Charging pile metering method and device, storage medium and electronic equipment

Abstract

The present disclosure relates to a charging pile metering method and device, a storage medium and an electronic device. The method comprises: performing parameter estimation processing based on current data, voltage data, resistance value data, an error compensation model corresponding to a plurality of temperature-related devices, and a preset digital twin model to obtain power calibration information corresponding to a current time; determining error mirror information corresponding to the current time based on output power information and the power calibration information; performing nonlinear change processing based on the error mirror information, historical state change information, and a preset neural network model to obtain residual prediction information; performing fusion processing based on the residual prediction information, the error mirror information, and the power calibration information to obtain a target power value; and determining target metering results corresponding to the current time based on the target power value and metering results corresponding to a previous time. The present disclosure can realize multi-path collaborative metering, and improve the accuracy of modeling and robustness of a charging pile metering system under complex working conditions.

Description

Technical Field

[0001] This disclosure relates to the field of charging pile technology, and in particular to charging pile metering methods, devices, storage media and electronic equipment. Background Technology

[0002] Existing charging stations generally adopt a single-path metering method, which means that electricity data is collected and settled through a single metering chip or electricity meter. This single-path metering mode faces many challenges in actual operation. Factors such as ambient temperature can significantly affect the metering accuracy of charging stations. In addition, the accuracy drift of the metering chip under long-term high-load operation, the metering deviation caused by the heat generated by the shunt, and electromagnetic compatibility issues all make it difficult to fully guarantee the reliability of single-path metering.

[0003] Current solutions attempt to improve metering accuracy by periodically calibrating a single metering device or comparing data between different metering devices. However, these solutions fail to address the dynamic adaptive calibration problem under varying load conditions, ambient temperatures, and power module operating conditions. When an anomaly occurs in a sampling path, the existing system cannot adjust the measurement parameters for that path in real time; it can only handle the issue by reporting the fault and waiting for repairs. This not only increases the failure rate and operating costs of charging stations but also reduces the continuity of charging services and the user experience. Inconsistencies in metering data between multiple devices are more likely to cause consumer disputes during the charging settlement process. Summary of the Invention

[0004] To address at least one of the aforementioned technical problems, this disclosure provides a charging pile metering method, apparatus, storage medium, and electronic device.

[0005] According to one aspect of this disclosure, a charging pile metering method is provided, applied to a charging pile main control system, the charging pile main control system including an energy metering module and multiple temperature correlation devices, the multiple temperature correlation devices including a power supply module, which includes: The current signal feature information collected by the power metering module at the current moment, the output power information corresponding to the power module, the current operating temperature data, and the error compensation model corresponding to the multiple temperature-related devices are obtained. The current signal feature information includes current data and voltage data. Based on the current data, the voltage data, the current operating temperature data, the error compensation model corresponding to the multiple temperature-related devices, and the preset digital twin model, parameter estimation processing is performed to obtain the power calibration information corresponding to the current moment. The error mirror information corresponding to the current moment is determined based on the output power information and the power calibration information corresponding to the current moment. Based on the error mirror information, historical state change information and preset neural network model corresponding to the current moment, nonlinear change processing is performed to obtain residual prediction information. The historical state change information includes state information corresponding to multiple moments within the target time period up to the current moment. The state information includes output power information and power calibration information. Based on the fusion processing of the residual prediction information, the error mirror information and the power calibration information, the target power value corresponding to the current moment is obtained; The target metering result for the current moment is determined based on the target power value at the current moment and the electricity metering result at the previous moment.

[0006] In some possible implementations, the plurality of temperature-correlated devices include sampling resistors, and the error compensation model corresponding to the plurality of temperature-correlated devices includes a resistance temperature drift model corresponding to the sampling resistors. The method further includes: Based on preset standard resistance data, preset reference temperature data, and the current operating temperature data, the resistance temperature drift model corresponding to the sampling resistor is determined. The formula is as follows:

[0007] in, To preset the nominal resistance data, This is the current operating temperature data. The preset reference temperature data is α, which is the first-order temperature coefficient, and β is the second-order temperature coefficient.

[0008] In some possible implementations, the plurality of temperature-correlated devices further include a shunt, and the error compensation model corresponding to the plurality of temperature-correlated devices includes a high-current model corresponding to the shunt. The method further includes: Obtain the resistance voltage data corresponding to the sampling resistor; Based on the resistance voltage data, the resistance temperature drift model, and the current data, the high-current model corresponding to the shunt is determined. The formula is as follows:

[0009] in, For resistance voltage data, This is a resistance temperature drift model, where I represents the current data. For current nonlinearity coefficient, This is the temperature coupling coefficient.

