A cross-region operation and maintenance method, device, medium and program product of a power equipment

Abstract

The application provides a cross-region operation and maintenance method, device, medium and program product of power equipment, and relates to the technical field of power equipment monitoring. The method comprises the following steps: acquiring an environment parameter set monitored by an edge computing node in real time and operation state data of a target power equipment in a target region; calling a preset regional coupling weight table from a cross-region equipment database according to the environment parameter set to generate a composite dynamic benchmark parameter set; acquiring a time domain mutation feature, an environment coupling feature set and a device state fingerprint code output by a local abnormality judgment engine; executing a cross-region collaborative diagnosis operation according to the time domain mutation feature, the environment coupling feature set and the device state fingerprint code to generate a dynamic parameter correction instruction set; and controlling the edge computing node to execute a cross-region collaborative control operation according to the dynamic parameter correction instruction set. The technical problem of low accuracy of cross-region operation and maintenance of power equipment in the related art is solved, and the technical effect of improving the accuracy of cross-region operation and maintenance of power equipment is achieved.

Description

Technical Field

[0001] This application relates to the field of power equipment monitoring technology, and in particular to a cross-regional operation and maintenance method, equipment, medium and program product for power equipment. Background Technology

[0002] With the rapid development of power systems, the safe operation and efficient maintenance of power equipment have become important issues in the power industry. This is especially true in large-scale, cross-regional power networks, where real-time monitoring and fault early warning of equipment are of paramount importance.

[0003] In related technologies, sensors are typically installed on power equipment to collect operational status data (e.g., current, voltage, etc.) in order to monitor the operating status of the equipment. This data is then transmitted wirelessly to a cloud server, where it is centrally processed and analyzed. Specifically, the cloud server utilizes big data analytics and machine learning algorithms to perform in-depth data mining and pattern recognition, aiming to achieve early warning and diagnosis of power equipment faults.

[0004] However, using the above methods, in large-scale power networks spanning different regions, the operating environments of power equipment vary greatly. This regional difference may lead to inaccurate assessment and analysis of the operating status of power equipment during cross-regional operation and maintenance, resulting in a low accuracy rate of cross-regional operation and maintenance of power equipment in related technologies. Summary of the Invention

[0005] This application provides a method, equipment, medium, and program product for cross-regional operation and maintenance of power equipment, which can improve the accuracy of cross-regional operation and maintenance of power equipment.

[0006] Firstly, this application provides a cross-regional operation and maintenance method for power equipment, applied to the aforementioned electronic equipment. The method includes: deploying edge computing nodes in the target region where the target power equipment is located, and acquiring a first set of environmental parameters and operating status data of the target power equipment obtained from real-time monitoring of the target region by the edge computing nodes. The first set of environmental parameters includes a first dynamic temperature gradient, a first humidity change rate, and a first geographic coordinate feature; the operating status data includes a first current harmonic component, a first voltage transient waveform, a first vibration energy spectral density, and a first vibration spectrum. Based on the first geographic coordinate feature, a preset regional coupling weight table is retrieved from a cross-regional equipment database. The preset regional coupling weight table includes parameters related to the target region. The system establishes association rules for equipment operating parameters in historically similar geographical regions; it generates a composite dynamic benchmark parameter set based on the first dynamic temperature gradient, the first humidity change rate, and the association rules for equipment operating parameters; it inputs operating status data into a local anomaly detection engine to obtain the temporal abrupt change features, environmental coupling feature set, and equipment status fingerprint code output by the local anomaly detection engine after performing multimodal anomaly detection on the operating status data based on the composite dynamic benchmark parameter set; it performs cross-regional collaborative diagnostic operations based on the temporal abrupt change features, environmental coupling feature set, and equipment status fingerprint code to generate a dynamic parameter correction instruction set; and it distributes the dynamic parameter correction instruction set to edge computing nodes to control the edge computing nodes to perform cross-regional collaborative control operations.

[0007] By adopting the above technical solution, edge computing nodes acquire environmental parameters and operational status data of target power equipment in real time. Utilizing geographic coordinate features to call a pre-defined regional coupling weight table, inter-regional correlation of equipment operational parameters can be achieved, thereby enhancing cross-regional collaboration in operation and maintenance. A composite dynamic benchmark parameter set generated by combining dynamic temperature gradients, humidity change rates, and equipment operational parameter correlation rules provides a dynamic, environment-related benchmark for anomaly detection. Inputting operational status data into the local anomaly detection engine accurately identifies the anomaly characteristics of the target power equipment. Generating a dynamic parameter correction instruction set through cross-regional collaborative diagnosis and distributing it to edge computing nodes for collaborative control enables intelligent and precise control of the target power equipment's operation and maintenance, effectively improving the efficiency and accuracy of cross-regional operation and maintenance. This solves the technical problem of low accuracy in cross-regional operation and maintenance of power equipment in related technologies, achieving the technical effect of improving the accuracy of cross-regional operation and maintenance of power equipment.

[0008] Optionally, a composite dynamic benchmark parameter set is generated based on the first dynamic temperature gradient, the first humidity change rate, and the association rules of equipment operating parameters. Specifically, this includes: performing regional feature extraction operations on the first dynamic temperature gradient and the first humidity change rate according to a preset time window to generate a regional feature vector; mapping the regional feature vector to a preset benchmark parameter template to obtain an association mapping result, wherein the benchmark parameter template is a parameter association table constructed based on historical operating data of power equipment in multiple regions, and the parameter association table includes equipment operating threshold ranges corresponding to different combinations of environmental parameters; determining the dynamic environmental disturbance factor of the target region based on the association mapping result and the association rules of equipment operating parameters, wherein the dynamic environmental disturbance factor is a weighting coefficient of the impact of environmental changes on the operating state of the target power equipment; and adjusting the preset anomaly judgment threshold of the target power equipment based on the association mapping result and the dynamic environmental disturbance factor to generate a composite dynamic benchmark parameter set for the target region.

[0009] By employing the above technical solution, the correspondence between regional feature vectors and benchmark parameter templates is determined based on regional feature extraction and correlation mapping. Furthermore, by combining equipment operating parameter correlation rules, dynamic environmental disturbance factors are determined, thereby more accurately reflecting the impact of environmental changes on the operating status of target power equipment. Based on the correlation mapping results and dynamic environmental disturbance factors, the preset anomaly judgment threshold is adjusted, resulting in a composite dynamic benchmark parameter set that better reflects actual operating conditions, further improving the accuracy of anomaly detection.

[0010] Optionally, the operating status data is input to the local anomaly detection engine to obtain the time-domain abrupt change features, environmental coupling feature set, and device status fingerprint code output by the local anomaly detection engine after performing multimodal anomaly detection on the operating status data based on the composite dynamic reference parameter set. Specifically, this includes: inputting the operating status data to the local anomaly detection engine to control the local anomaly detection engine to perform the following operations: the local anomaly detection engine normalizes the first current harmonic component, the first voltage transient waveform, the first vibration energy spectral density, and the first vibration spectrum to generate a composite status index; the local anomaly detection engine uses a preset sliding window algorithm to segment the first time-series data of the composite status index to determine the deviation between the composite status index and the composite dynamic reference parameter set, wherein the first time-series data is a composite... The composite state index is obtained from continuous time-series data before segmentation. The first time-series data includes the time-series data of the first current harmonic component, the first voltage transient waveform, the first vibration energy spectral density, and the first vibration spectrum after normalization. The deviation is the degree of difference between the composite state index and the composite dynamic reference parameter set. When the local anomaly judgment engine determines that the deviation is greater than a preset deviation threshold, it triggers a potential anomaly event and determines a sudden change time window, where the sudden change time window is the time interval in which the deviation is greater than the preset deviation threshold. The local anomaly judgment engine performs multimodal anomaly feature extraction operation based on the sudden change time window and the composite dynamic reference parameter set. The time-domain sudden change features, environmental coupling feature set, and device status fingerprint code output by the local anomaly judgment engine after performing the multimodal anomaly feature extraction operation are obtained.

[0011] By employing the above technical solution, the operational status data is normalized to generate a unified composite status index, facilitating subsequent analysis. Using a sliding window algorithm to segment the composite status index accurately determines the deviation between the composite status index and the composite dynamic benchmark parameter set. When the deviation exceeds a preset deviation threshold, a potential abnormal event is triggered, and a sudden change time window is determined, providing a foundation for subsequent multimodal anomaly feature extraction. By performing multimodal anomaly feature extraction, the anomaly characteristics of the target power equipment can be comprehensively acquired.

