Method, device, storage medium, equipment and product for identifying substation fault

Abstract

The application discloses a method, device, storage medium, equipment and product for identifying substation faults. The method comprises: acquiring a current industrial video picture in a substation, wherein the current industrial video picture comprises a plurality of frame video pictures; performing feature extraction on a current frame video picture in the plurality of frame video pictures to obtain a digital feature value; comparing the digital feature value with a plurality of pre-determined fault image feature thresholds to obtain a comparison result; and identifying whether a substation fault exists in the current frame video picture based on the comparison result, wherein the substation fault comprises a black screen fault, a flashing light fault and a smoke fault. The application solves the technical problem that a unified video picture analysis service system cannot be arranged in a control center to realize real-time monitoring of substation faults in the prior art.

Description

Technical Field

[0001] This invention relates to the field of substation fault identification technology, and more specifically, to a method, apparatus, storage medium, equipment, and product for identifying substation faults. Background Technology

[0002] The number of substations has been increasing year by year with socio-economic development. Currently, the number of substations above 110kV is enormous, and each substation is required to be equipped with a corresponding number of surveillance cameras. Main transmission lines now have full video surveillance coverage, and the number of camera feeds connected to the control center has also increased dramatically. When a fault occurs in the power grid, manually searching through massive amounts of camera feeds to discover, examine, locate, and identify the location and type of the fault is extremely time-consuming and inefficient. Furthermore, it is difficult to promptly alert and effectively control fires.

[0003] Furthermore, due to the limitations of traditional substation industrial video platforms in terms of data transmission technology, the method of deploying a unified video image analysis service system in the control center is limited by the bandwidth of the integrated data network, making it difficult to achieve real-time and comprehensive coverage of all monitoring cameras in all substations, and thus failing to achieve proactive perception and real-time monitoring of the fault operation status of substations.

[0004] There is currently no effective solution to the above problems. Summary of the Invention

[0005] This invention provides a method, apparatus, storage medium, equipment, and product for identifying substation faults, thereby at least solving the technical problem in related technologies where deploying a unified video image analysis service system in the control center cannot achieve real-time monitoring of substation faults.

[0006] According to one aspect of the present invention, a method for identifying substation faults is provided, comprising: acquiring a current industrial video frame within the substation, wherein the current industrial video frame includes multiple video frames; extracting features from the current video frame among the multiple video frames to obtain digital feature values; comparing the digital feature values ​​with multiple predetermined fault image feature thresholds to obtain a comparison result; and identifying whether a substation fault exists in the current video frame based on the comparison result, wherein the substation fault includes: black screen fault, flashing fault, and smoke fault.

[0007] Optionally, before acquiring the industrial video footage within the substation, the method further includes: acquiring historical industrial video footage within the substation in advance; identifying historical video frames containing the substation fault from the historical industrial video footage; extracting features from the historical video frames to obtain multiple fault image feature thresholds, and using these multiple fault image feature thresholds as the basis for identifying whether the current frame video footage contains the substation fault.

[0008] Optionally, the aforementioned digital feature values ​​include: horizontal and vertical feature values ​​of any fault phenomenon. Feature extraction is performed on the current frame of the video image from the multiple video frames to obtain digital feature values, including: calculating the image brightness of the current frame of the video image based on the component values ​​of the three primary colors to obtain pixel brightness values; inputting the pixel brightness values ​​into a pre-established fault recognition model to obtain the aforementioned horizontal and vertical feature values. The fault recognition model is trained and learned based on historical video frames containing the aforementioned substation faults from historical industrial video footage within the substation. The aforementioned horizontal feature values ​​reflect the statistical distribution of different pixel values ​​in the same video image; the aforementioned vertical feature values ​​reflect the statistical distribution of the same pixel value in different video images.

[0009] Optionally, identifying whether a substation fault exists in the current frame video based on the comparison results includes: if the comparison result is that the digital feature value is greater than or equal to any one of the fault image feature thresholds, then it is determined that the current frame video contains the substation fault; if the comparison result is that all the digital feature values ​​are less than multiple of the fault image feature thresholds, then it is determined that the current frame video does not contain the substation fault.

