Power data management method and system

Abstract

The invention discloses a power data management method and system, and the method comprises the steps: firstly obtaining the historical data of power equipment, and constructing a mathematical model of the historical data value and the service life change of the equipment; calculating data values of different life stages according to the model, drawing a life change curve and marking key nodes and features; taking the curve as a reference, comparing the curve with real-time data, and determining an early warning level and a data influence value; generating a power space situation estimation index in combination with multiple factors; determining the accuracy of a pre-judged node according to the index, analyzing the integrating degree of the curve, and reversely tracing the real inducement of the equipment; according to the scheme, the mathematical model is constructed to quantify the relationship between the equipment data value and the service life, the change trend is visually presented, the service life abnormity can be early warned in time, the operation situation is comprehensively evaluated, the fault inducement is traced, the management precision and efficiency are improved, and stable operation of the power system is guaranteed.

Description

Technical Field

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

[0002] With the booming power industry, the number of power equipment is increasing rapidly, and the amount of data generated during operation is exploding. This power data contains critical information such as equipment status and operating efficiency, and is crucial for ensuring the stable operation of the power system. However, power data management currently faces numerous challenges. First, data comes from a wide range of sources and formats, and lacks unified standards, making data integration difficult and hindering efficient utilization. Second, traditional data management methods struggle to accurately mine data for value, preventing timely detection of potential equipment failures and performance trends.

[0003] Current power equipment data processing and analysis suffers from significant deficiencies. Existing technologies often employ static models when processing power equipment data, failing to consider the impact of equipment aging on the reference value of historical data. This makes it difficult to accurately identify power anomalies using the power spatial situation prediction index, present detailed changes in equipment lifespan, or identify the time points of lifespan changes and corresponding data changes. Furthermore, power data analysis is processed in chronological order, making it difficult to trace the true causes of major faults (such as insulator flashovers) because they occur on the negative time axis before the fault manifests. This presents challenges such as time reversal asymmetry, hidden causes, and multi-order correlation masking. Summary of the Invention

[0004] This application provides a power data management method and system to more accurately assess equipment status, warn of risks, and accurately trace the true causes of equipment failures.

[0005] The present application provides a power data management method, the method comprising: S1, obtain historical data of a single power device and establish a mathematical model of the change in historical data value and equipment life; S2, calculates the data value of the device at different life stages based on the model, draws a life change curve and marks the decay time nodes and data typical characteristics; S3, using the life change curve as a reference curve and comparing it with the real-time collected data to determine the impact of the current data characteristics on the equipment life warning level and the corresponding data value; S4, combining the data impact value and other impact indices to generate the power spatial situation estimation index; S5, determines the accuracy of the predicted time node based on the power space situation prediction index, analyzes the fit between the reference curve and the current equipment life curve, and traces back to the real cause of the equipment.

[0006] Preferably, the S5, reverse tracing of the real cause of the device includes: collecting time data when the device actually fails or its performance deteriorates significantly, and calculating the accuracy index based on the predicted time node and the actual failure time; aligning the time axis of the reference curve and the current device life curve, calculating the difference in performance indicators between the reference curve and the current device life curve at the same time point, and evaluating the fit of the two curves based on the size and distribution of the difference; and using the back propagation algorithm to perform reverse tracing based on the fit of the predicted time node, simulating the inverse process from the fault manifestation to the initial cause.

[0007] Preferably, the reference curve includes: constructing a mathematical model describing the relationship between the historical data value V and the equipment life L ; Where V is the data value of the device at its life span L; is the initial data value of the device; is the attenuation coefficient, is the random error term; with the equipment life L as the horizontal axis and the data value V as the vertical axis, a life change curve is drawn, and the life change curve is used as the reference curve.

[0008] Preferably, in said S5, the real inducement of the reverse tracing device further includes: S51, counting the actual number of power equipment groups covered by the power system, and collecting data sets for the areas where each power equipment is located; S52, establishing a device wave function model that describes the probability distribution of each device in the device group in different states; S53, constructs a density matrix based on the device wave function model to quantify the degree of quantum entanglement and uncertainty of the device group; S54, design a quantum correlation decoder for the quantum entangled state in the device group, decode the quantum correlation information between devices and build a collaborative diagnosis model for the device group; S55, using the equipment group collaborative diagnosis model, processes and analyzes the data collected in real time to predict the collaborative failure risk of the equipment group.

