An adaptive error compensation method, system, device, and storage medium for electricity meters based on multi-physics coupling and latent variable modeling.

Abstract

This invention discloses an adaptive error compensation method, system, device, and storage medium for electricity meters based on multi-physical coupling and latent variable modeling, relating to the field of electricity metering and detection technology. The method includes constructing a multi-physical coupling basis vector containing univariate and cross-variables based on sensor output signals; jointly modeling latent variables based on the multi-physical coupling basis vector and parasitic capacitance changes, permeability drift, and shunt resistance offset to form a compensation mapping relationship of electromagnetic, thermal, and stress coupling; generating compensation coefficients using the compensation mapping relationship; and applying these compensation coefficients within the electricity metering link to complete the error compensation process. The method of this invention generates voltage, current, and phase compensation coefficients through multi-physical coupling basis vectors and latent variable modeling, achieving dynamic characterization and adaptive correction of error sources, and realizing dynamic and accurate correction of voltage, current, and phase, ensuring that the electricity meter maintains high-precision metering over a long period under complex environments and device drift conditions.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of electric energy metering and detection, in particular to an electric meter adaptive error compensation method, system and device based on multi-physical coupling and hidden variable modeling and a storage medium. BACKGROUND

[0002] With the expansion of the scale of the power system and the improvement of the intelligent level, the electric energy metering device has been transitioned from a mechanical structure to an electronic electric energy meter. Relying on high-precision sampling circuits, digital signal processing units and data interfaces, the electronic electric energy meter can not only complete basic electric quantity measurement, but also gradually undertake power analysis, data interaction and operation monitoring functions. In the links of residential electricity, industrial electricity and power grid dispatching, the electronic electric energy meter has become the core metering equipment. With the access of distributed power sources, the diversification of electricity consumption behavior and the frequent occurrence of harmonics and impulse currents, the operating environment of the electric energy meter presents a trend of complexity and dynamics, and the traditional compensation methods gradually reveal their limitations.

[0003] Existing research mainly focuses on two paths of hardware compensation and software compensation. Hardware compensation methods focus on component parameter design, such as improving the stability of sampling resistors, optimizing the material properties of current transformers, and introducing high-precision reference voltage sources. These methods have certain advantages in reducing single-source errors, but the design complexity and cost are high, and the application range is limited. Software compensation methods rely on algorithms to fit and correct errors. Common methods include function compensation based on temperature characteristics, linear regression methods based on least squares, nonlinear correction based on polynomial expansion, and neural network fitting methods that have emerged in recent years. Software compensation can improve the performance of the electric meter in dynamic environments to some extent, but the stability and interpretability are still insufficient under long-term operation and complex power signal conditions.

[0004] With the significant increase in the number of electric meter deployments and the continuous extension of the operating time, the sampling links and sensing units gradually show signs of aging and drifting. For example, small changes in parasitic capacitance can affect voltage measurement accuracy, shifts in magnetic permeability can change transformer characteristics, and shifts in shunt resistors can cause current measurement errors. The above problems often exhibit implicit and cumulative characteristics and are difficult to solve by a single compensation method. At the same time, temperature fluctuations, mechanical stress and electromagnetic interference in the operating environment of the electric meter often interact, forming a nonlinear coupling relationship. This multi-factor interaction can complicate the error sources and exacerbate the gap between the compensation model and the real environment. In the face of atypical operating conditions or extreme disturbance conditions, the model may produce unreasonable compensation outputs, making it difficult to ensure that the metering results are consistent with the basic laws of the power system. SUMMARY

[0005] In view of the above problems, the present application is proposed.

[0006] Therefore, the technical problem solved by the present application is that the existing electric energy meter error compensation method has the problems of ineffective modeling of the coupling relationship of multiple physical factors, difficulty in accurately representing the hidden variable state, low long-term operation stability, lack of physical consistency constraint of the compensation result, and how to realize adaptive error compensation based on the interaction of multiple physical quantities and the drift characteristics of hidden devices in a complex power environment.

