An Adaptive Reclosing Method and System for Transmission Lines in Winter Based on Evidence Theory Fusion

Abstract

This invention discloses an adaptive reclosing method, system, and electronic equipment for power transmission lines in winter based on evidence theory fusion. The method includes calculating the posterior probabilities of different subdivided fault causes under corresponding weather characteristics during winter power transmission line faults using a Bayesian formula model. These probabilities are then used as weights and incorporated into the fault cause identification and classification results output by a pre-constructed waveform image recognition model. Major fault categories are further subdivided to obtain the identification probabilities of different subdivided fault causes. The posterior probabilities and identification probabilities are fused using a D-S evidence theory fusion model to obtain the fused probabilities of different fault causes. Based on these probabilities, the reclosing operation mode, reclosing time, and number of reclosing operations are dynamically adjusted. Compared to existing technologies, this invention significantly improves the accuracy of fault cause identification and enables the reclosing system to dynamically adjust according to weather changes and fault analysis, providing effective decision support for adaptive reclosing of power transmission lines in winter.

Description

Technical Field

[0001] This invention belongs to the field of power transmission line protection and automation technology, specifically relating to an adaptive reclosing method, system and electronic equipment for power transmission lines in winter based on evidence theory fusion. Background Technology

[0002] Currently, fault recovery in transmission lines primarily relies on automatic reclosing mechanisms. When a fault occurs, the circuit breaker automatically resets to determine if the fault is transient and then performs recovery. However, traditional reclosing methods typically use fixed recovery times and attempts, without dynamic optimization based on specific weather conditions and fault characteristics. Particularly in winter, the impact of severe weather conditions such as snow accumulation, freezing, and strong winds on transmission lines is significant, leading to more complex and variable fault causes. For example, faults such as de-icing tripping and flashover are common in winter, and most are transient. Traditional reclosing systems do not flexibly adjust to these fault characteristics, often making it difficult to efficiently handle the variability and transient nature of winter faults. Especially when multiple reclosing operations fail or the fault cause is misjudged, traditional strategies may lead to power system instability, potentially causing equipment damage or widespread power outages.

[0003] Although existing reclosing systems have incorporated weather data and fault analysis to some extent, most still rely on static diagnostic methods and fail to dynamically adjust based on real-time weather changes, line conditions, and fault cause analysis. This static analysis approach makes the system unable to flexibly adapt to fault characteristics under different weather conditions, especially in extreme winter weather, where it cannot effectively cope with complex faults such as wind deflection, wildfires, and foreign objects. Therefore, there is an urgent need for an adaptive reclosing method for transmission lines that adapts to winter weather conditions. This strategy should be able to dynamically adjust the reclosing delay, frequency, and operation mode based on real-time weather changes and fault analysis to quickly recover from transient faults and implement reclosing blocking measures for permanent faults, ensuring the stability and safety of the power system. Summary of the Invention

[0004] To address the aforementioned technical problems, the present invention aims to provide an adaptive reclosing method, system, and electronic device for winter power transmission lines based on evidence theory fusion. This method incorporates the posterior probability calculated by a Bayesian formula model as a weight into the fault cause identification and classification results output by a waveform image recognition model. This subdivides major fault categories and, based on a DS evidence theory fusion model, fuses the identification probabilities of different subdivided fault causes with the posterior probabilities calculated by the Bayesian formula model. The fused fault cause probabilities serve as the decision-making basis for reclosing, dynamically adjusting the reclosing delay, number of reclosing cycles, and operation mode. This enables rapid recovery from transient faults and implements reclosing blocking measures for permanent faults, ensuring the stability and security of the entire power system.

[0005] To achieve the above objectives, the technical solution adopted by the present invention is as follows:

[0006] The first aspect of this invention discloses an adaptive reclosing method for winter transmission lines based on evidence theory fusion, comprising the following steps: S1, acquiring the corresponding weather characteristics when a fault occurs in a winter transmission line; S2, based on the acquired corresponding weather characteristics and a pre-built Bayesian formula model, calculating and obtaining the posterior probability of different subdivided fault causes under the corresponding weather characteristics; S3, inputting the electrical quantity waveform diagram of the winter transmission line to be identified into a pre-built waveform image recognition model to obtain the fault cause identification and classification result; S4, determining whether the fault cause identification and classification result in step S3 has a major fault category, and if so, introducing the method from step S2... The posterior probabilities of different subdivided fault causes are used as allocation weights to further subdivide the fault cause identification and classification results in step S3 to obtain the subdivided fault cause identification probabilities; S5, based on the DS evidence theory fusion model, the posterior probabilities of different subdivided fault causes obtained in step S2 based on the Bayesian formula model and the subdivided fault cause identification probabilities based on the waveform image recognition model and posterior probabilities in step S4 are fused and processed to output the fused fault cause probabilities; S6, based on the fused weather feature probabilities output in step S5, the operation mode, reclosing time and number of times of reclosing are dynamically adjusted.

[0007] In the above-disclosed steps, the present invention introduces the posterior probability calculated based on the Bayesian formula model as a weight into the fault cause identification and classification results output by the waveform image recognition model, subdivides the major fault categories, and fuses the identification probabilities of different subdivided fault causes with the posterior probabilities calculated based on the Bayesian formula model based on the DS evidence theory fusion model. The fused fault cause probability is used as the decision basis for reclosing, which effectively solves the problem that the existing waveform image recognition model is limited in identifying fault causes with extremely similar features and is difficult to guide reclosing decisions quickly and accurately.

