Panoramic monitoring method and device for distribution network area, and storage medium

Abstract

The invention discloses a distribution network area panoramic monitoring method and device and a storage medium, relates to the field of electric power information, and solves the problem that the abnormity of a distribution network area cannot be accurately positioned, and the method comprises the steps: starting an area monitoring unit, and setting an area monitoring task and a transmission period corresponding to the area monitoring unit; the transformer area monitoring unit collects corresponding transformer area image data according to the transformer area monitoring task; the master station management platform analyzes the transformer area image data collected by the transformer area monitoring unit, judges that the distribution network transformer area is abnormal in initial detection and generates a plug flow preview request, or judges that the distribution network transformer area is normal in initial detection and does not perform operation; the master station management platform analyzes the plug-flow video of the distribution network area, judges the abnormal condition of the distribution network area, and generates an abnormal signal and sends the abnormal signal to the user terminal if the distribution network area is abnormal; and the user terminal receives the abnormal signal generated by the master station management platform, knows the abnormal condition of the distribution network platform and makes a corresponding response, and the method achieves the precise recognition and positioning of the abnormality in the distribution network station area.

Description

Technical Field

[0001] The present invention relates to the field of electric power information technology, and in particular to a method, a device and a storage medium for panoramic monitoring of a distribution network area. Background Art

[0002] The distribution network area refers to an area located between the substation and the user, which is used to convert the electric energy transmitted by the high-voltage transmission line into low-voltage electric energy suitable for users through transformers, and distribute the electric energy to surrounding users; the distribution network area usually includes transformers, switchgear, distribution lines and other equipment to ensure that the electric energy is stably and reliably delivered to the user's electrical equipment; the distribution network area is responsible for distributing electric energy according to the real-time load situation. It can monitor and adjust power distribution to ensure the balance between power supply and user demand and avoid power overload or shortage; therefore, the normal operation of the distribution network area is urgently needed.

[0003] However, at present, when monitoring the distribution network area, the common method is for monitoring personnel to observe through cameras and actively identify abnormalities. This method wastes human resources. When the monitoring personnel are distracted, the abnormalities in the distribution network area cannot be discovered in time, causing property losses. To this end, the present invention proposes a method, device and storage medium for panoramic monitoring of a distribution network area. Summary of the invention

[0004] The purpose of the present invention is to propose a method, device and storage medium for panoramic monitoring of a distribution network area to solve the problems raised in the above-mentioned background technology.

[0005] In order to achieve the above object, the present invention adopts the following technical solutions: A method for panoramic monitoring of a distribution network area, the method comprising: Step S1, start the area monitoring unit, set the area monitoring task and transmission cycle corresponding to the area monitoring unit; Step S2, the area monitoring unit collects corresponding area image data according to the area monitoring task, and sends the area image data to the main station management platform according to the transmission cycle of the area monitoring unit; Step S3, the master station management platform analyzes the area image data collected by the area monitoring unit, determines that the distribution network area is abnormal in the initial inspection and generates a streaming preview request, or determines that the distribution network area is normal in the initial inspection and does not perform any operation; Step S4, the master station management platform analyzes the streaming video of the distribution network area to determine the abnormality of the distribution network area. If the distribution network area is abnormal, an abnormal signal is generated and sent to the user terminal; Step S5: The user terminal receives the abnormal signal generated by the master station management platform, learns the abnormal situation of the distribution network platform and takes corresponding measures.

[0006] Furthermore, the substation monitoring task is the monitoring coordinates and monitoring time of multiple monitoring objects in the distribution network substation.

[0007] Furthermore, the step S2 includes the following sub-steps: Step S21, obtaining the area monitoring task, and obtaining the monitoring coordinates and monitoring time of the monitoring object; Step S22, determining that the monitoring coordinates corresponding to the monitoring object are located in the monitoring of the ultra-high-definition front camera, the monitoring of the ultra-high-definition rear camera, or the monitoring of the ultra-wide-angle camera in the station monitoring unit, and recording the corresponding camera as a monitoring camera; Step S23, adjusting the center of the monitoring camera to the monitoring coordinates, and recording the corresponding area image data at the monitoring time; Step S24, using the AI ​​model to identify whether the clarity of the area image data contains the monitored object, if not, a retake signal is generated to the main station management platform; the main station management platform generates a new monitoring task corresponding to the monitoring according to the retake signal and sends it to the area monitoring unit; Step S25: If the area image data contains the monitored object, all area image data in the current transmission cycle are sent to the main station management platform at the time corresponding to the next transmission cycle.