[0007] To solve the above technical problems, the present application provides the following technical solutions: an electric meter adaptive error compensation method based on multi-physical coupling and hidden variable modeling, including constructing a multi-physical coupling base vector containing single variables and cross variables based on sensor output signals; performing hidden variable joint modeling based on the multi-physical coupling base vector and parasitic capacitance changes, permeability drift, and shunt resistance offset to form a compensation mapping relationship coupled by electromagnetism, heat, and stress; and generating compensation coefficients using the compensation mapping relationship to complete the error compensation process in the electric meter measurement link.

[0008] As a preferred scheme of the electric meter adaptive error compensation method based on multi-physical coupling and hidden variable modeling, the multi-physical coupling base vector includes temperature, stress, electromagnetic interference, and cross variables; the cross variables include the products of temperature and stress, temperature and electromagnetic interference, stress and electromagnetic interference, and the product terms of stress, temperature, and electromagnetic interference.

[0009] As a preferred scheme of the electric meter adaptive error compensation method based on multi-physical coupling and hidden variable modeling, the hidden variable joint modeling includes using an observation quantity constructed based on active power residual error, reactive power residual error, and harmonic energy residual error, and using an extended Kalman filter update step to identify the states of parasitic capacitance change parameters, permeability drift parameters, and shunt resistance offset parameters.

[0010] As a preferred scheme of the electric meter adaptive error compensation method based on multi-physical coupling and hidden variable modeling, the update step includes using a recursive least squares method with a forgetting factor to iteratively adjust the weight parameters of the explicit coupling base, and using a one-step fine-tuning method of a lightweight network to adjust the parameters of the nonlinear term.

[0011] As a preferred scheme of the electric meter adaptive error compensation method based on multi-physical coupling and hidden variable modeling, the compensation mapping relationship includes an explicit coupling linear term, a linear term based on hidden variables, and a nonlinear term based on voltage, current, phase, and total harmonic distortion rate, and the three parts are superimposed to generate compensation coefficients.

[0012] As a preferred scheme of the meter adaptive error compensation method based on multi-physical coupling and hidden variable modeling, the compensation coefficients include voltage compensation coefficients, current compensation coefficients and phase compensation coefficients; the voltage compensation coefficients include a proportional factor for correcting voltage amplitude and an offset for correcting direct current bias of the voltage signal; the current compensation coefficients include a proportional factor for correcting current amplitude and an offset for correcting amplitude-frequency response of the corresponding channel of the current signal; and the phase compensation coefficients include an angle correction amount for correcting fundamental phase difference between the voltage and the current and an angle correction amount for correcting harmonic phase difference.

[0013] As a preferred scheme of the meter adaptive error compensation method based on multi-physical coupling and hidden variable modeling, the error compensation process includes a projection correction step based on energy conservation constraint; the projection correction is performed by linearizing the energy balance equation, calculating a disturbance amount under quadratic programming, and writing back to the voltage compensation coefficients, the current compensation coefficients and the phase compensation coefficients.

[0014] Another object of the present application is to provide a meter adaptive error compensation system based on multi-physical coupling and hidden variable modeling, which can solve the problem that current meter compensation technology only relies on single physical quantity modeling and lacks effective identification of device implicit drift by fusing temperature quantity, stress quantity and electromagnetic interference quantity signals with parasitic capacitance change parameters, magnetic permeability drift parameters and shunt resistance offset parameters to construct an electromagnetic, thermal and stress coupled compensation mapping relationship.

