Multi-source data fusion isolation switch misoperation risk assessment method and system

Abstract

The invention discloses a multi-source data fusion isolation switch misoperation risk assessment method and system, and relates to the technical field of isolation switch misoperation risk management. The multi-source data fusion isolation switch misoperation risk assessment method comprises the following steps: monitoring isolation switch misoperation interference feedback; misoperation and accuracy monitoring; and carrying out abnormal superposition interference optimization judgment. According to the method, misoperation interference feedback is carried out on the isolating switch, whether misoperation and accuracy feedback are carried out or not is judged, if misoperation and accuracy feedback are carried out, accuracy feedback and optimization are carried out based on a misoperation and accuracy feedback result, and if misoperation and accuracy feedback are not carried out, optimization is carried out. If yes, fusion data accuracy analysis is carried out, and whether abnormal superposition interference optimization is carried out or not is judged, so that the effect of improving the accuracy of the misoperation risk assessment management of the multi-source data fusion isolating switch is achieved, and the problem that the accuracy of the misoperation risk assessment management of the multi-source data fusion isolating switch is low in the prior art is solved.

Description

Technical Field

[0001] The present invention relates to the technical field of isolating switch misoperation risk management, and in particular to an isolating switch misoperation risk assessment method and system based on multi-source data fusion. Background Art

[0002] Risk assessment of disconnector misoperation plays a vital role in power system operation. By integrating information from different data sources, it provides a comprehensive and accurate risk assessment for the safe operation of disconnectors, thereby effectively preventing misoperation accidents. The specific assessment process is as follows: First, multi-source data acquisition is performed. Existing technologies use multiple cameras deployed in the operation area to collect real-time visual recognition data of disconnectors, including misoperation behaviors (such as under-load pulling and closing), equipment status (real-time identification of contact closure gap, insulator surface damage, etc.), and environmental factors. Simultaneously collected limit feature data includes switch status signals (open, closed, and intermediate states) collected by limit sensors, trigger timing signals (opening trigger time, closing completion time), and mechanical travel data (moving contact travel length, in-position feedback signal). Then, multi-source data preprocessing is performed. After spatiotemporal alignment and feature extraction of multi-source data, the visual recognition results (contact opening distance, safety distance, etc.) are fused with limit features (opening and closing delay, current fluctuation, etc.) based on a Bayesian neural network. Finally, the fused results are input into a dynamic risk assessment model, such as the Spatial Temporal Graph Convolution (ST-GCN). The system can also use neural networks (e.g., LSTM) to detect device status faults and output the device risk level.

[0003] For example, the Chinese invention patent with the announcement number CN111639795B discloses a method for planning intelligent inspection tasks for substation robots, including: setting inspection tasks according to the type and quantity of inspection equipment required in the substation, and planning inspection routes according to different inspection tasks; inspection tasks include visible light diagnosis task points, appearance inspection task points, infrared diagnosis task points and sound diagnosis task points, visible light diagnosis task points include reading the mark identification of inspection equipment with instruments and checking whether the isolation switches are in place for inspection equipment with isolation switches, appearance inspection task points include appearance inspection of inspection equipment with external insulation, outer casing and respirator, infrared diagnosis task points include point temperature measurement detection, line temperature measurement detection, regional maximum temperature measurement detection and regional temperature distribution temperature measurement detection; the inspection route is an optimal inspection path with the robot charging position as the starting point, which includes all inspection task points in the inspection task.

[0004] For example, the Chinese invention patent with announcement number CN105321039B discloses an online monitoring data management system and method for an isolating switch, including: a data storage module for classifying and storing various raw data collected by the monitoring system; a data processing module for processing various raw data in the data storage module according to a user-defined calculation method or an original preset method, and comparing the processed data with the original data; a data diagnosis module for analyzing the raw data and processed data in the data storage module according to standard parameters, determining whether there is a fault in the isolating switch, and providing fault handling advice based on the contents of the fault fingerprint library.

[0005] The above technology has at least the following technical problems: During multi-source data collection, outdoor disconnectors may become loose due to long-term environmental erosion and mechanical wear, exacerbating misoperation. For example, the impact force generated during the disconnector opening or closing process prevents the camera from stably capturing the target outline, resulting in blurred images captured by the camera, reducing the quality of feature extraction, and adding more noise to the characteristic values ​​such as contact opening distance and safety distance output by visual recognition, directly interfering with the accuracy of the visual recognition results. At the same time, limit signals also have the risk of errors or failures. Looseness can indirectly cause contact jitter and hysteresis in the limit sensor, resulting in deviations from key timing characteristics such as the opening and closing triggering times and the in-position feedback signals. This will cause the limit characteristics to show opening and closing delays or timing anomalies. This, combined with the visual feature noise, further leads to deviations in the accuracy of the analysis results (such as opening delay) when analyzing disconnector misoperation based on the fused visual recognition data and limit feature data. This leads to low accuracy in the risk assessment and management of disconnector misoperation based on multi-source data fusion. Summary of the Invention

[0006] In order to solve the technical problem of low accuracy in the risk assessment and management of isolating switch misoperation based on multi-source data fusion in the prior art, the present invention provides a method and system for isolating switch misoperation risk assessment based on multi-source data fusion. The technical solution is as follows: On the one hand, a multi-source data fusion is provided for risk assessment of misoperation of isolating switches, which includes: in the process of multi-source data collection, performing misoperation interference feedback on the isolating switch and outputting misoperation interference feedback results for reflecting the interference of misoperation of the isolating switch on the data fusion process, judging whether to perform misoperation and accuracy feedback, the misoperation and accuracy feedback being used to evaluate the effect of the misoperation interference feedback results of the isolating switch on the collection qualification of visual recognition data and limit feature data; if misoperation and accuracy feedback is performed, accuracy feedback and optimization are performed based on the misoperation and accuracy feedback results for reflecting the visual recognition accuracy and limit feature accuracy output by the misoperation and accuracy feedback, the accuracy feedback and optimization are used to improve the anti-interference ability of visual recognition and limit feature collection to misoperation of the isolating switch; if misoperation and accuracy feedback is not performed, fusion data accuracy analysis is performed and based on the output fusion data accuracy analysis results for reflecting the qualified situation of data fusion, judging whether to perform abnormal superposition interference optimization to reduce the input noise of visual recognition data and limit feature data.

[0007] On the other hand, the multi-source data fusion isolating switch misoperation risk assessment system is applied as the multi-source data fusion isolating switch misoperation risk assessment method, including: an isolating switch misoperation interference feedback monitoring module, an misoperation and accuracy monitoring module and an abnormal superposition interference optimization judgment module; the isolating switch misoperation interference feedback monitoring module is used to perform isolating switch misoperation interference feedback during the multi-source data acquisition process and output an isolating switch misoperation interference feedback result for reflecting the interference of the isolating switch misoperation on the data fusion process, and judge whether to perform misoperation and accuracy feedback; the misoperation and accuracy monitoring module is used to perform accuracy feedback and optimization based on the misoperation and accuracy feedback result for reflecting the visual recognition accuracy and limit feature accuracy; the abnormal superposition interference optimization judgment module is used to perform fusion data accuracy analysis if no misoperation and accuracy feedback is performed and judge whether to perform abnormal superposition interference optimization to reduce the input noise of the visual recognition data and limit feature data based on the output fusion data accuracy analysis result for reflecting the qualified status of data fusion.

[0008] The beneficial effects brought about by the technical solution provided by the embodiment of the present invention include at least: 1. By providing interference feedback on misoperation of the isolating switch and judging whether to perform misoperation and accuracy feedback, it is helpful to accurately locate the interference points and impact degree of misoperation of the isolating switch on the data fusion process, and provide a clear judgment benchmark for subsequent targeted processing of data fusion anomalies, avoiding resource waste caused by blind optimization. If misoperation and accuracy feedback are performed, accuracy feedback and optimization are performed, which helps to improve the accuracy of visual recognition and the reliability of limit feature judgment in the isolating switch data fusion process. If misoperation and accuracy feedback are not performed, the fusion data accuracy analysis is performed and based on the output fusion data accuracy analysis results, it is judged whether to perform abnormal superposition interference optimization, which helps to timely check and deal with abnormal superposition interference problems that may exist in the data fusion process, and provide reliable data support for isolating switch operation status monitoring and operation and maintenance decision-making, thereby helping to improve the accuracy of misoperation risk assessment management of isolating switches fused with multi-source data, and solve the problem of low accuracy of misoperation risk assessment management of isolating switches fused with multi-source data in the existing technology.

