Intelligent management method and device for abnormal state of transformer equipment cluster

Abstract

Embodiments of the present disclosure disclose an abnormal state intelligent management method and device applied to a transformer equipment cluster. A specific implementation of the method includes: performing network link anomaly detection on a network communication device of the transformer equipment cluster to generate a network detection result; performing entity update on a transformer equipment association graph corresponding to the transformer equipment cluster to obtain an updated transformer equipment association graph; performing power transmission state detection on the transformer equipment cluster to generate a power transmission state detection result; performing abnormal state feature statistics to obtain abnormal state feature statistical data; issuing a power transmission state anomaly warning; and recording the abnormal state feature statistical data, the updated transformer equipment association graph, and the power transmission state detection result in a preset transformer equipment knowledge base. The implementation can improve the efficiency and accuracy of abnormal state detection of the transformer equipment.

Description

Technical Field

[0001] The embodiments disclosed herein relate to the fields of network connectivity, power detection, and computer technology, and specifically to intelligent management methods and devices for abnormal states applied to power equipment clusters. Background Technology

[0002] Intelligent management of abnormal states is a technology used to detect abnormal states in power equipment clusters. Currently, when detecting abnormal states in power equipment, a combination of artificial intelligence technology and semantic large-scale models is typically used to automatically extract core elements such as entities, relationships, and attributes from a large amount of pre-processed text data of the power equipment, thereby establishing a corresponding knowledge graph. Then, based on the established knowledge graph, operations such as abnormal state detection are performed on the power equipment to achieve the goal of managing the abnormal states of the power equipment cluster.

[0003] However, this approach requires preprocessing a large amount of text data related to power equipment. Due to the large amount of text data, the efficiency of updating entities in the knowledge graph using artificial intelligence processing frameworks or semantic large models is low. At the same time, due to signal fluctuations in network links, the efficiency and accuracy of detecting abnormal states of power equipment are further reduced. Summary of the Invention

[0004] The summary portion of this disclosure is intended to provide a brief overview of the concepts, which will be described in detail in the detailed description portion. This summary portion is not intended to identify key or essential features of the claimed technical solutions, nor is it intended to limit the scope of the claimed technical solutions.

[0005] Some embodiments of this disclosure propose intelligent management methods and devices for abnormal states of power equipment clusters to solve the technical problems mentioned in the background section above.

[0006] In a first aspect, some embodiments of this disclosure provide an intelligent management method for abnormal states applied to a substation equipment cluster. The method includes: performing network link anomaly detection on the network communication equipment of the substation equipment cluster to generate a network detection result; in response to the network detection result indicating that the network link is normal, updating the substation equipment association map corresponding to the substation equipment cluster to obtain an updated substation equipment association map, wherein the substation equipment association map represents the power transmission structure relationship between various substation equipment in the substation equipment cluster, and the updated substation equipment association map is updated based on the substation equipment code corresponding to each substation equipment; based on the above update... The system uses a post-modulation equipment association map to perform power transmission status detection on the power equipment cluster, generating power transmission status detection results. In response to the determination that the power transmission status detection results indicate an abnormal power transmission status, it performs abnormal status feature statistics based on the updated post-modulation equipment association map and the power transmission status detection results, obtaining abnormal status feature statistics. Based on the power transmission status detection results and the abnormal status feature statistics, it issues an abnormal power transmission status warning and records the abnormal status feature statistics, the updated post-modulation equipment association map, and the power transmission status detection results in a preset power equipment knowledge base.

[0007] Secondly, some embodiments of this disclosure provide an intelligent management device for abnormal states applied to a substation equipment cluster. The device includes: a network link anomaly detection unit configured to perform network link anomaly detection on the network communication devices of the substation equipment cluster to generate a network detection result; an entity update unit configured to, in response to the network detection result indicating that the network link is normal, update the entity of the substation equipment association map corresponding to the substation equipment cluster to obtain an updated substation equipment association map, wherein the substation equipment association map represents the power transmission structure relationship between various substation equipment in the substation equipment cluster, and the updated substation equipment association map is updated based on the substation equipment code corresponding to each substation equipment; and a power transmission status detection unit configured to... Based on the updated substation equipment association map, power transmission status detection is performed on the substation equipment cluster to generate power transmission status detection results. An abnormal status feature statistics unit is configured to, in response to determining that the power transmission status detection results indicate an abnormal power transmission status, perform abnormal status feature statistics based on the updated substation equipment association map and the power transmission status detection results to obtain abnormal status feature statistics. An abnormal power transmission status early warning unit is configured to issue an abnormal power transmission status early warning based on the power transmission status detection results and the abnormal status feature statistics, and to record the abnormal status feature statistics, the updated substation equipment association map, and the power transmission status detection results in a preset substation equipment knowledge base.

[0008] Thirdly, some embodiments of this disclosure provide an electronic device, including: one or more processors; and a storage device having one or more programs stored thereon, wherein when the one or more programs are executed by the one or more processors, the one or more processors implement the method described in any implementation of the first aspect above.

[0009] Fourthly, some embodiments of this disclosure provide a computer-readable medium having a computer program stored thereon, wherein the program, when executed by a processor, implements the method described in any of the implementations of the first aspect above.

[0010] The above embodiments of this disclosure have the following beneficial effects: The intelligent management method for abnormal states applied to power equipment clusters according to some embodiments of this disclosure can improve the efficiency and accuracy of abnormal state detection of power equipment. Specifically, the intelligent management method for abnormal states applied to power equipment clusters according to some embodiments of this disclosure first performs network link anomaly detection on the network communication equipment of the power equipment cluster to generate network detection results. Here, by performing network link anomaly detection, network fluctuations can be determined in a timely manner, reducing the impact on abnormal state detection of power equipment and improving its accuracy. Simultaneously, this also ensures timely network link connectivity, thereby improving the efficiency of abnormal state detection. Then, in response to the network detection results indicating normal network links, the power equipment association graph corresponding to the power equipment cluster is updated to obtain an updated power equipment association graph. The power equipment association graph represents the power transmission structure relationship between various power equipment in the power equipment cluster, and the updated power equipment association graph is updated based on the power equipment codes corresponding to each power equipment. Here, compared to a large amount of textual data related to power equipment, by introducing power equipment coding, the amount of data required for updating the power equipment association map of the power equipment cluster is greatly reduced. Furthermore, the structural relationships between power equipment can be quickly extracted through coding, improving the efficiency of updating the power equipment association map. This accelerates the detection of the power equipment cluster. Next, based on the updated power equipment association map, the power transmission status of the power equipment cluster is detected to generate power transmission status detection results. Then, in response to the determination that the power transmission status detection results indicate the existence of an anomaly in power transmission status, anomaly status feature statistics are performed based on the updated power equipment association map and the power transmission status detection results to obtain anomaly status feature statistics. This can be used to summarize the anomalies of power equipment for intelligent management. Finally, based on the power transmission status detection results and the anomaly status feature statistics, an anomaly warning is issued, and the anomaly status feature statistics, the updated power equipment association map, and the power transmission status detection results are recorded in a preset power equipment knowledge base. This can improve the efficiency and accuracy of detecting abnormal conditions in power equipment. Attached Figure Description

[0011] The above and other features, advantages, and aspects of the embodiments of this disclosure will become more apparent from the accompanying drawings and the following detailed description. Throughout the drawings, the same or similar reference numerals denote the same or similar elements. It should be understood that the drawings are schematic, and elements are not necessarily drawn to scale.

