2 As shown, the method further includes:

[0136] Step S9: If there is a defect in the target transmission accessory, calculate the difference between the relative temperature difference and the preset temperature difference threshold;

[0137] Step S10: Determine the defect level of the target transmission accessory according to the magnitude of the difference.

[0138] As a specific implementation, a mapping list of the corresponding relationship between the range of the difference magnitude and the defect level can be set, so as to determine the defect level of the target transmission accessory based on the mapping list. Among them, the defect level corresponding to the range of the difference magnitude can be set according to the actual situation.

[0139] Furthermore, the method may further include:

[0140] Send the determination result of whether there is a defect in the target transmission accessory and / or the defect level determined when there is a defect in the target transmission accessory to a preset user terminal.

[0141] In this embodiment, by feeding back the defect diagnosis result to the preset user terminal, it is convenient for relevant personnel to timely understand the situation of the defects of the transmission accessories.

[0142] The present invention also provides a transmission accessory defect automatic diagnosis device based on Fourier transform positioning. This device can be used to execute the transmission accessory defect automatic diagnosis method based on Fourier transform positioning described in any one of the above embodiments of the present invention.

[0143] Please refer to Figure 3 , Figure 3 which shows the structural connection block diagram of an automatic defect diagnosis device for transmission accessories based on Fourier transform positioning provided by an embodiment of the present invention.

[0144] An automatic defect diagnosis device for transmission accessories based on Fourier transform positioning provided by an embodiment of the present invention includes:

[0145] An acquisition module 1, configured to acquire image information including a target transmission accessory; the image information includes a visible light image and an infrared image;

[0146] A detection module 2, configured to detect the visible light image to determine the regional position of the target transmission accessory in the visible light image;

[0147] A position determination module 3, configured to determine the regional position of the target transmission accessory in the infrared image according to the regional position of the target transmission accessory in the visible light image and the corresponding relationship between the visible light image and the infrared image;

[0148] An extraction module 4, configured to extract a target transmission accessory regional image according to the regional position of the target transmission accessory in the infrared image;

[0149] A curve determination module 5, configured to perform grayscale processing on the target transmission accessory regional image, perform two-dimensional Fourier transform on the obtained target transmission accessory regional grayscale image to obtain a corresponding spectrogram, perform projection and inverse Fourier transform on the spectrogram, and obtain a brightness change curve of the target transmission accessory regional grayscale image;

[0150] An overheated area determination module 6, configured to perform brightness mutation detection on the brightness change curve to determine the target overheated area of the target transmission accessory regional grayscale image;

[0151] A first calculation module 7, configured to calculate the relative temperature difference of the target overheated area;

[0152] A defect diagnosis module 8, configured to compare the obtained relative temperature difference with a preset temperature difference threshold, and determine whether the target transmission accessory has a defect according to the obtained comparison result.

[0153] In an implementable manner, the detection module 2 includes:

[0154] A detection unit, configured to detect the visible light image by using a preset deep learning-based transmission accessory target detection model, and output the regional position of the target transmission accessory in the visible light image.

[0155] In an implementable manner, the overheat area determination module 6 includes:

[0156] An operation unit, configured to perform a difference operation on the brightness change curve to obtain a brightness difference function;

[0157] A coordinate determination unit, configured to determine a start mutation coordinate set and an end mutation coordinate set of the brightness according to the brightness difference function;

[0158] A combination unit, configured to combine the start mutation coordinate set and the end mutation coordinate set to obtain the overheat area coordinates of the target overheat area.

[0159] In an implementable manner, the coordinate determination unit includes:

[0160] A comparison subunit, configured to compare each brightness difference function value of the brightness difference function with a mutation threshold;

[0161] A first coordinate determination subunit, configured to use the coordinates corresponding to the brightness difference function values not less than the mutation threshold as start mutation coordinates to obtain a start mutation coordinate set;

[0162] A second coordinate determination subunit, configured to use the coordinates corresponding to the brightness difference function values less than the mutation threshold as end mutation coordinates to obtain an end mutation coordinate set.

[0163] In an implementable manner, the first calculation module 7 includes:

[0164] A first acquisition unit, configured to obtain the temperature values corresponding to all pixel points within the target overheat area based on the mapping relationship between the gray value and the temperature;

[0165] A first calculation unit, configured to average the temperature values corresponding to all pixel points to obtain the average temperature of the target overheat area;

[0166] A second acquisition unit, configured to obtain the normal operating temperature and the ambient temperature of the target transmission accessory;

[0167] A second calculation unit, configured to calculate the relative temperature difference of the target overheat area according to the average temperature, the normal operating temperature, and the ambient temperature.