[0009] 2. By first comparing whether the interference factor of unqualified opening error operation is greater than the interference factor of unqualified closing error operation, and then deciding whether to base it on the unqualified opening error operation interference value or the unqualified closing error operation interference value, or based on the unqualified opening error operation interference value and the unqualified closing error operation interference value at the same time, and performing harmonic average processing with the visual recognition accuracy value or the limit feature accuracy value, compared with the single judgment and analysis based on a single parameter in the existing technology, it helps to improve the comprehensive coverage of different types of unqualified error operation interference of disconnectors, avoid the analysis deviation caused by the existing technology relying only on a single parameter, and the problems of unclear optimization direction and waste of resources due to the single analysis dimension, and improve the overall reliability of disconnector data fusion.

[0010] 3. By judging whether the interference data of the misoperation of the disconnector meets the qualified conditions of the misoperation interference of the disconnector, if not, provide feedback on the misoperation and accuracy; if it meets, obtain the corresponding qualified visual recognition data and qualified limit feature data, and perform fusion data accuracy analysis, it helps to pre-judge the qualification of the misoperation interference data of the disconnector, directly eliminate the influence of unqualified interference data on the core data (visual recognition data and limit feature data), ensure that the marked qualified visual recognition data and qualified limit feature data have a reliable analysis basis, avoid interference data from contaminating the subsequent fusion process, and thus help to reduce the probability of abnormalities in data fusion from the source.

[0011] 4. First determine whether the monitored disconnector misoperation interference data meets the qualified conditions for disconnector misoperation interference. If it does not meet the qualified conditions for disconnector misoperation interference, provide feedback on misoperation and accuracy. If it meets the conditions, continue to monitor the number of misoperations. If the monitored number of misoperations is greater than the preset maximum total number of misoperations, send a maintenance reminder to the preset personnel. Otherwise, perform fusion data accuracy analysis based on visual recognition data and limit feature data. Since the system may fail and indirectly cause the monitored disconnector misoperation interference data to be unqualified, precise processing and early warning based on different scenarios can help avoid the lag of traditional operation and maintenance, shorten troubleshooting time, improve operation and maintenance efficiency, ensure that the visual recognition and limit feature data used for fusion analysis are highly reliable, and avoid efficiency waste caused by indiscriminate processing. BRIEF DESCRIPTION OF THE DRAWINGS

[0012] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0013] Figure 1 This is a flow chart of a method for assessing the risk of misoperation of an isolating switch using multi-source data fusion provided by an embodiment of the present invention; Figure 2 This is a general overview of the disconnector misoperation risk assessment method based on multi-source data fusion provided by an embodiment of the present invention; Figure 3 1. It is a schematic diagram of the error operation and accuracy feedback process of the disconnector error operation risk assessment method based on multi-source data fusion provided by an embodiment of the present invention; Figure 4 1 is a schematic diagram of the structure of the multi-source data fusion isolating switch misoperation risk assessment system provided by an embodiment of the present invention; Figure 5 This is the operational risk interface 1 provided in the embodiment of the present application; Figure 6 This is the second operational risk interface provided in the embodiment of this application. DETAILED DESCRIPTION

[0014] The technical solution of the present invention is described below in conjunction with the accompanying drawings.

[0015] In the embodiments of the present invention, words such as "exemplarily" and "for example" are used to indicate examples, illustrations, or explanations. Any embodiment or design described as an "exemplary" in the present invention should not be interpreted as being preferred or advantageous over other embodiments or designs. Rather, the use of the word "exemplary" is intended to present concepts in a concrete manner. Furthermore, in the embodiments of the present invention, "and / or" can mean both or either of the two.

[0016] In the embodiments of the present invention, the terms "image" and "picture" may sometimes be used interchangeably. It should be noted that, when the distinction is not emphasized, the meanings they convey are the same. The terms "of," "corresponding," and "corresponding" may sometimes be used interchangeably. It should be noted that, when the distinction is not emphasized, the meanings they convey are the same.

[0017] In order to make the technical problems, technical solutions and advantages to be solved by the present invention clearer, a detailed description will be given below with reference to the accompanying drawings and specific embodiments.

[0018] Example 1: The present invention provides a multi-source data fusion isolation switch misoperation risk assessment method. Figure 1 The flowchart of the multi-source data fusion isolation switch misoperation risk assessment method is shown. The processing flow of the method may include the following steps: Isolating switch misoperation interference feedback monitoring: During the multi-source data collection process, isolating switch misoperation interference feedback is performed and the isolating switch misoperation interference feedback result is output to reflect the interference of isolating switch misoperation on the data fusion process. Based on the isolating switch misoperation interference feedback result, it is determined whether to perform misoperation and accuracy feedback. The misoperation and accuracy feedback is used to evaluate the effect of the isolating switch misoperation interference feedback result on the collection qualification of visual recognition data and limit feature data. The isolating switch misoperation interference feedback monitoring helps to timely capture the interference of isolating switch misoperation on the multi-source data fusion process, clarify the interference effect, and provide a basis for determining whether to start misoperation and accuracy evaluation in the future, so as to ensure that the interference in the early stage of data fusion is perceptible and quantifiable.

[0019] Misoperation and accuracy monitoring: If misoperation and accuracy feedback is performed, accuracy feedback and optimization will be performed based on the misoperation and accuracy feedback results that reflect the visual recognition accuracy and limit feature accuracy output. Accuracy feedback and optimization are used to improve the anti-interference ability of visual recognition and limit feature acquisition against misoperation of the disconnector; through misoperation and accuracy monitoring, it helps to improve the anti-interference ability of visual recognition and limit feature accuracy against misoperation of the disconnector, and ensure the qualification of the core acquisition data.

[0020] Abnormal superposition interference optimization judgment: If no error operation and accuracy feedback are performed, the fusion data accuracy analysis is performed and based on the output fusion data accuracy analysis results that reflect the qualified status of data fusion, it is judged whether abnormal superposition interference optimization is required to reduce the input noise of visual recognition data and limit feature data; abnormal superposition interference optimization judgment helps to accurately judge whether abnormal superposition interference optimization is required, thereby effectively reducing the input noise of visual recognition and limit feature data and ensuring data fusion stability.

[0021] like Figure 2 As shown in FIG, it is a general overview diagram of the multi-source data fusion isolation switch misoperation risk assessment method provided in the embodiment of the present application, which is composed of Figure 2 It can be seen that: when the monitored disconnector misoperation interference data meets the qualified conditions for disconnector misoperation interference, the fusion data accuracy analysis is performed, otherwise the misoperation and accuracy feedback is performed to obtain the unqualified opening misoperation interference factor and the unqualified closing misoperation interference factor, and accuracy feedback and optimization are performed based on the unqualified opening misoperation interference value and the unqualified closing misoperation interference value. After the accuracy feedback and optimization are completed, the fusion data accuracy analysis is performed to obtain the fusion noise anomaly value. When the fusion noise anomaly value is greater than the preset fusion noise anomaly value, abnormal superposition interference optimization is performed, otherwise the corresponding disconnector misoperation interference data is marked as qualified risk assessment management data, and the behavior risk level is output based on the qualified risk assessment management data.

[0022] Before designing the multi-source data fusion disconnector misoperation risk assessment method provided in this application, a database for storing various setting data is established. The database includes but is not limited to preset opening misoperation interference values, preset closing misoperation interference values, preset maximum total number of misoperations, etc., and various numerical values ​​are directly set by technical personnel.

