A substation inspection image recognition method and system based on image processing

Abstract

The present invention discloses a substation inspection image recognition method and system based on image processing, which relates to the field of substation inspection technology. The method includes: remotely acquiring inspection images of various devices in the substation and marking their acquisition locations and acquisition times; identifying the device type in each inspection image and grouping the inspection images of different device types according to the image acquisition location and acquisition time; using a restricted domain comparison recognition algorithm to sequentially identify whether there are defective devices in each group, ignoring them if not, and proceeding to the next processing step if they are; diagnosing the identified defects based on a defect database, and generating an inspection report based on the diagnosis results and forwarding it to operation and maintenance personnel; regularly integrating the operation and maintenance reports returned by the operation and maintenance personnel into the defect database to ensure the accuracy of the diagnosis results. The restricted domain comparison recognition algorithm of the present invention greatly reduces the influencing factors brought about by acquisition time and acquisition location.

Description

Technical Field

[0001] The present invention relates to the technical field of substation inspection, and in particular to a substation inspection image recognition method and system based on image processing. Background Art

[0002] The recognition method of substation inspection images is one of the key technologies to ensure the safe operation of equipment in the power industry. For example, image processing technology is used to realize flame image detection of power plant boilers, infrared thermal imagers are used to diagnose electrical equipment faults, and deep learning-based defect recognition methods are used. These methods can significantly reduce costs and labor intensity and improve the effectiveness of the inspection process. Although image processing and recognition technology has made significant progress, complex image analysis and state recognition problems are still in the experimental research stage. Substation equipment is of various types, with large differences in appearance, and is easily affected by factors such as ambient lighting and shooting angles, which increases the difficulty of image recognition. In addition, the defect recognition method based on deep learning consumes a huge amount of resources. To solve the above problems, researchers in this field urgently need to develop an inspection image recognition method with high recognition accuracy, high stability, and saving of computing resources. Summary of the Invention

[0003] The present invention provides a substation inspection image recognition method based on image processing, comprising:

[0004] Step 1: Remotely obtain inspection images of each device in the substation and mark the collection location and time;

[0005] Step 2: Identify the device type in each inspection image and group the inspection images of different device types according to the image acquisition location and acquisition time;

[0006] Step 3: Use the restricted domain comparison and recognition algorithm to identify whether there are defective devices in each group. If not, ignore them. If so, proceed to the next processing step.

[0007] Step 4: Diagnose the identified defects based on the defect database, and generate an inspection report based on the diagnosis results and forward it to the operation and maintenance personnel;

[0008] Step 5: Regularly integrate the operation and maintenance reports sent back by operation and maintenance personnel into the defect database to ensure the accuracy of the diagnosis results.

[0009] In the above-mentioned substation inspection image recognition method based on image processing, the device type in each inspection image is identified, which is specifically divided into the following sub-steps:

[0010] Extract identification features of various types of equipment from historical inspection images;

[0011] Associate the identification features of various types of equipment with the equipment type and equipment placement;

[0012] Traverse the received inspection images and query the equipment type whose placement location is consistent with the current collection location;

[0013] Calculate the similarity between the identification features of the current inspection image and each device type in the query result, and use the device type with the highest similarity to annotate the current inspection image.

[0014] The above-mentioned substation inspection image recognition method based on image processing, wherein inspection images of different equipment types are grouped according to the image acquisition location and acquisition time, is specifically divided into the following sub-steps:

[0015] Divide the entire substation area into grids to obtain multiple sub-areas;

[0016] The obtained inspection images are grouped for the first time according to the acquisition time;

[0017] The inspection images are grouped for the second time based on the sub-area to which the acquisition locations belong being the same as the grouping condition to obtain the final grouping data.

[0018] The above-mentioned substation inspection image recognition method based on image processing uses a restricted domain contrast recognition algorithm to sequentially identify whether there is a defective device in each group. The method is specifically divided into the following sub-steps:

[0019] The first inspection image in the group is defined as the starting point of the algorithm;

[0020] Determine whether the device type of the starting image has been identified. If so, reset the algorithm starting point to the next inspection image. If not, extract the inspection image with the same device type as the starting image.

