Electrical equipment maintenance method, system and equipment based on digital twinning and medium

Abstract

The invention relates to the technical field of power equipment, in particular to a digital twinning-based power equipment maintenance method and system, equipment and a medium, and the method comprises the steps: obtaining the operation state data of the power equipment; performing anomaly detection analysis on the operation state data to obtain an anomaly detection result; determining a health degree index of the power equipment based on the anomaly detection result, and calculating a maintenance priority index of the power equipment according to the health degree index; and determining a maintenance management strategy according to the maintenance priority index, and performing maintenance management measures on the power equipment based on the maintenance management strategy. According to the invention, the operation and maintenance cost can be reduced while the maintenance accuracy of the power equipment is improved.

Description

Technical Field

[0001] This application relates to the technical field of power equipment, and in particular, to a power equipment maintenance method, system, device, and medium based on digital twin. Background Art

[0002] At present, the operation and maintenance of power equipment are crucial for the stability and security of the power grid. With the complexity and intelligence of the power grid system, the traditional power equipment maintenance method has been difficult to meet the requirements of modern power systems, and the intelligent operation and maintenance of power equipment have become the trend of the industry development.

[0003] In related technologies, to solve the problem of power equipment maintenance, the power equipment is usually maintained by means of regular inspection. By manually checking the appearance and operating parameters of the equipment, potential faults are found. However, this method fails to fully consider the actual operating state of the equipment, which easily leads to the problems of over-maintenance or under-maintenance, thereby increasing the operation and maintenance costs or causing the equipment to be damaged due to potential faults not being processed in time. Therefore, there is room for improvement. Summary of the Invention

[0004] This application provides a power equipment maintenance method, system, device, and medium based on digital twin, which can improve the maintenance accuracy of power equipment and reduce the operation and maintenance costs.

[0005] The above-mentioned first invention object of this application is achieved through the following technical solutions:

[0006] A power equipment maintenance method based on digital twin, the power equipment maintenance method based on digital twin includes:

[0007] Obtain the operation status data of the power equipment;

[0008] Perform anomaly detection and analysis on the operation status data to obtain an anomaly detection result;

[0009] Based on the anomaly detection result, determine the health index of the power equipment, and calculate the maintenance priority index of the power equipment according to the health index;

[0010] According to the maintenance priority index, determine a maintenance management strategy, and perform maintenance management measures on the power equipment based on the maintenance management strategy.

[0011] By adopting the above technical solution, by obtaining the operation status data of power equipment, the integrity and accuracy of the equipment operation data can be ensured, thereby providing a reliable basis for subsequent anomaly detection, health assessment, and maintenance decision-making, avoiding misjudgments caused by data loss or errors. By performing anomaly detection and analysis on the operation status data, abnormal conditions during equipment operation can be effectively identified, thereby avoiding the expansion of equipment failures caused by undetected anomalies in a timely manner, improving the operation safety and stability of the system. By calculating the health index and maintenance priority index of power equipment based on the anomaly detection results, the health status and maintenance urgency of the equipment can be quantified, thereby helping maintenance personnel to prioritize the handling of high-risk equipment, optimize the allocation of maintenance resources, and improve the overall maintenance efficiency. By formulating a maintenance management strategy and implementing maintenance management measures according to the maintenance priority index, the maintenance method can be intelligently selected according to the actual status of the equipment, thereby reducing unnecessary maintenance costs, while reducing the sudden failure rate and improving the availability and operation efficiency of the equipment.

[0012] In a preferred example, the present application can be further configured as follows: The anomaly detection and analysis of the operation status data to obtain an anomaly detection result specifically includes:

[0013] Based on data processing technology, perform data normalization processing on the operation status data to remove noise and smooth the data, obtaining the preprocessed operation status data;

[0014] According to the operation status data, identify the abnormal conditions of the power equipment to obtain the anomaly detection result.

[0015] By adopting the above technical solution, by performing data normalization processing on the operation status data, noise in the data can be removed and the data can be smoothed, thereby improving the accuracy of anomaly detection and avoiding false detection or missed detection caused by abnormal data fluctuations. By identifying the abnormal conditions of the equipment based on the processed operation status data, the abnormal state of the equipment can be accurately discovered.

[0016] In a preferred example, the present application can be further configured as follows: The identifying the abnormal conditions of the power equipment according to the operation status data to obtain the anomaly detection result specifically includes:

[0017] Obtain the historical operation status data and anomaly detection benchmark threshold of the power equipment;

[0018] Based on the anomaly scoring formula, perform an abnormal state assessment on the power equipment according to the historical operation status data, the anomaly detection benchmark threshold, and the operation status data to obtain an anomaly score value;

[0019] According to the anomaly score value, determine whether the anomaly score value is greater than the anomaly detection benchmark threshold;

[0020] If the abnormal score value is greater than the abnormal detection benchmark threshold, an abnormal detection result of device abnormality is generated.

[0021] By adopting the above technical solution, by obtaining the historical operation status data of the device and the abnormal detection benchmark threshold, an analysis benchmark for the long-term operation trend of the device can be provided, thereby improving the accuracy of abnormal detection, avoiding misjudgment caused by short-term fluctuations. By calculating the abnormal score value based on the abnormal scoring formula, the abnormal degree of the device can be quantified, providing an intuitive judgment basis and improving the efficiency of maintenance work. By judging whether the device is abnormal based on the abnormal score value, a reasonable abnormal detection threshold can be set, thereby reducing false alarms and missed alarms and improving the accuracy of abnormal detection. By generating an abnormal detection result when the abnormal score exceeds the threshold, the health index can be calculated in a timely manner when the device has an abnormality, and the health status and maintenance urgency of the device can be quantified, thereby ensuring that device abnormalities can be quickly responded to and improving the accuracy of fault detection.

