Risk assessment method and related device for substation based on artificial intelligence

Abstract

An embodiment of the present application relates to the field of safety warning, and provides a risk assessment method for a substation based on artificial intelligence, the method comprising: acquiring a target image of an electric power equipment to be detected in a substation; acquiring a reference image of the electric power equipment to be detected during normal operation; extracting contour difference information between the target image and the reference image; performing risk assessment on the electric power equipment to be detected based on the contour difference information to obtain a risk assessment result; and performing safety warning processing based on the risk assessment result. The method can be performed by conveniently acquiring a target image of the electric power equipment to be detected, using the target image to perform risk assessment, and obtaining a risk assessment result. Finally, the risk assessment result is used to perform safety warning processing, thereby improving the efficiency of risk analysis of electric power equipment in the substation.

Description

Technical Field

[0001] The present application relates to the field of safety early warning technology, and specifically to a risk assessment method and related devices for substations based on artificial intelligence. Background Art

[0002] When conducting safety warning analysis on equipment in existing substations, during the application of merging units of substation equipment, the fault clearing time is prolonged due to the maturity of technical equipment. The relay protection devices in some important scenarios still use cable analog sampling, resulting in the coexistence of analog and digital sampling methods, inconsistent transmission modes, a large number of equipment ports, complex circuits, and high operation and maintenance requirements, resulting in low efficiency in risk assessment of these devices. Summary of the Invention

[0003] The embodiments of the present application provide a risk assessment method and related devices for substations based on artificial intelligence, which can improve the efficiency of risk assessment of equipment in substations.

[0004] A first aspect of an embodiment of the present application provides a risk assessment method for a substation based on artificial intelligence, the method comprising:

[0005] Collect target images of power equipment to be inspected in substations;

[0006] Acquire reference images for testing power equipment during normal operation;

[0007] Extracting contour difference information between the target image and the reference image;

[0008] Performing risk assessment on the power equipment to be detected based on the profile difference information to obtain a risk assessment result;

[0009] Perform safety warning processing based on the risk assessment results.

[0010] In this example, by collecting the target image of the power equipment to be detected in the substation, obtaining a reference image of the power equipment under normal operation, extracting the contour difference information between the target image and the reference image, performing a risk assessment on the power equipment to be detected based on the contour difference information, obtaining a risk assessment result, and performing safety warning processing based on the risk assessment result, therefore, it is possible to conveniently collect the target image of the power equipment to be detected, use the target image to perform a risk assessment, obtain a risk assessment result, and finally use the risk assessment result to perform safety warning processing, thereby improving the efficiency of risk analysis of power equipment in the substation.

[0011] In one possible implementation, a method for extracting contour difference information between the target image and the reference image includes:

[0012] Performing Gaussian noise reduction processing on the target image to obtain a first target image, and performing Gaussian noise reduction processing on the reference image to obtain a first reference image;

[0013] Performing median filtering on the first target image to obtain a second target image, and performing median filtering on the first reference image to obtain a second reference image;

[0014] performing binarization processing on the second target image to obtain a third target image, and performing binarization processing on the second reference image to obtain a third reference image;

[0015] Acquiring a contour similarity between the third target image and the third reference image when the third target image and the third reference image are in an aligned state;

[0016] If the contour similarity is higher than a preset contour similarity, difference extraction is performed on the third target image and the third reference image to obtain contour difference information.

[0017] In one possible implementation, a method for performing difference extraction on the third target image and the third reference image to obtain contour difference information includes:

[0018] performing mask removal processing on the third target image to obtain a fourth target image, and performing mask removal processing on the third reference image to obtain a fourth reference image;

[0019] Difference extraction is performed based on the fourth target image and the fourth reference image to obtain contour difference information.