[0021] Traverse the extracted inspection images and calculate the mean difference of each identification feature between the current inspection image and other inspection images;

[0022] If the difference mean is greater than the threshold, the current inspection image is output as a defective device image;

[0023] After the extracted inspection images are traversed, the device type of the batch of inspection images is marked as recognized, and the algorithm starting point is reset to the next inspection image of the current starting image, and recognition continues until all inspection images in the group are recognized.

[0024] The above-mentioned substation inspection image recognition method based on image processing, wherein the identified defects are diagnosed based on the defect database, and an inspection report is generated based on the diagnosis results and forwarded to the operation and maintenance personnel, is specifically divided into the following sub-steps:

[0025] Train a defect diagnosis model based on the data in the defect database;

[0026] Input the defective inspection image features into the defect diagnosis model to obtain the diagnosis results;

[0027] Create an inspection report template and fill the diagnosis results and inspection images into the template to form a complete inspection report.

[0028] The above-mentioned substation inspection image recognition method based on image processing, in which the operation and maintenance reports sent back by the operation and maintenance personnel are regularly integrated into the defect database, is specifically divided into the following sub-steps:

[0029] Determine whether the defect diagnosis results in the returned operation and maintenance report are consistent with those in the inspection report;

[0030] If they are consistent, they are ignored. If they are inconsistent, the defect diagnosis results in the operation and maintenance report shall prevail, and the diagnosis results in the defect database shall be corrected;

[0031] If there is no diagnosis result in the inspection report, the inspection photos in the inspection report and the diagnosis result in the operation and maintenance report are added to the defect database.

[0032] The present invention also provides a substation inspection image recognition system based on image processing, which is characterized by comprising: an inspection image acquisition module, an inspection image grouping module, a defect recognition module, a defect diagnosis module, and a defect data update module;

[0033] Inspection image acquisition module, used to remotely acquire inspection images of each device in the substation and mark the acquisition location and time;

[0034] Inspection image grouping module, used to identify the device type in each inspection image and group inspection images of different device types according to the image acquisition location and acquisition time;

[0035] A defect identification module is used to sequentially identify defective devices in each group using a restricted domain comparison and identification algorithm;

[0036] The defect diagnosis module is used to diagnose identified defects based on the defect database and generate inspection reports based on the diagnosis results and forward them to the operation and maintenance personnel;

[0037] The defect data update module is used to regularly integrate the operation and maintenance reports sent back by operation and maintenance personnel into the defect database to ensure the accuracy of the diagnosis results.

[0038] The beneficial effects achieved by the present invention are as follows: the collection location is used to narrow the recognition range of the device type, thereby improving the recognition speed of the device; the restricted domain comparison recognition algorithm greatly reduces the influencing factors brought by the collection time and collection location; the defect database and defect diagnosis model are regularly updated, which improves the recognition accuracy while also ensuring stability. BRIEF DESCRIPTION OF THE DRAWINGS

[0039] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are only some embodiments described in the present invention. For ordinary technicians in this field, other drawings can also be obtained based on these drawings.

[0040] Figure 1 This is a flow chart of a substation inspection image recognition method based on image processing provided in Example 1 of the present application;

[0041] Figure 2 This is a schematic diagram of a substation inspection image recognition system based on image processing provided in Example 2 of the present application. DETAILED DESCRIPTION

[0042] The following is a clear and complete description of the technical solutions in the embodiments of the present invention, in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of them. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative work are within the scope of protection of the present invention.

[0043] Example 1

[0044] like Figure 1 As shown, the first embodiment of the present application provides a substation inspection image recognition method based on image processing, comprising:

[0045] Step S10: remotely obtain inspection images of each device in the substation and mark the acquisition location and acquisition time;

[0046] A data center is set up in the substation to obtain the inspection images collected by the inspection equipment in real time. The obtained inspection images are marked with the collection location and collection time, and encrypted and stored in the data center.

