Alternating current feeder switch constant value identification method and related device

Abstract

The invention provides an alternating current feeder switch constant value identification method and a related device, and the method comprises the steps: screening an open source data set of an alternating current feeder switch based on a predetermined mode, and obtaining a training set and a test set; inputting the training set into a convolutional neural network for training, and determining a target detection model; and inputting the test set into the trained target detection model to obtain a detection result of the feeder fixed value. According to the embodiment of the invention, the method can reduce the manual inspection of the transformer substation, avoids the error rate, facilitates the real-time and effective utilization of data at different levels, and is more beneficial to the flat management of all devices of the transformer substation.

Description

Technical Field

[0001] The present disclosure relates to the technical field of substation target identification, and in particular to an identification method for AC feeder switch setting and a related device. Background Art

[0002] The substation video and environmental monitoring system consists of an in-station monitoring workstation, RPU, video monitoring equipment, environmental information collection equipment, network equipment, etc., to realize the functions of collecting, processing, and monitoring the on-site video and various environmental information at the station. At present, the camera availability (%) index of 110kV and above substations has reached more than 95%, and the image video acquisition unit has high camera clarity, many monitoring points (many cameras), large video data flow, and long storage time. It can monitor the appearance and operating status of important operating equipment such as transformers and circuit breakers in the substation day and night, as well as the status of switches, switches, important instruments, and batteries. However, the current substation video and environmental monitoring system is mainly used for security, alarm, and dynamic environment monitoring, and there is huge room for development for the safe operation of equipment and the development and utilization of data indicators.

[0003] As the scale and complexity of power grids continue to increase, manual monitoring equipment can no longer meet the needs of development. Existing substation video and environmental monitoring systems are mainly used for security, alarm and dynamic environment monitoring. In the event of equipment accidents, they are mostly used for post-incident investigation and evidence collection, but cannot provide key indicators for accident prevention. In addition, as the scale and complexity of power grids continue to increase, manual inspections of substations are not only inefficient and costly, but also unable to fully identify existing problems, resulting in defects that cannot be eliminated in a timely manner, and even causing accidents and incidents, which is not conducive to risk control of fixed-value AC and DC systems. Summary of the invention

[0004] In view of this, the present disclosure aims to provide an identification method and related device for AC feeder switch setting to solve the above-mentioned technical problems in the prior art.

[0005] One aspect of the present disclosure provides a method for identifying a constant value of an AC feeder switch, comprising: screening an open source data set of an AC feeder switch based on a predetermined method to obtain a training set and a test set; inputting the training set into a convolutional neural network for training to determine a target detection model; and inputting the test set into the trained target detection model to obtain a detection result of a feeder constant value.

[0006] In some embodiments, the open source data set of the AC feeder switch is screened based on a predetermined method to obtain a training set and a test set, and the predetermined method is the ratio of the feeder standard setting value to the feeder non-standard setting value.

[0007] In some embodiments, the training set is input into a convolutional neural network for training to determine a target detection model, including: constructing a switch layer with feeder constant features; obtaining a multi-scale feature map and building a feature pyramid based on the obtained multi-scale feature map; locating and classifying targets in all multi-scale feature maps based on a loss function to determine a target detection model.

[0008] In some embodiments, before constructing the switch layer with feeder constant value features, it also includes preprocessing the image data in the training set before inputting the training set into the network.

[0009] In some embodiments, in the construction of a switch layer with feeder constant features, the feeder constant features include primary constant features and advanced constant features, wherein the primary features include at least horizontal lines, vertical lines, diagonal lines, and edge lines, and the advanced constant features include at least curves, contours, and shapes in the feeder switch image.

[0010] In some embodiments, the test set is input into the trained target detection model to obtain the detection result of the feeder constant using a non-maximum suppression method, the test set is input into the target detection model, and the feeder constant detection result is determined based on the score of the detection box.

[0011] In some embodiments, the test set is input into the trained target detection model to obtain the detection results of the feeder constant, including: obtaining the scores of all detection boxes; determining the best target detection box based on the scores, and removing other detection boxes whose scores are lower than a preset score threshold; and obtaining the final feeder constant detection results.