[0010] In some possible implementations, the plurality of temperature-correlated devices further include a front-end amplifier and an analog-to-digital converter sampling module, the error compensation model corresponding to the plurality of temperature-correlated devices includes the analog output voltage corresponding to the front-end amplifier, and the method further includes: The analog output voltage corresponding to the analog-to-digital converter sampling module is determined based on the voltage data and the current operating temperature data, using the following formula:

[0011]

[0012]

[0013] in, To simulate the output voltage, For voltage data, Let be the gain error function. For the input offset voltage function, , This is the calibration value at room temperature. , This is the first-order temperature drift coefficient; It is the second-order temperature drift coefficient.

[0014] In some possible implementations, the error compensation model corresponding to the plurality of temperature-correlated devices includes the digital code value corresponding to the analog-to-digital converter sampling module, and the method further includes: Obtain the resolution corresponding to the analog-to-digital converter sampling module; The digital code value corresponding to the analog-to-digital converter sampling module is determined based on the resolution, the voltage data, and the current operating temperature data, using the following formula:

[0015]

[0016] Where D is the digital code value and N is the resolution. As a reference voltage model, For the quantization error of the digital-to-analog converter, The preset nominal reference voltage; This is the first-order temperature drift coefficient; It is the second-order temperature drift coefficient.

[0017] In some possible implementations, the error compensation model corresponding to the power module is the power module model corresponding to the power module, and the method further includes: Obtain the number of power supplies corresponding to the power module; The power module model is determined based on the output power information and the number of power supplies. The formula is as follows:

[0018]

[0019] in, This provides the output power information for the power module, where n is the number of power supplies. This is a dynamic coefficient.

[0020] In some possible implementations, the method further includes: Backpropagation is performed based on the error mirror information and the preset digital twin model to obtain the gradient parameter information corresponding to the adjustable parameter information in the preset digital twin model. Based on the gradient parameter information and the preset error threshold, gradient descent optimization is performed to obtain the updated preset digital twin model.

[0021] According to a second aspect of this disclosure, a charging pile metering device is provided, applied to a charging pile main control system, the charging pile main control system including an energy metering module and multiple temperature correlation devices, the multiple temperature correlation devices including a power supply module, the device comprising: The information acquisition module is used to acquire the current signal feature information collected by the power metering module at the current moment, the output power information corresponding to the power module, the current operating temperature data, and the error compensation model corresponding to the multiple temperature-related devices. The current signal feature information includes current data and voltage data. The white-box processing module is used to perform parameter estimation processing based on the current data, the voltage data, the current operating temperature data, the error compensation model corresponding to the multiple temperature-related devices, and the preset digital twin model to obtain the power calibration information corresponding to the current moment. An error determination module is used to determine the error mirror information corresponding to the current time based on the output power information and the power calibration information corresponding to the current time. The residual prediction module is used to perform nonlinear change processing based on the error mirror information, historical state change information and preset neural network model corresponding to the current time to obtain residual prediction information. The historical state change information includes state information corresponding to multiple times within the target time period up to the current time. The state information includes output power information and power calibration information. The fusion processing module is used to perform fusion processing based on the residual prediction information, the error mirror information and the power calibration information to obtain the target power value corresponding to the current moment. The metering module is used to determine the target metering result corresponding to the current time based on the target power value corresponding to the current time and the electricity metering result corresponding to the previous time.

[0022] According to a third aspect of this disclosure, an electronic device is provided, including at least one processor and a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor, and the at least one processor implements the charging pile metering method as described in any one of the first aspects by executing the instructions stored in the memory.

[0023] According to a fourth aspect of this disclosure, a computer-readable storage medium is provided, wherein at least one instruction or at least one program is stored therein, the at least one instruction or at least one program being loaded and executed by a processor to implement the charging pile metering method as described in any of the first aspects.

[0024] It should be understood that the above general description and the following detailed description are exemplary and explanatory only, and are not intended to limit this disclosure.

[0025] Implementing this disclosure will have the following beneficial effects: By embedding an energy metering module into the main control system of the charging pile, the size of the charging pile is reduced. Parameter estimation processing is performed on current data, voltage data, current operating temperature data, error compensation models corresponding to multiple temperature-related devices, and a preset digital twin model to obtain the power calibration information corresponding to the current moment. A digital twin model corresponding to the physical metering system is constructed, realizing a bidirectional mapping between the physical and virtual systems. Error mirror information corresponding to the current moment is determined based on the current moment's output power information and power calibration information. An error mirror model is constructed based on the difference between the outputs of the physical and virtual systems, establishing a real-time, bidirectional, closed-loop data channel between the physical and virtual systems. Residual prediction information is obtained by performing nonlinear change processing based on the current moment's error mirror information, historical state change information, and a preset neural network model. The historical state change information includes state information corresponding to multiple moments within the target time period up to the current moment, including output power information and power calibration information. A black-box learning method is used to model the dynamic evolution of the error, which can compensate for transient errors and predict slowly varying errors caused by thermal effects, power state changes, etc. The target power value at the current moment is obtained by fusing residual prediction information, error mirror information, and power calibration information. Based on the target power value at the current moment and the electricity metering result at the previous moment, the target metering result at the current moment is determined. The detected metering results are then corrected, achieving high-precision modeling and robustness improvement of the charging pile metering system under complex operating conditions.