[0047] Step S20: Identify the device type in each inspection image, and group the inspection images of different device types according to the image acquisition location and acquisition time;

[0048] Current image recognition algorithms can identify the type of objects based on their features. This technology can be used to identify the type of equipment from inspection images. However, considering that equipment within a substation rarely changes its position, it is entirely feasible to shorten image recognition time by taking location into account. Specifically:

[0049] I. Extract identification features of various types of equipment in historical inspection images;

[0050] Image processing technology is used to extract the identification features of various types of equipment from historical inspection images, including color features, shape features, texture features and spatial relationship features. Then, a support vector machine is used to generate an identification weight for each identification feature. The higher the weight, the greater the role of the feature in type identification.

[0051] II. Associate the identifying characteristics of each device with its type and location;

[0052] III. Traverse the received inspection images and query the device type whose placement location matches the current collection location;

[0053] IV. Calculate the similarity between the identification features of the current inspection image and each device type in the query results, and annotate the current inspection image with the device type with the highest similarity;

[0054] The calculation formula for calculating the similarity between the inspection image and the equipment type identification feature is expressed as:

[0055] where a i is the i-th identification feature of the inspection image, μ i is the recognition weight of the i-th recognition feature, b i is the i-th identification feature of a certain device type, i ranges from 1 to n, n is the total number of identification features, and S is the similarity calculation result.

[0056] After the device type of the inspection image is identified, the inspection image is grouped. The specific steps are as follows:

[0057] I. Divide the entire substation area into a grid to obtain multiple sub-areas;

[0058] The parameters for dividing the grid are defined according to the actual application scenario, but it is necessary to ensure that there are more than two devices of the same type in a sub-area. In other words, it is necessary to ensure that each device has a reference for comparison, and this reference must be a device of the same type.

[0059] II. Grouping the acquired inspection images by acquisition time for the first time;

[0060] This step is to ensure that even if there is a problem with the data transmission link that causes a delay in receiving the inspection image, it will not affect the (defect) recognition effect of the inspection image;

[0061] III. Using the same sub-region as the grouping condition, the inspection images are grouped a second time to obtain the final grouped data;

[0062] At this time, the inspection images in a group all come from one sub-area and are collected at the same time.

[0063] Step S30: Using the restricted domain comparison and identification algorithm to identify whether there is a defective device in each group in turn, if not, ignore it, if yes, proceed to the next processing step;

[0064] The restricted domain comparison and recognition algorithm limits the comparison and recognition domain to a single group, minimizing the impact of different acquisition time and acquisition locations, thereby improving the accuracy and speed of defect recognition. The specific process can be divided into the following sub-steps:

[0065] I. Define the first inspection image in the group as the starting point of the algorithm;

[0066] II. Determine whether the device type of the starting image has been identified. If so, reset the algorithm starting point to the next inspection image. If not, extract the inspection image that matches the device type of the starting image.

[0067] Those skilled in the art should be aware that this step is to reset the algorithm starting point to the inspection image of the next device type, thereby extracting all inspection images of the device type;

[0068] The extracted inspection images and the current starting point image are stored together in an ordered sequence, and the arrangement order is consistent with the arrangement order within the group.

[0069] III. Traverse the extracted inspection images and calculate the mean difference between each identification feature of the current inspection image and other inspection images;

[0070] When humans identify defects on a device's exterior, they first focus on locations where the color or texture is significantly different from other parts, such as areas where paint is peeling, weathering, or bumps are obvious. Therefore, when calculating the difference between texture and color features, this algorithm also considers the differences between various parts of the device itself to improve accuracy. The specific formula for calculating the mean difference is:

[0071]

[0072] Among them, h0 and p0 represent the shape characteristics and spatial relationship characteristics of the current inspection image respectively, and h j 、pj They represent the shape features and spatial relationship features of the jth inspection image except the current inspection image, e jk 、c jk They represent the texture features and color features of the kth subdomain in the jth inspection image, respectively, and e jk+1 、c jk+1 They represent the texture features and color features of the k+1th subdomain in the jth inspection image, respectively, and e 0k 、c 0k They represent the texture features and color features of the kth subdomain in the current inspection image, e 0k+1 、c 0k+1 They represent the texture features and color features of the k+1th subdomain in the current inspection image, respectively. k ranges from 1 to w-1, where w is the total number of subdomains segmented from the inspection image. j ranges from 1 to m-1, where m is the total number of inspection images extracted this time. D is the calculation result of the difference mean.