[0012] Optionally, the local anomaly detection engine performs multimodal anomaly feature extraction based on the mutation time window and the composite dynamic benchmark parameter set. Specifically, this includes: the local anomaly detection engine extracts energy mutation points of the composite state index within the mutation time window from the dynamic environmental disturbance factors in the composite dynamic benchmark parameter set, and determines the mutation intensity, duration, and correlation of these energy mutation points to generate time-domain mutation features. The second time-series data is the continuous time series data of the composite state index within the mutation time window, and the mutation correlation is the correlation feature between the energy mutation point and historical energy mutation points. The local anomaly detection engine also determines the correlation between the energy mutation point and historical energy mutation points based on the regional feature vector in the composite dynamic benchmark parameter set. The second dynamic temperature gradient, second humidity change rate, and second geographic coordinate feature quantity corresponding to the time window are used to generate an environmental coupling feature set, wherein the environmental coupling feature set characterizes the correlation between the first environmental parameter and the sudden change in the operating state of the target power equipment; the local anomaly judgment engine determines the complexity features of the second current harmonic component, second voltage transient waveform, second vibration energy spectral density, and second vibration spectrum of the composite state index within the sudden change time window based on the equipment operating threshold interval in the composite dynamic benchmark parameter set, so as to generate the equipment state fingerprint code, wherein the second time series data includes the time series data of the second current harmonic component, second voltage transient waveform, second vibration energy spectral density, and second vibration spectrum after normalization processing.

[0013] By employing the above technical solution, energy mutation points are extracted within the mutation time window, and the mutation intensity, duration, and correlation of these points are determined, thereby ensuring the accuracy of temporal mutation feature extraction. Based on the environmental parameters corresponding to the mutation time window, an environmental coupling feature set is generated to characterize the correlation between environmental parameters and equipment operating state mutations. Furthermore, the complexity characteristics of composite state indicators within the mutation time window are determined, and equipment state fingerprint codes are generated, providing a reliable basis for the unique identification and anomaly diagnosis of target power equipment.

[0014] Optionally, cross-regional collaborative diagnostic operations are performed based on temporal abrupt change features, environmental coupling feature sets, and device status fingerprint codes to generate a dynamic parameter correction instruction set. Specifically, this includes: filtering historical anomaly events from a cross-regional device database based on second geographic coordinate features and preset filtering conditions, wherein historical anomaly events include historical environmental parameter sets that are the same as or similar to the first environmental parameter set; determining first historical anomaly features, historical repair strategies, and historical associated device parameter correction records based on historical anomaly events and historical environmental parameter sets; performing similarity matching between device status fingerprint codes and historical device status fingerprint codes in historical anomaly events to match candidate anomaly events, wherein historical anomaly events include candidate anomaly events; and performing association matching between temporal abrupt change features and second historical anomaly features of candidate anomaly events to obtain cross-regional anomaly correlation, wherein the first historical anomaly features... The common features include second historical anomaly features; based on the cross-regional anomaly correlation degree and historical correlation equipment parameter correction records, the potential anomaly source, associated impact parameters, and cross-regional cascading risk paths of the target power equipment are deduced in reverse. Among them, the associated impact parameters are parameters in the first environmental parameter set and operating status data that are directly or indirectly related to the potential anomaly source, and the cross-regional cascading risk paths are the paths through which the potential anomaly source propagates among multiple power equipment in different regions through the physical connection and logical dependency of the power grid. The multiple power equipment includes the target power equipment; anomaly repair priorities are generated based on the potential anomaly source, associated impact parameters, cross-regional cascading risk paths, and historical repair strategies. Among them, the anomaly repair priorities are quantitative indicators of the urgency of repairing different potential anomaly sources; and a dynamic parameter correction instruction set is generated based on the potential anomaly source, associated impact parameters, cross-regional cascading risk paths, and anomaly repair priorities.

[0015] By employing the above technical solution, historical anomalies similar to the current anomaly are screened out. These historical anomaly characteristics, historical repair strategies, and historical related equipment parameter correction records are then used to match and correlate candidate anomalies. By reverse-engineering potential anomaly sources, associated impact parameters, and cross-regional cascading risk paths, the root cause and propagation path of the anomaly can be accurately identified. Anomaly repair priorities are generated based on potential anomaly sources, associated impact parameters, cross-regional cascading risk paths, and historical repair strategies. A dynamic parameter correction instruction set is also generated based on these same criteria, enabling targeted anomaly repair and parameter adjustments, thereby improving operational efficiency and equipment reliability.

[0016] Optionally, a dynamic parameter correction instruction set specifically includes: dynamically adjusting the first correction weight of the coupling coefficient correction value in the preset regional coupling weight table according to the anomaly repair priority, so as to optimize the correlation rules of equipment operation parameters between regions, wherein the adjustment range of the first correction weight is positively correlated with the anomaly repair priority; determining the feedback compensation parameter of the dynamic environmental disturbance factor based on the cross-regional anomaly correlation degree and historical correlation equipment parameter correction records, wherein the feedback compensation parameter quantifies the interference intensity of environmental noise on composite state indicators; generating an edge meter based on the equipment maintenance cycle in the historical repair strategy and the priority mark in the cross-regional chain risk path. The monitoring frequency adaptive adjustment strategy for computing nodes includes increasing the monitoring frequency of the first power equipment corresponding to high-risk paths to the preset upper limit, and decreasing the monitoring frequency of the second power equipment corresponding to low-risk paths to the preset lower limit. Cross-regional chain risk paths include high-risk paths and low-risk paths, and the target power equipment includes the first power equipment and the second power equipment. The second correction weight and the regional correlation parameter compensation value of the composite dynamic benchmark parameter set are dynamically adjusted according to the parameter optimization trend in the historical related equipment parameter correction record. The adjustment direction of the second correction weight is the same as the parameter optimization trend.

[0017] By adopting the above technical solution, dynamically adjusting the first correction weight of the coupling coefficient correction value in the preset regional coupling weight table can optimize the correlation rules of equipment operating parameters between regions, making the correlation rules of equipment operating parameters more consistent with actual operating conditions. By determining the feedback compensation parameters of dynamic environmental disturbance factors, the interference intensity of environmental noise on composite state indicators can be quantified, thereby improving the accuracy of anomaly detection. In addition, an adaptive adjustment strategy for the monitoring frequency of edge computing nodes is generated, which can adaptively adjust the monitoring frequency according to the risk level of the target power equipment, thereby improving monitoring efficiency. By dynamically adjusting the second correction weight of the composite dynamic benchmark parameter set and the regional correlation parameter compensation value, the benchmark and parameters for anomaly detection can be further optimized, thereby improving the intelligent level of cross-regional operation and maintenance of power equipment.

[0018] Optionally, the dynamic parameter correction instruction set is sent to the edge computing nodes to control them to perform cross-regional collaborative control operations. Specifically, this includes: updating the preset regional coupling weight table based on the coupling coefficient correction value, and reconstructing the composite dynamic benchmark parameter set based on the updated preset regional coupling weight table; performing pre-distortion compensation processing on the subsequently collected second environmental parameter set based on the feedback compensation parameters. The second environmental parameter set is the set of environmental parameters collected after the first environmental parameter set, and the pre-distortion compensation processing involves performing inverse noise suppression on the third dynamic temperature gradient and the third humidity change rate in the second environmental parameter set. The system generates a compensated set of environmental parameters; for the first power equipment marked as high risk, according to the adaptive adjustment strategy of monitoring frequency, the sampling interval of the third current harmonic component and the third vibration energy spectral density is shortened to a first preset threshold, and a high-precision sensing mode is enabled; and for the second power equipment marked as low risk, according to the adaptive adjustment strategy of monitoring frequency, the sampling interval of the fourth voltage transient waveform and the fourth vibration spectrum is extended to a second preset threshold, and a low-power sensing mode is enabled; and the preset deviation threshold of the local anomaly judgment engine is dynamically adjusted according to the regional correlation parameter compensation value and the updated composite dynamic reference parameter set.

[0019] By adopting the above technical solution, after the dynamic parameter correction instruction set is sent to the edge computing node, the preset regional coupling weight table and the composite dynamic benchmark parameter set can be updated in real time, making the composite dynamic benchmark parameter set more consistent with the current operating status and environmental conditions of the power equipment. Pre-distortion compensation processing is applied to the subsequently collected environmental parameters (corresponding to the second environmental parameter set mentioned above) to reduce the interference of environmental noise on anomaly detection. Furthermore, adjusting the sampling interval and sensing mode of the equipment according to the adaptive adjustment strategy of monitoring frequency can reduce energy consumption while ensuring monitoring accuracy. Adjusting the preset deviation threshold based on the regional correlation parameter compensation value and the updated composite dynamic benchmark parameter set can further improve the accuracy and sensitivity of anomaly detection.

[0020] In a second aspect, embodiments of this application provide an electronic device comprising: one or more processors and a memory; the memory is coupled to one or more processors and is used to store computer program code, the computer program code including computer instructions, wherein one or more processors invoke the computer instructions to cause the electronic device to perform the method described in the first aspect and any possible implementation thereof.

[0021] Thirdly, embodiments of this application provide a computer program product containing instructions that, when the computer program product is run on an electronic device, cause the electronic device to perform the method described in the first aspect and any possible implementation thereof.

[0022] Fourthly, embodiments of this application provide a computer-readable storage medium including instructions that, when executed on an electronic device, cause the electronic device to perform the method described in the first aspect and any possible implementation thereof.