[0023] In this embodiment, the integrated effects of interference feedback monitoring of misoperation of the isolating switch, misoperation and accuracy monitoring, and optimization judgment of abnormal superimposed interference are interconnected, which helps to realize the full-process multi-source data collection and fusion guarantee from interference monitoring to accuracy optimization and then to noise control, comprehensively improves the reliability and anti-interference capability of the monitoring data related to the isolating switch, and provides high-quality data support for accurate judgment of the operating status of the isolating switch.

[0024] Furthermore, the specific process of performing the feedback of the misoperation interference of the isolating switch is as follows: obtaining the misoperation interference data of the isolating switch used to reflect the interference degree of the misoperation of the isolating switch within the specified misoperation monitoring time period; judging whether the misoperation interference data of the isolating switch meets the qualified conditions for misoperation interference of the isolating switch: if not, marking the corresponding misoperation interference data of the isolating switch as unqualified misoperation interference data of the isolating switch, and performing misoperation and accuracy feedback; if compliant, marking the visual recognition data corresponding to the misoperation interference data of the isolating switch that meets the qualified conditions for misoperation interference of the isolating switch as qualified visual recognition data, marking the corresponding limit feature data as qualified limit feature data, and performing fusion data accuracy analysis; unqualified misoperation interference data of the isolating switch includes unqualified opening misoperation interference value and unqualified closing misoperation interference value; misoperation interference data of the isolating switch includes unqualified opening misoperation interference value and unqualified closing misoperation interference value; misoperation interference data of the isolating switch includes unqualified opening misoperation interference value and unqualified closing misoperation interference value. The interference qualification condition indicates that the opening misoperation interference value is less than the preset opening misoperation interference value, and the closing misoperation interference value is less than the preset closing misoperation interference value, wherein the preset opening misoperation interference value is represented by the average value of the opening misoperation interference value in the historical time period, and the preset closing misoperation interference value is represented by the average value of the closing misoperation interference value in the historical time period; the designated misoperation monitoring time period represents the preset time period corresponding to the disconnector misoperation interference feedback; the disconnector misoperation interference data includes the opening misoperation interference value for reflecting the degree of deviation in opening completion and the closing misoperation interference value for reflecting the degree of deviation in closing completion; the disconnector opening time is monitored by a timer, and the difference between it and the preset opening time is used as the opening misoperation interference value; the disconnector closing time is monitored by a timer, and the difference between it and the preset closing time is used as the closing misoperation interference value.

[0025] In this embodiment, by marking the visual recognition data corresponding to the disconnector misoperation interference data that meets the qualified conditions for disconnector misoperation interference as qualified visual recognition data, marking the corresponding limit feature data as qualified limit feature data, and performing fusion data accuracy analysis, it is helpful to accurately screen out high-quality collected data (qualified visual recognition data and qualified limit feature data) that is less affected by misoperation interference, providing a reliable data basis for subsequent data fusion, and at the same time verifying the fusion effectiveness of the qualified data through fusion accuracy analysis to ensure the credibility of the data fusion results; when the disconnector misoperation interference data does not meet the qualified conditions for disconnector misoperation interference, performing misoperation and accuracy feedback is helpful to timely locate the collection unqualified problems of visual recognition data and limit feature data due to misoperation interference, and provide accurate feedback basis for subsequent targeted optimization of the collection mechanism and improvement of data collection anti-interference ability.

[0026] Furthermore, the misoperation and accuracy feedback includes the evaluation of the degree of misoperation interference of the disconnector and accuracy feedback and optimization; the evaluation of the degree of misoperation interference of the disconnector is used to evaluate the degree of influence of the unqualified disconnector misoperation interference data on the accuracy feedback and optimization. The specific process is as follows: the unqualified disconnector misoperation interference data is input into the misoperation interference degree mapping table, and the corresponding misoperation interference degree factor is read. The misoperation interference degree factor includes the unqualified opening misoperation interference factor and the unqualified closing misoperation interference factor, which are used to reflect the degree of influence of the unqualified disconnector misoperation interference data on the accuracy feedback and optimization; judgment is made based on the misoperation interference degree factor: when the unqualified opening misoperation interference factor is greater than the unqualified closing misoperation interference factor, accuracy feedback and optimization are reflected based on the unqualified opening misoperation interference value; when the unqualified opening misoperation interference factor is equal to the unqualified closing misoperation interference factor, accuracy feedback and optimization are performed based on the unqualified disconnector misoperation interference data; when the unqualified opening misoperation interference factor is less than the unqualified closing misoperation interference factor, accuracy feedback and optimization are performed based on the unqualified closing misoperation interference value.

[0027] like Figure 3 FIG. 1 is a flow chart of error operation and accuracy feedback of the multi-source data fusion isolation switch error operation risk assessment method provided by the embodiment of the present application, which is composed of Figure 3 It can be seen that: by inputting the unqualified disconnector misoperation interference data into the misoperation interference degree mapping table, the unqualified opening misoperation interference factor and the unqualified closing misoperation interference factor are obtained. When the unqualified opening misoperation interference factor is greater than the unqualified closing misoperation interference factor, the accuracy feedback and optimization are reflected based on the unqualified opening misoperation interference value. When the unqualified opening misoperation interference factor is equal to the unqualified closing misoperation interference factor, the accuracy feedback and optimization are performed based on the unqualified disconnector misoperation interference data. When the unqualified opening misoperation interference factor is less than the unqualified closing misoperation interference factor, the accuracy feedback and optimization are performed based on the unqualified closing misoperation interference value.

[0028] In an embodiment of the present application, several groups of mapping tables and mapping sets pre-constructed by designated personnel are retrieved from a database, including a misoperation interference degree mapping table, an exposure time adjustment mapping table, an aperture adjustment mapping table, a sampling window length mapping table, a fusion data accuracy mapping table, a sensitivity mapping set, a sensor gain mapping set, etc. The mapping relationship is dynamic, supporting both one-to-one correspondence of single-single parameters and multiple-to-one correspondence of multiple-single parameters; for example, by inputting the misoperation interference data of unqualified disconnectors in a historical time period, the performance reflection value of the metering pump, the combination of the visual recognition accuracy feedback value and the exposure frequency of the misoperation behavior camera, the combination of the visual recognition feedback deviation value and the camera focal length, the combination of the limit feature feedback deviation value and the number of sampling points of the opening and closing signals, the qualified fusion accuracy result, the combination of the fusion noise anomaly value and the ambient brightness, and the combination of the fusion noise anomaly value and the number of pixels of the misoperation behavior image into a machine learning model based on feature importance, such as a decision tree model, and obtaining corresponding weights or data by feature splitting, i.e., the misoperation interference degree factor, the exposure time adjustment value, etc., and correspondingly matching the data of the historical time period with the corresponding weights or data to obtain a mapping table and mapping set.

[0029] Specifically, the misoperation interference degree factor provided in this embodiment is determined based on the proportion of the corresponding unqualified isolating switch misoperation interference data, and is used to reflect the degree of influence of the unqualified isolating switch misoperation interference data on accuracy feedback and optimization. A one-to-one or many-to-one mapping relationship can be established between the unqualified isolating switch misoperation interference data and the corresponding misoperation interference degree factor; by inputting the unqualified isolating switch misoperation interference data obtained in real time into the corresponding misoperation interference degree mapping table, the corresponding misoperation interference degree factor is output according to the pre-set mapping relationship, and the value range is limited to the interval of 0-1.

