Power system metering secondary circuit detection and early warning method and device

Abstract

The present invention discloses a method and device for detecting and warning secondary circuits in a power system, and relates to the technical field of power circuit detection and warning. The method comprises: using the current test line of a portable calibrator to provide a current signal to the current terminal box merging unit of any secondary circuit in the power system, and providing a voltage signal to the voltage terminal box merging unit of the secondary circuit via a voltage pay-out vehicle; obtaining a current signal sequence, a voltage signal sequence, and an electric energy pulse signal; obtaining an iterative interactive current signal sequence and an iterative interactive voltage signal sequence; obtaining a target secondary circuit comprehensive error; and generating a first warning message when the target secondary circuit comprehensive error is greater than a preset error threshold. The present invention solves the technical problems of hysteresis and low warning reliability in the prior art for secondary circuit detection and warning, and achieves the technical effect of improving the accuracy of secondary circuit detection and warning.

Description

Technical Field

[0001] The present invention relates to the technical field of power circuit detection and early warning, and in particular to a method and device for detecting and early warning a secondary circuit of a power system metering system. Background Art

[0002] Smart substations offer significant advantages in safety, reliability, power quality, investment costs, and maintenance. In this context, ensuring the safe and stable operation of smart substations and measuring and safeguarding the stability of their metering devices have become pressing challenges. Currently, with the development of smart substations, the cost of measuring errors in secondary circuit metering devices, as well as the economic losses caused by untimely and inaccurate measurements, are increasing. Therefore, power companies are increasingly focusing on how to accurately, promptly, and conveniently measure secondary circuit metering device errors in all states of smart substations and improve measurement efficiency.

[0003] The existing technology has technical problems such as hysteresis in secondary circuit detection and early warning, and low early warning reliability. Summary of the Invention

[0004] The present application provides a method and device for detecting and warning a secondary circuit of a power system meter, which is used to solve the technical problems in the prior art of hysteresis in detecting and warning a secondary circuit and low reliability of warning.

[0005] In view of the above problems, the present application provides a method and device for detecting and warning of a secondary circuit of a power system metering system.

[0006] A first aspect of the present application provides a method for detecting and warning a secondary circuit of a power system metering system, the method comprising:

[0007] Use the current test line of the portable calibrator to provide current signals for the current terminal box merging unit of any secondary circuit in the power system, and use the voltage pay-out vehicle to provide voltage signals for the voltage terminal box merging unit of the secondary circuit;

[0008] Performing simultaneous data acquisition on the current terminal box merging unit and the voltage terminal box merging unit within a preset detection window, and using a wireless radio frequency synchronization module to receive the electric energy pulse signal of the digital electric energy meter to obtain a current signal sequence, a voltage signal sequence, and an electric energy pulse signal;

[0009] Performing multi-scale iterative interaction analysis on the current signal sequence and the voltage signal sequence to obtain an iterative interactive current signal sequence and an iterative interactive voltage signal sequence;

[0010] Perform secondary circuit comprehensive error analysis based on iterative interactive current signal sequence, iterative interactive voltage signal sequence and electric energy pulse signal to obtain target secondary circuit comprehensive error;

[0011] When the target secondary loop comprehensive error is greater than a preset error threshold, a first warning message is generated.

[0012] A second aspect of the present application provides a power system metering secondary circuit detection and early warning device, the device comprising:

[0013] The current signal providing module is used to provide a current signal to the current terminal box merging unit of any secondary circuit in the power system using the current test line of the portable calibrator, and to provide a voltage signal to the voltage terminal box merging unit of the secondary circuit through the voltage pay-out vehicle;

[0014] A signal sequence acquisition module is used to simultaneously collect data from the current terminal box merging unit and the voltage terminal box merging unit within a preset detection window, and to receive the electric energy pulse signal from the digital electric energy meter using a wireless radio frequency synchronization module to obtain a current signal sequence, a voltage signal sequence, and an electric energy pulse signal;

[0015] An iterative interaction analysis module is used to perform multi-scale iterative interaction analysis on the current signal sequence and the voltage signal sequence to obtain an iterative interaction current signal sequence and an iterative interaction voltage signal sequence;

[0016] A comprehensive error acquisition module is used to perform a comprehensive error analysis of the secondary circuit based on the iterative interactive current signal sequence, the iterative interactive voltage signal sequence and the electric energy pulse signal to obtain a target comprehensive error of the secondary circuit;

[0017] The first warning information generating module is used to generate a first warning information when the target secondary loop comprehensive error is greater than a preset error threshold.

[0018] One or more technical solutions provided in this application have at least the following technical effects or advantages:

[0019] The present application utilizes the current test line of a portable calibrator to provide a current signal for the current terminal box merging unit of any secondary circuit in the power system, and provides a voltage signal for the voltage terminal box merging unit of the secondary circuit through a voltage pay-out vehicle, and then performs simultaneous data acquisition on the current terminal box merging unit and the voltage terminal box merging unit within a preset detection window, and utilizes a wireless radio frequency synchronization module to receive the electric energy pulse signal of a digital electric energy meter, to obtain a current signal sequence, a voltage signal sequence, and an electric energy pulse signal, and then performs multi-scale iterative interactive analysis on the current signal sequence and the voltage signal sequence to obtain an iterative interactive current signal sequence and an iterative interactive voltage signal sequence, and performs a secondary circuit comprehensive error analysis based on the iterative interactive current signal sequence and the iterative interactive voltage signal sequence to obtain a target secondary circuit comprehensive error, and then generates a first warning message when the target secondary circuit comprehensive error is greater than a preset error threshold. The technical effect of improving the reliability of secondary circuit detection and warning is achieved. BRIEF DESCRIPTION OF THE DRAWINGS