[0010] Optionally, after determining that the current frame video shows a substation fault, the method further includes: determining whether there is a fire hazard at the substation based on the substation fault; if it is determined that there is a fire hazard at the substation, outputting fire alarm information, wherein the fire alarm information is used to prompt staff to handle the fire hazard in a timely manner; if it is determined that there is no fire hazard at the substation, determining fault handling decision information based on the substation fault; outputting fault prompt information and the fault handling decision information, wherein the fault prompt information is used to prompt staff to handle the substation fault in a timely manner based on the fault handling decision information.

[0011] Optionally, after determining that the current frame video does not contain the substation fault, the method further includes: returning to the step of obtaining the current industrial video image within the substation; after determining that the current frame video contains the substation fault, the method further includes: after initializing multiple fault image feature thresholds, returning to the step of obtaining the current industrial video image within the substation.

[0012] According to another aspect of the present invention, an apparatus for identifying substation faults is also provided, comprising: an acquisition module for acquiring current industrial video footage within the substation, wherein the current industrial video footage includes multiple video frames; an extraction module for extracting features from the current video frame among the multiple video frames to obtain digital feature values; a comparison module for comparing the digital feature values ​​with multiple predetermined fault image feature thresholds to obtain a comparison result; and an identification module for identifying whether a substation fault exists in the current video frame based on the comparison result, wherein the substation fault includes: black screen fault, flashing fault, and smoke fault.

[0013] According to another aspect of the present invention, a computer-readable storage medium is also provided, which stores a plurality of instructions adapted for loading by a processor and executing any one of the above-described methods for identifying substation faults.

[0014] According to another aspect of the present invention, an electronic device is also provided, including a memory and a processor, wherein the memory stores a computer program and the processor is configured to run the computer program to perform any of the above-described methods for identifying substation faults.

[0015] According to another aspect of the present invention, a computer program product is also provided, including a computer program that, when executed by a processor, implements the method for identifying substation faults according to any one of the above embodiments.

[0016] In this embodiment of the invention, the current industrial video frame within the substation is acquired, comprising multiple video frames. Feature extraction is performed on the current video frame from these multiple frames to obtain digital feature values. These digital feature values ​​are then compared with predetermined fault image feature thresholds to obtain comparison results. Based on these comparison results, the presence of a substation fault in the current video frame is identified. The substation faults include black screen faults, flashing faults, and smoke faults. This achieves the goal of timely real-time monitoring of substation faults, thereby improving the safe operation of the power grid and the reliability of power supply. Furthermore, it solves the technical problem in related technologies where a unified video image analysis service system deployed in the control center cannot achieve real-time monitoring of substation faults. Attached Figure Description

[0017] The accompanying drawings, which are included to provide a further understanding of the invention and form part of this application, illustrate exemplary embodiments of the invention and, together with their description, serve to explain the invention and do not constitute an undue limitation thereof. In the drawings:

[0018] Figure 1 This is a flowchart of a method for identifying substation faults according to an embodiment of the present invention;

[0019] Figure 2 This is a flowchart of an optional method for identifying substation faults according to an embodiment of the present invention;

[0020] Figure 3 This is a schematic diagram of a device for identifying substation faults according to an embodiment of the present invention. Detailed Implementation

[0021] To enable those skilled in the art to better understand the present invention, the technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings of the embodiments of the present invention. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort should fall within the scope of protection of the present invention.

[0022] It should be noted that the terms "first," "second," etc., in the specification, claims, and accompanying drawings of this invention are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that the embodiments of the invention described herein can be implemented in orders other than those illustrated or described herein. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover a non-exclusive inclusion; for example, a process, method, system, product, or apparatus that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or apparatus.

[0023] Example 1

[0024] According to an embodiment of the present invention, a method for identifying substation faults is provided. It should be noted that the steps shown in the flowchart in the accompanying drawings can be executed in a computer system such as a set of computer-executable instructions. Furthermore, although a logical order is shown in the flowchart, in some cases, the steps shown or described may be executed in a different order than that shown here.

