Substation equipment defect detection system and method based on visual recognition

Abstract

The present invention discloses a substation equipment defect detection system and method based on visual recognition, which specifically relates to the field of defect detection technology, including: step 1: obtaining the current appearance image and the current internal image of the substation equipment in the topological power grid area at time T, where the value of T is 1; step 2: obtaining the current evaluation coefficient of the substation equipment based on the current appearance image and the current internal image of the substation equipment; step 3: extracting the historical appearance image and the historical internal image of the substation equipment at time T‑a, and obtaining the historical evaluation coefficient of the substation equipment based on the historical appearance image and the historical internal image of the substation equipment; the present invention combines the optical image of the appearance of the substation equipment with the internal temperature distribution map of the transformer, and through real-time monitoring, historical comparison and automatic fault detection, effectively improves the efficiency and accuracy of substation equipment monitoring and maintenance, and improves the safety and reliability of the equipment.

Description

Technical Field

[0001] The present invention relates to the technical field of defect detection, and more specifically, to a substation equipment defect detection system and method based on visual recognition. Background Art

[0002] Substation equipment plays a vital role in the power system and is responsible for the transmission and distribution of electric energy. Since substation equipment is often exposed to the external environment during operation, the status detection and fault detection of the equipment are particularly important. Traditional equipment detection methods mainly rely on manual inspections and regular maintenance, which is not only time-consuming and labor-intensive, but also easily affected by human factors, resulting in untimely or inaccurate detection. With the advancement of science and technology, automated detection technology has gradually become an important means of substation equipment detection. The existing computer vision technology is used to obtain images of substation equipment through image acquisition devices (such as cameras, infrared cameras, etc.), and combined with image processing and machine learning algorithms to analyze the status of the equipment, which can effectively identify the defects of the equipment. For example, the patent application with publication number CN117934360A discloses a method for detecting thermal defects of substation power equipment based on infrared images. Although the above method can avoid false alarms of thermal defects of substation power equipment, the inventor has studied and applied the above method and the prior art and found that the above method and the prior art have at least the following defects:

[0003] 1. Since the exterior of substation equipment is usually made of metal, exposure problems are prone to occur when acquiring optical images, affecting image quality, which in turn leads to errors in defect detection and affects the accuracy of fault identification.

[0004] 2. The efficiency of using infrared images alone to identify faults in substation power equipment is low, and it may take multiple repeated identifications to accurately determine the defects of the equipment. This not only reduces the efficiency of substation equipment defect detection, but also reduces the automation level and accuracy of the detection process, which is not conducive to ensuring the stable operation of the power system.

[0005] To this end, the present invention provides a substation equipment defect detection system and method based on visual recognition. Summary of the invention

[0006] In order to overcome the above defects of the prior art, the present invention provides a substation equipment defect detection system and method based on visual recognition to solve the problems raised in the above background technology.

[0007] To achieve the above objectives, in a first aspect, the present invention provides the following technical solution: a method for detecting substation equipment defects based on visual recognition, comprising:

[0008] Step 1: Obtain the current appearance image and current internal image of the substation equipment in the topological power grid area at time T, where the value of T is 1;

[0009] Step 2: obtaining a current evaluation coefficient of the substation equipment based on the current appearance image and the current internal image of the substation equipment;

[0010] Step 3: extract the historical appearance image and the historical internal image of the substation equipment at time Ta, and obtain the historical evaluation coefficient of the substation equipment based on the historical appearance image and the historical internal image of the substation equipment; a is an integer greater than or equal to 1;

[0011] Step 4: determine whether the current evaluation coefficient is less than or equal to the historical evaluation coefficient, obtain a determination result, and obtain a fault image of the substation equipment according to the determination result;

[0012] Step 5: Transmit the fault image to the user management terminal.

[0013] Furthermore, the method for obtaining the current appearance image of the substation equipment in the topological power grid area includes:

[0014] Step a1: collect optical images of substation equipment through industrial cameras and divide them into A×B to obtain M areas, where M=A×B;

[0015] Step a2: grayscale the optical image and mark it as an appearance grayscale image, and obtain the grayscale value of each pixel in the appearance grayscale image; count the number of pixels in each area of ​​the optical image, and calculate the number of pixels in each area;

[0016] Step a3: Calculate the grayscale value mean of the M regions, and determine whether it exceeds the grayscale value threshold according to the grayscale value mean;

[0017] If the gray value mean exceeds the gray value threshold, the gray value mean of the M regions is exposed and adjusted to obtain the current appearance image;

[0018] If the gray value mean does not exceed the gray value threshold, the corresponding optical image is used as the current appearance image of the substation equipment.