[0020] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0021] Figure 1 A flow chart of a method for detecting and warning a secondary circuit in a power system metering system according to an embodiment of the present application;

[0022] Figure 2 A schematic diagram of a flow chart for obtaining an iterative interactive current signal sequence and an iterative interactive voltage signal sequence in a power system metering secondary circuit detection and early warning method provided in an embodiment of the present application;

[0023] Figure 3 This is a structural diagram of the power system metering secondary circuit detection and early warning device provided in an embodiment of the present application.

[0024] Explanation of the accompanying symbols: current signal providing module 11, signal sequence obtaining module 12, iterative interaction analysis module 13, comprehensive error obtaining module 14, first warning information generating module 15. DETAILED DESCRIPTION

[0025] This application provides a method and device for detecting and warning a secondary circuit of a power system meter, which is used to solve the technical problems in the prior art of hysteresis in secondary circuit detection and warning and low warning reliability.

[0026] The following will be combined with the drawings in the embodiments of this application to clearly and completely describe the technical solutions in the embodiments of this application. Obviously, the embodiments described are only part of the embodiments of this application, not all of them. Based on the embodiments in this application, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of this application.

[0027] It should be noted that the terms "including" and "having" are intended to cover non-exclusive inclusions. For example, a process, method, apparatus, product or server that includes a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or modules that are not explicitly listed or are inherent to these processes, methods, products or devices.

[0028] Example 1, as Figure 1 As shown, the present application provides a method for detecting and warning a secondary circuit of a power system metering system, the method comprising:

[0029] S1: Use the current test line of the portable calibrator to provide a current signal to the current terminal box merging unit of any secondary circuit in the power system, and use the voltage pay-out vehicle to provide a voltage signal to the voltage terminal box merging unit of the secondary circuit;

[0030] In one possible embodiment, the portable calibrator is a portable intelligent station metering secondary circuit field calibrator, which can provide analog signals for various types of equipment in the power system or measure the accuracy of the equipment. The portable intelligent station metering secondary circuit field calibrator is convenient for on-site operation and helps verify the accuracy of the power system equipment by providing accurate current and voltage signals. The current test line is the part of the portable calibrator used to provide current signals to the current terminal box merging unit in the power system. The current test line simulates the current signal and inputs the current signal into the power system to test the system response. The voltage pay-out vehicle is a device used to provide voltage signals to the power system on site, which can transmit the voltage signal to the voltage terminal box merging unit. The voltage pay-out vehicle can be used to test the power equipment without interfering with the operation of the system.

[0031] The current terminal box merging unit is a key component in the secondary circuit, responsible for aggregating and processing multiple current signals to accurately measure the current flowing through the system. The voltage terminal box merging unit is used to aggregate multiple voltage signals in the power system, ensuring the accuracy of voltage data for power quality analysis in the secondary circuit.

[0032] The current test line provides a current signal to the current terminal box merging unit, simulating the current conditions in a real working environment. The voltage payout vehicle also provides a voltage signal to the voltage terminal box merging unit, accurately simulating voltage changes. This prepares the system for secondary circuit detection and early warning. This ensures that during the test, each merging unit in the secondary circuit receives a standard test signal, providing a foundation for subsequent data acquisition and error detection.

[0033] S2: performing simultaneous data acquisition on the current terminal box merging unit and the voltage terminal box merging unit within a preset detection window, and using a wireless radio frequency synchronization module to receive the electric energy pulse signal of the digital electric energy meter to obtain a current signal sequence, a voltage signal sequence, and an electric energy pulse signal;

[0034] In one possible embodiment, the preset detection window is a test period pre-set within a time range. The length of the preset detection window and the frequency of detection are set by those skilled in the art based on the operating characteristics of the equipment, test requirements, and system load conditions. The wireless radio frequency synchronization module is a high-precision wireless synchronization technology device that ensures data synchronization between different devices through radio frequency technology, and can effectively receive electric energy pulse signals from digital electric energy meters to obtain accurate electric energy data. The digital electric energy meter outputs the consumed electric energy information in the form of electric energy pulses, and these pulse signals are used to accurately record the consumption of electric energy. Each electric energy pulse represents a certain amount of power consumption.

[0035] Preferably, the current signal and voltage signal are collected synchronously in the same time period, and the wireless radio frequency synchronization module is used to receive the electric energy pulse signal of the digital electric energy meter, and the time synchronization protocol of the smart substation (such as IEEE1588) is used to ensure the timing alignment of the collected data to avoid data asynchrony.

[0036] The current signal sequence, voltage signal sequence, and energy pulse signal are time series records of current, voltage, and energy pulse signals, respectively. The current signal sequence records current changes within a preset detection window, the voltage signal sequence records voltage changes within a preset detection window, and the energy pulse signal is used to record the pulse signal output of electrical energy. This achieves a comprehensive record of the operating status of the power system's secondary circuit.