[0025] Figure 1 This is a flowchart of a method for identifying substation faults according to an embodiment of the present invention, such as... Figure 1 As shown, the method includes the following steps:

[0026] Step S102: Obtain the current industrial video frame inside the substation, wherein the current industrial video frame contains multiple video frames.

[0027] Step S104: Extract features from the current frame of the video frame among the above multiple video frames to obtain digital feature values;

[0028] Step S106: Compare the above digital feature values ​​with multiple predetermined fault image feature thresholds to obtain the comparison results;

[0029] Step S108: Based on the comparison results, identify whether there is a substation fault in the current frame video. The substation faults include: black screen fault, flashing fault, and smoke fault.

[0030] In this embodiment of the invention, by acquiring the current industrial video footage within a substation, wherein the current industrial video footage contains multiple video frames; performing feature extraction on the current video frame from the multiple video frames to obtain digital feature values, wherein the digital feature values ​​include: horizontal feature values ​​and vertical feature values ​​of any fault phenomenon; comparing the digital feature values ​​with multiple predetermined fault image feature thresholds to obtain comparison results; and identifying whether a substation fault exists in the current video frame based on the comparison results, wherein the substation fault includes: black screen fault, flashing fault, and smoke fault, the invention achieves the purpose of timely real-time monitoring of substation faults, thereby realizing the technical effect of improving the safe operation of the power grid and the reliability of power supply, and thus solving the technical problem in related technologies where a unified video footage analysis service system deployed in the control center cannot achieve real-time monitoring of substation faults.

[0031] Optionally, each substation should be equipped with a corresponding number of surveillance cameras as required to monitor the operation status within the substation, and the main transmission lines should achieve full video surveillance coverage. Multiple surveillance cameras are connected to the substation's industrial video platform, which is connected to a unified video image analysis service system deployed in the control center. The monitoring images uploaded by the multiple cameras connected to the control center constitute the current industrial video image within the substation, which contains multiple video frames.

[0032] Optionally, the aforementioned digital feature values ​​include: horizontal and vertical feature values ​​of any fault phenomenon. This is achieved by digitizing industrial video footage within the substation and selectively collecting digital feature values ​​of fault images from the industrial video footage within the substation. These digital feature values ​​include both horizontal and vertical feature values ​​for a specific fault phenomenon. When the current industrial video footage from the substation is received and input to the control center in real time, since the current industrial video footage contains multiple video frames, features are extracted from the real-time input current video frame among these multiple frames. The obtained digital feature values ​​are compared with existing fault image feature thresholds. Based on the comparison results, it is determined whether a substation fault exists in the current video frame. The multiple fault image feature thresholds serve as reference thresholds. If the digital feature value detected in real time is higher than a certain fault image feature threshold, it is determined that a substation fault has occurred in the current video frame.

[0033] Through the embodiments of this application, intelligent sensing and edge computing technologies can be used to combine the substation abnormal phenomenon identification and analysis alarm device with the control center's integrated processing platform to create a brand-new, intelligent, and real-time power grid operation fault real-time perception and controller auxiliary decision-making system, which is particularly necessary for timely detection and effective control of substation fires and fire hazards.

[0034] As an optional embodiment, Figure 2 This is a flowchart of an optional method for identifying substation faults according to an embodiment of the present invention, such as... Figure 2 As shown, before acquiring industrial video footage from within the substation, the above method further includes:

[0035] Step S202: Pre-acquire historical industrial video footage of the aforementioned substation;

[0036] Step S204: Determine that the aforementioned historical industrial video footage contains historical video frames showing the aforementioned substation fault.

[0037] Step S206: Feature extraction is performed on the aforementioned historical frame video images to obtain multiple fault image feature thresholds, which are then used as the basis for identifying whether the current frame video image contains the aforementioned substation fault.

[0038] In the above optional embodiments, historical industrial video footage of the substation can be acquired in advance, and historical video frames containing substation faults can be identified from the historical industrial video footage. Feature extraction can be performed on the historical video frames to obtain multiple fault image feature thresholds.