[0012] Figure 1This is a flowchart of some embodiments of the intelligent management method for abnormal states applied to a cluster of power equipment according to the present disclosure; Figure 2 This is a schematic diagram of the structure of a network communication device; Figure 3 This is a structural schematic diagram of some embodiments of the intelligent management device for abnormal states applied to a power equipment cluster according to the present disclosure; Figure 4 This is a schematic diagram of the structure of an electronic device suitable for implementing some embodiments of the present disclosure. Detailed Implementation

[0013] Embodiments of this disclosure will now be described in more detail with reference to the accompanying drawings. While some embodiments of this disclosure are shown in the drawings, it should be understood that this disclosure can be implemented in various forms and should not be construed as limited to the embodiments set forth herein. Rather, these embodiments are provided to provide a more thorough and complete understanding of this disclosure. It should be understood that the accompanying drawings and embodiments of this disclosure are for illustrative purposes only and are not intended to limit the scope of protection of this disclosure.

[0014] It should also be noted that, for ease of description, only the parts relevant to the invention are shown in the accompanying drawings. Unless otherwise specified, the embodiments and features described in this disclosure can be combined with each other.

[0015] It should be noted that the concepts of "first" and "second" mentioned in this disclosure are used only to distinguish different devices, modules or units, and are not used to limit the order of functions performed by these devices, modules or units or their interdependencies.

[0016] It should be noted that the terms "a" and "a plurality of" used in this disclosure are illustrative rather than restrictive, and those skilled in the art should understand that, unless otherwise expressly indicated in the context, they should be understood as "one or more".

[0017] The names of messages or information exchanged between multiple devices in the embodiments of this disclosure are for illustrative purposes only and are not intended to limit the scope of such messages or information. This disclosure will now be described in detail with reference to the accompanying drawings and embodiments.

[0018] Figure 1 A flow 100 of some embodiments of an intelligent management method for abnormal states applied to a substation equipment cluster according to the present disclosure is shown. This intelligent management method for abnormal states applied to a substation equipment cluster includes the following steps: Step 101: Perform network link anomaly detection on the network communication equipment of the substation equipment cluster to generate network detection results.

[0019] In some embodiments, the executing entity (e.g., a computing device) of the intelligent management method for abnormal states applied to a power equipment cluster can perform network link anomaly detection on the network communication devices of the power equipment cluster via wired or wireless means to generate network detection results. The power equipment can be devices used for power transmission and control. For example, power equipment may include transformers, relays, circuit breakers, reactors, etc. A power equipment cluster is a collection of interconnected power equipment that jointly perform tasks such as power conversion, transmission, control, or monitoring.

[0020] It should be noted that the aforementioned wireless connection methods may include, but are not limited to, 3G / 4G / 5G connections, WiFi connections, Bluetooth connections, WiMAX connections, Zigbee connections, UWB (ultra wideband) connections, and other currently known or future wireless connection methods. For example, industrial wireless bridges.

[0021] It should be noted that the aforementioned computing devices can be either hardware or software. When the computing device is hardware, it can be implemented as a distributed cluster consisting of multiple servers or terminal devices, or as a single server or a single terminal device. When the computing device is software, it can be installed on the hardware devices listed above. It can be implemented as, for example, multiple software programs or software modules used to provide distributed services, or as a single software program or software module. No specific limitations are made here.

[0022] In some optional implementations of some embodiments, the network communication device may include: a wireless (WIFI) module, a routing and switching link module, a full-network communication module, a processing module, a logic array (Programmable Logic Array), a storage module, and a device industrial traffic card, wherein the industrial traffic card is equipped with a corresponding device network electronic card.

[0023] As an example, such as Figure 2As shown, the power transmission equipment can wirelessly or wiredly connect to the wireless module or routing and switching link module of the network communication equipment to send equipment data (such as power transmission status data) to the aforementioned execution entity. The all-network communication module (2G-5G) can be a module used to connect to corresponding network signals based on different operator phone numbers. Here, the wired connection can be used to connect the fiber optic cable for communication with the power transmission equipment, enabling network connections with other long-distance power transmission equipment or other network communication equipment in the power transmission equipment cluster. The device network electronic card (i.e., eSIM virtual card) can pre-store four operator phone numbers numbered 1, 2, 3, and 4. Then, each time, one operator phone number can be selected and written to the aforementioned device network data card for network connection. The processing module can record various transmission data in the network communication equipment (such as network connection mode switching, operator phone number switching, network traffic statistics, etc.) in the storage module.

[0024] The aforementioned implementing entity performs network link anomaly detection on the network communication equipment of the substation equipment cluster to generate network detection results, including: Step S1: In response to receiving a network connection command from a power equipment in the power equipment cluster, the wireless module or routing and switching link module connected to the power equipment is controlled to send the network connection command to the all-network communication module and the processing module. The processing module is further configured to perform network connection operations on four operator phone numbers pre-stored on the network electronic card of the device according to the network connection command. The network connection command is used for network connection testing.

[0025] In practice, considering that wired connections to power equipment are prone to failure due to external factors when establishing network connections, dual network connections (i.e., wired connection + wireless connection) are configured in the network communication equipment. This allows for timely response to emergencies. Network connection can be established via a wireless module or a routing and switching link module.

[0026] Here, one operator's phone number can be selected sequentially from the four operator phone numbers pre-stored on the aforementioned device network electronic card as a test phone number, written into the aforementioned device network traffic card using the aforementioned logic array, and the aforementioned all-network communication module can be controlled to perform network communication connection using the aforementioned test phone number.