[0009] Preferably, the S52 establishes a device wave function model that describes the probability distribution of each device in the device group in different states, including: determining all states that each device in the device group can be in; based on the collected data, counting the number of times the device is in each state, calculating the probability amplitude, and constructing a wave function Ψ that describes the device state; verifying the constructed wave function by comparing it with actual data to check whether it meets the normalization conditions and whether it can reasonably describe the state distribution of the device.

[0010] Preferably, the S54 includes: analyzing the quantum entangled state of the device group based on the constructed device group density matrix; clarifying the causal quantum correlation information between devices that needs to be decoded, and constructing a measurement basis according to the target correlation information; performing quantum measurement on the device group, and projecting the state of the device group onto the measurement basis; analyzing the probability distribution of the measurement results, and extracting the quantum correlation information between devices; in addition to the quantum correlation information, collecting the classical operation characteristics of the devices; and fusing the quantum correlation characteristics and the classical characteristics to form a comprehensive feature vector.

[0011] Preferably, the S51, collecting the data set of the area where each power equipment is located also includes: real-time monitoring of the conversion process of the equipment group between the quantum state and the classical state, and collecting data of the equipment group at the moment of conversion between the quantum state and the classical state; identifying the critical state at the moment of conversion to perform feature extraction to determine the fault characteristics unique to the boundary state; formulating a quantum-classical boundary state conversion control strategy based on the results of boundary state monitoring and identification; introducing boundary state characteristic parameters into the collaborative diagnosis model of the equipment group, and performing real-time monitoring and early warning of the operating status of the equipment group.

[0012] Preferably, the determination of the fault characteristics unique to the boundary state includes: preprocessing the collected data to remove noise and anomalies; analyzing the changing trends of quantum state and classical state parameters, and when the quantum state parameters and the classical state parameters change significantly at the same time, it is considered that the device group is in a critical state at the moment of conversion; and extracting the fault characteristics unique to the boundary state from the critical state data.

[0013] Preferably, the real-time monitoring and early warning of the operating status of the equipment group specifically include: introducing the extracted boundary state characteristic parameters into the equipment group collaborative diagnosis model; using historical data to retrain the updated model and adjust the parameters of the model; collecting the operating data of the equipment group in real time, extracting the boundary state characteristic parameters and classical characteristic parameters, and forming a comprehensive feature vector; inputting the real-time feature vector into the updated collaborative diagnosis model, and the model outputs the operating status of the equipment group and the fault risk prediction results; and formulating an early warning strategy based on the prediction results and the set risk threshold.

[0014] The present application also provides a power data management method, the system comprising: An acquisition module is used to obtain historical data of power equipment and establish a mathematical model of the value of historical data and the change of equipment life; The classification module is used to calculate the data value of the equipment at different life stages based on the model, draw the life change curve and mark the decay time nodes and data typical characteristics; The analysis module uses the life change curve as a reference curve and compares it with the real-time collected data to determine the impact of the current data characteristics on the equipment life warning level and the corresponding data value; Calculation module: Combines data impact value and other impact indexes to generate power space situation prediction index; The tracing module determines the accuracy of the predicted time node based on the power space situation prediction index, analyzes the fit between the reference curve and the current equipment life curve, and traces back the real cause of the equipment.

[0015] One or more technical solutions provided in this application have at least the following technical effects or advantages: By constructing a mathematical model that correlates the value of historical data with the lifespan of equipment, this approach effectively addresses key technical issues in power equipment management. Traditional power equipment management struggles to accurately quantify the value of equipment data as it changes with lifespan, preventing timely warnings of equipment lifespan issues. Furthermore, it struggles to comprehensively assess power spatial trends and trace the causes of equipment failures. This solution constructs a mathematical model to quantify the relationship between the value of equipment data and lifespan, visually presenting value trends and providing timely warnings of equipment life anomalies. It also integrates multi-dimensional data to generate a situation prediction index for a comprehensive assessment of operational status and can also reversely trace the true causes of equipment failures. This significantly improves the accuracy and efficiency of power equipment management, ensuring the stable and reliable operation of the power system.

[0016] By counting the number of power equipment clusters and collecting multi-dimensional data, a device wave function model is constructed to accurately describe the distribution of device states. Based on this model, a density matrix is ​​constructed to quantify the degree of quantum entanglement and uncertainty in the device cluster. A quantum correlation decoder is designed to extract quantum correlation information between devices and construct a collaborative diagnosis model for the device cluster. Ultimately, this model is used to predict the risk of collaborative failures. This series of technical solutions enables more comprehensive and in-depth status monitoring and fault prediction of power equipment clusters, effectively improving the safety and reliability of power system operation and providing strong support for intelligent power system management.