[0020] In one possible implementation, a method for performing risk assessment on the power equipment to be inspected based on the profile difference information to obtain a risk assessment result includes:

[0021] extracting difference component information according to the contour difference information;

[0022] extracting a difference component sub-image corresponding to the difference component information from the target image;

[0023] determining state information of the difference component according to the difference component sub-image;

[0024] A risk assessment is performed on the power equipment to be inspected according to the status information to obtain a risk assessment result.

[0025] In one possible implementation, a method for performing security warning processing based on the risk assessment result includes:

[0026] Determining a risk level based on the risk assessment results;

[0027] Obtain security warning information based on the risk level;

[0028] Perform warning processing according to the safety warning information.

[0029] A second aspect of an embodiment of the present application provides a risk assessment device for a substation based on artificial intelligence, the device comprising:

[0030] An acquisition unit, used to acquire target images of power equipment to be inspected in a substation;

[0031] an acquisition unit, configured to acquire a reference image for detecting the normal operation of the power equipment;

[0032] an extraction unit, configured to extract contour difference information between the target image and the reference image;

[0033] an evaluation unit, configured to perform a risk evaluation on the power equipment to be detected based on the profile difference information to obtain a risk evaluation result;

[0034] An early warning unit is used to perform safety early warning processing according to the risk assessment result.

[0035] In one possible implementation, the extraction unit is specifically configured to:

[0036] Performing Gaussian noise reduction processing on the target image to obtain a first target image, and performing Gaussian noise reduction processing on the reference image to obtain a first reference image;

[0037] Performing median filtering on the first target image to obtain a second target image, and performing median filtering on the first reference image to obtain a second reference image;

[0038] performing binarization processing on the second target image to obtain a third target image, and performing binarization processing on the second reference image to obtain a third reference image;

[0039] Acquiring a contour similarity between the third target image and the third reference image when the third target image and the third reference image are in an aligned state;

[0040] If the contour similarity is higher than a preset contour similarity, difference extraction is performed on the third target image and the third reference image to obtain contour difference information.

[0041] In one possible implementation, in extracting the difference between the third target image and the third reference image to obtain the contour difference information, the extraction unit is specifically configured to:

[0042] performing mask removal processing on the third target image to obtain a fourth target image, and performing mask removal processing on the third reference image to obtain a fourth reference image;

[0043] Difference extraction is performed based on the fourth target image and the fourth reference image to obtain contour difference information.

[0044] In one possible implementation, the evaluation unit is specifically configured to:

[0045] extracting difference component information according to the contour difference information;

[0046] extracting a difference component sub-image corresponding to the difference component information from the target image;

[0047] determining state information of the difference component according to the difference component sub-image;

[0048] A risk assessment is performed on the power equipment to be inspected according to the status information to obtain a risk assessment result.

[0049] In one possible implementation, the early warning unit is specifically configured to:

[0050] Determining a risk level based on the risk assessment results;

[0051] Obtain security warning information based on the risk level;

[0052] Perform warning processing according to the safety warning information.

[0053] A third aspect of an embodiment of the present application provides a terminal, comprising a processor, an input device, an output device, and a memory, wherein the processor, input device, output device, and memory are interconnected, wherein the memory is used to store a computer program, the computer program includes program instructions, and the processor is configured to call the program instructions and execute the step instructions in the first aspect of the embodiment of the present application.

[0054] The fourth aspect of the embodiments of the present application provides a computer-readable storage medium, wherein the above-mentioned computer-readable storage medium stores a computer program for electronic data exchange, wherein the above-mentioned computer program enables a computer to execute some or all of the steps described in the first aspect of the embodiments of the present application.

[0055] A fifth aspect of the embodiments of the present application provides a computer program product, wherein the computer program product includes a non-transitory computer-readable storage medium storing a computer program, wherein the computer program is operable to cause a computer to perform some or all of the steps described in the first aspect of the embodiments of the present application. The computer program product may be a software installation package. BRIEF DESCRIPTION OF THE DRAWINGS

[0056] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without any creative work.