[0015] As a preferred scheme of the meter adaptive error compensation system based on multi-physical coupling and hidden variable modeling, the system includes a coupling basis vector construction module, a hidden variable joint modeling module and a compensation application module; the coupling basis vector construction module is used to form a feature expression set containing single variables and cross variables according to output information of temperature quantity, stress quantity and electromagnetic interference quantity, and provide a unified hidden variable modeling input framework; the hidden variable joint modeling module is used to fuse and model the coupling basis vector with parasitic capacitance change parameters, magnetic permeability drift parameters and shunt resistance offset parameters, and update the hidden variable state in real time through an extended Kalman filtering calculation process based on active power residual error, reactive power residual error and harmonic residual error, to form an electromagnetic, thermal and stress coupled compensation mapping relationship; and the compensation application module is used to generate voltage compensation coefficients, current compensation coefficients and phase compensation coefficients based on the compensation mapping relationship, correct the compensation coefficients through projection operation under energy conservation constraint, and apply the corrected compensation coefficients to voltage channels, current channels and phase calculation channels to correct errors in the meter measurement link.

[0016] A computer device comprises a memory and a processor, the memory stores a computer program, and the processor executes the computer program to implement steps of an ammeter adaptive error compensation method based on multi-physical coupling and hidden variable modeling.

[0017] A computer readable storage medium stores a computer program, and the computer program is executed by a processor to implement steps of an ammeter adaptive error compensation method based on multi-physical coupling and hidden variable modeling.

[0018] The ammeter adaptive error compensation method based on multi-physical coupling and hidden variable modeling provided by the present application comprehensively characterizes environmental factors and cross effects by constructing a multi-physical coupling base vector, dynamically characterizes changes in parasitic capacitance, magnetic permeability drift and shunt resistance offset by joint modeling of hidden variables, and realizes real-time correction of voltage, current and phase by applying compensation coefficients in the measurement link. The present application achieves better results in terms of input feature coverage, model adaptability and measurement reliability. BRIEF DESCRIPTION OF DRAWINGS

[0019] In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings needed in the embodiment description will be briefly introduced. Obviously, the drawings in the following description are only some embodiments of the present application, and other drawings can be obtained by those skilled in the art without creative labor.

[0020] Figure 1 The overall flowchart of the ammeter adaptive error compensation method based on multi-physical coupling and hidden variable modeling provided by the present application is provided. DETAILED DESCRIPTION

[0021] In order to make the above-mentioned purposes, features and advantages of the present application more apparent and easy to understand, the specific embodiments of the present application will be described in detail below with reference to the drawings. Obviously, the described embodiments are only a part of the embodiments of the present application, not all embodiments. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative labor should be within the scope of protection of the present application.

[0022] Embodiment 1, refer to Figure 1 For an embodiment of the present application, an ammeter adaptive error compensation method based on multi-physical coupling and hidden variable modeling is provided, comprising:

[0023] S1: Based on the sensing output signal, a multi-physical coupling base vector containing single variables and cross variables is constructed.

[0024] Furthermore, the single variable 101 includes temperature 10, stress 11, and electromagnetic interference 12.

[0025] Furthermore, the multi-physics coupling basis vector 103 includes temperature 10, stress 11, electromagnetic interference 12, and cross-variable 102; the cross-variable 102 includes the product of temperature and stress, the product of temperature and electromagnetic interference, the product of stress and electromagnetic interference, and the product of stress, temperature, and electromagnetic interference.

[0026] It should be noted that the product term is completed through a digital arithmetic logic unit, for example, by setting up a corresponding multiplication instruction pipeline in the signal processor, inputting the temperature quantity 10, stress quantity 11 and electromagnetic interference quantity 12 one by one and performing combined operations. The generated coupling basis vector is stored in the form of a column vector and used as input data for subsequent joint modeling of latent variables. This ensures the integrity and consistency from the sensor output signal to the construction of multi-physical coupling features, and provides a high-dimensional, fully covered input feature space for the establishment of compensation mapping relationships.