[0008] Furthermore, by incorporating weather characteristic information as a non-electrical quantity feature into the waveform image recognition model and effectively integrating it with DS evidence theory, the accuracy of fault cause identification is improved. At the same time, the reclosing system can adapt to fault characteristics under different weather conditions and make dynamic adjustments based on real-time weather changes and fault analysis, providing effective decision support for adaptive reclosing of transmission lines in winter weather.

[0009] In addition, by dynamically adjusting the delay, number of times and operation mode of reclosing, this invention enables transient faults to be recovered quickly and takes measures to block reclosing for permanent faults, thus ensuring the stability and safety of the entire power system.

[0010] In this invention, in step S1, the weather characteristics corresponding to a transmission line fault in winter are mainly derived from the weather records in the fault inspection report. These records are typically based on real-time data from meteorological monitoring stations along the faulty line section or weather forecasts issued by the local meteorological bureau. Meteorological monitoring stations provide specific real-time weather data, such as temperature, humidity, and snowfall, while the forecasts from the meteorological bureau are used to supplement the weather conditions in the region.

[0011] In the winter transmission line adaptive reclosing method based on evidence theory fusion disclosed in the first aspect of the present invention, before step S1, step S0 is further included, which pre-constructs a Bayesian formula model capable of calculating the posterior probability of different subdivided fault causes based on known specific weather characteristics; it includes the following steps:

[0012] A historical fault sample database for winter transmission lines was constructed. The data in the historical fault sample database includes the time, location, type, detailed causes of the fault, and historical weather characteristics of each historical fault occurrence period.

[0013] Using the causes of transmission line faults occurring in winter as variable A and the corresponding weather characteristics as variable B, the frequency of occurrence of each sub-cause of fault in all fault events is statistically analyzed to obtain the prior probability P(A). i );

[0014] For each specific cause of failure, the frequency of weather characteristics occurring when that cause of failure occurs is statistically analyzed to obtain the conditional probability P(B|A). i );

[0015] Based on the prior probability P(A) i ) and conditional probability P(B|A i Construct and calculate the posterior probability P(A) i |B) Bayesian formula model:

[0016]

[0017] Where, ∑ j P(B|A j )P(A j P(B) represents the total probability of variable B occurring.

[0018] In the winter transmission line adaptive reclosing method based on evidence theory fusion disclosed in the first aspect of the present invention, each subdivided fault cause is assigned a unique label in the historical sample database, including wildfire, wind deflection, icing-de-icing jump, lightning strike, foreign object, pollution flashover-bird droppings, icing-insulator skirt bridging, pollution flashover-other pollution flashover; and the weather characteristics are standardized to include sunny, cloudy, thunderstorm, strong wind, strong convective wind, typhoon, heavy rain, light rain, heavy snow, light snow, dense fog, and dust storm.

[0019] In the winter transmission line adaptive reclosing method based on evidence theory fusion disclosed in the first aspect of the present invention, the step of further subdividing the fault cause identification and classification results in step S3 by introducing the posterior probabilities of different subdivided fault causes obtained in step S3 as allocation weights in step S4 includes at least the following:

[0020] The posterior probabilities of wind deflection fault and icing-de-icing jump fault in the subdivided fault causes in step S2 are normalized and used as weight allocation factors to further subdivide the probability of wind deflection and icing-de-icing jump fault categories output by the waveform image recognition model.

[0021] The posterior probabilities of the pollution flashover-bird droppings fault, icing-insulator skirt bridging fault, and pollution flashover-other pollution flashover faults in step S2 are normalized and used as weighting factors to further subdivide the pollution flashover fault probabilities output by the waveform image recognition model.

[0022] In the winter adaptive reclosing method for transmission lines based on evidence theory fusion disclosed in the first aspect of the present invention, step S5 involves fusion processing based on the DS evidence theory fusion model, specifically including:

[0023] The probability of identifying various fault causes in the segmented waveform image recognition model is used as the first independent evidence.

[0024] The posterior probability of various fault causes under different weather conditions based on Bayes' formula output is used as the second independent evidence.

[0025] The basic allocation probability value of the fused two pieces of evidence is calculated based on the Dempster combination rule, and the final output is the predicted probability of various fault causes after fusion.

[0026] In the winter transmission line adaptive reclosing method based on evidence theory fusion disclosed in the first aspect of the present invention, step S6, the step of dynamically adjusting the reclosing operation mode, includes:

[0027] Based on the predicted probability of different fault causes, reclosing operations are performed.

[0028] If reclosing fails, force power supply or lockout reclosing operation shall be performed according to the criteria corresponding to different fault causes.

[0029] In the winter transmission line adaptive reclosing method based on evidence theory fusion disclosed in the first aspect of the present invention, step S6, which involves performing forced power supply or blocking reclosing operation according to the criteria corresponding to different fault causes, includes:

[0030] If the cause of the fault is identified as an ice-free jump fault, the reclosing is performed after a delay of Δt. Δt is determined based on the bounce recovery time of the ice-free jump, and the statistical value is 3-6s.

