Continuous metering remote monitoring method for live-line replacement of meter

Abstract

The invention discloses a remote monitoring method for continuous metering of an electrified replacement meter, which relates to the technical field of remote monitoring of continuous metering and comprises the following steps of: receiving original data on a new meter based on a remote monitoring system, analyzing a data structure of the original data and constructing a data format conversion model; applying the data format conversion model to the real-time metering data of the old meter to obtain a standardized data packet; synchronizing the standardized data packet to a new meter and performing data verification to complete the inheritance of the historical data of the meter; and analyzing sensor observation data of the new meter based on a Kalman filtering algorithm to complete meter state estimation and anomaly detection. The technical problems of data migration distortion, incapability of sensing state change, continuous metering interruption and the like in a meter replacement process are solved.

Description

Technical Field

[0001] The present invention relates to the technical field of remote monitoring of continuous metering, and more particularly to a remote monitoring method for continuous metering by live replacement of a meter. Background Art

[0002] Live meter replacement ensures the normal operation of electricity metering equipment without disrupting power supply. During this process, the system can replace the meter without disconnecting the power supply through wireless communication, data synchronization, and other technologies. However, the following potential failures and threats may still occur during this process: Data transfer errors: When an electricity meter is replaced, the data from the old meter must be accurately transferred to the new meter. Errors, network instability, device failure, or incompatibility during data transfer can result in incomplete or erroneous data transfer, impacting subsequent electricity bill settlement and customer service.

[0003] Insufficient equipment status monitoring: During the process of replacing meters under power, if problems such as improper meter installation or abnormal meter connection occur, the existing monitoring system may not be able to detect them in time, thereby delaying fault handling and may even cause electrical fires or other serious safety hazards.

[0004] In view of the above problems, the present invention proposes a solution. Summary of the Invention

[0005] In order to overcome the above-mentioned defects of the prior art, an embodiment of the present invention provides a remote monitoring method for continuous metering during live meter replacement. By constructing a data format conversion model that adapts to the protocols of old and new meters, realizing standardized inheritance of historical data, and introducing a state estimation and anomaly detection mechanism based on Kalman filtering, technical problems such as data migration distortion, inability to perceive state changes, and interruption of continuous metering during meter replacement can be solved.

[0006] To achieve the above object, the present invention provides the following technical solutions: A remote monitoring method for continuous metering during live meter replacement includes the following steps: receiving raw data from a new meter based on a remote monitoring system, parsing its data structure and constructing a data format conversion model; applying the data format conversion model to the real-time metering data of the old meter to obtain a standardized data packet; synchronizing the standardized data packet to the new meter and performing data verification to complete the inheritance of the meter's historical data; and analyzing the sensor observation data of the new meter based on a Kalman filter algorithm to complete meter state estimation and anomaly detection.

[0007] In a preferred embodiment, the remote monitoring system receives the original data on the new meter, parses its data structure and constructs a data format conversion model, specifically: the new meter sends the original data packet to the remote monitoring system through the built-in communication module; the remote monitoring system parses the communication protocol structure of the original data packet, and generates a protocol dictionary containing field definitions, encoding rules and verification mechanisms; based on the protocol dictionary, a data format conversion model is constructed, and the model includes a mapping function from the old meter data field to the new meter field.

[0008] In a preferred embodiment, the new meter sends an original data packet to the remote monitoring system through a built-in communication module. Specifically, when the new meter is connected to the remote monitoring system for the first time, it reports the device identification information, protocol type, data frame structure, service field definition and test data sample to the remote monitoring system through its built-in communication module (supporting communication methods such as GPRS, NB-IoT or PLC) to form an original data packet.

[0009] In a preferred embodiment, the remote monitoring system parses the data packet to obtain a protocol dictionary, and constructs a data format conversion model based on the protocol dictionary. The specific steps are as follows: parsing each business field of the new meter based on the protocol dictionary, and establishing a one-to-one corresponding field mapping relationship with the unified standard format adopted by the remote monitoring system (IEC 62056 protocol or internal enterprise standard); detecting the data unit system and precision parameters of each business field of the new meter, recording them in the mapping rules for subsequent unified processing of the old meter data; parsing the timestamp format of the new meter, and generating a unified timestamp conversion rule so that the time axis of the old meter data and the new meter data can be directly aligned; identifying the communication frame check method adopted by the new meter, and incorporating the check method into the model to ensure that the old meter data meets the same integrity check logic after conversion; integrating the above-mentioned field mapping relationship, unit and precision parameters, timestamp conversion rules and check logic to construct a data format conversion model, and storing it in the remote monitoring system for subsequent direct call for old meter data format conversion.

