Cloud collaborative data supervision system and method applied to power equipment

Abstract

The invention discloses a cloud collaborative data supervision system and method applied to power equipment, and relates to the technical field of cloud data management. Power equipment data are collected through a cloud, the collected original data are standardized to obtain operation characteristics, and after the cloud issues an instruction, the same operation characteristics of the power equipment are recorded in a unified manner; performing preliminary alarm according to the difference of the operation characteristics, calling historical characteristic data, classifying the operation characteristic abnormity of the power equipment, analyzing the abnormal association between the operation characteristics of the power equipment, performing secondary analysis on the operation characteristics of the power equipment, and sending a chain abnormity alarm and a key attention prompt to a manager through the cloud. According to the method, the stability of the power equipment management is enhanced by capturing the temperature change rate of each key stage, dynamically adjusting the temperature parameters in a predictive manner and integrating an associated monitoring and risk early warning mechanism.

Description

Technical Field

[0001] The present invention relates to the technical field of cloud data management, and in particular to a cloud collaborative data monitoring system and method applied to power equipment. Background Art

[0002] In the field of power equipment operation supervision, traditional monitoring technology has long faced multiple technical bottlenecks. On the one hand, existing systems generally rely on the threshold judgment mechanism of a single operating feature, which can only set fixed alarm limits for basic parameters such as voltage and current of the equipment, and lack systematic analysis of the equipment's operating status. This model is easily interfered by external factors such as environmental noise and data fluctuations, resulting in a large number of false alarms or missed reports. For example, in industrial scenarios with strong electromagnetic interference, partial discharge monitoring equipment often misjudges instantaneous noise as equipment abnormalities. At the same time, single feature analysis is difficult to capture the correlation between the multi-dimensional operating parameters of the equipment, and cannot fully reflect the health status of the equipment. For example, capacitor group failures are often complexly correlated with multiple power quality indicators such as voltage deviation and harmonic distortion rate, but traditional methods are difficult to achieve multivariate cross-analysis; On the one hand, traditional monitoring systems generally exhibit passive response technical characteristics, triggering alarms only when equipment parameters significantly exceed thresholds, and lacking the ability to predict potential risks. This model often results in operations and maintenance personnel intervening only after equipment failures occur, failing to take preventative measures in the early stages of failure. For example, when a wind turbine is operating at variable loads, vibration data collected by a single sensor may not be able to promptly reflect subtle wear inside the gearbox. Traditional systems, lacking the ability to correlate and analyze historical data, struggle to identify early signs of failure. On the other hand, equipment maintenance strategies have long relied on experience-driven regular inspections or post-fault repair models, resulting in significant resource misallocation. Regular inspections cannot accurately identify the actual health status of equipment, which can easily lead to over-maintenance or under-maintenance. For example, some equipment in good operating condition frequently undergoes unnecessary repairs, while equipment with real hidden dangers does not receive timely attention. At the same time, the post-fault repair model lacks the ability to predict the probability of equipment failure, which often leads to maintenance resources being stretched in emergencies. In addition, the existing technology's statistical analysis of equipment abnormality characteristics remains at the simple counting level and fails to build a comprehensive evaluation system. For example, factors such as the number of abnormal characteristics and the degree of chain abnormality correlation have not been incorporated into the maintenance priority judgment model, resulting in a lack of data support for maintenance decisions. Summary of the Invention

[0003] The purpose of the present invention is to provide a cloud-based collaborative data monitoring system and method for power equipment to solve the problems raised in the above-mentioned background technology.

[0004] In order to solve the above technical problems, the present invention provides the following technical solutions: a cloud-based collaborative data monitoring method for power equipment, comprising the following steps: S1. Collect power equipment data through the cloud, standardize the collected raw data, and obtain operating characteristics; S2. After the cloud issues a command, the same operating characteristics of the power equipment are uniformly recorded, and preliminary alarms are issued based on the differences in operating characteristics; S3. Call historical characteristic data to classify abnormal operating characteristics of power equipment; S4. Analyze abnormal correlations between operating characteristics of power equipment; S5. Conduct secondary analysis of the operating characteristics of power equipment and issue chain abnormality alarms and key attention reminders to management personnel through the cloud; S6. Analyze the equipment stability at the end of the monitoring period to identify the electrical equipment that needs maintenance.