[0031] If the fault is identified as a flashover fault, then reclosing will be performed normally.

[0032] If the cause of the fault is identified as a wildfire fault, check whether the wildfire has been extinguished. If it has been extinguished, perform a forced power supply operation. If it has not been extinguished, lock the reclosing circuit breaker.

[0033] If the fault is identified as a foreign object fault, check whether the foreign object has been removed. If it has been removed, perform a forced power supply operation. If it has not been removed, lock the reclosing circuit breaker.

[0034] If the cause of the fault is identified as wind deflection, the adaptive reclosing system needs to attempt reclosing again based on the wind speed data observed by the nearby automatic weather station. Power can only be supplied when the wind speed drops below the design wind speed value of the corresponding line; otherwise, the reclosing will be blocked.

[0035] The second aspect of this invention discloses an adaptive reclosing system for winter transmission lines based on evidence theory fusion, comprising:

[0036] The weather feature acquisition unit is configured to acquire the corresponding weather features when a transmission line fault occurs in winter.

[0037] The fault cause posterior probability acquisition unit is constructed by calculating and obtaining the posterior probability of different subdivided fault causes based on the corresponding weather features, according to the acquired corresponding weather features and based on the pre-built Bayesian formula model.

[0038] The fault cause graphic identification unit is constructed by inputting the electrical quantity waveform diagram of the winter transmission line to be identified into a pre-built waveform image recognition model to obtain the fault cause identification and classification results.

[0039] The fault cause subdivision processing unit is constructed to determine whether the fault cause identification and classification result has a major category of fault. If the determination is yes, the posterior probability of the occurrence of different subdivision fault causes obtained in step S3 is introduced as the allocation weight to further subdivide the fault cause identification and classification result in step S3 to obtain the subdivision of different fault cause identification probabilities.

[0040] The fusion processing unit is constructed as follows: based on the DS evidence theory fusion model, it fuses the posterior probabilities of different subdivided fault causes obtained based on the Bayesian formula model and the identification probabilities of different fault causes after subdivision based on the waveform image recognition model and the posterior probabilities, and outputs the fused probabilities of different fault causes.

[0041] The reclosing unit is designed to dynamically adjust the reclosing operation mode, reclosing time, and number of reclosing operations based on the probability of different fault causes after the weather characteristics are fused from the fusion processing module.

[0042] The winter transmission line adaptive reclosing system based on evidence theory fusion disclosed in the second aspect of the present invention also includes a Bayesian formula model building unit, which is constructed in advance to build a Bayesian formula model that can calculate the posterior probability of different subdivided fault causes based on known specific weather characteristics.

[0043] The third aspect of the present invention discloses an electronic device, including a memory, a processor, and a bus. The memory stores a computer program executable by the processor. When the electronic device is running, the memory and the processor communicate with each other via the bus. The processor executes the computer program to perform the winter transmission line adaptive reclosing method based on evidence theory fusion disclosed in the first aspect of the present invention.

[0044] The beneficial effects of this invention are as follows:

[0045] This invention incorporates the posterior probability calculated based on a Bayesian formula model as weights into the fault cause identification and classification results output by a waveform image recognition model. This subdivides major fault categories and fuses the identification probabilities of different subdivided fault causes with the posterior probabilities calculated based on the Bayesian formula model using a DS evidence theory fusion model. The fused fault cause probabilities serve as the decision basis for reclosing operations, significantly improving the accuracy and robustness of fault cause identification compared to existing technologies. Furthermore, by introducing weather characteristic information as a non-electrical quantity feature into the waveform image recognition model and effectively fusing it with DS evidence theory, the reclosing system can adapt to fault characteristics under different weather conditions. It also dynamically adjusts based on real-time weather changes and fault analysis, providing effective decision support for adaptive reclosing of transmission lines in winter. In addition, by dynamically adjusting the reclosing delay, number of reclosing cycles, and operation mode, this invention can quickly recover from transient faults and implement reclosing blocking measures for permanent faults, thereby ensuring the stability and safety of the entire power system.

[0046] The following describes in detail the adaptive reclosing method, system, and electronic equipment for winter power transmission lines based on evidence theory fusion, using the embodiments shown in the accompanying drawings. Attached Figure Description

[0047] Figure 1 This is a flowchart illustrating the steps of the adaptive reclosing method for winter power transmission lines based on evidence theory fusion of the present invention.

[0048] Figure 2 This is a flowchart illustrating the fusion process based on the DS evidence theory in a specific implementation of the present invention.

[0049] Figure 3 This is the adaptive reclosing execution decision diagram in a specific implementation of the present invention;

[0050] Figure 4 This is a flowchart of the adaptive reclosing system for winter transmission lines based on evidence theory fusion, as described in this invention. Detailed Implementation

[0051] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only a part of the embodiments of the present invention, and not all of them. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative effort are within the scope of protection of the present invention. It should be noted that, unless otherwise specified, the embodiments and features in the embodiments of this application can be combined with each other.

