Transformer substation video operation intelligent analysis method and system based on artificial intelligence recognition

Abstract

The invention discloses a transformer substation video operation intelligent analysis method and system based on artificial intelligence identification, and belongs to the technical field of data processing, and the method comprises the following steps: obtaining surrounding environment influence parameters, and carrying out the analysis to obtain a surrounding environment influence driving value; acquiring a working picture of the transformer substation circuit breaker, dividing the working picture into a plurality of areas, and analyzing to obtain an affected value of each area; dividing each confidence level region based on the affected value of each region, matching to obtain an infrared reflection artifact correction scheme of each region, performing infrared reflection artifact correction to obtain an artifact correction temperature of each region, and processing to obtain a video operation detection reference temperature; the operation state parameters of the circuit breaker of the transformer substation are obtained, and the video operation detection reference temperature is fused for discrimination, thereby obtaining the video operation detection temperature through analysis, and uploading the video operation detection temperature to the background data management center for display. The problem that in the prior art, due to the fact that infrared reflection artifact analysis is not carried out, transformer substation circuit breaker temperature identification is not accurate is solved.

Description

Technical Field

[0001] The present invention relates to the field of data processing technology, and in particular to an intelligent analysis method and system for substation video operations based on artificial intelligence recognition. Background Art

[0002] With the development of electrical technology, intelligent robots based on artificial intelligence are widely used in substation video operation analysis systems. The existing substation video operation analysis system collects pictures of the substation and then performs performance analysis of the substation equipment.

[0003] For example, the patent application with publication number: CN113033835A discloses an intelligent inspection method, system and storage medium based on a substation, including: receiving monitoring instructions, and calling corresponding acquisition equipment according to the monitoring instructions; obtaining multiple inspection pictures of substation equipment collected by the acquisition equipment according to preset inspection rules, and analyzing the performance indicators of the substation equipment according to the multiple inspection pictures. The present invention automatically and remotely collects inspection pictures of substation equipment, and then intelligently analyzes the inspection pictures to obtain the performance indicators of the substation equipment. There is no need for manual inspection, which reduces manpower loss and improves the inspection efficiency and accuracy of substations.

[0004] For example, the invention patent with announcement number: CN118365181B announces an intelligent analysis management system and method for substation equipment based on edge computing, including: collecting images of target devices at various angles to form a training set, training through a target recognition algorithm to obtain a recognition model of the target device, deploying the recognition model to several device posture detectors, connecting several device posture detectors in sequence, any device posture detector collects video information of the target device, and judges the direction of change of the posture of the target device through the image change of the target device in the image frame in the video information. The device posture detector judges the direction of change of the posture of the target device based on its own judgment, and sends a positioning data packet to the next device posture detector. Each device posture detector respectively collects the change direction information in the received positioning data packet to determine the device posture detector to which the changed posture of the target device points.

[0005] However, in the process of implementing the technical solution of the invention in the embodiments of the present application, the present application found that the above technology has at least the following technical problems: In the prior art, during video operation, thermodynamic analysis is usually directly performed on the pictures in the video operation to obtain the temperature of the disconnector. However, the metal shell and the contact surface of the circuit breaker in a gas-insulated substation have a high reflectivity. Therefore, the surface of the circuit breaker in a gas-insulated substation is prone to reflecting ambient light or thermal radiation inside the equipment in infrared imaging, thus forming artifacts. The prior art ignores the influence of infrared reflection artifacts on temperature detection during the temperature analysis of the substation circuit breaker, resulting in inaccurate temperature analysis of the substation circuit breaker in video operation detection. If the temperature analysis of the substation circuit breaker is inaccurate, it will cause the phenomenon of mis-tripping of the circuit breaker. Therefore, there is a problem of inaccurate temperature identification of the substation circuit breaker due to the lack of infrared reflection artifact analysis. Summary of the Invention

[0006] By providing an intelligent analysis method and system for substation video operation with artificial intelligence recognition, the embodiments of the present application solve the problem of inaccurate temperature identification of the substation circuit breaker due to the lack of infrared reflection artifact analysis in the prior art, achieve precise detection of the temperature of the substation circuit breaker, and avoid mis-tripping of the circuit breaker caused by inaccurate temperature detection of the substation circuit breaker.

[0007] The embodiments of the present application provide an intelligent analysis method for substation video operation with artificial intelligence recognition, including the following steps: after receiving a monitoring operation signal, the intelligent operation robot obtains the surrounding environment influence parameters and analyzes to obtain the surrounding environment influence driving value; uses the intelligent operation robot to perform video operation to obtain the working pictures of the substation circuit breaker, divides them into several regions, and analyzes to obtain the influence value of each region; based on the influence value of each region, divides each confidence level region, matches to obtain the infrared reflection artifact correction scheme for each region, and performs infrared reflection artifact correction to obtain the artifact correction temperature of each region, and processes to obtain the video operation detection reference temperature; obtains the operation state parameters of the substation circuit breaker, and fuses the video operation detection reference temperature for discrimination, thereby analyzing to obtain the video operation detection temperature and uploading it to the background data management center for display.

[0008] The embodiment of the present application provides an intelligent analysis system for substation video operations with artificial intelligence recognition, including: a surrounding environment analysis module, an impact analysis module, a temperature preliminary correction module, and a temperature depth correction module; wherein, the surrounding environment analysis module is used to obtain surrounding environment impact parameters and analyze to obtain a surrounding environment impact driving value after the intelligent operation robot receives a monitoring operation signal; the impact analysis module is used to obtain working pictures of the substation circuit breaker through video operations using the intelligent operation robot, divide them into several regions, and analyze to obtain the affected values of each region; the temperature preliminary correction module is used to divide each confidence level region based on the affected values of each region, match the infrared reflection artifact correction scheme for each region, perform infrared reflection artifact correction to obtain the artifact correction temperature of each region, and process to obtain the video operation detection reference temperature; the temperature depth correction module is used to obtain the operation state parameters of the substation circuit breaker, fuse with the video operation detection reference temperature for discrimination, thereby analyze to obtain the video operation detection temperature, and upload it to the background data management center for display.

[0009] One or more technical solutions provided in the embodiment of the present application have at least the following technical effects or advantages: 1. The intelligent analysis method for substation video operations with artificial intelligence recognition provided by the present invention analyzes to obtain the surrounding environment impact driving value and the affected values of each region, thereby dividing each confidence level region, matching the corresponding infrared reflection artifact correction scheme for each confidence level region for temperature correction to obtain the video operation detection reference temperature, and further analyzing to obtain the video operation detection temperature in combination with the operation state parameters of the substation circuit breaker, realizing the accurate detection of the temperature of the substation circuit breaker, avoiding the mis-tripping of the circuit breaker caused by inaccurate temperature detection of the substation circuit breaker, and effectively solving the problem of inaccurate temperature recognition of the substation circuit breaker in the prior art due to the lack of infrared reflection artifact analysis.