[0008] Furthermore, the step S3 includes the following sub-steps: Step S31, acquiring the area image data corresponding to the distribution network area, and obtaining real-time images of multiple monitoring areas in the distribution network area; Step S32, identifying the intrusion of personnel in the distribution network area. If there is intrusion of personnel in the distribution network area, it is determined that the initial inspection of personnel in the distribution network area is abnormal; Step S33, if there is no human intrusion in the distribution network area, proceed to the subsequent steps; Step S34, identifying the situation of foreign objects hanging in the distribution network area. If there are foreign objects hanging in the distribution network area, it is determined that the distribution network area is abnormal in the initial inspection; Step S35, if there is no foreign object hanging in the distribution network area, it is determined that the initial inspection of the distribution network area is normal, and no operation is performed; Step S36: If the distribution network area has an initial inspection suspension abnormality or an initial inspection personnel abnormality, a streaming preview request is generated and sent to the area monitoring unit; the area monitoring unit receives the streaming preview request and establishes a live streaming connection with the main station management platform.

[0009] Furthermore, the identification process of human intrusion is specifically as follows: Step S321, obtaining a real-time image outside the distribution network area edge, wherein the distribution network area edge specifically refers to the location of the distribution network base station edge; Step S322, obtaining R value components RZi, G value components GZi and B value components BZi of RGB values ​​corresponding to a plurality of pixel points in the real-time image outside the area, where i is the number of the pixel point, i=1, 2, ..., z, and z is a positive integer; Step S323: For any pixel point, the pixel value XSi of the corresponding pixel point is calculated by the formula, and the specific formula is: XSi=A1×RZi+A2×GZi+A3×BZi; where A1, A2 and A3 are fixed proportional coefficients, A1, A2 and A3 are all greater than zero and A1+A2+A3=1; Step S324, comparing the pixel value of the pixel point with the first threshold value, if the pixel value of the pixel point is greater than or equal to the first threshold value, the corresponding pixel point is recorded as black, if the pixel value of the pixel point is less than the first threshold value, the corresponding pixel point is recorded as white; Step S325, connect all black pixels to obtain the real-time image contour; match the real-time image contour with the vehicle contour set and the human contour set respectively; if the match is successful, it is determined that there is human intrusion in the distribution network area; if the match fails, it is determined that there is no human intrusion in the distribution network area.

[0010] Furthermore, the identification process of the suspension condition is specifically as follows: Step S341, obtaining the area image data corresponding to the cable in the distribution network area, and obtaining the trend line of the cable; Step S342, enlarging the image corresponding to the cable according to the predetermined cable patrol direction to realize cable patrol monitoring; Step S343, calculating the cable width between the upper surface of the cable and the lower surface of the cable corresponding to the plurality of points, and reading the mode of the cable width as the second threshold; Step S344, comparing the cable width with the second threshold, if the cable width at any point is greater than or equal to T times the second threshold, it is determined that there is a foreign object hanging in the distribution network area; Step S345: If the cable widths at all points are less than T times the second threshold, it is determined that there is no foreign object hanging in the distribution network area.

[0011] Furthermore, the step S4 includes the following sub-steps: Step S41, obtaining the streaming video of the distribution network area; Step S42, identifying a person or vehicle in the image streaming video by the method described in step S32, and generating an abnormal signal if the identification is successful; if the identification fails, adjusting the substation monitoring unit to the audio-visual fusion mode to collect audio data of the distribution network substation in real time; Step S43, converting the audio data into a high-frequency sound pressure cloud map through the unique voiceprint model library of the main station management platform; integrating the high-frequency sound pressure cloud map with the streaming video; and locating the location of the sound source by observing the color depth of the high-frequency sound pressure cloud map; Step S44, extracting audio data at the location of the sound source and recording it as core audio data, and then calculating similarity between the core audio data and the multiple groups of audio clips; Step S45, comparing the first audio similarity and the second audio similarity of the plurality of audio segments with the similarity interval respectively, recording the audio segments within the similarity interval as similar segments, and not performing any operation on the audio segments outside the similarity interval; wherein the similarity interval is specifically [0.9, 1.1]; Step S46, obtaining the distribution network health rate of the corresponding core audio data by dividing the similar segments by the total number of audio segments. If the distribution network health rate is less than the preset distribution network health rate, the distribution network area is considered abnormal; if the distribution network health rate is greater than or equal to the preset distribution network health rate, the noise in the distribution network area is considered normal, and the subsequent steps are performed; Step S47, changing the area monitoring unit to the infrared temperature measurement imaging mode, and sequentially adjusting the positions of the transformer, the hardware, and the wires for a second monitoring time; Step S48, reading the temperature of different areas in the streaming video at any time, taking the maximum temperature of different areas as the area video temperature at the corresponding time, and comparing the area video temperature with the temperature threshold; Step S49, if the corresponding area video temperature at any time is greater than or equal to the temperature threshold, it is determined that there is a high temperature abnormality in the distribution network area and an abnormal signal is generated; if the area video temperature at all times is less than the temperature threshold, it is determined that the distribution network area is normal.