[0039] By pre-extracting fault image features such as black screens, flashes, and smoke from industrial videos within substations, and obtaining multiple pre-determined fault image feature thresholds, the processing of industrial video images within substations can be referenced to determine whether faults exist. This allows for the timely detection of substation faults such as black screens, flashes, and smoke. These substation faults are primarily used to reflect whether there are fire hazards within the substation, achieving the purpose of identifying fire hazards and issuing alarms. This improves the efficiency of fault location and handling decisions by staff, thereby ensuring the safe and stable operation of the power grid.

[0040] As an optional embodiment, feature extraction is performed on the current frame of the video frame among the above-mentioned multiple video frames to obtain digital feature values, including:

[0041] Step S302: Calculate the image brightness of the current frame video frame based on the component values ​​of the three primary colors to obtain the pixel brightness value;

[0042] Step S304: Input the pixel brightness value into the pre-established fault identification model to obtain the horizontal feature value and the vertical feature value. The fault identification model is trained and learned based on historical frame video images of the substation fault in the historical industrial video images of the substation. The horizontal feature value is used to reflect the statistical distribution of different pixel values ​​in the same video image. The vertical feature value is used to reflect the statistical distribution of the same pixel value in different video images.

[0043] In the above optional embodiments, the brightness of the current frame video image can be extracted based on the component values ​​of the three primary colors RGB. The pixel brightness value Y can be calculated using the following formula: Y = (0.299*R) + (0.587*G) + (0.114*B). By inputting the above pixel brightness value into a pre-established fault identification model, the above horizontal feature value and the above vertical feature value are obtained. That is, the fault identification model is established based on the extracted images of black screen, flash, and smoke to organize the horizontal and vertical feature values. The horizontal feature value refers to the statistical distribution of different pixel values ​​in the same image; the vertical feature value refers to the statistical distribution of the same pixel value in different images.

[0044] As an optional embodiment, when the current frame of video screen goes black, all pixels of the digital image are black, and the values ​​of the red (R), green (G), and blue (B) components of each pixel are very low, resulting in a very low brightness value. The brightness value is calculated for each pixel of each frame of image. When the brightness value of all pixels is less than a preset black screen fault characteristic threshold, a black screen fault can be determined to have occurred.

[0045] As another optional embodiment, when a flash occurs in the current frame of video, the pixel brightness in the flash area is very high. Therefore, the pixel brightness value in the flash area differs significantly from that in the real-time model. When this difference exceeds the corresponding flash fault characteristic threshold and the duration is short, it can be determined that an arc discharge phenomenon has occurred, i.e., a flash fault has been identified.

[0046] As another optional embodiment, when smoke appears in the current frame of the video, the atmospheric scattering caused by smoke particles affects image imaging. Smoke attenuates scene radiation, resulting in semi-transparent properties and creating a suspected smoke region. Within this suspected smoke region, real-time image modeling and motion region extraction are performed. Utilizing features such as the color, texture, shape, drift, flicker, and frequency of the smoke, and combining these diverse features for classification, along with the edge point characteristics of both smoke and non-smoke interference, a fuzzy clustering model for edge points suitable for smoke detection is obtained, which can determine the occurrence of smoke.

[0047] It should be noted that the solution provided in this application embodiment has been proven feasible through use and has completed system testing. Testing has shown that the system is fully functional and meets the needs of practical applications. As an optional embodiment, during implementation or installation, the model of the camera and the DVR and NVR used in the substation can be considered to avoid inaccurate acquisition of video protocols and identification of DVR / NVR camera feeds by the edge computing terminal, which could lead to inaccurate calculation and monitoring correspondence or failure to acquire video sources, resulting in missed warning opportunities.

[0048] As an optional embodiment, such as Figure 2 As shown, based on the above comparison results, identifying whether a substation fault exists in the current frame of the video footage includes:

[0049] Step S402: If the comparison result is that the digital feature value is greater than or equal to any of the fault image feature thresholds, then it is determined that the current frame video image has the substation fault.

[0050] Step S404: If the comparison result shows that all of the above digital feature values ​​are less than the threshold values ​​of multiple above fault image features, then it is determined that the above current frame video does not contain the above substation fault.