[0037] Simultaneously acquires multi-dimensional data such as current, voltage, and energy pulses to provide accurate measurement data. Synchronous data acquisition allows precise tracking of the operating status of various metering devices in the power system, ensuring timely detection of potential electrical faults or anomalies, thereby improving measurement reliability and accuracy.

[0038] S3: Perform multi-scale iterative interactive analysis on the current signal sequence and the voltage signal sequence to obtain an iterative interactive current signal sequence and an iterative interactive voltage signal sequence;

[0039] In one embodiment, the current signal sequence and the voltage signal sequence are subjected to feature analysis at different scales to capture the transient changes and long-term trends of the secondary circuit within a preset detection window, thereby obtaining more representative iterative interactive current signals and iterative interactive voltage signals, and providing more reliable analysis data for subsequent error detection and early warning analysis.

[0040] Preferably, a multi-scale analysis is first performed on the current and voltage signal sequences. Signal features at different time scales are extracted and interactively calculated to ensure the fusion of short- and long-term feature information. For example, a short-time window can identify sudden current pulse anomalies, while a long-time window can detect slowly changing trend deviations. Subsequently, an iterative interactive analysis method is used to perform multiple rounds of updates on features at different time scales. By constructing an iterative interactive matrix, current and voltage features can be propagated across different scales, resulting in more robust anomaly detection capabilities.

[0041] By obtaining iterative interactive current signals and iterative interactive voltage signals that are more stable than the original signals, the technical effect of reducing errors caused by data noise or single-scale analysis is achieved.

[0042] S4: Perform secondary circuit comprehensive error analysis based on the iterative interactive current signal sequence, the iterative interactive voltage signal sequence, and the electric energy pulse signal to obtain the target secondary circuit comprehensive error;

[0043] S5: When the target secondary loop comprehensive error is greater than a preset error threshold, a first warning message is generated.

[0044] In an embodiment of the present application, a standard electric energy meter measurement module (included in the portable calibrator) is used to calculate electric energy from the iterative interactive current signal and the iterative interactive voltage signal to obtain a standard electric energy. The calculated standard electric energy is then subtracted from the iterative interactive electric energy pulse signal, and the calculated difference is compared with the standard electric energy to obtain the target secondary circuit comprehensive error.

[0045] Preferably, the standard electric energy meter measurement module is embedded with a standard electric energy calculation formula, wherein the standard electric energy calculation formula is: ; is the standard electrical energy, is the instantaneous power, is the preset detection window, is the iterative interactive voltage signal sequence, The standard electric energy calculation formula is used to calculate the standard electric energy of the iterative interactive current signal sequence and the iterative interactive voltage signal sequence.

[0046] In one embodiment, the preset error threshold is the maximum error for normal secondary circuit operation, pre-set by those skilled in the art. When the target secondary circuit combined error exceeds the preset error threshold, it indicates a secondary circuit anomaly, and the first warning message is generated. This first warning message alerts personnel to abnormal secondary circuit operation in the power system. By iteratively interacting with the signal, data quality is improved, ensuring the reliability and accuracy of error analysis and the timeliness of warnings.

[0047] Further, such as Figure 2 As shown, a multi-scale iterative interactive analysis is performed on the current signal sequence and the voltage signal sequence to obtain an iterative interactive current signal sequence and an iterative interactive voltage signal sequence. In this embodiment of the application, step S3 further includes:

[0048] The current signal and the voltage signal are respectively used as a node to construct an initialization detection topology network, and the detection topology network sequence is constructed by combining the current signal sequence and the voltage signal sequence;

[0049] Acquire a feature extraction scale set, use the feature extraction scales in the feature extraction scale set as receptive fields, and construct an adaptive feature extractor set;

[0050] Using the adaptive feature extractor set to extract features from the detection topology network sequence respectively to obtain a detection topology network feature set;

[0051] Performing iterative interactive analysis on the detection topology network feature set to obtain target iterative interactive detection topology network features;

[0052] A convolution operation is performed on the target iterative interactive detection topology network feature and the last detection topology network in the detection topology network sequence to obtain an iterative interactive detection topology network, and an iterative interactive current signal sequence and an iterative interactive voltage signal sequence are extracted from the iterative interactive detection topology network.

[0053] In one possible embodiment, an initialization detection topology for the secondary circuit of a power system is constructed, using current and voltage signals as nodes and their relationships (such as timing correlation and physical connection relationships) as edges. This initialization detection topology network is used to establish a synchronous relationship between current and voltage, and to perform feature extraction and optimization in subsequent analysis. The current signal sequence and voltage signal sequence are input into the initialization detection topology network in a synchronous manner to obtain the detection topology network sequence. The detection topology network sequence is used to reflect the synchronous changes of current and voltage over time.

[0054] The feature extraction scale set refers to the set of parameters used to capture features at different time scales and spatial ranges. The receptive field refers to the range of perception at each node during the feature extraction process. For example, a short time window may only capture local changes, while a large range may allow for the identification of global trends. By setting different receptive fields, we can adaptively extract features at different scales based on signal characteristics.

[0055] Preferably, the adaptive feature extractor set consists of multiple feature extractors, each corresponding to a different receptive field, adapted to signal patterns of varying scales. By combining multiple adaptive feature extractors, more comprehensive signal features can be extracted, resulting in the detection topology network feature set. The topology network detection feature set reflects the operational characteristics of current and voltage within a preset detection window, including timing characteristics (mean, standard deviation, and skewness) and frequency domain characteristics (harmonic components, energy distribution, and primary frequency). This achieves the technical effect of improving signal analysis accuracy.