[0168] In an implementable manner, the defect diagnosis module 8 includes:

[0169] A defect determination unit, configured to determine that the target transmission accessory has a defect if the obtained relative temperature difference exceeds the preset temperature difference threshold.

[0170] In an implementable manner, in Figure 3Based on the device shown above, as Figure 4 shown, the device further includes:

[0171] A second calculation module 9, configured to calculate the difference between the relative temperature difference and the preset temperature difference threshold if there is a defect in the target transmission accessory;

[0172] A defect level determination module 10, configured to determine the defect level of the target transmission accessory according to the magnitude of the difference.

[0173] The present invention also provides an automatic diagnosis device for defects in transmission accessories based on Fourier transform positioning, including:

[0174] A memory, configured to store instructions; wherein, the instructions are used to implement the automatic diagnosis method for defects in transmission accessories based on Fourier transform positioning as described in any one of the above embodiments;

[0175] A processor, configured to execute the instructions in the memory.

[0176] The present invention also provides a computer-readable storage medium, on which a computer program is stored, and when the computer program is executed by a processor, it implements the automatic diagnosis method for defects in transmission accessories based on Fourier transform positioning as described in any one of the above embodiments.

[0177] Those skilled in the art can clearly understand that for the convenience and brevity of description, the specific working processes of the devices and modules described above can refer to the corresponding processes in the foregoing method embodiments, and the specific beneficial effects of the devices and modules described above can refer to the corresponding beneficial effects in the foregoing method embodiments, which will not be elaborated herein.

[0178] In several embodiments provided by the present application, it should be understood that the disclosed devices and methods can be implemented in other ways. For example, the device embodiments described above are merely illustrative. For example, the division of the modules is only a logical function division, and there may be other division methods in actual implementation. For example, multiple modules or components can be combined or integrated into another device, or some features can be ignored or not executed.

[0179] The modules described as separate components may or may not be physically separated, and the components shown as modules may or may not be physical modules, that is, they can be located in one place, or distributed to multiple network modules. Some or all of the modules can be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0180] In addition, in each embodiment of the present invention, each functional module can be integrated into one processing module, or each module can exist physically alone, or two or more modules can be integrated into one module. The above integrated modules can be implemented in the form of hardware or in the form of software functional modules.

[0181] If the above integrated module is implemented in the form of a software functional module and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art, or all or part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions for causing a computer device (which can be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the methods described in each embodiment of the present invention. The foregoing storage medium includes: various media such as USB flash drives, mobile hard disks, read-only memories (ROM, Read-Only Memory), random access memories (RAM, Random Access Memory), magnetic disks, or optical discs that can store program codes.

[0182] As described above, the above embodiments are only used to illustrate the technical solutions of the present invention and are not intended 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 described in the foregoing embodiments, or perform equivalent replacements on some of the technical features; and these modifications or replacements do 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

1. An automatic diagnosis method for defects of transmission accessories based on Fourier transform positioning, characterized in that, Including: Obtaining image information including a target transmission accessory; the image information includes a visible light image and an infrared image; Detecting the visible light image to determine the regional position of the target transmission accessory in the visible light image; According to the regional position of the target transmission accessory in the visible light image, using the corresponding relationship between the visible light image and the infrared image, determining the regional position of the target transmission accessory in the infrared image; Extracting a target transmission accessory regional image according to the regional position of the target transmission accessory in the infrared image; Performing grayscale processing on the target transmission accessory regional image, performing two-dimensional Fourier transform on the obtained target transmission accessory regional grayscale image to obtain a corresponding spectrogram, performing projection and inverse Fourier transform on the spectrogram to obtain a brightness change curve of the target transmission accessory regional grayscale image; Performing brightness mutation detection on the brightness change curve to determine a target overheating region of the target transmission accessory regional grayscale image; Calculating the relative temperature difference of the target overheating region; Comparing the obtained relative temperature difference with a preset temperature difference threshold, and determining whether there is a defect in the target transmission accessory according to the obtained comparison result; The performing brightness mutation detection on the brightness change curve to determine a target overheating region of the target transmission accessory regional grayscale image includes: Performing a difference operation on the brightness change curve to obtain a brightness difference function; Determining a start mutation coordinate set and an end mutation coordinate set of brightness according to the brightness difference function; Combining the start mutation coordinate set and the end mutation coordinate set to obtain the overheating region coordinates of the target overheating region.