[0012] Another aspect of the present disclosure provides an apparatus for identifying constants of an AC feeder switch, comprising: an acquisition module, used to screen an open source data set of an AC feeder switch based on a predetermined method to obtain a training set and a test set; a determination module, used to input the training set into a convolutional neural network for training to determine a target detection model; and a detection module, used to input the test set into the trained target detection model to obtain a detection result of a feeder constant.

[0013] Another aspect of an embodiment of the present disclosure provides a storage medium storing a computer program, wherein the computer program implements the steps of any of the above methods when executed by a processor.

[0014] Another aspect of an embodiment of the present disclosure provides an electronic device, comprising at least a memory and a processor, wherein a computer program is stored in the memory, and the processor implements the steps of any of the above methods when executing the computer program in the memory.

[0015] The secondary development of deep learning for substation video and environmental monitoring systems can not only extract safe operation and data indicators in real time and in a critical manner, but also reduce labor costs and avoid error rates, and is also conducive to reducing the burden on the grassroots and implementing flat management. It will provide a strong technical guarantee for promoting the management of power grids to gradually develop in the direction of automation, integration, centralization and intelligence.

[0016] The disclosed embodiments can reduce manpower inspections of substations, avoid errors, facilitate the use of real-time data effectiveness at different levels, and are more beneficial to the flat management of various equipment in substations.

[0017] In order to make the above-mentioned objectives, features and advantages of the present disclosure more obvious and easy to understand, preferred embodiments are specifically cited below and described in detail with reference to the attached drawings. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] In the drawings that are not necessarily drawn to scale, the same reference numerals may describe similar parts in different views. The same reference numerals with letter suffixes or different letter suffixes may represent different instances of similar parts. The drawings generally illustrate various embodiments by way of example and not limitation, and together with the specification and claims, are used to illustrate the disclosed embodiments. When appropriate, the same reference numerals are used throughout the drawings to refer to the same or similar parts. Such embodiments are illustrative and are not intended to be exhaustive or exclusive embodiments of the present apparatus or method. The drawings described herein are used to provide a further understanding of the present disclosure and constitute a part of this application. The illustrative embodiments of the present disclosure and their descriptions are used to explain the present disclosure and do not constitute an improper limitation of the present disclosure. In the drawings:

[0019] Figure 1 It is a schematic diagram of the steps of a method for identifying a constant value of an AC feeder switch provided by an embodiment of the present disclosure;

[0020] Figure 2 is a flow chart of a method for identifying a constant value of an AC feeder switch provided by an embodiment of the present disclosure;

[0021] Figure 3 It is a schematic diagram of the standard setting value of the feeder line of the station AC system in the embodiment of the present disclosure;

[0022] Figure 4 It is a schematic diagram of non-standard setting values ​​of feeder lines of the station AC system in an embodiment of the present disclosure. DETAILED DESCRIPTION

[0023] The specific embodiments of the present disclosure are described in detail below with reference to the accompanying drawings, but are not intended to limit the present disclosure.

[0024] It should be understood that various modifications may be made to the embodiments disclosed herein. Therefore, the above description should not be considered as limiting, but merely as an example of an embodiment. Other modifications within the scope and spirit of the present disclosure will occur to those skilled in the art.

[0025] The accompanying drawings, which are incorporated in and constitute a part of the specification, illustrate embodiments of the present disclosure and, together with the general description of the present disclosure given above and the detailed description of the embodiments given below, serve to explain the principles of the present disclosure.

[0026] These and other characteristics of the present disclosure will become apparent from the following description of a preferred form of embodiment given as a non-limiting example, with reference to the attached drawings.

[0027] It should also be understood that, although the present disclosure has been described with reference to some specific examples, those skilled in the art will be able to realize many other equivalent forms of the present disclosure that have the features described in the claims and are therefore within the scope of protection defined thereby.

[0028] The above and other aspects, features and advantages of the present disclosure will become more apparent from the following detailed description when taken in conjunction with the accompanying drawings.