[0030] Specifically, the specific process of accuracy feedback and optimization is as follows: when it is monitored that the interference factor of unqualified opening misoperation is greater than the interference factor of unqualified closing misoperation, the unqualified opening misoperation interference value used to reflect the interference degree of opening misoperation and the visual recognition accuracy value used to measure the interference degree of visual recognition accuracy are harmonized and averaged as the visual recognition accuracy feedback value, and the unqualified opening misoperation interference value and the limiting feature accuracy value used to measure the accuracy of the limiting feature are harmonized and averaged as the limiting feature accuracy feedback value. The larger the unqualified opening misoperation interference value is, the more serious the opening interference is, and the higher the visual recognition accuracy and the limiting feature accuracy are affected by the opening interference. By harmonizing and averaging the unqualified opening misoperation interference value used to reflect the interference degree of opening misoperation and the visual recognition accuracy value used to measure the interference degree of visual recognition accuracy, the unqualified opening misoperation interference value and the limiting feature accuracy value used to measure the accuracy of visual recognition accuracy are harmonized and averaged. The limit feature accuracy value that measures the accuracy of the limit feature is harmonized and averaged, which helps to achieve targeted focus on the strong interference scenario of the opening error operation, so that the accuracy feedback value of the visual recognition and the limit feature is more in line with the actual impact of the opening interference on data collection, and provides an accurate quantitative basis for the subsequent optimization of the camera imaging qualification and reduction of the limit feature delay deviation during the opening process; the imaging duration of the erroneous operation behavior image is monitored by a timer, and the difference between it and the preset erroneous operation behavior image imaging duration is used as the visual recognition accuracy value, which is used to reflect the qualification of the picture collected by the camera when the camera collects the image of the opening or closing process of the disconnector. The larger the visual recognition accuracy value, the greater the interference to the accuracy of the picture collected by the camera when the camera collects the image of the opening or closing process of the disconnector; the time difference between the limit feature being triggered and the trigger signal being detected and responded to is monitored by a timer as the limit feature accuracy value, which is used to reflect the delay deviation of the limit feature.

[0031] When it is monitored that the unqualified opening error operation interference factor is equal to the unqualified closing error operation interference factor, the result of harmonizing and averaging the unqualified opening error operation interference value, the unqualified closing error operation interference value and the visual recognition accuracy value is used as the visual recognition accuracy feedback value, and the result of harmonizing and averaging the unqualified opening error operation interference value, the unqualified closing error operation interference value and the limit feature accuracy value is used as the limit feature accuracy feedback value. At the same time, the unqualified opening error operation interference value and the unqualified closing error operation interference value are harmonized and averaged, which means that the opening interference and the closing interference are similar, and the visual recognition accuracy and the limit feature accuracy are affected by the opening interference and the closing interference. The degree is similar. The larger the unqualified opening error operation interference value and the unqualified closing error operation interference value, the greater the visual recognition accuracy feedback value and the feature accuracy feedback value may be. By harmonizing and averaging the unqualified opening error operation interference value, the unqualified closing error operation interference value and the limit feature accuracy value, the unqualified opening error operation interference value and the unqualified closing error operation interference value are harmonized and averaged, which helps to take into account the balanced interference scenarios of opening and closing error operations, and let the accuracy feedback value fully reflect the comprehensive impact of the two error operation interferences on visual recognition and limit feature acquisition, and provide comprehensive quantitative support for the synchronous optimization of data acquisition quality of opening and closing processes.

[0032] When it is monitored that the interference factor of unqualified opening misoperation is smaller than the interference factor of unqualified closing misoperation, the result of harmonized averaging of the unqualified closing misoperation interference value and the visual recognition accuracy value, which is used to reflect the interference degree of closing misoperation, is used as the visual recognition accuracy feedback value, and the result of harmonized averaging of the unqualified closing misoperation interference value and the limit feature accuracy value is used as the limit feature accuracy feedback value. This helps to accurately focus on the strong interference scenario of closing misoperation, so that the accuracy feedback value accurately matches the impact of closing interference on data acquisition, and provides a clear quantitative direction for targeted optimization of the camera image qualification during the closing process and reduction of limit feature delay deviation. The larger the unqualified closing misoperation interference value, the more serious the closing interference, and the more the visual recognition accuracy and limit feature accuracy are affected by closing interference.

[0033] It should be added that accuracy feedback and optimization also include visual recognition-limit feature accuracy feedback judgment, and the specific process is as follows: judgment is made based on the visual recognition accuracy feedback value and the limit feature accuracy feedback value: if the visual recognition accuracy feedback value is less than the preset visual recognition accuracy feedback value, visual recognition accuracy optimization is performed to improve the anti-interference ability of visual recognition to misoperation of the disconnector, otherwise a fusion data accuracy analysis is performed, wherein the preset visual recognition accuracy feedback value is represented by the average value of the visual recognition accuracy feedback value in the historical time period; if the limit feature accuracy feedback value is less than the preset limit feature accuracy feedback value, limit feature accuracy optimization is performed to improve the timing accuracy of the limit signal, otherwise a fusion data accuracy analysis is performed, wherein the preset limit feature accuracy feedback value is represented by the average value of the limit feature accuracy feedback value in the historical time period.

[0034] In this embodiment, specific accuracy feedback and optimization measures are determined based on the visual recognition accuracy feedback value and the limit feature accuracy feedback value obtained from the evaluation of the interference degree of misoperation of the disconnector, which helps to convert the quantitative interference evaluation results into targeted optimization actions, avoid the blindness of the optimization measures, and efficiently improve the ability of the two types of data collection to resist misoperation interference; through the interaction between the evaluation of the interference degree of misoperation of the disconnector and the accuracy feedback and optimization, the upper and lower parts are connected, which helps to form a closed-loop management from quantitative interference evaluation to precise optimization and improvement: the evaluation of the interference degree of misoperation of the disconnector provides a clear problem orientation and quantitative basis for accuracy feedback and optimization, and the accuracy feedback and optimization are implemented to solve the shortcomings found in the evaluation. The two work together to ensure the continuous qualification of visual recognition and limit feature data collection, thereby stabilizing the quality of multi-source data fusion and laying a solid data foundation for accurate monitoring of the operating status of the disconnector.

[0035] Furthermore, the specific process of visual recognition accuracy optimization is as follows: the visual recognition accuracy feedback value and the camera exposure frequency corresponding to the misoperation behavior directly read by the camera are input into the exposure time adjustment mapping table, and the exposure time adjustment value is read; the amplitude corresponding to the exposure time adjustment value is used as the adjustment step, and the exposure time is gradually reduced; the accuracy of the limit feature is optimized, specifically: the limit feature data is filtered based on the moving average filtering algorithm to suppress the high-frequency noise and instantaneous hysteresis in the sensor signal, and improve the timing accuracy and stability of the limit signal; the visual recognition accuracy optimization and the limit feature accuracy optimization also include visual recognition-limit feature qualification judgment, and the specific process is as follows: after the visual recognition accuracy optimization or the limit feature accuracy optimization is completed, it is judged whether the re-acquired visual recognition accuracy feedback value is still less than the preset visual recognition accuracy feedback value, and whether the limit feature accuracy feedback value is still less than the preset limit feature accuracy feedback value. If the visual recognition accuracy feedback value is still less than the preset visual recognition accuracy feedback value, obtain the information used to reflect the visual recognition accuracy. The visual recognition feedback deviation value of the accuracy deviation degree is obtained and the deviation-visual recognition accuracy optimization is performed, otherwise the fusion data accuracy analysis is performed. If the limiting feature accuracy feedback value is still less than the preset limiting feature accuracy feedback value, the limiting feature feedback deviation value used to reflect the accuracy deviation degree of the limiting feature is obtained and the deviation-limiting feature accuracy optimization is performed, otherwise the fusion data accuracy analysis is performed; the deviation-visual recognition accuracy optimization means providing reliable visual input for multi-source data fusion through dynamic aperture adjustment to improve the accuracy of misoperation risk assessment; the deviation-limiting feature accuracy optimization means suppressing transient noise interference by dynamically adjusting the sampling window length to extract more stable limiting features, thereby improving the accuracy of misoperation risk assessment; the visual recognition feedback deviation value is represented by the difference between the preset visual recognition accuracy feedback value and the visual recognition accuracy feedback value obtained after the visual recognition accuracy optimization is completed; the limiting feature feedback deviation value is represented by the difference between the preset limiting feature accuracy feedback value and the limiting feature accuracy feedback value obtained after the limiting feature accuracy optimization is completed.