[0022] In a preferred example of the present application, it can be further configured as: based on the abnormal detection result, determine the health index of the power device, and calculate the maintenance priority index of the power device according to the health index, specifically including:

[0023] If the abnormal detection result is device abnormality, input the operation data into a preset digital twin model, and obtain a digital twin simulation result from the digital twin model;

[0024] According to the digital twin simulation result, combine the health calculation formula to calculate the device health, and obtain the health index;

[0025] Determine the maintenance priority index of the power device according to the health index, the abnormal score value and the operation status data.

[0026] By adopting the above technical solution, when the device has an abnormality, by using the digital twin model for simulation analysis, the operation status of the device can be reproduced based on the virtual environment, thereby assisting in fault diagnosis and providing a more accurate analysis of the abnormal cause. By calculating the device health index based on the digital twin simulation result, a precise health assessment can be carried out in combination with the operation characteristics of the device, thereby improving the accuracy of health calculation and providing more reliable data support for the maintenance priority assessment. By calculating the maintenance priority index according to the health index and the abnormal score, the maintenance urgency of the device can be quantified, thereby helping maintenance personnel to reasonably allocate maintenance resources, improving the operation and maintenance efficiency, and reducing the operation and maintenance cost.

[0027] In a preferred example, the present application can be further configured as follows: determining the maintenance priority index of the power equipment according to the health index, the abnormal score value, and the operation status data specifically includes:

[0028] Obtaining the equipment importance parameter of the power equipment;

[0029] Based on the maintenance priority index calculation formula, determining the maintenance priority index of the power equipment according to the health index, the abnormal score value, the equipment importance parameter, and the operation status data.

[0030] By adopting the above technical solution, by obtaining the importance parameter of the equipment, the importance of the equipment can be comprehensively evaluated in combination with the key degree of the equipment in the system, so as to ensure that the maintenance decision gives priority to the equipment that has a greater impact on the system operation, and improve the overall stability of the power system. By calculating the maintenance priority index based on the maintenance priority index calculation formula, the maintenance requirements of the equipment can be comprehensively evaluated in combination with multiple factors such as health, abnormal score, and equipment importance, so as to improve the scientificity and rationality of the maintenance measures and optimize the allocation of maintenance resources.

[0031] In a preferred example, the present application can be further configured as follows: determining the maintenance management strategy according to the maintenance priority index, and implementing the maintenance management measures on the power equipment based on the maintenance management strategy, specifically including:

[0032] If the maintenance priority index is greater than the first set threshold, take emergency maintenance measures and immediately perform equipment maintenance or replacement;

[0033] If the maintenance priority index is between the first set threshold and the second set threshold, take predictive maintenance measures and formulate the optimal maintenance time window of the power equipment in combination with the digital twin simulation result to reduce the unplanned downtime;

[0034] If the maintenance priority index is less than the second set threshold, take preventive maintenance measures and include them in the regular inspection plan to reduce the future equipment failure probability.

[0035] By adopting the above technical solution, by performing emergency maintenance when the maintenance priority index exceeds the first set threshold, it is possible to ensure that high-risk equipment is processed in a timely manner, thereby reducing the incidence of serious failures, avoiding equipment damage or downtime caused by sudden failures. By performing predictive maintenance when the maintenance priority index is between the first set threshold and the second set threshold, it is possible to arrange maintenance in advance when the equipment can still operate normally, thereby reducing unplanned downtime and improving equipment utilization. By performing preventive maintenance when the maintenance priority index is lower than the second set threshold, it is possible to incorporate the equipment into the regular inspection plan, thereby reducing the potential aging or failure risks during long-term operation and improving the long-term operation reliability of the equipment.

[0036] In a preferred example of the present application, it can be further configured that: after executing the maintenance management measure, obtain the maintenance result, and use the maintenance result to optimize the digital twin model and adjust the equipment parameters to optimize the false alarm rate of anomaly detection.

[0037] By adopting the above technical solution, by obtaining the maintenance result after the execution of the maintenance management measure, it is possible to accurately evaluate the maintenance effect, thereby providing data support for subsequent maintenance optimization, improving the pertinence and effectiveness of maintenance. By optimizing the digital twin model based on the maintenance result and adjusting the equipment parameters, it is possible to adjust the simulation model parameters based on the actual maintenance feedback, thereby improving the accuracy of the digital twin model, making it more conform to the actual operating state of the equipment, improving the reliability of anomaly detection, and reducing the operation and maintenance costs and equipment losses caused by misjudgment.

[0038] The above second invention object of the present application is achieved by the following technical solutions:

[0039] A digital twin-based power equipment maintenance system, the digital twin-based power equipment maintenance system includes:

[0040] A data acquisition module for obtaining the operating state data of power equipment;

[0041] An anomaly detection module for performing anomaly detection and analysis on the operating state data to obtain an anomaly detection result;

[0042] A health assessment module for determining the health index of the power equipment based on the anomaly detection result, and calculating the maintenance priority index of the power equipment according to the health index;

[0043] A maintenance decision module for determining the maintenance management strategy of the power equipment according to the maintenance priority index, and performing maintenance management measures on the power equipment based on the maintenance management strategy.