[0056] Preferably, the feature extraction scale set is used as the receptive field set, and the corresponding multiple sample detection topology network sequence sets and multiple sample detection topology network feature sets are obtained as training data. The receptive field set and the corresponding multiple sample detection topology network sequence sets are used as input, and the multiple sample detection topology network feature sets are used as output. The framework set constructed based on the feedforward neural network is supervised and trained until the training converges, thereby obtaining the trained adaptive feature extractor set. By constructing the adaptive feature extractor set, the technical effect of paving the way for subsequent multi-scale feature extraction is achieved.

[0057] By performing iterative interactive analysis on the detection topology network feature set, the detection topology network features of different scales are calculated and optimized multiple times, making the feature expression more stable. For example, the current fluctuation at a certain scale may affect the stability of the entire loop. Through iterative analysis, the fluctuations at other scales can be comprehensively considered to optimize the contribution of the fluctuation to the overall error calculation. Furthermore, through convolution operation, the target iterative interactive detection topology network features are fused with the last detection topology network in the detection topology network sequence. This process can further optimize the feature expression so that the final extracted signal sequence not only contains the original data information, but also integrates the signal features, achieving the technical effect of improving the robustness of the signal.

[0058] Preferably, multiple sample iterative interaction detection topology network features and multiple sample detection topology networks, as well as corresponding multiple sample iterative interaction detection topology networks, are obtained as training data, and supervised training is performed on a framework constructed based on a convolutional neural network until the training converges, thereby obtaining a trained convolutional operation network layer. The convolutional operation network layer is used to perform convolution analysis on the target iterative interaction detection topology network features and the last detection topology network in the detection topology network sequence to obtain an iterative interaction detection topology network.

[0059] Then, iterative interactive current and voltage signal sequences are extracted from the final iterative interactive detection topology network. Compared to the original signal sequences, these signal sequences have a higher signal-to-noise ratio and more stable feature expression, which is helpful for subsequent comprehensive error analysis and detection warning.

[0060] Furthermore, iterative interaction analysis is performed on the detection topology network feature set to obtain target iterative interaction detection topology network features. In the embodiment of the present application, step S3 further includes:

[0061] randomly extracting a first detection topology network feature and a second detection topology network feature from the detection topology network feature set without replacement;

[0062] Performing iterative interactive analysis on the first detection topology network feature and the second detection topology network feature to obtain a first iterative interactive detection topology network feature;

[0063] randomly extracting a third detection topology network feature from the detection topology network feature set without replacement, performing iterative interaction analysis on the third detection topology network feature and the first iterative interaction detection topology network feature, and obtaining a second iterative interaction detection topology network feature;

[0064] By analogy, based on the N-2th iterative interactive detection topology network feature, the Nth detection topology network feature randomly extracted from the detection topology network feature set without replacement is subjected to iterative interactive analysis to obtain the target iterative interactive detection topology network feature, where N is the number of detection topology network features in the detection topology network feature set, and N is an integer greater than or equal to 1.

[0065] Furthermore, the first detection topology network feature and the second detection topology network feature are iteratively interactively analyzed to obtain a first iterative interactive detection topology network feature. In this embodiment of the application, step S3 further includes:

[0066] Perform inner product mapping on the first detection topology network feature and the second detection topology network feature to obtain a first similarity set;

[0067] Normalizing the first similarity set and adding the normalized result to the initially empty matrix to obtain a first iterative interaction matrix;

[0068] A convolution operation is performed on the first iterative interaction matrix and the second detection topology network feature to obtain a first iterative interaction detection topology network feature.

[0069] In one possible embodiment, the first detection topology network feature and the second detection topology network feature are randomly extracted from the detection topology network feature set without replacement to ensure that the features extracted in each iteration are new and avoid redundancy. Then, a first round of interactive analysis is performed, and the first detection topology network feature and the second detection topology network feature are fused to obtain the first iterative interactive detection topology network feature. The first iterative interactive detection topology network feature is the feature of the second detection topology network feature after complementary enhancement with the first detection topology network feature, thus achieving the goal of initially fusing features from different sources.

[0070] The third detection topology network feature is extracted again randomly without replacement, and based on the results of the first round of interaction, a new interaction analysis is performed with the first iterative interaction detection topology network feature. Based on the same principle as that for obtaining the first iterative interaction detection topology network feature, a more representative feature is obtained, and the second iterative interaction detection topology network feature is obtained. The iterative interaction analysis is continued until all features are used. Until the N-1th round, based on the N-2th iterative interaction detection topology network feature, the Nth detection topology network feature is introduced for the final interaction analysis to obtain the target iterative interaction detection topology network feature. Wherein, N is the number of detection topology network features in the detection topology network feature set, and N is an integer greater than or equal to 1. During the iterative process, each round of iteration can optimize the feature, making it more suitable for error detection and early warning analysis. And by random sampling without replacement, it is ensured that all features are fully utilized and will not be reused. Preferably, features of different scales and categories are fully integrated through interaction, achieving the technical effect of improving sensitivity to errors and abnormal states.