[0052] like Figure 1As shown, this invention discloses an adaptive reclosing method for winter transmission lines based on evidence theory fusion, comprising the following steps: S1, acquiring the corresponding weather characteristics when a fault occurs in a winter transmission line; S2, based on the acquired corresponding weather characteristics and a pre-built Bayesian formula model, calculating and obtaining the posterior probability of different subdivided fault causes under the corresponding weather characteristics; S3, inputting the electrical quantity waveform diagram of the winter transmission line to be identified into a pre-built waveform image recognition model to obtain the fault cause identification and classification result; S4, determining whether the fault cause identification and classification result in step S3 has a major fault category. If the determination is yes, then the method in step S2 is introduced. The posterior probabilities of different subdivided fault causes are used as allocation weights to further subdivide the fault cause identification and classification results in step S3 to obtain the subdivided fault cause identification probabilities; S5, based on the DS evidence theory fusion model, the posterior probabilities of different subdivided fault causes obtained in step S2 based on the Bayesian formula model and the subdivided fault cause identification probabilities based on the waveform image recognition model and posterior probabilities in step S4 are fused and processed to output the fused fault cause probabilities; S6, based on the fused weather feature probabilities output in step S5, the operation mode, reclosing time and number of times of reclosing are dynamically adjusted.

[0053] In this invention, the posterior probability calculated based on the Bayesian formula model is used as a weight and incorporated into the fault cause identification and classification results output by the waveform image recognition model. Major fault categories are further subdivided, and the subdivided fault cause identification probabilities are fused with the posterior probabilities calculated based on the Bayesian formula model using a DS evidence theory fusion model. The fused fault cause probabilities serve as the decision basis for reclosing operations, significantly improving the accuracy and robustness of fault cause identification compared to existing technologies. Furthermore, weather characteristic information is introduced as a non-electrical quantity feature into the waveform image recognition model and effectively fused with DS evidence theory, enabling the reclosing system to adapt to fault characteristics under different weather conditions and dynamically adjust based on real-time weather changes and fault analysis. This provides effective decision support for adaptive reclosing of transmission lines in winter. Moreover, by dynamically adjusting the reclosing delay, number of reclosing cycles, and operation mode, this invention can quickly recover from transient faults and implement reclosing blocking measures for permanent faults, thereby ensuring the stability and safety of the entire power system.

[0054] In a preferred embodiment, before step S1, a step S0 is further included, in which a Bayesian formula model capable of calculating the posterior probability of different subdivided fault causes based on known specific weather characteristics is pre-constructed, specifically as follows:

[0055] 1) Construct a sample database of transmission line faults in winter

[0056] First, collect and organize historical data on transmission line fault events during winter. The sample database should ensure that the data includes the time, location, type, cause of the fault, and detailed weather characteristics for each fault event's time period. Data sources primarily include event records in fault patrol reports, real-time weather data provided by meteorological monitoring stations, and weather forecasts issued by local meteorological bureaus. These sources ensure an accurate match between fault events and corresponding weather characteristics.

[0057] After data collection, data cleaning and preprocessing are performed. Outliers and missing values ​​in the sample database are removed or imputed to ensure data integrity and accuracy. Furthermore, to ensure data consistency, data standardization is necessary so that different weather characteristics and fault types can be uniformly measured and compared in subsequent analyses.

[0058] The causes of the faults are categorized in detail, including: wildfires, wind deflection, icing-de-icing skipping, lightning strikes, foreign objects, pollution flashover-bird droppings, icing-insulator skirt bridging, pollution flashover-other pollution flashovers, and so on. Each fault cause is assigned a unique label to ensure the clarity and accuracy of the classification and facilitate subsequent analysis.

[0059] Simultaneously, the collected weather features need to be standardized, unifying the classification of different meteorological monitoring data to facilitate matching and analysis with fault causes. Specifically, the standardized weather features are divided into N categories, including: sunny, cloudy, thunderstorms, strong winds, severe convective winds, typhoons, heavy rain, light rain, heavy snow, light snow, dense fog, and dust storms, among other weather types. After standardization, each category of weather features accurately reflects the specific meteorological conditions at the time of the fault, providing reliable input data for subsequent Bayesian statistical analysis.

[0060] Based on the prior probability P(A) i ) and conditional probability P(B|A i Construct and calculate the posterior probability P(A) i |B) Bayesian formula model:

[0061]

[0062] Where, ∑ j P(B|A j )P(A j P(B) represents the total probability of variable B occurring.

[0063] 2) Obtain the prior distribution and sample conditional probability of the sample database data.

[0064] Define variables A and B, where A represents the cause of the fault event that occurs in the transmission line during winter, and B represents the weather characteristics corresponding to the fault event.

[0065] The prior distribution reflects the fundamental frequency of different failure causes among all failure events. By statistically analyzing the historical failure sample database, the frequency of each sub-failure cause among all failure events is calculated to obtain the prior probability P(A). i );

[0066] Conditional probability reflects the correlation between the cause of a failure and weather conditions. For each specific cause of a failure, the frequency of weather characteristics occurring when that cause occurs is statistically analyzed to obtain the conditional probability P(B|A). i ).

[0067] 3) Calculate the posterior probability based on Bayes' theorem

[0068] Furthermore, the posterior distribution of different fault causes under different weather characteristics is determined, and the posterior probability P(A) is calculated using Bayes' theorem. i |B), the calculation formula is:

[0069]

[0070] Where, ∑ j P(B|A j )P(A j P(B) represents the total probability of variable B occurring.