[0036] It should be added that the combination of the visual recognition accuracy feedback value and the exposure frequency of the erroneous operation behavior camera provided in this embodiment establishes a one-to-one or many-to-one mapping relationship with the corresponding exposure time adjustment value; by inputting the combination of the visual recognition accuracy feedback value and the exposure frequency of the erroneous operation behavior camera collected in real time into the corresponding exposure time adjustment mapping table, the corresponding exposure time adjustment value is output according to the pre-set mapping relationship, and the value range is limited to the interval of 0-1.

[0037] In this embodiment, by using the amplitude corresponding to the exposure time adjustment value as the adjustment step and gradually reducing the exposure time, it is helpful to achieve smooth and controllable optimization of camera imaging parameters, avoid fluctuations in image quality caused by sudden changes in exposure time, accurately improve the imaging qualification of visual recognition data under interference from incorrect operations (such as reducing overexposure and improving image clarity), and provide a stable image basis for subsequent visual recognition accuracy; by performing visual recognition-limit feature qualification to determine whether to continue to take deviation-visual recognition accuracy optimization and deviation-limit feature accuracy optimization, it is avoided to over-optimize qualified data (such as causing resource waste or new deviations), and only accurately optimize unqualified data to ensure the necessity and efficiency of optimization measures; by using visual recognition feedback deviation value and limit feature feedback deviation value as feedback values ​​to perform deviation-visual recognition accuracy optimization and deviation-limit feature accuracy optimization, it is helpful to accurately locate the problem level of visual recognition and limit feature, so that the optimization action can target the root cause of deviation, and efficiently improve the accuracy and anti-interference ability of the two types of data collection.

[0038] Furthermore, the specific process of deviation-visual recognition accuracy optimization is as follows: the visual recognition feedback deviation value and the camera focal length directly read through the camera are input into the aperture adjustment mapping table to read the aperture adjustment value; the amplitude corresponding to the aperture adjustment value is used as the adjustment step, and the aperture is reduced step by step; if after the deviation-visual recognition accuracy optimization is completed, the visual recognition accuracy feedback value obtained again is not less than the preset visual recognition accuracy feedback value, then the fusion data accuracy analysis is performed, otherwise a visual recognition abnormality alarm is sent; by using the amplitude corresponding to the aperture adjustment value as the adjustment step, the aperture is reduced step by step, which helps to optimize the camera optical parameters smoothly and controllably, avoid sudden changes in the aperture causing drastic fluctuations in the depth of field or the amount of light entering the picture, and accurately improve the clarity of the visual recognition image under the interference of misoperation (such as enhancing picture details and reducing stray light interference), providing a high-quality imaging foundation for the optimization of visual recognition accuracy.

[0039] The specific process of optimizing the accuracy of the deviation-limit feature is as follows: input the limit feature feedback deviation value and the number of sampling points of the opening and closing signals monitored by the oscilloscope and spectrum analyzer into the sampling window length mapping table to read the sampling window length adjustment value; use the amplitude corresponding to the sampling window length adjustment value as the adjustment step, and increase the sampling window length step by step; if after the deviation-limit feature accuracy optimization is completed, if the limit feature accuracy feedback value obtained again is not less than the preset limit feature accuracy feedback value, then perform fusion data accuracy analysis, otherwise send a limit feature abnormality alarm; by using the amplitude corresponding to the sampling window length adjustment value as the adjustment step, gradually increasing the sampling window length, it helps to smoothly expand the sampling range of the limit feature data, reduce the impact of instantaneous noise on the sampling results, more fully capture the effective signal of the limit feature, improve the stability and accuracy of the limit feature data acquisition, and provide reliable data support for subsequent limit feature accuracy optimization.

[0040] Specifically, the specific process of performing fusion data accuracy analysis is as follows: obtaining a fusion noise anomaly value used to reflect the degree of noise anomaly in the fusion process of visual recognition data and limit feature data; making a judgment based on the fusion noise anomaly value: if the fusion noise anomaly value is greater than the preset fusion noise anomaly value, perform abnormal superposition interference optimization, otherwise mark the corresponding disconnector misoperation interference data as qualified risk assessment management data; the qualified risk assessment management data is used to input the preset risk assessment model to obtain the output behavior risk level of the disconnector misoperation analysis, for example, the qualified risk assessment management data is input into the ST-GCN model to output the behavior risk level; the noise intensity of the corresponding fusion signal in the fusion process of visual recognition data and limit feature data is monitored by a spectrum analyzer and a sound level meter, and the difference between it and the preset fusion noise intensity is used as the fusion noise anomaly value.

[0041] It should be added that the combination of the visual recognition feedback deviation value and the camera focal length, as well as the combination of the limit feature feedback deviation value and the number of sampling points of the opening and closing signals provided in this embodiment, establish a one-to-one or many-to-one mapping relationship with the corresponding aperture adjustment value and the sampling window length adjustment value; by inputting the combination of the visual recognition feedback deviation value and the camera focal length, as well as the combination of the limit feature feedback deviation value and the number of sampling points of the opening and closing signals collected in real time into the corresponding aperture adjustment mapping table and the sampling window length mapping table, the corresponding aperture adjustment value and the sampling window length adjustment value are output according to the pre-set mapping relationship, and the value range is limited to the interval of 0-1.

[0042] In this embodiment, if the visual recognition accuracy feedback value re-obtained after the deviation-visual recognition accuracy optimization and the deviation-limiting feature accuracy optimization is not less than the preset visual recognition accuracy feedback value, or the limiting feature accuracy feedback value is not less than the preset limiting feature accuracy feedback value, then a fusion data accuracy analysis is performed to obtain qualified risk assessment management data, which helps to verify the actual effect of the deviation-visual recognition accuracy optimization and the deviation-limiting feature accuracy optimization, and further evaluate the qualified risks of the visual recognition data and limiting feature data after meeting the standards in the fusion process, identify possible problems in the fusion link in advance, provide a quantitative basis for risk control of multi-source data fusion quality, and ensure the reliability of the final fusion result.

[0043] Furthermore, the specific process of optimizing abnormal superposition interference is as follows: input the qualified fusion accuracy result into the fusion data accuracy mapping table to obtain the fusion-accuracy factor used to reflect the degree of influence of the misoperation of the disconnector on the fusion process of the visual recognition data and the limit feature data. The qualified fusion accuracy result includes the misoperation interference data of the disconnector and the fusion noise anomaly value. The fusion-accuracy factor includes the fusion-visual recognition degree factor and the fusion-limit feature degree factor. Judgment is made based on the fusion-accuracy factor: if the fusion-visual recognition degree factor is greater than the fusion-limit feature degree factor, only the fusion-visual recognition optimization for reducing the noise abnormality superposition of the visual recognition data is executed, which helps to achieve targeted focusing on the problem of interference of the visual recognition data caused by the misoperation of the disconnector, concentrate resources to reduce its noise abnormality superposition, avoid over-optimization of the limit feature data with smaller interference impact, and improve efficiency. Improve the anti-interference ability of visual recognition data in the fusion process; if the fusion-visual recognition degree factor is less than the fusion-limit feature degree factor, only the fusion-limit feature optimization used to reduce the noise anomaly superposition of the limit feature data is executed, which helps to accurately locate the interference shortcomings of the limit feature data caused by the misoperation of the isolation switch, and reduce its noise anomaly superposition in a targeted manner, avoiding the waste of resources on visual recognition data with less interference impact, and effectively improving the stability of the limit feature data in the fusion process; if the fusion-visual recognition degree factor is equal to the fusion-limit feature degree factor, executing the fusion-visual recognition optimization and the fusion-limit feature optimization at the same time helps to take into account the balanced interference problem of the visual recognition data and the limit feature data caused by the misoperation of the isolation switch, and simultaneously reduce the noise anomaly superposition of the two types of data, ensuring that the anti-interference ability of the two is improved simultaneously during the fusion process, and ensuring the balance and reliability of the overall fusion data quality.