[0029] Specific embodiments of the present disclosure are described hereinafter with reference to the accompanying drawings; however, it should be understood that the disclosed embodiments are merely examples of the present disclosure, which may be implemented in a variety of ways. Well-known and / or repeated functions and structures are not described in detail to avoid obscuring the present disclosure with unnecessary or redundant details. Therefore, the specific structural and functional details disclosed herein are not intended to be limiting, but merely serve as a basis and representative basis for the claims to teach those skilled in the art to use the present disclosure in a variety of ways with substantially any suitable detailed structure.

[0030] It should be noted that the terms "first", "second", etc. in the specification and claims of the present disclosure and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchangeable where appropriate, so that the embodiments of the present disclosure described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions, for example, a process, method, system, product, or device that includes a series of steps or units is not necessarily limited to those steps or units that are clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products, or devices.

[0031] This specification may use the phrases "in one embodiment," "in another embodiment," "in a further embodiment," or "in other embodiments," all of which may refer to one or more of the same or different embodiments according to the present disclosure.

[0032] As the scale and complexity of power grids continue to increase, manual monitoring equipment can no longer meet the needs of development. Secondary development of deep learning for substation video and environmental monitoring systems can not only extract safe operation and data indicators in real time and critically, but also reduce labor costs and avoid error rates. It is also conducive to reducing the burden on the grassroots and implementing flat management. It can provide strong technical support for promoting the management of power grids to gradually develop in the direction of automation, integration, centralization and intelligence.

[0033] In order to improve the lean, intelligent, and digital management capabilities of relay protection and meet the requirements of versatility, compatibility, and scalability, the first embodiment of the present disclosure provides an identification method for AC feeder switch setting, which implements monitoring and tracking based on the SSD algorithm of the video system, such as Figure 1 Combined with Figure 2 As shown, the identification method includes:

[0034] S101, screening the open source dataset of AC feeder switches based on a predetermined method to obtain a training set and a test set.

[0035] In this step, the open source data set of the AC feeder switch is screened based on a predetermined method to obtain a training set and a test set. Specifically, the above-mentioned open source data set is a feeder switch image of the station AC system, and the above-mentioned predetermined method can be the ratio of the feeder standard setting value to the feeder non-standard setting value. In this step, specifically, firstly, the open source data set is collected and screened according to the ratio of the feeder standard setting value to the feeder non-standard setting value of 1:1, and a training set and a test set are generated respectively.

[0036] in, Figure 3 and Figure 4The standard setting value of the feeder of the station AC system and the non-standard setting value of the feeder of the station AC system are shown respectively. The training set in this step can be set to the standard value according to the existing technology, where, for example, the main feeder protection setting value of the 380V station AC system can be (1) overcurrent protection stage I: 3.0*Ie, T=0.2S, where Ie is the rated current of the low-voltage side of the station transformer); (2) overcurrent protection stage II: 1.0*In, T=15S, where In is the rated current of the 380V circuit breaker; (3) zero-sequence overcurrent protection: 0.2*Ie, T=0.6S. The setting values ​​of 380V feeder protection can be (1) overcurrent protection stage I: 2.0*Ie, T=0S, the quick-break stage must be put into operation; (2) overcurrent protection stage II: 1.0*In, T=10S; (3) zero-sequence overcurrent protection: 0.1Ie, T=0.3S; Note: The long delay meets the requirements of I 2 *The inverse time setting principle of t=K (constant).

[0037] S102, inputting the training set into a convolutional neural network for training to determine a target detection model.

[0038] After the open source dataset of AC feeder switches is screened based on a predetermined method in the above step S101 to obtain a training set and a test set, in this step, the training set is input into a convolutional neural network for training to determine a target detection model. Specifically, the following steps are included:

[0039] S201, construct a switch layer with feeder setting characteristics.

[0040] In this step, a switch layer with feeder fixed value features is constructed. Specifically, before constructing the feeder fixed value feature layer, the image format is uniformly set. Specifically, in order to facilitate the recognition of the SSD algorithm of the neural network, the image data in the training set is preprocessed before the training set is input into the network. For example, the size of all feeder images can be unified into a 300×300 format.