[0044] By adopting the above technical solution, by obtaining the operation status data of power equipment, the integrity and accuracy of the equipment operation data can be ensured, thus providing a reliable basis for subsequent anomaly detection, health assessment, and maintenance decision-making, avoiding misjudgments caused by data missing or errors. By performing anomaly detection and analysis on the operation status data, abnormal situations during equipment operation can be effectively identified, thus avoiding the expansion of equipment failures caused by the failure to detect anomalies in a timely manner, and improving the operation safety and stability of the system. By calculating the health index and maintenance priority index of power equipment based on the anomaly detection results, the health status and maintenance urgency of the equipment can be quantified, thus helping maintenance personnel to prioritize the processing of high-risk equipment, optimize the allocation of maintenance resources, and improve the overall maintenance efficiency. By formulating a maintenance management strategy and implementing maintenance management measures according to the maintenance priority index, the maintenance method can be intelligently selected according to the actual status of the equipment, thus reducing unnecessary maintenance costs, while reducing the sudden failure rate and improving the availability and operation efficiency of the equipment.

[0045] The above-mentioned third object of the present application is achieved by the following technical solution:

[0046] A computer device includes a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, the steps of the above-mentioned power equipment management method are implemented.

[0047] The above-mentioned fourth object of the present application is achieved by the following technical solution:

[0048] A computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the steps of the above-mentioned power equipment management method are implemented.

[0049] In summary, the present application includes at least one of the following beneficial technical effects:

[0050] 1. By obtaining the operation status data of power equipment, the integrity and accuracy of equipment operation data can be ensured, thus providing a reliable basis for subsequent anomaly detection, health assessment, and maintenance decision-making, avoiding misjudgments caused by data missing or errors. By performing anomaly detection and analysis on the operation status data, abnormal conditions during equipment operation can be effectively identified, thus avoiding the expansion of equipment failures caused by undetected anomalies in a timely manner, improving the operation safety and stability of the system. By calculating the health index and maintenance priority index of power equipment based on the anomaly detection results, the health status and maintenance urgency of the equipment can be quantified, thus helping maintenance personnel to prioritize the handling of high-risk equipment, optimize the allocation of maintenance resources, and improve the overall maintenance efficiency. By formulating maintenance management strategies and implementing maintenance management measures according to the maintenance priority index, the maintenance method can be intelligently selected based on the actual status of the equipment, thus reducing unnecessary maintenance costs, while reducing the sudden failure rate and improving the availability and operation efficiency of the equipment;

[0051] 2. When an anomaly occurs in the equipment, by using the digital twin model for simulation analysis, the operation status of the equipment can be reproduced based on the virtual environment, thus assisting in fault diagnosis and providing a more accurate analysis of the anomaly cause. By calculating the equipment health index based on the digital twin simulation results, a precise health assessment can be carried out in combination with the operation characteristics of the equipment, thus improving the accuracy of health index calculation and providing more reliable data support for maintenance priority assessment. By calculating the maintenance priority index based on the health index and anomaly score, the maintenance urgency of the equipment can be quantified, thus helping maintenance personnel to reasonably allocate maintenance resources, improve operation and maintenance efficiency, and reduce operation and maintenance costs;

[0052] 3. By obtaining the maintenance results after the implementation of maintenance management measures, the maintenance effect can be accurately evaluated, thus providing data support for subsequent maintenance optimization, improving the pertinence and effectiveness of maintenance. By optimizing the digital twin model based on the maintenance results and adjusting the equipment parameters, the simulation model parameters can be adjusted based on the actual maintenance feedback, thus improving the accuracy of the digital twin model, making it more in line with the actual operation status of the equipment, improving the reliability of anomaly detection, and reducing operation and maintenance costs and equipment losses caused by misjudgments. Description of the Drawings

[0053] Figure 1 is the implementation flowchart of the digital twin-based power equipment maintenance method in an embodiment of the present application;

[0054] Figure 2 is the implementation flowchart of step S20 in the digital twin-based power equipment maintenance method in an embodiment of the present application;

[0055] Figure 3 is the implementation flowchart of step S22 in the digital twin-based power equipment maintenance method in an embodiment of the present application;

[0056] Figure 4 It is the implementation flowchart of step S30 in the power equipment maintenance method based on digital twin in an embodiment of the present application;

[0057] Figure 5 It is the implementation flowchart of step S33 in the power equipment maintenance method based on digital twin in an embodiment of the present application;

[0058] Figure 6 It is the implementation flowchart of step S40 in the power equipment maintenance method based on digital twin in an embodiment of the present application;

[0059] Figure 7 It is a principle block diagram of a power equipment maintenance system based on digital twin in an embodiment of the present application;

[0060] Figure 8 It is a schematic internal structure diagram of a computer device in an embodiment of the present application. Detailed implementation manners

[0061] The following embodiments will help those skilled in the art to further understand the role of the present application, but do not limit the present application in any form. It should be noted that those of ordinary skill in the art can make several deformations and improvements without departing from the concept of the present application. These all belong to the protection scope of the present application.

[0062] In the following description, specific details such as specific system structures and technologies are proposed for the purpose of illustration rather than limitation, so as to thoroughly understand the embodiments of the present application. However, those skilled in the art should clearly understand that the present application can also be implemented in other embodiments without these specific details. In other cases, detailed descriptions of well-known systems, systems, circuits, and methods are omitted to avoid unnecessary details from interfering with the description of the present application.

[0063] It should be understood that when used in the specification of the present application and the appended claims, the term "comprising" indicates the presence of the described features, wholes, steps, operations, elements, and / or components, but does not exclude the presence or addition of one or more other features, wholes, steps, operations, elements, components, and / or their combinations.

[0064] The present application will be further described in detail below with reference to the accompanying drawings.