[0023] One or more technical solutions provided in the embodiments of this application have at least the following technical effects or advantages:

[0024] 1. The cross-regional operation and maintenance method for power equipment provided in this application enables edge computing nodes to acquire environmental parameters and operational status data of the target region in real time. By utilizing geographic coordinate features to call a preset regional coupling weight table, the operating parameters of the equipment can be correlated between regions, thereby enhancing the cross-regional collaboration of operation and maintenance. A composite dynamic benchmark parameter set generated by combining dynamic temperature gradients, humidity change rates, and equipment operating parameter correlation rules can provide a dynamic, environment-related benchmark for anomaly detection. After inputting the operational status data into the local anomaly detection engine, the abnormal characteristics of the target power equipment can be accurately obtained. A dynamic parameter correction instruction set is generated through cross-regional collaborative diagnosis and then distributed to edge computing nodes for collaborative control, enabling intelligent and precise control of the operation and maintenance of the target power equipment, thereby effectively improving the efficiency and accuracy of cross-regional operation and maintenance of the target power equipment.

[0025] 2. The cross-regional operation and maintenance method for power equipment provided in this application determines the correspondence between regional feature vectors and benchmark parameter templates based on regional feature extraction and correlation mapping. Furthermore, by combining equipment operating parameter correlation rules, dynamic environmental disturbance factors are determined, thereby more accurately reflecting the impact of environmental changes on the operating status of the target power equipment. Based on the correlation mapping results and dynamic environmental disturbance factors, the preset anomaly judgment threshold is adjusted, and the generated composite dynamic benchmark parameter set better reflects actual operating conditions, further improving the accuracy of anomaly detection.

[0026] 3. The cross-regional operation and maintenance method for power equipment provided in this application normalizes the operating status data to generate a unified composite status index for subsequent analysis. A sliding window algorithm is used to segment the composite status index, accurately determining the deviation between the composite status index and the composite dynamic benchmark parameter set. When the deviation exceeds a preset deviation threshold, a potential abnormal event is triggered, and a sudden change time window is determined, providing a foundation for subsequent multimodal anomaly feature extraction. By performing multimodal anomaly feature extraction, the anomaly characteristics of the target power equipment can be comprehensively obtained. Attached Figure Description

[0027] Figure 1 This is a flowchart illustrating a cross-regional operation and maintenance method for power equipment in an embodiment of this application.

[0028] Figure 2 This is a schematic diagram of the physical device structure of an electronic device in an embodiment of this application. Detailed Implementation

[0029] The terminology used in the following embodiments of this application is for the purpose of describing particular embodiments only and is not intended to be limiting of this application. As used in the specification and appended claims of this application, the singular expressions “a,” “an,” “the,” “the,” “the,” and “this” are intended to include the plural expressions as well, unless the context clearly indicates otherwise. It should also be understood that the term “and / or” as used in this application refers to any or all possible combinations including one or more of the listed items.

[0030] Hereinafter, the terms "first" and "second" are used for descriptive purposes only and should not be construed as implying or suggesting relative importance or implicitly indicating the number of indicated technical features. Thus, a feature defined as "first" or "second" may explicitly or implicitly include one or more of that feature, and in the description of the embodiments of this application, unless otherwise stated, "multiple" means two or more.

[0031] This application provides a cross-regional operation and maintenance method for power equipment, see reference. Figure 1 , Figure 1 This is a flowchart illustrating a cross-regional operation and maintenance method for power equipment in an embodiment of this application, including the following steps:

[0032] Step S101: Deploy edge computing nodes in the target area where the target power equipment is located, and obtain the first set of environmental parameters and the operating status data of the target power equipment obtained by the edge computing nodes in real time monitoring the target area. The first set of environmental parameters includes the first dynamic temperature gradient, the first humidity change rate, and the first geographic coordinate feature quantity. The operating status data includes the first current harmonic component, the first voltage transient waveform, the first vibration energy spectral density, and the first vibration spectrum.

[0033] Step S102: Retrieve a preset regional coupling weight table from the cross-regional device database based on the first geographic coordinate feature. The preset regional coupling weight table includes association rules for device operating parameters of historical regions with the same or similar geographic features as the target region.

[0034] Step S103: Generate a composite dynamic reference parameter set based on the first dynamic temperature gradient, the first humidity change rate, and the association rules of equipment operating parameters;

[0035] Step S104: Input the running status data into the local anomaly detection engine to obtain the temporal abrupt change features, environmental coupling feature set, and device status fingerprint code output by the local anomaly detection engine after performing multimodal anomaly detection on the running status data based on the composite dynamic benchmark parameter set.

[0036] Step S105: Perform cross-regional collaborative diagnostic operations based on temporal abrupt change characteristics, environmental coupling feature set, and device status fingerprint encoding to generate a dynamic parameter correction instruction set;

[0037] Step S106: The dynamic parameter correction instruction set is sent to the edge computing node to control the edge computing node to perform cross-regional collaborative control operations.

[0038] In the above embodiments, the target power equipment is power equipment that needs to be monitored and managed within a specific region, such as transformers and generators. The target region is the specific geographical location or area where the target power equipment is located. The edge computing node is a computing entity deployed close to the data generation source (i.e., the target power equipment) for real-time data processing and analysis. The first environmental parameter set is the set of environmental data obtained by the edge computing node through real-time monitoring of the target region, including multiple environmental indicators. The first dynamic temperature gradient is the rate of temperature change in the target region over time and space. The first humidity change rate is the rate of humidity change in the target region. The first geographic coordinate feature is the geographic location information of the target region, such as latitude and longitude, altitude, natural landmarks such as buildings, rivers, and mountains, and artificial landmarks. Operating status data refers to various data generated by the target power equipment during operation, such as electrical parameters like current and voltage (reflecting the electrical performance and operating status of the target power equipment), power parameters like power and frequency (evaluating the energy conversion efficiency and stability of the target power equipment), environmental parameters like temperature and humidity (monitoring the environment in which the target power equipment is located to determine its impact on equipment operation), mechanical parameters like vibration and noise (reflecting the mechanical performance and operating status of the target power equipment to determine if abnormal vibration or noise exists), and chemical parameters like oil level and gas content (for certain specific equipment, used to monitor the state of the internal medium, such as transformer oil level and gas content). The first current harmonic component is the harmonic component in the current, used to reflect the waveform quality of the current. The first voltage transient waveform is the voltage fluctuation over a short period of time. The first vibration energy spectral density describes the energy distribution of the equipment vibration; this equipment vibration can be generated by the target power equipment itself or by other equipment around the target power equipment, etc., without limitation. The first vibration spectrum is used to describe the frequency distribution characteristics of the vibration signal of the target power equipment and / or other equipment around the target power equipment, that is, the magnitude or intensity of vibration energy of different frequency components. It helps to analyze the vibration state of the target power equipment and thus determine whether there is any abnormality or fault in the target power equipment.

[0039] Through the above steps, edge computing nodes acquire real-time environmental parameters and operational status data of target power equipment in the target region. By utilizing geographic coordinate features to call a pre-defined regional coupling weight table, the operational parameters of equipment across regions can be correlated, thereby enhancing cross-regional collaboration in operation and maintenance. A composite dynamic benchmark parameter set generated by combining dynamic temperature gradients, humidity change rates, and equipment operational parameter correlation rules provides a dynamic, environment-related benchmark for anomaly detection. After inputting operational status data into the local anomaly detection engine, the abnormal characteristics of the target power equipment can be accurately obtained. By generating a dynamic parameter correction instruction set through cross-regional collaborative diagnosis and distributing it to edge computing nodes for collaborative control, intelligent and precise control of the operation and maintenance of target power equipment can be achieved, effectively improving the efficiency and accuracy of cross-regional operation and maintenance. This solves the technical problem of low accuracy in cross-regional operation and maintenance of power equipment in related technologies, achieving the technical effect of improving the accuracy of cross-regional operation and maintenance of power equipment.

[0040] The entity performing the above steps may be a control system with cross-regional operation and maintenance capabilities, or a control device with cross-regional operation and maintenance capabilities, or a controller or processor in the device or system, or a standalone controller or processor, or other processing devices or processing units with similar processing functions, but is not limited to these.

[0041] In an optional embodiment, a composite dynamic benchmark parameter set is generated based on a first dynamic temperature gradient, a first humidity change rate, and equipment operating parameter association rules. Specifically, this includes: performing regional feature extraction operations on the first dynamic temperature gradient and the first humidity change rate according to a preset time window to generate a regional feature vector; mapping the regional feature vector to a preset benchmark parameter template to obtain an association mapping result, wherein the benchmark parameter template is a parameter association table constructed based on historical operating data of power equipment in multiple regions, and the parameter association table includes equipment operating threshold ranges corresponding to different combinations of environmental parameters; determining the dynamic environmental disturbance factor of the target region based on the association mapping result and equipment operating parameter association rules, wherein the dynamic environmental disturbance factor is a weighting coefficient of the impact of environmental changes on the operating state of the target power equipment; and adjusting the preset anomaly judgment threshold of the target power equipment based on the association mapping result and the dynamic environmental disturbance factor to generate a composite dynamic benchmark parameter set for the target region.