[0005] Furthermore, in step S1, any cloud monitors X sets of similar power equipment under unified management, and the equipment set is {A1, A2, ..., A x ,…,A X}, the uniformly managed similar power equipment refers to the similar power equipment that is uniformly issued instructions, receives information and handles exceptions by the cloud, where A x It represents the xth power equipment of the same type monitored by the cloud. After monitoring the xth power equipment and standardizing the raw data of the power equipment, Y operating characteristics of the xth power equipment are obtained. The operating characteristics set is {B x_1 ,B x_2 ,…,B x_y ,…,B x_Y}, where B x_y Indicates the yth operating characteristic of the xth power equipment, sets the initial collection time interval T, and timestamps the operating characteristics collected at the same time; the cloud performs unified management and monitoring of similar power equipment, which can realize centralized operations such as issuing instructions, receiving information, and handling exceptions, greatly improving management efficiency and response speed. Standardizing the original data of the equipment can eliminate data format differences, make the operating characteristics of different equipment consistent and comparable, and lay a standardized foundation for subsequent exception analysis. Setting a fixed collection time interval and timestamp the operating characteristics can build a time-series equipment operation data chain, which is convenient for accurately tracing the operating status of the equipment at different stages, and also provides orderly data support for subsequent feature correlation analysis and abnormal evolution tracking based on the time dimension, making equipment operation monitoring more systematic and traceable.

[0006] Furthermore, in step S2, after the cloud issues an instruction to the power equipment, the yth operation characteristic of the power equipment is uniformly recorded. The yth operation characteristic of the X power equipment is {B 1_y ,B 2_y ,…,B x_y ,…,B X_y}, perform preliminary abnormality monitoring, the preliminary abnormality monitoring is: when (B x_y -B y ) / B y ≤α y When the yth operating characteristic of the xth power equipment is judged to be normal, B y is the average value of the yth operating characteristics of X power equipment, α y is the allowable amplitude of the yth operating characteristic fluctuation; when (B x_y -B y ) / B y >α y When the yth operating characteristic of the xth power equipment is judged to be abnormal, an abnormal alarm of the yth operating characteristic of the xth power equipment is issued to the management personnel in the cloud; after the cloud issues instructions to the power equipment, the operating characteristics are uniformly recorded, which can realize centralized data collection and management of the same characteristics of similar equipment, so that the operating status of scattered equipment can be systematically presented. By conducting preliminary abnormality monitoring by comparing the characteristics of a single device with the group average, the normal operating range of individual equipment can be accurately defined with the help of the common benchmarks of similar equipment, which not only avoids the one-sidedness of single device data judgment, but also relies on the stability of group data to improve the scientific nature of abnormality identification. When the characteristic fluctuation exceeds the allowable range, the cloud alarm is immediately triggered, which allows the management personnel to grasp the abnormal condition of the equipment at the first time, providing an opportunity to quickly intervene in fault processing and prevent the expansion of abnormalities, effectively ensuring the safety and reliability of equipment operation, and making equipment abnormality monitoring more real-time and targeted.

[0007] Furthermore, in step S3, the historical power equipment characteristics are called, with the current time as the end point, the power equipment characteristics collected N times are called, and the x-th power equipment is analyzed. The number of times the y1-th operating characteristic is judged to be abnormal is N x_y1 ; When the y1th operating feature is judged to be abnormal, the number of times the y2th operating feature is judged to be abnormal is N x_y1_y2 When the y1th operating feature is judged to be abnormal, the number of times the y2th operating feature obtained in the next time sequence is judged to be abnormal is n x_y1_y2The call to historical power equipment characteristics can explore the time series patterns of equipment operation, and provide a long-term perspective for analyzing the evolution of equipment anomalies by looking back on multiple rounds of collected data. Statistics on the number of abnormalities of a specific operating characteristic can accurately measure the frequency of abnormalities of that characteristic, and by correlating the number of coordinated occurrences of abnormalities of different characteristics, it is possible to discover potential correlation patterns between equipment operating characteristics, especially by tracking the abnormalities of subsequent characteristics in chronological order, which can capture the transmission chain and chain reaction signs of abnormalities within the equipment. This in-depth mining and hierarchical statistics of historical data allows equipment anomaly analysis to break out of the limitations of single judgments, accumulate data support for equipment health status assessment from the perspective of long-term association and transmission mechanisms, and make anomaly monitoring more forward-looking and systematic.

[0008] Furthermore, in step S4, the synchronization anomaly coefficient of the y1th operating characteristic and the y2th operating characteristic of the xth device is recorded as C y1-y2 =N x_y1_y2 / N x_y1 , the linkage anomaly coefficient of the y1th operating characteristic and the y2th operating characteristic of the xth device is c y1-y2 =n x_y1_y2 / N x_y1 , and then get the additional abnormal parameter D of the y1th operating feature to the y2th operating feature y1-y2 , D y1-y2 =(C y1-y2 +c y1-y2 ) / 2, the D y1-y2 It describes the degree of impact of the y1th operating characteristic anomaly on the y2th operating characteristic anomaly. By calculating the synchronous anomaly coefficient and the chain anomaly coefficient between equipment operating characteristics, the degree of correlation between different characteristic anomalies can be accurately quantified. The synchronous anomaly coefficient reflects the frequency of collaborative characteristic anomalies, while the chain anomaly coefficient captures the probability of anomaly transmission over time. The combination of the two forms an additional anomaly parameter that comprehensively characterizes the strength of anomaly correlation between characteristics. This quantitative analysis overcomes the limitations of independent judgment of a single characteristic, shifting equipment anomaly monitoring from isolated analysis to correlation analysis, providing a quantitative basis for feature linkage for subsequent anomaly judgment. This allows managers to understand the transmission patterns and synergistic relationships of characteristic anomalies within the equipment, fully considering the mutual influence between characteristics when issuing anomaly warnings. This ensures that anomaly identification is more aligned with the actual operating logic of the equipment, effectively improving the accuracy and systematic nature of fault prediction.