[0071] This formula allows the calculation of the i-th cause of failure, A, given a specific weather characteristic B. i The probability of occurrence.

[0072] In this embodiment of the invention, step S4, which introduces the posterior probabilities of different subdivided fault causes obtained in step S3 as allocation weights, further subdivides the fault cause identification and classification results in step S3, and includes at least:

[0073] The posterior probabilities of wind deflection fault and icing-de-icing jump fault in the subdivided fault causes in step S2 are normalized and used as weight allocation factors to further subdivide the probability of wind deflection and icing-de-icing jump fault categories output by the waveform image recognition model.

[0074] The posterior probabilities of the pollution flashover-bird droppings fault, icing-insulator skirt bridging fault, and pollution flashover-other pollution flashover faults in step S2 are normalized and used as weighting factors to further subdivide the pollution flashover fault probabilities output by the waveform image recognition model.

[0075] like Figure 2 As shown, in this embodiment of the invention, in step S5, fusion processing is performed based on the DS evidence theory fusion model, specifically as follows:

[0076] First, the electrical quantity waveforms of the fault cases to be identified are input into a pre-trained waveform image recognition model to obtain preliminary fault cause classification results.

[0077] Furthermore, the fault cause classification results of the waveform image recognition model are further subdivided. The posterior probability calculated in step S2 is introduced and normalized to process the posterior probabilities of wind deflection and icing-de-icing jump faults, which are then used as weighting factors to further refine the probability of wind deflection and icing-de-icing jump fault categories output by the waveform recognition model.

[0078] The posterior probabilities of flashover-bird droppings, icing-insulator skirt bridging, and flashover-other flashover faults are normalized and used as weighting factors to further refine the probability of major flashover fault categories output by the waveform recognition model.

[0079] A DS evidence theory fusion model is constructed, which fuses the identification probabilities of various fault causes from the segmented waveform image recognition model and the posterior probabilities of various fault causes based on Bayes' theorem statistics. The specific construction method includes:

[0080] 1) Establish an evidence theory identification framework Θ. In this embodiment, the identification framework is the set of causes of transmission line faults in winter, and the causes of transmission line faults in winter can be divided into M categories:

[0081] Θ={F1,F2,…,F m}

[0082] In the formula, m is the category number of the cause of the fault, and F m This indicates the cause of the fault in the m-th type of transmission line.

[0083] 2) Determine the basic probability assignment function m i (F j The following formula can be used to calculate:

[0084]

[0085] In the formula, m i (F j Y is the basic probability assignment value of the i-th piece of evidence for the j-th cause of the failure. ij The probability of the i-th piece of evidence being the cause of the j-th failure.

[0086] 3) Determine the conflict coefficient k of independent evidence m1 and m2 using the following formula:

[0087]

[0088] In the formula, m1(A i ) represents the predicted probability of the i-th fault cause output by the waveform image recognition model, m2(Bj ) represents the posterior probability of the j-th cause of failure output by the Bayesian statistical model.

[0089] 4) The basic probability assignment values ​​of the two models are fused based on the Dempster combination rule. The combination rule formula is as follows:

[0090]

[0091] In the formula, Let A represent the basic probability assignment value after fusion, and let A be the proposition A. i and Proposition B j The intersection between them, in this embodiment A is the same fault cause output by the two models.

[0092] This invention utilizes the DS evidence theory to effectively integrate the identification results of waveform image recognition models and the posterior probability results of Bayesian statistical models, thereby improving the accuracy and robustness of fault cause identification.

[0093] like Figure 3 As shown, this embodiment illustrates an adaptive reclosing execution decision graph. This decision graph dynamically adjusts the reclosing operation strategy based on fused weather information and corrected probabilities of various fault causes. The adaptive reclosing method primarily optimizes for transient faults, while for permanent faults, it blocks reclosing and only restores power after confirming the fault cause. Specific methods include:

[0094] 1) Determine the cause of the transmission circuit fault.

[0095] Based on the corrected DS evidence fusion results, the predicted probabilities of various fault causes are sorted from high to low, and the fault cause with the highest probability is selected as the final identification result.

[0096] 2) Adaptive reclosing method

[0097] Depending on the cause of the fault, an appropriate adaptive reclosing method is adopted, which specifically includes:

[0098] Ice-free jumping fault: Since this type of fault has a short bounce recovery time, it is recommended to perform reclosing operation after a delay of Δt = 3-6s.

[0099] Pollution flashover fault: This type of fault is usually transient, so reclosing can be performed normally.

[0100] Lightning strike fault: Lightning strike faults are usually transient and can be reclosed normally.

[0101] Wildfire Fault: First, perform a reclosing operation. If reclosing fails, check if the wildfire in the affected section of the line has been extinguished.

[0102] If the wildfire has been extinguished, then perform a forced power supply operation;

[0103] If the wildfire is not extinguished, the reclosing switch will be locked, and power will be restored only after the wildfire is extinguished.

[0104] Foreign object fault: First, perform a reclosing operation. If reclosing fails, check whether the foreign object in the faulty line section has been removed.