[0042] In the above embodiments, the preset time window represents a fixed time period pre-set before the regional feature extraction operation, used to limit the scope of the analyzed data and ensure the timeliness and relevance of the data. The regional feature extraction operation refers to extracting information representing the environmental characteristics of the target region from the first dynamic temperature gradient and the first humidity change rate, such as extreme weather events and seasonal changes. The regional feature vector is a mathematical vector used to represent the result of the regional feature extraction operation, with each component corresponding to a specific regional feature. The preset benchmark parameter template is a reasonable threshold range for the equipment operating status under different combinations of environmental parameters, constructed based on historical operating data of power equipment in multiple regions. The parameter association table is the specific form of the preset benchmark parameter template, including the correspondence between different combinations of environmental parameters and the equipment operating threshold range.

[0043] In the above embodiments, a preset time window is set, such as every hour, every half day, or every day, for periodic data processing. Within the preset time window, a regional feature extraction algorithm can be used to process the first dynamic temperature gradient and the first humidity change rate of the target region to generate a regional feature vector. The regional feature vector integrates the regional characteristics of the temperature gradient and humidity change rate. The regional feature extraction algorithm includes, but is not limited to, statistical analysis and trend recognition. The regional feature vector is associated and mapped with a preset benchmark parameter template. The preset benchmark parameter template is constructed based on extensively collected historical operating data of power equipment in multiple regions. The preset benchmark parameter template includes the correspondence between different combinations of environmental parameters and the equipment operating threshold range. By comparing the regional feature vector and the preset benchmark parameter template, the expected operating state range of the power equipment under the current environmental conditions can be determined. The dynamic environmental disturbance factor is determined based on the association mapping result and the preset equipment operating parameter association rule. The preset equipment operating parameter association rule describes the impact of different environmental factors on the operating state of the power equipment and the differences in this impact across different regions. The dynamic environmental disturbance factor can be a weighting coefficient used to reflect the actual degree of impact of environmental changes on the operating state of the target power equipment. The preset anomaly detection thresholds for target power equipment are adjusted based on the correlation mapping results and dynamic environmental disturbance factors. This aims to make the anomaly detection criteria more closely reflect the current actual environmental conditions, thereby improving the accuracy and effectiveness of monitoring. The adjusted set of preset anomaly detection thresholds generates a composite dynamic benchmark parameter set for the target region. This set not only includes the operating threshold information of the power equipment but also incorporates the influence of regional characteristics and dynamic environmental disturbance factors. In practical applications, the composite dynamic benchmark parameter set can be used to monitor the operating status of power equipment in real time and compare it with real-time collected operating data. If the real-time data exceeds the threshold range defined by the composite dynamic benchmark parameter set, an alarm is triggered, alerting operators to potential equipment anomalies or malfunctions. This enables precise monitoring and management of power equipment in different regions and environments.

[0044] In an optional embodiment, the operating status data is input to the local anomaly detection engine to obtain the time-domain abrupt change features, environmental coupling feature set, and device status fingerprint code output by the local anomaly detection engine after performing multimodal anomaly detection on the operating status data according to the composite dynamic reference parameter set. Specifically, this includes: inputting the operating status data to the local anomaly detection engine to control the local anomaly detection engine to perform the following operations: the local anomaly detection engine normalizes the first current harmonic component, the first voltage transient waveform, the first vibration energy spectral density, and the first vibration spectrum to generate a composite status index; the local anomaly detection engine uses a preset sliding window algorithm to segment the first time-series data of the composite status index to determine the deviation between the composite status index and the composite dynamic reference parameter set, wherein the first time-series data... The data is a continuous time series of composite state indicators before segmentation. The first time series data includes the time series data of the first current harmonic component, the first voltage transient waveform, the first vibration energy spectral density, and the first vibration spectrum after normalization. The deviation is the degree of difference between the composite state indicators and the composite dynamic reference parameter set. When the local anomaly judgment engine determines that the deviation is greater than a preset deviation threshold, it triggers a potential anomaly event and determines a sudden change time window, where the sudden change time window is the time interval in which the deviation is greater than the preset deviation threshold. The local anomaly judgment engine performs a multimodal anomaly feature extraction operation based on the sudden change time window and the composite dynamic reference parameter set. The local anomaly judgment engine then outputs the time-domain sudden change features, environmental coupling feature set, and device status fingerprint code after performing the multimodal anomaly feature extraction operation.

[0045] In the above embodiments, the local anomaly detection engine refers to a functional module dedicated to analyzing the operating status data of power equipment and determining whether anomalies exist. Normalization processing refers to converting data of different dimensions or ranges into data under a unified scale for easier comparison and analysis. The composite state index is obtained by normalizing multiple state parameters (e.g., first current harmonic component, first voltage transient waveform, first vibration energy spectral density, first vibration spectrum, etc.) and is used to represent the overall operating status of the target power equipment. The preset sliding window algorithm is an algorithm for processing time series data. It processes data in segments by sliding a fixed-length window to facilitate the analysis of local characteristics of the data. Deviation is the degree of difference between the composite state index and the composite dynamic benchmark parameter set, used to quantify the deviation of the current state of the target power equipment from its normal state. The preset deviation threshold is a pre-set threshold for determining whether an anomaly has occurred in the equipment. When the deviation exceeds the preset deviation threshold, it is considered that the target power equipment may have an anomaly (i.e., triggering a potential anomaly event). The potential anomaly event can be an anomaly event that is about to occur in the target power equipment, or an anomaly event that has already occurred in the target power equipment, etc. A mutation time window refers to the time interval within which the deviation exceeds a preset deviation threshold, used to determine the time range in which an anomaly occurs. Multimodal anomaly feature extraction refers to the process of extracting anomaly features from multiple dimensions (e.g., time domain, frequency domain, environment, etc.) for in-depth analysis of the causes of equipment anomalies. Time-domain mutation features refer to features that change abruptly in the time domain, used to describe how the equipment state changes over time. Environmental coupling feature sets refer to the correlation features between the target circuit equipment state and environmental factors (e.g., temperature, humidity, etc.), used to analyze the impact of environmental factors on the target circuit equipment state. Equipment state fingerprint encoding is obtained by encoding the target circuit equipment state features, used to uniquely identify the current state of the target power equipment.

[0046] In the above embodiments, the operating status data of the target power equipment (e.g., current, voltage, vibration, etc., reflecting the real-time operating status of the power equipment) are continuously collected and input into the local anomaly detection engine. The local anomaly detection engine receives operating status data such as the first current harmonic component, the first voltage transient waveform, the first vibration energy spectral density, and the first vibration spectrum from sensors. To unify the dimensions and eliminate differences between data, the anomaly detection engine first normalizes the operating status data, that is, converts data from different ranges to the same scale, which facilitates subsequent analysis and comparison. After normalization, the operating status data is integrated into a composite status index, comprehensively reflecting the overall operating status of the power equipment. The local anomaly detection engine uses a preset sliding window algorithm to segment the first time series data of the composite status index, dividing the continuous time series data into multiple overlapping time periods (i.e., time windows), and then processes and analyzes the data within each time window. The local anomaly detection engine can capture the changing trend and abnormal fluctuations of the composite status index in different time periods. Within each time window, the local anomaly detection engine calculates the deviation between the composite status index and the composite dynamic benchmark parameter set. The deviation is an indicator that measures the degree of difference between the current equipment status and the benchmark equipment status, and is used to reflect whether the power equipment deviates from the expected operating range.

[0047] In the above embodiments, when the local anomaly detection engine detects that the deviation within a certain time window exceeds a preset deviation threshold, it means that a potential anomaly may have occurred in the power equipment, triggering a potential anomaly event and determining a sudden change time window. The sudden change time window refers to the time interval during which the deviation exceeds the preset deviation threshold, marking the start and end times of the anomaly event. The local anomaly detection engine performs a multimodal anomaly feature extraction operation based on the sudden change time window and a composite dynamic benchmark parameter set. The multimodal anomaly feature extraction operation can extract key features of the anomaly event from multiple dimensions (e.g., time domain, frequency domain, environment, etc.). Key features include time-domain sudden change features (e.g., sudden changes in current, voltage, etc.), environmental coupling feature sets (e.g., the influence of environmental factors such as temperature and humidity on equipment status), and equipment status fingerprint encoding (a unique equipment status identifier used to distinguish different anomaly events). The local anomaly detection engine outputs key features to facilitate rapid location of the anomaly cause and take corresponding maintenance measures to ensure the stable operation of the power equipment. At the same time, the key features can also be used as training data to optimize and improve the algorithm and performance of the anomaly detection engine.