[0065] In one embodiment, as Figure 1 shown, the present application discloses a power equipment maintenance method based on digital twin, which specifically includes the following steps:

[0066] S10: Obtain the operation status data of the power equipment.

[0067] Specifically, the operating status data is collected in real time by a variety of sensors on the power equipment. The types of sensors include voltage sensors for measuring voltage, current sensors for measuring current, temperature sensors for measuring temperature, and acceleration sensors for measuring vibration conditions. These sensors collect data according to a fixed sampling period, where the sampling period can be 1s, 10s, or 60s, and transmit the data to the data processing module through an industrial bus protocol. During the data collection process, a verification mechanism, such as cyclic redundancy check, is adopted to ensure the integrity and accuracy of data transmission. If sensor data is lost or abnormal, a data compensation mechanism is triggered, and the compensation methods include historical data interpolation, comparison with data of adjacent devices, and adaptive estimation to ensure data integrity.

[0068] S20: Conduct anomaly detection and analysis on the operating status data to obtain the anomaly detection result.

[0069] Specifically, the anomaly detection and analysis adopt methods based on statistical analysis and time series analysis. First, calculate the mean and standard deviation of each operating parameter, and conduct a preliminary screening in combination with the set threshold. Subsequently, use the exponentially weighted moving average (EWMA) method to analyze the short-term and long-term trend changes to detect sudden anomalies and trend anomalies, thereby obtaining the anomaly detection result.

[0070] S30: Based on the anomaly detection result, determine the health index of the power equipment, and calculate the maintenance priority index of the power equipment according to the health index.

[0071] Specifically, when the anomaly detection result indicates that the equipment is abnormal, calculate the health of the power equipment based on this anomaly detection result to quantitatively represent the health status of the equipment. The higher the value, the better the health status of the equipment. Therefore, when calculating the maintenance priority index based on the health index, comprehensively consider the health index, anomaly score value, and equipment importance parameter, and obtain the final maintenance priority index through a weighted calculation method. The higher the maintenance priority index, the higher the priority for maintaining the equipment.

[0072] S40: Determine the maintenance management strategy according to the maintenance priority index, and implement maintenance management measures for the power equipment based on the maintenance management strategy.

[0073] Specifically, after the calculation of the maintenance priority index is completed, compare the preset maintenance priority index with the preset maintenance level threshold to determine the maintenance strategy. For example, if MPI > MPI 紧急 , then perform emergency maintenance. If MPI 预测 ≤MPI≤MPI 紧急 , then perform predictive maintenance. If MPI < MPI 预测 , then perform preventive maintenance.

[0074] In one embodiment, such asFigure 2 As shown, in step S20, that is, performing anomaly detection and analysis on the operation status data to obtain the anomaly detection result, specifically including:

[0075] S21: Based on data processing technology, perform data normalization on the operation status data to remove noise and smooth the data, obtaining the preprocessed operation status data.

[0076] Specifically, based on data processing technology, perform data normalization on the operation status data. For example, use the Z-score normalization method to standardize data with different units and magnitudes for subsequent analysis. At the same time, for noise removal, the Kalman filter or wavelet transform method can be used to eliminate the high-frequency noise introduced by sensor errors. For data smoothing, the moving average or exponential smoothing method can be used to reduce the impact of short-term fluctuations on anomaly detection, thus finally obtaining stable operation status data.

[0077] S22: Identify the abnormal conditions of the power equipment according to the operation status data, obtaining the anomaly detection result.

[0078] Specifically, after the operation status data is normalized and noise is removed, it enters the anomaly detection and analysis stage. Perform anomaly detection and analysis on the normalized data. If the equipment parameters exceed the set safe operation range, they are marked as abnormal. Record all anomaly detection results in the anomaly log and enter the next health assessment.

[0079] In one embodiment, as Figure 3 shown, in step S22, that is, identifying the abnormal conditions of the power equipment according to the operation status data, obtaining the anomaly detection result, specifically including:

[0080] S221: Obtain the historical operation status data and anomaly detection benchmark thresholds of the power equipment.

[0081] Specifically, the historical operation status data is extracted from the database, including the equipment operation parameters, maintenance records, and fault data within a set past period. The anomaly detection benchmark thresholds are calculated based on historical statistical analysis. First, perform clustering analysis on the historical data to divide different operating condition modes, calculate the distribution range of operation parameters in each mode, set the upper and lower limits of the normal range, and adjust the anomaly detection threshold in combination with expert experience. If the equipment is in different operating modes, dynamically adjust the threshold to adapt to different working conditions. For example, for a transformer, its normal temperature range may vary depending on the load rate, so the threshold should be adaptively adjusted according to the load situation. All historical data and threshold information are stored in the buffer for subsequent use.

[0082] S222: Based on the anomaly scoring formula, perform an anomaly status assessment on the power equipment according to the historical operation status data, the anomaly detection benchmark threshold, and the operation status data to obtain the anomaly score value.

[0083] Specifically, the anomaly scoring formula adopts a weighted calculation formula to combine multiple anomaly factors into a single score. The scoring range is usually from 0 to 100. The higher the score, the more serious the anomaly. The calculation process takes into account the current state of the equipment, historical anomaly records, anomaly change rate, etc. If the score is higher than the set threshold, it enters the maintenance priority calculation stage. Among them, the anomaly scoring formula is as follows:

[0084]

[0085] Among them, X is the current device monitoring value, such as current, voltage, temperature, etc.; μ is the mean value of the device's historical normal operation data; σ is the standard deviation of the device's historical operation data; α is the trend influence factor, which is used to control the balance between short-term fluctuations and long-term trends; EWMA t is the exponentially weighted moving average, representing the long-term operation trend of the device.