[0009] Further, in step S5, when the abnormal alarm of the y1th operation characteristic abnormal alarm of the xth power equipment is triggered in the preliminary abnormal monitoring, a secondary judgment is made on the y2th operation characteristic of the xth power equipment. When the y2th operating characteristic of the xth power equipment is judged to be normal, B y2is the average value of the y2th operating characteristics of X power equipment, α y2 is the allowable amplitude of the y2th operating characteristic fluctuation; when When the y2th operating characteristic of the xth power equipment is judged to be abnormal, an alarm of abnormal chain reaction of the y2th operating characteristic of the xth power equipment is sent to the management personnel through the cloud; When all the operating characteristics are judged to be normal in the initial abnormality monitoring, the operating characteristics are correlated and monitored, and the x-th power equipment is analyzed. The set of operating characteristics judged to be abnormal or chain abnormal in the previous monitoring with the current time as the end point is {G x_1 ,G x_2 ,…,G x_m ,…,G x_M}, where G x_m Indicates {G x_1 ,G x_2 ,…,G x_m ,…,G x_M}, calculate the calibration coefficient F of the yth operating characteristic of the xth power equipment y , the calibration coefficient F y For the set {D G1-y ,D G2-y ,…,D Gm-y ,…,D GM-y}The sum of the internal values, where D Gm-y Indicates the operating characteristics G x_m For the additional abnormal parameters of the y-th running feature, when When , it is judged that the yth operating characteristic of the xth power equipment is normal; when When the system determines that the yth operating characteristic of the xth power device presents an abnormal risk, it sends a key attention reminder for the yth operating characteristic of the xth power device to the management personnel via the cloud. When a preliminary abnormality is triggered, a secondary judgment is made on the associated characteristics by adding abnormal parameters. This can fully utilize the abnormal transmission patterns between device characteristics and avoid the isolation of single feature judgments. This not only reduces the risk of missed judgments due to feature linkage, but also accurately identifies true chain abnormalities, making cloud-based alerts more consistent with the actual fault logic of the equipment. When the preliminary judgment is normal, the correlation effect of historical abnormal characteristics is summarized through calibration coefficients, which can explore the potential abnormal risks behind the current normal characteristics. This extends the monitoring perspective from the immediate state to the historical correlation evolution, allowing management personnel to intervene in advance when the characteristics are not yet obviously abnormal, changing from passive response to active prevention, effectively improving the foresight and comprehensiveness of equipment abnormality warnings, and providing more in-depth decision-making support for equipment health management.

[0010] In step S6, at the end of any monitoring cycle, the number of abnormal features, the number of interlocking abnormal features, and the number of key features of concern for any power equipment are counted. The weighted sum of these numbers is used to determine the stability of the power equipment. The β power equipment with the lowest stability is then selected for maintenance, where β is the number of power equipment to be maintained. After the monitoring cycle, the number of abnormal features of each type is counted and the stability is weighted to calculate a comprehensive quantitative assessment of the reliability of the equipment's operating status. This comprehensive approach, which considers abnormal features, interlocking abnormal features, and key features of concern, avoids the one-sidedness of single-metric assessments and makes the assessment of equipment health more accurate in line with actual operating conditions. Selecting maintenance targets based on stability ranking can accurately locate the most problematic equipment, prioritizing maintenance resources to the highest-risk areas. This changes the traditional blind maintenance model, improves maintenance efficiency and effectiveness, eliminates potential equipment hazards in advance, effectively reduces the failure rate, and ensures the overall stable operation of the power equipment fleet.

[0011] A cloud-based collaborative data monitoring system for power equipment, comprising: a data acquisition and standardization module, a preliminary anomaly monitoring module, a historical data feature analysis module, a feature anomaly correlation analysis module, a secondary analysis and alarm module, and an equipment maintenance decision module; The data acquisition and standardization module is used to collect power equipment data through the cloud, standardize the collected raw data, and obtain operating characteristics; The preliminary abnormality monitoring module is used to uniformly record the same operating characteristics of the power equipment after the cloud issues instructions, and issue preliminary alarms based on the differences in the operating characteristics; The historical data feature analysis module is used to call historical feature data and classify abnormalities in the operation characteristics of power equipment; The feature anomaly correlation analysis module is used to analyze the anomaly correlation between the operating features of the power equipment; The secondary analysis and alarm module is used to perform secondary analysis on the operating characteristics of the power equipment and send chain abnormality alarms and key attention reminders to management personnel through the cloud; The equipment maintenance decision module is used to analyze the equipment stability at the end of the monitoring period, so as to identify the power equipment that needs maintenance.