[0010] In a preferred embodiment, the data format conversion model is applied to the real-time metering data of the old meter to obtain a standardized data packet, specifically: the operating parameters of the old meter are collected through the meter's built-in communication module to obtain an original data set; the original data set is input into the data format conversion model to generate a standardized data packet containing the main data.

[0011] In a preferred embodiment, the operating parameters of the old meter are collected through the built-in communication module of the meter to obtain the original data set. Specifically, the old meter uses its built-in communication module to collect parameters such as voltage, current, active power, reactive power, instantaneous load, accumulated electric energy and collection timestamp in real time to form the original data set.

[0012] In a preferred embodiment, the original data set is input into the data format conversion model to generate a standardized data packet containing the main data. The specific steps are as follows: according to the field mapping relationship of the data format conversion model, the data fields of the old meter are mapped one-to-one to the unified standard format fields; based on the unit and precision parameters of the data format conversion model, the unit and precision of the old meter data are standardized to ensure the consistency of the data between the old and new meters; according to the timestamp conversion rules preset in the data format conversion model, the timestamp encoding format of the old meter is converted into a unified standard timestamp; the source device information, acquisition frequency, protocol version and data conversion rule identifier are written into the standardized data packet to automatically verify the data compatibility when the new meter inherits it later; a cyclic redundancy check (CRC) polynomial operation is performed on the main data of the standardized data packet to generate a number of bit check codes for subsequent data integrity verification; the check code is appended to the end of the standardized data packet to form a final transmission data packet; the final transmission data packet is sent to the remote monitoring system via the communication network as the data packet inherited by the new meter later.

[0013] In a preferred embodiment, the standardized data packet is synchronized to the new meter and data verification is performed to complete the inheritance of the meter's historical data, including the following steps: detecting the access status of the new meter and receiving the final transmission data packet from the old meter or data transfer device; extracting the cyclic redundancy check code from the tail of the final transmission data packet; recalculating the cyclic redundancy check value for the main data of the final transmission data packet; comparing the recalculated verification value with the extracted verification code: if the verification value matches, parsing the main data and performing data synchronization with the new meter; if the verification value does not match, generating an abnormal information packet containing an error identifier, and uploading the abnormal information packet to the system background.

[0014] In a preferred embodiment, in this embodiment, the sensor observation data of the new meter is analyzed based on the Kalman filter algorithm to complete the meter state estimation and anomaly detection, including the following steps: constructing an observation data vector based on the sensor observation data of the new meter, and initializing the input parameters of the Kalman filter algorithm, including the initial state estimation vector, the initial covariance matrix, the state transfer matrix and the observation noise covariance matrix; executing the iterative process of the Kalman filter algorithm, based on the current state estimation vector and the covariance matrix, calculating the optimal smoothed state estimation value vector at the current moment through the state update equation; calculating the residual between the observation data vector and the optimal smoothed state estimation vector, and judging whether the amplitude of the residual exceeds the preset anomaly threshold: if so, it is determined that there is an anomaly in the current operating state of the meter; if not, returning to the previous step.

[0015] In a preferred embodiment, the state transfer matrix is ​​generated by a historical load training model, including online modeling of the state transfer relationship based on the historical load curve and real-time power fluctuation characteristics of the new meter, and iterative adjustment of the parameters of the state transfer matrix.

[0016] In a preferred embodiment, the abnormality threshold is determined based on the confidence level set by the system, combined with the Mahalanobis distance of the residual and the current covariance matrix, and calculated according to the critical value of the chi-square distribution to determine whether the current state is within the statistical abnormality range.

[0017] A remote monitoring device for continuous metering during live meter replacement comprises: a conversion model construction module for receiving raw data from a new meter based on a remote monitoring system, parsing its data structure, and constructing a data format conversion model; a format conversion module for applying the data format conversion model to the real-time metering data of the old meter to obtain a standardized data packet; a data integration module for synchronizing the standardized data packet to the new meter and performing data verification to complete the inheritance of the meter's historical data; and an anomaly detection module for analyzing the sensor observation data of the new meter based on a Kalman filter algorithm to complete meter state estimation and anomaly detection.