[0041] In this step, based on the training set, features are extracted by SSD algorithm with VGG-16 as the backbone network, and on this basis, a convolutional layer is added to obtain the feature map of the feeder switch. In the process of feature extraction, not only the primary fixed-value features in the feeder switch image are extracted, where the primary features include, for example, horizontal lines, vertical lines, diagonal lines, edge lines, etc.; but also the advanced fixed-value features of the feeder fixed values ​​such as curves, contours and shapes in the feeder switch image can be extracted, and then the switch layer is constructed by extracting the above-mentioned primary fixed-value features and advanced fixed-value features.

[0042] S202, obtaining a multi-scale feature map and building a feature pyramid based on the obtained multi-scale feature map.

[0043] After constructing the switch layer with the feeder constant value feature through the above step S201, in this step, a multi-scale feature map is obtained and a feature pyramid is built based on the obtained multi-scale feature map.

[0044] Considering that generally a large-scale feature map is used to detect a forward propagation target with a smaller area in the image data, and a small-scale feature map is used to detect a backward propagation target with a larger area in the image data, it is possible to detect targets of any size. In this step, the convolutional layer in the above step S201 is used to scan the feeder switch image again, so as to obtain feature maps of different scales from the 1st to the nth in sequence. The so-called multi-scale feature map in this step refers to feature maps of different sizes and shapes.

[0045] Furthermore, fusion is performed based on the obtained multi-scale feature maps, wherein the information in the multi-scale feature maps is fused by building a feature pyramid. Then, the processed training set is input into the convolutional neural network for multiple rounds of iterative training.

[0046] S203, locating and classifying the targets in all multi-scale feature maps based on the loss function, and determining the target detection model.

[0047] After obtaining the multi-scale feature map through the above step S202 and building the feature pyramid based on the obtained multi-scale feature map, in this step, the targets in all multi-scale feature maps are located and classified based on the loss function, and the target detection model is determined. Specifically, the loss function is used to locate and classify the targets in all multi-scale feature maps. Since the SSD model sets sliding windows of different sizes in the original image, the sliding windows of different sizes are classified and regressed, corresponding to 6 types of PNet, respectively, thereby optimizing the characteristic parameters of the feeder constant vector group, and then generating the target detection model in the feature map.

[0048] S103, inputting the test set into the trained target detection model to obtain the detection result of the feeder constant.

[0049] After the training set is input into the convolutional neural network for training and the target detection model is determined in the above step S102, in this step, the test set is input into the trained target detection model to obtain the detection result of the feeder constant value. Specifically, in this step, for example, the non-maximum suppression method is used, the test set is input into the target detection model, and the feeder constant value detection result is determined based on the score of the detection box.

[0050] Further, the determining of the feeder fixed value detection result based on the score of the detection frame includes:

[0051] Obtain the scores of all detection frames; determine the best target detection frame based on the scores, and remove other detection frames whose scores are lower than a preset score threshold; and obtain the final feeder fixed value detection result.

[0052] The disclosed embodiment is based on the optical character intelligent automatic recognition technology of the deep learning SSD model. By mining the AC and DC graphics and images of the substation video and environmental monitoring system, and through continuous learning of the convolutional neural network, key data indicators of AC and DC monitoring are extracted, and the risks of the AC and DC systems used in the station are accurately assessed.

[0053] The disclosed embodiments can reduce manpower inspections of substations, avoid errors, facilitate the use of real-time data effectiveness at different levels, and are more beneficial to the flat management of various equipment in substations.

[0054] Based on the same inventive concept as the first embodiment above, the second embodiment of the present disclosure provides an AC feeder switch setting identification device, comprising:

[0055] An acquisition module, used to filter the open source data set of AC feeder switches based on a predetermined method to obtain a training set and a test set;

[0056] A determination module, used to input the training set into a convolutional neural network for training and determine a target detection model;

[0057] The detection module is used to input the test set into the trained target detection model to obtain the detection result of the feeder constant.

[0058] Furthermore, the open source data set of the AC feeder switch is screened based on a predetermined method to obtain a training set and a test set, and the predetermined method is the ratio of the feeder standard setting value to the feeder non-standard setting value.