[0012] Compared with existing technologies, the present invention achieves the following beneficial effects: First, by building a multi-level anomaly monitoring system, it enables precise control of the operating status of power equipment. The system first standardizes the raw data of the equipment and collects timestamps. A fluctuation threshold is set based on the average operating characteristics of similar equipment to make a preliminary anomaly judgment. Simultaneously, a synchronous anomaly coefficient and a chain anomaly coefficient are introduced to perform a secondary judgment based on the correlation analysis of the initial anomaly characteristics. This avoids alarm bias caused by misjudgment of a single feature, improves the accuracy and reliability of anomaly identification, and enables the cloud to more accurately locate the actual abnormal condition of the equipment.

[0013] On the one hand, it innovatively integrates correlation monitoring and risk warning mechanisms. Even if all characteristics are initially monitored to be normal, the calibration coefficient will be calculated to assess potential risks based on the additional impact of historical abnormalities or chain abnormal characteristics on current operating characteristics, and key attention reminders will be sent for characteristics that exceed the risk threshold, realizing the transition from passive response to abnormalities to active risk prediction, discovering hidden problems in equipment operation in advance, and providing more sufficient decision-making time for equipment failure prevention.

[0014] On the other hand, a stability assessment system is constructed to comprehensively count the number of equipment abnormal characteristics, chain abnormal characteristics and key characteristics and calculate the stability by weight. Equipment that needs maintenance is accurately located by stability sorting, changing the traditional blind maintenance mode, making maintenance work more targeted, optimizing resource allocation, improving the maintenance efficiency of power equipment, and ensuring the stability and reliability of power system operation. BRIEF DESCRIPTION OF THE DRAWINGS

[0015] The accompanying drawings are used to provide a further understanding of the present invention and constitute a part of the specification. Together with the embodiments of the present invention, they are used to explain the present invention and do not constitute a limitation of the present invention. In the accompanying drawings: Figure 1 This is a structural diagram of a cloud-based collaborative data monitoring system for power equipment according to the present invention; Figure 2 This is a flow chart of a cloud-based collaborative data monitoring method applied to power equipment according to the present invention. DETAILED DESCRIPTION

[0016] The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of the present invention.

[0017] See also Figure 1 and Figure 2 The present invention provides a technical solution: a cloud-based collaborative data monitoring method for power equipment, comprising the following steps: S1. Collect power equipment data through the cloud, standardize the collected raw data, and obtain operating characteristics; S2. After the cloud issues a command, the same operating characteristics of the power equipment are uniformly recorded, and preliminary alarms are issued based on the differences in operating characteristics; S3. Call historical characteristic data to classify abnormal operating characteristics of power equipment; S4. Analyze abnormal correlations between operating characteristics of power equipment; S5. Conduct secondary analysis of the operating characteristics of power equipment and issue chain abnormality alarms and key attention reminders to management personnel through the cloud; S6. Analyze the equipment stability at the end of the monitoring period to identify the electrical equipment that needs maintenance.

[0018] In step S1, any cloud monitors X sets of similar power equipment under unified management, and the equipment set is {A1, A2, ..., A x ,…,A X}, the uniformly managed similar power equipment refers to the similar power equipment that is uniformly issued instructions, receives information and handles exceptions by the cloud, where A x It represents the xth power equipment of the same type monitored by the cloud. After monitoring the xth power equipment and standardizing the raw data of the power equipment, Y operating characteristics of the xth power equipment are obtained. The operating characteristics set is {B x_1 ,B x_2 ,…,B x_y ,…,B x_Y}, where B x_y Indicates the yth operating characteristic of the xth power equipment, sets the initial collection time interval T, and timestamps the operating characteristics collected at the same time; the cloud performs unified management and monitoring of similar power equipment, which can realize centralized operations such as issuing instructions, receiving information, and handling exceptions, greatly improving management efficiency and response speed. Standardizing the original data of the equipment can eliminate data format differences, make the operating characteristics of different equipment consistent and comparable, and lay a standardized foundation for subsequent exception analysis. Setting a fixed collection time interval and timestamp the operating characteristics can build a time-series equipment operation data chain, which is convenient for accurately tracing the operating status of the equipment at different stages, and also provides orderly data support for subsequent feature correlation analysis and abnormal evolution tracking based on the time dimension, making equipment operation monitoring more systematic and traceable.