[0027] Specifically, before obtaining network communication connection information corresponding to each operator's phone number to obtain a network communication connection information set, and storing the network communication connection information set in the storage module, the process includes the following steps: The processing module selects one of the four carrier phone numbers pre-stored on the network electronic card of the aforementioned device as the test phone number.

[0028] Perform the following steps for each test phone number using a logical array: The first step is to clear the initial number from the industrial data card of the aforementioned equipment.

[0029] The second step is to write the test phone number to the industrial data card of the device. Writing different carrier phone numbers to the industrial data card allows access to the corresponding carrier's network.

[0030] The third step involves, upon completion of the write operation, controlling the all-network communication module to establish a network communication connection between the written device's industrial data card and the communication base station. Specifically, the data traffic of the four carrier phone numbers on the device's network electronic card is shared.

[0031] Step S2 involves obtaining network communication connection information corresponding to each operator's phone number, resulting in a network communication connection information set, and storing this set in the storage module. Each network communication connection information corresponds to one operator's phone number.

[0032] In practice, for each carrier phone number, the following steps are performed to generate each network communication connection information in the network communication connection information set: The first step is to obtain the fiber optic transmission signal strength, wireless transmission signal strength, base station signal strength, wireless received signal strength, and signal-to-noise ratio (SNR) values ​​for the aforementioned operator's phone number over a specific period. This period can be pre-set, for example, within one hour of the current time. Here, the wireless transmission signal strength value (RSSI, Received Signal Strength Indicator) characterizes the strength of the wireless transmission signal and determines whether interference exists in the system. The base station signal strength value (RSRP, Reference Signal Received Power) characterizes the downlink signal power strength from the base station antenna to the substation equipment. The wireless received signal strength value (RSRQ, Reference Signal Received Quality) characterizes the ratio of the received reference signal to other interfering signals, measured in dB. A higher RSRQ value indicates less interference and better signal quality. The signal-to-noise ratio (SINR, Signal to Interference plus Noise Ratio) is the ratio of signal strength to interference plus noise. SINR is a parameter measuring signal quality; it represents the ratio of the strength of the received useful signal to the strength of the received interfering signal (including noise and interference), measured in dB. A higher SINR value indicates better signal quality. Additionally, by introducing the fiber optic transmission signal strength value, it can be used to measure fiber optic signals. Specifically, both wired and wireless connections can be measured simultaneously during signal testing. In practice, when power equipment communicates, fiber optic connections (i.e., wired connections) are prioritized; if the fiber optic signal is interrupted, a wireless connection is used instead.

[0033] The second step is to determine the network communication connection information by matching the above-mentioned operator phone numbers with the corresponding fiber optic transmission signal strength value, wireless transmission signal strength value, base station signal strength value, wireless reception signal strength value, and signal-to-noise ratio value.

[0034] Step S3: Based on the above network communication connection information set, select the operator's phone number that meets the preset communication conditions from the above four operator phone numbers as the target phone number, and use the above logic array to write the target phone number into the above equipment industrial traffic card, and perform network communication equipment networking operation to provide network connection for the substation equipment through the above wireless module or the above routing and switching link module.

[0035] Optionally, based on the aforementioned network communication connection information set, the target phone number is selected from the four operator phone numbers that meet the preset communication conditions, including the following steps: The first step is to retrieve the signal strength weight data for each operator's phone number from the aforementioned storage module, thus obtaining a signal strength weight dataset. This signal strength weight data is pre-generated based on network fluctuations of the four operator's phone numbers at different time periods. Secondly, each signal strength weight dataset can include five weight values ​​corresponding to: fiber optic transmission signal strength, wireless transmission signal strength, base station signal strength, wireless received signal strength, and signal-to-noise ratio.

[0036] The second step involves fusing the signal strength weight data corresponding to each operator's phone number from the aforementioned signal strength weight dataset with the fiber optic transmission signal strength value, wireless transmission signal strength value, base station signal strength value, wireless reception signal strength value, and signal-to-noise ratio (SNR) value from the corresponding network communication connection information to generate a signal connection strength value. Specifically, the fiber optic transmission signal strength value, wireless transmission signal strength value, base station signal strength value, wireless reception signal strength value, and SNR value can be weighted and summed with their corresponding weight values ​​to obtain the signal connection strength value. Here, the aforementioned signal connection strength value represents the network signal strength value corresponding to the aforementioned operator's phone number.

[0037] The third step is to determine that the operator's phone number corresponding to the largest signal connection strength value among all signal connection strength values ​​meets the above-mentioned preset communication conditions, and then use the operator's phone number corresponding to the largest signal connection strength value as the target phone number.

[0038] Optionally, if the detected network connection signal is less than the preset signal strength, it can be determined that the network connection status of the power equipment is in a network fluctuation state.

[0039] Step S4: In response to detecting network connection fluctuations in the network connection status of the substation equipment, the network connection information of the three operator phone numbers (excluding the target phone number) out of the four operator phone numbers is detected again. Specifically, the network connection information of the three operator phone numbers out of the four operator phone numbers can be detected again through the aforementioned processing module.

[0040] Step S5: Select the operator's phone number from the three operator phone numbers whose network connection information meets the preset communication conditions as the current phone number. Here, the preset communication conditions may be that the signal strength value included in the network connection information is the highest.

[0041] Step S6: Write the current phone number to the industrial traffic card of the device and perform network communication device networking operation to control the wireless module or the routing and switching link module to provide network connection for the power equipment.

[0042] Step S7: In response to a successful network connection, generate a network detection result indicating that the network link is normal.

[0043] Optionally, in response to the determination that all network communication connection information or all network connection information does not meet the aforementioned preset communication conditions, the aforementioned execution entity controls the power-off protection module to cut off the power to the network communication equipment, and performs a restart operation and network reconnection operation after a preset time period. In practice, considering that when all network communication connection information or all network connection information does not meet the aforementioned preset communication conditions, there may be situations where signal fluctuations occur due to abnormalities in the network communication equipment (e.g., overheating). Therefore, controlling the power-off of the aforementioned network communication equipment and performing a restart operation and network reconnection operation after a preset time period can protect the aforementioned network communication equipment to a certain extent. At the same time, it greatly maintains the normal network connection.

[0044] Optionally, in response to detecting network connection fluctuations in the network connection status of the substation equipment, the aforementioned executing entity may further detect the network connection information corresponding to three of the four operator phone numbers, which may include the following steps: Step S1: In response to determining that the power equipment in the aforementioned power equipment cluster is connected to the aforementioned wireless module network, obtain the latency sequence, packet loss rate sequence, response time sequence, data upload rate sequence, and data download rate sequence of the power equipment in the aforementioned power equipment cluster within a target time period. The target time period can be a period of time preceding the current time (e.g., within 3 days). Each data point in the latency sequence, packet loss rate sequence, response time sequence, data upload rate sequence, and data download rate sequence can be in hourly units, i.e., each data point corresponds to one hour, to obtain continuous time data.