[0059] Furthermore, the determination module includes:

[0060] A layer construction unit, used for constructing a switch layer with feeder setting characteristics;

[0061] A feature map acquisition unit, used to acquire a multi-scale feature map and build a feature pyramid based on the acquired multi-scale feature map;

[0062] The model determination unit is used to locate and classify the targets in all multi-scale feature maps based on the loss function and determine the target detection model.

[0063] Furthermore, it also includes a preprocessing module for preprocessing the image data in the training set before inputting the training set into the network.

[0064] Furthermore, the feeder constant value features include primary constant value features and advanced constant value features, wherein the primary features include at least horizontal lines, vertical lines, diagonal lines and edge lines, and the advanced constant value features include at least curves, contours and shapes in the feeder switch picture.

[0065] Furthermore, the method of inputting the test set into the trained target detection model to obtain the detection result of the feeder constant is to use a non-maximum suppression method, input the test set into the target detection model, and determine the feeder constant detection result based on the score of the detection box.

[0066] Furthermore, the detection module includes:

[0067] A score acquisition unit, used to obtain the scores of all detection boxes;

[0068] An optimal determination unit, configured to determine an optimal target detection frame based on the score, and remove other detection frames whose scores are lower than a preset score threshold;

[0069] The result acquisition unit is used to obtain the final feeder fixed value detection result.

[0070] The disclosed embodiments can reduce manpower inspections of substations, avoid errors, facilitate the use of real-time data effectiveness at different levels, and are more beneficial to the flat management of various equipment in substations.

[0071] A third embodiment of the present disclosure provides a storage medium storing a computer program. When the computer program is executed by a processor, the steps of implementing the above method include:

[0072] S11, screening the open source dataset of AC feeder switches based on a predetermined method to obtain a training set and a test set;

[0073] S12, inputting the training set into a convolutional neural network for training to determine a target detection model;

[0074] S13, inputting the test set into the trained target detection model to obtain the detection result of the feeder constant.

[0075] Of course, other steps of the control method can also be used to implement the above embodiment.

[0076] The disclosed embodiments can reduce manpower inspections of substations, avoid errors, facilitate the use of real-time data effectiveness at different levels, and are more beneficial to the flat management of various equipment in substations.

[0077] A fourth embodiment of the present disclosure provides an electronic device, the electronic device comprising at least a memory and a processor, the memory storing a computer program, and the processor implementing the steps of the above method when executing the computer program on the memory, specifically comprising:

[0078] S21, filtering the open source dataset of AC feeder switches based on a predetermined method to obtain a training set and a test set;

[0079] S22, inputting the training set into a convolutional neural network for training to determine a target detection model;

[0080] S23, inputting the test set into the trained target detection model to obtain the detection result of the feeder constant.

[0081] The disclosed embodiments can reduce manpower inspections of substations, avoid errors, facilitate the use of real-time data effectiveness at different levels, and are more beneficial to the flat management of various equipment in substations.

[0082] The technicians in the relevant field can clearly understand that for the convenience and simplicity of description, only the division of the above-mentioned functional units and modules is used as an example for illustration. In practical applications, the above-mentioned function allocation can be completed by different functional units and modules as needed, that is, the internal structure of the device can be divided into different functional units or modules to complete all or part of the functions described above. The functional units and modules in the embodiment can be integrated in a processing unit, or each unit can exist physically separately, or two or more units can be integrated in one unit. The above-mentioned integrated unit can be implemented in the form of hardware or in the form of software functional units. In addition, the specific names of the functional units and modules are only for the convenience of distinguishing each other, and are not used to limit the scope of protection of this application. The specific working process of the units and modules in the above-mentioned system can refer to the corresponding process in the aforementioned method embodiment, which will not be repeated here.

[0083] In the above embodiments, the description of each embodiment has its own emphasis. For parts that are not described or recorded in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0084] 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.

[0085] In the embodiments provided in the present application, it should be understood that the disclosed devices / terminal equipment and methods can be implemented in other ways. For example, the device / terminal equipment embodiments described above are only schematic. For example, the division of the modules or units is only a logical function division. There may be other division methods in actual implementation, such as 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.

[0086] 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.

[0087] 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. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of software functional units.