[0012] Furthermore, the calculation process of the similarity rate corresponding to the audio clips is specifically as follows: Step S441, obtaining core audio data, performing enhancement operation on the core audio data to obtain enhanced audio data. Specifically, the enhancement operation is: ZQ(y)=1-μ / y; where μ is a constant between (0.95, 0.995); y is the core audio data, and ZQ(y) is the enhanced audio data; Step S442, dividing the enhanced audio data into a plurality of enhanced audio segments, and numbering the enhanced audio segments as n, where n=1, 2, ..., f, and f is an upper limit value of n; Step S443, select any enhanced audio segment ZQ(y)n, obtain two or one adjacent enhanced audio segments as adjacent audio segments, cut the adjacent audio segment in half, and then combine it with the enhanced audio segment to obtain a combined audio segment ZHn of the enhanced audio segment; Step S444, processing the combined audio segment through a first window function to obtain a first processed audio segment corresponding to the combined audio segment ZHn, and processing the combined audio segment through a second window function to obtain a second processed audio segment; The window function JG(y) is specifically: JG(y)=a-(1-a)×cos(2π×n / f); where a is a constant, a=0.53836 for the first processing window function, and a=0.5 for the second window function; Step S445, and so on, executing the window function on all the combined audio segments to obtain multiple groups of first processed audio segments and multiple groups of second processed audio segments; Step S446, reading a first audio peak value DYFn, a first audio valley value DYGn, and a first audio frequency DYPn corresponding to any first processed audio segment; The first audio similarity YXSn corresponding to the first processed audio segment is calculated by the formula, and the specific formula is: ; Wherein, B1, B2 and B3 are fixed value proportional coefficients; BZFn is the standard audio peak value corresponding to the healthy operation state of the distribution network area; BZGn is the standard audio valley value corresponding to the healthy operation state of the distribution network area; BZPn is the standard audio frequency corresponding to the healthy operation state of the distribution network area; Step S447: Similarly, read the second audio peak value DEFn, the second audio valley value DEGn and the second audio frequency DEPn corresponding to any second processed audio segment; and calculate the second audio similarity EXSn corresponding to the second processed audio segment; .

[0013] Furthermore, a computer device is provided, the computer device comprising: A memory storing a computer program; A processor is communicatively connected to the memory, and when the computer program is executed by the processor, the above method is implemented.

[0014] Furthermore, a computer-readable storage medium stores a computer program, which implements the above method when executed by a processor.

[0015] In summary, due to the adoption of the above technical solution, the beneficial effects of the present invention are: 1. The present invention first starts the area monitoring unit, sets the area monitoring task and transmission cycle corresponding to the area monitoring unit; then uses the area monitoring unit to collect corresponding area image data according to the area monitoring task, and sends the area image data to the main station management platform according to the transmission cycle of the area monitoring unit; then the main station management platform analyzes the area image data collected by the area monitoring unit, determines that the distribution network area is abnormal in the initial inspection, generates a push stream preview request, or determines that the distribution network area is normal in the initial inspection and does not perform any operation; 2. The present invention also analyzes the streaming video of the distribution network area through the main station management platform to determine the abnormal situation of the distribution network area. If the distribution network area is abnormal, an abnormal signal is generated and sent to the user terminal. In summary, the user terminal is finally used to receive the abnormal signal generated by the main station management platform, the abnormal situation of the distribution network platform is known and corresponding measures are taken. The present invention realizes accurate identification of abnormal phenomena in the distribution network area. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] In order to facilitate understanding by those skilled in the art, the present invention is further described below with reference to the accompanying drawings.

[0017] Figure 1 is a schematic diagram of the method of the present invention; Figure 2 is a flowchart of the method of the present invention; Figure 3 It is a schematic diagram of the distribution network area in the present invention; Figure 4 is a schematic diagram of the cable in the present invention; Figure 5 is a schematic diagram of combining audio data in the present invention; Figure 6 It is a schematic diagram of the structure of the computer device in the present invention. DETAILED DESCRIPTION

[0018] The technical solution of the present invention will be clearly and completely described below in conjunction with the embodiments. Obviously, the described embodiments are only part of the embodiments of the present invention, rather than all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0019] Example 1: Please refer to Figure 1-Figure 5 As shown, the technical solution provided by the present invention is: a method for panoramic monitoring of distribution network substations, the method involving a substation monitoring unit, a master station management platform and a user terminal; wherein the substation monitoring unit is used to monitor the distribution network substation in real time; the master station management platform is used to analyze the real-time situation of the distribution network; the user terminal receives the real-time status of the distribution network substation; The station area monitoring unit is composed of an ultra-high-definition front camera, an ultra-high-definition rear camera, an ultra-wide-angle camera, a tilt sensor and a vibration sensor; In this embodiment, the distribution network area panoramic monitoring method is specifically as follows: Step S1, start the substation monitoring unit, set the substation monitoring task and transmission cycle corresponding to the substation monitoring unit; the substation monitoring task is specifically: the monitoring coordinates and monitoring time of multiple monitoring objects in the distribution network substation; among which the monitoring objects are specifically: transmission lines, transformers, fuses and low-voltage distribution terminals.