[0057] Figure 1 A flowchart of a risk assessment method for a substation based on artificial intelligence is provided for an embodiment of the present application;

[0058] Figure 2 A schematic diagram of the structure of a terminal provided in an embodiment of the present application;

[0059] Figure 3 A structural schematic diagram of a risk assessment device for a substation based on artificial intelligence is provided for an embodiment of the present application. DETAILED DESCRIPTION

[0060] The following will be combined with the drawings in the embodiments of this application to clearly and completely describe the technical solutions in the embodiments of this application. Obviously, the embodiments described are only part of the embodiments of this application, not all of the embodiments. Based on the embodiments in this application, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of this application.

[0061] The terms "first," "second," and the like in the specification and claims of this application and the accompanying drawings are used to distinguish between different objects, not to describe a particular order. Furthermore, the terms "including," "having," and any variations thereof, are intended to cover non-exclusive inclusions. For example, a process, method, system, product, or apparatus comprising a series of steps or elements is not limited to the listed steps or elements but may optionally include steps or elements not listed, or may optionally include other steps or elements inherent to the process, method, product, or apparatus.

[0062] References to "embodiments" in this application mean that a particular feature, structure, or characteristic described in connection with the embodiment may be included in at least one embodiment of the application. The appearance of this phrase in various places in the specification does not necessarily refer to the same embodiment, nor does it constitute an independent or alternative embodiment that is mutually exclusive of other embodiments. It is understood, both explicitly and implicitly, by those skilled in the art that the embodiments described in this application may be combined with other embodiments.

[0063] In order to better understand the risk assessment method for substations based on artificial intelligence provided by the embodiment of the present application, the risk assessment method for substations in the existing scheme is briefly introduced below. In the existing scheme, the relay protection devices in substations in some important scenarios still use cable analog sampling, resulting in the coexistence of analog and digital sampling methods, and the transmission mode of analog data and digital data is not unified. In addition, due to the number of equipment ports, etc., a large amount of data comparison is required, and manual participation is required to conduct risk investigation, which makes the efficiency of risk analysis low.

[0064] In order to solve the above technical problems, the embodiment of the present application provides a risk assessment method for substations based on artificial intelligence. It can conveniently collect target images of the power equipment to be detected, use the target images to perform risk assessment, obtain risk assessment results, and finally use the risk assessment results to perform safety warning processing, thereby improving the efficiency of risk analysis of power equipment in substations.

[0065] See also Figure 1 , Figure 1 The present invention provides a flow chart of a risk assessment method for a substation based on artificial intelligence. Figure 1 As shown, the method includes:

[0066] 101. Collect target images of the power equipment to be inspected in the substation.

[0067] The target image can be captured using a camera, specifically a camera on a mobile phone or tablet. The electrical equipment to be inspected can include a power cord, circuit breaker, or terminal. The target image can specifically include the power cord, circuit breaker, or terminal, which is then used to conduct a subsequent risk assessment of the power cord, circuit breaker, or terminal, ultimately forming a safety assessment of the substation. Specifically, the risk assessment results of one or more power equipment to be inspected in the substation can be used as the substation safety assessment result.

[0068] 102. Obtain reference images for detecting power equipment during normal operation.

[0069] Specifically, when the power equipment under inspection is operating normally, a camera can capture its corresponding image for subsequent risk assessment. For example, when inspecting power equipment, the circuit breaker needs to be closed to disconnect the circuit and ensure safety during maintenance. The reference image can be an image of the circuit breaker in the closed state. Both the reference image and the target image can be processed using OpenCV, an image and vision processing library for image processing, computer vision, and machine learning.

[0070] 103. Extract contour difference information between the target image and the reference image.

[0071] The target image and the reference image may be subjected to denoising, filtering, and binarization processing respectively, and then an alignment operation may be performed, and contour difference information may be extracted after the alignment.

[0072] 104. Perform risk assessment on the power equipment to be detected based on the profile difference information to obtain a risk assessment result.