[0086] Exemplarily, the calculation formula of EWMA at time t is as follows:

[0087]

[0088] X t is the device operation data at the current moment t, such as current, voltage, temperature, vibration, etc.; λ is the smoothing factor, which determines the sensitivity of EWMA to new data, 0 < λ ≤ 1; EWMA t-1 is the EWMA value calculated at the previous moment t - 1; if it is desired that EWMA mainly considers the last 10 data points, then ; if it is desired that EWMA pays more attention to the latest data point, then a larger λ can be directly set, such as 0.8. If α is smaller, the system pays more attention to the fluctuations within a short period of time, which is suitable for detecting instantaneous anomalies, such as sudden increase in current, voltage fluctuations, etc.; if α is larger, EWMA contributes more to the anomaly score AS, which is suitable for detecting trend anomalies, such as slow increase in temperature, cable aging, etc. Among them, for key equipment such as main transformers and GIS equipment, due to the large impact of equipment aging trends, a higher α value is set, with a value between 0.5 - 0.8, to improve the ability to detect trend anomalies; for non-key equipment such as secondary equipment and sensors, sudden failures are usually more common, so a lower α value is set, with a value between 0.1 - 0.3, to avoid overemphasizing trend changes.

[0089] S223: According to the anomaly score value, determine whether the anomaly score value is greater than the anomaly detection benchmark threshold.

[0090] Specifically, the abnormal score value is compared with the set abnormal detection benchmark threshold. If the abnormal score is higher than the abnormal detection benchmark threshold, it is determined that the device has an abnormality; otherwise, it is determined that the device is operating normally or has a minor abnormality.

[0091] S224: If the abnormal score value is greater than the abnormal detection benchmark threshold, generate an abnormal detection result indicating device abnormality.

[0092] Specifically, when the abnormal score is higher than the abnormal detection benchmark threshold, it is determined that the device has an abnormality, and thus an abnormal detection result indicating device abnormality is generated.

[0093] In one embodiment, as Figure 4 shown, in step S30, based on the abnormal detection result, determine the health index of the power device, and calculate the maintenance priority index of the power device according to the health index, which specifically includes:

[0094] S31: If the abnormal detection result is device abnormality, input the operation data into a preset digital twin model, and obtain the digital twin simulation result from the digital twin model.

[0095] Specifically, when the abnormal detection result is device abnormality, after inputting the operation data into the digital twin model, first perform data mapping to ensure that the input data of the digital twin model is consistent with the actual operation data of the device. Subsequently, use the simulation engine to run the digital twin simulation, simulate the operation state of the device under different working conditions, and predict the operation trend within a certain period of time in the future. The simulation results include the health trend, possible fault points, and recommended maintenance measures. The digital twin simulation results are used to optimize the health calculation and provide data support for the maintenance strategy.

[0096] S32: According to the digital twin simulation result, combine it with the health calculation formula to calculate the device health index.

[0097] Specifically, for the digital twin simulation result obtained through the digital twin model simulation, when the simulation error corresponding to the digital twin simulation result exceeds the set threshold, enter the step of calculating the health index of the power device, and calculate the health index using the health calculation formula. After the calculation is completed, the health index is stored in the database and used for the maintenance priority calculation. Among them, the health calculation formula is as follows:

[0098] Among them, T dev 、I dev 、V dev 、A dev respectively represent the deviation amounts of temperature, current, voltage, and vibration; T nom 、I nom 、V nom 、Anom is the reference value for the normal operation of the device; W 1 , W 2 , W 3 , W 4 are the weights of the influencing factors, determined from historical data analysis. Based on historical operation data, for each influencing factor such as temperature, current, voltage, and vibration, calculate their standardized weights according to the degree of influence on the device health, σ x is the standard deviation of this parameter, μ x is the mean value of this parameter, and the calculation method is as follows:

[0099]

[0100]

[0101] Exemplarily, if the temperature in the current data is 90°C, the current is 55A, the voltage is 230V, and the vibration parameter is 0.8m / s², and the temperature in the normal reference value is 85°C, the current is 50A, the voltage is 220V, and the vibration parameter is 0.5m / s², calculate the deviation values T dev is 5, I dev is 5, V dev is 10, A dev is 0.3, and each influencing factor W 1 is 0.3, W 2 is 0.25, W 3 is 0.25, W 4 is 0.2, thus obtaining a health index of 82.6, indicating that the device status is still good, but the deviations of some parameters such as temperature, current, and vibration are relatively large, and continuous monitoring is required.

[0102] S33: Determine the maintenance priority index of the power equipment according to the health index, abnormal score value, and operating status data.

[0103] Specifically, the calculation of the maintenance priority index comprehensively considers the health index, abnormal score value, and equipment importance parameters to ensure that maintenance resources are preferentially allocated to high-risk equipment. The calculation process first obtains the health index HI and normalizes it so that its range is limited between 0 and 100. At the same time, obtain the abnormal score and adjust the weight in combination with the equipment historical data to reflect the influence of short-term and long-term abnormalities. Subsequently, obtain the importance parameter of the equipment and calculate the maintenance priority index based on the health index and abnormal score.

[0104] In one embodiment, as Figure 5 shown, in step S33, that is, determine the maintenance priority index of the power equipment according to the health index, abnormal score value, and operating status data, specifically including:

[0105] S331: Obtain the equipment importance parameter of the power equipment.