[0010] 2. The present invention uses the intelligent operation robot to obtain the working pictures of the substation circuit breaker through video operations, divides them into several regions, analyzes to obtain the affected values of each region, and compares and analyzes to obtain the affected values of each region, thereby realizing the accurate assessment of the influence degree of infrared artifacts and ensuring that the subsequent correction scheme can be finely adjusted according to the actual situation of each region.

[0011] 3. The present invention divides each confidence level region based on the affected values of each region, matches the infrared reflection artifact correction scheme for each region, and performs infrared reflection artifact correction, thereby obtaining the artifact correction temperature of each region and marking it as the video operation detection reference temperature. Furthermore, the hierarchical correction for different confidence level regions ensures that the video operation detection reference temperature is more real and reliable, avoiding the problem of inaccurate video operation detection temperature caused by infrared reflection artifacts.

[0012] 4. The present invention obtains an environmental temperature adjustment factor by analyzing the environmental temperature, thereby correcting the video operation detection reference temperature for environmental factors to obtain the first temperature for video operation detection. At the same time, by obtaining the operating state parameter of the substation circuit breaker and analyzing it to obtain the operating state trade-off index of the substation circuit breaker, and comparing it with the operating state trade-off threshold range of the substation circuit breaker, the temperature for video operation detection is further obtained, realizing the accurate discrimination of the temperature for video operation detection, ensuring the true reflection of the operating state of the substation circuit breaker and the actual temperature, and effectively avoiding the problem of false power-off caused by temperature detection errors.

[0013] 5. By obtaining the operating state deviation coefficient, the video operation parameters of the intelligent operation robot are adjusted accordingly, thereby realizing the adaptive optimization of the video operation parameters, and further ensuring the quality of video operation image acquisition, providing high-quality image data support for temperature detection. Brief Description of the Drawings

[0014] Figure 1 It is a flowchart of the intelligent analysis method for substation video operation with artificial intelligence recognition provided by an embodiment of the present application; Figure 2 It is a schematic structural diagram of the intelligent analysis system for substation video operation with artificial intelligence recognition provided by an embodiment of the present application. Detailed Embodiments

[0015] The embodiment of the present application provides an intelligent analysis method and system for substation video operation with artificial intelligence recognition, which solves the problem of inaccurate temperature recognition of substation circuit breakers in the prior art due to the lack of infrared reflection artifact analysis, achieves the accurate detection of the temperature of substation circuit breakers, and avoids false power-off of circuit breakers caused by inaccurate temperature detection of substation circuit breakers.

[0016] In order to better understand the above technical solutions, the above technical solutions will be described in detail below in conjunction with the accompanying drawings of the specification and specific embodiments.

[0017] Such as Figure 1As shown in the figure, it is a flowchart of an intelligent analysis method for substation video operations using artificial intelligence recognition provided by an embodiment of the present application. The method includes the following steps: After the intelligent operation robot receives the monitoring operation signal, it obtains the surrounding environment impact parameters and analyzes to obtain the surrounding environment impact driving value; uses the intelligent operation robot to perform video operations to obtain the working pictures of the substation circuit breaker, divides them into several regions, and analyzes to obtain the impact values of each region; based on the impact values of each region, divides each confidence level region, matches to obtain the infrared reflection artifact correction scheme for each region, and performs infrared reflection artifact correction to obtain the artifact correction temperature of each region, and processes to obtain the video operation detection reference temperature; obtains the operating state parameters of the substation circuit breaker, and fuses the video operation detection reference temperature for discrimination, thereby analyzing to obtain the video operation detection temperature and uploading it to the background data management center for display.

[0018] Further, to obtain the surrounding environment impact parameters and analyze to obtain the surrounding environment impact driving value, the specific method is as follows: Obtain the surrounding environment impact parameters, where the surrounding environment impact parameters include the surface reflectivity of each adjacent device, the straight-line interval distance of the substation circuit breaker, and the environmental illuminance; obtain the preset surrounding environment impact reference set in the database, where the surrounding environment impact reference set includes the surface reflectivity reference value, the straight-line interval distance impact element, and the ideal environmental illuminance value; based on the comparison analysis and fusion processing of the surrounding environment impact parameters and the surrounding environment impact reference set, obtain the surrounding environment impact driving value; the specific analysis process of the surrounding environment impact driving value is: Compare and analyze the surface reflectivity of each adjacent device and the environmental illuminance with the surface reflectivity reference value and the ideal environmental illuminance value respectively to obtain the comparison results. At the same time, multiply and couple the straight-line interval distance of the substation circuit breaker of each adjacent device with the straight-line interval distance impact element to obtain the multiplicative coupling result. Then, introduce the corresponding weighting factors to perform multi-dimensional nesting on the comparison results and the multiplicative coupling result, and aggregate to obtain the surrounding environment impact driving value.

[0019] In this embodiment, it should be noted that each adjacent device refers to other devices adjacent to the substation circuit breaker within a preset range; the straight-line interval distance of the substation circuit breaker refers to the straight-line interval distance between other adjacent devices and the substation circuit breaker.

[0020] The surface reflectivity of each adjacent device can be obtained by querying the device information of each adjacent device in the database. The straight-line interval distance of the substation circuit breaker can be identified by the intelligent operation robot. The specific identification method is to use the intelligent operation robot to obtain the pictures of the video operation and analyze them using a deep learning framework (such as TensorFlow) based on the pictures of the video operation. The environmental illuminance can be detected by the light sensor carried by the intelligent operation robot.

[0021] Based on the analysis of the surrounding environment impact parameters, the driving value of the surrounding environment impact is obtained. This takes into account the mutual influence relationships among these parameters. For example, the surface of a device with a high reflectivity will reflect more environmental radiation, resulting in a larger measurement error. The higher the reflectivity, the more environmental light and thermal radiation are reflected, which will increase the intensity of the infrared afterimage. The smaller the linear interval distance, the greater the mutual influence between devices. Devices at close range are more susceptible to interference from reflected light or thermal radiation, leading to measurement errors or artifact phenomena. The higher the environmental illuminance, the more light is reflected from the device surface, which will result in stronger reflected light or thermal radiation and increase the artifact phenomenon.

[0022] The driving value of the surrounding environment impact is obtained through the following specific method: ; In the formula, represents the driving value of the surrounding environment impact, represents the surface reflectivity of the i-th adjacent device, where i represents the number of the adjacent device, , represents the total number of adjacent devices, represents the surface reflectivity reference value, represents the environmental illuminance, represents the ideal value of the environmental illuminance, The linear interval distance of the substation circuit breaker of the i-th adjacent device, represents the linear interval distance influence element of the i-th adjacent device, represents the surface reflectivity weighting factor, represents the environmental illuminance weighting factor.