2. The automatic defect diagnosis method for transmission accessories based on Fourier transform positioning according to claim 1, characterized in that The detecting the visible light image to determine the regional position of the target transmission accessory in the visible light image includes: Detecting the visible light image by using a preset transmission accessory target detection model based on deep learning, and outputting the regional position of the target transmission accessory in the visible light image.

3. The automatic diagnosis method for transmission accessory defects based on Fourier transform positioning according to claim 1, characterized in that, The determining a start mutation coordinate set and an end mutation coordinate set of brightness according to the brightness difference function includes: Comparing each brightness difference function value of the brightness difference function with a mutation threshold; Taking the coordinates corresponding to the brightness difference function values not less than the mutation threshold as start mutation coordinates to obtain a start mutation coordinate set; Taking the coordinates corresponding to the brightness difference function values less than the mutation threshold as end mutation coordinates to obtain an end mutation coordinate set.

4. The automatic diagnosis method for defects of transmission accessories based on Fourier transform positioning according to claim 1, characterized in that, The calculating the relative temperature difference of the target overheating region includes: Based on the mapping relationship between the grayscale value and the temperature, obtaining the temperature values corresponding to all pixel points in the target overheating region; Averaging the temperature values corresponding to all pixel points to obtain the average temperature of the target overheating region; Obtaining the normal operating temperature and the ambient temperature of the target transmission accessory; Calculating the relative temperature difference of the target overheating region according to the average temperature, the normal operating temperature and the ambient temperature.

5. The automatic diagnosis method for defects of transmission accessories based on Fourier transform positioning according to claim 1, characterized in that The comparing the obtained relative temperature difference with a preset temperature difference threshold, and determining whether there is a defect in the target transmission accessory according to the obtained comparison result includes: If the obtained relative temperature difference exceeds the preset temperature difference threshold, it is determined that there is a defect in the target transmission accessory.

6. The automatic diagnosis method for transmission accessory defects based on Fourier transform positioning according to claim 5, characterized in that The method further includes: If there is a defect in the target transmission accessory, calculate the difference between the relative temperature difference and the preset temperature difference threshold; Determine the defect level of the target transmission accessory according to the magnitude of the difference.

7. An automatic diagnosis device for defects of transmission accessories based on Fourier transform positioning, characterized in that, It includes: An acquisition module, configured to acquire image information including a target transmission accessory; The image information includes a visible light image and an infrared image; A detection module, configured to detect the visible light image to determine the regional position of the target transmission accessory in the visible light image; A position determination module, configured to determine the regional position of the target transmission accessory in the infrared image according to the regional position of the target transmission accessory in the visible light image and the corresponding relationship between the visible light image and the infrared image; An extraction module, configured to extract a target transmission accessory regional image according to the regional position of the target transmission accessory in the infrared image; A curve determination module, configured to perform grayscale processing on the target transmission accessory regional image, perform two-dimensional Fourier transform on the obtained target transmission accessory regional grayscale image to obtain a corresponding spectrogram, perform projection and inverse Fourier transform on the spectrogram, and obtain the brightness change curve of the target transmission accessory regional grayscale image; An overheated area determination module, configured to perform brightness mutation detection on the brightness change curve to determine the target overheated area of the target transmission accessory regional grayscale image; A first calculation module, configured to calculate the relative temperature difference of the target overheated area; A defect diagnosis module, configured to compare the obtained relative temperature difference with the preset temperature difference threshold, and determine whether there is a defect in the target transmission accessory according to the obtained comparison result; The overheated area determination module includes: An operation unit, configured to perform a difference operation on the brightness change curve to obtain a brightness difference function; A coordinate determination unit, configured to determine a start mutation coordinate set and an end mutation coordinate set of the brightness according to the brightness difference function; A combination unit, configured to combine the start mutation coordinate set and the end mutation coordinate set to obtain the overheated area coordinates of the target overheated area.

8. An automatic diagnosis device for transmission accessory defects based on Fourier transform positioning, characterized in that, It includes: A memory, configured to store instructions; wherein, the instructions are used to implement the automatic diagnosis method for defects of transmission accessories based on Fourier transform positioning according to any one of claims 1-6; A processor, configured to execute the instructions in the memory.

9. A computer-readable storage medium, characterized in that, A computer program is stored on the computer-readable storage medium, and when the computer program is executed by the processor, it implements the automatic diagnosis method for defects of transmission accessories based on Fourier transform positioning according to any one of claims 1-6.

Images