[0045] Step S2: Based on the aforementioned delay duration sequence, packet loss rate sequence, response duration sequence, data upload rate sequence, and data download rate sequence, a wireless signal fluctuation curve is generated. This involves first processing the aforementioned delay duration sequence, packet loss rate sequence, response duration sequence, data upload rate sequence, and data download rate sequence. Specifically, the data processing steps may include: 1. Data cleaning: Remove outliers or invalid data to ensure data accuracy and consistency.

[0046] 2. Standardize data: Transform the data to the same scale for subsequent analysis.

[0047] 3. Time Series Alignment: Ensure that the timestamps of all sequences are aligned for synchronous analysis. This results in the processed latency sequence, processed packet loss rate sequence, processed response time sequence, processed data upload rate sequence, and processed data download rate sequence.

[0048] Then, features can be extracted from the processed latency sequence, processed packet loss rate sequence, processed response time sequence, processed data upload rate sequence, and processed data download rate sequence. Specifically, the feature extraction steps may include: 1. Delay characteristics: Calculate the average, maximum, minimum, and standard deviation of the delay to reflect the stability and fluctuation of network delay.

[0049] 2. Packet loss characteristics: Calculate the average, maximum, minimum, and standard deviation of the packet loss rate to assess the stability and reliability of the network.

[0050] 3. Response characteristics: Calculate the average, maximum, and minimum response times to reflect the actual network response speed of the power equipment.

[0051] 4. Rate characteristics: Calculate the average, peak, and fluctuation range of upload and download speeds to assess the network's transmission capacity and bandwidth utilization.

[0052] Next, the wireless signal fluctuation curve is generated through the following steps: 1. Based on the extracted features, construct signal models (such as time series models, regression models, etc.) to simulate network signal fluctuations.

[0053] 2. Synthetic Signal: Input each feature sequence (delay, packet loss rate, response time, upload rate, download rate) into the signal model and synthesize a comprehensive signal according to the specified weights to reflect the overall fluctuation of the network signal.

[0054] 3. Smoothing: The composite signal is smoothed to reduce the impact of noise and outliers, improving signal accuracy and readability. Here, the smoothed signal is the wireless signal fluctuation curve.

[0055] Step S3: In response to determining that the mean of the aforementioned wireless signal fluctuation curve is less than a preset threshold, and that at least one of the aforementioned delay duration sequence, packet loss rate sequence, response duration sequence, data upload rate sequence, and data download rate sequence satisfies the corresponding threshold condition, a wireless fluctuation identifier characterizing abnormal network connection fluctuations of the aforementioned wireless module is generated. The threshold condition may be that at least one of the aforementioned delay duration sequence, packet loss rate sequence, and response duration sequence has a value greater than the corresponding threshold, or that at least one of the aforementioned data upload rate sequence and data download rate sequence has a value less than the corresponding threshold.

[0056] Step S4: In response to the wireless fluctuation identifier generated by the above processing module, a wired connection prompt message is sent to the substation equipment in the above substation equipment cluster.

[0057] Step S5: In response to determining that the power equipment in the aforementioned power equipment cluster is connected to the aforementioned routing switching link module network, a routing connection data sequence is obtained. This routing link data may include delay duration sequences, packet loss rate sequences, response duration sequences, data upload rate sequences, and data download rate sequences, etc.

[0058] Step S6: Based on the aforementioned routing connection data sequence, generate a wired signal fluctuation curve. The implementation method and corresponding technical effects of generating the wired signal fluctuation curve can be referred to in step S2 above, and will not be elaborated further.

[0059] Step S7: In response to determining that the mean value of the wired signal fluctuation curve is less than the mean value of the wireless signal fluctuation curve, a wireless connection prompt message is sent to the power equipment in the power equipment cluster.

[0060] Step S8: In response to determining that the mean of the wired signal fluctuation curve is less than the mean of the wireless signal fluctuation curve, and the mean of the wireless signal fluctuation curve is less than a preset threshold, and that at least one of the delay duration sequence, the packet loss rate sequence, the response duration sequence, the data upload rate sequence, and the data download rate sequence satisfies the corresponding threshold condition, the network connection information corresponding to the three operator phone numbers other than the target phone number among the four operator phone numbers is detected through the connection step.

[0061] In practice, although the network connection of the operator corresponding to the target phone number may be stable, network fluctuations may occur in the wireless module or routing and switching link module due to abnormal problems with network communication equipment. Therefore, even switching operator phone numbers cannot guarantee network stability. To solve this problem, firstly, the network connection status of operator phone numbers with signal connection strength values ​​below a preset threshold is determined to be in a state of network fluctuation. Thus, one of the other three operator phone numbers can be dynamically assigned to continue the network connection. Secondly, considering that when all network communication connection information or all network connection information does not meet the above preset communication conditions, there may be situations where signal fluctuations are caused by abnormalities in network communication equipment (e.g., overheating). Therefore, controlling the power outage of the aforementioned network communication equipment and performing restart and network connection operations after a preset time period can protect the aforementioned network communication equipment to a certain extent, while greatly maintaining normal network connectivity. This avoids the need to ensure normal network connectivity. Finally, considering that relying solely on signal connection strength values ​​to judge network fluctuations has significant discrepancies, and it is difficult to judge the fluctuations of each operator phone number based on data from different time periods. Therefore, by introducing latency sequences, packet loss rate sequences, response time sequences, data upload rate sequences, and data download rate sequences, wireless signal fluctuation curves and wired signal fluctuation curves are generated. This allows for the dynamic recording of abnormal fluctuations in each operator's phone number. Furthermore, the operator's phone number can be dynamically changed over time to further ensure normal network connectivity between power distribution equipment.

[0062] Step 102: In response to the network detection result indicating that the network link is normal, update the entity map of the substation equipment cluster to obtain the updated substation equipment association map.

[0063] In some embodiments, the execution entity may, in response to the network detection result indicating that the network link is normal, update the entity mapping of the substation equipment cluster to obtain an updated substation equipment mapping. The substation equipment mapping represents the power transmission structure relationship between the various substation equipment in the substation equipment cluster, and the updated substation equipment mapping is updated based on the substation equipment codes corresponding to each substation equipment.