[0019] Furthermore, the method for obtaining the current internal image of the substation equipment in the topological power grid area includes:

[0020] Step b1: obtaining a first serial number of a current appearance image of a substation device;

[0021] Step b2: collecting an infrared image of the substation equipment by using an infrared thermal imager and marking the infrared image with a second number;

[0022] Step b3: taking the second number that satisfies the preset corresponding relationship with the first number as an associated mark, and acquiring the corresponding infrared image based on the associated mark as the current internal image of the substation equipment.

[0023] Furthermore, the method for obtaining the current evaluation coefficient of the substation equipment includes:

[0024] Based on the current appearance image of the substation equipment, obtaining a pixel mean value of the current appearance image;

[0025] Based on the current internal image of the substation equipment, obtaining a temperature difference value of the current internal image;

[0026] The pixel mean and temperature difference are marked as Xj and Wz respectively;

[0027] The pixel mean and temperature difference are dimensionless and then calculated using a formula to obtain the current evaluation coefficient of the substation equipment.

[0028] Furthermore, the method for obtaining the pixel mean of the current appearance image includes:

[0029] Step c1: performing content recognition on the current appearance image of the substation equipment to obtain a target sub-image;

[0030] Step c2: Obtain the total number of pixels in the current appearance image and divide it by the number of pixels in the target sub-image to obtain the pixel mean of the current appearance image.

[0031] Furthermore, the method for obtaining the temperature difference of the current internal image includes:

[0032] Step d1: grayscale processing is performed on the current internal image of the substation equipment to obtain an infrared grayscale image;

[0033] Step d2: marking the first representation frame and the second representation frame in the infrared grayscale image;

[0034] Step d3: Calculate the average distance between the first representation frame and the second representation frame based on the distance formula, and use the average distance between the first representation frame and the second representation frame as the temperature difference of the current internal image.

[0035] Further, the method of judging whether the current evaluation coefficient is less than or equal to the historical evaluation coefficient and obtaining the judgment result includes:

[0036] Compare current assessment coefficients with historical assessment coefficients;

[0037] If the current evaluation coefficient is less than or equal to the historical evaluation coefficient, return to step 1 and set T = T + a;

[0038] If the current assessment coefficient is greater than the historical assessment coefficient, the difference between the current assessment coefficient and the historical assessment coefficient is used as the operation assessment difference, and the operation assessment difference is analyzed to determine whether there is any abnormality in the transformer equipment.

[0039] Furthermore, the method of analyzing the operation evaluation difference and determining whether there is any abnormality in the transformer equipment includes:

[0040] comparing the operation evaluation difference with a preset operation evaluation difference threshold;

[0041] If the operation evaluation difference is less than or equal to the preset operation evaluation difference threshold, it is determined that there is no abnormality in the substation equipment, and the process returns to step 1;

[0042] If the operation evaluation difference is greater than a preset operation evaluation difference threshold, it is determined that there is an abnormality in the substation equipment, and the current appearance image of the substation equipment is analyzed to obtain a fault image of the substation equipment.

[0043] Furthermore, the method of analyzing the current appearance image of the substation equipment to obtain the fault image of the substation equipment includes:

[0044] Divide the current appearance image of the substation equipment to obtain Q image sub-regions of the current appearance image, and mark them as current sub-regions;

[0045] Divide the historical appearance image of the substation equipment to obtain the corresponding image sub-regions of the historical appearance image, and mark them as historical sub-regions;

[0046] Extract the brightness value of the current sub-region and the brightness value of the historical sub-region, and calculate the brightness difference coefficient based on the formula;

[0047] A preset coefficient threshold is set, and the brightness difference coefficient is compared with the preset coefficient threshold. If the brightness difference coefficient is greater than or equal to the coefficient threshold, the current appearance image and the corresponding current internal image are used as the fault image of the substation equipment. If the brightness difference coefficient is less than the coefficient threshold, only the current internal image is marked as a fault image, and a fault warning is generated.

[0048] In a second aspect, the present invention provides a substation equipment defect detection system based on visual recognition, which is used to implement the above-mentioned substation equipment defect detection method based on visual recognition, comprising:

[0049] The image acquisition module is used to obtain the current appearance image and the current internal image of the substation equipment in the topological power grid area at time T, where the value of T is 1;

[0050] An image analysis module, for acquiring a current evaluation coefficient of the substation equipment based on a current appearance image and a current internal image of the substation equipment;

[0051] A historical analysis module, used to extract the historical appearance image and the historical internal image of the substation equipment at time Ta, and obtain the historical evaluation coefficient of the substation equipment based on the historical appearance image and the historical internal image of the substation equipment; a is an integer greater than or equal to 1;

[0052] A judgment module, used to judge whether the current evaluation coefficient is less than or equal to the historical evaluation coefficient, obtain a judgment result, and obtain a fault image of the substation equipment according to the judgment result;

[0053] The image transmission module is used to transmit the fault image to the user management terminal.