[0051] In the above optional embodiments, the digital feature value is compared with each of the above fault image feature thresholds. If the comparison result is that the digital feature value is greater than or equal to any of the above fault image feature thresholds, it is determined that the current frame video image has the above substation fault; otherwise, if the comparison result is that the digital feature value is less than multiple of the above fault image feature thresholds, it is determined that the current frame video image does not have the above substation fault.

[0052] Substations are crucial hubs for voltage conversion and power distribution in power systems, containing numerous electrical equipment including transformers, high-voltage switches, capacitors, and power cables. When equipment insulation is damaged due to a fault, fire hazards are easily created, making them high-risk locations for electrical fires. Fire hazards in substations are a significant factor affecting the operational risks of the power grid; a fire in a substation will severely impact the safe operation of the grid and the reliability of power supply. Therefore, fire and fire hazard identification, analysis, and alarm systems are of great importance to the safe operation of substations. However, currently widely used smoke alarms and other detection and sensing systems suffer from problems such as lag and high false alarm rates, and cannot promptly detect fire hazards such as arcing, electric sparks, and small amounts of smoke.

[0053] Therefore, in this embodiment of the application, an optional embodiment is also provided, in which, after determining that the current frame video image contains the aforementioned substation fault, the method further includes:

[0054] Step S502: Determine whether there is a fire hazard in the substation based on the aforementioned substation fault.

[0055] Step S504: If it is determined that the above-mentioned fire hazard exists in the above-mentioned substation, a fire alarm message is output, wherein the fire alarm message is used to prompt the staff to deal with the above-mentioned fire hazard in a timely manner.

[0056] Step S506: If it is determined that there is no fire hazard in the substation, then determine the fault handling decision information based on the substation fault.

[0057] Step S508: Output fault prompt information and the aforementioned fault handling decision information, wherein the aforementioned fault prompt information is used to prompt staff to handle the aforementioned substation fault in a timely manner based on the aforementioned fault handling decision information.

[0058] In this embodiment of the application, the substation is first judged to determine whether there is a fire hazard based on the substation fault. It should be noted that when a fire hazard occurs, the fluctuation range of the feature value of the real-time image model is large. Suspicious video images can be extracted from the video stream, such as black screen, flashing, and smoke video images.

[0059] For example, if it is determined that the aforementioned fire hazard exists in the substation, a fire alarm message will be output to prompt staff to handle the fire hazard in a timely manner; if it is determined that the aforementioned fire hazard does not exist in the substation, fault handling decision information will be determined based on the fault of the substation, and fault prompt information and the aforementioned fault handling decision information will be output to prompt staff to handle the fault of the substation in a timely manner based on the aforementioned fault handling decision information.

[0060] Through the above embodiments of this application, fire hazards such as substation fires and arcing or small amounts of smoke within the station can be detected, effectively solving the problems of lag and high false alarm rate in currently widely used smoke alarm and other detection and sensing systems.

[0061] As an optional embodiment, it remains as follows Figure 2 As shown, after determining that the current frame video does not contain the substation fault, the method further includes: returning to the step of obtaining the current industrial video image within the substation.

[0062] As another optional embodiment, after determining that the current frame video image contains the substation fault, the method further includes: after initializing multiple fault image feature thresholds, returning to the step of obtaining the current industrial video image within the substation.

[0063] As an optional implementation, if the real-time image model within the substation is normal but a fault has already occurred, it is necessary to reinitialize multiple of the aforementioned fault image feature thresholds before returning to the step of obtaining the current industrial video frame within the substation. If it is determined that the current frame of video does not contain the aforementioned substation fault, then the process directly returns to the step of obtaining the current industrial video frame within the substation.

[0064] Example 2

[0065] According to an embodiment of the present invention, an apparatus embodiment for implementing the above-described method for identifying substation faults is also provided. Figure 3This is a schematic diagram of a device for identifying substation faults according to an embodiment of the present invention, as shown below. Figure 3 As shown, the above-mentioned device for identifying substation faults includes: an acquisition module 300, an extraction module 302, a comparison module 304, and an identification module 306, wherein:

[0066] The acquisition module 300 is used to acquire the current industrial video image within the substation, wherein the current industrial video image contains multiple video frames; the extraction module 302 is used to extract features from the current video frame among the multiple video frames to obtain digital feature values; the comparison module 304 is used to compare the digital feature values ​​with multiple predetermined fault image feature thresholds to obtain comparison results; and the identification module 306 is used to identify whether there is a substation fault in the current video frame based on the comparison results, wherein the substation fault includes: black screen fault, flashing fault, and smoke fault.