[0017] By monitoring the quantum-to-classical state conversion process of a cluster of devices in real time and collecting key data, the team accurately identifies critical states at the moment of conversion and extracts boundary-state fault characteristics. Based on this, an effective conversion control strategy is developed, and boundary-state characteristics are incorporated into a collaborative diagnostic model. This solution enables comprehensive control of the quantum-to-electrostatic conversion process of a cluster of devices, enabling more timely detection of potential fault risks, improving the stability and reliability of the cluster's operations, and providing strong and comprehensive support for intelligent management and fault prevention of the cluster. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] Figure 1 A schematic diagram of a flow chart of a power data management method according to an embodiment of the present invention; Figure 2 This is a structural block diagram of a power data management system according to an embodiment of the present invention. DETAILED DESCRIPTION

[0019] To facilitate understanding of the present invention, the present application will be described more comprehensively below with reference to the relevant drawings; the drawings show preferred embodiments of the present invention, but the present invention can be implemented in many different forms and is not limited to the embodiments described herein; on the contrary, the purpose of providing these embodiments is to enable a more thorough and comprehensive understanding of the disclosed content of the present invention.

[0020] It should be noted that the terms “vertical”, “horizontal”, “up”, “down”, “left”, “right” and similar expressions used in this document are for illustrative purposes only and do not represent the only implementation method.

[0021] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by those skilled in the art to which this invention pertains; the terms used herein in the specification of the present invention are for the purpose of describing specific embodiments only and are not intended to limit the present invention; the term "and / or" used herein includes any and all combinations of one or more of the associated listed items.

[0022] Example 1: Figure 1 It is a flowchart of a power data management method according to an embodiment of the present invention.

[0023] like Figure 1 As shown, a power data management method includes the following steps: S1, obtain the historical data of a single power device and establish a mathematical model of the change in historical data value and equipment life.

[0024] Specifically, we counted the actual number of power equipment in the power system and collected data sets from the area where each power equipment is located, including environmental monitoring data, basic operating status data, user electricity usage data, and historical power data. We also analyzed the impact of equipment aging on data value, taking into account equipment age, maintenance records, environmental factors, and other factors. We then constructed a mathematical model describing the relationship between historical data value (V) and equipment lifespan (L).

[0025] The mathematical model describing the relationship between historical data value (V) and equipment life (L) is as follows:

[0026] V is the data value of the device at its life span L; is the initial data value of the device (i.e. the data value when the lifespan is 0); is the decay coefficient, which indicates how quickly the value of data decreases as its age increases; Is a random error term, which can usually be ignored or set to 0 in actual calculations (if the model is accurate enough and the data quality is high). Before calculation, it is necessary to determine the parameters in the model and . Use historical data to fit the model, that is, find a set of and The value of minimizes the difference between the model's predicted data value and the observed data value. Once the model parameters are determined, the data value of the device at different life stages can be calculated. The life stages for which data value calculations are required (e.g., 1 year, 5 years, 10 years, etc.) are determined. Each selected life stage, L, is substituted into the model formula to calculate the corresponding data value, V.

[0027] S2, calculates the data value of the device at different life stages based on the model, draws the life change curve and marks the decay time nodes and data typical characteristics.

[0028] Specifically, using the mathematical model established in S1, we input different values ​​of device lifespan (L) and calculate the corresponding data value (V). We then plot a lifespan curve with device lifespan (L) on the horizontal axis and data value (V) on the vertical axis. We set a data value decay threshold. When the data value falls below this threshold, the corresponding lifespan point is marked as the decay time node. We observe and record typical characteristics of the data during the decay process, such as increased data fluctuations and an increase in outliers.

[0029] Among them, the decay time node indicates the time point when the value of device data begins to decline significantly, indicating that the device is aging or its performance is declining.

[0030] S3, using the life change curve as a reference curve and comparing it with the real-time collected data, determines the impact value of the current data characteristics on the equipment life warning level and the corresponding data.

[0031] Specifically, based on the constructed model, a device life cycle curve is generated, which shows the expected trend of device performance indicators over time. Real-time data is aligned with corresponding time points on the device life cycle curve. The difference between the real-time data and the reference curve is calculated. Features related to device life cycle are extracted from the real-time data and compared with the features on the reference curve. Based on the size of the difference and the trend of feature changes, the device life cycle warning level is divided. Based on the difference and feature changes, the data impact value is calculated to quantify the impact of real-time data on device life cycle.