[0106] Specifically, the equipment importance parameter is assigned according to the criticality of the power equipment in the entire power grid, including the impact of the equipment on load stability, historical failure rate, dependence on upstream or downstream equipment, etc. For example, the main transformer of a substation occupies a key position in the system, and its importance parameter is relatively high, while the importance parameter of some secondary load equipment is relatively low. All calculated equipment importance parameters are normalized to between 0 and 1 to reasonably allocate weights in the calculation of maintenance priorities.

[0107] S332: Based on the maintenance priority index calculation formula, determine the maintenance priority index of the power equipment according to the health index, abnormal score value, equipment importance parameter, and operating status data.

[0108] Specifically, the calculation of the maintenance priority index is based on the equipment health index HI and its normalized result, and at the same time, it is comprehensively calculated in combination with the abnormal score, equipment importance, and operating status data. The calculation formula is as follows:

[0109]

[0110] Among them, MPI is the maintenance priority index, and the larger the value, the more urgent the equipment maintenance requirement. AS is the abnormal score, which is used to measure the current abnormal degree of the equipment; HI is the health index, which reflects the current health status of the equipment; ω is the equipment importance parameter, which represents the criticality of the equipment in the system and is determined by factors such as power grid topology and historical fault impact. The value range is usually 0.1 - 2.0. For key equipment such as the main transformer, the ω value is between 1.5 - 2.0. Even if the health is relatively high, it may be preferentially maintained. For non-key equipment such as sensors, the ω value is between 0.1 - 0.5. Even if the health is relatively low, the maintenance priority may still be relatively low.

[0111] In one embodiment, as Figure 6 shown, in step S40, that is, according to the maintenance priority index, determine the maintenance management strategy, and based on the maintenance management strategy, perform maintenance management measures on the power equipment, specifically including:

[0112] S41: If the maintenance priority index is greater than the first set threshold, take emergency maintenance measures and immediately perform equipment repair or replacement.

[0113] Specifically, if the maintenance priority index is greater than the first set threshold, that is, MPI > MPI 紧急, an emergency maintenance is immediately triggered. The emergency maintenance includes equipment shutdown inspection, replacement of faulty components, and adjustment of operation strategies. First, obtain the latest operation data and anomaly detection records of the equipment, and retrieve the digital twin simulation results to analyze the cause of the fault. If the critical components of the equipment are damaged or the operation parameters exceed the safe range, perform equipment replacement or repair. After the emergency maintenance is completed, the maintenance results are stored in the database and fed back to the health calculation module to optimize the anomaly detection threshold.

[0114] S42: If the maintenance priority index is between the first set threshold and the second set threshold, predictive maintenance measures are taken. Combine the digital twin simulation results to formulate the optimal maintenance time window for power equipment to reduce unplanned downtime.

[0115] Specifically, if the maintenance priority index is between the first set threshold and the second set threshold, that is, MPI 预测 ≤MPI≤MPI 紧急 , then a predictive maintenance strategy is adopted. The goal of predictive maintenance is to formulate the best maintenance time when the equipment can still operate to reduce unplanned downtime. During the calculation process, first analyze the remaining life of the equipment in combination with the digital twin simulation data. If the remaining life of the equipment is shorter than the set maintenance lead time, a maintenance work order is automatically generated. Subsequently, analyze the equipment operation scheduling, select a period with a lower load as the optimal maintenance time window, and notify the maintenance personnel. After the predictive maintenance is completed, the relevant data is stored in the database and fed back to the digital twin model for optimization and adjustment.

[0116] S43: If the maintenance priority index is less than the second set threshold, preventive maintenance measures are taken and incorporated into the regular inspection plan to reduce the future probability of equipment failure.

[0117] Specifically, if the maintenance priority index is less than the second set threshold, that is, MPI < MPI 预测 , then the equipment does not require emergency or predictive maintenance, but is incorporated into the regular inspection plan. The inspection plan is formulated based on the equipment category and historical maintenance cycle to ensure reasonable allocation of maintenance resources. Preventive maintenance measures include operation status inspection, equipment parameter adjustment, and necessary component replacement. During the inspection process, if an anomaly is found, recalculate the equipment maintenance priority and adjust the maintenance plan according to the calculation results. After the preventive maintenance is completed, the maintenance records are stored in the database for subsequent anomaly detection and health assessment optimization.

[0118] In one embodiment, after step S40, after implementing the maintenance management measures, obtain the maintenance results and use the maintenance results to optimize the digital twin model and adjust the equipment parameters to optimize the anomaly detection false alarm rate.

[0119] Specifically, after the device executes the maintenance management measures, obtain the maintenance results, including data such as the repair situation of device failures, the change trends of key parameters before and after maintenance, and the evaluation of device operation stability. The maintenance results can monitor the device status changes through sensors and record data in combination with the feedback from operation and maintenance personnel. The data sources of the maintenance results include: device repair logs; device operation status data after maintenance (change trends of voltage, current, temperature, vibration, etc.); comparison of anomaly scores before and after maintenance to evaluate whether the anomaly situation has been significantly reduced.

[0120] More specifically, according to the operation data of the device after maintenance, adjust the parameters of the digital twin model to make the simulation data closer to the real device state. Adopt data fitting techniques, such as the least squares method or gradient descent, to optimize the model parameters. Use the LSTM prediction model to train the digital twin model to make the digital twin model have self-adaptive capabilities and improve the accuracy of future anomaly detection.

[0121] It should be understood that the magnitudes of the sequence numbers of the steps in the above embodiments do not mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation to the implementation process of the embodiments of the present application.