[0105] If the foreign object has been removed, perform a forced power supply operation;

[0106] If the foreign object is not removed, the reclosing circuit will be locked, and power will be restored after the foreign object is removed.

[0107] Wind speed deviation fault: First, perform a reclosing operation. If reclosing fails, obtain real-time wind speed data from a weather station near the faulty line section.

[0108] If the wind speed is lower than the design wind speed, then a forced power supply operation will be performed;

[0109] If the wind speed is greater than the design wind speed, the reclosing circuit will be blocked, and power will be restored after the wind speed decreases.

[0110] This adaptive reclosing method can dynamically adjust the reclosing operation mode to ensure timely recovery from transient faults, while taking safer measures to handle permanent faults, thereby optimizing the operational reliability of the power system.

[0111] This embodiment analyzes several transmission line fault cases in a western region over the past year to make reclosing decisions. A specific implementation case is as follows:

[0112] Fault Case 1

[0113] At 01:37 on January 1, 2024, a fault occurred on the MH East Line of 220 kV in section 041 to 042. On the day of the fault, there was continuous heavy fog and sub-zero temperature.

[0114] A DS evidence theory fusion model was used to identify the cause of the fault, confirming it as an icing-de-icing trip. Based on the fault identification results, the reclosing method was optimized. Considering that the recovery after a de-icing trip requires a certain amount of time, a 5-second delay reclosing method was adopted, meaning that reclosing was attempted only after 5 seconds of fault isolation. The purpose of this strategy is to allow sufficient time for conductor bounce recovery and ice removal, thereby reducing the frequency of trip reclosing and improving power supply reliability.

[0115] The operational results after implementation showed that this 5-second delay reclosing method effectively avoided multiple trips and achieved a reasonable reclosing delay. This measure successfully restored the line to normal operation, ensuring power supply reliability.

[0116] Fault Case 2

[0117] At 17:49 on February 16, 2024, a fault occurred in phase B conductor of pole No. 33 of the 110 kV TD line. The weather at the time of the fault was windy, with the maximum instantaneous wind speed reaching 25.6 m / s.

[0118] The DS evidence theory fusion model was used to identify the cause of the fault, confirming that it was wind deflection. Considering that the high wind speed might continue or fluctuate, and that multiple trips might occur during the wind's weakening, the reclosing method was optimized and adjusted. Given that the fault occurred under conditions where the wind speed exceeded the design wind speed of 23.5 m / s, it was ultimately decided to adopt a blocked reclosing method.

[0119] The operational results after implementation show that the interlocking reclosing method effectively avoids the problem of multiple trips caused by strong winds.

[0120] Fault Case 3

[0121] At 2:19 PM on February 21, 2024, a fault occurred on tower No. 188 of the 220 kV YB line. Subsequent on-site inspection reports indicated that at the time of the fault, snow accumulated on the surface of the A-phase insulators (due to continuous snowfall from the 18th to the early morning of the 21st) melted and mixed with surface dust to form icicles. As temperatures gradually rose and the weather cleared during the day on the 21st, the icicles accumulated on the insulator surface, creating a conductive path at the insulator skirts, ultimately triggering a flashover and causing the line to trip.

[0122] The DS evidence theory fusion model was used to identify the cause of the fault, confirming it as icing-insulator skirt bridging. Based on the fault identification results, the reclosing method was optimized and adjusted. Since the electric arc during the flashover process generates high temperatures, it rapidly heats and melts the icing channels, thereby restoring the electrical insulation performance of the insulator; this type of fault is a transient event. Considering that the insulator returns to normal electrical insulation after the icing melts and the arc subsides, it was decided to operate according to the normal reclosing method, i.e., immediately perform the reclosing operation.

[0123] The results after implementation showed that the rapid reclosing method successfully restored power supply and ensured power continuity.

[0124] like Figure 4 As shown, the present invention also discloses an adaptive reclosing system for winter transmission lines based on evidence theory fusion, comprising: a weather feature acquisition unit configured to acquire the corresponding weather features when a fault occurs on a winter transmission line;

[0125] The fault cause posterior probability acquisition unit is constructed by calculating and obtaining the posterior probability of different subdivided fault causes based on the corresponding weather features, according to the acquired corresponding weather features and based on the pre-built Bayesian formula model.

[0126] The fault cause graphic identification unit is constructed by inputting the electrical quantity waveform diagram of the winter transmission line to be identified into a pre-built waveform image recognition model to obtain the fault cause identification and classification results.

[0127] The fault cause subdivision processing unit is constructed to determine whether the fault cause identification and classification result has a major category of fault. If the determination is yes, the posterior probability of the occurrence of different subdivision fault causes obtained in step S3 is introduced as the allocation weight to further subdivide the fault cause identification and classification result in step S3 to obtain the subdivision of different fault cause identification probabilities.

[0128] The fusion processing unit is constructed as follows: based on the DS evidence theory fusion model, it fuses the posterior probabilities of different subdivided fault causes obtained based on the Bayesian formula model and the identification probabilities of different fault causes after subdivision based on the waveform image recognition model and the posterior probabilities, and outputs the fused probabilities of different fault causes.

[0129] The reclosing unit is designed to dynamically adjust the reclosing operation mode, reclosing time, and number of reclosing operations based on the probability of different fault causes after the weather characteristics are fused from the fusion processing module.