[0032] The calculation formula for data impact value is:

[0033] , is the weight coefficient, is the difference between the real-time data and the reference curve, ΔF is the change in the characteristic, is the remaining life of the equipment (estimated from the reference curve).

[0034] S4, combines the data impact value and other impact indices to generate the power spatial situation prediction index.

[0035] Among them, other impact indices include: calculating the predicted environmental impact index based on environmental monitoring data, calculating the basic operating status index based on basic operating status data (which can be calculated based on the degree of deviation between the equipment operating status and the ideal state), and calculating the predicted power load impact index based on user electricity consumption data and historical power data (predicted using a time series forecasting model, calculated based on the difference between the predicted value and the historical average).

[0036] Specifically, data related to the operating environment of power equipment, such as temperature, humidity, air quality, and wind speed, is collected. This environmental monitoring data is processed to extract key features, such as the frequency of extreme weather events and the rate of change of environmental parameters. Using machine learning algorithms, an environmental impact prediction model is constructed, and a predicted environmental impact index is calculated based on current and historical environmental data. Basic operating status data for power equipment, such as voltage, current, power factor, and equipment temperature, is collected. The current operating status of the equipment is assessed based on the operating specifications or industry standards provided by the equipment manufacturer. Based on the assessment results, a basic operating status index is calculated to reflect the health and operating efficiency of the equipment. User electricity usage data and historical power load data are collected, and future power load is predicted using time series analysis. Based on the predicted results, a predicted power load impact index is calculated to reflect the potential impact of future power load on the power spatial situation. Weights are assigned to the data impact value, predicted environmental impact index, basic operating status index, and predicted power load impact index based on the degree of impact of each index on the power spatial situation.

[0037] Among them, the power spatial situation prediction index can be calculated by weighted average of various indices:

[0038] , , and is the weight of each index, is the predicted environmental impact index, is the basic operating status index, It is the predicted power load impact index.

[0039] S5, determines the accuracy of the predicted time node based on the power space situation prediction index, analyzes the fit between the reference curve and the current equipment life curve, and traces back to the real cause of the equipment.

[0040] Specifically, data is collected on the time when the device actually fails or experiences significant performance degradation. Accuracy metrics are calculated based on the predicted time points and the actual failure time. The time axes of the reference curve and the current device life curve are aligned, and the difference in performance metrics between the reference and current curves at the same time points is calculated. The fit between the two curves is evaluated based on the magnitude and distribution of the difference. Based on the fit between the predicted time points, a backpropagation algorithm is used to trace back, simulating the reverse process from the failure manifestation to the initial cause. (The backpropagation algorithm must account for time reversal asymmetry, namely the decay of information entropy from the failure manifestation (t=0) to the cause (t=-Δt).

[0041] During the time-travel process, the algorithm should construct a multi-order correlation model. Through time series analysis and causal inference, it should reveal the inherent connections between each stage, restore the complete fault chain, and identify and address hidden causes (for example, initial micro-defects (such as a 0.1mm crack) may appear as normal noise during routine monitoring. To this end, the algorithm should use highly sensitive detection technology, combining historical and real-time data, and using pattern recognition and anomaly detection methods to identify potential causes) and multi-order correlation masking (for example, the chain reaction of guano contamination → partial discharge → insulation aging → flashover may be fragmented by discrete data points). Based on the results of the time-travel algorithm, the true cause of the current equipment failure is determined. The cause may include environmental factors (such as guano contamination), equipment aging, improper operation, etc. An assessment report is generated, including the equipment name, location, cause type, time of occurrence, and potential risks.

[0042] The technical solutions in the above embodiments of the present application have at least the following technical effects or advantages: By constructing a mathematical model that correlates the value of historical data with the lifespan of equipment, this approach effectively addresses key technical issues in power equipment management. Traditional power equipment management struggles to accurately quantify the value of equipment data as it changes with lifespan, preventing timely warnings of equipment lifespan issues. Furthermore, it struggles to comprehensively assess power spatial trends and trace the causes of equipment failures. This solution constructs a mathematical model to quantify the relationship between the value of equipment data and lifespan, visually presenting value trends and providing timely warnings of equipment life anomalies. It also integrates multi-dimensional data to generate a situation prediction index for a comprehensive assessment of operational status and can also reversely trace the true causes of equipment failures. This significantly improves the accuracy and efficiency of power equipment management, ensuring the stable and reliable operation of the power system.