[0073] The difference component information can be extracted based on the contour difference information, and the difference component information can be used to extract the corresponding difference component sub-image in the target image. Risk assessment is performed based on the difference component sub-image to obtain a risk assessment result.

[0074] 105. Perform safety warning processing based on the risk assessment results.

[0075] The risk level can be obtained based on the risk assessment results, and the safety warning processing can be carried out based on the safety warning information corresponding to the risk level. The safety warning information can include the corresponding warning level and the warning text information corresponding to the risk level. Different risk levels have their own corresponding warning text. Specifically, for example, if the risk level is level 1, the warning text may be "There is an operational risk, please pay attention!"; if the risk level is level 2, the warning text may be "The risk is high, please investigate the risk immediately!". This is for example only and is not a specific limitation.

[0076] In this example, by collecting the target image of the power equipment to be detected in the substation, obtaining a reference image of the power equipment under normal operation, extracting the contour difference information between the target image and the reference image, performing a risk assessment on the power equipment to be detected based on the contour difference information, obtaining a risk assessment result, and performing safety warning processing based on the risk assessment result, therefore, it is possible to conveniently collect the target image of the power equipment to be detected, use the target image to perform a risk assessment, obtain a risk assessment result, and finally use the risk assessment result to perform safety warning processing, thereby improving the efficiency of risk analysis of power equipment in the substation.

[0077] In one possible implementation, a method for extracting contour difference information between the target image and the reference image includes:

[0078] A1. performing Gaussian noise reduction processing on the target image to obtain a first target image, and performing Gaussian noise reduction processing on the reference image to obtain a first reference image;

[0079] A2. performing median filtering on the first target image to obtain a second target image, and performing median filtering on the first reference image to obtain a second reference image;

[0080] A3. performing binarization processing on the second target image to obtain a third target image, and performing binarization processing on the second reference image to obtain a third reference image;

[0081] A4. Acquire contour similarity between the third target image and the third reference image when the third target image and the third reference image are in an aligned state;

[0082] A5. If the contour similarity is higher than a preset contour similarity, performing difference extraction on the third target image and the third reference image to obtain contour difference information.

[0083] Specifically, a general Gaussian noise reduction method can be used to perform noise reduction on the target image and the reference image to obtain a corresponding first target image and a first reference image. A general median filtering method can then be used to filter the first target image and the first reference image to obtain a corresponding second target image and a second reference image. A general binarization method can be used to binarize the second target image and the second reference image to obtain a corresponding third target image and a third reference image.

[0084] After processing the third target image and the third reference image, they need to be aligned in the coordinate system. This alignment can be performed using a common alignment method. After the alignment, the power equipment to be inspected in the third target image and the third reference image partially or completely overlap. Specifically, partial overlap indicates that the power equipment to be inspected may be at risk, while complete overlap indicates that the risk is low or non-existent.

[0085] Before obtaining the contour similarity between the third target image and the third reference image when the third target image and the third reference image are in an aligned state, contour features can be extracted from the aligned third target image and the third reference image to obtain corresponding contour features, and then the contour features are amplified for use in image jitter comparison, and SIM is used to evaluate the contour similarity.

[0086] When the contour similarity is less than the preset contour similarity, it indicates that the power equipment to be detected is in a risky state. In this case, there is no need to perform subsequent contour difference information extraction, thereby improving the efficiency of the judgment.

[0087] When extracting contour difference information, the third target image and the third reference image may be subjected to mask removal processing respectively to obtain the corresponding fourth target image and fourth reference image, and finally the fourth target image and the fourth reference image are used to perform difference extraction to obtain contour difference information.

[0088] In this example, the target image and the reference image are subjected to denoising, filtering, and binarization, and then an alignment operation is performed. After the alignment, the contour difference information is extracted, thereby improving the accuracy of the contour difference information extraction.