[0064] In some optional implementations of certain embodiments, in response to the network detection result indicating that the network link is normal, the execution entity updates the entity mapping of the substation equipment cluster to obtain the updated substation equipment mapping, including: Step S1: Obtain the device transmission dataset of the substation equipment cluster. Each device transmission dataset corresponds to one substation equipment. The device transmission data may include information such as equipment type, equipment identifier, and substation equipment code. In practice, after joining the cluster, when transmitting data, the substation equipment can synchronously send its substation equipment code to the aforementioned execution entity.

[0065] Step S2: Extract the corresponding substation codes from the above-mentioned equipment transmission dataset to obtain a substation code set. Each substation code corresponds to one substation, and these codes are pre-generated based on the association relationships between the corresponding substation and other substations in the substation cluster.

[0066] In practice, substation equipment codes can consist of a region identifier, equipment identifier, status code, link identifier, and location code. For example, if the substation equipment is an oil-immersed main transformer, the corresponding equipment code could be: BJ-TRS01-110A-R-G1-XXXXOPTLSMF. Here, the region identifier is BJ, representing the Beijing area; the equipment identifier is TRS01; the equipment level identifier is 110 amps, 110 kV core; and the operating status identifier is R, indicating normal operation. The location identifier is G1, and the link identifier is XXXXOPTLSMF. Here, XXXX indicates no parent device, and OPTLSMF indicates single-mode fiber optic output.

[0067] Step S3: In response to determining that there are substation equipment codes in the above-mentioned substation equipment code set that do not match any of the preset equipment codes in the preset equipment code table, the mismatched substation equipment codes are identified as equipment codes to be added, thus obtaining a group of equipment codes to be added. The presence of substation equipment codes in the above-mentioned substation equipment code set that do not match any of the preset equipment codes in the preset equipment code table indicates that there is a change in equipment within the above-mentioned substation equipment cluster.

[0068] Specifically, the preset equipment code table stores the historical codes of each power equipment. If a certain power equipment code is not found in the table, it indicates that the corresponding power equipment structure has changed, power equipment has been added, or power equipment has been removed.

[0069] Step S4 involves decoding the aforementioned group of codes for the device to be added, resulting in a group of decoded substation equipment information. This decoding process can involve splitting the codes for the device to be added using position indexing to obtain sub-code groups. Then, the decoding information corresponding to each sub-code is determined from a pre-set decoding table, and the decoding information corresponding to each sub-code group is determined as the substation equipment decoding information according to the decoding order. Here, each piece of substation equipment decoding information corresponds to one code for the device to be added. The decoding table can be a pre-established data table based on each code and its corresponding code interpretation information.

[0070] Step S5: Based on the aforementioned substation equipment decoding information group, update the entities in the aforementioned substation equipment association graph to obtain the updated substation equipment association graph. Specifically, for each substation equipment code, if the substation equipment code includes information representing a newly added device, combine the information in the substation equipment code according to a preset feature order to form the information of the current entity, while simultaneously saving the association relationships between the current entity and other entities. Secondly, if the substation equipment code includes information representing a device change, the corresponding entity can be determined according to the device identifier, and different information can be updated to that entity, thus obtaining the updated substation equipment association graph. Here, a portion of the substation equipment code (e.g., the device identifier) ​​can also be used as the entity identifier.

[0071] In practice, considering the large amount of text data, updating entities in the substation equipment association graph using artificial intelligence processing frameworks or large semantic models is inefficient. Therefore, introducing substation equipment coding can be used for rapid entity updates. Specifically, firstly, there is no need to create corresponding text data for substation equipment; only coding according to a preset coding method is required. When the substation equipment cluster transmits data, the new substation equipment code is uploaded, allowing for real-time monitoring of substation equipment changes. Thus, the changes to the substation equipment and their corresponding parameters are determined through code parsing, thereby improving the efficiency of updating the substation equipment association graph.

[0072] Step 103: Based on the updated power equipment association map, perform power transmission status detection on the power equipment cluster to generate power transmission status detection results.

[0073] In some embodiments, the aforementioned execution entity may perform power transmission status detection on the power equipment cluster based on the updated power equipment association map to generate power transmission status detection results.

[0074] In some optional implementations of certain embodiments, the execution entity performs power transmission status detection on the substation equipment cluster based on the updated substation equipment association map to generate power transmission status detection results, including: Step S1 involves real-time power transmission status detection of the aforementioned power equipment cluster to obtain a power transmission status dataset. Specifically, the equipment operating status identifier of the power equipment can be determined from its corresponding equipment code using an index. If the equipment operating status identifier indicates that the power transmission status is operational, then the corresponding power transmission status data is obtained.

[0075] Step S2 involves performing data fluctuation detection on each power transmission status data point in the aforementioned power transmission status dataset to obtain a power fluctuation sensing result set. First, data cleaning is performed to fill in missing data and remove outliers. Then, different data types (e.g., voltage, current) are standardized. Next, a sliding window threshold is set to determine whether there are overall abnormal fluctuations in the power transmission status data within a window duration (e.g., 3 minutes). Finally, if no abnormal fluctuations are detected, a power fluctuation sensing result indicating no data anomalies is generated. Conversely, a power fluctuation sensing result indicating abnormal data fluctuations is generated. Here, each power fluctuation sensing result corresponds to a substation device.

[0076] Step S3: Based on the aforementioned power fluctuation sensing result set, and according to the entity relationships between the updated substation association map and each substation in the aforementioned substation cluster, the power transmission status data in the aforementioned power transmission status dataset is split into a set of split data groups. Each split data group in the aforementioned set of split data groups corresponds to an associated subnet composed of multiple substations. Secondly, data splitting can be performed by using the entity of the substation corresponding to each power fluctuation sensing result in the aforementioned power fluctuation sensing result set as the main node, and splitting the associated entities as child nodes, thereby obtaining associated subnets. Then, the associated subnets corresponding to the power fluctuation sensing results representing abnormal data fluctuations can be identified as associated subnets, resulting in a set of associated subnets. Finally, according to the nodes included in each associated subnet in the associated subnet group, the corresponding power transmission status data is grouped to obtain a set of split data groups. Here, each split data group corresponds to an associated subnet.