[0048] In an optional embodiment, the local anomaly detection engine performs multimodal anomaly feature extraction based on the mutation time window and the composite dynamic benchmark parameter set. Specifically, this includes: the local anomaly detection engine extracts energy mutation points of the composite state index within the mutation time window from the dynamic environmental disturbance factors in the composite dynamic benchmark parameter set, and determines the mutation intensity, mutation duration, and mutation correlation of the energy mutation points to generate time-domain mutation features. The second time-series data is continuous time-series data of the composite state index within the mutation time window, and the mutation correlation is the correlation feature between the energy mutation point and historical energy mutation points. The local anomaly detection engine determines the correlation between the energy mutation point and historical energy mutation points based on the regional feature vector in the composite dynamic benchmark parameter set. The second dynamic temperature gradient, second humidity change rate, and second geographic coordinate feature quantity corresponding to the mutation time window are used to generate an environmental coupling feature set, wherein the environmental coupling feature set characterizes the correlation between the first environmental parameter and the mutation of the target power equipment's operating state. The local anomaly judgment engine determines the complexity features of the second current harmonic component, second voltage transient waveform, second vibration energy spectral density, and second vibration spectrum of the composite state index within the mutation time window based on the equipment operating threshold range in the composite dynamic benchmark parameter set, in order to generate an equipment state fingerprint code. The second time series data includes the time series data of the second current harmonic component, second voltage transient waveform, second vibration energy spectral density, and second vibration spectrum after normalization processing.

[0049] In the above embodiments, the energy mutation point represents the point where the composite state index undergoes a sudden and significant change in time series data within the mutation time window. The mutation intensity refers to the magnitude of the state index change at the energy mutation point, used to quantify the severity of the state change. The mutation duration refers to the length of time from the start to the end of the energy mutation point, reflecting the duration of the state change. The mutation correlation refers to the similarity or correlation between the energy mutation point and historical energy mutation points, used to analyze the trend and pattern of state changes. The second time series data specifically refers to the continuous time series data of the composite state index within the determined mutation time window, used for further analysis of equipment state mutations. The second dynamic temperature gradient is determined based on the regional feature vector, representing the rate of temperature change in the environment where the equipment is located within the mutation time window, reflecting the impact of ambient temperature on the equipment state. The second humidity change rate is determined based on the regional feature vector, representing the humidity change in the environment where the equipment is located within the mutation time window. The second geographic coordinate feature quantity refers to the specific geographic location information of the target power equipment. The equipment operation threshold range is the allowable range of each state parameter during normal operation of the equipment, defined in the composite dynamic reference parameter set. Complexity characteristics refer to the degree of complexity of composite state indicators (e.g., second current harmonic component, second voltage transient waveform, second vibration energy spectral density, and second vibration spectrum) within the abrupt change time window, reflecting the diversity and complexity of equipment states.

[0050] In the above embodiments, after a potential abnormal event is detected and a mutation time window is determined, the local anomaly detection engine captures the second time-series data of the composite state index within the mutation time window. The second time-series data is a continuous time series record of the composite state index during the anomaly occurrence. To capture key points of state changes, the local anomaly detection engine uses dynamic environmental disturbance factors from the composite dynamic benchmark parameter set to detect energy mutation points in the second time-series data. The dynamic environmental disturbance factors reflect the degree of influence of environmental changes on the operating state of power equipment, which can help the local anomaly detection engine more accurately locate state mutations caused by environmental changes. By calculating the mutation intensity (i.e., the magnitude of the state change), mutation duration (i.e., the duration of the state change), and mutation correlation (i.e., the similarity or correlation between the current energy mutation point and historical energy mutation points), the local anomaly detection engine generates time-domain mutation features. These time-domain mutation features can provide intuitive information about the temporal characteristics and trends of abnormal events. To determine the relationship between abnormal events and environmental factors, the local anomaly detection engine uses the regional feature vector in the composite dynamic benchmark parameter set to determine the second dynamic temperature gradient, the second humidity change rate, and the second geographic coordinate feature quantity corresponding to the mutation time window. These environmental parameters are correlated with the sudden changes in the operating state of the power equipment, generating an environmental coupling feature set. The environmental coupling feature set reveals how environmental factors affect the operating state of the equipment.

[0051] In the above embodiments, the local anomaly detection engine further extracts complexity features from the second current harmonic component, second voltage transient waveform, second vibration energy spectral density, and second vibration spectrum in the second time-series data based on the equipment operating threshold range in the composite dynamic reference parameter set. These complexity features reflect the operating characteristics of the power equipment under abnormal conditions, such as the harmonic components of current and voltage, and the energy distribution of vibration. The local anomaly detection engine generates a unique equipment status fingerprint code to distinguish different abnormal events and equipment states. The local anomaly detection engine outputs key information such as time-domain abrupt change features, environmental coupling feature set, and equipment status fingerprint code to comprehensively analyze potential abnormal events, thereby enabling rapid location of anomaly causes, assessment of anomaly impacts, and implementation of corresponding maintenance measures. In an optional embodiment, a cross-regional collaborative diagnostic operation is performed based on temporal abrupt change features, environmental coupling feature sets, and device status fingerprint codes to generate a dynamic parameter correction instruction set. Specifically, this includes: filtering historical anomaly events from a cross-regional device database based on second geographic coordinate features and preset filtering conditions, wherein the historical anomaly events include historical environmental parameter sets that are the same as or similar to the first environmental parameter set; determining first historical anomaly features, historical repair strategies, and historical associated device parameter correction records based on the historical anomaly events and historical environmental parameter sets; performing similarity matching between the device status fingerprint codes and the historical device status fingerprint codes in the historical anomaly events to match candidate anomaly events, wherein the historical anomaly events include candidate anomaly events; and performing association matching between temporal abrupt change features and the second historical anomaly features of the candidate anomaly events to obtain the cross-regional anomaly correlation degree, wherein the first... The system includes a first historical anomaly feature and a second historical anomaly feature. Based on cross-regional anomaly correlation and historical correlation equipment parameter correction records, it reverse-engineers the potential anomaly sources, associated impact parameters, and cross-regional cascading risk paths of the target power equipment. The associated impact parameters are parameters in the first environmental parameter set and operating status data that are directly or indirectly related to the potential anomaly source. The cross-regional cascading risk path is the path by which the potential anomaly source propagates among multiple power equipment in different regions through power grid physical connections and logical dependencies. These multiple power equipment include the target power equipment. Anomaly repair priorities are generated based on the potential anomaly source, associated impact parameters, cross-regional cascading risk paths, and historical repair strategies. The anomaly repair priority is a quantitative indicator of the urgency of repairing different potential anomaly sources. Finally, a dynamic parameter correction instruction set is generated based on the potential anomaly source, associated impact parameters, cross-regional cascading risk paths, and anomaly repair priorities.

[0052] In the above embodiments, cross-regional collaborative diagnostic operation refers to using equipment data and information distributed in different regions to collaboratively analyze and diagnose target power equipment to obtain more comprehensive and accurate diagnostic results. The dynamic parameter correction instruction set is a series of instructions generated for the target power equipment based on the results of cross-regional collaborative diagnosis, used to adjust its operating parameters and optimize its operating state. The second geographic coordinate feature specifically refers to the geographic location information of the target power equipment, used to filter historical anomaly events from the cross-regional equipment database that are similar to or have similar environmental conditions. The preset filtering conditions are set according to actual needs and are used to filter historical anomaly events that meet the conditions from the cross-regional equipment database. The filtering criteria may include the similarity of environmental parameters, the type of anomaly event, etc. Historical anomaly events refer to anomaly events that occurred in the past and may have similarity or correlation with the current abnormal state of the target power equipment. Anomaly events include historical environmental parameter sets that are the same as or similar to the first environmental parameter set, which helps to analyze the possible causes of the current abnormal state. The first historical anomaly feature refers to the feature set extracted from historical anomaly events to describe the characteristics of the anomaly event. The feature set may include temporal abrupt change features, environmental coupling features, etc. The second set of historical anomaly features is a subset of the first set of historical anomaly features, specifically referring to those features that may be related to the current time-domain abrupt change features. "Historical repair strategies" refer to the repair measures and strategies taken in response to historical anomaly events, which can provide a reference for repairing the current anomaly state. Historical related equipment parameter correction records refer to records of corrections made to related equipment parameters during historical anomaly events; these records help analyze the impact of the current anomaly state on related equipment.

[0053] In the above embodiments, when the local anomaly detection engine identifies potential anomalies on the target power equipment and outputs relevant temporal abrupt change features, environmental coupling feature sets, and equipment status fingerprint codes, it begins to execute cross-regional anomaly association analysis and remediation strategy formulation. Specifically, using the second geographic coordinate feature of the target power equipment, combined with preset screening conditions (e.g., environmental similarity, equipment type matching, etc.), historical anomalies occurring under similar or identical environmental conditions are screened from the cross-regional equipment database. These historical anomalies include a rich set of historical environmental parameters (e.g., temperature, humidity, geographic location, etc.), as well as historical anomaly features, historical remediation strategies, and historical associated equipment parameter correction records associated with the historical environmental parameter sets. Further analysis is performed on the screened historical anomalies to determine the first historical anomaly feature, historical remediation strategy, and historical associated equipment parameter correction records for each historical anomaly. The equipment status fingerprint code of the current anomaly event is matched with the historical equipment status fingerprint codes in the historical anomalies. By comparing the similarity of the fingerprint codes, a set of candidate anomalies can be matched, where the anomalies and the current anomalies have a high degree of similarity in equipment status.