[0023] The surface reflectivity weighting factor and the environmental illuminance weighting factor can be obtained by matching in the database. For example, the reflectivity weighting factor and the environmental illuminance weighting factor can be obtained from the database. For example, the reflectivity weighting factor can be obtained by acquiring the historical reflectivity stored in the database and the corresponding reflectivity weighting factor, thereby constructing a reflectivity mapping set, where there is a one-to-one or many-to-one correspondence relationship in this mapping set. By inputting the reflectivity data to be used into the reflectivity mapping set, the reflectivity weighting factor can be obtained. The acquisition method of the environmental illuminance weighting factor is the same as that of the reflectivity weighting factor and can also be obtained by matching in the corresponding mapping set, where the environmental illuminance weighting factor corresponds to the environmental illuminance mapping set.

[0024] The straight-line spacing distance influence element can be obtained from the database. The specific method is as follows: Obtain each preset straight-line spacing distance interval and the corresponding straight-line spacing distance influence element in the database, and compare them with each straight-line spacing distance. If there is a straight-line spacing distance within a certain straight-line spacing distance interval, obtain the straight-line spacing distance influence element corresponding to this interval as the straight-line spacing distance influence element.

[0025] By obtaining the surrounding environment influence parameters and comparing and analyzing them with the preset reference set, the automatic evaluation of the influence of the surrounding environment on the temperature measurement of the substation circuit breaker is realized. Considering the influences of surface reflectivity, straight-line spacing distance, and environmental illuminance comprehensively, the accuracy of the evaluation of the influence of the surrounding environment is improved. It can adapt to different environmental conditions and enhance the adaptability and flexibility of temperature analysis.

[0026] Furthermore, the affected values of each region are analyzed. The specific method is as follows: Use an intelligent operation robot for video operation to obtain the working pictures of the substation circuit breaker and divide them into several regions; obtain the working picture detection parameters of each region, where the working picture detection parameters include the light reflection intensity and the artifact coverage area ratio of each region; obtain the current artifact movement speed; obtain the preset artifact movement speed influence element and the working picture detection allowable set in the database, where the working picture detection allowable set includes the allowable value of light reflection intensity and the allowable value of artifact coverage area ratio; perform multiplicative coupling processing based on the artifact movement speed influence element and the current artifact movement speed to obtain the multiplicative coupling processing result, and simultaneously compare and analyze the light reflection intensity and the artifact coverage area ratio with the allowable value of light reflection intensity and the allowable value of artifact coverage area ratio respectively to obtain the comparative analysis result, and then introduce the corresponding weighting factors to perform multi-dimensional nesting on the multiplicative coupling processing result and the comparative analysis result, and aggregate to obtain the affected values of each region.

[0027] In this embodiment, the multiplicative coupling processing is the multiplication processing.

[0028] The light reflection intensity and the artifact coverage area ratio of each region can be obtained by analyzing with a multi-functional image inspection tool (PixSpy). The current artifact movement speed can be obtained from the database. By analyzing the time point when the current artifact movement speed is obtained and comparing it with the preset time interval in the database, if this time point is within a certain preset time interval in the database, obtain the current artifact movement speed corresponding to this time interval as the current artifact movement speed.

[0029] By analyzing the working image detection parameters of each region and the current artifact movement speed to obtain the affected value of each region, the mutual influence relationship between these parameters is considered. For example, the higher the light reflection intensity, the more ambient light or thermal radiation is reflected, resulting in more artifact regions, thus increasing the artifact coverage area ratio. The higher the light reflection intensity, the faster the movement speed of the artifacts, because the increased intensity of the reflected light causes the dynamic changes of the artifacts in the image to be more obvious. If the current artifact movement speed is faster and the artifact coverage area ratio is larger, the affected fluctuation of each region is greater and more affected.

[0030] The affected value of each region is obtained by the following specific method: ; In the formula, represents the affected value of the j-th region, represents the light reflection intensity of each j-th region, and j represents the region number, , represents the total number of regions, represents the allowable value of the light reflection intensity, represents the artifact coverage area ratio of each j-th region, represents the allowable value of the artifact coverage area ratio, represents the current artifact movement speed, represents the artifact movement speed influencing element, represents the light reflection intensity weighting factor, represents the artifact coverage area ratio weighting factor.

[0031] The light reflection intensity weighting factor and the artifact coverage area ratio weighting factor can be obtained from the database. For example, the light reflection intensity weighting factor can be obtained by acquiring the historical light reflection intensity stored in the database and the corresponding light reflection intensity weighting factor of the historical light reflection intensity, thereby constructing a light reflection intensity mapping set, in which there is a one-to-one or many-to-one correspondence relationship in the mapping set. By inputting the light reflection intensity data to be used into the light reflection intensity mapping set, the light reflection intensity weighting factor can be obtained. The acquisition method of the artifact coverage area ratio weighting factor is the same as that of the light reflection intensity weighting factor and can also be obtained by matching in the corresponding mapping set, where the artifact coverage area ratio weighting factor corresponds to the artifact coverage area ratio mapping set.

[0032] The artifact movement speed influencing element can be obtained from a database. For example, the artifact movement speed influencing element can be obtained by acquiring the historical artifact movement speed stored in the database and the corresponding artifact movement speed influencing element of the historical artifact movement speed, thereby constructing an artifact movement speed mapping set. There is a one-to-one or many-to-one correspondence relationship in this mapping set. By inputting the current artifact movement speed data to be used into the artifact movement speed mapping set, the artifact movement speed influencing element can be obtained.

[0033] By dividing the working picture of the substation circuit breaker into several regions and analyzing the affected values of each region respectively, the refined monitoring of the substation circuit breaker state is realized, the accuracy and reliability of the monitoring are improved. Comprehensively considering the light reflection intensity, the artifact coverage area ratio, and the current artifact movement speed to comprehensively evaluate the degree of artifact influence on each region, ensuring the accuracy of the evaluation result. By introducing a weighting factor for multi-dimensional nested analysis, it helps to improve the reliability of the substation circuit breaker temperature measurement and prevent misjudgment caused by measurement errors.

[0034] Furthermore, based on the affected values of each region, each confidence level region is divided, and the infrared reflection artifact correction scheme for each region is matched. The specific method is: obtain the preset first confidence threshold and the second confidence threshold in the database and compare them with the affected values of each region, thereby dividing each confidence level region and matching the infrared reflection artifact correction scheme for each region; the infrared reflection artifact correction scheme for each region includes the first infrared reflection artifact correction scheme, the second infrared reflection artifact correction scheme, and the third infrared reflection artifact correction scheme; if the affected value of a certain region is above the first confidence threshold, then this region is divided into the third-level confidence region, and the infrared reflection artifact correction scheme for this region is defined as the third infrared reflection artifact correction scheme; if the affected value of a certain region is less than the first confidence threshold and above the second confidence threshold, then this region is divided into the second-level confidence region, and the infrared reflection artifact correction scheme for this region is defined as the second infrared reflection artifact correction scheme; if the affected value of a certain region is less than the second confidence threshold, then this region is divided into the first-level confidence region, and the infrared reflection artifact correction scheme for this region is defined as the first infrared reflection artifact correction scheme.