[0018] A remote monitoring device for continuous metering of live meter replacement comprises a memory and a processor: the memory is used to store a program; the processor is used to execute the program to implement each step of the remote monitoring method for continuous metering of live meter replacement.

[0019] A readable storage medium stores a computer program, which, when executed by a processor, implements various steps of a remote monitoring method for continuous metering during hot-swap meter replacement.

[0020] The technical effects and advantages of the remote monitoring method for continuous metering by live meter replacement of the present invention are as follows: 1. By constructing a data format conversion model between old and new meters, the present invention achieves unified and standardized mapping under different communication protocols, electricity measurement units, and timestamp formats. This allows the historical data of the old meter to be smoothly inherited to the new meter without interruption of power supply, ensuring the continuity and consistency of metering data during the replacement process, and avoiding the errors and workload caused by manual meter reading or data migration.

[0021] 2. The present invention introduces a dynamic state estimation method based on Kalman filtering, combines the real-time observation data of the new meter with the historical operating load, and establishes a system state adaptive prediction mechanism, which can effectively identify metering anomalies and system drift. By iteratively optimizing the state transfer matrix parameters, it improves the stability of state estimation and the sensitivity of anomaly detection, thereby enhancing the intelligent diagnostic capability of the remote monitoring system in complex power grid environments. BRIEF DESCRIPTION OF THE DRAWINGS

[0022] Figure 1 A flowchart of a remote monitoring method for continuous metering with live meter replacement provided by an embodiment of the present invention; Figure 2 A schematic diagram of a residual mean convergence curve during state transfer matrix parameter optimization provided by an embodiment of the present invention; Figure 3 A schematic structural diagram of a remote monitoring device for live meter replacement and continuous measurement provided by an embodiment of the present invention.

[0023] Figure 4 The present invention provides a structural block diagram of an exemplary electronic device that can be used to implement the embodiments of the present disclosure.

[0024] Figure 5 A schematic diagram of an exemplary storage medium provided in an embodiment of the present invention that can be used to implement an embodiment of the present disclosure. DETAILED DESCRIPTION

[0025] The following will provide a clear and complete description of the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. All other embodiments obtained by ordinary technicians in this field based on the embodiments of the present invention without making any creative efforts shall fall within the scope of protection of the present invention.

[0026] Example 1, Figure 1 The present invention provides a remote monitoring method for continuous metering of live meter replacement, comprising the following steps: S1, based on the remote monitoring system, receives the raw data from the new meter, parses its data structure and builds a data format conversion model; S2, applies the data format conversion model to the real-time metering data of the old meters to obtain a standardized data package; S3: Synchronize the standardized data package to the new meter and perform data verification to complete the inheritance of the meter's historical data; S4, based on the Kalman filter algorithm, analyzes the sensor observation data of the new meter to complete meter state estimation and anomaly detection.

[0027] This embodiment realizes the standardized mapping and inheritance of historical data by constructing a data format conversion model between the old and new meters, ensuring the continuity and structural compatibility of metering data during the replacement of new meters. At the same time, the introduction of a dynamic state estimation and residual monitoring mechanism based on Kalman filtering not only improves the operational reliability of new meters in the initial access period, but also has the ability to adaptively model operational state drift. The state transfer matrix parameters are initialized by fitting the historical load sequence and can be iteratively optimized under the residual drive, thereby improving the accuracy and robustness of state estimation. Overall, the present invention provides a remote monitoring method that supports live replacement, continuous metering, anomaly perception, and parameter adaptability, which is suitable for ensuring operational stability in large-scale smart meter access scenarios.

[0028] S1, based on the remote monitoring system, receives the raw data from the new meter, parses its data structure and builds a data format conversion model, specifically: S11, the new meter sends the original data packet to the remote monitoring system through the built-in communication module; S12, the remote detection system parses the communication protocol structure of the original data packet and generates a protocol dictionary including field definitions, encoding rules and verification mechanisms; S13, constructing a data format conversion model based on the protocol dictionary, wherein the model includes a mapping function from old meter data fields to new meter fields.

[0029] In this embodiment, the new meter sends an original data packet to the remote monitoring system via the built-in communication module, specifically: When a new meter is first connected to the remote monitoring system, it reports device identification information, protocol type, data frame structure, service field definition, and test data samples to the remote monitoring system through its built-in communication module (supporting communication methods such as GPRS, NB-IoT, or PLC) to form an original data packet.