[0054] Technical effects and advantages of the present invention:

[0055] 1. The present invention effectively analyzes and adjusts the optical image of the substation equipment, ensures the quality and reliability of the image, obtains the current appearance image, and improves the accuracy for judging whether the transformer equipment is faulty.

[0056] 2. At time T, obtain the current appearance image and current internal image of the substation equipment in the topological power grid area; obtain the current evaluation coefficient of the substation equipment based on the current appearance image and current internal image of the substation equipment; extract the historical appearance image and historical internal image of the substation equipment at time Ta, and obtain the historical evaluation coefficient of the substation equipment based on the historical appearance image and historical internal image of the substation equipment; determine whether the current evaluation coefficient is less than or equal to the historical evaluation coefficient, obtain a judgment result, and obtain a fault image of the substation equipment according to the judgment result; transmit the fault image to the user management end; the present invention combines the optical image of the appearance of the substation equipment with the internal temperature distribution map of the transformer, and through real-time monitoring, historical comparison and automatic fault detection, effectively improves the efficiency and accuracy of substation equipment monitoring and maintenance, and improves the safety and reliability of the equipment. BRIEF DESCRIPTION OF THE DRAWINGS

[0057] Figure 1 This is a flow chart of a method for detecting substation equipment defects based on visual recognition according to Example 1;

[0058] Figure 2 is the infrared grayscale image of Example 1;

[0059] Figure 3 This is a schematic diagram of the structure of a substation equipment defect detection system based on visual recognition according to Example 2;

[0060] Figure 4 This is a schematic diagram of an electronic device according to Embodiment 3;

[0061] Figure 5 A schematic diagram of a computer-readable storage medium of Example 4. DETAILED DESCRIPTION

[0062] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0063] In addition, the accompanying drawings are only schematic illustrations of the present invention and are not necessarily drawn to scale. The same reference numerals in the figures represent the same or similar parts, and their repeated description will be omitted. Some of the block diagrams shown in the accompanying drawings are functional entities and do not necessarily correspond to physically or logically independent entities. The functional entities can be implemented in software form, or implemented in one or more hardware modules or integrated circuits, or implemented in different networks and / or processor methods and / or microcontroller methods.

[0064] It should be understood that, although the terms "first", "second", etc. may be used herein to describe various units, these units should not be limited by these terms. These terms are used only to distinguish one unit from another unit. For example, without departing from the scope of the exemplary embodiments, a first unit may be referred to as a second unit, and a similar second unit may be referred to as a first unit. The term "and / or" used herein includes any and all combinations of one or more of the listed associated items.

[0065] Example 1

[0066] See also Figure 1 As shown, this embodiment discloses a method for detecting substation equipment defects based on visual recognition, including:

[0067] Step 1: At time T, obtain the current appearance image and current internal image of the substation equipment in the topological power grid area, where the value of T is 1.

[0068] It should be noted that the specific types of substation equipment include but are not limited to transformers, high-voltage switchgear and arc discharge equipment; this embodiment uses transformers as an example to detect equipment defects. The topological grid area is divided based on the geographical location, load distribution or power supply reliability of the urban power grid, which is specifically determined by the staff. Among them, a urban power grid includes several topological grid areas, and each topological grid area contains multiple substation equipment.

[0069] It should also be noted that: the current appearance image and the current internal image of the substation equipment are collected in a time series; the unit of T can be minutes, hours or days.

[0070] It should be understood that the current appearance image of the substation equipment is obtained by taking an optical image of the transformer at any angle using a high-resolution industrial camera. The industrial camera can provide high-resolution images, which are helpful in identifying physical damage, contamination and other abnormal conditions on the appearance of the transformer. The current internal image of the substation equipment is obtained by taking an infrared thermal imaging device to capture the internal temperature distribution map of the transformer at the angle corresponding to the optical image. Infrared thermal imaging can detect the temperature distribution, identify overheating problems inside the transformer, and prevent potential failures.

[0071] In implementation, the method for obtaining the current appearance image of the substation equipment in the topological power grid area includes:

[0072] Step a1: Use an industrial camera to capture the optical image of the substation equipment and divide it into A×B to obtain M areas, where M=A×B.