[0035] In this embodiment, by dividing each region into different confidence level regions and matching the corresponding infrared reflection artifact correction scheme, the precise correction of regions with different degrees of influence is realized, improving the accuracy of the substation circuit breaker temperature measurement. For different confidence level regions, different correction schemes are adopted, ensuring the enhanced correction of high-affected regions and the simplified processing of low-affected regions, improving the correction efficiency and the accuracy of the correction.

[0036] Further, the infrared reflection artifact correction scheme for each region is specifically as follows: The infrared reflection artifact correction scheme for each region includes the first infrared reflection artifact correction scheme, the second infrared reflection artifact correction scheme, and the third infrared reflection artifact correction scheme; obtain the preset surrounding environment impact driving value intervals in the database and the environmental correction reference factors corresponding to each surrounding environment impact driving value interval, and match them with the surrounding environment impact driving values to obtain the detection temperature correction factor (the specific method is: match the surrounding environment impact driving values with each surrounding environment impact driving value interval, if the surrounding environment impact driving value is within a certain preset surrounding environment impact driving value interval, then obtain the environmental correction reference factor corresponding to this interval as the environmental correction factor); the first infrared reflection artifact correction scheme is specifically as follows: obtain the center point temperature of each first-level confidence region, and the average temperature difference of the adjacent regions corresponding to each first-level confidence region (statistically process the center point temperature differences between each first-level confidence region and all its corresponding adjacent regions to obtain the average temperature difference of the adjacent regions corresponding to each first-level confidence region, and the center point temperature of each first-level confidence region refers to the detection temperature detected by the intelligent operation robot), and perform direct attenuation correction in combination with the detection temperature correction factor to obtain the artifact correction temperature of each first-level confidence region after correction (the specific method of direct attenuation correction is: perform a difference operation on the center point temperature of each first-level confidence region and the average temperature difference of the adjacent regions corresponding to each first-level confidence region to obtain the difference operation result, and multiply this difference operation result by the detection temperature correction factor to obtain the detection temperature correction temperature, and then perform a difference operation on the center point temperature of each first-level confidence region and the detection temperature correction temperature to obtain the artifact correction temperature of each first-level confidence region after correction. The specific method is: ; where, represents the artifact correction temperature of the k-th first-level confidence region after correction, k represents the number of the first-level confidence region, , represents the total number of first-level confidence regions, represents the center point temperature of the k-th first-level confidence region, represents the average temperature difference of the adjacent regions of the k-th first-level confidence region, represents the detection temperature correction factor); the second infrared reflection artifact correction scheme is specifically as follows: obtain the regional gradient amplitude of each second-level confidence region, and perform gradient correction in combination with the detection temperature correction factor to obtain the artifact correction temperature of each second-level confidence region after correction (the specific steps are: within each region, use the image processing algorithm [Canny operator] to calculate the regional gradient amplitude of each region, subtract the product of the detection temperature correction factor and the corresponding regional gradient amplitude from the center point temperature of each second-level confidence region, and the artifact correction temperature of each second-level confidence region after correction can be obtained. The specific method is: ; wherein, represents the artifact-corrected temperature of the l-th second-level confidence region after correction, l represents the number of the second-level confidence region, , represents the total number of second-level confidence regions, represents the central point temperature of the l-th second-level confidence region, represents the detection temperature correction factor, represents the regional gradient amplitude of the l-th second-level confidence region (the regional gradient amplitude can be obtained by applying the Sobel operator to the working picture of the substation circuit breaker)); The third infrared reflection artifact correction scheme is specifically: obtaining the regional average temperature of each third-level confidence region, performing weighted average using the Gaussian function to obtain the Gaussian weighted average value, and performing multiplicative coupling processing on the Gaussian weighted average value and the detection temperature correction factor to obtain the artifact-corrected temperature of each third-level confidence region after correction (the specific method is: performing weighted average on the central point temperature of each region adjacent to each third-level confidence region and the central point temperature of the corresponding third-level confidence region by introducing the Gaussian function to obtain the Gaussian weighted average value, and multiplying the Gaussian weighted average value by the detection temperature correction factor to obtain the artifact-corrected temperature of each third-level confidence region after correction); jointly marking the artifact-corrected temperature of each first-level confidence region, the artifact-corrected temperature of each second-level confidence region, and the artifact-corrected temperature of each third-level confidence region after correction as the artifact-corrected temperature of each region.

[0037] In this embodiment, by obtaining each preset peripheral environment influence driving value interval and the corresponding environment correction reference factor in the database and matching them with the real-time detected peripheral environment influence driving value, the detection temperature correction factor is obtained. This step realizes the adaptive adjustment of the temperature correction by dynamic environmental factors, ensures that the correction factor matches the actual measurement environment, and thus makes the overall infrared temperature correction have self-adaptability and robustness.

[0038] By setting the infrared reflection artifact correction schemes for each region including the first infrared reflection artifact correction scheme, the second infrared reflection artifact correction scheme, and the third infrared reflection artifact correction scheme, it makes up for the local deficiencies of a single correction method, and further provides a more accurate temperature reference for the subsequent cross-verification with the equipment operating state. Since infrared artifacts usually lead to inaccurate temperature detection, which in turn causes misoperations of protection devices such as mispower-off. Through multi-scheme, hierarchical, and dynamic correction, the artifact interference is effectively eliminated, and the detection temperature of the video operation is closer to the real temperature.

[0039] By fusing the artifact correction temperature of each region with the operating state parameters of the substation circuit breaker (including multi-dimensional monitoring parameters such as electrical and mechanical), the equipment status can be determined more accurately, avoiding unnecessary power-off operations due to false temperature reporting, thus protecting the normal operation of the equipment and reducing the economic losses and failure risks caused by misoperation.

[0040] Furthermore, the steps to obtain the video operation detection reference temperature are as follows: Obtain the preset weight factors for each confidence level region in the database. The weight factors for each confidence level region include the weight factor for the first-level confidence region, the weight factor for the second-level confidence region, and the weight factor for the third-level confidence region. Take the average value of the artifact correction temperatures of each first-level confidence region, each second-level confidence region, and each third-level confidence region after correction to obtain the average temperature of each confidence level region. Then, perform weighted analysis on the average temperature of each confidence level region based on the weight factor for the first-level confidence region, the weight factor for the second-level confidence region, and the weight factor for the third-level confidence region, and perform multi-dimensional nesting to obtain the video operation detection reference temperature.

[0041] In this embodiment, the specific method to obtain the video operation detection reference temperature is as follows: ; In the formula, represents the video operation detection reference temperature, represents the weight factor for the first-level confidence region, represents the artifact correction temperature of the k-th first-level confidence region after correction, where k represents the number of the first-level confidence region, , represents the total number of first-level confidence regions, represents the artifact correction temperature of the l-th second-level confidence region after correction, where l represents the number of the second-level confidence region, , represents the total number of second-level confidence regions, represents the artifact correction temperature of the m-th third-level confidence region after correction, where m represents the number of the third-level confidence region, , represents the total number of third-level confidence regions, represents the weight factor for the first-level confidence region, represents the weight factor for the second-level confidence region, represents the weight factor for the third-level confidence region.