[0019] In step S2, after the cloud issues an instruction to the power equipment, the yth operation feature of the power equipment is uniformly recorded. The yth operation feature of X power equipment is {B 1_y ,B 2_y ,…,B x_y ,…,BX_y}, perform preliminary abnormality monitoring, the preliminary abnormality monitoring is: when (B x_y -B y ) / B y ≤α y When the yth operating characteristic of the xth power equipment is judged to be normal, B y is the average value of the yth operating characteristics of X power equipment, α y is the allowable amplitude of the yth operating characteristic fluctuation; when (B x_y -B y ) / B y >α y When the yth operating characteristic of the xth power equipment is judged to be abnormal, an abnormal alarm of the yth operating characteristic of the xth power equipment is issued to the management personnel in the cloud; after the cloud issues instructions to the power equipment, the operating characteristics are uniformly recorded, which can realize centralized data collection and management of the same characteristics of similar equipment, so that the operating status of scattered equipment can be systematically presented. By conducting preliminary abnormality monitoring by comparing the characteristics of a single device with the group average, the normal operating range of individual equipment can be accurately defined with the help of the common benchmarks of similar equipment, which not only avoids the one-sidedness of single device data judgment, but also relies on the stability of group data to improve the scientific nature of abnormality identification. When the characteristic fluctuation exceeds the allowable range, the cloud alarm is immediately triggered, which allows the management personnel to grasp the abnormal condition of the equipment at the first time, providing an opportunity to quickly intervene in fault processing and prevent the expansion of abnormalities, effectively ensuring the safety and reliability of equipment operation, and making equipment abnormality monitoring more real-time and targeted.

[0020] In step S3, the historical power equipment characteristics are called, with the current time as the end point, the power equipment characteristics collected N times are called, and the x-th power equipment is analyzed. The number of times the y1-th operating characteristic is judged to be abnormal is N x_y1 ; When the y1th operating feature is judged to be abnormal, the number of times the y2th operating feature is judged to be abnormal is N x_y1_y2 When the y1th operating feature is judged to be abnormal, the number of times the y2th operating feature obtained in the next time sequence is judged to be abnormal is n x_y1_y2The call to historical power equipment characteristics can explore the time series patterns of equipment operation, and provide a long-term perspective for analyzing the evolution of equipment anomalies by looking back on multiple rounds of collected data. Statistics on the number of abnormalities of a specific operating characteristic can accurately measure the frequency of abnormalities of that characteristic, and by correlating the number of coordinated occurrences of abnormalities of different characteristics, it is possible to discover potential correlation patterns between equipment operating characteristics, especially by tracking the abnormalities of subsequent characteristics in chronological order, which can capture the transmission chain and chain reaction signs of abnormalities within the equipment. This in-depth mining and hierarchical statistics of historical data allows equipment anomaly analysis to break out of the limitations of single judgments, accumulate data support for equipment health status assessment from the perspective of long-term association and transmission mechanisms, and make anomaly monitoring more forward-looking and systematic.

[0021] In step S4, the synchronization anomaly coefficient of the y1th operating characteristic and the y2th operating characteristic of the xth device is recorded as C y1-y2 =N x_y1_y2 / N x_y1 , the linkage anomaly coefficient of the y1th operating characteristic and the y2th operating characteristic of the xth device is c y1-y2 =n x_y1_y2 / N x_y1 , and then get the additional abnormal parameter D of the y1th operating feature to the y2th operating feature y1-y2 =(C y1-y2 +c y1-y2 ) / 2; By calculating the synchronous anomaly coefficient and the chain anomaly coefficient between the operating characteristics of the equipment, the degree of correlation between the occurrence of anomalies of different characteristics can be accurately quantified. The synchronous anomaly coefficient can reflect the frequency of feature collaborative anomalies, and the chain anomaly coefficient captures the probability of anomaly transmission over time. The combination of the two forms an additional anomaly parameter that can comprehensively characterize the strength of the abnormal correlation between features. This quantitative analysis breaks the limitation of independent judgment of a single feature, allowing equipment anomaly monitoring to shift from isolated analysis to correlation analysis, providing a quantitative basis for feature linkage for subsequent anomaly judgment. Managers can use this to grasp the transmission rules and collaborative relationships of feature anomalies within the equipment, fully consider the mutual influence between features when issuing abnormality warnings, make anomaly identification more in line with the actual operation logic of the equipment, and effectively improve the accuracy and systematicness of fault prediction.