[0020] Step S2, the area monitoring unit collects corresponding area image data according to the area monitoring task, and sends the area image data to the main station management platform according to the transmission cycle of the area monitoring unit; In this embodiment, step S2 includes the following sub-steps: Step S21, obtaining the area monitoring task, and obtaining the monitoring coordinates and monitoring time of the monitoring object; Step S22, determining that the monitoring coordinates corresponding to the monitoring object are located in the monitoring of the ultra-high-definition front camera, the monitoring of the ultra-high-definition rear camera, or the monitoring of the ultra-wide-angle camera in the station monitoring unit, and recording the corresponding camera as a monitoring camera; It should be noted that if the monitored object is under the surveillance of two cameras at the same time, both cameras will be recorded as monitoring cameras; Step S23, adjusting the center of the monitoring camera to the monitoring coordinates, and recording the corresponding area image data at the monitoring time; Step S24, using the AI ​​model to identify whether the clarity of the area image data contains the monitored object, if not, a retake signal is generated to the main station management platform; the main station management platform generates a new monitoring task corresponding to the monitoring according to the retake signal and sends it to the area monitoring unit; Step S25: If the area image data contains the monitored object, all area image data in the current transmission cycle are sent to the main station management platform at the time corresponding to the next transmission cycle.

[0021] Step S3, the master station management platform analyzes the area image data collected by the area monitoring unit, determines that the distribution network area is abnormal in the initial inspection and generates a streaming preview request, or determines that the distribution network area is normal in the initial inspection and does not perform any operation; In this embodiment, step S3 includes the following sub-steps: Step S31, acquiring the area image data corresponding to the distribution network area, and obtaining real-time images of multiple monitoring areas in the distribution network area; Step S32, identifying the intrusion of personnel in the distribution network area. If there is intrusion of personnel in the distribution network area, it is determined that the initial inspection of personnel in the distribution network area is abnormal; Specifically, the identification process of human intrusion is as follows: Step S321, as Figure 3 As shown, a real-time image outside the distribution network area is obtained, wherein the distribution network area edge specifically refers to the location of the edge of the distribution network base station; Step S322, obtaining R value components RZi, G value components GZi and B value components BZi of RGB values ​​corresponding to a plurality of pixel points in the real-time image outside the area, where i is the number of the pixel point, i=1, 2, ..., z, and z is a positive integer; Step S323: For any pixel point, the pixel value XSi of the corresponding pixel point is calculated by the formula, and the specific formula is: XSi=A1×RZi+A2×GZi+A3×BZi; where A1, A2 and A3 are fixed proportional coefficients, A1, A2 and A3 are all greater than zero and A1+A2+A3=1; Step S324, comparing the pixel value of the pixel point with the first threshold value, if the pixel value of the pixel point is greater than or equal to the first threshold value, the corresponding pixel point is recorded as black, if the pixel value of the pixel point is less than the first threshold value, the corresponding pixel point is recorded as white; Step S325, connect all black pixels to obtain the real-time image contour; match the real-time image contour with the vehicle contour set and the human contour set respectively; if the match is successful, it is determined that there is a human intrusion in the distribution network area; if the match fails, it is determined that there is no human intrusion in the distribution network area; Step S33, if there is no human intrusion in the distribution network area, proceed to the subsequent steps; Step S34, identifying the situation of foreign objects hanging in the distribution network area. If there are foreign objects hanging in the distribution network area, it is determined that the distribution network area is abnormal in the initial inspection; Specifically, the identification process of the suspension situation is as follows: Step S341, obtaining the area image data corresponding to the cable in the distribution network area, and obtaining the trend line of the cable; Step S342, enlarging the image corresponding to the cable according to the predetermined cable patrol direction to realize cable patrol monitoring; Step S343, as Figure 4 As shown, the cable width between the upper surface of the cable and the lower surface of the cable corresponding to the multiple points is calculated, and the mode of the cable width is read as the second threshold; Step S344, comparing the cable width with the second threshold, if the cable width at any point is greater than or equal to T times the second threshold, it is determined that there is a foreign object hanging in the distribution network area; Step S345, if the cable widths at all points are less than T times the second threshold, it is determined that there is no foreign object hanging in the distribution network area; Step S35, if there is no foreign object hanging in the distribution network area, it is determined that the initial inspection of the distribution network area is normal, and no operation is performed; Step S36: If the distribution network area has an initial inspection suspension abnormality or an initial inspection personnel abnormality, a streaming preview request is generated and sent to the area monitoring unit; the area monitoring unit receives the streaming preview request and establishes a live streaming connection with the main station management platform.