[0042] Further, obtain the operating state parameters of the substation circuit breaker, and fuse the video operation detection reference temperature for discrimination, and thus analyze and obtain the video operation detection temperature. The specific method is as follows: Obtain the operating state parameters of the substation circuit breaker. The operating state parameters of the substation circuit breaker include the abnormal verification parameters and mechanical abnormal verification parameters of the substation circuit breaker. The abnormal verification parameters of the substation circuit breaker include the loop resistance and load current of the substation circuit breaker. The mechanical abnormal verification parameters include the arc frequency and mechanical frequency inside the substation circuit breaker. Obtain the calibration reference set. The calibration reference set includes the loop resistance reference value, load current reference value, arc frequency reference value, and mechanical frequency reference value. Compare and analyze the operating state parameters of the substation circuit breaker with the calibration reference set respectively, and introduce the corresponding weighting factors to obtain the operating state trade-off index of the substation circuit breaker. Obtain the ambient temperature. Obtain the preset ambient temperature intervals and the corresponding reference ambient temperature adjustment factors in the database, and compare them with the ambient temperature. If the ambient temperature is within a certain preset ambient temperature interval, obtain the corresponding reference ambient temperature adjustment factor in this interval as the ambient temperature adjustment factor. Based on the ambient temperature adjustment factor, correct the video operation detection reference temperature to obtain the first video operation detection temperature (the specific method is: ; where, represents the first video operation detection temperature, represents the ambient temperature adjustment factor, represents the video operation detection reference temperature); Obtain the preset operating state trade-off threshold interval of the substation circuit breaker in the database, and compare it with the operating state trade-off index of the substation circuit breaker. If the operating state trade-off index of the substation circuit breaker is within the operating state trade-off threshold interval of the substation circuit breaker, then use the first video operation detection temperature as the video operation detection temperature. Otherwise, correct it based on the first video operation detection temperature to obtain the video operation detection temperature.

[0043] In this embodiment, the loop resistance of the substation circuit breaker can be measured by a loop resistance tester, the load current can be obtained through a current transformer, the arc frequency inside the substation circuit breaker can be measured by an oscilloscope, and the mechanical frequency of the substation circuit breaker can be measured by a vibration sensor.

[0044] The trade-off index for the operating state of a substation circuit breaker is obtained by analyzing the loop resistance, load current, arc frequency, and mechanical frequency inside the substation circuit breaker. This takes into account the mutual influence relationships among these parameters. For example, the loop resistance affects the magnitude of the load current, resulting in a decrease in arc energy, which in turn affects the stability of the arc frequency. Abnormal vibration of mechanical components increases the loop resistance, thereby indirectly affecting the arc frequency and mechanical frequency. High load current leads to an increase in the arc frequency, while also causing vibration of mechanical components and affecting the mechanical frequency. Changes in the arc frequency affect the voltage and current distribution in the circuit, and thus affect the stability of the loop resistance and load current.

[0045] The trade-off index for the operating state of a substation circuit breaker is obtained through the following specific method: ; In the formula, represents the trade-off index for the operating state of the substation circuit breaker, represents the loop resistance of the substation circuit breaker, represents the reference value of the loop resistance, represents the load current of the substation circuit breaker, represents the reference value of the load current, represents the arc frequency inside the substation circuit breaker, represents the reference value of the arc frequency, represents the mechanical frequency inside the substation circuit breaker, represents the reference value of the mechanical frequency, represents the weighting factor of the loop resistance, represents the weighting factor of the load current, represents the weighting factor of the arc frequency, represents the weighting factor of the mechanical frequency.

[0046] The weighting factors of the loop resistance, load current, arc frequency, and mechanical frequency can be obtained from a database. For example, the weighting factor of the loop resistance can be obtained by acquiring the historical loop resistance stored in the database and the corresponding weighting factor of the loop resistance. Thus, a loop resistance mapping set is constructed, in which there is a one-to-one or many-to-one correspondence. By inputting the loop resistance data to be used into the loop resistance mapping set, the weighting factor of the loop resistance can be obtained. The acquisition methods of the weighting factors of the load current, arc frequency, and arc frequency are the same as that of the weighting factor of the loop resistance and can also be obtained by matching in the corresponding mapping sets. Among them, the weighting factor of the load current corresponds to the load current mapping set, the weighting factor of the arc frequency corresponds to the arc frequency mapping set, and the mechanical frequency factor corresponds to the arc frequency mapping set.

[0047] By analyzing the operating state parameters of the substation circuit breaker, the influence of single temperature measurement error on fault judgment is reduced, and the detected temperature can more truly reflect the operating state of the equipment. When the video data is deviated due to artifacts, cross-verification can be carried out after fusing electrical and mechanical parameters to reduce the misjudgment risk caused by a single data source. By introducing a calibration reference set and a weighting factor, the actual measured parameters are compared with the preset standard, and the generated equipment operating state trade-off index provides a strong reference for subsequent temperature correction, thus ensuring that the video detection temperature judgment is more comprehensive and objective. The ambient temperature adjustment factor can reflect the influence of environmental changes on the thermal state of the equipment in real time, so that the video detection temperature takes into account the external thermal environment interference.

[0048] Further, based on the video operation detection of the first temperature for correction, the video operation detection temperature is obtained. The specific method is as follows: Obtain the maximum value and the minimum value of the substation circuit breaker operating state trade-off threshold interval, and compare them with the substation circuit breaker operating state trade-off index; if the substation circuit breaker operating state trade-off index is less than the minimum value of the interval, analyze and obtain the first deviation coefficient of the operating state, and based on the first deviation coefficient of the operating state, correct the first temperature detected by the video operation downward to obtain the video operation detection temperature; if the substation circuit breaker operating state trade-off index is greater than the maximum value of the interval, analyze and obtain the second deviation coefficient of the operating state, and based on the second deviation coefficient of the operating state, correct the first temperature detected by the video operation upward to obtain the video operation detection temperature.

[0049] In this embodiment, if the substation circuit breaker operating state trade-off index is less than the minimum value of the interval, the first deviation coefficient of the operating state is analyzed. The specific method is as follows: Perform a difference processing on the minimum value of the interval and the substation circuit breaker operating state trade-off index, and divide the difference by the minimum value of the interval to obtain the first deviation coefficient of the operating state.

[0050] Based on the first deviation coefficient of the operating state, correct the first temperature detected by the video operation downward to obtain the video operation detection temperature. The specific steps are as follows: Obtain the mapping set of the operating state and the temperature deviation coefficient preset in the database, and input the first deviation coefficient of the operating state into the mapping set of the operating state and the temperature deviation coefficient. If the first deviation coefficient of the operating state is within a certain operating state interval of the mapping set of the operating state and the temperature deviation coefficient, obtain the temperature deviation coefficient corresponding to the operating state interval as the first deviation coefficient of the operating temperature, and based on the first deviation coefficient of the operating temperature, correct the first temperature detected by the video operation downward to obtain the video operation detection temperature. The specific method is as follows: ; where represents the video operation detection temperature, represents the first temperature detected by the video operation, represents the first deviation coefficient of the operating temperature.