[0073] It should be noted that the collected optical image is divided into M regions, and due to the equal division process, each region contains the same number of pixels.

[0074] Step a2: grayscale the optical image and mark it as an appearance grayscale image, and obtain the grayscale value of each pixel in the appearance grayscale image; count the number of pixels in each area of ​​the optical image, and calculate the number of pixels in each area; the calculation formula for the number of pixels in each area is:

[0075]

[0076] Where: P m Represents the number of pixels in each area, P 总 represents the total number of pixels in the optical image, and M represents the total number of regions;

[0077] Step a3: Calculate the grayscale value mean of the M regions, and determine whether it exceeds the grayscale value threshold according to the grayscale value mean;

[0078] If the gray value mean exceeds the gray value threshold, the gray value mean of the M regions is exposed and adjusted to obtain the current appearance image;

[0079] It should be noted that: the gray value threshold is determined by technical personnel in this field based on actual needs and a large amount of experimental data; the method for adjusting the exposure of the mean gray value of M areas is to use the "Image" > "Adjustment" > "Auto Levels" function in Photoshop for quick adjustment.

[0080] If the gray value mean does not exceed the gray value threshold, the corresponding optical image is used as the current appearance image of the substation equipment.

[0081] It is additionally noted that the mean grayscale value of the M regions is the exposure intensity of the M regions. An exposure intensity matrix is ​​constructed based on the exposure intensity of the M regions. The exposure intensity matrix is ​​an A'×B' matrix, wherein A'=A, B'=B, and the elements in the A'×B' matrix correspond one-to-one to the regions in the optical image. The exposure intensity matrix is ​​the exposure intensity distribution.

[0082] The calculation method of the gray value mean includes:

[0083]

[0084] Where, Hg m is the mean grayscale value of the mth region in the optical image, Hdmn is the grayscale value of the nth pixel in the mth region of the optical image, m∈[1,M], n∈[1,P m ].

[0085] Since the appearance of transformer equipment is usually made of metal, exposure problems are prone to occur when acquiring optical images, affecting image quality. Through the above steps, the optical image of substation equipment can be effectively analyzed and adjusted to ensure the quality and reliability of the image, so as to obtain the current appearance image, which improves the accuracy of the next step in determining whether the transformer equipment is faulty.

[0086] Specifically, the method for obtaining the current internal image of the substation equipment in the topological power grid area includes:

[0087] Step b1: obtaining a first serial number of a current appearance image of a substation device;

[0088] Step b2: collecting an infrared image of the substation equipment by using an infrared thermal imager and marking the infrared image with a second number;

[0089] Step b3: taking the second number that satisfies the preset corresponding relationship with the first number as an associated mark, and acquiring the corresponding infrared image based on the associated mark as the current internal image of the substation equipment.

[0090] It should be noted that: each substation equipment is preset with a unique first number and a unique second number by the staff. The first number and the second number are set in the substation equipment in the form of digital tags, and each unique first number and unique second number are one-to-one associated and pre-stored in the database. For example, assuming that the first number is S1, the second number is s1, and S1 and s1 are in a preset corresponding relationship, it means that the two substation equipment are the same.

[0091] Step 2: obtaining a current evaluation coefficient of the substation equipment based on the current appearance image and the current internal image of the substation equipment;

[0092] In implementation, the method for obtaining the current evaluation coefficient of the substation equipment includes:

[0093] Based on the current appearance image of the substation equipment, obtaining a pixel mean value of the current appearance image;

[0094] Specifically, the method for obtaining the pixel mean of the current appearance image includes:

[0095] Step c1: performing content recognition on the current appearance image of the substation equipment to obtain a target sub-image;

[0096] It should be noted that content recognition can be achieved through manual selection, can be determined using the color threshold method, or can be achieved through tools such as quick selection in Adobe Photoshop.

[0097] Step c2: Obtain the total number of pixels in the current appearance image and divide it by the number of pixels in the target sub-image to obtain the pixel mean of the current appearance image;

[0098] Based on the current internal image of the substation equipment, obtaining a temperature difference value of the current internal image;

[0099] In implementation, the method for obtaining the temperature difference value of the current internal image includes:

[0100] Step d1: grayscale processing is performed on the current internal image of the substation equipment to obtain an infrared grayscale image;

[0101] Step d2: marking the first representation frame and the second representation frame in the infrared grayscale image;

[0102] like Figure 2 As shown, it should be noted that: the first characterization frame refers to the same pixel point where the temperature of the substation equipment is most concentrated in the infrared grayscale image (marked frame 1), and the second characterization frame refers to the same pixel point where the temperature of the substation equipment is most dispersed in the infrared grayscale image (marked frame 2). The first characterization frame and the second characterization frame can be marked by the staff, or determined according to the distance between the pixel point and the edge;

[0103] Step d3: Calculate the average distance between the first representation frame and the second representation frame based on the distance formula, and use the average distance between the first representation frame and the second representation frame as the temperature difference of the current internal image.