[0044] Specifically, the fusion-accuracy factor provided in this embodiment is determined based on the proportion of the corresponding qualified fusion accuracy results, and is used to reflect the degree of influence of the qualified fusion accuracy results on the fusion process of the visual recognition data and the limit feature data caused by the misoperation of the disconnector. A one-to-one or many-to-one mapping relationship can be established between the qualified fusion accuracy results and the corresponding fusion-accuracy factors; by inputting the qualified fusion accuracy results obtained in real time into the corresponding fusion data accuracy mapping table, the corresponding fusion-accuracy factor is output according to the pre-set mapping relationship, and the value range is limited to the interval of 0-1.

[0045] Fusion-visual recognition optimization, specifically: the sensitivity adjustment value is obtained by centrally mapping the fusion noise anomaly value and the ambient brightness input monitored by the illuminance meter, and the corresponding amplitude is used as the adjustment step to reduce the sensitivity step by step. This helps to smoothly and accurately reduce the camera sensitivity and avoid the superposition of image noise caused by high sensitivity. At the same time, it adapts to the ambient light conditions, improves the cleanliness of the visual recognition image, and reduces noise interference for subsequent data fusion. When the fusion-visual recognition optimization is completed and the fusion noise anomaly value is monitored to be still not greater than the preset fusion noise anomaly value, the corresponding isolation switch misoperation interference data will be marked as qualified risk assessment management data, otherwise a fusion-visual recognition optimization abnormality prompt will be sent.

[0046] Specifically, the combination of the fused noise outlier value and the ambient brightness, and the combination of the fused noise outlier value and the number of pixels in the erroneous operation behavior image provided in this embodiment establish a one-to-one or many-to-one mapping relationship with the corresponding sensitivity adjustment value and the sensor gain adjustment value; by inputting the combination of the fused noise outlier value and the ambient brightness, and the combination of the fused noise outlier value and the number of pixels in the erroneous operation behavior image collected in real time into the corresponding sensitivity mapping set and the sensor gain mapping set, the corresponding sensitivity adjustment value and the sensor gain adjustment value are output according to the pre-set mapping relationship, and the value range is limited to the interval of 0-1.

[0047] Fusion-limit feature optimization, specifically: input the fusion noise outlier value and the number of pixels of the erroneous operation behavior image monitored by image analysis software, such as Adobe Photoshop, into the sensor gain mapping to centrally obtain the sensor gain adjustment value, and use its corresponding amplitude as the adjustment step to gradually increase the sensor gain, which helps to smoothly amplify the effective signal (such as the erroneous operation behavior detail signal). While ensuring the clarity of the pixel features of the erroneous operation image, it combats fusion noise interference, improves the accuracy of visual recognition data in capturing erroneous operation behaviors, and provides a more reliable image signal foundation for data fusion. When the fusion-limit feature optimization is completed and the fusion noise outlier value is monitored to be still no greater than the preset fusion noise outlier value, the corresponding isolating switch erroneous operation interference data will be marked as qualified risk assessment management data, otherwise a fusion-limit feature optimization abnormality prompt will be sent.

[0048] like Figure 4 As shown, it is a structural schematic diagram of the multi-source data fusion isolating switch misoperation risk assessment system provided by an embodiment of the present application, and is applied as a multi-source data fusion isolating switch misoperation risk assessment method, which is characterized by including: an isolating switch misoperation interference feedback monitoring module, an misoperation and accuracy monitoring module and an abnormal superposition interference optimization judgment module; the isolating switch misoperation interference feedback monitoring module is used to perform isolating switch misoperation interference feedback during the multi-source data acquisition process and output an isolating switch misoperation interference feedback result for reflecting the interference of the isolating switch misoperation on the data fusion process, and judge whether to perform misoperation and accuracy feedback based on the isolating switch misoperation interference feedback result; the misoperation and accuracy monitoring module is used to perform accuracy feedback and optimization based on the misoperation and accuracy feedback output for reflecting the visual recognition accuracy and limit feature accuracy; the abnormal superposition interference optimization judgment module is used to perform fusion data accuracy analysis if no misoperation and accuracy feedback is performed and judge whether to perform abnormal superposition interference optimization to reduce the input noise of the visual recognition data and the limit feature data based on the output fusion data accuracy analysis result for reflecting the qualified status of the data fusion.

[0049] In this embodiment, a judgment is first made based on the fusion-visual recognition degree factor and the fusion-limiting feature degree factor, and then the specific measures of fusion-visual recognition optimization and fusion-limiting feature optimization are decided. The two are interrelated, which helps to achieve the precise positioning of the main interference shortcomings of visual recognition data and limiting feature data in the fusion process based on the quantified fusion-visual recognition degree factor and the fusion-limiting feature degree factor, avoid the waste of resources caused by indiscriminate optimization, and ensure that the optimization action is strongly correlated with the actual interference situation, effectively reduce the noise anomaly superposition of the two types of data, and ultimately ensure the accuracy and stability of the multi-source data fusion results.

[0050] like Figure 5 As shown, this is the operational risk interface 1 provided by the embodiment of the present application, such as Figure 6 As shown, the second operational risk interface provided by an embodiment of the present application is used to implement the operational risk link function in the risk type management module in the power risk management system; the power risk management system includes a risk type management module, a risk identification module, a risk assessment module and a system management module, wherein the risk type management module includes equipment risks, operational risks, power grid operation risks and environmental and external risks, the risk identification module includes risk data collection and automatic risk identification, the risk assessment module includes risk level assessment, risk trend prediction and risk alarm, and the system management module includes user and authority management, system configuration and database.

[0051] Depend on Figure 5 It can be seen that the currently monitored power equipment is the disconnector (No. 17), the current error operation feedback progress is 50%, the visual recognition status light and the limit feature status light are both red, and the status is abnormal. Click Modify Configuration to enter the second operation risk interface. Figure 6 It can be seen that the current optimization progress is displayed as 50%, and the error operation feedback progress is updated to 80%.

[0052] Example 2: Based on Example 1, the specific process of feedback on misoperation interference of the isolating switch is as follows: if the monitored misoperation interference data of the isolating switch does not meet the qualified conditions for misoperation interference of the isolating switch, feedback on misoperation and accuracy is performed; if it meets the conditions, it is determined whether the number of monitored misoperations is greater than the preset maximum total number of misoperations. If so, a maintenance prompt is sent to the preset personnel, otherwise a fusion data accuracy analysis is performed based on the visual recognition data and the limit feature data; the total number of opening and closing of the isolating switch within the specified misoperation monitoring time period is monitored by a counter as the number of misoperations, and the preset maximum total number of misoperations is represented by the maximum value of the number of misoperations in the historical time period.

[0053] In this embodiment, embodiment 2 adds a secondary judgment of the number of erroneous operations. Even if the interference data meets the qualification conditions, if the number of erroneous operations exceeds the preset maximum total number of erroneous operations, additional processing is triggered, thereby avoiding the potential risk of qualified single interference data but high-frequency erroneous operations (for example, the disconnector may have hidden problems such as operating mechanism jamming and inductive sluggishness. Single interference does not exceed the standard but frequent occurrence will accumulate risks). By sending maintenance reminders to preset personnel, high-frequency erroneous operations are often not simple data collection problems, but are more likely to point to mechanical failures of the disconnector itself (such as abnormal opening and closing mechanisms) or loopholes in the operating process. Sending maintenance reminders in advance can prompt operation and maintenance personnel to promptly check potential problems in the equipment hardware operation links, avoid the accumulation of faults due to ignoring high-frequency erroneous operations, and thereby reduce subsequent more serious operating accidents (such as line failures caused by erroneous operations).

[0054] In summary, the embodiment of the present application helps to accurately locate the interference points and impact of the isolating switch misoperation on the data fusion process by performing interference feedback on the isolating switch misoperation and judging whether to perform misoperation and accuracy feedback, and provides a clear judgment basis for subsequent targeted processing of data fusion anomalies, avoiding resource waste caused by blind optimization. If misoperation and accuracy feedback are performed, accuracy feedback and optimization are performed, which helps to improve the accuracy of visual recognition and the reliability of limit feature judgment in the isolating switch data fusion process. If misoperation and accuracy feedback are not performed, the fusion data accuracy analysis is performed and it is judged whether to perform abnormal superposition interference optimization based on the output fusion data accuracy analysis results, which helps to timely check and deal with abnormal superposition interference problems that may exist in the data fusion process, and provide reliable data support for isolating switch operating status monitoring and operation and maintenance decision-making, thereby helping to improve the accuracy of isolating switch misoperation risk assessment management of multi-source data fusion, and solve the problem of low accuracy of isolating switch misoperation risk assessment management of multi-source data fusion in the prior art.