[0130] In this embodiment of the invention, a Bayesian formula model building unit is also included, which is constructed in advance to build a Bayesian formula model that can calculate the posterior probability of different subdivided fault causes based on known specific weather characteristics.

[0131] The present invention also discloses an electronic device, including a memory, a processor, and a bus. The memory stores a computer program executable by the processor. When the electronic device is running, the memory and the processor communicate with each other via the bus. The processor executes the computer program to perform the winter transmission line adaptive reclosing method based on evidence theory fusion disclosed in the first aspect of the present invention.

[0132] In the several embodiments provided in this application, it should be understood that the disclosed apparatus and methods can also be implemented in other ways. The apparatus embodiments described above are merely illustrative. For example, the flowcharts and block diagrams in the accompanying drawings illustrate the architecture, functionality, and operation of possible implementations of apparatus, methods, and computer program products according to various embodiments of this application. In this regard, each block in a flowchart or block diagram may represent a module, segment, or portion of code containing one or more executable instructions for implementing a specified logical function. It should also be noted that in some alternative implementations, the functions marked in the blocks may occur in a different order than those marked in the drawings. For example, two consecutive blocks may actually be executed substantially in parallel, and they may sometimes be executed in reverse order, depending on the functions involved. It should also be noted that each block in a block diagram and / or flowchart, and combinations of blocks in block diagrams and / or flowcharts, can be implemented using a dedicated hardware-based system that performs the specified function or action, or using a combination of dedicated hardware and computer instructions.

[0133] In addition, the functional modules in the various embodiments of this application can be integrated together to form an independent part, or each module can exist independently, or two or more modules can be integrated to form an independent part.

[0134] If the aforementioned functions are implemented as software functional modules and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, or a 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 to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of this application. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0135] The above description is merely an embodiment of this application and is not intended to limit the scope of protection of this application. Various modifications and variations can be made to this application by those skilled in the art. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of this application should be included within the scope of protection of this application. It should be noted that similar reference numerals and letters in the following figures indicate similar items; therefore, once an item is defined in one figure, it does not need to be further defined and explained in subsequent figures.

[0136] The above description is merely a specific embodiment of this application, but the scope of protection of this application is not limited thereto. Any variations or substitutions that can be easily conceived by those skilled in the art within the scope of the technology disclosed in this application should be included within the scope of protection of this application. Therefore, the scope of protection of this application should be determined by the scope of the claims.

[0137] It should be noted that, in this document, relational terms such as "first" and "second" are used only to distinguish one entity or operation from another, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Furthermore, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Without further limitations, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes said element.

[0138] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and are not intended to limit it. Although the present invention has been described in detail with reference to preferred embodiments, those skilled in the art should understand that modifications or equivalent substitutions can be made to the technical solutions of the present invention without departing from the spirit and scope of the technical solutions of the present invention, and all such modifications or substitutions should be covered within the scope of the claims of the present invention.

Claims

1. A method for adaptive reclosing of power transmission lines in winter based on evidence theory fusion, characterized in that, Includes the following steps: S1, obtain the corresponding weather characteristics when a transmission line fault occurs in winter; S2, based on the obtained corresponding weather features, and using a pre-built Bayesian formula model, calculate and obtain the posterior probability of different subdivided fault causes under the corresponding weather features; S3, input the electrical quantity waveform of the winter transmission line to be identified into the pre-built waveform image recognition model to obtain the fault cause identification and classification results; S4. Determine whether the fault cause identification and classification result in step S3 has a major category of fault. If it is determined to be yes, then the posterior probability of the occurrence of different subdivided fault causes obtained in step S2 is introduced as the allocation weight to further subdivide the fault cause identification and classification result in step S3 to obtain the subdivided different fault cause identification probabilities. S5. Based on the DS evidence theory fusion model, the posterior probabilities of different subdivided fault causes obtained in step S2 based on the Bayesian formula model and the identification probabilities of different fault causes subdivided based on the waveform image recognition model and the posterior probabilities in step S4 are fused together to output the fused probabilities of different fault causes. S6. Based on the probability of different fault causes after fusing weather features output in step S5, dynamically adjust the operation mode, reclosing time and number of times of reclosing. In step S4, the posterior probabilities of different subdivided fault causes obtained in step S2 are introduced as allocation weights to further subdivide the fault cause identification and classification results in step S3. This step includes at least the following: The posterior probabilities of wind deflection fault and icing-de-icing jump fault in the subdivided fault causes in step S2 are normalized and used as weight allocation factors to further subdivide the probability of wind deflection and icing-de-icing jump fault categories output by the waveform image recognition model. The posterior probabilities of pollution flashover-bird droppings fault, icing-insulator skirt bridging fault and pollution flashover-other pollution flashover fault in the subdivided fault causes in step S2 are normalized and used as weight allocation factors to further subdivide the pollution flashover fault probability output by the waveform image recognition model. In step S6, the step of dynamically adjusting the reclosing operation mode includes: Based on the predicted probability of different fault causes, reclosing operations are performed. If reclosing fails, force power supply or lockout reclosing operation shall be performed according to the criteria corresponding to different fault causes.