[0104] The pixel mean and temperature difference are marked as Xj and Wz respectively;

[0105] The pixel mean and temperature difference are dimensionless and then calculated using a formula to obtain the current evaluation coefficient of the substation equipment; the calculation formula of the current evaluation coefficient is:

[0106]

[0107] Wherein: Yxp represents the current evaluation coefficient, α1 is the weight factor of the pixel mean, α2 is the weight factor of the temperature difference, α1 and α2 are both greater than zero, ln(·) represents a logarithmic function with e as the base, and the weight factors are all set by technicians in this field based on experience.

[0108] Step 3: extract the historical appearance image and the historical internal image of the substation equipment at time Ta, and obtain the historical evaluation coefficient of the substation equipment based on the historical appearance image and the historical internal image of the substation equipment; a is an integer greater than or equal to 1;

[0109] It should be noted that: the initial value of a is 1, which is the same as the unit of T, and the unit of a is one of minutes, hours or days; it should be noted that the units of T and a are consistent, if the unit of T is minutes, then a is also minutes; the process of obtaining the historical evaluation coefficient is the same as the method of obtaining the current evaluation coefficient mentioned above, and the present invention will not go into details about this, and the historical evaluation coefficient is pre-stored in the database and can be directly retrieved when used.

[0110] Step 4: Determine whether the current evaluation coefficient is less than or equal to the historical evaluation coefficient, and obtain a determination result, and obtain a fault image of the substation equipment according to the determination result.

[0111] In implementation, the method for determining whether the current evaluation coefficient is less than or equal to the historical evaluation coefficient includes:

[0112] Compare current assessment coefficients with historical assessment coefficients;

[0113] If the current evaluation coefficient is less than or equal to the historical evaluation coefficient, return to step 1 and set T = T + a;

[0114] If the current evaluation coefficient is greater than the historical evaluation coefficient, the difference between the current evaluation coefficient and the historical evaluation coefficient is used as the operation evaluation difference, and the operation evaluation difference is analyzed to determine whether there is an abnormality in the transformer equipment.

[0115] It should be noted that: if the current evaluation coefficient is less than or equal to the historical evaluation coefficient, then return to step 1, which means that there is no abnormality or fault in the corresponding substation equipment, and let T=T+a. If the current evaluation coefficient is greater than the historical evaluation coefficient, it means that there is an abnormality or fault in the corresponding substation equipment, and further analysis and determination are required; further explanation is that if T+a=1, and the unit is hour, that is, when a is zero, the current appearance image and the current internal image of the substation equipment at time 1 are obtained. When the current evaluation coefficient is less than or equal to the historical evaluation coefficient, the current appearance image and the current internal image of the substation equipment at time T+a=1+1=2 are obtained.

[0116] Specifically, the method of analyzing the operation evaluation difference and determining whether there is any abnormality in the transformer equipment includes:

[0117] comparing the operation evaluation difference with a preset operation evaluation difference threshold;

[0118] If the operation evaluation difference is less than or equal to the preset operation evaluation difference threshold, it is determined that the substation equipment is abnormal, and the process returns to step 1;

[0119] If the operation evaluation difference is greater than a preset operation evaluation difference threshold, it is determined that the substation equipment is abnormal, and the current appearance image of the substation equipment is analyzed to obtain a fault image of the substation equipment;

[0120] It should be noted that: if the operation evaluation difference is less than or equal to the preset operation evaluation difference threshold, then T=T+a is set and the process returns to step 1, indicating that there is no abnormality in the corresponding power station equipment, and a in the T+a time is increased by 1.

[0121] Specifically, the method of analyzing the current appearance image of the substation equipment to obtain the fault image of the substation equipment includes:

[0122] Divide the current appearance image of the substation equipment to obtain Q image sub-regions of the current appearance image, and mark them as current sub-regions;

[0123] Divide the historical appearance image of the substation equipment to obtain the corresponding image sub-regions of the historical appearance image, and mark them as historical sub-regions;

[0124] Extract the brightness value of the current sub-region and the brightness value of the historical sub-region, and calculate the brightness difference coefficient based on the formula:

[0125]

[0126] Where: Fp represents the brightness difference coefficient, L0 represents the brightness value of the historical sub-region, D represents the brightness value of the current sub-region; q represents the number of brightness difference coefficients, q = 1, 2, ..., Q;

[0127] A preset coefficient threshold is set, and the brightness difference coefficient is compared with the preset coefficient threshold. If the brightness difference coefficient is greater than or equal to the preset coefficient threshold, the current appearance image and the corresponding current internal image are used as the fault image of the substation equipment. If the brightness difference coefficient is less than the preset coefficient threshold, only the current internal image is marked as a fault image, and a fault warning is generated.