[0089] In one possible implementation, a method for performing difference extraction on the third target image and the third reference image to obtain contour difference information includes:

[0090] B1. performing mask removal processing on the third target image to obtain a fourth target image, and performing mask removal processing on the third reference image to obtain a fourth reference image;

[0091] B2. Perform difference extraction based on the fourth target image and the fourth reference image to obtain contour difference information.

[0092] A general mask removal processing method may be used to perform mask removal processing on the third target image and the third reference image to obtain a corresponding fourth target image and a fourth reference image.

[0093] OpenCV can be used to perform comparison processing on the fourth target image and the fourth reference image to obtain a comparison processing result, and then the comparison processing result is centrally focused and retained, and the outer frame is extracted to finally obtain contour difference information.

[0094] In one possible implementation, a method for performing risk assessment on the power equipment to be inspected based on the profile difference information to obtain a risk assessment result includes:

[0095] C1. extracting difference component information based on the contour difference information;

[0096] C2. extracting a difference component sub-image corresponding to the difference component information from the target image;

[0097] C3. Determine status information of the difference component according to the difference component sub-image;

[0098] C4. Perform risk assessment on the power equipment to be inspected based on the status information to obtain a risk assessment result.

[0099] Among them, the corresponding difference component information can be extracted based on the position information of the difference contour corresponding to the contour difference information. For example, if the position information of the difference contour corresponding to the contour difference information is the position of an open switch, the switch component can be used as the difference component, and the difference component information can be extracted. Since the contour difference information represents the difference in contour position, it may not fully reflect the complete contour of the difference component, that is, only part of the contour is different. The difference may be an actual difference, or it may be a misidentification caused by the influence of ambient light, etc. Therefore, it is necessary to extract the difference component sub-image that includes the component, and perform subsequent processing based on the difference component sub-image to improve accuracy.

[0100] After extracting the difference component sub-image, the contour information of the difference component can be extracted to obtain the actual contour. Based on this actual contour, the status information of the difference component can be determined. If the similarity between the actual contour and the contour in the normal working state exceeds a preset threshold, the status information is normal. If it is below the preset threshold, the status information is abnormal.

[0101] When using status information for abnormality assessment, if the similarity between the corresponding actual contour and the contour under normal working conditions is lower than the preset threshold, and the difference between the actual contour and the preset threshold is within the preset range, the risk assessment result can be extremely high risk (since such differences are easily ignored, the risk level is higher). If the difference is within the preset range, the risk assessment result is high risk; if the similarity between the actual contour and the contour under normal working conditions is greater than the preset threshold, the risk assessment result is low risk.

[0102] In one possible implementation, a method for performing security warning processing based on the risk assessment result includes:

[0103] D1. Determine the risk level based on the risk assessment results;

[0104] D2. Obtain security warning information based on the risk level;

[0105] D3. Perform warning processing according to the safety warning information.

[0106] The risk assessment result includes a risk level, and the corresponding risk level can be extracted from the risk assessment result.

[0107] Safety warning information can include a corresponding warning level and warning text corresponding to the risk level. Different risk levels have corresponding warning text. For example, if the risk level is level 1, the warning text may be "There is an operational risk, please pay attention!"; if the risk level is level 2, the warning text may be "The risk is high, please investigate immediately!" This is just an example and is not intended to be limiting.

[0108] In a specific implementation, the present application also provides another risk assessment method for a substation based on artificial intelligence, specifically:

[0109] The system runs on an Android phone, which is natively developed using C++ and integrates OpenCV for intelligent image processing. OpenCV is an image and vision processing library used for image processing, computer vision, and machine learning.

[0110] First, read the image of the current facility from the SQLite database. Then call the Android camera to display the binary image and manually align the image.