[0122] In one embodiment, a power device maintenance system based on digital twins is provided. The power device maintenance system based on digital twins corresponds one-to-one with the power device maintenance method based on digital twins in the above embodiments. As Figure 7 shown, the power device maintenance system based on digital twins includes a data acquisition module, an anomaly detection module, a health assessment module, and a maintenance decision module. The detailed description of each functional module is as follows:

[0123] The data acquisition module is used to obtain the operation status data of the power device;

[0124] The anomaly detection module is used to perform anomaly detection and analysis on the operation status data to obtain the anomaly detection results;

[0125] The health assessment module is used to determine the health index of the power device based on the anomaly detection results, and calculate the maintenance priority index of the power device according to the health index;

[0126] The maintenance decision module is used to determine the maintenance management strategy according to the maintenance priority index, and execute the maintenance management measures on the power device based on the maintenance management strategy.

[0127] Optionally, the anomaly detection module specifically includes:

[0128] The data preprocessing sub-module is used to perform data normalization processing on the operation status data based on data processing techniques to remove noise and smooth the data, and obtain the preprocessed operation status data;

[0129] Anomaly recognition sub-module, which is used to identify the abnormal conditions of power equipment according to the operation status data and obtain the anomaly detection results.

[0130] Optionally, the anomaly recognition sub-module specifically includes:

[0131] Historical data acquisition unit, which is used to acquire the historical operation status data and anomaly detection benchmark thresholds of power equipment;

[0132] Anomaly score calculation unit, which is used to evaluate the abnormal state of power equipment based on the anomaly score formula according to the historical operation status data, anomaly detection benchmark thresholds and operation status data, and obtain the anomaly score value;

[0133] Anomaly threshold judgment unit, which is used to determine whether the anomaly score value is greater than the anomaly detection benchmark threshold according to the anomaly score value;

[0134] Anomaly alarm unit, which is used to generate the anomaly detection result of equipment anomaly if the anomaly score value is greater than the anomaly detection benchmark threshold.

[0135] Optionally, the health assessment module specifically includes:

[0136] Digital twin simulation sub-module, which is used to input the operation data into a preset digital twin model and obtain the digital twin simulation result from the digital twin model if the anomaly detection result is equipment anomaly;

[0137] Health calculation sub-module, which is used to calculate the equipment health according to the digital twin simulation result and in combination with the health calculation formula to obtain the health index;

[0138] Maintenance priority calculation sub-module, which is used to determine the maintenance priority index of power equipment according to the health index, anomaly score value and operation status data.

[0139] Optionally, the maintenance priority calculation sub-module specifically includes:

[0140] Equipment importance analysis unit, which is used to acquire the equipment importance parameters of power equipment;

[0141] Maintenance priority calculation unit, which is used to determine the maintenance priority index of power equipment based on the maintenance priority index calculation formula according to the health index, anomaly score value, equipment importance parameters and operation status data.

[0142] Optionally, the maintenance decision module specifically includes:

[0143] Emergency maintenance processing sub-module, which is used to take emergency maintenance measures and immediately perform equipment overhaul or replacement if the maintenance priority index is greater than the first set threshold;

[0144] A predictive maintenance sub-module, which is used to take predictive maintenance measures if the maintenance priority index is between the first set threshold and the second set threshold, and formulate the optimal maintenance time window for power equipment in combination with the digital twin simulation results to reduce unplanned downtime;

[0145] A preventive maintenance sub-module, which is used to take preventive maintenance measures if the maintenance priority index is less than the second set threshold and incorporate them into the regular inspection plan to reduce the future probability of equipment failure.

[0146] Optionally, the power equipment maintenance system based on digital twin further includes:

[0147] A maintenance result analysis module, which is used to obtain the maintenance result after executing the maintenance management measure, and use the maintenance result to optimize the digital twin model and adjust the equipment parameters to optimize the false alarm rate of anomaly detection.

[0148] For the specific limitations of the power equipment maintenance system based on digital twin, reference can be made to the limitations of the power equipment maintenance method based on digital twin in the above text, which will not be elaborated here. Each module in the above power equipment maintenance system based on digital twin can be implemented in whole or in part by software, hardware and their combination. The above modules can be embedded in the processor of the computer device in hardware form or independent of it, or stored in the memory of the computer device in software form, so that the processor can call and execute the operations corresponding to the above modules.

[0149] In one embodiment, a computer device is provided. The computer device can be a server, and its internal structure diagram can be as Figure 8 shown. The computer device includes a processor, a memory, a network interface and a database connected through a system bus. Among them, the processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program and a database. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The database of the computer device is used to store data information such as operation status data, anomaly detection results, digital twin models, etc. The network interface of the computer device is used to communicate with external terminals through a network connection. When the computer program is executed by the processor, it realizes a power equipment maintenance method based on digital twin.

[0150] In one embodiment, a computer device is provided, including a memory, a processor and a computer program stored on the memory and executable on the processor. When the processor executes the computer program, the following steps are realized:

[0151] Obtain the operation status data of the power equipment;

[0152] Perform anomaly detection and analysis on the operation status data to obtain the anomaly detection result;

[0153] Based on the anomaly detection result, determine the health index of the power equipment, and calculate the maintenance priority index of the power equipment according to the health index;

[0154] Determine the maintenance management strategy according to the maintenance priority index, and perform maintenance management measures on the power equipment based on the maintenance management strategy.

[0155] In one embodiment, a computer-readable storage medium is provided, on which a computer program is stored. When the computer program is executed by a processor, the following steps are implemented:

[0156] Obtain the operation status data of the power equipment;

[0157] Perform anomaly detection and analysis on the operation status data to obtain the anomaly detection result;

[0158] Based on the anomaly detection result, determine the health index of the power equipment, and calculate the maintenance priority index of the power equipment according to the health index;

[0159] Determine the maintenance management strategy according to the maintenance priority index, and perform maintenance management measures on the power equipment based on the maintenance management strategy.