[0071] In one embodiment of the present application, the first iterative interaction detection topology network feature is finally obtained by performing inner product mapping, similarity normalization, constructing an interaction matrix and convolution operation on the first detection topology network feature and the second detection topology network feature. Preferably, the cosine similarity calculation formula is used to perform corresponding feature similarity calculations on the first detection topology network feature and the second detection topology network feature to obtain the first similarity set. The first similarity set is used to describe the degree of similarity between the first detection topology network feature and the second detection topology network feature. Furthermore, the softmax normalization formula is used to normalize the first similarity set to ensure that the similarity range is within . The normalized result is added to the initially empty matrix to obtain the first iterative interaction matrix. The first iterative interaction matrix reflects the interaction weight between the first detection topology network feature and the second detection topology network feature.

[0072] Then, using graph convolution operation, the first iterative interaction matrix is used as the adjacency weight and convolved with the second detection topology network feature. Preferably, the convolution calculation formula is: ,in, For the first iteration, interactive detection of topological network features is performed. is the activation function (such as ReLU), is the first iteration interaction matrix, is the second detection topology network feature, The weight matrix is pre-constructed by a person skilled in the art. The first iterative interactive detection topology network feature is obtained by performing a convolution operation. The technical effect of further optimizing the detection topology network feature and making it have a stronger feature expression capability is achieved.

[0073] Furthermore, to obtain a feature extraction scale set, step S3 of the embodiment of the present application further includes:

[0074] Obtaining a set of detection anomaly logs of the secondary circuit within a historical window;

[0075] Using the anomaly type as an index, perform the same type aggregation on the detection anomaly log set to obtain L clustered detection anomaly log sets, where L is an integer greater than or equal to 1;

[0076] Performing dual-dimensional centralized identification of anomaly time scales on the L cluster detection anomaly log sets to obtain L centralized identification anomaly time scale sets, wherein the dual-dimensional centralized identification of anomaly time scales is to perform balanced identification from two dimensions: the similarity of time nodes of the cluster detection anomaly logs and the similarity of anomaly time sizes of the cluster detection anomaly logs;

[0077] The L concentrated anomaly identification time scale sets are unioned to obtain a feature extraction scale set.

[0078] Furthermore, performing two-dimensional centralized identification of abnormal time scales on the L cluster detection abnormal log sets to obtain L centralized identification abnormal time scale sets, step S3 of the embodiment of the present application further includes:

[0079] Randomly select a preset number of cluster detection anomaly logs from the L cluster detection anomaly log sets as L centralized identification center sets;

[0080] According to a preset recognition threshold, the neighborhoods of the centralized recognition centers in the L centralized recognition center sets are respectively constructed to obtain L centralized recognition center neighborhood sets;

[0081] Performing loss analysis on the L centralized identification center neighborhood sets using a two-dimensional centralized identification loss function to obtain L two-dimensional centralized identification loss amounts;

[0082] When the L two-dimensional centralized identification loss amounts are less than or equal to a preset loss amount threshold, the neighborhood means of the L centralized identification center neighborhood sets are calculated respectively to obtain L centralized identification abnormal time scale sets.

[0083] Furthermore, the loss function for two-dimensional centralized recognition is:

[0084] ;

[0085] in, To identify the loss amount in two dimensions, is the number of centralized identification centers in a centralized identification center set, For a centralized identification center set The neighborhood of the centralized identification center of the centralized identification center, For the The first Cluster detection of abnormal log time nodes, For the The time node of the cluster detection anomaly log corresponding to the centralized identification center, For the The abnormal time size of the cluster detection abnormal log corresponding to the centralized identification center, For the The first The abnormal time size of the abnormal log detected by clustering, The weight is used to balance the similarity between time nodes and the similarity between abnormal time sizes.

[0086] In one possible embodiment, during the operation of the secondary circuit of a smart substation, the system records various abnormalities (such as current anomalies, voltage anomalies, and errors exceeding the specified limit). A historical time window is set (e.g., the last month or year), and a set of detected anomaly logs within that time window is extracted to obtain the detected anomaly log set. The logs are clustered using the anomaly type (e.g., abnormal current fluctuations, voltage imbalance, and combined errors exceeding the specified limit) as an index to obtain a set of logs corresponding to each anomaly type, i.e., the L clustered detected anomaly log sets. L represents the type of anomaly that occurred in the secondary circuit within the historical window.

[0087] Furthermore, the L sets of clustered anomaly logs are subjected to dual-dimensional centralized identification of anomaly time scales. Specifically, this involves balanced identification based on the similarity of the time nodes within the clustered anomaly logs and the similarity of the anomaly time magnitudes within the clustered anomaly logs. This yields the L sets of centralized anomaly time scales, capturing the time scales at which anomalies occur and providing data support for subsequent analysis. The L sets of centralized anomaly time scales are then unioned to avoid duplication of scales and waste of computing power, thereby yielding the feature extraction scale set.

[0088] A preset number of cluster detection anomaly logs are randomly selected from the L cluster detection anomaly log sets as L centralized identification center sets. The preset number is set by those skilled in the art. Each centralized identification center is used as a representative sample initially selected from the cluster logs to construct a benchmark for anomaly identification and improve the accuracy of clustering. The preset identification threshold is a similarity range with the centralized identification center when constructing the centralized identification center neighborhood, which is pre-set by those skilled in the art. When the similarity between the cluster detection anomaly logs in the L cluster detection anomaly log sets and the centralized identification centers of the corresponding L centralized identification center sets respectively meets the preset identification threshold, they are added to the corresponding centralized identification center neighborhood, thereby obtaining the L centralized identification center neighborhood sets.