[0055] The above embodiments can be implemented in whole or in part via software, hardware (e.g., circuits), firmware, or any other combination thereof. When implemented using software, the above embodiments can be implemented in whole or in part in the form of a computer program product. A computer program product comprises one or more computer instructions or computer programs. When the computer instructions or computer program are loaded or executed on a computer, the processes or functions according to the embodiments of the present invention are fully or partially generated. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. Computer instructions can be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another. For example, computer instructions can be transmitted from one website, computer, server, or data center to another website, computer, server, or data center via wired means (e.g., infrared, wireless, microwave, etc.). A computer-readable storage medium can be any available medium accessible by a computer or a data storage device such as a server or data center that contains a collection of one or more available media. Available media can be magnetic media (e.g., floppy disks, hard disks, magnetic tapes), optical media (e.g., DVDs), or semiconductor media. Semiconductor media can be solid-state drives.

[0056] Those skilled in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professionals and technicians can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of the present invention.

[0057] If a function is implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, or the portion that contributes to the prior art, or the portion of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions for enabling a computer device (which can be a personal computer, server, or network device, etc.) to execute all or part of the steps of the various embodiments of the method of the present invention. The aforementioned storage medium includes various media that can store program code, such as USB flash drives, mobile hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0058] The above are merely specific embodiments of the present invention, but the scope of protection of the present invention is not limited thereto. Any modifications or substitutions that can be easily conceived by a person skilled in the art within the technical scope disclosed in the present invention should be included within the scope of protection of the present invention. Therefore, the scope of protection of the present invention should be based on the scope of protection of the claims.

Claims

1. A multi-source data fusion risk assessment method for disconnector misoperation, characterized by: The method comprises: During the multi-source data collection process, the isolating switch misoperation interference feedback is performed and the isolating switch misoperation interference feedback result is outputted, which is used to reflect the interference of the isolating switch misoperation on the data fusion process, and it is determined whether to perform misoperation and accuracy feedback. The misoperation and accuracy feedback is used to evaluate the effect of the isolating switch misoperation interference feedback result on the collection qualification of the visual recognition data and the limit feature data; If misoperation and accuracy feedback is performed, accuracy feedback and optimization are performed based on the misoperation and accuracy feedback results output by the misoperation and accuracy feedback, which reflect the accuracy of visual recognition and limit feature. The accuracy feedback and optimization are used to improve the anti-interference ability of visual recognition and limit feature acquisition against misoperation of the disconnector; If no error operation and accuracy feedback is performed, the fusion data accuracy analysis is performed and based on the output fusion data accuracy analysis results reflecting the qualified status of data fusion, it is determined whether to perform abnormal superposition interference optimization to reduce the input noise of visual recognition data and limit feature data.

2. The multi-source data fusion isolation switch misoperation risk assessment method according to claim 1 is characterized in that: The specific process of performing interference feedback of misoperation of the isolation switch is as follows: Acquiring disconnector misoperation interference data reflecting the interference degree of disconnector misoperation within a specified misoperation monitoring time period; Determine whether the disconnector misoperation interference data meets the disconnector misoperation interference qualification conditions: If it does not meet the requirements, the corresponding disconnector misoperation interference data will be marked as unqualified disconnector misoperation interference data, and feedback on misoperation and accuracy will be provided. If it meets the requirements, the visual recognition data corresponding to the disconnector misoperation interference data that meets the qualified conditions of disconnector misoperation interference will be marked as qualified visual recognition data, the corresponding limit feature data will be marked as qualified limit feature data, and the fusion data accuracy analysis will be performed. The unqualified disconnector misoperation interference data includes an unqualified opening misoperation interference value and an unqualified closing misoperation interference value; The disconnector misoperation interference qualified condition indicates that the opening misoperation interference value is less than the preset opening misoperation interference value, and the closing misoperation interference value is less than the preset closing misoperation interference value; The disconnector misoperation interference data includes an opening misoperation interference value for reflecting the degree of deviation in opening completion and a closing misoperation interference value for reflecting the degree of deviation in closing completion.

3. The multi-source data fusion isolation switch misoperation risk assessment method according to claim 2 is characterized in that: The specific process of performing interference feedback of misoperation of the isolation switch is as follows: If the monitored disconnector misoperation interference data does not meet the disconnector misoperation interference qualification conditions, provide misoperation and accuracy feedback; If it meets the requirements, it is determined whether the number of monitored erroneous operations is greater than the preset maximum total number of erroneous operations. If so, a maintenance reminder is sent to the preset personnel. Otherwise, the fusion data accuracy analysis is performed based on the visual recognition data and the limit feature data; The number of misoperations represents the total number of times the disconnector is opened and closed within a specified misoperation monitoring time period.

4. The multi-source data fusion isolating switch misoperation risk assessment method according to claim 2 or 3, characterized in that: The misoperation and accuracy feedback includes the evaluation of the interference degree of misoperation of the isolation switch and the accuracy feedback and optimization; The evaluation of the degree of interference caused by misoperation of disconnectors is used to evaluate the impact of misoperation interference data of unqualified disconnectors on accuracy feedback and optimization. The specific process is as follows: Inputting the unqualified disconnector misoperation interference data into the misoperation interference degree mapping table, and reading the corresponding misoperation interference degree factor, wherein the misoperation interference degree factor includes an unqualified opening misoperation interference factor and an unqualified closing misoperation interference factor, which are used to reflect the degree of influence of the unqualified disconnector misoperation interference data on accuracy feedback and optimization; When the interference factor of unqualified opening misoperation is greater than the interference factor of unqualified closing misoperation, the unqualified opening misoperation interference value is used to reflect accuracy feedback and optimization; When the interference factor of unqualified opening misoperation is equal to the interference factor of unqualified closing misoperation, accuracy feedback and optimization are performed based on the unqualified disconnector misoperation interference data; When the interference factor of unqualified opening error operation is smaller than the interference factor of unqualified closing error operation, accuracy feedback and optimization are performed based on the unqualified closing error operation interference value.

5. The multi-source data fusion isolation switch misoperation risk assessment method according to claim 4 is characterized in that: The specific process of accuracy feedback and optimization is as follows: When it is monitored that the interference factor of the unqualified opening erroneous operation is greater than the interference factor of the unqualified closing erroneous operation, the result of harmonic averaging of the unqualified opening erroneous operation interference value used to reflect the interference degree of the opening erroneous operation and the visual recognition accuracy value used to measure the interference degree of the visual recognition accuracy is used as the visual recognition accuracy feedback value, and the result of harmonic averaging of the unqualified opening erroneous operation interference value and the limit feature accuracy value used to measure the accuracy of the limit feature is used as the limit feature accuracy feedback value; When it is monitored that the interference factor of unqualified opening error operation is equal to the interference factor of unqualified closing error operation, the result of harmonic averaging of the unqualified opening error operation interference value, the unqualified closing error operation interference value and the visual recognition accuracy value is used as the visual recognition accuracy feedback value, and the result of harmonic averaging of the unqualified opening error operation interference value, the unqualified closing error operation interference value and the limit feature accuracy value is used as the limit feature accuracy feedback value; When it is monitored that the interference factor of the unqualified opening error operation is smaller than the interference factor of the unqualified closing error operation, the result of harmonic averaging of the unqualified closing error operation interference value used to reflect the interference degree of the closing error operation and the visual recognition accuracy value is used as the visual recognition accuracy feedback value, and the result of harmonic averaging of the unqualified closing error operation interference value and the limit feature accuracy value is used as the limit feature accuracy feedback value; The accuracy feedback and optimization also includes visual recognition-limit feature accuracy feedback judgment, the specific process is as follows: Judgment is made based on the feedback value of visual recognition accuracy and the feedback value of limit feature accuracy: If the visual recognition accuracy feedback value is less than the preset visual recognition accuracy feedback value, the visual recognition accuracy optimization is performed to improve the anti-interference ability of the visual recognition against misoperation of the disconnector, otherwise the fusion data accuracy analysis is performed; If the limit feature accuracy feedback value is less than the preset limit feature accuracy feedback value, the limit feature accuracy optimization is performed to improve the timing accuracy of the limit signal; otherwise, the fusion data accuracy analysis is performed.