[0073] IV. If the difference mean is greater than the threshold, the current inspection image is output as a defective device image;

[0074] V. After the extracted inspection images are traversed, the device type of the inspection images in the batch is marked as identified, and the algorithm starting point is reset to the inspection image next to the current starting image. Step II is continued until all inspection images in the group are identified;

[0075] The inspection images in each group are processed through the above steps. It should be noted that the defective inspection images output in this step will be transmitted to step S40 for processing in real time without waiting until all inspection images are processed.

[0076] Step S40: diagnose the identified defects based on the defect database, and generate an inspection report based on the diagnosis results and forward it to the operation and maintenance personnel;

[0077] The defect database maintains all discovered equipment defects in the substation and their related inspection images. This data is used to train a defect diagnosis model to achieve automatic diagnosis of inspection images. Specifically:

[0078] I. Train a defect diagnosis model based on the data in the defect database;

[0079] The device identification features in each inspection image in the defect database are extracted as input, including shape features, color features, texture features, and spatial relationship features; the corresponding historical diagnosis results are used as output, and a defect diagnosis model is trained in a supervised manner, which is expressed as:

[0080] Where Y is the model output, x vis the vth identification feature of the input, ε v is the autoregressive coefficient of the vth identification feature, is the diagnostic coefficient of the vth identification feature, θ v is the diagnostic bias of the vth identification feature, v ranges from 1 to V, V is the length of the input set, δ u is the output weight of the u-th layer of the model, is the output bias of the u-th layer of the model, u ranges from 1 to U, and U is the total number of layers of the model.

[0081] II. Inputting the defective inspection image features into the defect diagnosis model to obtain the diagnosis results;

[0082] III. Create an inspection report template and enter the diagnosis results and inspection images into the template to form a complete inspection report;

[0083] The inspection report template has two preset sections: diagnosis results and details. The details section is used to display inspection images, collection location, collection time and other detailed fields, while the diagnosis results are used to display the output results of the model.

[0084] Step S50: Regularly integrate the operation and maintenance reports sent back by the operation and maintenance personnel into the defect database to ensure the accuracy of the diagnosis results;

[0085] The maintenance reports sent back by maintenance personnel contain accurate defect diagnosis information. By integrating this data into the defect database and then using the integrated new information to incrementally train the defect diagnosis model, the diagnosis results can be made more comprehensive and accurate. The specific integration process is divided into the following sub-steps:

[0086] I. Determine whether the defect diagnosis results in the returned operation and maintenance report are consistent with those in the inspection report;

[0087] II. If they are consistent, ignore them. If they are inconsistent, use the defect diagnosis results in the operation and maintenance report as the basis and correct the diagnosis results in the defect database.

[0088] III. If the inspection report does not contain a diagnosis result, the inspection photos in the inspection report and the diagnosis result in the operation and maintenance report are added to the defect database;

[0089] If the defect diagnosis model encounters an unprecedented equipment defect, that is, if there is no information about this type of defect in the defect database, the output result will be interpreted as an empty string and backfilled into the inspection report, which will trigger the processing method of this step.

[0090] Example 2

[0091] like Figure 2As shown, the second embodiment of the present application provides a substation inspection image recognition system based on image processing, including: an inspection image acquisition module 21, an inspection image grouping module 22, a defect recognition module 23, a defect diagnosis module 24, and a defect data update module 25;

[0092] The inspection image acquisition module 21 is used to remotely acquire inspection images of various devices in the substation and mark the acquisition location and acquisition time.