[0030] The remote detection system parses the communication protocol structure of the original data packet and generates a protocol dictionary containing field definitions, encoding rules and verification mechanisms, specifically: After receiving the original data packet, the remote monitoring system parses it through a protocol parsing engine, extracting and identifying various elements of the communication protocol, including field order, field length, data type, encoding method, timestamp format, unit system, precision parameters, and verification rules. These elements are then systematically organized to create a protocol dictionary. This protocol dictionary serves as a basic reference document for subsequent data format conversion.

[0031] The data format conversion model is constructed based on the protocol dictionary, and the specific steps are as follows: S131, parses each service field of the new meter based on the protocol dictionary and establishes a one-to-one mapping relationship between the fields and the unified standard format (IEC 62056 protocol or internal enterprise standard) used by the remote monitoring system, forming the basic framework of the mapping function; S132, detecting the data unit system and precision parameters of each business field of the new meter, recording them in the mapping rules, and constructing a numerical conversion function for subsequent unified processing of the old meter data; S133, parsing the timestamp format of the new meter and generating a unified timestamp conversion function to ensure that the time axes of the old meter data and the new meter data can be directly aligned; S134, identifying the communication frame check method used by the new meter, constructing a check conversion function, and incorporating the check method into the model to ensure that the old meter data meets the same integrity check logic after conversion; S135, integrate the above-mentioned field mapping relationship, value conversion function, timestamp conversion function and verification conversion function to form a complete mapping function system, build a data format conversion model, and store it in the remote monitoring system for direct call of subsequent old meter data format conversion.

[0032] The mapping function specifically includes: Field mapping function: realizes the conversion of the old meter field name and position to the corresponding field of the new meter; Numeric conversion function: realize the conversion of numerical values ​​between different unit systems and precision parameters; Timestamp conversion function: realize the conversion between different timestamp formats; Verification conversion function: realizes conversion and verification between different verification algorithms.

[0033] In summary, through this embodiment, the remote monitoring system obtains a data format conversion model to ensure that the historical data of the old meter and the real-time data of the new meter can be connected under a unified data structure and accuracy standard, providing a basis for subsequent continuous measurement and anomaly detection.

[0034] S2, applies the data format conversion model to the real-time metering data of the old meter to obtain a standardized data package, specifically: S21, collecting the operating parameters of the old meter through the built-in communication module of the meter to obtain the original data set; S22, input the original data set into the data format conversion model to generate a standardized data package containing the subject data.

[0035] In this embodiment, the operating parameters of the old meter are collected through the communication module built into the meter to obtain the original data set, specifically: The old meter uses its built-in communication module to collect parameters such as voltage, current, active power, reactive power, instantaneous load, accumulated electric energy and collection timestamp in real time to form the original data set.

[0036] The original data set is input into the data format conversion model to generate a standardized data package containing the main data. The specific steps are as follows: S221, mapping the data fields of the old meter to the unified standard format fields one by one according to the field mapping relationship of the data format conversion model; S222, based on the unit and precision parameters of the data format conversion model, standardize the unit and precision of the old meter data to ensure consistency between the new and old meters; S223, converting the timestamp encoding format of the old meter into a unified standard timestamp according to the timestamp conversion rules preset in the data format conversion model; S224, writing source device information, acquisition frequency, protocol version, and data conversion rule identifier into the standardized data packet so that data compatibility can be automatically verified when a new meter is subsequently inherited; S225, performing a cyclic redundancy check (CRC) polynomial operation on the main data of the standardized data packet to generate a multi-bit check code for subsequent data integrity verification; appending the check code to the end of the standardized data packet to form a final transmission data packet; the final transmission data packet is sent to the remote monitoring system via the communication network as a data packet inherited by subsequent new meters.

[0037] S3 synchronizes the standardized data package to the new meter and performs data verification to complete the meter historical data inheritance, including the following steps: S31, detecting the access status of the new meter and receiving the final transmission data packet from the old meter or the data transfer device; S32, extracting a cyclic redundancy check code from the tail of the final transmission data packet; S33, recalculating a cyclic redundancy check value for the main body data of the final transmission data packet; S34, compare the recalculated check value with the extracted check code: if the check values ​​match, parse the main data and synchronize data with the new meter; if the check values ​​do not match, generate an abnormal information packet containing an error identifier, and upload the abnormal information packet to the system background.