[0089] A loss analysis is performed on the L centralized identification center neighborhood sets using a two-dimensional centralized identification loss function to obtain L two-dimensional centralized identification loss amounts. The two-dimensional centralized identification loss function is used to analyze the degree of identification partition loss for the centralized identification center neighborhood sets. When the L two-dimensional centralized identification loss amounts are less than or equal to a preset loss threshold, the neighborhood means of the L centralized identification center neighborhood sets are calculated to obtain L centralized identification anomaly time scale sets.

[0090] By clustering anomaly types, we can improve the pertinence of time scale division and reduce false alarms. By using dual-dimensional centralized identification, we can ensure that the feature extraction scale adapts to the characteristics of different types of anomalies and improve the robustness of the model. Then, by combining the similarity of time nodes and the similarity of anomaly time size, we can improve the rationality of scale division and make detection more accurate.

[0091] In summary, the embodiments of the present application have at least the following technical effects:

[0092] The present application utilizes the current test line of a portable calibrator to provide a current signal for the current terminal box merging unit of any secondary circuit in the power system, and provides a voltage signal for the voltage terminal box merging unit of the secondary circuit through a voltage pay-out vehicle, and then performs simultaneous data acquisition on the current terminal box merging unit and the voltage terminal box merging unit within a preset detection window, and utilizes a wireless radio frequency synchronization module to receive the electric energy pulse signal of a digital electric energy meter, to obtain a current signal sequence, a voltage signal sequence, and an electric energy pulse signal, and then performs multi-scale iterative interactive analysis on the current signal sequence and the voltage signal sequence to obtain an iterative interactive current signal sequence and an iterative interactive voltage signal sequence, and performs a secondary circuit comprehensive error analysis based on the iterative interactive current signal sequence and the iterative interactive voltage signal sequence to obtain a target secondary circuit comprehensive error, and then generates a first warning message when the target secondary circuit comprehensive error is greater than a preset error threshold. The technical effect of improving the reliability of secondary circuit detection and warning is achieved.

[0093] Embodiment 2 is based on the same inventive concept as the power system metering secondary circuit detection and early warning method in the above embodiment. Figure 3 As shown, the present application provides a power system metering secondary circuit detection and early warning device, and the device and method embodiments in the present application are based on the same inventive concept. Among them, the device includes:

[0094] The current signal providing module 11 is used to provide a current signal to the current terminal box merging unit of any secondary circuit in the power system using the current test line of the portable calibrator, and to provide a voltage signal to the voltage terminal box merging unit of the secondary circuit through the voltage pay-out vehicle;

[0095] The signal sequence acquisition module 12 is used to collect data from the current terminal box merging unit and the voltage terminal box merging unit simultaneously within a preset detection window, and to receive the electric energy pulse signal from the digital electric energy meter using a wireless radio frequency synchronization module to obtain a current signal sequence, a voltage signal sequence, and an electric energy pulse signal;

[0096] An iterative interaction analysis module 13 is configured to perform multi-scale iterative interaction analysis on the current signal sequence and the voltage signal sequence to obtain an iterative interaction current signal sequence and an iterative interaction voltage signal sequence;

[0097] A comprehensive error obtaining module 14 is configured to perform a comprehensive error analysis on the secondary circuit based on the iterative interactive current signal sequence, the iterative interactive voltage signal sequence, and the electric energy pulse signal to obtain a target comprehensive error of the secondary circuit;

[0098] The first warning information generating module 15 is configured to generate a first warning information when the target secondary circuit comprehensive error is greater than a preset error threshold.

[0099] Furthermore, the iterative interaction analysis module 13 is configured to perform the following steps:

[0100] The current signal and the voltage signal are respectively used as a node to construct an initialization detection topology network, and the detection topology network sequence is constructed by combining the current signal sequence and the voltage signal sequence;

[0101] Acquire a feature extraction scale set, use the feature extraction scales in the feature extraction scale set as receptive fields, and construct an adaptive feature extractor set;

[0102] Using the adaptive feature extractor set to extract features from the detection topology network sequence respectively to obtain a detection topology network feature set;

[0103] Performing iterative interactive analysis on the detection topology network feature set to obtain target iterative interactive detection topology network features;

[0104] A convolution operation is performed on the target iterative interactive detection topology network feature and the last detection topology network in the detection topology network sequence to obtain an iterative interactive detection topology network, and an iterative interactive current signal sequence and an iterative interactive voltage signal sequence are extracted from the iterative interactive detection topology network.

[0105] Furthermore, the iterative interaction analysis module 13 is configured to perform the following steps:

[0106] randomly extracting a first detection topology network feature and a second detection topology network feature from the detection topology network feature set without replacement;

[0107] Performing iterative interactive analysis on the first detection topology network feature and the second detection topology network feature to obtain a first iterative interactive detection topology network feature;

[0108] randomly extracting a third detection topology network feature from the detection topology network feature set without replacement, performing iterative interaction analysis on the third detection topology network feature and the first iterative interaction detection topology network feature, and obtaining a second iterative interaction detection topology network feature;

[0109] By analogy, based on the N-2th iterative interactive detection topology network feature, the Nth detection topology network feature randomly extracted from the detection topology network feature set without replacement is subjected to iterative interactive analysis to obtain the target iterative interactive detection topology network feature, where N is the number of detection topology network features in the detection topology network feature set, and N is an integer greater than or equal to 1.