[0093] The inspection image grouping module 22 is used to identify the device type in each inspection image and group the inspection images of different device types according to the image acquisition location and acquisition time; specifically, it includes: a device type identification submodule, a substation segmentation submodule, and a group data acquisition submodule;

[0094] The device type identification submodule is used to identify the type of device in the image based on the collection location of the inspection image;

[0095] Current image recognition algorithms can identify the type of objects based on their features. This technology can be used to identify the type of equipment from inspection images. However, considering that equipment within a substation rarely changes its position, it is entirely feasible to shorten image recognition time by taking location into account. Specifically:

[0096] I. Extract identification features of various types of equipment in historical inspection images;

[0097] Image processing technology is used to extract the identification features of various types of equipment from historical inspection images, including color features, shape features, texture features and spatial relationship features. Then, a support vector machine is used to generate an identification weight for each identification feature. The higher the weight, the greater the role of the feature in type identification.

[0098] II. Associate the identifying characteristics of each device with its type and location;

[0099] III. Traverse the received inspection images and query the device type whose placement location matches the current collection location;

[0100] IV. Calculate the similarity between the identification features of the current inspection image and each device type in the query results, and annotate the current inspection image with the device type with the highest similarity;

[0101] The calculation formula for calculating the similarity between the inspection image and the equipment type identification feature is expressed as:

[0102] where a i is the i-th identification feature of the inspection image, μ iis the recognition weight of the i-th recognition feature, b i is the i-th identification feature of a certain device type, i ranges from 1 to n, n is the total number of identification features, and S is the similarity calculation result.

[0103] The substation subdivision module is used to divide the entire substation area into grids to obtain multiple sub-areas;

[0104] The parameters for dividing the grid are defined according to the actual application scenario, but it is necessary to ensure that there are more than two devices of the same type in a sub-area. In other words, it is necessary to ensure that each device has a reference for comparison, and this reference must be a device of the same type.

[0105] The grouping data acquisition submodule is used to group the acquired inspection images for the first time according to the acquisition time, and then group the inspection images for the second time based on the same sub-area to which the acquisition location belongs to obtain the final grouped data;

[0106] Grouping by acquisition time ensures that even if the inspection image is delayed due to problems in the data transmission link, the (defect) recognition effect of the inspection image will not be affected; ultimately, the inspection images in each group come from the same sub-area and the acquisition time is also consistent.

[0107] The defect identification module 23 is used to sequentially identify defective devices in each group using a restricted domain comparison and identification algorithm;

[0108] The restricted domain comparison and recognition algorithm limits the comparison and recognition domain to a single group, minimizing the impact of different acquisition time and acquisition locations, thereby improving the accuracy and speed of defect recognition. The specific process can be divided into the following sub-steps:

[0109] I. Define the first inspection image in the group as the starting point of the algorithm;

[0110] II. Determine whether the device type of the starting image has been identified. If so, reset the algorithm starting point to the next inspection image. If not, extract the inspection image that matches the device type of the starting image.

[0111] The extracted inspection images and the current starting point image are stored together in an ordered sequence, and the arrangement order is consistent with the arrangement order within the group.

[0112] III. Traverse the extracted inspection images and calculate the mean difference between each identification feature of the current inspection image and other inspection images;

[0113] When humans identify defects on a device's exterior, they first focus on locations where the color or texture is significantly different from other parts, such as areas where paint is peeling, weathering, or bumps are obvious. Therefore, when calculating the difference between texture and color features, this algorithm also considers the differences between various parts of the device itself to improve accuracy. The specific formula for calculating the mean difference is:

[0114]

[0115] Among them, h0 and p0 represent the shape characteristics and spatial relationship characteristics of the current inspection image respectively, and h j 、p j They represent the shape features and spatial relationship features of the jth inspection image except the current inspection image, e jk 、c jk They represent the texture features and color features of the kth subdomain in the jth inspection image, respectively, and e jk+1 、c jk+1 They represent the texture features and color features of the k+1th subdomain in the jth inspection image, respectively, and e 0k 、c 0k They represent the texture features and color features of the kth subdomain in the current inspection image, e 0k+1 、c 0k+1 They represent the texture features and color features of the k+1th subdomain in the current inspection image, respectively. k ranges from 1 to w-1, where w is the total number of subdomains segmented from the inspection image. j ranges from 1 to m-1, where m is the total number of inspection images extracted this time. D is the calculation result of the difference mean.