[0043] Example 2: Existing power data analysis and fault prediction technologies primarily focus on tracing the causes of failures in individual devices. However, in actual power grid operation, multiple devices may exhibit coordinated failure characteristics due to quantum entanglement (e.g., shared electromagnetic fields, mechanical resonance). In this case, methods for tracing the causes of failures in individual devices fail, making it impossible to accurately predict and diagnose coordinated failures in a group of devices. To address this issue, the present embodiment of the application offers certain optimizations based on the above-mentioned examples.

[0044] In some embodiments, in step S5, the actual cause of the reverse tracing device further includes: S51, counting the actual number of power equipment groups covered by the power system, and collecting data sets of the areas where each power equipment is located.

[0045] The data set includes: environmental monitoring data, basic operating status data, user electricity consumption data and historical power data.

[0046] S52, establishing a device wave function model that describes the probability distribution of each device in the device group in different states.

[0047] Specifically, each device in the device group is analyzed in detail to determine all possible states it can be in. For example, for a transformer, possible states include normal operation, overload, local overheating, insulation aging, fault shutdown, etc. The determined device states are encoded for subsequent digital processing. Assuming that the device has n possible states, use Indicates that (j=1,2, ,n) represents the jth state of the device.

[0048] Based on the collected data, count the number of times the device is in each state. Assume that within a period of time, the device is in state The number of times is , the total number of device state transitions is M ( ), the device is in state The probability amplitude The calculation formula is: , based on the frequency, the probability that a device is in a certain state is proportional to the frequency of the state appearing in the historical data.

[0049] According to the calculated probability , construct a wave function Ψ that describes the device state. For each device in the device group, its wave function Ψ can be expressed as a linear combination of the device in various states, that is: ,in, The device is in state The probability amplitude satisfies the normalization condition The physical meaning of the normalization condition is that the device must be in one of n possible states, and the sum of the probabilities of being in various states is 1.

[0050] The constructed wave function is verified by comparing it with the actual data to check whether it meets the normalization conditions and whether it can reasonably describe the state distribution of the device.

[0051] S53, constructs a density matrix based on the device wave function model to quantify the degree of quantum entanglement and uncertainty of the device group.

[0052] The degree of quantum entanglement in a device group is quantified using entanglement entropy. The device group is divided into two subsystems, A and B. For example, a portion of the devices can be assigned to subsystem A, while the remaining devices can be assigned to subsystem B. Subsystem B is traced to obtain the reduced density matrix of subsystem A. The trace operation sums all possible states of subsystem B and then calculates the entanglement entropy. The specific calculation process for entanglement entropy is referenced in existing technologies and is not detailed here. Von Neumann entropy is used to quantify the uncertainty of the device group. The specific calculation process is referenced in existing technologies and is not detailed here.

[0053] S54, designs a quantum correlation decoder for the quantum entangled state in the device group, decodes the quantum correlation information between devices and builds a collaborative diagnosis model for the device group.

[0054] Specifically, the entangled state representation is determined. Based on the constructed device cluster density matrix, the quantum entangled state of the device cluster is analyzed. For example, if the device cluster consists of two subsystems A and B, its entangled state may be represented as ,in and are the states of subsystems A and B respectively, is a complex coefficient that satisfies the normalization condition .

[0055] Design a decoding measurement basis. Clearly identify the causal quantum correlation information between devices that need to be decoded, and construct a measurement basis based on the target correlation information. , the measurement basis can be expressed as ,in and are the measurement basis vectors of subsystems A and B. The choice of measurement basis should be able to extract the correlation information in the entangled state to the greatest extent.

[0056] Implement quantum measurement. Perform quantum measurement on the device group and project the state of the device group onto the measurement basis. The measurement result appears in the form of probability. It is measured that subsystem A is in state And subsystem B is in state The probability of . Perform multiple measurements and statistically analyze the distribution of measurement results to obtain more accurate quantum correlation information.

[0057] Key information extraction. Analyze the probability distribution of the measurement results and extract the quantum correlation information between devices. For example, the degree of correlation between devices can be quantified by calculating the mutual information between the measurement results: I(A;B)=H(A)+H(B)-H(A,B), where H(A), H(B), and H(A,B) are the Shannon entropies of subsystem A, subsystem B, and device group AB, respectively. The Shannon entropy is calculated as H(X)=- , P(x) is the probability that system X is in state x.