[0022] Step S4, the master station management platform analyzes the streaming video of the distribution network area to determine the abnormality of the distribution network area. If the distribution network area is abnormal, an abnormal signal is generated and sent to the user terminal; In this embodiment, step S4 includes the following sub-steps: Step S41, obtaining the streaming video of the distribution network area; Step S42, identifying a person or vehicle in the image streaming video by the method described in step S32, and generating an abnormal signal if the identification is successful; if the identification fails, adjusting the substation monitoring unit to the audio-visual fusion mode to collect audio data of the distribution network substation in real time; Step S43, converting the audio data into a high-frequency sound pressure cloud map through the unique voiceprint model library of the main station management platform; integrating the high-frequency sound pressure cloud map with the streaming video; and locating the location of the sound source by observing the color depth of the high-frequency sound pressure cloud map; Step S44, extracting audio data at the location of the sound source and recording it as core audio data, and then calculating similarity between the core audio data and the multiple groups of audio clips; The calculation process of the similarity rate of the audio clips is as follows: Step S441, obtaining core audio data, performing enhancement operation on the core audio data to obtain enhanced audio data. Specifically, the enhancement operation is: ZQ(y)=1-μ / y; where μ is a constant between (0.95, 0.995), preferably 0.97; y is the core audio data, and ZQ(y) is the enhanced audio data; Step S442, dividing the enhanced audio data into a plurality of enhanced audio segments, and numbering the enhanced audio segments as n, where n=1, 2, ..., f, and f is an upper limit of n; preferably, the length of each audio segment during the division is 20 milliseconds to 30 milliseconds; Step S443, as Figure 5 As shown, any enhanced audio segment ZQ(y)n is selected, two or one enhanced audio segments adjacent to it are obtained and recorded as adjacent audio segments, the adjacent audio segments are cut in half, and then combined with the enhanced audio segment to obtain a combined audio segment ZHn of the enhanced audio segments; Step S444, processing the combined audio segment through a first window function to obtain a first processed audio segment corresponding to the combined audio segment ZHn, and processing the combined audio segment through a second window function to obtain a second processed audio segment; The window function JG(y) is specifically: JG(y)=a-(1-a)×cos(2π×n / f); where a is a constant, a=0.53836 for the first processing window function, and a=0.5 for the second window function; Step S445, and so on, executing the window function on all the combined audio segments to obtain multiple groups of first processed audio segments and multiple groups of second processed audio segments; Step S446, reading a first audio peak value DYFn, a first audio valley value DYGn, and a first audio frequency DYPn corresponding to any first processed audio segment; The first audio similarity YXSn corresponding to the first processed audio segment is calculated by the formula, and the specific formula is: ; Wherein, B1, B2 and B3 are fixed value proportional coefficients; BZFn is the standard audio peak value corresponding to the healthy operation state of the distribution network area; BZGn is the standard audio valley value corresponding to the healthy operation state of the distribution network area; BZPn is the standard audio frequency corresponding to the healthy operation state of the distribution network area; Step S447: Similarly, read the second audio peak value DEFn, the second audio valley value DEGn and the second audio frequency DEPn corresponding to any second processed audio segment; and calculate the second audio similarity EXSn corresponding to the second processed audio segment; ; Step S45, comparing the first audio similarity and the second audio similarity of the plurality of audio segments with the similarity interval respectively, recording the audio segments within the similarity interval as similar segments, and not performing any operation on the audio segments outside the similarity interval; wherein the similarity interval is specifically [0.9, 1.1]; Step S46, obtaining the distribution network health rate of the corresponding core audio data by dividing the similar segments by the total number of audio segments. If the distribution network health rate is less than the preset distribution network health rate, the distribution network area is considered abnormal; if the distribution network health rate is greater than or equal to the preset distribution network health rate, the noise in the distribution network area is considered normal, and the subsequent steps are performed; Step S47, changing the area monitoring unit to the infrared temperature measurement imaging mode, and sequentially adjusting the positions of the transformer, the hardware, and the wires for a second monitoring time; The infrared temperature measurement imaging mode can acquire infrared imaging videos or images; transformers (current problems cause heating of capacitor bushings, connecting wires, etc.), hardware (grounding wires, insulators, and connecting hardware, etc.) and conductors are all parts prone to heating; Step S48, reading the temperature of different areas in the streaming video at any time, taking the maximum temperature of different areas as the area video temperature at the corresponding time, and comparing the area video temperature with the temperature threshold; Step S49, if the corresponding area video temperature at any time is greater than or equal to the temperature threshold, it is determined that there is a high temperature abnormality in the distribution network area and an abnormal signal is generated; if the area video temperature at all times is less than the temperature threshold, it is determined that the distribution network area is normal.

[0023] Step S5, the user terminal receives the abnormal signal generated by the master station management platform, learns the abnormal situation of the distribution network platform and takes corresponding measures; Specifically, distribution network maintenance workers or management personnel are dispatched to the distribution network substation to conduct on-site inspection or maintenance.