[0038] Specifically: After a new meter is online, its communication module establishes a connection with the remote monitoring system through networking. The remote monitoring system confirms the successful connection of the new meter through polling and obtains its device identification code as the basis for subsequent data matching; The remote monitoring system extracts the CRC checksum at the end of the standardized data packet associated with the new meter in a fixed format. The CRC checksum has been calculated based on the main data in step S2 and is located several bytes after the end of the data packet. The remote monitoring system recalculates the CRC polynomial on the main portion of the standardized data packet (using the same polynomial and initial values ​​as used when constructing the model), generates a new checksum, and compares it byte by byte with the original checksum extracted in step S32. If the checksums match, data synchronization is performed; if not, an exception message including an error code is uploaded to the system backend.

[0039] This embodiment ensures that the synchronization process of historical data between old and new meters has a strict data integrity verification mechanism, avoids erroneous inheritance caused by transmission damage or equipment anomalies, and provides a reliable data basis for subsequent continuous measurement and anomaly detection.

[0040] S4, based on the Kalman filter algorithm, analyzes the sensor observation data of the new meter to complete meter state estimation and anomaly detection.

[0041] It should be noted that in order to distinguish the Kalman filter time step from the modeling window of the state transfer matrix parameters, in this embodiment, the discrete time step in the filtering process is represented by the subscript k, and the data samples involved in the state transfer matrix training process are represented by t to represent the corresponding timestamp.

[0042] In this embodiment, the Kalman filter algorithm is used to analyze the sensor observation data of the new meter to complete meter state estimation and abnormality detection, including the following steps: S41, constructing an observation data vector based on the sensor observation data of the new meter, and initializing input parameters of the Kalman filter algorithm, including an initial state estimation vector, an initial covariance matrix, a state transfer matrix, and an observation noise covariance matrix; S42, executing the iterative process of the Kalman filter algorithm, based on the current state estimation vector and covariance matrix, calculating the optimal smoothed state estimation value vector at the current moment through the state update equation; S43, calculate the residual between the observed data vector and the optimal smoothed state estimation vector, and determine whether the amplitude of the residual exceeds the preset abnormality threshold: if so, it is determined that there is an abnormality in the current operating state of the meter; if not, return to the previous step S42.

[0043] The state update equation is a process of calculating the predicted state vector and updating the optimal smoothed state estimation vector of the Kalman filter.

[0044] Specifically, the new meter's sensors collect observation data including voltage U, current I, active power P and reactive power Q, and upload them to the remote monitoring system to construct the observation data vector ; At the same time, according to the system initialization settings, set the initial state estimation vector is the historical running mean, and the covariance matrix is ​​initialized to a diagonal positive definite matrix , state transition matrix Generated by historical load training model; Observation noise covariance matrix (process noise) and (Environmental noise) During initialization, the initial value is set based on the manufacturer's specified accuracy and the on-site environmental noise experience value; The remote monitoring system first estimates the state vector based on the previous moment and the state transfer matrix , perform state prediction calculation and output the predicted state vector ; Then, based on the prediction covariance update formula, combined with the process observation noise covariance matrix, the prediction covariance matrix is ​​calculated ; By calculating the Kalman gain matrix , combined with the observation data vector at the current moment , for the predicted state vector Make corrections and output the optimal smoothed state estimate vector , and update the covariance matrix synchronously ; Perform difference calculation on the current observation vector and the optimal smoothed state estimate vector to form a residual vector ; The residual vector Substitute into the Mahalanobis distance calculation model, combined with the current covariance matrix Solving weighted distance ; The obtained weighted distance and abnormal threshold To compare: If the weighted distance exceeds the anomaly threshold, the system determines that the current observation is abnormal, automatically records the abnormal point and uploads it; If the weighted distance is within the abnormal threshold range, the system determines that the current estimate is reliable and returns to S42 to perform the state update of the next time step; The observation data vector is a column vector arranged in the order of sampling period and is time-aligned and unit-normalized; The abnormal threshold Based on the confidence level set by the system , combined with the residual Mahalanobis distance and the current covariance matrix, is calculated according to the chi-square distribution critical value to determine whether the current state is within the statistical abnormal range, where n is the vector dimension of the residual.

[0045] Among them, the specific formula of the observation data vector is as follows:

[0046] Where k represents the current sampling time.