[0088] If the integrated module is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the present application implements all or part of the processes in the above-mentioned embodiment method, and can also be completed by instructing the relevant hardware through a computer program. The computer program can be stored in a computer-readable storage medium. When the computer program is executed by the processor, the steps of the above-mentioned motor torque control method embodiments can be implemented. Among them, the computer program includes computer program code, and the computer program code can be in source code form, object code form, executable file or some intermediate form. The computer-readable medium may include: any entity or device capable of carrying the computer program code, recording medium, U disk, mobile hard disk, disk, optical disk, computer memory, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), electric carrier signal, telecommunication signal and software distribution medium. It should be noted that the content contained in the computer-readable medium can be appropriately increased or decreased according to the requirements of legislation and patent practice in the jurisdiction. For example, in some jurisdictions, according to legislation and patent practice, computer-readable media do not include electric carrier signals and telecommunication signals.

[0089] In addition, the features of the embodiments shown in the drawings of the present application or the various embodiments mentioned in this specification are not necessarily understood as independent embodiments. Instead, each feature described in one example of an embodiment can be combined with one or more other desired features from other embodiments to produce other embodiments not described in words or with reference to the drawings.

[0090] The embodiments described above are only used to illustrate the technical solutions of the present application, rather than to limit them. Although the present application has been described in detail with reference to the aforementioned embodiments, a person skilled in the art should understand that the technical solutions described in the aforementioned embodiments may still be modified, or some of the technical features may be replaced by equivalents. Such modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present application, and should all be included in the protection scope of the present application.

Claims

1. A method for identifying a constant value of an AC feeder switch, characterized in that: include: The open source dataset of AC feeder switches is screened based on a predetermined method to obtain a training set and a test set; Inputting the training set into a convolutional neural network for training to determine a target detection model; The test set is input into the trained target detection model to obtain the detection result of the feeder constant.

2. The identification method according to claim 1, characterized in that: The open source data set of the AC feeder switch is screened based on a predetermined method to obtain a training set and a test set, and the predetermined method is the ratio of the feeder standard setting value to the feeder non-standard setting value.

3. The identification method according to claim 1, characterized in that: The step of inputting the training set into a convolutional neural network for training to determine a target detection model includes: Construct a switch layer with feeder setting characteristics; Obtain a multi-scale feature map and build a feature pyramid based on the obtained multi-scale feature map; Based on the loss function, the objects in all multi-scale feature maps are located and classified, and the object detection model is determined.

4. The identification method according to claim 3, characterized in that: Before constructing the switch layer with feeder fixed value characteristics, the method also includes preprocessing the image data in the training set before inputting the training set into the network.

5. The identification method according to claim 3, characterized in that: In the construction of the switch layer with feeder fixed value features, the feeder fixed value features include primary fixed value features and advanced fixed value features, wherein the primary features at least include horizontal lines, vertical lines, diagonal lines and edge lines, and the advanced fixed value features at least include curves, contours and shapes in the feeder switch picture.

6. The identification method according to claim 1, characterized in that: The method of inputting the test set into the trained target detection model to obtain the detection result of the feeder constant value is to use the non-maximum suppression method, input the test set into the target detection model, and determine the feeder constant value detection result based on the score of the detection box.

7. The identification method according to claim 1, characterized in that: The step of inputting the test set into the trained target detection model to obtain a detection result of a feeder constant value includes: Get the scores of all detection boxes; Determine the best target detection frame based on the score, and remove other detection frames whose scores are lower than a preset score threshold; Get the final feeder constant value detection result.

8. An identification device for AC feeder switch setting, characterized in that: include: An acquisition module, used to filter the open source data set of AC feeder switches based on a predetermined method to obtain a training set and a test set; A determination module, used to input the training set into a convolutional neural network for training and determine a target detection model; The detection module is used to input the test set into the trained target detection model to obtain the detection result of the feeder constant.

9. A storage medium storing a computer program, characterized in that: When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 7 are implemented.

10. An electronic device, comprising at least a memory and a processor, wherein a computer program is stored in the memory, wherein: The processor implements the steps of the method of any one of claims 1 to 7 when executing the computer program on the memory.

Images