[0116] IV. If the difference mean is greater than the threshold, the current inspection image is output as a defective device image;

[0117] V. After the extracted inspection images are traversed, the device type of the inspection images in the batch is marked as identified, and the algorithm starting point is reset to the inspection image next to the current starting image. Step II is continued until all inspection images in the group are identified;

[0118] The inspection images in each group are processed through the above steps. It should be noted that the defective inspection images output by this module will be transmitted to the defect diagnosis module 24 for processing in real time without waiting until all inspection images are processed.

[0119] The defect diagnosis module 24 is used to diagnose the identified defects based on the defect database and generate an inspection report based on the diagnosis results and forward it to the operation and maintenance personnel; it specifically includes: a defect diagnosis model training submodule, a diagnosis result acquisition submodule, and an inspection report generation submodule;

[0120] The defect diagnosis model training submodule is used to train a defect diagnosis model using data in the defect database;

[0121] The device identification features in each inspection image in the defect database are extracted as input, including shape features, color features, texture features, and spatial relationship features; the corresponding historical diagnosis results are used as output, and a defect diagnosis model is trained in a supervised manner, which is expressed as:

[0122] Where Y is the model output, x v is the vth identification feature of the input, εv is the autoregressive coefficient of the vth identification feature, is the diagnostic coefficient of the vth identification feature, θ v is the diagnostic bias of the vth identification feature, v ranges from 1 to V, V is the length of the input set, δ u is the output weight of the u-th layer of the model, is the output bias of the u-th layer of the model, u ranges from 1 to U, and U is the total number of layers of the model.

[0123] The diagnosis result acquisition submodule is used to input the defective inspection image features into the defect diagnosis model to obtain the diagnosis result.

[0124] The inspection report generation submodule is used to create an inspection report template and fill the diagnosis results and inspection images back into the template to form a complete inspection report;

[0125] The inspection report template has two preset sections: diagnosis results and details. The details section is used to display inspection images, collection location, collection time and other detailed fields, while the diagnosis results are used to display the output results of the model.

[0126] The defect data update module 25 is used to regularly integrate the operation and maintenance reports sent back by the operation and maintenance personnel into the defect database to ensure the accuracy of the diagnosis results;

[0127] The maintenance reports sent back by maintenance personnel contain accurate defect diagnosis information. By integrating this data into the defect database and then using the integrated new information to incrementally train the defect diagnosis model, the diagnosis results can be made more comprehensive and accurate. The specific integration process is divided into the following sub-steps:

[0128] I. Determine whether the defect diagnosis results in the returned operation and maintenance report are consistent with those in the inspection report;

[0129] II. If they are consistent, ignore them. If they are inconsistent, use the defect diagnosis results in the operation and maintenance report as the basis and correct the diagnosis results in the defect database.

[0130] III. If the inspection report does not contain a diagnosis result, the inspection photos in the inspection report and the diagnosis result in the operation and maintenance report are added to the defect database;

[0131] If the defect diagnosis model encounters an unprecedented equipment defect, that is, if there is no information about this type of defect in the defect database, the output result will be interpreted as an empty string and backfilled into the inspection report, which will trigger the processing method of this step.

[0132] Corresponding to the above embodiment, an embodiment of the present invention provides a computer storage medium, comprising: at least one memory and at least one processor;

[0133] The memory is used to store one or more program instructions;

[0134] The processor is used to run one or more program instructions to execute a substation inspection image recognition method based on image processing.

[0135] Corresponding to the above embodiment, an embodiment of the present invention provides a computer-readable storage medium, which contains one or more program instructions, and the one or more program instructions are used by a processor to execute a substation inspection image recognition method based on image processing.