[0047] The specific formula of the initial state estimation vector is as follows:

[0048] Where W is the length of the history window used for initialization, is the mathematical expectation, It means that for the observation data z between the selected time window kW and k, the mean vector is calculated in each dimension as the initial state estimate.

[0049] The state covariance matrix is ​​initialized as a diagonal positive definite matrix. The specific formula is as follows:

[0050] Where, is the identity matrix, The state error variance is a built-in parameter of the system.

[0051] The specific calculation formula for the predicted state vector is as follows:

[0052] Where, Expressed as the state estimation vector at the previous moment and the state transition matrix Perform matrix multiplication to obtain the predicted state vector.

[0053] The specific calculation formula of the prediction covariance matrix is ​​as follows:

[0054] The specific calculation formula of the Kalman gain matrix is ​​as follows:

[0055] Where, For the observation matrix at the current moment, define the mapping relationship between the state vector and the observation vector. In order to adapt to the actual situation where the observation channel, sensor configuration or observation accuracy changes over time, It is usually adjusted dynamically over time. If the system observation structure is fixed, it can be set as a constant matrix.

[0056] The specific calculation formula of the optimal smoothed state estimation vector is as follows:

[0057] The specific formula for updating the covariance matrix is ​​as follows:

[0058] The specific calculation formula of the residual vector is as follows:

[0059] The specific calculation formula of weighted distance is as follows:

[0060] Where, is the residual covariance.

[0061] In this embodiment, the state transition matrix is ​​generated by a historical load training model, which includes online modeling of the state transition relationship based on the historical load curve and real-time power fluctuation characteristics of the new meter, and iterative adjustment of the parameters of the state transition matrix, specifically: Taking the historical active power sequence of the newly connected meter in the recent period as the data basis, a sliding time window of length N is set to extract the original load sequence from it and instantaneous fluctuation As the training data feature, the instantaneous fluctuation is obtained by first-order difference calculation. The specific formula is as follows:

[0062] Combine the above features into the input vector for each time step and construct the input feature matrix At the same time, the observation state is defined as , collect the corresponding state sequence . Ultimately, and Align to form N state transition samples , used to fit the state transition model.

[0063] Then, based on the state transition sample sequence constructed above, the exponentially weighted recursive least squares (EWRLS) method is used to calculate the state transition matrix in the linear state space model. The initial parameters of are fitted and estimated. Specifically: Let the transfer equation in Flattened to parameter vector , and convert each sample into regression form. The specific expression is as follows:

[0064] in, is the matrix Kronecker product operation. Through the above steps, the parameter vector The estimated value is continuously updated with the sample iteration, and the result of each recursive iteration is recorded as , and finally obtain the estimated value after convergence , as the first round state transfer matrix parameter vector , reconstruct the initial state transfer matrix .

[0065] The initial state transfer matrix parameters are embedded in the Kalman filter state prediction stage, running multiple time steps to collect the residual sequence between the predicted state and the actual observation , and calculate its mean , standard deviation and covariance ; Based on the assumption that the historical residual sequence obeys an approximate Gaussian distribution, the drift judgment threshold is set. , used to identify whether the state transfer matrix parameters deviate significantly from the actual operating characteristics; If the current residual mean If the drift judgment threshold is exceeded, it is determined that the current state transfer matrix has drift and needs to be corrected. Specifically: Residual As the objective function gradient signal, the stochastic gradient descent (SGD) algorithm is used to adjust the state transfer matrix parameters Perform iterative optimization. The specific iterative formula is as follows:

[0066] Where i is the iteration round, is the learning rate, the loss function is the weighted residual square term, and the specific formula is as follows:

[0067] Gradient term The specific calculation formula is as follows:

[0068] Where, is the predicted state; To verify convergence, the residual mean is recorded after each iteration. If the mean value shows a monotonically decreasing trend and converges with the iteration rounds, it is determined that the state transfer matrix has successfully fitted the current operating state; Finally, the converged state transfer matrix parameters are output , and is continuously used in the subsequent Kalman filtering process to achieve dynamic adaptation of the model to changes in grid operating conditions and improve the accuracy of state estimation.