[0067] It should be noted that the above modules can be implemented by software or hardware. For example, for the latter, it can be implemented in the following ways: the above modules can be located in the same processor; or the above modules can be located in different processors in any combination.

[0068] It should be noted that the acquisition module 300, extraction module 302, comparison module 304, and identification module 306 mentioned above correspond to steps S102 to S108 in Embodiment 1. The instances and application scenarios implemented by the above modules and their corresponding steps are the same, but they are not limited to the content disclosed in Embodiment 1. It should be noted that the above modules, as part of the device, can run on a computer terminal.

[0069] It should be noted that the optional or preferred implementation methods of this embodiment can be found in the relevant description in Embodiment 1, and will not be repeated here.

[0070] The aforementioned device for identifying substation faults may also include a processor and a memory. The aforementioned acquisition module 300, extraction module 302, comparison module 304, and identification module 306 are all stored in the memory as program units, and the processor executes the aforementioned program units stored in the memory to realize the corresponding functions.

[0071] The processor contains a core that retrieves corresponding program units from memory. One or more cores may be configured. Memory may include non-persistent memory in computer-readable media, such as random access memory (RAM) and / or non-volatile memory, such as read-only memory (ROM) or flash RAM. Memory includes at least one memory chip.

[0072] According to an embodiment of this application, an embodiment of a computer-readable storage medium is also provided. Optionally, in this embodiment, the computer-readable storage medium includes a stored program, wherein, when the program is executed, it controls the device where the computer-readable storage medium is located to perform any of the methods for identifying substation faults described above.

[0073] Optionally, in this embodiment, the computer-readable storage medium may be located in any computer terminal in a group of computer terminals in a computer network, or in any mobile terminal in a group of mobile terminals, and the computer-readable storage medium includes a stored program.

[0074] Optionally, during program execution, the device containing the computer-readable storage medium performs the following functions: acquiring the current industrial video frame within the substation, wherein the current industrial video frame contains multiple video frames; extracting features from the current video frame among the multiple video frames to obtain digital feature values, wherein the digital feature values ​​include: horizontal and vertical feature values ​​of any fault phenomenon; comparing the digital feature values ​​with multiple predetermined fault image feature thresholds to obtain comparison results; and identifying whether a substation fault exists in the current video frame based on the comparison results, wherein the substation fault includes: black screen fault, flashing fault, and smoke fault.

[0075] Optionally, during program execution, the device containing the computer-readable storage medium may perform the following functions: pre-acquire historical industrial video footage of the substation; determine historical video frames containing substation faults from the historical industrial video footage; extract features from the historical video frames to obtain multiple fault image feature thresholds, and use these multiple fault image feature thresholds as the basis for identifying whether the current video frame contains a substation fault.

[0076] Optionally, during program execution, the device containing the computer-readable storage medium performs the following functions: calculating the image brightness of the current frame video frame based on the component values ​​of the three primary colors to obtain pixel brightness values; inputting the pixel brightness values ​​into a pre-established fault identification model to obtain the horizontal feature values ​​and the vertical feature values, wherein the fault identification model is trained and learned based on historical frame video frames containing the substation fault in historical industrial video frames within the substation; the horizontal feature values ​​are used to reflect the statistical distribution of different pixel values ​​in the same video image; the vertical feature values ​​are used to reflect the statistical distribution of the same pixel value in different video images.

[0077] Optionally, during program execution, the device containing the computer-readable storage medium is controlled to perform the following functions: if the comparison result is that the digital feature value is greater than or equal to any one of the fault image feature thresholds, then it is determined that the current frame video image contains the substation fault; if the comparison result is that all the digital feature values ​​are less than multiple of the fault image feature thresholds, then it is determined that the current frame video image does not contain the substation fault.