[0110] Furthermore, the iterative interaction analysis module 13 is configured to perform the following steps:

[0111] Perform inner product mapping on the first detection topology network feature and the second detection topology network feature to obtain a first similarity set;

[0112] Normalizing the first similarity set and adding the normalized result to the initially empty matrix to obtain a first iterative interaction matrix;

[0113] A convolution operation is performed on the first iterative interaction matrix and the second detection topology network feature to obtain a first iterative interaction detection topology network feature.

[0114] Furthermore, the iterative interaction analysis module 13 is configured to perform the following steps:

[0115] Obtaining a set of detection anomaly logs of the secondary circuit within a historical window;

[0116] Using the anomaly type as an index, perform the same type aggregation on the detection anomaly log set to obtain L clustered detection anomaly log sets, where L is an integer greater than or equal to 1;

[0117] Performing dual-dimensional centralized identification of anomaly time scales on the L cluster detection anomaly log sets to obtain L centralized identification anomaly time scale sets, wherein the dual-dimensional centralized identification of anomaly time scales is to perform balanced identification from two dimensions: the similarity of time nodes of the cluster detection anomaly logs and the similarity of anomaly time sizes of the cluster detection anomaly logs;

[0118] The L concentrated anomaly identification time scale sets are unioned to obtain a feature extraction scale set.

[0119] Furthermore, the iterative interaction analysis module 13 is configured to perform the following steps:

[0120] Randomly select a preset number of cluster detection anomaly logs from the L cluster detection anomaly log sets as L centralized identification center sets;

[0121] According to a preset recognition threshold, the neighborhoods of the centralized recognition centers in the L centralized recognition center sets are respectively constructed to obtain L centralized recognition center neighborhood sets;

[0122] Performing loss analysis on the L centralized identification center neighborhood sets using a two-dimensional centralized identification loss function to obtain L two-dimensional centralized identification loss amounts;

[0123] When the L two-dimensional centralized identification loss amounts are less than or equal to a preset loss amount threshold, the neighborhood means of the L centralized identification center neighborhood sets are calculated respectively to obtain L centralized identification abnormal time scale sets.

[0124] Furthermore, the loss function for two-dimensional centralized recognition is:

[0125] ;

[0126] in, To identify the loss amount in two dimensions, is the number of centralized identification centers in a centralized identification center set, For a centralized identification center set The neighborhood of the centralized identification center of the centralized identification center, For the The first Cluster detection of abnormal log time nodes, For the The time node of the cluster detection anomaly log corresponding to the centralized identification center, For the The abnormal time size of the cluster detection abnormal log corresponding to the centralized identification center, For the The first The abnormal time size of the abnormal log detected by clustering, The weight is used to balance the similarity between time nodes and the similarity between abnormal time sizes.

[0127] It should be noted that the order in which the embodiments of the present application are presented is for illustrative purposes only and does not necessarily represent the superiority or inferiority of the embodiments. Furthermore, the foregoing descriptions of specific embodiments of this specification are provided. Furthermore, the processes depicted in the accompanying drawings do not necessarily require the specific order or sequential sequence shown to achieve the desired results. In certain embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0128] The above description is only a preferred embodiment of the present application and is not intended to limit the present application. Any modifications, equivalent replacements, improvements, etc. made within the spirit and principles of the present application should be included in the scope of protection of the present application.

[0129] This specification and drawings are merely illustrative of the present application and are intended to cover any and all modifications, variations, combinations, or equivalents within the scope of this application. Obviously, those skilled in the art may make various modifications and variations to this application without departing from the scope of this application. Thus, this application is intended to include such modifications and variations as fall within the scope of this application and its equivalents.