[0111] Then, the two images are subjected to Gaussian noise reduction, followed by median filtering, grayscale conversion, and binarization thresholding. Based on manual alignment, the images are aligned using the ORB (Oriented FAST and Rotated BRIEF) feature to test the alignment accuracy. After alignment, the contour features are searched and amplified for image jitter comparison. The contour similarity is evaluated. If the similarity is high, the mask is removed to improve the difference comparison. The images are compared using OpenCV. The comparison results are focused on the center and retained. The outer border is removed. The final image is drawn to show the difference. Photos are taken with a mobile phone, including the plug-in, circuit breaker, and terminal, and stored in the mobile phone via a SQLite database. When taking a second photo, the first image is read and compared with the current image to find any differences. To improve the comparison accuracy, the Android system manually aligns the images when taking photos.

[0112] For the same example as above, please refer to Figure 2 , Figure 2 A schematic diagram of the structure of a terminal provided in an embodiment of the present application is shown in FIG. Figure 2 As shown, the system comprises a processor, an input device, an output device and a memory, which are interconnected, wherein the memory is used to store a computer program, the computer program includes program instructions, and the processor is configured to call the program instructions, and the program includes instructions for executing the following steps;

[0113] Collect target images of power equipment to be inspected in substations;

[0114] Acquire reference images for testing power equipment during normal operation;

[0115] Extracting contour difference information between the target image and the reference image;

[0116] Performing risk assessment on the power equipment to be detected based on the profile difference information to obtain a risk assessment result;

[0117] Perform safety warning processing based on the risk assessment results.

[0118] The above mainly introduces the scheme of the embodiment of the present application from the perspective of the execution process on the method side. It is understandable that, in order to implement the above functions, the terminal includes hardware structures and / or software modules corresponding to the execution of each function. Those skilled in the art should easily realize that, in combination with the units and algorithm steps of the various examples described in the embodiments provided herein, the present application can be implemented in the form of hardware or a combination of hardware and computer software. Whether a function is executed in a hardware or computer software driven hardware manner 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.

[0119] The embodiment of the present application can divide the terminal into functional units according to the above method example. For example, each functional unit can be divided according to each function, or two or more functions can be integrated into one processing unit. The above integrated unit can be implemented in the form of hardware or in the form of software functional units. It should be noted that the division of units in the embodiment of the present application is schematic and is only a logical functional division. In actual implementation, there may be other division methods.

[0120] In line with the above, please see Figure 3 , Figure 3 The present invention provides a schematic diagram of a risk assessment device for a substation based on artificial intelligence. Figure 3 As shown, the device includes:

[0121] The acquisition unit 301 is used to acquire target images of the power equipment to be detected in the substation;

[0122] An acquisition unit 302 is configured to acquire a reference image for detecting normal operation of the power equipment;

[0123] An extraction unit 303 is configured to extract contour difference information between the target image and the reference image;

[0124] An evaluation unit 304 is configured to perform a risk evaluation on the power equipment to be detected based on the profile difference information to obtain a risk evaluation result;

[0125] The early warning unit 305 is used to perform security early warning processing according to the risk assessment result.

[0126] In a possible implementation, the extraction unit 303 is specifically configured to:

[0127] Performing Gaussian noise reduction processing on the target image to obtain a first target image, and performing Gaussian noise reduction processing on the reference image to obtain a first reference image;

[0128] Performing median filtering on the first target image to obtain a second target image, and performing median filtering on the first reference image to obtain a second reference image;

[0129] performing binarization processing on the second target image to obtain a third target image, and performing binarization processing on the second reference image to obtain a third reference image;

[0130] Acquiring a contour similarity between the third target image and the third reference image when the third target image and the third reference image are in an aligned state;

[0131] If the contour similarity is higher than a preset contour similarity, difference extraction is performed on the third target image and the third reference image to obtain contour difference information.

[0132] In a possible implementation, in extracting the difference between the third target image and the third reference image to obtain the contour difference information, the extraction unit 303 is specifically configured to:

[0133] performing mask removal processing on the third target image to obtain a fourth target image, and performing mask removal processing on the third reference image to obtain a fourth reference image;

[0134] Difference extraction is performed based on the fourth target image and the fourth reference image to obtain contour difference information.