[0051] If the trade-off index of the substation circuit breaker operating state is greater than the maximum value of the interval, the second deviation coefficient of the operating state is obtained through analysis. The specific method is as follows: perform a difference operation between the maximum value of the interval and the trade-off index of the substation circuit breaker operating state, and then divide this difference by the maximum value of the interval to obtain the second deviation coefficient of the operating state.

[0052] Based on the second deviation coefficient of the operating state, the first temperature detected by the video operation is corrected upward to obtain the temperature detected by the video operation. The specific steps are as follows: obtain the mapping set of the preset operating state and temperature deviation coefficient in the database, and input the second deviation coefficient of the operating state into the mapping set of the operating state and temperature deviation coefficient. If the second deviation coefficient of the operating state is within a certain operating state interval of the mapping set of the operating state and temperature deviation coefficient, then obtain the temperature deviation coefficient corresponding to this operating state interval as the second deviation coefficient of the operating temperature, and correct the first temperature detected by the video operation downward based on the second deviation coefficient of the operating temperature to obtain the temperature detected by the video operation. The specific method is as follows: ; where represents the temperature detected by the video operation, represents the first temperature detected by the video operation, represents the second deviation coefficient of the operating temperature.

[0053] By comparing the trade-off index of the substation circuit breaker operating state with the preset threshold interval (maximum value and minimum value), and respectively obtaining the first deviation coefficient or the second deviation coefficient of the operating state based on the deviation situation, the first temperature detected by the video operation is corrected downward or upward to obtain a more accurate detected temperature. When the measured operating state index deviates from the preset range, the automatic correction of the temperature is realized by calculating the deviation coefficient, so that the detected temperature dynamically adapts to the actual environment, eliminates systematic deviation, and makes the correction result closer to the actual equipment temperature.

[0054] Furthermore, it also includes: obtaining the operating state deviation coefficient, and accordingly adjusting the video operation parameters of the intelligent operation robot. The specific method is as follows: obtain the operating state deviation coefficient, and accordingly adjust the video operation parameters of the intelligent operation robot. The operating state deviation coefficient includes the first deviation coefficient of the operating state and the second deviation coefficient of the operating state; the video operation parameters include the aperture f value and the focal length; if the operating state deviation coefficient is the first deviation coefficient of the operating state, then adjust the video operation parameters upward based on the operating state deviation coefficient; if the operating state deviation coefficient is the second deviation coefficient of the operating state, then adjust the video operation parameters downward based on the operating state deviation coefficient.

[0055] In this embodiment, if the operation status deviation coefficient is the first operation status deviation coefficient, the video operation parameters are adjusted upward based on the operation status deviation coefficient. The specific steps are as follows: Obtain the preset mapping set of operation status and video operation parameter deviation coefficients in the database, and input the first operation status deviation coefficient into the mapping set of operation status and video operation parameter deviation coefficients. If the first operation status deviation coefficient is within a certain operation status interval of the mapping set of operation status and video operation parameter deviation coefficients, obtain the corresponding video operation parameter deviation of this operation status interval as the first video operation deviation coefficient, where the first video operation deviation coefficient includes the first aperture f-value deviation coefficient of the video operation and the first focal length deviation coefficient of the video operation. Adjust the video operation parameters upward based on the first video operation deviation coefficient. The specific method is as follows: Multiply the aperture f-value by the first aperture f-value deviation coefficient of the video operation and then add the result to the aperture f-value to obtain the upward-adjusted aperture f-value. ; In the formula, represents the upward-adjusted aperture f-value, represents the aperture f-value, represents the first aperture f-value deviation coefficient of the video operation.

[0056] Multiply the focal length by the first focal length deviation coefficient of the video operation and then add the result to the focal length to obtain the upward-adjusted focal length. ; In the formula, represents the upward-adjusted focal length, represents the focal length, represents the first focal length deviation coefficient of the video operation.

[0057] If the operation status deviation coefficient is the second operation status deviation coefficient, the video operation parameters are adjusted downward based on the operation status deviation coefficient. The specific steps are as follows: Obtain the preset mapping set of operation status and video operation parameter deviation coefficients in the database, and input the second operation status deviation coefficient into the mapping set of operation status and video operation parameter deviation coefficients. If the second operation status deviation coefficient is within a certain operation status interval of the mapping set of operation status and video operation parameter deviation coefficients, obtain the corresponding video operation parameter deviation of this operation status interval as the second video operation deviation coefficient, where the second video operation deviation coefficient includes the second aperture f-value deviation coefficient of the video operation and the second focal length deviation coefficient of the video operation. Adjust the video operation parameters downward based on the second video operation deviation coefficient. The specific method is as follows: Multiply the aperture f-value by the second aperture f-value deviation coefficient of the video operation and then subtract the result from the aperture f-value to obtain the downward-adjusted aperture f-value. ; In the formula, X represents the downward-adjusted aperture f-value, represents the aperture f-value, Represents the deviation coefficient of the second aperture f-value of the video operation.

[0058] Multiply the focal length by the deviation coefficient of the second focal length of the video operation and then subtract the focal length to obtain the downward-adjusted focal length. X ; In the formula, Represents the downward-adjusted focal length, Represents the focal length, Represents the deviation coefficient of the second focal length of the video operation.

[0059] Based on the feedback mechanism, adjust the camera parameters (aperture, focal length) to ensure high-quality image data is obtained under different environmental conditions, providing an equipment basis for temperature detection and area division, thereby reducing optical acquisition errors and improving the stability of temperature analysis.

[0060] As Figure 2 shown, it is a schematic structural diagram of the intelligent analysis system for substation video operations with artificial intelligence recognition provided by the embodiment of the present application. The intelligent analysis system for substation video operations with artificial intelligence recognition provided by the embodiment of the present application includes: a peripheral environment analysis module, an impact analysis module, a temperature preliminary correction module, and a temperature deep correction module; among them, the peripheral environment analysis module is used to obtain the peripheral environment impact parameters and analyze the obtained peripheral environment impact driving value after the intelligent operation robot receives the monitoring operation signal; the impact analysis module is used to use the intelligent operation robot to perform video operations to obtain the working pictures of the substation circuit breaker, divide them into several regions, and analyze the affected values of each region; the temperature preliminary correction module is used to divide each confidence level region based on the affected values of each region, match the infrared reflection artifact correction scheme for each region, perform infrared reflection artifact correction, obtain the artifact correction temperature of each region, and process to obtain the detection reference temperature of the video operation; the temperature deep correction module is used to obtain the operation state parameters of the substation circuit breaker, and fuse the detection reference temperature of the video operation for discrimination, thereby analyzing the detection temperature of the video operation and uploading it to the background data management center for display.