[0054] In the above embodiments, the second historical anomaly features of the matched candidate anomaly events are correlated with the temporal abrupt change features of the current anomaly event. By calculating the cross-regional anomaly correlation degree (a quantitative indicator used to measure the similarity and correlation between the current anomaly event and historical anomaly events), the range of candidate anomaly events can be further narrowed down, and the historical anomaly events most likely associated with the current anomaly event can be identified. Based on the cross-regional anomaly correlation degree and historical associated equipment parameter correction records, the potential anomaly sources, associated impact parameters, and cross-regional cascading risk paths of the target power equipment are derived in reverse. Potential anomaly sources refer to equipment components or environmental factors that may cause the current anomaly event to occur. Associated impact parameters refer to the first set of environmental parameters and operating status data that are directly or indirectly associated with the potential anomaly source. Cross-regional cascading risk paths refer to the paths through which the potential anomaly source propagates among multiple power equipment in different regions through the physical connection and logical dependency of the power grid. Based on the potential anomaly sources, associated impact parameters, cross-regional cascading risk paths, and historical repair strategies, anomaly repair priorities (quantitative indicators used to measure the urgency of repairing different potential anomaly sources) are generated. A dynamic parameter correction instruction set is generated based on potential anomaly sources, associated impact parameters, cross-regional cascading risk paths, and anomaly repair priorities. The dynamic parameter correction instruction set may include parameter adjustment suggestions for the target power equipment and its associated equipment, aiming to prevent or mitigate the impact of potential anomalies.

[0055] In an optional embodiment, the dynamic parameter correction instruction set specifically includes: dynamically adjusting the first correction weight of the coupling coefficient correction value in the preset regional coupling weight table according to the anomaly repair priority, so as to optimize the correlation rules of equipment operation parameters between regions, wherein the adjustment range of the first correction weight is positively correlated with the anomaly repair priority; determining the feedback compensation parameter of the dynamic environmental disturbance factor according to the cross-regional anomaly correlation degree and historical correlation equipment parameter correction records, wherein the feedback compensation parameter is to quantify the interference intensity of environmental noise on composite state indicators; generating based on the equipment maintenance cycle in the historical repair strategy and the priority mark in the cross-regional chain risk path. An adaptive adjustment strategy for the monitoring frequency of edge computing nodes includes increasing the monitoring frequency of the first power equipment corresponding to a high-risk path to a preset upper limit, and decreasing the monitoring frequency of the second power equipment corresponding to a low-risk path to a preset lower limit. Cross-regional chain risk paths include both high-risk and low-risk paths, and the target power equipment includes the first and second power equipment. The strategy also involves dynamically adjusting the second correction weight of the composite dynamic benchmark parameter set and the regional correlation parameter compensation value based on the parameter optimization trend in the historical related equipment parameter correction records. The adjustment direction of the second correction weight is the same as the parameter optimization trend.

[0056] In the above embodiments, the anomaly repair priority refers to an indicator that ranks equipment anomaly repair tasks based on factors such as the urgency and scope of impact of equipment anomalies. The first correction weight is a weight coefficient that adjusts the coupling coefficient correction value, determining the degree of influence of the coupling coefficient correction value in the inter-regional equipment operating parameter association rules. Cross-regional anomaly correlation refers to the degree of correlation between equipment anomaly states in different regions, reflecting the spatial propagation and diffusion of equipment anomalies. The feedback compensation parameter is a parameter used to quantify the interference intensity of environmental noise on composite state indicators. It compensates for composite state indicators based on changes in environmental noise to improve the accuracy of equipment state assessment. The adaptive adjustment strategy for monitoring frequency refers to a strategy that dynamically adjusts the monitoring frequency of edge computing nodes based on equipment anomalies and risk levels, aiming to optimize the allocation of monitoring resources and improve monitoring efficiency. The second correction weight is a weight coefficient that corrects parameters in the composite dynamic benchmark parameter set, determining the magnitude and direction of parameter correction. The regional correlation parameter compensation value is a parameter used to compensate for differences in equipment operating parameters between regions. Based on the coupling relationship and parameter differences between regions, the equipment operating parameters are compensated to improve the accuracy of parameter evaluation.

[0057] In the above embodiments, after identifying potential abnormal events on the target power equipment and generating a dynamic parameter correction instruction set, the dynamic parameter correction instruction set is used to optimize the association rules of equipment operating parameters between regions, adjust the feedback compensation of environmental disturbance factors, adaptively adjust the monitoring frequency of edge computing nodes, and dynamically adjust the composite dynamic benchmark parameter set. Specifically, the first correction weight of the coupling coefficient correction value in the preset regional coupling weight table is dynamically adjusted according to the anomaly repair priority. The preset regional coupling weight table is a table used to describe the association relationship of equipment operating parameters between different regions, and includes the coupling coefficient correction values ​​between each region. The first correction weight is adjusted accordingly based on the urgency of the anomaly repair priority. If the anomaly repair priority is high, it indicates that the impact range of the current abnormal event is large or the risk is high, and the adjustment range of the first correction weight may be increased to optimize the association rules of equipment operating parameters between regions and improve the response speed and accuracy of abnormal events.

[0058] In the above embodiments, feedback compensation parameters for dynamic environmental disturbance factors are determined based on cross-regional anomaly correlation and historical related equipment parameter correction records. By comparing the cross-regional anomaly correlation between current and historical anomalies, and combining environmental noise data from historical related equipment parameter correction records, feedback compensation parameters are calculated. This allows for a more accurate assessment of the impact of environmental noise on equipment operating status, leading to the development of more effective anomaly handling strategies. An adaptive adjustment strategy for edge computing node monitoring frequency is generated based on equipment maintenance cycles in historical repair strategies and priority markers in cross-regional cascading risk paths. This adaptive adjustment strategy includes increasing the monitoring frequency of the first power equipment (i.e., equipment in a high-risk state) corresponding to high-risk paths to a preset upper limit to ensure timely detection and handling of potential anomalies, and reducing the monitoring frequency of the second power equipment (i.e., equipment in a low-risk state) corresponding to low-risk paths to a preset lower limit to reduce unnecessary resource waste. Monitoring frequency can be adaptively adjusted according to risk level to improve operational efficiency.

[0059] In the above embodiments, the second correction weight of the composite dynamic benchmark parameter set and the regional correlation parameter compensation value are dynamically adjusted based on the parameter optimization trends in historical related equipment parameter correction records. The composite dynamic benchmark parameter set is a set of parameters used to describe the normal operating status of equipment. By analyzing the parameter optimization trends (e.g., increasing or decreasing trends of parameter values) in historical related equipment parameter correction records, the second correction weight is adjusted accordingly. If the parameter optimization trend indicates that a certain parameter value is gradually optimizing (e.g., reducing losses or improving efficiency), the second correction weight of that parameter may be increased to emphasize its importance in the equipment operating status assessment; conversely, its weight will be decreased. The regional correlation parameter compensation value is also adjusted based on the parameter optimization trends to reflect the differences and correlations in equipment operating status between different regions. Through this series of dynamic adjustment strategies, accurate monitoring of equipment operating status and rapid response to abnormal events can be achieved, improving the efficiency and accuracy of operation and maintenance management.

[0060] In an optional embodiment, a dynamic parameter correction instruction set is sent to the edge computing node to control the edge computing node to perform cross-regional collaborative control operations. Specifically, this includes: updating a preset regional coupling weight table based on the coupling coefficient correction value, and reconstructing a composite dynamic baseline parameter set based on the updated preset regional coupling weight table; performing pre-distortion compensation processing on the subsequently collected second environmental parameter set based on feedback compensation parameters, wherein the second environmental parameter set is the set of environmental parameters collected after the first environmental parameter set, and the pre-distortion compensation processing involves applying feedback compensation parameters to the third dynamic temperature gradient and the third humidity change rate in the second environmental parameter set. Noise suppression is implemented to generate a compensated set of environmental parameters; for the first power equipment marked as high-risk, the sampling interval between the third current harmonic component and the third vibration energy spectral density is shortened to a first preset threshold and a high-precision sensing mode is enabled, according to the monitoring frequency adaptive adjustment strategy; for the second power equipment marked as low-risk, the sampling interval between the fourth voltage transient waveform and the fourth vibration spectrum is extended to a second preset threshold and a low-power sensing mode is enabled, according to the monitoring frequency adaptive adjustment strategy; and the preset deviation threshold of the local anomaly judgment engine is dynamically adjusted according to the regional correlation parameter compensation value and the updated composite dynamic reference parameter set.