2. The adaptive reclosing method for winter transmission lines based on evidence theory fusion according to claim 1, characterized in that, Before step S1, there is also step S0, which pre-constructs a Bayesian formula model that can calculate the posterior probability of different subdivided fault causes based on the weather characteristics corresponding to the fault event. It includes the following steps: A historical fault sample database for winter transmission lines is constructed. The data in the historical fault sample database includes the time, location, type, detailed causes of the fault, and historical weather characteristics of each historical fault occurrence period. The causes of fault events occurring on transmission lines in winter are used as variables. A And the weather characteristics corresponding to the failure event are used as variables. B The frequency of occurrence of each sub-cause of failure in all failure events is statistically analyzed to obtain the prior probability. For each specific cause of failure, the frequency of weather characteristics occurring when that cause of failure occurs is statistically analyzed to obtain the conditional probability. Based on prior probability and conditional probability Constructing the calculation of posterior probability Bayesian formula model: in, , which represents the total probability of variable B occurring.

3. The adaptive reclosing method for winter transmission lines based on evidence theory fusion according to claim 2, characterized in that, In the historical sample database, each subdivided fault cause is assigned a unique label, including wildfire, wind deflection, icing-de-icing jump, lightning strike, foreign object, pollution flashover-bird droppings, icing-insulator skirt bridging, pollution flashover-other pollution flashover; and the weather characteristics are standardized to include sunny, cloudy, thunderstorm, strong wind, strong convective wind, typhoon, heavy rain, light rain, heavy snow, light snow, dense fog, and dust storm.

4. The adaptive reclosing method for winter transmission lines based on evidence theory fusion according to claim 3, characterized in that, In step S5, fusion processing is performed based on the DS evidence theory fusion model, specifically including: The probability of identifying various fault causes in the segmented waveform image recognition model is used as the first independent evidence. The posterior probability of various fault causes under different weather conditions based on Bayes' formula output is used as the second independent evidence. The basic allocation probability value of the fused two pieces of evidence is calculated based on the Dempster combination rule, and the final output is the predicted probability of various fault causes after fusion.

5. The adaptive reclosing method for winter transmission lines based on evidence theory fusion according to claim 4, characterized in that, In step S6, the steps of performing forced power supply or blocking reclosing operation according to the criteria corresponding to different fault causes include: If the fault is identified as an ice-free jump fault, reclosing is performed after a delay of ∆t. ∆t is determined based on the bounce recovery time of the ice-free jump, and the statistical value is 3-6s. If the fault is identified as a flashover fault, then reclosing will be performed normally. If the cause of the fault is identified as a wildfire fault, check whether the wildfire has been extinguished. If it has been extinguished, perform a forced power supply operation. If it has not been extinguished, lock the reclosing circuit breaker. If the fault is identified as a foreign object fault, check whether the foreign object has been removed. If it has been removed, perform a forced power supply operation. If it has not been removed, lock the reclosing circuit breaker. If the cause of the fault is identified as wind deflection, the adaptive reclosing system needs to attempt reclosing again based on the wind speed data observed by the nearby automatic weather station. Power can only be supplied when the wind speed drops below the design wind speed value of the corresponding line; otherwise, the reclosing will be blocked.

6. A system for implementing the winter adaptive reclosing method for transmission lines based on evidence theory fusion according to any one of claims 1-5, characterized in that, include: The weather feature acquisition unit is configured to acquire the corresponding weather features when a transmission line fault occurs in winter. The fault cause posterior probability acquisition unit is constructed by calculating and obtaining the posterior probability of different subdivided fault causes based on the corresponding weather features, according to the acquired corresponding weather features and based on the pre-built Bayesian formula model. The fault cause graphic identification unit is constructed by inputting the electrical quantity waveform diagram of the winter transmission line to be identified into a pre-built waveform image recognition model to obtain the fault cause identification and classification results. The fault cause subdivision processing unit is configured to determine whether the fault cause identification and classification result has a major category of fault. If the determination is yes, the posterior probability of the occurrence of different subdivision fault causes obtained in step S2 is introduced as the allocation weight to further subdivide the fault cause identification and classification result in step S3 to obtain the subdivision of different fault cause identification probabilities. The fusion processing unit is constructed as follows: based on the DS evidence theory fusion model, it fuses the posterior probabilities of different subdivided fault causes obtained based on the Bayesian formula model and the identification probabilities of different fault causes subdivided based on the waveform image recognition model and the posterior probabilities, and outputs the fused probabilities of different fault causes. The reclosing unit is designed to dynamically adjust the reclosing operation mode, reclosing time, and number of reclosing operations based on the probability of different fault causes after the weather characteristics are fused from the fusion processing module.

7. The adaptive reclosing system for winter transmission lines based on evidence theory fusion according to claim 6, characterized in that, It also includes a Bayesian formula model building unit, which is constructed by pre-building a Bayesian formula model that can calculate the posterior probability of different subdivided fault causes based on the weather characteristics corresponding to the fault event.

8. An electronic device, characterized in that, The device includes a memory, a processor, and a bus. The memory stores a computer program executable by the processor. When the electronic device is running, the memory and the processor communicate via the bus. The processor executes the computer program to perform the winter transmission line adaptive reclosing method based on evidence theory fusion as described in any one of claims 1-5.

Images