[0128] It should be noted that if the brightness difference coefficient is less than the preset coefficient threshold, only the current internal image is marked as a fault image, and the reason for generating a fault warning is that since there is no obvious abnormality in the current appearance image, the abnormal internal temperature of the transformer may be caused by overload operation, short circuit or poor contact of the iron core in the transformer, and it is necessary to remind the staff through an early warning for further maintenance.

[0129] Step 5: Transmit the fault image to the user management terminal.

[0130] It should be noted that: the user management end receives the current appearance image and the corresponding current internal image of the transformer equipment; it is helpful for the staff to perform appearance diagnosis, analyze the abnormal points in the appearance image, and then diagnose the specific damage location and type of the transformer, and perform classification processing (such as surface cleaning, repair or replacement of parts); and it is helpful for the staff to perform internal diagnosis, analyze the hot spots in the temperature distribution map, diagnose possible internal electrical faults or cooling system problems, and determine the severity and cause of the fault (such as winding short circuit, core failure, cooling failure, etc.).

[0131] This embodiment obtains the current appearance image and the current internal image of the substation equipment in the topological power grid area at time T; obtains the current evaluation coefficient of the substation equipment based on the current appearance image and the current internal image of the substation equipment; extracts the historical appearance image and the historical internal image of the substation equipment at time Ta, and obtains the historical evaluation coefficient of the substation equipment based on the historical appearance image and the historical internal image of the substation equipment; determines whether the current evaluation coefficient is less than or equal to the historical evaluation coefficient, obtains the judgment result, and obtains the fault image of the substation equipment according to the judgment result; transmits the fault image to the user management end; This embodiment combines the optical image of the appearance of the substation equipment with the internal temperature distribution map of the transformer, and through real-time monitoring, historical comparison and automatic fault detection, effectively improves the efficiency and accuracy of substation equipment monitoring and maintenance, and improves the safety and reliability of the equipment.

[0132] Example 2

[0133] See also Figure 3 As shown, this embodiment provides a substation equipment defect detection system based on visual recognition, including:

[0134] The image acquisition module is used to obtain the current appearance image and the current internal image of the substation equipment in the topological power grid area at time T, where the value of T is 1;

[0135] An image analysis module, for acquiring a current evaluation coefficient of the substation equipment based on a current appearance image and a current internal image of the substation equipment;

[0136] A historical analysis module, used to extract the historical appearance image and the historical internal image of the substation equipment at time Ta, and obtain the historical evaluation coefficient of the substation equipment based on the historical appearance image and the historical internal image of the substation equipment; a is an integer greater than or equal to 1;

[0137] A judgment module, used to judge whether the current evaluation coefficient is less than or equal to the historical evaluation coefficient, obtain a judgment result, and obtain a fault image of the substation equipment according to the judgment result;

[0138] The image transmission module is used to transmit the fault image to the user management terminal.

[0139] Example 3

[0140] See also Figure 4 As shown, this embodiment provides an electronic device 500. The electronic device 500 may include one or more processors and one or more memories. The memories store computer-readable codes, and when the computer-readable codes are run by one or more processors, the substation equipment defect detection method based on visual recognition as described above may be executed.

[0141] The system according to the embodiment of the present application can also be used Figure 3 The electronic device architecture shown in FIG. Figure 3 As shown, the electronic device 500 may include a bus 501, one or more CPUs 502, a read-only memory (ROM) 503, a random access memory (RAM) 504, a communication port 505 connected to a network, an input / output 506, a hard disk 507, etc. The storage device in the electronic device 500, such as the ROM 503 or the hard disk 507, may store the substation equipment defect detection method based on visual recognition provided by the present application. Furthermore, the electronic device 500 may also include a user interface 508. Of course, Figure 3 The architecture shown is only exemplary and can be omitted according to actual needs when implementing different devices. Figure 3 One or more components of an electronic device are shown.

[0142] Example 4

[0143] See also Figure 5As shown, this embodiment provides a computer-readable storage medium storing instructions. When the instructions are executed on a computer, the computer executes the substation equipment defect detection method based on visual recognition of Example 1.