[0058] Build a collaborative diagnosis model for a cluster of devices. In addition to quantum correlation information, collect classical operating characteristics of the devices, such as voltage, current, and temperature. Fuse the quantum correlation and classical characteristics to form a comprehensive feature vector. Collect device operating data in real time, extract quantum correlation and classical characteristics, and form a comprehensive feature vector. Input the real-time feature vector into the trained collaborative diagnosis model for real-time diagnosis, generating diagnostic results for the devices.

[0059] S55, using the equipment group collaborative diagnosis model, processes and analyzes the data collected in real time to predict the collaborative failure risk of the equipment group.

[0060] Specifically, if the device group has quantum entanglement characteristics, the quantum state of the device group can be estimated based on the real-time collected data using techniques such as quantum state tomography. For example, for the entangled state of two devices, the density matrix ρ of the quantum state can be reconstructed using methods such as maximum likelihood estimation by measuring the results under different basis vectors multiple times. Based on the estimated quantum state, the quantum correlation characteristics between the devices are calculated. The preprocessed classical features and the extracted quantum correlation features are fused to form a comprehensive feature vector ,in is the classical eigenvector, The quantum correlation eigenvector is extracted in real time and fed into the collaborative diagnosis model. The model calculates the input eigenvector and outputs a prediction of the collaborative failure risk of the device cluster. A threshold for collaborative failure risk is set based on actual needs and historical data. For example, a probability greater than 0.7 for a device cluster to be in a critical failure state indicates a high collaborative failure risk. Decisions are then made based on the prediction results and the risk threshold.

[0061] The technical solutions in the above embodiments of the present application have at least the following technical effects or advantages: By counting the number of power equipment clusters and collecting multi-dimensional data, a device wave function model is constructed to accurately describe the distribution of device states. Based on this model, a density matrix is ​​constructed to quantify the degree of quantum entanglement and uncertainty in the device cluster. A quantum correlation decoder is designed to extract quantum correlation information between devices and construct a collaborative diagnosis model for the device cluster. Ultimately, this model is used to predict the risk of collaborative failures. This series of technical solutions enables more comprehensive and in-depth status monitoring and fault prediction of power equipment clusters, effectively improving the safety and reliability of power system operation and providing strong support for intelligent power system management.

[0062] Example 3: In a hybrid quantum-classical system, when a group of power devices transitions between quantum and classical states, boundary state information loss can occur. Existing technologies are unable to effectively capture the critical state at the moment of transition, resulting in the collapse of quantum correlations during classical transitions, high information loss rates, masking boundary state fault characteristics, and failure of collaborative prediction models in the transition region. To address these issues, the present embodiment provides certain optimizations based on the above-mentioned examples.

[0063] In some embodiments, in step S51, collecting a data set of the area where each power device is located further includes: 1A, real-time monitoring of the conversion process of the device group between the quantum state and the classical state, and data collection at the moment of conversion of the device group between the quantum state and the classical state.

[0064] Specifically, sensors capable of simultaneously monitoring both quantum and classical states are installed in the device cluster. Special equipment such as quantum bit detectors are used for quantum state monitoring, while conventional voltage, current, temperature, and other sensors are used for classical state monitoring. The signals collected by the sensors are digitized and transmitted to the data processing center. The status of the device cluster is continuously monitored, and when it is detected that the device cluster may be in the transition zone between quantum and classical states, the data collection frequency is increased. For example, the data collection rate can be increased from once per second to once per millisecond. The timestamp of the conversion moment, quantum state parameters (such as the spin state of the quantum bit, the degree of entanglement, etc., if measurable), and classical state parameters (such as voltage, current, temperature, etc.) are recorded.

[0065] 1B, identify the critical state at the transition moment and perform feature extraction to determine the fault characteristics unique to the boundary state.

[0066] Specifically, the collected data is preprocessed to remove noise and outliers. For example, a moving average filter is used to smooth the classical state data. The changing trends of quantum and classical state parameters are analyzed. When both quantum and classical state parameters show significant changes simultaneously, the device cluster is considered to be in a critical state at the moment of transition. Fault signatures unique to boundary states are extracted from the critical state data. For example, the rate of change of quantum state parameters and the magnitude of the sudden change in classical state parameters (such as the maximum sudden change in current) are extracted.

[0067] 1C. Based on the results of boundary state monitoring and identification, formulate a quantum-classical boundary state conversion control strategy.