[0077] Step S4 involves performing power transmission status detection on each of the split data groups in the aforementioned set of split data groups, and generating power transmission status detection results representing power transmission status anomalies for each split data group where anomalies are detected. For each split data group, the split data can be combined into a data matrix according to the node arrangement order in the associated subnet. Then, the data matrix is ​​input into a pre-trained decision tree model to perform power transmission status detection and obtain the power transmission status detection results. Here, the output of the decision tree model can be a result vector containing two values. The first value in the result vector represents the presence of a power transmission status anomaly, and the second value represents the absence of a power transmission status anomaly. Specifically, the values ​​in the result vector can be result identifiers. If the result identifier is used as a value, the identifier "1" can represent a power transmission status anomaly, and vice versa, the identifier "0" can be used. Finally, each identifier representing a power transmission status anomaly and its corresponding entity identifier can be determined as the power transmission status detection result.

[0078] In practice, while artificial intelligence (AI) methods effectively identify anomalies in power transmission from various substation devices, they suffer from black-box issues and sample shortages, relying heavily on training with samples set for each substation. However, when faced with substation connection replacements or additions, it's difficult to promptly adapt to updated substation association maps. Therefore, step 103 allows for real-time anomaly detection of power transmission status based on a substation cluster. Specifically, grid splitting allows for the analysis of anomalies on a smaller scale. Furthermore, splitting the associated subnets incorporates the structural characteristics of substation connections during detection, making the results more reliable. Finally, machine learning algorithms are used to replace AI models as a lightweight identification method, thereby improving detection efficiency.

[0079] Step 104: In response to the determination that the power transmission status detection result indicates the existence of an abnormal power transmission status, the abnormal status feature statistics are obtained by performing abnormal status feature statistics based on the updated substation equipment association map and the power transmission status detection result.

[0080] In some embodiments, the execution entity may, in response to determining that the power transmission status detection result indicates the existence of a power transmission status anomaly, perform anomaly status feature statistics based on the updated substation equipment association map and the power transmission status detection result to obtain anomaly status feature statistics.

[0081] In some optional implementations of certain embodiments, in response to determining that the power transmission status detection result indicates the existence of a power transmission status anomaly, the execution entity performs anomaly status feature statistics based on the updated substation equipment association map and the power transmission status detection result to obtain anomaly status feature statistical data, including: Step S1: Determine the entity information in the updated substation equipment association map that corresponds to the power transmission status detection result, and use this information as target entity information to obtain a target entity information group. The target entity information is entity information that characterizes an abnormal power transmission status. Furthermore, the target entity information may include the corresponding entity identifier and power transmission status data.

[0082] Step S2: Using the aforementioned target entity information group and historical abnormal state information set, perform abnormal state feature statistics to obtain abnormal state feature statistical data. This abnormal state feature statistics may involve determining the frequency of abnormal occurrence, the magnitude of abnormal fluctuations, the duration of abnormality, and the entity identifier associated with the abnormality for each entity in the target entity information and historical abnormal state information sets, and using these as the abnormal state feature statistical data.

[0083] In practice, statistical analysis of the characteristics of power transmission anomalies detected in various power transmission equipment can be used for subsequent maintenance of the equipment.

[0084] Step 105: Based on the power transmission status detection results and abnormal status characteristic statistics, issue an abnormal power transmission status warning, and record the abnormal status characteristic statistics, the updated substation equipment association map, and the power transmission status detection results in the preset substation equipment knowledge base.

[0085] In some embodiments, the aforementioned executing entity can issue a power transmission status anomaly warning based on the power transmission status detection results and the aforementioned abnormal status characteristic statistics, and record the aforementioned abnormal status characteristic statistics, the aforementioned updated substation equipment association map, and the aforementioned power transmission status detection results in a preset substation equipment knowledge base. Specifically, firstly, a power anomaly table record can be constructed using the aforementioned abnormal status characteristic statistics, the aforementioned updated substation equipment association map, and the aforementioned power transmission status detection results. Then, the aforementioned power anomaly table record can be input into the preset substation equipment knowledge base. Here, by recording various data, it can be used for anomaly backtracking and intelligent management of abnormal states. Additionally, the substation equipment with abnormal power transmission status can be coded as warning information, thereby providing a power transmission status anomaly warning.

[0086] The above embodiments of this disclosure have the following beneficial effects: The intelligent management method for abnormal states applied to power equipment clusters according to some embodiments of this disclosure can improve the efficiency and accuracy of abnormal state detection of power equipment. Specifically, the intelligent management method for abnormal states applied to power equipment clusters according to some embodiments of this disclosure first performs network link anomaly detection on the network communication equipment of the power equipment cluster to generate network detection results. Here, by performing network link anomaly detection, network fluctuations can be determined in a timely manner, reducing the impact on abnormal state detection of power equipment and improving its accuracy. Simultaneously, this also ensures timely network link connectivity, thereby improving the efficiency of abnormal state detection. Then, in response to the network detection results indicating normal network links, the power equipment association graph corresponding to the power equipment cluster is updated to obtain an updated power equipment association graph. The power equipment association graph represents the power transmission structure relationship between various power equipment in the power equipment cluster, and the updated power equipment association graph is updated based on the power equipment codes corresponding to each power equipment. Here, compared to a large amount of textual data related to power equipment, by introducing power equipment coding, the amount of data required for updating the power equipment association map of the power equipment cluster is greatly reduced. Furthermore, the structural relationships between power equipment can be quickly extracted through coding, improving the efficiency of updating the power equipment association map. This accelerates the detection of the power equipment cluster. Next, based on the updated power equipment association map, the power transmission status of the power equipment cluster is detected to generate power transmission status detection results. Then, in response to the determination that the power transmission status detection results indicate the existence of an anomaly in power transmission status, anomaly status feature statistics are performed based on the updated power equipment association map and the power transmission status detection results to obtain anomaly status feature statistics. This can be used to summarize the anomalies of power equipment for intelligent management. Finally, based on the power transmission status detection results and the anomaly status feature statistics, an anomaly warning is issued, and the anomaly status feature statistics, the updated power equipment association map, and the power transmission status detection results are recorded in a preset power equipment knowledge base. This can improve the efficiency and accuracy of detecting abnormal conditions in power equipment. Further reference Figure 3 As an implementation of the methods shown in the above figures, this disclosure provides some embodiments of an intelligent management device for abnormal states applied to a substation equipment cluster. These device embodiments are similar to... Figure 1 Corresponding to the method embodiments shown, this intelligent management device for abnormal states of power equipment clusters can be specifically applied to various electronic devices.