[0078] Optionally, during program execution, the device containing the computer-readable storage medium may perform the following functions: determine whether there is a fire hazard in the substation based on the aforementioned substation fault; if it is determined that there is a fire hazard in the substation, output fire alarm information, wherein the fire alarm information is used to prompt staff to handle the fire hazard in a timely manner; if it is determined that there is no fire hazard in the substation, determine fault handling decision information based on the aforementioned substation fault; output fault prompt information and the aforementioned fault handling decision information, wherein the fault prompt information is used to prompt staff to handle the substation fault in a timely manner based on the aforementioned fault handling decision information.

[0079] Optionally, during program execution, the device containing the computer-readable storage medium is controlled to perform the following functions: return to the step of acquiring the current industrial video image within the substation; after determining that the current frame video image contains the substation fault, the method further includes: after initializing multiple fault image feature thresholds, returning to the step of acquiring the current industrial video image within the substation.

[0080] According to an embodiment of the present invention, a computer-readable storage medium is also provided, wherein the computer-readable storage medium stores a plurality of instructions adapted for loading by a processor and executing any one of the above-described methods for identifying substation faults.

[0081] According to an embodiment of the present invention, an embodiment of an electronic device is also provided, including a memory and a processor, wherein the memory stores a computer program and the processor is configured to run the computer program to perform any of the above-described methods for identifying substation faults.

[0082] According to an embodiment of the present invention, an embodiment of a computer program product is also provided, including a computer program that, when executed by a processor, implements the method for identifying substation faults according to any one of the above-described methods.

[0083] The sequence numbers of the above embodiments of the present invention are for descriptive purposes only and do not represent the superiority or inferiority of the embodiments.

[0084] In the above embodiments of the present invention, the descriptions of each embodiment have different focuses. For parts not described in detail in a certain embodiment, please refer to the relevant descriptions of other embodiments.

[0085] In the several embodiments provided in this application, it should be understood that the disclosed technical content can be implemented in other ways. The device embodiments described above are merely illustrative; for example, the division of units can be a logical functional division, and in actual implementation, there may be other division methods. For instance, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the displayed or discussed mutual coupling, direct coupling, or communication connection may be through some interfaces; the indirect coupling or communication connection between units or modules may be electrical or other forms.

[0086] The units described as separate components may or may not be physically separate. 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 units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0087] Furthermore, the functional units in the various embodiments of the present invention can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or as a software functional unit.

[0088] If the integrated unit is implemented as 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 technical solution of the present invention, in essence, or the part that contributes to the prior art, or all or part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a computer-readable storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of the present invention. The aforementioned computer-readable storage medium includes various media capable of storing program code, such as USB flash drives, read-only memory (ROM), random access memory (RAM), portable hard drives, magnetic disks, or optical disks.

[0089] The above description is only a preferred embodiment of the present invention. It should be noted that for those skilled in the art, several improvements and modifications can be made without departing from the principle of the present invention, and these improvements and modifications should also be considered within the scope of protection of the present invention.

Claims

1. A method for identifying substation faults, characterized in that, include: Acquire the current industrial video feed within the substation, wherein the current industrial video feed contains multiple video frames; Feature extraction is performed on the current frame of the multiple video frames to obtain digital feature values; The digital feature values ​​are compared with multiple predetermined fault image feature thresholds to obtain the comparison results; Based on the comparison results, it is identified whether there is a substation fault in the current frame video image, wherein the substation fault includes: black screen fault, flashing fault, and smoke fault; The digital feature values ​​include: horizontal and vertical feature values ​​for any fault phenomenon; feature extraction is performed on the current frame of the multiple video frames to obtain digital feature values, including: calculating the image brightness of the current frame of the video frame based on the component values ​​of the three primary colors to obtain pixel brightness values; inputting the pixel brightness values ​​into a pre-established fault identification model to obtain the horizontal and vertical feature values, wherein the fault identification model is trained and learned based on historical frame video frames containing the substation fault in historical industrial video footage of the substation; the horizontal feature values ​​are used to reflect the statistical distribution of different pixel values ​​in the same video image; the vertical feature values ​​are used to reflect the statistical distribution of the same pixel value in different video images; The method further includes: extracting the image features of black screen faults, flashing faults, and smoke faults that have occurred in the industrial video of the substation, and obtaining the multiple fault image feature thresholds, wherein the multiple fault image feature thresholds include: a black screen fault feature threshold and a flashing fault feature threshold; calculating the brightness value corresponding to each pixel in the current frame video image, and determining that the black screen fault exists in the current frame video image if the brightness value corresponding to all pixels is less than the black screen fault feature threshold.