[0135] In one possible implementation, the evaluation unit 304 is specifically configured to:

[0136] extracting difference component information according to the contour difference information;

[0137] extracting a difference component sub-image corresponding to the difference component information from the target image;

[0138] determining state information of the difference component according to the difference component sub-image;

[0139] A risk assessment is performed on the power equipment to be inspected according to the status information to obtain a risk assessment result.

[0140] In one possible implementation, the early warning unit 305 is specifically configured to:

[0141] Determining a risk level based on the risk assessment results;

[0142] Obtain security warning information based on the risk level;

[0143] Perform warning processing according to the safety warning information.

[0144] An embodiment of the present application also provides a computer storage medium, wherein the computer storage medium stores a computer program for electronic data exchange, and the computer program enables a computer to execute part or all of the steps of any one of the artificial intelligence-based substation risk assessment methods described in the above method embodiments.

[0145] An embodiment of the present application also provides a computer program product, which includes a non-transitory computer-readable storage medium storing a computer program, and the computer program enables a computer to execute part or all of the steps of any one of the artificial intelligence-based substation risk assessment methods recorded in the above method embodiments.

[0146] It should be noted that for the aforementioned method embodiments, for the sake of simplicity, they are all expressed as a series of action combinations, but those skilled in the art should be aware that this application is not limited by the order of the actions described, because according to this application, certain steps can be performed in other orders or simultaneously. Secondly, those skilled in the art should also be aware that the embodiments described in the specification are all preferred embodiments, and the actions and modules involved are not necessarily required by this application.

[0147] In the above embodiments, the description of each embodiment has its own focus. For parts that are not described in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0148] In the several embodiments provided in this application, it should be understood that the disclosed devices can be implemented in other ways. For example, the device embodiments described above are merely illustrative. For example, the division of the units is merely a logical function division. In actual implementation, there may be other division methods, 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, and the indirect coupling or communication connection of devices or units can be electrical or other forms.

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

[0150] In addition, the functional units in the various embodiments of the application may be integrated into a single processing unit, or each unit may exist physically separately, or two or more units may be integrated into a single unit. The aforementioned integrated units may be implemented in the form of hardware or software program modules.

[0151] If the integrated unit is implemented in the form of a software program module and sold or used as an independent product, it can be stored in a computer-readable memory. Based on this understanding, the technical solution of the present application is essentially or the part that contributes to the prior art or all or part of the technical solution can be embodied in the form of a software product, and the computer software product is stored in a memory, including a number of instructions for enabling a computer device (which can be a personal computer, a server or a network device, etc.) to execute all or part of the steps of the method described in each embodiment of the present application. The aforementioned memory includes: various media that can store program codes, such as a U disk, a read-only memory (ROM), a random access memory (RAM), a mobile hard disk, a magnetic disk or an optical disk.

[0152] Those skilled in the art will understand that all or part of the steps in the various methods of the above embodiments can be completed by instructing related hardware through a program, and the program can be stored in a computer-readable memory, which may include: a flash drive, a read-only memory, a random access memory, a magnetic disk or an optical disk, etc.

[0153] The above is a detailed introduction to the embodiments of the present application. Specific examples are used herein to illustrate the principles and implementation methods of the present application. The description of the above embodiments is only used to help understand the method and core idea of ​​the present application. At the same time, for those skilled in the art, according to the idea of ​​the present application, there may be changes in the specific implementation methods and application scope. In summary, the content of this specification should not be understood as a limitation on the present application.

Claims

1. A risk assessment method for substations based on artificial intelligence, characterized in that: The method comprises: Collect target images of power equipment to be inspected in substations; Acquire reference images for testing power equipment during normal operation; Extracting contour difference information between the target image and the reference image; Performing risk assessment on the power equipment to be detected according to the profile difference information to obtain a risk assessment result; Perform safety warning processing according to the risk assessment results.