[0022] In step S5, when the abnormal alarm of the y1th operation characteristic abnormal alarm of the xth power equipment is triggered in the preliminary abnormal monitoring, a secondary judgment is made on the y2th operation characteristic of the xth power equipment. When the y2th operating characteristic of the xth power equipment is judged to be normal, B y2 is the average value of the y2th operating characteristics of X power equipment, α y2 is the allowable amplitude of the y2th operating characteristic fluctuation; when When the y2th operating characteristic of the xth power equipment is judged to be abnormal, an alarm of abnormal chain reaction of the y2th operating characteristic of the xth power equipment is sent to the management personnel through the cloud; When all the operating characteristics are judged to be normal in the initial abnormality monitoring, the operating characteristics are correlated and monitored, and the x-th power equipment is analyzed. The set of operating characteristics judged to be abnormal or chain abnormal in the previous monitoring with the current time as the end point is {G x_1 ,G x_2 ,…,G x_m ,…,G x_M}, where G x_m Indicates {G x_1 ,G x_2 ,…,G x_m ,…,G x_M}, calculate the calibration coefficient F of the yth operating characteristic of the xth power equipment y , the calibration coefficient F y For the set {D G1-y ,D G2-y ,…,D Gm-y ,…,D GM-y}The sum of the internal values, where D Gm-y Indicates the operating characteristics G x_m For the additional abnormal parameters of the y-th running feature, when When , it is judged that the yth operating characteristic of the xth power equipment is normal; when When the system determines that the yth operating characteristic of the xth power device presents an abnormal risk, it sends a key attention reminder for the yth operating characteristic of the xth power device to the management personnel via the cloud. When a preliminary abnormality is triggered, a secondary judgment is made on the associated characteristics by adding abnormal parameters. This can fully utilize the abnormal transmission patterns between device characteristics and avoid the isolation of single feature judgments. This not only reduces the risk of missed judgments due to feature linkage, but also accurately identifies true chain abnormalities, making cloud-based alerts more consistent with the actual fault logic of the equipment. When the preliminary judgment is normal, the correlation effect of historical abnormal characteristics is summarized through calibration coefficients, which can explore the potential abnormal risks behind the current normal characteristics. This extends the monitoring perspective from the immediate state to the historical correlation evolution, allowing management personnel to intervene in advance when the characteristics are not yet obviously abnormal, changing from passive response to active prevention, effectively improving the foresight and comprehensiveness of equipment abnormality warnings, and providing more in-depth decision-making support for equipment health management.

[0023] In step S6, at the end of any monitoring cycle, the number of abnormal features, the number of interlocking abnormal features, and the number of key features of concern for any power equipment are counted. The weighted sum of these numbers is used to determine the stability of the power equipment. The β power equipment with the lowest stability is then selected for maintenance, where β is the number of power equipment to be maintained. After the monitoring cycle, the number of abnormal features of each type is counted and the stability is weighted to calculate a comprehensive quantitative assessment of the reliability of the equipment's operating status. This comprehensive approach, which considers abnormal features, interlocking abnormal features, and key features of concern, avoids the one-sidedness of single-metric assessments and makes the assessment of equipment health more accurate in line with actual operating conditions. Selecting maintenance targets based on stability ranking can accurately locate the most problematic equipment, prioritizing maintenance resources to the highest-risk areas. This changes the traditional blind maintenance model, improves maintenance efficiency and effectiveness, eliminates potential equipment hazards in advance, effectively reduces the failure rate, and ensures the overall stable operation of the power equipment fleet.

[0024] A cloud-based collaborative data monitoring system for power equipment, comprising: a data acquisition and standardization module, a preliminary anomaly monitoring module, a historical data feature analysis module, a feature anomaly correlation analysis module, a secondary analysis and alarm module, and an equipment maintenance decision module; The data collection and standardization module is used to collect power equipment data through the cloud, standardize the collected raw data, and obtain operating characteristics; The preliminary abnormality monitoring module is used to uniformly record the same operating characteristics of power equipment after the cloud issues instructions, and issue preliminary alarms based on the differences in operating characteristics; The historical data feature analysis module is used to call historical feature data and classify abnormalities in the operation characteristics of power equipment; The feature anomaly correlation analysis module is used to analyze the abnormal correlation between the operating characteristics of power equipment; The secondary analysis and alarm module is used to conduct secondary analysis of the operating characteristics of power equipment and send chain abnormality alarms and key attention reminders to management personnel through the cloud; The equipment maintenance decision module is used to analyze the equipment stability at the end of the monitoring period to identify the power equipment that needs maintenance.

[0025] Example 1: In a cloud-based collaborative data monitoring system for power equipment, real-time monitoring of similar power equipment across multiple substations is required. For example, a cloud-based system manages multiple transformers of the same model across different sites, continuously collecting operational data through sensors deployed on the equipment.

[0026] The cloud-based system initiates data collection at regular intervals, standardizing each transformer's raw operating data (such as temperature, current, and voltage). For example, when collecting oil temperature data for a particular transformer, the system converts the sensor's raw signal into a uniformly formatted temperature value. It also timestamps all operating parameters collected at the same point in time, creating a time-series record of operational characteristics. These characteristics encompass multiple key equipment indicators, ensuring comparable operating conditions across transformers.

[0027] When the cloud sends a status query command to all transformers, the system automatically aggregates the same type of operating characteristics across all devices (such as the real-time oil temperature of all transformers) and calculates the group average for that characteristic. If the oil temperature of a particular transformer deviates from the group average by more than a preset acceptable fluctuation range, the system immediately identifies the characteristic as abnormal and sends an alert to management. For example, if the oil temperature of a particular transformer is significantly higher than the average for similar devices, the cloud interface will highlight the device number and simultaneously push the type and location of the abnormality to alert operations and maintenance personnel.

[0028] The system can access historical operating data collected recently for a particular transformer and conduct in-depth analysis of the frequency of anomalies associated with specific features. For example, if a transformer's oil temperature is found to be frequently abnormal during recent monitoring, the system will further count the number of anomalies associated with this feature (such as winding temperature) and the transmission of anomalies in the preceding and following time series. By tracing back historical data, it is possible to uncover the evolution of equipment anomalies and determine whether there are signs of synergistic anomalies or chain reactions between different features.