6. The multi-source data fusion isolating switch misoperation risk assessment method according to claim 5, characterized in that: The specific process of optimizing the visual recognition accuracy is as follows: Input the visual recognition accuracy feedback value and the exposure frequency of the erroneous operation behavior camera into the exposure time adjustment mapping table, and read the exposure time adjustment value; Use the amplitude corresponding to the exposure time adjustment value as the adjustment step to reduce the exposure time step by step; The accuracy optimization of the limit feature is specifically: filtering the limit feature data based on a moving average filtering algorithm to suppress high-frequency noise and transient hysteresis in the sensor signal, thereby improving the timing accuracy and stability of the limit signal; The optimization of the accuracy of visual recognition and the accuracy of the limiting feature also includes performing a visual recognition-limiting feature qualification judgment, and the specific process is as follows: After the visual recognition accuracy optimization or the limiting feature accuracy optimization is completed, determine whether the re-acquired visual recognition accuracy feedback value is still less than the preset visual recognition accuracy feedback value, and whether the limiting feature accuracy feedback value is still less than the preset limiting feature accuracy feedback value; if the visual recognition accuracy feedback value is still less than the preset visual recognition accuracy feedback value, obtain a visual recognition feedback deviation value reflecting the degree of deviation of the visual recognition accuracy and perform deviation-visual recognition accuracy optimization; otherwise, perform fusion data accuracy analysis; if the limiting feature accuracy feedback value is still less than the preset limiting feature accuracy feedback value, obtain a limiting feature feedback deviation value reflecting the degree of deviation of the limiting feature accuracy and perform deviation-limiting feature accuracy optimization; otherwise, perform fusion data accuracy analysis; The deviation-visual recognition accuracy optimization means providing reliable visual input for multi-source data fusion through dynamic aperture adjustment, thereby improving the accuracy of misoperation risk assessment; The deviation-limit feature accuracy optimization means that transient noise interference is suppressed by dynamically adjusting the sampling window length to extract more stable limit features, thereby improving the accuracy of misoperation risk assessment.

7. The multi-source data fusion isolation switch misoperation risk assessment method according to claim 6 is characterized in that: The specific process of the deviation-visual recognition accuracy optimization is as follows: Input the visual recognition feedback deviation value and the camera focal length into the aperture adjustment mapping table to read the aperture adjustment value; The aperture is gradually reduced with the amplitude corresponding to the aperture adjustment value as the adjustment step; If the re-acquired visual recognition accuracy feedback value is not less than the preset visual recognition accuracy feedback value after the deviation-visual recognition accuracy optimization is completed, the fusion data accuracy analysis is performed, otherwise a visual recognition abnormality alarm is issued; The specific process of optimizing the accuracy of the deviation-limit feature is as follows: Input the limit feature feedback deviation value and the number of sampling points of the opening and closing signals into the sampling window length mapping table to read the sampling window length adjustment value; The amplitude corresponding to the sampling window length adjustment value is used as the adjustment step, and the sampling window length is increased step by step; If the newly acquired limit feature accuracy feedback value is not less than the preset limit feature accuracy feedback value after the deviation-limit feature accuracy optimization is completed, the fusion data accuracy analysis is performed, otherwise a limit feature abnormality alarm is sent.

8. The multi-source data fusion isolating switch misoperation risk assessment method according to claim 7, characterized in that: The specific process of performing the fusion data accuracy analysis is as follows: Obtaining a fusion noise anomaly value used to reflect the degree of noise anomaly during the fusion process of visual recognition data and limited feature data; If the fusion noise anomaly value is greater than the preset fusion noise anomaly value, the abnormal superposition interference optimization is performed. Otherwise, the corresponding disconnector misoperation interference data is marked as qualified risk assessment management data; The qualified risk assessment management data is used to input into a preset risk assessment model to obtain the behavior risk level of the disconnector misoperation analysis output; The fusion noise anomaly value is represented by the difference between the noise intensity of the corresponding fusion signal during the fusion process of the visual recognition data and the limit feature data and the preset fusion noise intensity.

9. The multi-source data fusion isolating switch misoperation risk assessment method according to claim 8, characterized in that: The specific process of performing abnormal superposition interference optimization is as follows: Inputting the qualified fusion accuracy result into the fusion data accuracy mapping table to obtain a fusion-accuracy factor used to reflect the degree of influence of the disconnector misoperation on the fusion process of the visual recognition data and the limit feature data, wherein the qualified fusion accuracy result includes the disconnector misoperation interference data and the fusion noise anomaly value, and the fusion-accuracy factor includes the fusion-visual recognition degree factor and the fusion-limit feature degree factor; If the fusion-visual recognition degree factor is greater than the fusion-limited feature degree factor, only the fusion-visual recognition optimization for reducing the noise anomaly superposition of the visual recognition data is performed; If the fusion-visual recognition degree factor is less than the fusion-limited feature degree factor, only the fusion-limited feature optimization for reducing the noise anomaly superposition of the limited feature data is performed; If the fusion-visual recognition degree factor is equal to the fusion-limited feature degree factor, perform the fusion-visual recognition optimization and the fusion-limited feature optimization simultaneously; The fusion-visual recognition optimization specifically includes: centrally obtaining a sensitivity adjustment value by mapping the fusion noise anomaly value and the ambient brightness input sensitivity, using the corresponding amplitude as the adjustment step, and gradually reducing the sensitivity. When the fusion-visual recognition optimization is completed and the fusion noise anomaly value is monitored to be still no greater than the preset fusion noise anomaly value, the corresponding disconnector misoperation interference data is marked as qualified risk assessment management data, otherwise a fusion-visual recognition optimization abnormality prompt is sent; The fusion-limit feature optimization is specifically as follows: the fusion noise anomaly value and the number of pixels in the misoperation behavior image are input into the sensor gain mapping to centrally obtain the sensor gain adjustment value, and the corresponding amplitude is used as the adjustment step to increase the sensor gain step by step. When the fusion-limit feature optimization is completed and it is monitored that the fusion noise anomaly value is still not greater than the preset fusion noise anomaly value, the corresponding isolation switch misoperation interference data is marked as qualified risk assessment management data, otherwise a fusion-limit feature optimization abnormality prompt is sent.

10. A multi-source data fusion isolating switch misoperation risk assessment system, which applies the multi-source data fusion isolating switch misoperation risk assessment method according to any one of claims 1 to 9, characterized in that: include: Isolating switch misoperation interference feedback monitoring module, misoperation and accuracy monitoring module and abnormal superimposed interference optimization judgment module; The isolating switch misoperation interference feedback monitoring module is used to perform isolating switch misoperation interference feedback during the multi-source data acquisition process and output an isolating switch misoperation interference feedback result that reflects the interference of the isolating switch misoperation on the data fusion process, and determines whether to perform misoperation and accuracy feedback; The misoperation and accuracy monitoring module is used to perform accuracy feedback and optimization based on the misoperation and accuracy feedback results output by the misoperation and accuracy feedback, which reflect the accuracy of visual recognition and the accuracy of the limit feature; The abnormal superposition interference optimization judgment module is used to perform fusion data accuracy analysis if no erroneous operation and accuracy feedback are performed, and based on the output fusion data accuracy analysis result reflecting the qualified status of data fusion, determine whether to perform abnormal superposition interference optimization to reduce the input noise of visual recognition data and limit feature data.

Images