2. The risk assessment method for substations based on artificial intelligence according to claim 1 is characterized in that: The extracting the contour difference information between the target image and the reference image comprises: Performing Gaussian noise reduction processing on the target image to obtain a first target image, and performing Gaussian noise reduction processing on the reference image to obtain a first reference image; Performing median filtering on the first target image to obtain a second target image, and performing median filtering on the first reference image to obtain a second reference image; Binarizing the second target image to obtain a third target image, and binarizing the second reference image to obtain a third reference image; Acquiring a contour similarity between the third target image and the third reference image when the third target image and the third reference image are in an aligned state; If the contour similarity is higher than a preset contour similarity, a difference extraction is performed on the third target image and the third reference image to obtain contour difference information.

3. The risk assessment method for substations based on artificial intelligence according to claim 2 is characterized in that: The step of performing difference extraction on the third target image and the third reference image to obtain contour difference information includes: performing mask removal processing on the third target image to obtain a fourth target image, and performing mask removal processing on the third reference image to obtain a fourth reference image; Difference extraction is performed based on the fourth target image and the fourth reference image to obtain contour difference information.

4. The risk assessment method for a substation based on artificial intelligence according to any one of claims 1 to 3, characterized in that: The step of performing risk assessment on the power equipment to be detected according to the profile difference information to obtain a risk assessment result includes: extracting difference component information according to the contour difference information; extracting a difference component sub-image corresponding to the difference component information from the target image; determining state information of the difference component according to the difference component sub-image; A risk assessment is performed on the power equipment to be inspected according to the state information to obtain a risk assessment result.

5. The risk assessment method for substations based on artificial intelligence according to claim 4 is characterized in that: The performing of safety warning processing according to the risk assessment result includes: Determining a risk level based on the risk assessment results; Obtaining security warning information according to the risk level; Perform warning processing according to the safety warning information.

6. A risk assessment device for a substation based on artificial intelligence, characterized in that: The device comprises: A collection unit, used to collect target images of power equipment to be detected in the substation; An acquisition unit, used for acquiring a reference image for detecting the normal operation of the electric power equipment; An extraction unit, used to extract contour difference information between the target image and the reference image; An evaluation unit, configured to perform risk evaluation on the power equipment to be detected according to the profile difference information to obtain a risk evaluation result; The early warning unit is used to perform safety early warning processing according to the risk assessment result.

7. The risk assessment method for substations based on artificial intelligence according to claim 6 is characterized in that: The extraction unit is specifically used for: Performing Gaussian noise reduction processing on the target image to obtain a first target image, and performing Gaussian noise reduction processing on the reference image to obtain a first reference image; Performing median filtering on the first target image to obtain a second target image, and performing median filtering on the first reference image to obtain a second reference image; Binarizing the second target image to obtain a third target image, and binarizing the second reference image to obtain a third reference image; Acquiring a contour similarity between the third target image and the third reference image when the third target image and the third reference image are in an aligned state; If the contour similarity is higher than a preset contour similarity, a difference extraction is performed on the third target image and the third reference image to obtain contour difference information.

8. The risk assessment method for substations based on artificial intelligence according to claim 7 is characterized in that: In the aspect of extracting the difference between the third target image and the third reference image to obtain the contour difference information, the extraction unit is specifically used for: performing mask removal processing on the third target image to obtain a fourth target image, and performing mask removal processing on the third reference image to obtain a fourth reference image; Difference extraction is performed based on the fourth target image and the fourth reference image to obtain contour difference information.

9. A terminal, characterized in that: It includes a processor, an input device, an output device and a memory, which are interconnected, wherein the memory is used to store a computer program, the computer program includes program instructions, and the processor is configured to call the program instructions to execute the risk assessment method for substations based on artificial intelligence as described in any one of claims 1 to 5.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program, which includes program instructions. When the program instructions are executed by a processor, the processor executes the risk assessment method for a substation based on artificial intelligence as described in any one of claims 1 to 5.

Images