[0087] like Figure 3As shown, an intelligent management device 300 for abnormal states applied to a power equipment cluster in some embodiments includes: a network link anomaly detection unit 301, an entity update unit 302, a power transmission status detection unit 303, an abnormal state feature statistics unit 304, and a power transmission status anomaly early warning unit 305. The network link anomaly detection unit 301 is configured to perform network link anomaly detection on the network communication devices of the power equipment cluster to generate network detection results; the entity update unit 302 is configured to update the entity of the power equipment association map corresponding to the power equipment cluster in response to the network detection results indicating that the network link is normal, thereby obtaining an updated power equipment association map. The updated power equipment association map represents the power transmission structure relationship between various power equipment in the power equipment cluster, and the updated power equipment association map is updated based on the power equipment codes corresponding to each power equipment; the power transmission status detection unit 303 is configured to perform entity updates on the power equipment based on the updated power equipment association map. The cluster performs power transmission status detection to generate power transmission status detection results; the abnormal status feature statistics unit 304 is configured to, in response to determining that the power transmission status detection results indicate the existence of power transmission status anomalies, perform abnormal status feature statistics based on the updated substation equipment association map and the power transmission status detection results to obtain abnormal status feature statistics; the power transmission status anomaly early warning unit 305 is configured to issue a power transmission status anomaly early warning based on the power transmission status detection results and the abnormal status feature statistics, and record the abnormal status feature statistics, the updated substation equipment association map, and the power transmission status detection results in a preset substation equipment knowledge base.

[0088] It is understandable that the units described in the intelligent management device 300 for abnormal states applied to substation equipment clusters are similar to those in the reference system. Figure 1 The steps in the described method correspond accordingly. Therefore, the operations, features, and beneficial effects described above for the method are also applicable to the intelligent abnormal state management device 300 and its constituent units applied to the substation equipment cluster, and will not be repeated here. The following is for reference. Figure 4 It illustrates a schematic diagram of the structure of an electronic device (such as a computing device) suitable for implementing some embodiments of the present disclosure. Figure 4 The electronic device shown is merely an example and should not be construed as limiting the functionality or scope of the embodiments of this disclosure. Figure 4As shown, the computer device includes a processor, memory, and a network interface connected via a system bus. The memory may include a non-volatile storage medium and internal memory. The non-volatile storage medium may store an operating system and a computer program. The computer program includes program instructions that, when executed, cause the processor to perform any of the methods described above. The processor provides computational and control capabilities to support the operation of the entire computer device. The internal memory provides an environment for the execution of the computer program in the non-volatile storage medium; when executed by the processor, the computer program causes the processor to perform any of the methods described above. The network interface is used for network communication, such as sending assigned tasks. Those skilled in the art will understand that... Figure 4 The structure shown is merely a block diagram of a portion of the structure related to the present disclosure and does not constitute a limitation on the computer device to which the present disclosure is applied. A specific computer device may include more or fewer components than those shown in the figure, or combine certain components, or have different component arrangements.

[0089] It should be understood that the processor can be a Central Processing Unit (CPU), but it can also be other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. Among these, a general-purpose processor can be a microprocessor or any conventional processor.

[0090] In one embodiment, the processor is configured to run a computer program stored in a memory to perform the following steps: perform network link anomaly detection on the network communication devices of the substation equipment cluster to generate network detection results; in response to the network detection results indicating that the network link is normal, update the substation equipment association map corresponding to the substation equipment cluster to obtain an updated substation equipment association map, wherein the substation equipment association map represents the power transmission structure relationship between each substation equipment in the substation equipment cluster, and the updated substation equipment association map is updated according to the substation equipment code corresponding to each substation equipment; based on the updated substation equipment association map... The system uses an equipment association map to detect the power transmission status of a cluster of substation equipment, generating power transmission status detection results. In response to the determination that the power transmission status detection results indicate an anomaly in power transmission status, it performs anomaly characteristic statistics based on the updated substation equipment association map and the power transmission status detection results, obtaining anomaly characteristic statistical data. Based on the power transmission status detection results and the anomaly characteristic statistical data, it issues an anomaly warning for power transmission status, and records the anomaly characteristic statistical data, the updated substation equipment association map, and the power transmission status detection results in a pre-defined substation equipment knowledge base.

[0091] This disclosure also provides a computer-readable storage medium storing a computer program, the computer program including program instructions, and the method implemented when the program instructions are executed can be referred to the various embodiments of the methods described above.

[0092] The aforementioned computer-readable storage medium may be an internal storage unit of the computer device described in the foregoing embodiments, such as the hard disk or memory of the computer device. Alternatively, the aforementioned computer-readable storage medium may be an external storage device of the computer device, such as a plug-in hard disk, SmartMedia Card (SMC), Secure Digital (SD) card, or Flash Card equipped on the computer device.

[0093] It should be noted that, in this document, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or system 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 system. Unless otherwise specified, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or system that includes that element.

[0094] The above description is merely a selection of preferred embodiments of this disclosure and an explanation of the technical principles employed. Those skilled in the art should understand that the scope of the invention involved in the embodiments of this disclosure is not limited to technical solutions formed by specific combinations of the above-described technical features, but should also cover other technical solutions formed by arbitrary combinations of the above-described technical features or their equivalents without departing from the above-described inventive concept. For example, technical solutions formed by substituting the above-described features with (but not limited to) technical features with similar functions disclosed in the embodiments of this disclosure.

Claims

1. An intelligent management method for abnormal states applied to a cluster of power equipment, characterized in that, include: Perform network link anomaly detection on the network communication equipment of the substation equipment cluster to generate network detection results; In response to the network detection result indicating that the network link is normal, the device transmission dataset of the substation equipment cluster is obtained; The transformer codes corresponding to each transformer are extracted from the equipment transmission dataset to obtain a transformer code set, wherein each transformer code corresponds to one transformer. The transformer codes are generated in advance based on the association relationship between the corresponding transformer and other transformers in the transformer cluster. In response to determining that there are transformer codes in the transformer code set that do not match the preset device codes in the preset device code table, the mismatched transformer codes are identified as device codes to be added, resulting in a group of device codes to be added. The mismatched transformer codes indicate that there is a device change in the transformer cluster. The group of device codes to be added is decoded to obtain a transformer decoded information group. Based on the transformer decoded information group, entities are updated in the transformer association graph to obtain an updated transformer association graph. The transformer association graph represents the power transmission structure relationship between each transformer in the transformer cluster, and the updated transformer association graph is updated based on the transformer codes corresponding to each transformer. Based on the updated power equipment association map, power transmission status detection is performed on the power equipment cluster to generate power transmission status detection results. In response to determining that the power transmission status detection result indicates the existence of a power transmission status anomaly, the abnormal status feature statistics are obtained by performing anomaly status feature statistics based on the updated substation equipment association map and the power transmission status detection result. Based on the power transmission status detection results and the abnormal status characteristic statistics, an abnormal power transmission status warning is issued, and the abnormal status characteristic statistics, the updated substation equipment association map, and the power transmission status detection results are recorded in a preset substation equipment knowledge base.