Claims

1. A power system metering secondary circuit detection and early warning method, characterized in that: Methods include: Use the current test line of the portable calibrator to provide current signals for the current terminal box merging unit of any secondary circuit in the power system, and use the voltage pay-out vehicle to provide voltage signals for the voltage terminal box merging unit of the secondary circuit; Performing simultaneous data acquisition on the current terminal box merging unit and the voltage terminal box merging unit within a preset detection window, and using a wireless radio frequency synchronization module to receive the electric energy pulse signal of the digital electric energy meter to obtain a current signal sequence, a voltage signal sequence, and an electric energy pulse signal; Performing multi-scale iterative interaction analysis on the current signal sequence and the voltage signal sequence to obtain an iterative interactive current signal sequence and an iterative interactive voltage signal sequence; Perform secondary circuit comprehensive error analysis based on iterative interactive current signal sequence, iterative interactive voltage signal sequence and electric energy pulse signal to obtain target secondary circuit comprehensive error; When the target secondary circuit comprehensive error is greater than a preset error threshold, a first warning message is generated; Perform multi-scale iterative interaction analysis on the current signal sequence and the voltage signal sequence to obtain an iterative interactive current signal sequence and an iterative interactive voltage signal sequence, including: The current signal and the voltage signal are respectively used as a node to construct an initialization detection topology network, and the detection topology network sequence is constructed by combining the current signal sequence and the voltage signal sequence; Acquire a feature extraction scale set, use the feature extraction scales in the feature extraction scale set as receptive fields, and construct an adaptive feature extractor set; Using the adaptive feature extractor set to extract features from the detection topology network sequence respectively to obtain a detection topology network feature set; Performing iterative interactive analysis on the detection topology network feature set to obtain target iterative interactive detection topology network features; Performing a convolution operation on the target iterative interactive detection topology network feature and the last detection topology network in the detection topology network sequence to obtain an iterative interactive detection topology network, and extracting an iterative interactive current signal sequence and an iterative interactive voltage signal sequence from the iterative interactive detection topology network; Performing iterative interactive analysis on the detection topology network feature set to obtain target iterative interactive detection topology network features, including: randomly extracting a first detection topology network feature and a second detection topology network feature from the detection topology network feature set without replacement; Performing iterative interactive analysis on the first detection topology network feature and the second detection topology network feature to obtain a first iterative interactive detection topology network feature; randomly extracting a third detection topology network feature from the detection topology network feature set without replacement, performing iterative interaction analysis on the third detection topology network feature and the first iterative interaction detection topology network feature, and obtaining a second iterative interaction detection topology network feature; Similarly, based on the N-2th iterative interactive detection topology network feature, an iterative interactive analysis is performed on the Nth detection topology network feature randomly extracted from the detection topology network feature set without replacement to obtain a target iterative interactive detection topology network feature, where N is the number of detection topology network features in the detection topology network feature set and N is an integer greater than or equal to 1; Get the feature extraction scale set, including: Obtaining a set of detection anomaly logs of the secondary circuit within a historical window; Using the anomaly type as an index, perform the same type aggregation on the detection anomaly log set to obtain L clustered detection anomaly log sets, where L is an integer greater than or equal to 1; Performing dual-dimensional centralized identification of anomaly time scales on the L cluster detection anomaly log sets to obtain L centralized identification anomaly time scale sets, wherein the dual-dimensional centralized identification of anomaly time scales is to perform balanced identification from two dimensions: the similarity of time nodes of the cluster detection anomaly logs and the similarity of anomaly time sizes of the cluster detection anomaly logs; The L concentrated anomaly identification time scale sets are unioned to obtain a feature extraction scale set.

2. The power system metering secondary circuit detection and early warning method according to claim 1, characterized in that: Performing iterative interactive analysis on the first detection topology network feature and the second detection topology network feature to obtain a first iterative interactive detection topology network feature includes: Perform inner product mapping on the first detection topology network feature and the second detection topology network feature to obtain a first similarity set; Normalizing the first similarity set and adding the normalized result to the initially empty matrix to obtain a first iterative interaction matrix; A convolution operation is performed on the first iterative interaction matrix and the second detection topology network feature to obtain a first iterative interaction detection topology network feature.

3. The power system metering secondary circuit detection and early warning method according to claim 1, characterized in that: Performing dual-dimensional centralized identification of abnormal time scales on the L cluster detection abnormal log sets to obtain L centralized identification abnormal time scale sets, including: Randomly select a preset number of cluster detection anomaly logs from the L cluster detection anomaly log sets as L centralized identification center sets; According to a preset recognition threshold, the neighborhoods of the centralized recognition centers in the L centralized recognition center sets are respectively constructed to obtain L centralized recognition center neighborhood sets; Performing loss analysis on the L centralized identification center neighborhood sets using a two-dimensional centralized identification loss function to obtain L two-dimensional centralized identification loss amounts; When the L two-dimensional centralized identification loss amounts are less than or equal to a preset loss amount threshold, the neighborhood means of the L centralized identification center neighborhood sets are calculated respectively to obtain L centralized identification abnormal time scale sets.

4. The power system metering secondary circuit detection and early warning method according to claim 3, characterized in that: The two-dimensional centralized recognition loss function is: ； in, To identify the loss amount in two dimensions, is the number of centralized identification centers in a centralized identification center set, For a centralized identification center set The neighborhood of the centralized identification center of the centralized identification center, For the The first Cluster detection of abnormal log time nodes, For the The time node of the cluster detection anomaly log corresponding to the centralized identification center, For the The abnormal time size of the cluster detection abnormal log corresponding to the centralized identification center, For the The first The abnormal time size of the abnormal log detected by clustering, The weight is used to balance the similarity between time nodes and the similarity between abnormal time sizes.

5. The power system metering secondary circuit detection and early warning device is characterized by: The device for implementing the power system metering secondary circuit detection and early warning method according to any one of claims 1 to 4 comprises: The current signal providing module is used to provide a current signal to the current terminal box merging unit of any secondary circuit in the power system using the current test line of the portable calibrator, and to provide a voltage signal to the voltage terminal box merging unit of the secondary circuit through the voltage pay-out vehicle; A signal sequence acquisition module is used to simultaneously collect data from the current terminal box merging unit and the voltage terminal box merging unit within a preset detection window, and to receive the electric energy pulse signal from the digital electric energy meter using a wireless radio frequency synchronization module to obtain a current signal sequence, a voltage signal sequence, and an electric energy pulse signal; An iterative interaction analysis module is used to perform multi-scale iterative interaction analysis on the current signal sequence and the voltage signal sequence to obtain an iterative interaction current signal sequence and an iterative interaction voltage signal sequence; A comprehensive error acquisition module is used to perform a comprehensive error analysis of the secondary circuit based on the iterative interactive current signal sequence, the iterative interactive voltage signal sequence and the electric energy pulse signal to obtain a target comprehensive error of the secondary circuit; The first warning information generating module is used to generate a first warning information when the target secondary loop comprehensive error is greater than a preset error threshold.

Images