[0024] In this application, if corresponding calculation formulas appear, the above calculation formulas are all dimensionless and take their numerical calculations. The weight coefficients, proportional coefficients and other coefficients in the formulas are set to a result value obtained by quantifying each parameter. The size of the weight coefficient and the proportional coefficient can be determined as long as it does not affect the proportional relationship between the parameter and the result value.

[0025] Embodiment 2: Figure 6 The structural diagram of a computer device is illustrated, and the computer device may include: a processor, a communication interface, a memory, and a communication bus, wherein the processor, the communication interface, and the memory communicate with each other through the communication bus. The processor may call the logic instructions in the memory to execute a distribution network area panoramic monitoring method, and the method includes: starting the area monitoring unit, setting the area monitoring task and transmission cycle corresponding to the area monitoring unit; the area monitoring unit collects the corresponding area image data according to the area monitoring task, and sends the area image data to the main station management platform according to the transmission cycle of the area monitoring unit; the main station management platform analyzes the area image data collected by the area monitoring unit, determines that the distribution network area is abnormal in the initial inspection and generates a push stream preview request, or determines that the distribution network area is normal in the initial inspection and does not operate; the main station management platform analyzes the push stream video of the distribution network area, determines the abnormal situation of the distribution network area, and if the distribution network area is abnormal, generates an abnormal signal and sends it to the user terminal; the user terminal receives the abnormal signal generated by the main station management platform, learns the abnormal situation of the distribution network platform and makes corresponding responses.

[0026] In addition, the logic instructions in the above-mentioned memory can be implemented in the form of software functional units and can be stored in a computer-readable storage medium when sold or used as an independent product. Based on this understanding, the technical solution of the present application can be essentially or partly embodied in the form of a software product that contributes to the prior art. The computer software product is stored in a storage medium, including several instructions to enable a computer device (which can be a personal computer, server, or network device, etc.) to execute all or part of the steps of the method described in each embodiment of the present application. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), disk or optical disk, etc. Various media that can store program codes.

[0027] On the other hand, the present application also provides a computer program product, which includes a computer program stored on a computer-readable storage medium, and the computer program includes program instructions. When the program instructions are executed by a computer, the computer can execute a distribution network area panoramic monitoring method provided by the above methods, the method including: starting the area monitoring unit, setting the area monitoring task and transmission cycle corresponding to the area monitoring unit; the area monitoring unit collects corresponding area image data according to the area monitoring task, and sends the area image data to the master station management platform according to the transmission cycle of the area monitoring unit; the master station management platform analyzes the area image data collected by the area monitoring unit, determines that the distribution network area is initially inspected abnormally and generates a push stream preview request, or determines that the distribution network area is initially inspected normally and does not perform any operation; the master station management platform analyzes the push stream video of the distribution network area, determines the abnormal situation of the distribution network area, and if the distribution network area is abnormal, generates an abnormal signal and sends it to the user terminal; the user terminal receives the abnormal signal generated by the master station management platform, learns the abnormal situation of the distribution network platform and makes corresponding responses.

[0028] On the other hand, the present application also provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, is implemented to execute a distribution network substation panoramic monitoring method provided above, the method comprising: starting the substation monitoring unit, setting the substation monitoring task and transmission cycle corresponding to the substation monitoring unit; the substation monitoring unit collects corresponding substation image data according to the substation monitoring task, and sends the substation image data to the master station management platform according to the transmission cycle of the substation monitoring unit; the master station management platform analyzes the substation image data collected by the substation monitoring unit, determines that the distribution network substation is initially inspected to be abnormal and generates a streaming preview request, or determines that the distribution network substation is initially inspected to be normal and does not perform any operation; the master station management platform analyzes the streaming video of the distribution network substation, determines the abnormal situation of the distribution network substation, and if the distribution network substation is abnormal, generates an abnormal signal and sends it to the user terminal; the user terminal receives the abnormal signal generated by the master station management platform, learns of the abnormal situation of the distribution network platform and makes corresponding responses.

[0029] The device embodiments described above are merely illustrative, wherein the units described as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, they may be located in one place, or they may be distributed on multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the scheme of this embodiment. Those of ordinary skill in the art may understand and implement it without creative work.

[0030] Through the description of the above implementation methods, those skilled in the art can clearly understand that each implementation method can be implemented by means of software plus a necessary general hardware platform, and of course, can also be implemented by hardware. Based on this understanding, the above technical solution is essentially or the part that contributes to the prior art can be embodied in the form of a software product, and the computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, a disk, an optical disk, etc., including a number of instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to execute the methods described in each embodiment or some parts of the embodiments.

[0031] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present application, rather than to limit it. Although the present application has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present application.