2. The method according to claim 1, characterized in that, The step of performing power transmission status detection on the substation cluster based on the updated substation equipment association map to generate power transmission status detection results includes: Real-time power transmission status detection is performed on the power equipment cluster to obtain a power transmission status dataset; Data fluctuation detection is performed on each power transmission status data in the power transmission status dataset to obtain a power fluctuation perception result set. Based on the power fluctuation sensing result set, according to the entity relationship between the updated power equipment association map and each power equipment in the power equipment cluster, the power transmission status data in the power transmission status dataset is split into a set of split data groups, wherein each split data group in the set of split data groups corresponds to an association subnet composed of multiple power equipment. Power transmission status detection is performed on each of the split data groups in the split data group set, and for each split data group where power transmission status anomalies are detected, a power transmission status detection result characterizing the power transmission status anomaly is generated.

3. The method according to claim 2, characterized in that, In response to determining that the power transmission status detection result indicates the existence of a power transmission status anomaly, the abnormal status feature statistics are obtained by performing anomaly status feature statistics based on the updated substation equipment association map and the power transmission status detection result, including: The entity information corresponding to the power transmission status detection result in the updated substation equipment association map is determined as the target entity information, and a target entity information group is obtained. The target entity information is the entity information that characterizes the abnormal power transmission status. Using the target entity information group and the historical abnormal state information set, abnormal state feature statistics are performed to obtain abnormal state feature statistics.

4. The method according to claim 1, characterized in that, The network communication equipment includes: a wireless module, a routing and switching link module, a full-network communication module, a processing module, a logic array, a storage module, and an industrial traffic card. The industrial traffic card contains a corresponding network electronic card. The process of detecting network link anomalies in the network communication equipment of the substation equipment cluster to generate network detection results includes: In response to receiving a network connection command from a power equipment in a power equipment cluster, the wireless module or routing and switching link module connected to the power equipment is controlled to send the network connection command to the full-network communication module and the processing module. The processing module is used to perform network connection operations on four operator phone numbers pre-stored on the network electronic card of the device according to the network connection command. Obtain network communication connection information corresponding to each operator's phone number to obtain a network communication connection information set, and store the network communication connection information set in the storage module; Based on the network communication connection information set, select the operator's phone number that meets the preset communication conditions from the four operator phone numbers as the target phone number, and use the logic array to write the target phone number into the equipment industrial traffic card, and perform network communication equipment networking operation to provide network connection for the power equipment through the wireless module or the routing and switching link module; In response to the detection that the network connection status of the power equipment is in a state of network fluctuation, the network connection information of the three operator phone numbers other than the target phone number among the four operator phone numbers is detected again; Select the operator's phone number from the three operator phone numbers whose network connection information meets the preset communication conditions as the current phone number; Write the current phone number into the industrial data card of the device, and perform network communication device networking operation to control the wireless module or the routing and switching link module to provide network connection for the power equipment; In response to a successful network connection, a network detection result indicating that the network link is normal is generated.

5. The method according to claim 4, characterized in that, Before obtaining the network communication connection information corresponding to each operator's phone number, obtaining the network communication connection information set, and storing the network communication connection information set in the storage module, the method further includes: The processing module selects one of the four carrier phone numbers pre-stored on the device's network electronic card as the test phone number. Perform the following steps on the test phone number using a logical array: Clear the initial number from the industrial flow card of the device; Write the test phone number to the device's industrial data card; Upon completion of the write operation, the control module connects the written device industrial traffic card to the communication base station for network communication.

6. The method according to claim 5, characterized in that, The step of selecting a target phone number from the four operator phone numbers that meets preset communication conditions based on the network communication connection information set includes: The signal strength weight data corresponding to each operator's phone number is obtained from the storage module to obtain the signal strength weight dataset; For each operator's phone number, the signal strength weight data corresponding to the operator's phone number in the signal strength weight dataset is fused with the fiber optic transmission signal strength value, wireless transmission signal strength value, base station signal strength value, wireless reception signal strength value and signal-to-noise ratio value in the corresponding network communication connection information to generate a signal connection strength value. In response to determining that the operator's phone number corresponding to the largest signal connection strength value among all signal connection strength values ​​meets the preset communication conditions, the operator's phone number corresponding to the largest signal connection strength value is taken as the target phone number.

7. An intelligent management device for abnormal states applied to a cluster of power equipment, characterized in that, include: The network link anomaly detection unit is configured to perform network link anomaly detection on the network communication equipment of the substation equipment cluster in order to generate network detection results; The entity update unit is configured to obtain the device transmission dataset of the substation equipment cluster in response to the network detection result indicating that the network link is normal. The transformer codes corresponding to each transformer are extracted from the equipment transmission dataset to obtain a transformer code set, wherein each transformer code corresponds to one transformer. The transformer codes are generated in advance based on the association relationship between the corresponding transformer and other transformers in the transformer cluster. In response to determining that there are transformer codes in the transformer code set that do not match the preset device codes in the preset device code table, the mismatched transformer codes are identified as device codes to be added, resulting in a group of device codes to be added. The mismatched transformer codes indicate that there is a device change in the transformer cluster. The group of device codes to be added is decoded to obtain a transformer decoded information group. Based on the transformer decoded information group, entities are updated in the transformer association graph to obtain an updated transformer association graph. The transformer association graph represents the power transmission structure relationship between each transformer in the transformer cluster, and the updated transformer association graph is updated based on the transformer codes corresponding to each transformer. The power transmission status detection unit is configured to perform power transmission status detection on the substation equipment cluster based on the updated substation equipment association map, so as to generate power transmission status detection results. An abnormal state feature statistics unit is configured to perform abnormal state feature statistics based on the updated substation equipment association map and the power transmission status detection result in response to determining that the power transmission status detection result indicates the existence of an abnormal power transmission status. The power transmission status anomaly early warning unit is configured to issue a power transmission status anomaly early warning based on the power transmission status detection results and the abnormal status feature statistics, and to record the abnormal status feature statistics, the updated substation equipment association map, and the power transmission status detection results in a preset substation equipment knowledge base.

8. An electronic device, characterized in that, include: One or more processors; Storage device, on which one or more programs are stored, When the one or more programs are executed by the one or more processors, the one or more processors implement the method as described in any one of claims 1-6.

9. A computer-readable medium, characterized in that, It stores a computer program thereon, wherein the program, when executed by a processor, implements the method as described in any one of claims 1-6.

Images