[0027] It should also be noted that the sensor output signal 100 includes, by setting the operating baseline and symbol convention, a unified sampling period index is established by setting the sampling rate, analysis window length, and harmonic upper limit, represented as:

[0028] ,

[0029] Harmonic index, represented as:

[0030] ,

[0031] in, This represents the index of a discrete sampling point within a window. This indicates the total number of sampling points within the current sampling period. Indicates the harmonic index. This indicates the maximum order of the current harmonic. The effective values ​​of the voltage and current signals sampled from the meter are calculated and expressed as follows:

[0032] , ,

[0033] in, Indicates the first Within the first time window Voltage sampling value at point, Indicates the first Within the first time window Current sampling value at the point, This represents the effective value of the voltage sampled by the meter. This represents the effective value of the current obtained from the meter sampling. Fundamental component features are extracted from the acquired effective values ​​of the voltage and current signals, and the total harmonic distortion rate of the voltage and current is calculated, expressed as:

[0034] , ,

[0035] , ,

[0036] in, Indicates the current number The fundamental complex component of the voltage within a time window Indicates the current number The fundamental complex component of the current within a time window. This represents the discrete Fourier basis functions, used to project the meter's sampled signal into the frequency domain to extract the fundamental and harmonic components. This indicates the highest order in harmonic analysis, i.e., the upper limit of the harmonic order considered when calculating the total harmonic distortion rate. Indicates the first Total harmonic distortion of voltage within a time window Indicates the first Total harmonic distortion of current within a time window Indicates the current number The voltage in the first time window Second harmonic amplitude Indicates the current number The current in the first time window The amplitude of the second harmonic, through normalized harmonic content, measures the degree of distortion of voltage and current waveforms, providing support for harmonic characteristics. This is achieved by normalizing temperature, stress, and electromagnetic interference to obtain a unified-dimensional multi-physics coupling basis vector, expressed as:

[0037] ,

[0038] ,

[0039] in, This represents the normalized dimensionless temperature variable. This indicates the current temperature (°C). This represents the dimensionless stress variable after normalization. This represents the dimensionless variable of electromagnetic interference after normalization. Indicates the current profit ( ), This indicates the current electromagnetic interference level (V / m). Indicates the reference value for electromagnetic interference. This represents the normalized parameter of electromagnetic interference. represents the first window, the multi-physical coupling basis vector of the window; cross-variable coupling is performed.

[0040] It should also be noted that, as mentioned in the reference Figure 1 , by constructing the coupling basis vectors of the single variable 101 and the cross variable 102, the nonlinear relationship between the temperature quantity 10, the stress quantity 11 and the electromagnetic interference quantity 12 can be fully described, providing high-dimensional input features for hidden variable modeling and error compensation.

[0041] S2: Joint modeling of hidden variables based on multi-physical coupling basis vectors and parasitic capacitance changes, permeability drifts, and shunt resistance shifts, forming a compensation mapping relationship of electromagnetic, thermal, and stress coupling.

[0042] Further, the joint modeling of hidden variables includes using observation quantities constructed based on active power residuals, reactive power residuals, and harmonic energy residuals, represented as:

[0043] ,

[0044] wherein, represents the residual vector, i.e. the observation quantity input for hidden variable estimation, represents the current reference active power (W), which is simultaneously compared with the reactive power as the reference, represents the current reference reactive power (W), represents the compensated voltage effective value (V), represents the compensated current effective value (A), represents the dimensionless harmonic energy calibration function, which calculates the impact of harmonics on power based on THD, represents the product of the fundamental power reference (W), represents the voltage compensation coefficient 23, represents the current compensation coefficient 24, represents the phase compensation coefficient 25, represents the current harmonic voltage, represents the current harmonic current, represents the current harmonic phase, which is used to represent the harmonic energy distribution, represents the total harmonic distortion of voltage, represents the total harmonic distortion of current, which uses an extended Kalman filter update step to identify the state of the parasitic capacitance change parameter, the permeability drift parameter, and the shunt resistance shift parameter.