[0144] The formulas involved in the above are all calculated by removing dimensions and taking their numerical values. They are a formula that is closest to the actual situation obtained by collecting a large amount of data and performing software simulation. The weight factors in the formula and the preset thresholds in the analysis process are set by technicians in this field according to actual conditions or obtained by simulating a large amount of data; the size of the weight factor is to quantify each parameter to obtain a specific value for subsequent comparison. The size of the weight factor depends on the amount of sample data and the corresponding processing coefficient initially set by technicians in this field for each group of sample data; as long as it does not affect the proportional relationship between the parameter and the quantized value.

[0145] The above embodiments can be implemented in whole or in part by software, hardware, firmware or any other combination. When implemented using software, the above embodiments can be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions or computer programs. When the computer instructions or computer programs are loaded or executed on a computer, the process or function described in the embodiment of the present application is generated in whole or in part. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable devices. The computer instructions can be stored in a computer-readable storage medium, or transmitted from one computer-readable storage medium to another computer-readable storage medium. For example, the computer instructions can be transmitted from one website site, computer, server or data center to another website site, computer, server or data center via a wired network. The computer-readable storage medium can be any available medium that a computer can access or a data storage device such as a server or data center that contains one or more available media sets. The available medium can be a magnetic medium (e.g., a floppy disk, a hard disk, a tape), an optical medium (e.g., a DVD), or a semiconductor medium. The semiconductor medium can be a solid-state hard disk.

[0146] Those of ordinary skill in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of this application.

[0147] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working processes of the systems, devices and units described above can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0148] In the several embodiments provided in the present application, it should be understood that the disclosed systems, devices and methods can be implemented in other ways. For example, the device embodiments described above are only schematic. For example, the division of the units is only one. There may be other division methods in actual implementation. For example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.

[0149] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0150] In addition, each functional unit in each embodiment of the present application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit.

[0151] If the functions are implemented in the form of software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present application can be essentially or partly embodied in the form of a software product that contributes to the prior art. The computer software product is stored in a storage medium, including several instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the methods described in the various embodiments of the present application. The aforementioned storage media include: U disk, mobile hard disk, read-only memory (ROM), random access memory (RAM), disk or optical disk, and other media that can store program codes.

[0152] The above is only a specific implementation of the present application, but the protection scope of the present application is not limited thereto. Any person skilled in the art who is familiar with the present technical field can easily think of changes or substitutions within the technical scope disclosed in the present application, which should be included in the protection scope of the present application. Therefore, the protection scope of the present application should be based on the protection scope of the claims.

[0153] Finally: The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present invention should be included in the protection scope of the present invention.

Claims

1. A method for detecting substation equipment defects based on visual recognition, characterized in that: include: Step 1: Obtain the current appearance image and current internal image of the substation equipment in the topological power grid area at time T, where the value of T is 1; The method for obtaining the current appearance image of the substation equipment in the topological power grid area includes: Step a1: collect optical images of substation equipment through industrial cameras and divide them into M areas; Step a2: grayscale the optical image and mark it as an appearance grayscale image, and obtain the grayscale value of each pixel in the appearance grayscale image; count the number of pixels in each area of ​​the optical image, and calculate the number of pixels in each area; Step a3: Calculate the grayscale value mean of the M regions, and determine whether it exceeds the grayscale value threshold according to the grayscale value mean; If the gray value mean exceeds the gray value threshold, the gray value mean of the M regions is exposed and adjusted to obtain the current appearance image; If the gray value mean does not exceed the gray value threshold, the corresponding optical image is used as the current appearance image of the substation equipment; The method for obtaining the current internal image of the substation equipment in the topological power grid area includes: Step b1: obtaining a first serial number of a current appearance image of a substation device; Step b2: collecting an infrared image of the substation equipment by using an infrared thermal imager and marking the infrared image with a second number; Step b3: taking the second number that satisfies the preset corresponding relationship with the first number as an associated mark, and acquiring a corresponding infrared image based on the associated mark as the current internal image of the substation equipment; Step 2: obtaining a current evaluation coefficient of the substation equipment based on the current appearance image and the current internal image of the substation equipment; Methods for obtaining the current evaluation coefficients of substation equipment include: Based on the current appearance image of the substation equipment, obtaining a pixel mean value of the current appearance image; Based on the current internal image of the substation equipment, obtaining a temperature difference value of the current internal image; The pixel mean and temperature difference are marked as Xj and Wz respectively; The pixel mean and temperature difference are dimensionless and then calculated using a formula to obtain the current evaluation coefficient of the substation equipment; Step 3: extract the historical appearance image and the historical internal image of the substation equipment at time Ta, and obtain the historical evaluation coefficient of the substation equipment based on the historical appearance image and the historical internal image of the substation equipment; a is an integer greater than or equal to 1; Step 4: determine whether the current evaluation coefficient is less than or equal to the historical evaluation coefficient, obtain a determination result, and obtain a fault image of the substation equipment according to the determination result; Step 5: Transmit the fault image to the user management terminal.