[0061] In summary, in this embodiment, by analyzing the obtained peripheral environment impact driving value and the affected values of each region, each confidence level region is divided, and the corresponding infrared reflection artifact correction scheme is matched for each confidence level region for temperature correction to obtain the detection reference temperature of the video operation. Furthermore, by combining the operation state parameters of the substation circuit breaker, the detection temperature of the video operation is analyzed, realizing the accurate detection of the temperature of the substation circuit breaker, avoiding the mispower-off of the circuit breaker caused by inaccurate temperature detection of the substation circuit breaker, and effectively solving the problem of inaccurate temperature recognition of the substation circuit breaker caused by the lack of infrared reflection artifact analysis in the prior art.

[0062] Those skilled in the art should understand that the embodiments of the present invention can be provided as a method, a system, or a computer program product. Therefore, the present invention can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Moreover, the present invention can take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) that contain computer-usable program code.

[0063] The present invention is described with reference to the flowcharts and / or block diagrams of methods, apparatuses (systems), and computer program products according to embodiments of the present invention. It should be understood that each flow and / or block in the flowchart and / or block diagram, as well as the combination of flows and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to the processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing devices to generate a machine, such that the instructions executed by the processor of the computer or other programmable data processing devices produce means for implementing the functions specified in Figure 1 one flow or multiple flows and / or blocks Figure 1 one block or multiple blocks.

[0064] These computer program instructions can also be stored in a computer-readable memory that can direct a computer or other programmable data processing device to work in a specific manner, such that the instructions stored in the computer-readable memory produce a manufactured article including instruction means that implement the functions specified in Figure 1 one flow or multiple flows and / or blocks Figure 1 one block or multiple blocks.

[0065] These computer program instructions can also be loaded onto a computer or other programmable data processing device, such that a series of operation steps are executed on the computer or other programmable device to generate a computer-implemented process, and thus the instructions executed on the computer or other programmable device provide steps for implementing the functions specified in Figure 1 one flow or multiple flows and / or blocks Figure 1 one block or multiple blocks.

[0066] Although the preferred embodiments of the present invention have been described, those skilled in the art can make additional changes and modifications once they learn the basic creative concepts. Therefore, the appended claims are intended to be construed as including the preferred embodiments and all changes and modifications that fall within the scope of the present invention.

[0067] Obviously, those skilled in the art can make various modifications and variations to the present invention without departing from the spirit and scope of the present invention. Thus, if these modifications and variations of the present invention fall within the scope of the claims of the present invention and their equivalent technologies, the present invention is also intended to include these modifications and variations.

Claims

1. An intelligent analysis method for substation video operations identified by artificial intelligence, characterized in that, Including the following steps: After the intelligent operation robot receives the monitoring operation signal, it obtains the surrounding environment impact parameters and analyzes to obtain the surrounding environment impact driving value; Use the intelligent operation robot to perform video operation to obtain the working pictures of the substation circuit breaker, divide them into several regions, and analyze to obtain the affected values of each region; Based on the affected values of each region, divide each confidence level region, match the infrared reflection artifact correction scheme for each region, and perform infrared reflection artifact correction to obtain the artifact correction temperature of each region, and process to obtain the video operation detection reference temperature; Obtain the operation state parameters of the substation circuit breaker, and fuse the video operation detection reference temperature for discrimination, thereby analyzing to obtain the video operation detection temperature and uploading it to the background data management center for display.

2. The intelligent analysis method for substation video operations identified by artificial intelligence according to claim 1, wherein: The method for obtaining the surrounding environment impact parameters and analyzing to obtain the surrounding environment impact driving value is specifically as follows: Obtain the surrounding environment impact parameters, where the surrounding environment impact parameters include the surface reflectivity of each adjacent device, the straight-line interval distance of the substation circuit breaker, and the ambient illuminance; Obtain the preset surrounding environment impact reference set in the database, where the surrounding environment impact reference set includes the surface reflectivity reference value, the straight-line interval distance impact element, and the ambient illuminance ideal value; Based on the comparison analysis and fusion processing of the surrounding environment impact parameters and the surrounding environment impact reference set, obtain the surrounding environment impact driving value; The specific analysis process of the surrounding environment impact driving value is as follows: Compare and analyze the surface reflectivity of each adjacent device and the ambient illuminance with the surface reflectivity reference value and the ambient illuminance ideal value respectively to obtain the comparison results. At the same time, perform multiplicative coupling on the straight-line interval distance of the substation circuit breaker of each adjacent device and the straight-line interval distance impact element to obtain the multiplicative coupling result. Then introduce the corresponding weighting factors to perform multi-dimensional nesting on the comparison results and the multiplicative coupling result, and aggregate to obtain the surrounding environment impact driving value.

3. The intelligent analysis method for substation video operations identified by artificial intelligence according to claim 1, wherein: The method for analyzing to obtain the affected values of each region is specifically as follows: Use the intelligent operation robot to perform video operation to obtain the working pictures of the substation circuit breaker and divide them into several regions; Obtain the working picture detection parameters of each region, where the working picture detection parameters include the light reflection intensity and the artifact coverage area ratio of each region; Obtain the current artifact moving speed; Obtain the preset artifact moving speed impact element and the working picture detection permission set in the database, where the working picture detection permission set includes the light reflection intensity permission value and the artifact coverage area ratio permission value; Based on the multiplicative coupling processing of the artifact moving speed impact element and the current artifact moving speed, obtain the multiplicative coupling processing result. Synchronously compare and analyze the light reflection intensity and the artifact coverage area ratio with the light reflection intensity permission value and the artifact coverage area ratio permission value respectively to obtain the comparison analysis result. Then introduce the corresponding weighting factors to perform multi-dimensional nesting on the multiplicative coupling processing result and the comparison analysis result, and aggregate to obtain the affected values of each region.

4. The intelligent analysis method for substation video operations identified by artificial intelligence according to claim 1, wherein: Based on the affected values of each region, divide each confidence level region and match the infrared reflection artifact correction scheme for each region. The specific method is as follows: Obtain the preset first confidence threshold and second confidence threshold in the database, and compare them with the affected values of each region, thereby dividing each confidence level region and performing matching to obtain the infrared reflection artifact correction scheme for each region; The infrared reflection artifact correction schemes for each region include the first infrared reflection artifact correction scheme, the second infrared reflection artifact correction scheme, and the third infrared reflection artifact correction scheme; If the affected value of a certain region is above the first confidence threshold, then divide this region into the third-level confidence region, and simultaneously define the infrared reflection artifact correction scheme for this region as the third infrared reflection artifact correction scheme; If the affected value of a certain region is less than the first confidence threshold and above the second confidence threshold, then divide this region into the second-level confidence region, and simultaneously define the infrared reflection artifact correction scheme for this region as the second infrared reflection artifact correction scheme; If the affected value of a certain region is less than the second confidence threshold, then divide this region into the first-level confidence region, and simultaneously define the infrared reflection artifact correction scheme for this region as the first infrared reflection artifact correction scheme.