[0045] It should be noted that the updating step includes iteratively adjusting the weight parameters of the explicit coupling base by using a recursive least square method with a forgetting factor, and adjusting the parameters of the nonlinear term by using a one-step fine-tuning method of the lightweight network.

[0046] It should be noted that the compensation mapping relationship 201 includes an explicit coupling linear term, a linear term based on a hidden variable, and a nonlinear term based on voltage, current, phase, and total harmonic distortion rate, and the three parts are superimposed to generate a compensation coefficient 202.

[0047] It should also be noted that, as shown in reference Figure 1 It should also be noted that, as shown in reference

[0048] S3: Generate compensation coefficients using the compensation mapping relationship, and apply the compensation coefficients in the metering link of the meter to complete the error compensation process.

[0049] Further, the compensation coefficient 202 includes a voltage compensation coefficient 23, a current compensation coefficient 24, and a phase compensation coefficient 25; the voltage compensation coefficient includes a proportional factor for correcting the voltage amplitude and an offset for correcting the direct current bias of the voltage signal; the current compensation coefficient includes a proportional factor for correcting the current amplitude and an offset for correcting the amplitude-frequency response of the corresponding channel of the current signal; the phase compensation coefficient includes an angle correction amount for correcting the fundamental phase difference between the voltage and the current, and an angle correction amount for correcting the harmonic phase difference.

[0050] The compensation coefficient calculation method is represented as:

[0051]

[0052]

[0053] wherein, represents a compensation factor vector , i.e. a compensation coefficient, for correcting the voltage, current, and phase, represents an explicit coupling coefficient matrix corresponding to the cross variables of the temperature, force, and electromagnetic interference, represents a hidden variable mapping coefficient matrix for converting the influence of the hidden variable into a compensation amount, represents a normalized hidden variable estimation value updated by the updating step based on the extended Kalman filter, ​​represents a light-weight neural network for compensating non-linear correction, represents i.e. a feature input vector, represents a parasitic capacitance change relative to a reference value, reflecting the degree of capacitance aging, represents a permeability drift relative to a reference value, reflecting the magnetic performance deviation, represents a shunt resistance offset relative to a reference value, reflecting the current detection path degradation.

[0054] It should be noted that the error compensation process includes a projection correction 300 step based on the energy conservation constraint; the projection correction 300 calculates the disturbance quantity under the quadratic programming by linearizing the energy balance equation, and writes back to the voltage compensation coefficient 23, the current compensation coefficient 24 and the phase compensation coefficient 25.

[0055] It should also be noted that the projection correction 300 is represented as:

[0056] ,

[0057] ,

[0058] ,

[0059] wherein, represents a voltage compensation amount, represents a current compensation amount, represents a phase correction amount for secondary adjustment of the existing compensation coefficient, represents a voltage weight, represents a current weight, represents a phase weight, determined by the energy meter's sensitivity analysis of the parasitic capacitance change, permeability drift and shunt resistance offset factors on the measurement error, for balancing the contribution of the compensation components to the energy conservation constraint under multi-physical coupling.

[0060] It should also be noted that by applying the compensation coefficient in the measurement link, combined with the projection correction 300 of the energy conservation constraint, the dynamic and accurate correction of voltage, current and phase is realized, and the deviation caused by environmental interference of parasitic effects is effectively eliminated.

[0061] Embodiment 2, as an embodiment of the present application, provides an energy meter adaptive error compensation system based on multi-physical coupling and hidden variable modeling, including a coupling base vector construction module, a hidden variable joint modeling module and a compensation application module.

[0062] The coupling base vector construction module is used to form a feature expression set containing single variables and cross variables according to the output information of temperature, stress and electromagnetic interference, and provides a unified hidden variable modeling input framework.