2. The method according to claim 1, characterized in that, Before acquiring industrial video footage from within the substation, the method further includes: Historical industrial video footage of the substation was acquired in advance. Identify historical video frames containing the substation fault within the historical industrial video footage; Feature extraction is performed on the historical video frames to obtain multiple fault image feature thresholds, which are then used as the basis for identifying whether the current video frame contains the substation fault.

3. The method according to claim 1, characterized in that, Identifying whether a substation fault exists in the current frame of video based on the comparison results includes: If the comparison result is that the digital feature value is greater than or equal to any of the fault image feature thresholds, then it is determined that the current frame video image contains the substation fault. If the comparison result shows that all the digital feature values ​​are less than the multiple fault image feature thresholds, then it is determined that the current frame video does not contain the substation fault.

4. The method according to claim 3, characterized in that, After determining that the substation fault exists in the current frame of video, the method further includes: Determine whether there is a fire hazard at the substation based on the substation fault. If the fire hazard is determined to exist in the substation, a fire alarm message is output, which is used to prompt staff to deal with the fire hazard in a timely manner. If it is determined that the substation does not pose the fire hazard, then fault handling decision information is determined based on the substation fault. Output fault prompt information and fault handling decision information, wherein the fault prompt information is used to prompt staff to handle the substation fault in a timely manner according to the fault handling decision information.

5. The method according to claim 3, characterized in that, After determining that the current frame video does not contain the substation fault, the method further includes: returning to the step of obtaining the current industrial video image within the substation; After determining that the current frame video shows a substation fault, the method further includes: after initializing multiple fault image feature thresholds, returning to the step of obtaining the current industrial video image within the substation.

6. A device for identifying substation faults, characterized in that, include: The acquisition module is used to acquire the current industrial video footage within the substation, wherein the current industrial video footage contains multiple video frames; The extraction module is used to extract features from the current frame of the multiple video frames to obtain digital feature values; The comparison module is used to compare the digital feature value with multiple predetermined fault image feature thresholds to obtain the comparison result; The identification module is used to identify whether there is a substation fault in the current frame video based on the comparison result, wherein the substation fault includes: black screen fault, flashing fault, and smoke fault; The extraction module is further configured to: calculate the image brightness of the current frame video image based on the component values ​​of the three primary colors when the digital feature values ​​include the horizontal and vertical feature values ​​of any fault phenomenon, thereby obtaining pixel brightness values; input the pixel brightness values ​​into a pre-established fault recognition model to obtain the horizontal and vertical feature values, wherein the fault recognition model is trained and learned based on historical frame video images of the substation where the substation fault exists in historical industrial video images within the substation; the horizontal feature values ​​are used to reflect the statistical distribution of different pixel values ​​in the same video image; the vertical feature values ​​are used to reflect the statistical distribution of the same pixel value in different video images; The device is further configured to extract the image features of black screen faults, flashing faults, and smoke faults that have occurred in the industrial video of the substation, and obtain the plurality of fault image feature thresholds, wherein the plurality of fault image feature thresholds include: black screen fault feature threshold and flashing fault feature threshold; calculate the brightness value corresponding to each pixel in the current frame video image, and determine that the black screen fault exists in the current frame video image if the brightness value corresponding to all pixels is less than the black screen fault feature threshold.

7. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores a plurality of instructions adapted for loading by a processor and executing the method for identifying substation faults as described in any one of claims 1 to 5.

8. An electronic device comprising a memory and a processor, characterized in that, The memory stores a computer program, and the processor is configured to run the computer program to perform the method for identifying substation faults as described in any one of claims 1 to 5.

9. A computer program product, comprising a computer program, characterized in that, When the computer program is executed by a processor, it implements the method for identifying substation faults according to any one of claims 1 to 5.

Images