Claims

1. A method for panoramic monitoring of distribution network areas, characterized in that: Methods include: Step S1, start the area monitoring unit, set the area monitoring task and transmission cycle corresponding to the area monitoring unit; Step S2, the area monitoring unit collects corresponding area image data according to the area monitoring task, and sends the area image data to the main station management platform according to the transmission cycle of the area monitoring unit; Step S3, the master station management platform analyzes the area image data collected by the area monitoring unit, determines that the distribution network area is abnormal in the initial inspection and generates a streaming preview request, or determines that the distribution network area is normal in the initial inspection and does not perform any operation; Step S4, the master station management platform analyzes the streaming video of the distribution network area to determine the abnormality of the distribution network area. If the distribution network area is abnormal, an abnormal signal is generated and sent to the user terminal; Step S5: The user terminal receives the abnormal signal generated by the master station management platform, learns the abnormal situation of the distribution network platform and takes corresponding measures.

2. A method for panoramic monitoring of distribution network areas according to claim 1, characterized in that: The substation monitoring task is to monitor the coordinates and time of multiple monitoring objects in the distribution network substation.

3. A method for panoramic monitoring of distribution network areas according to claim 2, characterized in that: The step S2 includes the following sub-steps: Step S21, obtaining the area monitoring task, and obtaining the monitoring coordinates and monitoring time of the monitoring object; Step S22, determining that the monitoring coordinates corresponding to the monitoring object are located in the monitoring of the ultra-high-definition front camera, the monitoring of the ultra-high-definition rear camera, or the monitoring of the ultra-wide-angle camera in the station monitoring unit, and recording the corresponding camera as a monitoring camera; Step S23, adjusting the center of the monitoring camera to the monitoring coordinates, and recording the corresponding area image data at the monitoring time; Step S24, using the AI ​​model to identify whether the clarity of the area image data contains the monitored object, if not, a retake signal is generated to the main station management platform; the main station management platform generates a new monitoring task corresponding to the monitoring according to the retake signal and sends it to the area monitoring unit; Step S25: If the area image data contains the monitored object, all area image data in the current transmission cycle are sent to the main station management platform at the time corresponding to the next transmission cycle.

4. A method for panoramic monitoring of distribution network areas according to claim 3, characterized in that: The step S3 includes the following sub-steps: Step S31, acquiring the area image data corresponding to the distribution network area, and obtaining real-time images of multiple monitoring areas in the distribution network area; Step S32, identifying the intrusion of personnel in the distribution network area. If there is intrusion of personnel in the distribution network area, it is determined that the initial inspection of personnel in the distribution network area is abnormal; Step S33, if there is no human intrusion in the distribution network area, proceed to the subsequent steps; Step S34, identifying the hanging foreign objects in the distribution network area. If there are hanging foreign objects in the distribution network area, it is determined that the initial inspection of the distribution network area is abnormal. Step S35, if there is no foreign object hanging in the distribution network area, it is determined that the initial inspection of the distribution network area is normal, and no operation is performed; Step S36: If the distribution network area has an initial inspection suspension abnormality or an initial inspection personnel abnormality, a streaming preview request is generated and sent to the area monitoring unit; the area monitoring unit receives the streaming preview request and establishes a live streaming connection with the main station management platform.

5. A method for panoramic monitoring of distribution network areas according to claim 4, characterized in that: The identification process of human intrusion is as follows: Step S321, obtaining a real-time image outside the distribution network area edge, wherein the distribution network area edge specifically refers to the location of the distribution network base station edge; Step S322, obtaining R value components RZi, G value components GZi and B value components BZi of RGB values ​​corresponding to a plurality of pixel points in the real-time image outside the area, where i is the number of the pixel point, i=1, 2, ..., z, and z is a positive integer; Step S323: For any pixel point, the pixel value XSi of the corresponding pixel point is calculated by the formula, and the specific formula is: XSi=A1×RZi+A2×GZi+A3×BZi; where A1, A2 and A3 are fixed proportional coefficients, A1, A2 and A3 are all greater than zero and A1+A2+A3=1; Step S324, comparing the pixel value of the pixel point with the first threshold value, if the pixel value of the pixel point is greater than or equal to the first threshold value, the corresponding pixel point is recorded as black, if the pixel value of the pixel point is less than the first threshold value, the corresponding pixel point is recorded as white; Step S325, connect all black pixels to obtain the real-time image contour; match the real-time image contour with the vehicle contour set and the human contour set respectively; if the match is successful, it is determined that there is human intrusion in the distribution network area; if the match fails, it is determined that there is no human intrusion in the distribution network area.

6. A method for panoramic monitoring of distribution network areas according to claim 4, characterized in that: The identification process of the suspension situation is as follows: Step S341, obtaining the area image data corresponding to the cable in the distribution network area, and obtaining the trend line of the cable; Step S342, enlarging the image corresponding to the cable according to the predetermined cable patrol direction to realize cable patrol monitoring; Step S343, calculating the cable width between the upper surface of the cable and the lower surface of the cable corresponding to the plurality of points, and reading the mode of the cable width as the second threshold; Step S344, comparing the cable width with the second threshold, if the cable width at any point is greater than or equal to T times the second threshold, it is determined that there is a foreign object hanging in the distribution network area; Step S345: If the cable widths at all points are less than T times the second threshold, it is determined that there is no foreign object hanging in the distribution network area.