[0061] In the above embodiments, the coupling coefficient correction value refers to the value after adjusting the original coupling coefficient, reflecting the correction result of the correlation between the operating parameters of equipment in different regions. The coupling coefficient correction value is used to update the preset regional coupling weight table to more accurately describe the coupling relationship between the operating parameters of equipment in different regions. The second environmental parameter set refers to the set of environmental parameters collected after the first environmental parameter set. The second environmental parameter set is the latest data of the equipment operating environment and is used to evaluate and monitor the operating status of the equipment. The pre-distortion compensation processing is to perform reverse noise suppression processing on the environmental parameters. The feedback compensation parameters are used to reverse adjust the third dynamic temperature gradient and the third humidity change rate in the second environmental parameter set to eliminate the influence of environmental noise on the collected environmental parameters and generate a compensated environmental parameter set. The first power equipment and the second power equipment refer to power equipment marked as high risk and low risk, respectively. The monitoring frequency and sensing mode of the first power equipment and the second power equipment are adjusted according to the monitoring frequency adaptive adjustment strategy. The regional correlation parameter compensation value is a parameter used to compensate for the differences in the operating parameters of equipment in different regions. It is adjusted according to the coupling relationship between regions and the parameter differences to optimize the preset deviation threshold of the local anomaly judgment engine.

[0062] In the above embodiments, the preset regional coupling weight table can be updated based on the coupling coefficient correction value calculated above. After the update is completed, the composite dynamic benchmark parameter set is reconstructed using the new coupling weight table. The composite dynamic benchmark parameter set includes various parameter values ​​of the power equipment under normal operating conditions, which are used for subsequent equipment status assessment. Environmental parameters after the first environmental parameter set is collected are formed to form the second environmental parameter set. Based on the feedback compensation parameters calculated above, the third dynamic temperature gradient and the third humidity change rate in the second environmental parameter set are pre-distorted and compensated, that is, the influence of environmental noise on parameter measurement is reduced by reverse noise suppression, thereby generating the compensated environmental parameter set. For the first power equipment marked as high risk, according to the monitoring frequency adaptive adjustment strategy, the sampling interval of the third current harmonic component and the third vibration energy spectral density is shortened to the first preset threshold (e.g., 100 data points per second, 110 data points per second, 150 data points per second, etc., which are not limited here), and the high-precision sensing mode is enabled to improve the accuracy and real-time performance of data collection. For the second power equipment marked as low-risk, according to the adaptive adjustment strategy of monitoring frequency, the sampling interval of the fourth voltage transient waveform and the fourth vibration spectrum is extended to a second preset threshold (e.g., 10 data acquisitions per second, 15 data acquisitions per second, and 20 data acquisitions per second), and a low-power sensing mode is enabled to reduce resource consumption and extend equipment life. Based on the regional correlation parameter compensation value and the updated composite dynamic benchmark parameter set, the preset deviation threshold of the local anomaly judgment engine is dynamically adjusted. The preset deviation threshold is used to determine whether the equipment status deviates from the normal range, thereby triggering an anomaly alarm or taking corresponding handling measures. The adjusted preset deviation threshold is more consistent with the current operating status of the equipment and environmental conditions, improving the accuracy and reliability of anomaly judgment. By implementing the above steps, precise monitoring of the operating status of power equipment and rapid response to abnormal events can be achieved. The updated preset regional coupling weight table and composite dynamic benchmark parameter set improve the accuracy of equipment status assessment, pre-distortion compensation processing reduces the impact of environmental noise on parameter measurement, the adaptive adjustment strategy of monitoring frequency optimizes the efficiency of data acquisition and resource consumption, and the dynamically adjusted preset deviation threshold improves the reliability of anomaly judgment. These measures have collectively improved the efficiency of power equipment operation and maintenance management and the stability of equipment operation.

[0063] Through the embodiments of this application, edge computing nodes are deployed in the target region to acquire environmental parameters and equipment operating status data in real time. Utilizing the geographical location characteristics of the target region, a preset regional coupling weight table is called from the cross-regional equipment database. Combined with real-time data, a composite dynamic benchmark parameter set is generated. The operating status data is input into the local anomaly judgment engine for multimodal anomaly detection and key features are output. Based on the key features, cross-regional collaborative diagnosis is executed to generate a dynamic parameter correction instruction set, which is then sent to the edge nodes to achieve cross-regional collaborative control of the target power equipment.

[0064] The electronic device in the embodiments of this invention is described below from the perspective of hardware processing. (See attached document.) Figure 2 , Figure 2 This is a schematic diagram of the physical device structure of an electronic device in an embodiment of this application.

[0065] It should be noted that, Figure 2 The structure of the electronic device shown is merely an example and should not impose any limitation on the functionality and scope of use of the embodiments of the present invention.

[0066] like Figure 2 As shown, the electronic device includes a Central Processing Unit (CPU) 201, which can perform various appropriate actions and processes according to a program stored in Read-Only Memory (ROM) 202 or a program loaded from storage portion 208 into Random Access Memory (RAM) 203, such as performing the methods described in the above embodiments. The RAM 203 also stores...

[0067] It contains various programs and data required for system operation. CPU 201, ROM 202, and RAM 203 are interconnected via bus 204. Input / output (I / O) interface 205 is also connected to bus 204.

[0068] The following components are connected to I / O interface 205: input section 206 including audio input devices, push-button switches, etc.; output section 207 including a liquid crystal display (LCD) and audio output devices, indicator lights, etc.; storage section 208 including a hard disk, etc.; and communication section 209 including a network interface card such as a LAN (Local Area Network) card, modem, etc. Communication section 209 performs communication processing via a network such as the Internet. Drive 210 is also connected to I / O interface 205 as needed. Removable media 211, such as a disk, optical disk, magneto-optical disk, semiconductor memory, etc., are installed on drive 210 as needed so that computer programs read from them can be installed into storage section 208 as needed.

[0069] In particular, according to embodiments of the present invention, the processes described above with reference to the flowcharts can be implemented as computer software programs. For example, embodiments of the present invention include a computer program product comprising a computer program carried on a computer-readable medium, the computer program containing computer programs for performing the methods shown in the flowcharts. In such embodiments, the computer program can be downloaded and installed from a network via communication section 209, and / or installed from removable medium 211. When the computer program is executed by central processing unit (CPU) 201, it performs the various functions defined in the present invention.

[0070] It should be noted that specific examples of computer-readable storage media may include, but are not limited to: electrical connections having one or more wires, portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM), flash memory, optical fiber, portable compact disc read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination thereof. In this invention, a computer-readable storage medium can be any tangible medium containing or storing a program that can be used by or in conjunction with an instruction execution system, apparatus, or device.

[0071] The flowcharts and block diagrams in the accompanying drawings illustrate the architecture, functionality, and operation of possible implementations of systems, methods, and computer program products according to various embodiments of the present invention. Each block in a flowchart or block diagram may represent a module, program segment, or portion of code, which contains one or more executable instructions for implementing a specified logical function. It should also be noted that in some alternative implementations, the functions indicated in the blocks may occur in a different order than those shown in the drawings.

[0072] Specifically, the electronic device in this embodiment includes a processor and a memory. The memory stores a computer program. When the computer program is executed by the processor, it implements the cross-regional operation and maintenance method for power equipment provided in the above embodiment.

[0073] In another aspect, the present invention also provides a computer-readable storage medium, which may be included in the electronic device described in the above embodiments; or it may exist independently and not assembled into the electronic device. The storage medium carries one or more computer programs that, when executed by a processor of the electronic device, cause the electronic device to implement the cross-regional operation and maintenance method for power equipment provided in the above embodiments.

[0074] The above-described embodiments are only used to illustrate the technical solutions of this application, and are not intended to limit it. Although this application has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features. Such modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the scope of the technical solutions of the embodiments of this application.

[0075] Those skilled in the art will understand that all or part of the processes in the methods of the above embodiments can be implemented by a computer program instructing related hardware. This program can be stored in a computer-readable storage medium, and when executed, it can include the processes described in the above method embodiments. The aforementioned storage medium includes various media capable of storing program code, such as ROM or random access memory (RAM), magnetic disks, or optical disks.

Claims

1. A cross-regional operation and maintenance method of a power device, characterized in that, The method comprises the steps of: deploying an edge computing node in a target region where a target power device is located, and obtaining a first environmental parameter set obtained by the edge computing node in real-time monitoring of the target region and operation state data of the target power device, wherein the first environmental parameter set comprises a first dynamic temperature gradient, a first humidity change rate, and a first geographic coordinate characteristic quantity, and the operation state data comprises a first current harmonic component, a first voltage transient waveform, a first vibration energy spectrum density, and a first vibration frequency spectrum; calling a preset regional coupling weight table from a cross-regional device database according to the first geographic coordinate characteristic quantity, wherein the preset regional coupling weight table comprises a device operation parameter association rule of a historical region with the same or similar geographical features as the target region; generating a composite dynamic reference parameter set according to the first dynamic temperature gradient, the first humidity change rate, and the device operation parameter association rule; inputting the operation state data into a local anomaly judgment engine to obtain a time-domain mutation feature, an environmental coupling feature set, and a device state fingerprint code output by the local anomaly judgment engine after performing a multi-modal anomaly detection operation on the operation state data according to the composite dynamic reference parameter set; performing a cross-regional collaborative diagnosis operation according to the time-domain mutation feature, the environmental coupling feature set, and the device state fingerprint code to generate a dynamic parameter correction instruction set; downloading the dynamic parameter correction instruction set to the edge computing node to control the edge computing node to perform a cross-regional collaborative control operation.