[0069] The specific calculation formula for the drift judgment threshold is as follows:

[0070] In Example 2, in order to verify that the proposed residual-driven adaptive optimization method has good convergence and practical tracking capabilities when the state transfer matrix drifts, this example carried out the following simulation experiments: (1) Setting the real state transfer matrix Assume that the real state transfer matrix of the system is:

[0071] The initial state is set to , under ideal conditions without process noise interference, the simulation generates a state sequence of length L = 200, and its update formula is:

[0072] (2) Initial state transfer matrix setting Assume that the initial state transfer matrix obtained using exponentially weighted recursive least squares (EWRLS) is

[0073] Due to parameter drift with the real system, the state estimate obtained by Kalman prediction will continue to produce systematic residuals.

[0074] (3) Iterative optimization process The true state is taken as the observation value, and the The residual between the estimated states obtained by performing Kalman prediction is used as the optimization target.

[0075] The loss function is constructed as:

[0076] In order to simplify the experimental implementation and focus on the verification of the state transfer matrix parameter optimization strategy, the residual loss function is set as , that is, the state prediction residual is measured in the form of the square of the two norms. This form is used when the covariance matrix is ​​the unit matrix (i.e. ), and the weighted Mahalanobis distance loss function:

[0077] Essentially equivalent. In practical engineering applications, if the errors in the various state dimensions exhibit heteroscedasticity or statistical correlation, covariance estimation can be introduced to further enhance robustness. In this embodiment, to avoid interference from covariance estimation errors on optimization convergence, the identity matrix is ​​used as a covariance approximation, thereby more purely observing the adaptive adjustment capability of the state transfer matrix parameters and the monotonic convergence trend of the residual mean.

[0078] Furthermore, stochastic gradient descent (SGD) is used to derive the state transfer matrix parameter vector To update:

[0079] The learning rate , the gradient is calculated according to the chain rule.

[0080] (4) Calculate the residual mean after each iteration , draw the curve of residual mean changing with iteration rounds to check whether it converges. The results are as follows Figure 2 As shown in the figure, as the iteration proceeds, the residual mean shows a monotonically decreasing trend and eventually converges, which verifies the effectiveness and robustness of the state transfer matrix optimization method under ideal noise-free conditions.

[0081] Example 3, A remote monitoring device for continuous measurement of live meter replacement, such as Figure 3 Shown, including: A conversion model building module is used to receive raw data from new meters based on the remote monitoring system, parse its data structure and build a data format conversion model; A format conversion module, used to apply the data format conversion model to the real-time metering data of the old meter to obtain a standardized data packet; Data integration module, used to synchronize standardized data packages to new meters and perform data verification to complete the inheritance of historical meter data; The anomaly detection module is used to analyze the sensor observation data of the new meter based on the Kalman filter algorithm to complete meter state estimation and anomaly detection.

[0082] Example 4, A remote monitoring device for continuous measurement of live meter replacement, such as Figure 4 As shown, it includes a memory and a processor: the memory is used to store programs; the processor is used to execute the programs to implement any implementation method in Example 1.

[0083] Since the remote monitoring device for continuous metering with live meter replacement introduced in this embodiment is the device used to implement the method in Example 1 of the present invention, based on the method introduced in Example 1 of the present application, those skilled in the art can understand the specific implementation of the electronic device of this embodiment and its various variations, so how the electronic device implements the method in the embodiment of the present application will not be described in detail here. As long as the device used by those skilled in the art to implement the method in the embodiment of the present application falls within the scope of protection of this application.

[0084] Example 5, A readable storage medium having a computer program stored thereon, such as Figure 5 As shown, when the computer program is executed by a processor, any implementation method in Example 1 is implemented.

[0085] The above formulas are all dimensionless and numerical calculations. The formulas are obtained by collecting a large amount of data and performing software simulation to obtain the most recent real situation. The preset parameters in the formulas are set by technicians in this field according to actual conditions.

[0086] The above embodiments may be implemented in whole or in part through software, hardware, firmware, or any other combination thereof. When implemented using software, the above embodiments may be implemented in whole or in part in the form of a computer program product.

[0087] Those skilled in the art will appreciate that the modules and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of this application.

[0088] In addition, each functional module in each embodiment of the present application may be integrated into one processing module, or each module may exist physically separately, or two or more modules may be integrated into one module.

[0089] The above description is merely a specific embodiment of the present application, but the scope of protection of the present application is not limited thereto. Any changes or substitutions that can be easily conceived by a person skilled in the art within the technical scope disclosed in this application should be included in the scope of protection of this application. Therefore, the scope of protection of this application should be based on the scope of protection of the claims.

[0090] Finally: The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present invention should be included in the scope of protection of the present invention.