[0063] The hidden variable joint modeling module is used for fused modeling of the coupling basis vector and the parasitic capacitance change parameter, the magnetic permeability drift parameter and the shunt resistance offset parameter, real-time updating of the hidden variable state is performed through an observation quantity input based on the active power residual error, the reactive power residual error and the harmonic residual error, and an extended Kalman filtering calculation process, and a compensation mapping relationship of electromagnetic, thermal and stress coupling is formed.

[0064] The compensation application module is used for generating voltage compensation coefficients, current compensation coefficients and phase compensation coefficients on the basis of the compensation mapping relationship, correcting the compensation coefficients through projection operation under the energy conservation constraint, and applying the corrected compensation coefficients to the voltage channel, the current channel and the phase calculation channel respectively to perform error correction in the electric metering link.

[0065] If the functions are implemented in the form of software function units and sold or used as independent products, they can be stored in a computer readable storage medium. Based on this understanding, the technical solutions of the present application essentially or the parts that contribute to the prior art or parts of the technical solutions can be embodied in the form of a software product, which is stored in a storage medium and includes a plurality of instructions for causing a computer device (which can be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the embodiments of the present application. The aforementioned storage medium includes: a U disk, a mobile hard disk, a read-only memory (ROM, Read-Only Memory), a random access memory (RAM, Random Access Memory), a magnetic disk or an optical disk and various program code storage media.

[0066] The logic and / or steps represented in the flowchart or otherwise described herein, for example, can be considered a list of executable instructions for implementing logic functions, and can be specifically embodied in any computer-readable medium for use by an instruction execution system, apparatus or device, such as a computer-based system, a system including a processor or other system that can fetch and execute instructions from an instruction execution system, apparatus or device, or in conjunction with these instructions execution system, apparatus or device. For the purpose of this specification, the "computer-readable medium" can be any device that can contain, store, communicate, propagate or transport programs for use by an instruction execution system, apparatus or device, or in conjunction with these instruction execution system, apparatus or device.

[0067] ​More specific examples (a non-exhaustive list) of the computer-readable medium include the following: an electrical connection (electronic) having one or more wires, a portable computer diskette (magnetic), a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or Flash memory), an optical fiber device, and a portable compact disc read-only memory (CDROM). Additionally, the computer-readable medium can also be paper or another suitable medium upon which the program is printed, as the program can be electronically captured, for example, via an optical scanner, then compiled, interpreted, or otherwise processed, as necessary, and stored in a computer memory.

[0068] It should be understood that aspects of the application can be implemented in hardware, software, firmware or combinations thereof. In the embodiments described above, various steps or methods can be implemented, for example, by software or firmware stored in memory and executed by a suitable instruction execution system. For example, if implemented in hardware, and in another embodiment, any of the following technologies, known in the art, or their combinations can be used: discrete logic circuitry having logic gates for implementing logic functions upon an application of data signals, application specific integrated circuits having appropriate combinational logic gates, programmable gate arrays (PGA), field programmable gate arrays (FPGA), and the like.

[0069] It should be noted that the above examples are merely intended to illustrate the technical solutions of the present application and not to limit the same. Although the present application has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical solutions of the present application can be modified or replaced by equivalents without departing from the spirit and scope of the present application, and all such modifications or replacements should be included in the scope of the claims of the present application.

Claims

1. An ammeter adaptive error compensation method based on multi-physical coupling and hidden variable modeling, characterized in that, The method comprises the steps of: Based on the sensing output signal, a multi-physical coupling base vector containing single variables and cross variables is constructed; Based on the multi-physical coupling base vector and the parasitic capacitance change, the magnetic permeability drift and the shunt resistance offset, a hidden variable joint modeling is performed to form a compensation mapping relationship of electromagnetic, thermal and stress coupling; A compensation coefficient is generated by using the compensation mapping relationship, and the error compensation process is completed by applying the compensation coefficient in the electric metering link; The multi-physical coupling base vector includes temperature, stress and electromagnetic interference variables and cross variables; The cross variables include the products of temperature and stress, temperature and electromagnetic interference, stress and electromagnetic interference, and the products of stress, temperature and electromagnetic interference; The hidden variable joint modeling includes using the observation quantity constructed based on the active power residual error, the reactive power residual error and the harmonic energy residual error, and using the extended Kalman filter update step to identify the state of the parasitic capacitance change parameter, the magnetic permeability drift parameter and the shunt resistance offset parameter.