[0029] Based on historical data statistics, the system calculates the frequency of synchronous anomalies and the probability of chain anomalies between different operating characteristics, generating quantified additional anomaly parameters. For example, when an oil temperature anomaly occurs, the ratio of synchronous winding temperature anomalies to the total number of oil temperature anomalies, as well as the probability of a subsequent winding temperature anomaly in the next monitoring session after the oil temperature anomaly, are combined to generate an anomaly correlation parameter for oil temperature to winding temperature. This parameter characterizes the strength of the mutual influence between characteristics and provides a linkage basis for subsequent anomaly determination.

[0030] When the oil temperature of a transformer triggers a preliminary abnormality alarm, the system automatically performs a secondary judgment on its winding temperature and adjusts the judgment threshold based on pre-calculated abnormality-related parameters. If the winding temperature deviation is within the adjusted range, it is judged to be normal; if it exceeds the range, it is considered a chain abnormality and an alarm is issued. In addition, when all features are initially judged to be normal, the system will review the features that have experienced abnormalities or chain abnormalities in the previous monitoring cycle and calculate the combined impact coefficient of these historical abnormal features on the current features. If a feature's deviation exceeds the risk threshold due to the combined influence of historical abnormal features, even if the current data appears normal, a key attention reminder will be issued to management personnel to provide early warning of potential failures.

[0031] After each monitoring cycle, the system counts the number of abnormal features, the number of cascading abnormal features, and the number of key features for each transformer, and uses a weighted calculation to derive the equipment stability index. For example, if a transformer frequently experiences abnormal oil temperatures, which trigger cascading abnormal winding temperatures, and multiple features are listed as key features, its stability score will be significantly reduced. The system sorts by stability and prioritizes the worst-performing equipment for inclusion in the maintenance plan. This ensures that O&M resources are precisely allocated to the highest-risk equipment, enabling a shift from reactive maintenance to proactive prevention, and ensuring the overall safe operation of the power equipment fleet.

[0032] Through the collaborative supervision of the above-mentioned entire process, the cloud system has achieved multi-dimensional monitoring of the operating status of power equipment, abnormal correlation analysis, and precise maintenance decision-making, effectively improving the efficiency and reliability of equipment management and providing data support for the stable operation of the power grid.

[0033] It will be apparent to those skilled in the art that the present invention is not limited to the details of the exemplary embodiments described above and that the invention can be embodied in other specific forms without departing from the spirit or essential characteristics of the invention. Therefore, the embodiments should be considered in all respects as illustrative and non-restrictive, and the scope of the invention is defined by the appended claims, not the foregoing description, and all variations within the meaning and range of equivalents of the claims are intended to be included therein. Any reference sign in a claim should not be construed as limiting the claim to which it relates.

Claims

1. A cloud-based collaborative data monitoring method for power equipment, characterized by: The method comprises the following steps: S1. Collect power equipment data through the cloud, standardize the collected raw data, and obtain operating characteristics; S2. After the cloud issues a command, the same operating characteristics of the power equipment are uniformly recorded, and preliminary alarms are issued based on the differences in operating characteristics; S3. Call historical characteristic data to classify abnormal operating characteristics of power equipment; S4. Analyze abnormal correlations between operating characteristics of power equipment; S5. Conduct secondary analysis of the operating characteristics of power equipment and issue chain abnormality alarms and key attention reminders to management personnel through the cloud; S6. Analyze the equipment stability at the end of the monitoring period to identify the electrical equipment that needs maintenance.

2. The cloud-based collaborative data monitoring method for power equipment according to claim 1, characterized in that: In step S1, any cloud monitors X sets of similar power equipment under unified management, and the equipment set is {A1, A2, ..., A x ,…,A X }, the uniformly managed similar power equipment refers to the similar power equipment that is uniformly issued instructions, receives information and handles exceptions by the cloud, where A x It represents the xth power equipment of the same type monitored by the cloud. After monitoring the xth power equipment and standardizing the raw data of the power equipment, Y operating characteristics of the xth power equipment are obtained. The operating characteristics set is {B x_1 ,B x_2 ,…,B x_y ,…,B x_Y }, where B x_y It represents the yth operating characteristic of the xth power equipment, sets the initial collection time interval T, and timestamps the operating characteristics collected at the same time.

3. The cloud-based collaborative data monitoring method for power equipment according to claim 2, characterized in that: In step S2, after the cloud issues an instruction to the power equipment, the yth operation feature of the power equipment is uniformly recorded. The yth operation feature of X power equipment is {B 1_y ,B 2_y ,…,B x_y ,…,B X_y }, perform preliminary abnormality monitoring, the preliminary abnormality monitoring is: when (B x_y -B y ) / B y ≤α y When the yth operating characteristic of the xth power equipment is judged to be normal, B y is the average value of the yth operating characteristics of X power equipment, α y is the allowable amplitude of the yth operating characteristic fluctuation; when (B x_y -B y ) / B y >α y When the yth operating characteristic of the xth power equipment is determined to be abnormal, an abnormal alarm of the yth operating characteristic of the xth power equipment is issued to the management personnel in the cloud.