Claims

1. A remote monitoring method for continuous measurement of live meter replacement, characterized in that: The following steps are involved: Receive raw data from new meters based on the remote monitoring system, parse its data structure and build a data format conversion model; Apply the data format conversion model to the real-time metering data of the old meters to obtain a standardized data package; Synchronize the standardized data package to the new meter and perform data verification to complete the inheritance of the meter's historical data; The sensor observation data of the new meter is analyzed based on the Kalman filter algorithm to complete meter state estimation and anomaly detection.

2. The remote monitoring method for continuous metering of live meter replacement according to claim 1 is characterized in that: The remote monitoring system receives the raw data from the new meter, parses its data structure and builds a data format conversion model, specifically: The new meter sends raw data packets to the remote monitoring system via the built-in communication module; The remote detection system parses the communication protocol structure of the original data packet and generates a protocol dictionary containing field definitions, encoding rules and verification mechanisms; A data format conversion model is constructed based on the protocol dictionary, wherein the model includes a mapping function from old meter data fields to new meter fields.

3. The remote monitoring method for continuous metering of live meter replacement according to claim 2 is characterized in that: The data format conversion model is applied to the real-time metering data of the old meter to obtain a standardized data packet, specifically: The operating parameters of the old meter are collected through the meter's built-in communication module to obtain the original data set; The original data set is input into the data format conversion model to generate a standardized data package containing the subject data.

4. The remote monitoring method for continuous metering of live meter replacement according to claim 3 is characterized in that: The standardized data package is synchronized to the new meter and data verification is performed to complete the inheritance of the meter's historical data, specifically: Detect the access status of the new meter and receive the final transmission data packet from the old meter or data transfer device; Extracting a cyclic redundancy check code from the tail of the final transmission data packet; Recalculating a cyclic redundancy check value for the main body data of the final transmission data packet; Comparing the recalculated check value with the extracted check code: if the check values ​​match, parsing the main data and performing data synchronization with the new meter; If the check value does not match, an abnormal information packet containing an error identifier is generated and uploaded to the system backend.

5. The remote monitoring method for continuous metering of live meter replacement according to claim 4 is characterized in that: The method of analyzing the sensor observation data of the new meter based on the Kalman filter algorithm to complete meter state estimation and anomaly detection includes the following steps: Constructing an observation data vector based on the sensor observation data of the new meter and initializing the input parameters of the Kalman filter algorithm, including the initial state estimation vector, the initial covariance matrix, the state transfer matrix, and the observation noise covariance matrix; Execute the iterative process of the Kalman filter algorithm, based on the current state estimate vector and covariance matrix, calculate the optimal smoothed state estimate value vector at the current moment through the state update equation; Calculate the residual between the observed data vector and the optimal smoothed state estimation vector, and determine whether the magnitude of the residual exceeds the preset abnormality threshold: if so, it is determined that the current operating state of the meter is abnormal; if not, return to the previous step.

6. The remote monitoring method for continuous metering of live meter replacement according to claim 5 is characterized in that: The state transfer matrix is ​​generated by a historical load training model, including online modeling of the state transfer relationship based on the historical load curve and real-time power fluctuation characteristics of the new meter, and iterative adjustment of the parameters of the state transfer matrix.

7. The remote monitoring method for continuous metering of live meter replacement according to claim 6, characterized in that: The abnormal threshold is obtained by comparing the Mahalanobis distance of the calculated residual with the threshold of the chi-square distribution.

8. A remote monitoring device for continuous measurement of live meter replacement, characterized in that: include: A conversion model building module is used to receive raw data from new meters based on the remote monitoring system, parse its data structure and build a data format conversion model; A format conversion module, used to apply the data format conversion model to the real-time metering data of the old meter to obtain a standardized data packet; Data integration module, used to synchronize standardized data packages to new meters and perform data verification to complete the inheritance of historical meter data; The anomaly detection module is used to analyze the sensor observation data of the new meter based on the Kalman filter algorithm to complete meter state estimation and anomaly detection.

9. A remote monitoring device for continuous measurement of live meter replacement, characterized in that: Including memory and processor: The memory is used to store programs; The processor is used to execute the program to implement each step of the remote monitoring method for continuous metering of live meter replacement as described in any one of claims 1 to 7.

10. A readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, each step of the remote monitoring method for continuous metering of live meter replacement as described in any one of claims 1 to 7 is implemented.

Images