2. The method of claim 1, wherein the method is based on multi-physical coupling and hidden variable modeling. The update step includes, The weight parameters of the explicit coupling base are iteratively adjusted by using the recursive least squares method with a forgetting factor, and the parameters of the nonlinear term are adjusted by using the one-step fine-tuning method of the lightweight network.

3. The method of claim 1 or 2, wherein the method is based on multi-physical coupling and hidden variable modeling. The compensation mapping relationship includes, It is composed of an explicit coupling linear term, a linear term based on a hidden variable, and a nonlinear term based on voltage, current, phase and total harmonic distortion rate, and the three parts are superimposed to generate a compensation coefficient.

4. The method of claim 3, wherein the method is based on multi-physical coupling and hidden variable modeling. The compensation coefficient includes, Voltage compensation coefficient, current compensation coefficient and phase compensation coefficient; The voltage compensation coefficient includes a proportional factor for correcting the voltage amplitude and an offset for correcting the direct current bias of the voltage signal; The current compensation coefficient includes a proportional factor for correcting the current amplitude and an amplitude-frequency response offset for correcting the corresponding channel of the current signal; The phase compensation coefficient includes an angle correction amount for correcting the fundamental phase difference between voltage and current and an angle correction amount for correcting the harmonic phase difference.

5. The adaptive error compensation method for the ammeter based on the multi-physical coupling and the hidden variable modeling according to any one of claims 1, 2, 4, characterized in that: The error compensation process includes, Projection correction step based on energy conservation constraint; The projection correction calculates the disturbance by linearizing the energy balance equation under the quadratic programming, and writes back to the voltage compensation coefficient, the current compensation coefficient and the phase compensation coefficient.

6. The adaptive error compensation system for electric meter based on multi-physical coupling and hidden variable modeling, adopting the adaptive error compensation method for electric meter based on multi-physical coupling and hidden variable modeling according to any one of claims 1-5, characterized in that: It includes a coupling base vector construction module, a hidden variable joint modeling module and a compensation application module; The coupling base vector construction module is used to form a feature expression set containing single variables and cross variables according to the output information of temperature, stress and electromagnetic interference, and to provide a unified hidden variable modeling input framework; The hidden variable joint modeling module is used to fuse the coupling base vector with the parasitic capacitance change parameter, the magnetic permeability drift parameter and the shunt resistance offset parameter, and to update the hidden variable state in real time by using the observation quantity input based on the active power residual error, the reactive power residual error and the harmonic residual error, and combining the extended Kalman filter calculation process, to form a compensation mapping relationship of electromagnetic, thermal and stress coupling; The compensation application module is used for generating voltage compensation coefficients, current compensation coefficients and phase compensation coefficients on the basis of the compensation mapping relationship, correcting the compensation coefficients through projection operation under the energy conservation constraint, and applying the corrected compensation coefficients to voltage channels, current channels and phase calculation channels respectively to correct errors in the metering link. 7.A computer device, comprising a memory and a processor, wherein the memory stores a computer program, and the computer device is configured to perform the method according to any one of claims 1-6 when the computer program is executed by the processor. The processor implements the steps of the meter adaptive error compensation method based on multi-physical coupling and hidden variable modeling in any one of claims 1-5 when executing the computer program.

8. A computer-readable storage medium having stored thereon a computer program, characterized in that, The processor implements the steps of the meter adaptive error compensation method based on multi-physical coupling and hidden variable modeling in any one of claims 1-5 when executing the computer program.

Images