2. The method of claim 1, wherein, The method of generating a composite dynamic reference parameter set according to the first dynamic temperature gradient, the first humidity change rate, and the device operation parameter association rule specifically comprises: performing a regional feature extraction operation on the first dynamic temperature gradient and the first humidity change rate according to a preset time window to generate a regional feature vector; associating and mapping the regional feature vector with a preset reference parameter template to obtain an association mapping result, wherein the reference parameter template is a parameter association table constructed according to historical operation data of multi-regional power devices, and the parameter association table comprises device operation threshold intervals corresponding to different environmental parameter combinations; determining a dynamic environmental disturbance factor of the target region according to the association mapping result and the device operation parameter association rule, wherein the dynamic environmental disturbance factor is a weight coefficient of the influence of environmental changes on the operation state of the target power device; adjusting a preset anomaly judgment threshold of the target power device according to the association mapping result and the dynamic environmental disturbance factor to generate the composite dynamic reference parameter set of the target region.

3. The method of claim 1, wherein, The method of inputting the operation state data into a local anomaly judgment engine to obtain a time-domain mutation feature, an environmental coupling feature set, and a device state fingerprint code output by the local anomaly judgment engine after performing a multi-modal anomaly detection operation on the operation state data according to the composite dynamic reference parameter set specifically comprises: inputting the operation state data into the local anomaly judgment engine to control the local anomaly judgment engine to perform the following operations: The local anomaly judgment engine normalizes the first current harmonic component, the first voltage transient waveform, the first vibration energy spectral density and the first vibration frequency spectrum to generate a composite state indicator; The local anomaly judgment engine uses a preset sliding window algorithm to segment the first time series data of the composite state indicator to determine a deviation degree between the composite state indicator and the composite dynamic reference parameter set, wherein the first time series data is continuous time series data of the composite state indicator before the segmentation, the first time series data includes time series data of the first current harmonic component, the first voltage transient waveform, the first vibration energy spectral density and the first vibration frequency spectrum after the normalization, and the deviation degree is a difference degree between the composite state indicator and the composite dynamic reference parameter set; When the local anomaly judgment engine determines that the deviation degree is greater than a preset deviation threshold, it triggers a potential abnormal event and determines a mutation time window, wherein the mutation time window is a time interval in which the deviation degree is greater than the preset deviation threshold; The local anomaly judgment engine performs a multi-modal anomaly feature extraction operation according to the mutation time window and the composite dynamic reference parameter set; The local anomaly judgment engine acquires the time domain mutation feature, the environment coupling feature set and the device state fingerprint code output by the multi-modal anomaly feature extraction operation.

4. The method of claim 3, wherein, The local anomaly judgment engine performs a multi-modal anomaly feature extraction operation according to the mutation time window and the composite dynamic reference parameter set, specifically including: The local anomaly judgment engine extracts an energy mutation point of the second time series data of the composite state indicator in the mutation time window according to a dynamic environmental disturbance factor in the composite dynamic reference parameter set, and determines a mutation intensity, a mutation duration and a mutation correlation of the energy mutation point to generate the time domain mutation feature, wherein the second time series data is continuous time series data of the composite state indicator in the mutation time window, and the mutation correlation is an association feature between the energy mutation point and a historical energy mutation point; The local anomaly judgment engine determines a second dynamic temperature gradient, a second humidity change rate and a second geographic coordinate feature quantity corresponding to the mutation time window according to a regional feature vector in the composite dynamic reference parameter set to generate the environment coupling feature set, wherein the environment coupling feature set represents the association between the first environment parameter and the operation state mutation of the target power device. The local anomaly judgment engine determines complexity characteristics of a second current harmonic component, a second voltage transient waveform, a second vibration energy spectrum density and a second vibration frequency spectrum of the composite state indicator in the mutation time window according to a device running threshold interval in the composite dynamic reference parameter set, to generate the device state fingerprint code, wherein the second time sequence data includes time sequence data of the second current harmonic component, the second voltage transient waveform, the second vibration energy spectrum density and the second vibration frequency spectrum after the normalization processing.

5. The method of claim 4, wherein, The cross-regional collaborative diagnosis operation is performed according to the time domain mutation characteristics, the environment coupling characteristic set and the device state fingerprint code to generate a dynamic parameter correction instruction set, specifically including: According to the second geographic coordinate feature quantity and a preset screening condition, a historical abnormal event of a reference region is screened out from the cross-regional device database, wherein the historical abnormal event includes a historical environment parameter set same as or similar to the first environment parameter set; According to the historical abnormal event and the historical environment parameter set, a first historical abnormal feature, a historical repair strategy and a historical associated device parameter correction record are determined; The device state fingerprint code is similarity matched with a historical device state fingerprint code in the historical abnormal event to match a candidate abnormal event, wherein the historical abnormal event includes the candidate abnormal event; The time domain mutation characteristics are associated matched with a second historical abnormal feature of the candidate abnormal event to obtain a cross-regional abnormal association degree, wherein the first historical abnormal feature includes the second historical abnormal feature; According to the cross-regional abnormal association degree and the historical associated device parameter correction record, a potential abnormal source, an associated impact parameter and a cross-regional chain risk path of the target power device are reversely deduced, wherein the associated impact parameter is a parameter in the first environment parameter set and the running state data that is directly or indirectly associated with the potential abnormal source, the cross-regional chain risk path is a path through which the potential abnormal source propagates among a plurality of power devices in different regions through a power grid physical connection and a logical dependency relationship, and the plurality of power devices include the target power device; According to the potential abnormal source, the associated impact parameter, the cross-regional chain risk path and the historical repair strategy, an abnormal repair priority is generated, wherein the abnormal repair priority is a quantitative indicator of a repair urgency degree of different potential abnormal sources; According to the potential abnormal source, the associated impact parameter, the cross-regional chain risk path and the abnormal repair priority, a dynamic parameter correction instruction set is generated.

6. The method of claim 5, wherein, The dynamic parameter correction instruction set specifically includes: According to the abnormal repair priority, a first correction weight of a coupling coefficient correction value in a preset regional coupling weight table is dynamically adjusted to optimize a device running parameter association rule between regions, wherein the adjustment range of the first correction weight is positively correlated with the abnormal repair priority; Determine a feedback compensation parameter of a dynamic environmental disturbance factor according to the cross-regional abnormal correlation degree and the historical correlation equipment parameter correction record, wherein the feedback compensation parameter is a quantitative environmental noise interference intensity on the composite state index; Generate a monitoring frequency adaptive adjustment strategy of the edge computing node according to the equipment maintenance period in the historical repair strategy and the priority marking in the cross-regional chain risk path, wherein the monitoring frequency adaptive adjustment strategy includes that the monitoring frequency of a first power equipment corresponding to a high-risk path is raised to a preset upper limit of the monitoring frequency, and the monitoring frequency of a second power equipment corresponding to a low-risk path is reduced to a preset lower limit of the monitoring frequency, the cross-regional chain risk path includes the high-risk path and the low-risk path, and the target power equipment includes the first power equipment and the second power equipment; Dynamically adjust a second correction weight of the composite dynamic reference parameter set and a regional correlation parameter compensation value according to a parameter optimization trend in the historical correlation equipment parameter correction record, wherein the adjustment direction of the second correction weight is the same as the parameter optimization trend.

7. The method of claim 6, wherein, The dynamic parameter correction instruction set is sent to the edge computing node to control the edge computing node to perform a cross-regional cooperative control operation, specifically including: Update the preset regional coupling weight table according to the coupling coefficient correction value, and reconstruct the composite dynamic reference parameter set according to the updated preset regional coupling weight table; Perform pre-distortion compensation processing on a second environment parameter set collected subsequently according to the feedback compensation parameter, wherein the second environment parameter set is a set of environment parameters collected after the first environment parameter set, and the pre-distortion compensation processing is reverse noise suppression on a third dynamic temperature gradient and a third humidity change rate in the second environment parameter set to generate a compensated environment parameter set; According to the monitoring frequency adaptive adjustment strategy, for the first power equipment marked as high risk, the sampling interval of the third current harmonic component and the third vibration energy spectrum density is shortened to a first preset threshold, and a high-precision sensing mode is enabled, and according to the monitoring frequency adaptive adjustment strategy, for the second power equipment marked as low risk, the sampling interval of the fourth voltage transient waveform and the fourth vibration frequency spectrum is extended to a second preset threshold, and a low-power consumption sensing mode is enabled. Dynamically adjust a preset deviation threshold of a local anomaly judgment engine according to the regional correlation parameter compensation value and the updated composite dynamic reference parameter set.

8. An electronic device, comprising: The electronic device includes one or more processors and a memory; the memory is coupled with the one or more processors, the memory is used to store computer program code, the computer program code includes computer instructions, and the one or more processors invoke the computer instructions to make the electronic device execute the method in any one of claims 1-7.

9. A computer-readable storage medium comprising instructions, characterized in that, When the instructions run on an electronic device, the electronic device executes the method in any one of claims 1-7.

10. A computer program product, characterised in that, The computer program product, when run on an electronic device, causes the electronic device to perform the method of any one of claims 1-7.

Images