[0136] The embodiment disclosed in the present invention provides a computer-readable storage medium, in which computer program instructions are stored. When the computer program instructions are executed on a computer, the computer executes the above-mentioned substation inspection image recognition method based on image processing.

[0137] In the embodiments of the present invention, the processor may be an integrated circuit chip having signal processing capabilities. The processor may be a general-purpose processor, a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a field programmable gate array (FPGA), or other programmable logic devices, discrete gate or transistor logic devices, or discrete hardware components.

[0138] The methods, steps, and logic diagrams disclosed in the embodiments of the present invention can be implemented or executed. A general-purpose processor can be a microprocessor or any conventional processor. The steps of the methods disclosed in the embodiments of the present invention can be directly implemented and executed by a hardware decoding processor, or by a combination of hardware and software modules within the decoding processor. The software modules can be located in a storage medium well-established in the art, such as random access memory, flash memory, read-only memory, programmable read-only memory, electrically erasable programmable memory, or registers. The processor reads the information from the storage medium and, in conjunction with its hardware, completes the steps of the aforementioned methods.

[0139] The storage medium may be a memory and may be, for example, a volatile memory or a nonvolatile memory, or may include both volatile and nonvolatile memory.

[0140] Among them, the non-volatile memory can be a read-only memory (ROM), a programmable read-only memory (PROM), an erasable programmable read-only memory (EPROM), an electrically erasable programmable read-only memory (EEPROM), or a flash memory.

[0141] Volatile memory may be random access memory (RAM), which is used as an external cache memory. By way of example and not limitation, many forms of RAM are available, such as static random access memory (SRAM), dynamic random access memory (DRAM), synchronous dynamic random access memory (SDRAM), double data rate synchronous dynamic random access memory (DDRSDRAM), enhanced synchronous dynamic random access memory (ESDRAM), synchronous link dynamic random access memory (SLDRAM), and direct RAM bus random access memory (DRRAM).

[0142] The storage media described in the embodiments of the present invention are intended to include, but are not limited to, these and any other suitable types of memory.

[0143] Those skilled in the art will appreciate that in one or more of the above examples, the functions described herein can be implemented using a combination of hardware and software. When software is used, the corresponding functions can be stored in a computer-readable medium or transmitted as one or more instructions or codes on a computer-readable medium. Computer-readable media include computer storage media and communication media, wherein communication media includes any medium that facilitates the transmission of computer programs from one place to another. The storage medium can be any available medium that can be accessed by a general-purpose or special-purpose computer.

[0144] The specific implementation methods described above further illustrate the objectives, technical solutions and beneficial effects of the present invention in detail. It should be understood that the above description is only a specific implementation method of the present invention and is not intended to limit the scope of protection of the present invention. Any modifications, equivalent replacements, improvements, etc. made on the basis of the technical solution of the present invention should be included in the scope of protection of the present invention.