[0068] Specifically, based on the extracted boundary state characteristics, the stability and reliability of the device cluster during the transition between quantum and classical states are analyzed. For example, if the rate of change of the quantum entanglement entropy is too large, it may lead to unstable performance of the device cluster. Based on the analysis results, a control strategy is formulated. For example, when the rate of change of the quantum entanglement entropy exceeds a certain threshold α, the operating parameters of the device cluster are adjusted, such as reducing the input power or changing the operating frequency.

[0069] 1D, introduce boundary state characteristic parameters into the equipment group collaborative diagnosis model to conduct real-time monitoring and early warning of the equipment group's operating status.

[0070] Specifically, the extracted boundary state characteristic parameters are introduced into the equipment cluster collaborative diagnosis model. For example, in a neural network model, these characteristic parameters are used as new input nodes. The updated model is retrained using historical data to adjust the model parameters. The operating data of the equipment cluster is collected in real time, and the boundary state characteristic parameters and classical characteristic parameters are extracted to form a comprehensive feature vector. The real-time feature vector is input into the updated collaborative diagnosis model, which outputs the operating status of the equipment cluster and the failure risk prediction results. Based on the prediction results and the set risk threshold, an early warning strategy is formulated. For example, when the probability of the equipment cluster being in a serious failure state is greater than a certain threshold β, an early warning signal is issued to notify relevant personnel to take action.

[0071] The technical solutions in the above embodiments of the present application have at least the following technical effects or advantages: By monitoring the quantum-to-classical state conversion process of a cluster of devices in real time and collecting key data, the team accurately identifies critical states at the moment of conversion and extracts boundary-state fault characteristics. Based on this, an effective conversion control strategy is developed, and boundary-state characteristics are incorporated into a collaborative diagnostic model. This solution enables comprehensive control of the quantum-to-electrostatic conversion process of a cluster of devices, enabling more timely detection of potential fault risks, improving the stability and reliability of the cluster's operations, and providing strong and comprehensive support for intelligent management and fault prevention of the cluster.

[0072] Furthermore, an embodiment of the present invention also provides a power data management system.

[0073] Figure 2 It is a structural diagram of a power data management system according to an embodiment of the present invention.

[0074] like Figure 2 As shown, an electric power data management system includes: an acquisition module, a classification module, an analysis module, a calculation module and a tracing module.

[0075] An acquisition module is used to obtain historical data of power equipment and establish a mathematical model of the value of historical data and the change of equipment life; The classification module is used to calculate the data value of the equipment at different life stages based on the model, draw the life change curve and mark the decay time nodes and data typical characteristics; The analysis module uses the life change curve as a reference curve and compares it with the real-time collected data to determine the impact of the current data characteristics on the equipment life warning level and the corresponding data value; Calculation module: Combines data impact value and other impact indexes to generate power space situation prediction index; The tracing module determines the accuracy of the predicted time node based on the power space situation prediction index, analyzes the fit between the reference curve and the current equipment life curve, and traces back the real cause of the equipment.

[0076] It should be noted that other specific implementation contents of a power data management system according to an embodiment of the present invention may refer to the above-mentioned power data management method.

[0077] The foregoing description is merely a preferred embodiment of the present invention and is not intended to limit the present invention. Various modifications and variations are readily apparent to those skilled in the art. Any modifications, equivalent substitutions, or improvements made within the spirit and principles of the present invention shall be included within the scope of protection of the present invention.

Claims

1. A power data management method, characterized in that: The method comprises: S1, obtain historical data of a single power device and establish a mathematical model of the change in historical data value and equipment life; S2, calculates the data value of the device at different life stages based on the model, draws a life change curve and marks the decay time nodes and data typical characteristics; S3, using the life change curve as a reference curve and comparing it with the real-time collected data to determine the impact of the current data characteristics on the equipment life warning level and the corresponding data value; S4, combining the data impact value and other impact indices to generate the power spatial situation estimation index; S5, determines the accuracy of the predicted time node based on the power space situation prediction index, analyzes the fit between the reference curve and the current equipment life curve, and traces back to the real cause of the equipment.

2. The power data management method according to claim 1, wherein: The S5, reverse tracing of the real cause of the device includes: collecting time data when the device actually fails or its performance deteriorates significantly, and calculating the accuracy index based on the predicted time node and the actual failure time; aligning the time axis of the reference curve and the current device life curve, calculating the difference in performance indicators between the reference curve and the current device life curve at the same time point, and evaluating the fit of the two curves based on the size and distribution of the difference; and using the back propagation algorithm to perform reverse tracing based on the fit of the predicted time node, simulating the inverse process from the fault manifestation to the initial cause.