2. The method for detecting substation equipment defects based on visual recognition according to claim 1 is characterized in that: Methods for obtaining the pixel mean of the current appearance image include: Step c1: performing content recognition on the current appearance image of the substation equipment to obtain a target sub-image; Step c2: Obtain the total number of pixels in the current appearance image and divide it by the number of pixels in the target sub-image to obtain the pixel mean of the current appearance image.

3. The method for detecting substation equipment defects based on visual recognition according to claim 2 is characterized in that: Methods for obtaining the temperature difference of the current internal image include: Step d1: grayscale processing is performed on the current internal image of the substation equipment to obtain an infrared grayscale image; Step d2: marking the first representation frame and the second representation frame in the infrared grayscale image; Step d3: Calculate the average distance between the first representation frame and the second representation frame based on the distance formula, and use the average distance between the first representation frame and the second representation frame as the temperature difference of the current internal image.

4. The method for detecting substation equipment defects based on visual recognition according to claim 3 is characterized in that: The method of judging whether the current evaluation coefficient is less than or equal to the historical evaluation coefficient and obtaining the judgment result includes: Compare current assessment coefficients with historical assessment coefficients; If the current evaluation coefficient is less than or equal to the historical evaluation coefficient, return to step 1 and set T = T + a; If the current evaluation coefficient is greater than the historical evaluation coefficient, the difference between the current evaluation coefficient and the historical evaluation coefficient is used as the operation evaluation difference, and the operation evaluation difference is analyzed to determine whether there is any abnormality in the substation equipment.

5. The method for detecting substation equipment defects based on visual recognition according to claim 4 is characterized in that: Methods for analyzing the operational evaluation difference and determining whether there are abnormalities in the substation equipment include: comparing the operation evaluation difference with a preset operation evaluation difference threshold; If the operation evaluation difference is less than or equal to the preset operation evaluation difference threshold, it is determined that there is no abnormality in the substation equipment, and the process returns to step 1; If the operation evaluation difference is greater than a preset operation evaluation difference threshold, it is determined that there is an abnormality in the substation equipment, and the current appearance image of the substation equipment is analyzed to obtain a fault image of the substation equipment.

6. The method for detecting substation equipment defects based on visual recognition according to claim 5 is characterized in that: The method of analyzing the current appearance image of the substation equipment to obtain the fault image of the substation equipment includes: Divide the current appearance image of the substation equipment to obtain Q image sub-regions of the current appearance image, and mark them as current sub-regions; Divide the historical appearance image of the substation equipment to obtain the corresponding image sub-regions of the historical appearance image, and mark them as historical sub-regions; Extract the brightness value of the current sub-region and the brightness value of the historical sub-region, and calculate the brightness difference coefficient based on the formula; A preset coefficient threshold is set, and the brightness difference coefficient is compared with the preset coefficient threshold. If the brightness difference coefficient is greater than or equal to the preset coefficient threshold, the current appearance image and the corresponding current internal image are used as the fault image of the substation equipment. If the brightness difference coefficient is less than the preset coefficient threshold, only the current internal image is marked as a fault image, and a fault warning is generated.

7. A substation equipment defect detection system based on visual recognition, used to implement the substation equipment defect detection method based on visual recognition as described in any one of claims 1 to 6, characterized in that: include: The image acquisition module is used to obtain the current appearance image and the current internal image of the substation equipment in the topological power grid area at time T, where the value of T is 1; An image analysis module, for acquiring a current evaluation coefficient of the substation equipment based on a current appearance image and a current internal image of the substation equipment; A historical analysis module, used to extract the historical appearance image and the historical internal image of the substation equipment at time Ta, and obtain the historical evaluation coefficient of the substation equipment based on the historical appearance image and the historical internal image of the substation equipment; a is an integer greater than or equal to 1; A judgment module, used to judge whether the current evaluation coefficient is less than or equal to the historical evaluation coefficient, obtain a judgment result, and obtain a fault image of the substation equipment according to the judgment result; The image transmission module is used to transmit the fault image to the user management terminal.

Images