Claims

1. A substation inspection image recognition method based on image processing, characterized in that: include: Step 1: Remotely obtain inspection images of each device in the substation and mark the collection location and time; Step 2: Identify the device type in each inspection image and group the inspection images of different device types according to the image acquisition location and acquisition time. This is divided into the following sub-steps: Divide the entire substation area into grids to obtain multiple sub-areas; The obtained inspection images are grouped for the first time according to the acquisition time; The inspection images are grouped for the second time based on the sub-area to which the acquisition locations belong, to obtain the final grouping data. Step 3: Use the restricted domain comparison and recognition algorithm to identify whether there are defective devices in each group. If not, ignore them. If so, proceed to the next processing step. The restricted domain comparison and identification algorithm is used to identify whether there are defective devices in each group in turn. The specific steps are as follows: The first inspection image in the group is defined as the starting point of the algorithm; Determine whether the device type of the starting image has been identified. If so, reset the algorithm starting point to the next inspection image. If not, extract the inspection image with the same device type as the starting image. Traverse the extracted inspection images and calculate the mean difference of each identification feature between the current inspection image and other inspection images. The formula for calculating the mean difference is expressed as: ,in 、 Respectively represent the shape characteristics and spatial relationship characteristics of the current inspection image, 、 Respectively represent the shape features and spatial relationship features of the jth inspection image except the current inspection image, 、 They represent the texture features and color features of the kth subdomain in the jth inspection image, 、 They represent the texture features and color features of the k+1th subdomain in the jth inspection image, 、 Respectively represent the texture features and color features of the kth subdomain in the current inspection image, 、 They represent the texture features and color features of the k+1th subdomain in the current inspection image, respectively. k ranges from 1 to w-1, where w is the total number of subdomains segmented from the inspection image. j ranges from 1 to m-1, where m is the total number of inspection images extracted this time. D is the calculation result of the difference mean. If the difference mean is greater than the threshold, the current inspection image is output as a defective device image; After the extracted inspection images are traversed, the device type of the inspection images in the batch is marked as recognized, and the algorithm starting point is reset to the next inspection image after the current starting image, and recognition continues until all inspection images in the group are recognized; Step 4: Diagnose the identified defects based on the defect database, and generate an inspection report based on the diagnosis results and forward it to the operation and maintenance personnel; Step 5: Regularly integrate the operation and maintenance reports sent back by operation and maintenance personnel into the defect database to ensure the accuracy of the diagnosis results.

2. The substation inspection image recognition method based on image processing according to claim 1 is characterized in that: Identifying the device type in each inspection image is divided into the following sub-steps: Extract identification features of various types of equipment from historical inspection images; Associate the identification features of various types of equipment with the equipment type and equipment placement; Traverse the received inspection images and query the equipment type whose placement location is consistent with the current collection location; Calculate the similarity between the identification features of the current inspection image and each device type in the query result, and use the device type with the highest similarity to annotate the current inspection image.

3. The substation inspection image recognition method based on image processing according to claim 1 is characterized in that: The identified defects are diagnosed based on the defect database, and an inspection report is generated based on the diagnosis results and forwarded to the operation and maintenance personnel. The specific steps are as follows: Train a defect diagnosis model based on the data in the defect database; Input the defective inspection image features into the defect diagnosis model to obtain the diagnosis results; Create an inspection report template and fill the diagnosis results and inspection images into the template to form a complete inspection report.

4. The substation inspection image recognition method based on image processing according to claim 1 is characterized in that: Regularly integrate the operation and maintenance reports sent back by operation and maintenance personnel into the defect database, which is divided into the following sub-steps: Determine whether the defect diagnosis results in the returned operation and maintenance report are consistent with those in the inspection report; If they are consistent, they are ignored. If they are inconsistent, the defect diagnosis results in the operation and maintenance report shall prevail, and the diagnosis results in the defect database shall be corrected; If there is no diagnosis result in the inspection report, the inspection photos in the inspection report and the diagnosis result in the operation and maintenance report are added to the defect database.

5. A substation inspection image recognition system based on image processing, characterized in that: The system is used to execute the substation inspection image recognition method based on image processing according to any one of claims 1 to 4, wherein the system comprises: an inspection image acquisition module, an inspection image grouping module, a defect recognition module, a defect diagnosis module, and a defect data update module; Inspection image acquisition module, used to remotely acquire inspection images of each device in the substation and mark the acquisition location and time; Inspection image grouping module, used to identify the device type in each inspection image and group inspection images of different device types according to the image acquisition location and acquisition time; A defect identification module is used to sequentially identify defective devices in each group using a restricted domain comparison and identification algorithm; The defect diagnosis module is used to diagnose identified defects based on the defect database and generate inspection reports based on the diagnosis results and forward them to the operation and maintenance personnel; The defect data update module is used to regularly integrate the operation and maintenance reports sent back by operation and maintenance personnel into the defect database to ensure the accuracy of the diagnosis results.

6. A computer storage medium, characterized in that include: at least one memory and at least one processor; a memory for storing one or more program instructions; A processor is used to run one or more program instructions to execute the substation inspection image recognition method based on image processing as described in any one of claims 1 to 4.

Images