7. A method for panoramic monitoring of distribution network areas according to claim 4, characterized in that: The step S4 includes the following sub-steps: Step S41, obtaining the streaming video of the distribution network area; Step S42, identifying a person or vehicle in the image streaming video by the method in step S32, and generating an abnormal signal if the identification is successful; if the identification fails, adjusting the substation monitoring unit to the audio-visual fusion mode to collect audio data of the distribution network substation in real time; Step S43, converting the audio data into a high-frequency sound pressure cloud map through the unique voiceprint model library of the main station management platform; integrating the high-frequency sound pressure cloud map with the streaming video; and locating the location of the sound source by observing the color depth of the high-frequency sound pressure cloud map; Step S44, extracting audio data at the location of the sound source and recording it as core audio data, and then calculating similarity between the core audio data and the multiple groups of audio clips; Step S45, comparing the first audio similarity and the second audio similarity of the plurality of audio segments with the similarity interval respectively, recording the audio segments within the similarity interval as similar segments, and not performing any operation on the audio segments outside the similarity interval; wherein the similarity interval is specifically [0.9, 1.1]; Step S46, obtaining the distribution network health rate of the corresponding core audio data by dividing the similar segments by the total number of audio segments. If the distribution network health rate is less than the preset distribution network health rate, the distribution network area is considered abnormal; if the distribution network health rate is greater than or equal to the preset distribution network health rate, the noise in the distribution network area is considered normal, and the subsequent steps are performed; Step S47, changing the area monitoring unit to the infrared temperature measurement imaging mode, and sequentially adjusting the positions of the transformer, the hardware, and the wires for a second monitoring time; Step S48, reading the temperature of different areas in the streaming video at any time, taking the maximum temperature of different areas as the area video temperature at the corresponding time, and comparing the area video temperature with the temperature threshold; Step S49, if the corresponding area video temperature at any time is greater than or equal to the temperature threshold, it is determined that there is a high temperature abnormality in the distribution network area and an abnormal signal is generated; if the area video temperature at all times is less than the temperature threshold, it is determined that the distribution network area is normal.

8. A method for panoramic monitoring of distribution network areas according to claim 7, characterized in that: The calculation process of the similarity rate corresponding to the audio clip is specifically as follows: Step S441, obtaining core audio data, performing enhancement operation on the core audio data to obtain enhanced audio data, the enhancement operation is: ZQ(y)=1-μ / y; where μ is a constant between (0.95, 0.995); y is the core audio data, and ZQ(y) is the enhanced audio data; Step S442, dividing the enhanced audio data into a plurality of enhanced audio segments, and numbering the enhanced audio segments as n, where n=1, 2, ..., f, and f is an upper limit value of n; Step S443, select any enhanced audio segment ZQ(y)n, obtain two or one adjacent enhanced audio segments as adjacent audio segments, cut the adjacent audio segment in half, and then combine it with the enhanced audio segment to obtain a combined audio segment ZHn of the enhanced audio segment; Step S444, processing the combined audio segment through a first window function to obtain a first processed audio segment corresponding to the combined audio segment ZHn, and processing the combined audio segment through a second window function to obtain a second processed audio segment; The window function JG(y) is specifically: JG(y)=a-(1-a)×cos(2π×n / f); where a is a constant, a=0.53836 for the first processing window function, and a=0.5 for the second window function; Step S445, and so on, executing the window function on all the combined audio segments to obtain multiple groups of first processed audio segments and multiple groups of second processed audio segments; Step S446, reading a first audio peak value DYFn, a first audio valley value DYGn, and a first audio frequency DYPn corresponding to any first processed audio segment; The first audio similarity YXSn corresponding to the first processed audio segment is calculated by the formula, and the specific formula is: ; Wherein, B1, B2 and B3 are fixed value proportional coefficients; BZFn is the standard audio peak value corresponding to the healthy operation state of the distribution network area; BZGn is the standard audio valley value corresponding to the healthy operation state of the distribution network area; BZPn is the standard audio frequency corresponding to the healthy operation state of the distribution network area; Step S447: Similarly, read the second audio peak value DEFn, the second audio valley value DEGn and the second audio frequency DEPn corresponding to any second processed audio segment; and calculate the second audio similarity EXSn corresponding to the second processed audio segment; 。 9. A computer device, characterized in that: The computer device comprises: A memory storing a computer program; A processor is communicatively connected to the memory, and when the computer program is executed by the processor, the method described in any one of claims 1 to 8 is implemented.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the program is executed by a processor, the method according to any one of claims 1 to 8 is implemented.

Images