5. The intelligent analysis method for substation video operation identified by artificial intelligence according to claim 4, characterized in that: The infrared reflection artifact correction schemes for each region are specifically as follows: The infrared reflection artifact correction schemes for each region include the first infrared reflection artifact correction scheme, the second infrared reflection artifact correction scheme, and the third infrared reflection artifact correction scheme; Obtain the preset driving value intervals of the influence of each surrounding environment in the database and the environmental correction reference factors corresponding to each driving value interval of the influence of the surrounding environment, and perform matching with the driving value of the surrounding environment influence to obtain the detection temperature correction factor; The first infrared reflection artifact correction scheme is specifically as follows: Obtain the center point temperature of each first-level confidence region and the average temperature difference of the adjacent regions corresponding to each first-level confidence region, and perform direct attenuation correction in combination with the detection temperature correction factor to obtain the artifact correction temperature of each first-level confidence region after correction; The second infrared reflection artifact correction scheme is specifically as follows: Obtain the regional gradient amplitude of each second-level confidence region, and thereby perform gradient correction in combination with the detection temperature correction factor to obtain the artifact correction temperature of each second-level confidence region after correction; The third infrared reflection artifact correction scheme is specifically as follows: Obtain the regional average temperature of each third-level confidence region, perform weighted average using the Gaussian function to obtain the Gaussian weighted average value, and perform multiplicative coupling processing on the Gaussian weighted average value and the detection temperature correction factor to obtain the artifact correction temperature of each third-level confidence region after correction; Jointly mark the artifact correction temperatures of each first-level confidence region, each second-level confidence region, and each third-level confidence region after correction as the artifact correction temperature of each region.

6. The intelligent analysis method for substation video operation identified by artificial intelligence according to claim 5, wherein: The steps for obtaining the detection reference temperature of the video operation are as follows: Obtain the preset weighting factors for each level of confidence region in the database, and the weighting factors for each level of confidence region include the weighting factor for the first-level confidence region, the weighting factor for the second-level confidence region, and the weighting factor for the third-level confidence region; The artifact correction temperatures of each first-level confidence region, the artifact correction temperatures of each second-level confidence region, and the artifact correction temperatures of each third-level confidence region after correction are respectively averaged to obtain the temperature averages of each level of confidence region. Then, weighted analysis is performed on the temperature averages of each level of confidence region based on the first-level confidence region weighting factor, the second-level confidence region weighting factor, and the third-level confidence region weighting factor, and multi-dimensional nesting is carried out to obtain the video operation detection reference temperature.

7. The intelligent analysis method for substation video operations identified by artificial intelligence according to claim 1, characterized in that: Obtain the operating state parameters of the substation circuit breaker, and fuse with the video operation detection reference temperature for discrimination, and thus analyze and obtain the video operation detection temperature. The specific method is as follows: Obtain the operating state parameters of the substation circuit breaker, and the operating state parameters of the substation circuit breaker include the abnormal verification parameters and mechanical abnormal verification parameters of the substation circuit breaker; The abnormal verification parameters of the substation circuit breaker include the loop resistance and load current of the substation circuit breaker; The mechanical abnormal verification parameters include the arc frequency and mechanical frequency inside the substation circuit breaker; Obtain a calibration reference set, and the calibration reference set includes a loop resistance reference value, a load current reference value, an arc frequency reference value, and a mechanical frequency reference value; The operating state parameters of the substation circuit breaker and the calibration reference set are respectively compared and analyzed, and the corresponding weighting factors are introduced to obtain the operating state trade-off index of the substation circuit breaker; Obtain the ambient temperature; Obtain each preset ambient temperature range in the database and the corresponding reference ambient temperature adjustment factor for each ambient temperature range, and compare with the ambient temperature. If the ambient temperature is within a certain preset ambient temperature range, obtain the reference ambient temperature adjustment factor corresponding to this range as the ambient temperature adjustment factor; Perform ambient factor correction on the video operation detection reference temperature based on the ambient temperature adjustment factor to obtain the first video operation detection temperature; Obtain the preset substation circuit breaker operating state trade-off threshold range in the database, and compare with the substation circuit breaker operating state trade-off index. If the substation circuit breaker operating state trade-off index is within the substation circuit breaker operating state trade-off threshold range, take the first video operation detection temperature as the video operation detection temperature, otherwise perform correction based on the first video operation detection temperature to obtain the video operation detection temperature.

8. The intelligent analysis method for substation video operation identified by artificial intelligence according to claim 7, characterized in that: The specific method for performing correction based on the first video operation detection temperature to obtain the video operation detection temperature is as follows: Obtain the maximum value and minimum value of the substation circuit breaker operating state trade-off threshold range, and compare with the substation circuit breaker operating state trade-off index; If the substation circuit breaker operating state trade-off index is less than the minimum value of the range, analyze and obtain the first deviation coefficient of the operating state, and perform downward correction on the first video operation detection temperature based on the first deviation coefficient of the operating state to obtain the video operation detection temperature; If the substation circuit breaker operating state trade-off index is greater than the maximum value of the range, analyze and obtain the second deviation coefficient of the operating state, and perform upward correction on the first video operation detection temperature based on the second deviation coefficient of the operating state to obtain the video operation detection temperature.

9. The intelligent analysis method for substation video operations identified by artificial intelligence according to claim 8, characterized in that: It also includes: Obtain the operation status deviation coefficient, and accordingly adjust the video operation parameters of the intelligent operation robot. The specific method is as follows: Obtain the operation status deviation coefficient, and accordingly adjust the video operation parameters of the intelligent operation robot. The operation status deviation coefficient includes the first operation status deviation coefficient and the second operation status deviation coefficient; The video operation parameters include the aperture f value and the focal length; If the operation status deviation coefficient is the first operation status deviation coefficient, adjust the video operation parameters upward based on the operation status deviation coefficient; If the operation status deviation coefficient is the second operation status deviation coefficient, adjust the video operation parameters downward based on the operation status deviation coefficient.

10. A system applying the intelligent analysis method for substation video operations identified by artificial intelligence as described in any one of claims 1-9, characterized in that It includes: The surrounding environment analysis module, the influence analysis module, the temperature preliminary correction module, and the temperature depth correction module; Among them, the surrounding environment analysis module is used to obtain the surrounding environment influence parameters and analyze the obtained surrounding environment influence driving value after the intelligent operation robot receives the monitoring operation signal; The influence analysis module is used to use the intelligent operation robot to obtain the working pictures of the substation circuit breaker during video operation, divide them into several regions, and analyze the affected values of each region; The temperature preliminary correction module is used to divide each confidence level region based on the affected values of each region, match the infrared reflection artifact correction scheme for each region, perform infrared reflection artifact correction to obtain the artifact correction temperature of each region, and process to obtain the video operation detection reference temperature; The temperature depth correction module is used to obtain the operation status parameters of the substation circuit breaker, fuse and judge the video operation detection reference temperature, thereby analyzing the obtained video operation detection temperature and uploading it to the background data management center for display.

Images