3. The power data management method according to claim 2, wherein: The reference curve includes: constructing a mathematical model describing the relationship between the historical data value V and the equipment life L ; Where V is the data value of the device at its life span L; is the initial data value of the device; is the attenuation coefficient, is the random error term; with the equipment life L as the horizontal axis and the data value V as the vertical axis, a life change curve is drawn, and the life change curve is used as the reference curve.

4. The power data management method according to claim 1, wherein: In S5, the real incentives for reverse tracing the device also include: S51, counting the actual number of power equipment groups covered by the power system, and collecting data sets for the areas where each power equipment is located; S52, establishing a device wave function model that describes the probability distribution of each device in the device group in different states; S53, constructs a density matrix based on the device wave function model to quantify the degree of quantum entanglement and uncertainty of the device group; S54, design a quantum correlation decoder for the quantum entangled state in the device group, decode the quantum correlation information between devices and build a collaborative diagnosis model for the device group; S55, using the equipment group collaborative diagnosis model, processes and analyzes the data collected in real time to predict the collaborative failure risk of the equipment group.

5. The power data management method according to claim 4, characterized in that: The S52 is to establish a device wave function model that describes the probability distribution of each device in the device group in different states, including: determining all states that each device in the device group can be in; based on the collected data, counting the number of times the device is in each state, calculating the probability amplitude, and constructing a wave function Ψ that describes the device state; verifying the constructed wave function by comparing it with the actual data to check whether it meets the normalization conditions and whether it can reasonably describe the state distribution of the device.

6. The power data management method according to claim 4, characterized in that: The S54 includes: analyzing the quantum entangled state of the device group based on the constructed device group density matrix; clarifying the causal quantum correlation information between devices that needs to be decoded, and constructing a measurement basis based on the target correlation information; performing quantum measurement on the device group, and projecting the state of the device group onto the measurement basis; analyzing the probability distribution of the measurement results, and extracting the quantum correlation information between devices; in addition to the quantum correlation information, collecting the classical operation characteristics of the devices; and fusing the quantum correlation characteristics and the classical characteristics to form a comprehensive feature vector.

7. The power data management method according to claim 4, wherein: The S51, collecting the data set of the area where each power equipment is located, also includes: real-time monitoring of the conversion process between the quantum state and the classical state of the equipment group, and collecting data of the equipment group at the moment of conversion between the quantum state and the classical state; identifying the critical state at the moment of conversion and performing feature extraction to determine the fault characteristics unique to the boundary state; formulating a quantum-classical boundary state conversion control strategy based on the results of boundary state monitoring and identification; introducing boundary state characteristic parameters into the equipment group collaborative diagnosis model, and performing real-time monitoring and early warning of the operating status of the equipment group.

8. The power data management method according to claim 7, characterized in that: The method of determining the fault characteristics unique to the boundary state includes: preprocessing the collected data to remove noise and anomalies; analyzing the changing trends of quantum state and classical state parameters; when the quantum state parameters and the classical state parameters show significant changes at the same time, it is considered that the device group is in a critical state at the moment of conversion; and extracting the fault characteristics unique to the boundary state from the critical state data.

9. The power data management method according to claim 7, wherein: The real-time monitoring and early warning of the operating status of the equipment group specifically includes: introducing the extracted boundary state characteristic parameters into the equipment group collaborative diagnosis model; using historical data to retrain the updated model and adjust the model parameters; collecting the operating data of the equipment group in real time, extracting the boundary state characteristic parameters and classical characteristic parameters, and forming a comprehensive characteristic vector; inputting the real-time characteristic vector into the updated collaborative diagnosis model, and the model outputting the operating status of the equipment group and the fault risk prediction results; and formulating an early warning strategy based on the prediction results and the set risk threshold.

10. A power data management system, applied to a power data management method according to any one of claims 1 to 9, characterized in that: The system comprises: An acquisition module is used to obtain historical data of power equipment and establish a mathematical model of the value of historical data and the change of equipment life; The classification module is used to calculate the data value of the equipment at different life stages based on the model, draw the life change curve and mark the decay time nodes and data typical characteristics; The analysis module uses the life change curve as a reference curve and compares it with the real-time collected data to determine the impact of the current data characteristics on the equipment life warning level and the corresponding data value; Calculation module: Combines data impact value and other impact indexes to generate power space situation prediction index; The tracing module determines the accuracy of the predicted time node based on the power space situation prediction index, analyzes the fit between the reference curve and the current equipment life curve, and traces back the real cause of the equipment.

Images