4. The cloud-based collaborative data monitoring method for power equipment according to claim 3 is characterized by: In step S3, the historical power equipment characteristics are called, with the current time as the end point, the power equipment characteristics collected N times are called, and the x-th power equipment is analyzed. The number of times the y1-th operating characteristic is judged to be abnormal is N x_y1 ; When the y1th operating feature is judged to be abnormal, the number of times the y2th operating feature is judged to be abnormal is N x_y1_y2 When the y1th operating feature is judged to be abnormal, the number of times the y2th operating feature obtained in the next time sequence is judged to be abnormal is n x_y1_y2 .

5. The cloud-based collaborative data monitoring method for power equipment according to claim 4 is characterized in that: In step S4, the synchronization anomaly coefficient of the y1th operating characteristic and the y2th operating characteristic of the xth device is recorded as C y1-y2 =N x_y1_y2 / N x_y1 , the linkage anomaly coefficient of the y1th operating characteristic and the y2th operating characteristic of the xth device is c y1-y2 =n x_y1_y2 / N x_y1 , and then get the additional abnormal parameter D of the y1th operating feature to the y2th operating feature y1-y2 , D y1-y2 =(C y1-y2 +c y1-y2 ) / 2.

6. The cloud-based collaborative data monitoring method for power equipment according to claim 5, characterized in that: In step S5, when the abnormal alarm of the y1th operation characteristic abnormal alarm of the xth power equipment is triggered in the preliminary abnormal monitoring, a secondary judgment is made on the y2th operation characteristic of the xth power equipment. When the y2th operating characteristic of the xth power equipment is judged to be normal, B y2 is the average value of the y2th operating characteristics of X power equipment, α y2 is the allowable amplitude of the y2th operating characteristic fluctuation; when When the y2th operating characteristic of the xth power equipment is judged to be abnormal, a chain abnormality alarm of the y2th operating characteristic of the xth power equipment is sent to the management personnel through the cloud.

7. The cloud-based collaborative data monitoring method for power equipment according to claim 6, characterized in that: When all the operating characteristics are judged to be normal in the initial abnormality monitoring, the operating characteristics are correlated and monitored, and the x-th power equipment is analyzed. The set of operating characteristics judged to be abnormal or chain abnormal in the previous monitoring with the current time as the end point is {G x_1 ,G x_2 ,…,G x_m ,…,G x_M }, where G x_m Indicates {G x_1 ,G x_2 ,…,G x_m ,…,G x_M }, calculate the calibration coefficient F of the yth operating characteristic of the xth power equipment y , the calibration coefficient F y For the set {D G1-y ,D G2-y ,…,D Gm-y ,…,D GM-y }The sum of the internal values, where D Gm-y Indicates the operating characteristics G x_m For the additional abnormal parameters of the y-th running feature, when When , it is judged that the yth operating characteristic of the xth power equipment is normal; when When the yth operating characteristic of the xth power equipment is judged to have an abnormal risk, a key attention reminder of the yth operating characteristic of the xth power equipment is sent to the management personnel through the cloud.

8. The cloud-based collaborative data monitoring method for power equipment according to claim 6, characterized in that: In step S6, at the end of any monitoring cycle, the number of abnormal features, the number of chained abnormal features and the number of key features of any power equipment are counted, and the stability of the power equipment is obtained by weighted summation of the number of abnormal features, the number of chained abnormal features and the number of key features, and then β power equipment with the lowest stability are selected for maintenance, where β is the established number of maintenance power equipment.

9. A cloud-based collaborative data monitoring system for power equipment, the system being applied to a cloud-based collaborative data monitoring method for power equipment according to any one of claims 1 to 8, characterized in that: The system includes: a data acquisition and standardization module, a preliminary anomaly monitoring module, a historical data feature analysis module, a feature anomaly correlation analysis module, a secondary analysis and alarm module, and an equipment maintenance decision module; The data acquisition and standardization module is used to collect power equipment data through the cloud, standardize the collected raw data, and obtain operating characteristics; The preliminary abnormality monitoring module is used to uniformly record the same operating characteristics of the power equipment after the cloud issues instructions, and issue preliminary alarms based on the differences in the operating characteristics; The historical data feature analysis module is used to call historical feature data and classify abnormalities in the operation characteristics of power equipment; The feature anomaly correlation analysis module is used to analyze the anomaly correlation between the operating features of the power equipment; The secondary analysis and alarm module is used to perform secondary analysis on the operating characteristics of the power equipment and send chain abnormality alarms and key attention reminders to management personnel through the cloud; The equipment maintenance decision module is used to analyze the equipment stability at the end of the monitoring period, so as to identify the power equipment that needs maintenance.

Images