[0160] Those of ordinary skill in the art can understand that all or part of the processes of implementing the methods in the above embodiments can be completed by instructing relevant hardware through a computer program. The computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above methods. Among them, any reference to a memory, storage, database, or other medium used in the embodiments provided in the present application can include non-volatile and / or volatile memories. Non-volatile memories can include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM), or flash memory. Volatile memories can include random access memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in various forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous link (Synchlink) DRAM (SLDRAM), memory bus (Rambus) direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM), etc.

[0161] Those skilled in the art can clearly understand that, for the convenience and brevity of description, only the above division of each functional unit and module is used as an example. In actual applications, the above functions can be allocated to different functional units and modules according to needs, that is, the internal structure of the system can be divided into different functional units or modules to complete all or part of the functions described above.

[0162] The above-described embodiments are only used to illustrate the technical solutions of the present application, rather than to limit it; although the present application has been described in detail with reference to the foregoing embodiments, those of ordinary skill in the art should understand that they can still modify the technical solutions recorded in the foregoing embodiments, or perform equivalent replacements on some of the technical features; and these modifications or replacements do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of the present application, and should all be included in the protection scope of the present application.

Claims

1. A power equipment maintenance method based on digital twins, characterized in that: The digital twin-based power equipment maintenance method includes: Obtaining operating status data of power equipment; Performing anomaly detection analysis on the operating status data to obtain an anomaly detection result; Based on the abnormality detection result, determining the health index of the power equipment, and calculating the maintenance priority index of the power equipment according to the health index; A maintenance strategy is determined according to the maintenance priority index, and maintenance management measures are performed on the power equipment based on the maintenance strategy.

2. The power equipment maintenance method according to claim 1, characterized in that: The performing anomaly detection analysis on the operating status data to obtain an anomaly detection result specifically includes: Based on data processing technology, the operating status data is subjected to data normalization processing to remove noise and smooth the data, thereby obtaining preprocessed operating status data; According to the operating status data, the abnormal condition of the electric power equipment is identified to obtain the abnormality detection result.

3. The power equipment maintenance method according to claim 2, characterized in that: The identifying the abnormal condition of the electric power equipment according to the operating status data to obtain the abnormality detection result specifically includes: Acquiring historical operating status data and anomaly detection benchmark threshold of the electric power equipment; Based on an abnormality scoring formula, an abnormal state evaluation is performed on the power equipment according to the historical operating state data, the abnormality detection reference threshold and the operating state data to obtain an abnormality scoring value; Determining, based on the anomaly score value, whether the anomaly score value is greater than the anomaly detection reference threshold; If the anomaly score value is greater than the anomaly detection reference threshold, an anomaly detection result of the device anomaly is generated.

4. The power equipment maintenance method according to claim 3, characterized in that: The determining, based on the abnormality detection result, the health index of the electric power equipment, and calculating, according to the health index, the maintenance priority index of the electric power equipment specifically includes: If the abnormality detection result is that the equipment is abnormal, the operation data is input into a preset digital twin model, and a digital twin simulation result is obtained from the digital twin model; According to the digital twin simulation results, the health of the equipment is calculated in combination with a health calculation formula to obtain the health index; A maintenance priority index of the power equipment is determined according to the health index, the abnormality score value and the operating status data.

5. The power equipment maintenance method according to claim 4, characterized in that: Determining the maintenance priority index of the power equipment according to the health index, the abnormality score value and the operating status data specifically includes: Obtaining equipment importance parameters of the electric power equipment; Based on the maintenance priority index calculation formula, the maintenance priority index of the power equipment is determined according to the health index, the abnormality score value, the equipment importance parameter and the operating status data.

6. The power equipment maintenance method according to claim 5, characterized in that: The determining of a maintenance strategy according to the maintenance priority index, and executing maintenance management measures on the power equipment based on the maintenance strategy specifically includes: If the maintenance priority index is greater than the first set threshold, emergency maintenance measures are taken to immediately overhaul or replace the equipment; If the maintenance priority index is between the first set threshold and the second set threshold, predictive maintenance measures are taken, and an optimal maintenance time window for the power equipment is formulated in combination with the digital twin simulation result to reduce unplanned downtime; If the maintenance priority index is less than the second set threshold, preventive maintenance measures are taken and incorporated into a regular inspection plan to reduce the probability of future equipment failures.

7. The power equipment maintenance method according to any one of claims 1 to 6, characterized in that: After executing the maintenance management measures, maintenance results are obtained, and the digital twin model is optimized using the maintenance results to adjust equipment parameters to optimize the false alarm rate of abnormality detection.

8. A power equipment maintenance system based on digital twins, characterized in that: The digital twin-based power equipment maintenance system includes: A data acquisition module is used to obtain the operating status data of the power equipment; An anomaly detection module, used to perform anomaly detection analysis on the operating status data to obtain an anomaly detection result; A health evaluation module, configured to determine a health index of the power equipment based on the abnormality detection result, and calculate a maintenance priority index of the power equipment according to the health index; A maintenance decision module is used to determine a maintenance strategy according to the maintenance priority index, and to execute maintenance management measures on the power equipment based on the maintenance strategy.

9. A computer device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the computer program, the steps of the power equipment maintenance method according to any one of claims 1 to 7 are implemented.

10. A computer-readable storage medium storing a computer program, characterized in that: When the computer program is executed by a processor, the steps of the power equipment maintenance method according to any one of claims 1 to 7 are implemented.

Images