[0026] Other features and aspects of this disclosure will become clear from the following detailed description of exemplary embodiments with reference to the accompanying drawings. Attached Figure Description

[0027] To more clearly illustrate the technical solutions of this application, the accompanying drawings used in the description of the embodiments or prior art will be briefly introduced below. Obviously, the drawings described below are merely some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without any creative effort.

[0028] Figure 1 A flowchart illustrating a charging pile metering method according to an embodiment of the present disclosure is shown. Figure 2 A schematic diagram of the structure of a charging pile main control system according to an embodiment of the present disclosure is shown; Figure 3 A schematic diagram of the structure of a charging pile metering device according to an embodiment of the present disclosure is shown; Figure 4 A block diagram of an electronic device according to an embodiment of the present disclosure is shown. Detailed Implementation

[0029] The technical solutions in the embodiments of this specification will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this specification, and not all embodiments. Based on the embodiments in this specification, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this invention.

[0030] It should be noted that the terms "first," "second," etc., in the specification, claims, and accompanying drawings of this invention are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that the embodiments of the invention described herein can be implemented in orders other than those illustrated or described herein. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover non-exclusive inclusion; for example, a process, method, system, product, or server that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or devices.

[0031] Various exemplary embodiments, features, and aspects of this disclosure will now be described in detail with reference to the accompanying drawings. The same reference numerals in the drawings denote elements that have the same or similar functions. Although various aspects of the embodiments are shown in the drawings, they are not necessarily drawn to scale unless specifically indicated otherwise.

[0032] The term “exemplary” as used herein means “serving as an example, embodiment, or illustration.” Any embodiment illustrated herein as “exemplary” is not necessarily to be construed as superior to or better than other embodiments.

[0033] In this document, the term "and / or" is merely a description of the relationship between related objects, indicating that three relationships can exist. For example, A and / or B can represent three cases: A alone, A and B simultaneously, and B alone. Furthermore, the term "at least one" in this document means any combination of at least two of any one or more elements. For example, including at least one of A, B, and C can mean including any one or more elements selected from the set consisting of A, B, and C.

[0034] Furthermore, to better illustrate this disclosure, numerous specific details are set forth in the following detailed description. Those skilled in the art will understand that this disclosure can be practiced without certain specific details. In some instances, methods, means, components, and circuits well known to those skilled in the art have not been described in detail in order to highlight the main points of this disclosure.

[0035] Figure 1 This diagram illustrates a flow chart of a charging pile metering method according to an embodiment of the present disclosure, as shown below. Figure 1 As shown, this method is applied to a charging pile main control system. The charging pile main control system includes an energy metering module and multiple temperature-correlated devices. The multiple temperature-correlated devices include a power supply module. The method includes: S101. Obtain the current signal characteristic information collected by the power metering module at the current moment, the output power information corresponding to the power module, the current operating temperature data, and the error compensation model corresponding to multiple temperature-related devices. The current signal characteristic information includes current data and voltage data. The charging pile main control system also includes a control module and a temperature sampling module. The main execution body of the method in this application is the control module. The charging pile main control system embeds an energy metering module. The energy metering module and the control module are connected by communication. Multiple temperature-related devices include a sampling resistor, a power supply module, a shunt, a front-end amplifier, and an analog-to-digital converter sampling module, i.e., an ADC sampling module. The charging pile main control system also includes a resistor voltage divider module. The analog-to-digital converter sampling module is set between the control module and the DC bus. The temperature sampling module and the control module are electrically connected. The voltage signal collected and the current signal at both ends of the shunt are input to the analog sampling input port of the energy metering module through the series resistor voltage divider module.

[0036] In some embodiments, such as Figure 2 As shown, the power metering module integrates the collected voltage and current signals to obtain the output power. A pulse generator outputs a real-time pulse for power verification. In this design, when the charging pile starts charging, the power metering module communicates the collected voltage, current, and active power data with the control module MCU via SPI. The MCU simultaneously uses an ADC sampling module to sample the bus voltage and current in real time. A temperature sampling module collects the current operating temperature data. Due to the drift caused by temperature changes in resistors, shunts, and the ADC sampling module, as well as the physical deviations resulting from different power topologies, a device physical error model is established. For problems that white-box systems cannot handle, such as electromagnetic interference (EMI), aging, nonlinear coupling, high-frequency dynamic ripple, and complex load changes, a black-box residual learning model is established, ultimately fusing the output error.

[0037] The control module can use an Arm Cortex-M7 core microcontroller with a 600MHz clock speed, enabling high-speed computing. The power metering module includes a metering chip with a built-in 20-bit ADC sampling and digital signal processing unit. This chip can read voltage, current, active power, and metering signals, and output pulses. The metering chip includes, but is not limited to, an analog front-end (AFE) unit, a programmable gain amplifier (PGA), a digital signal processing (DSP) unit, a communication interface unit, and a reference voltage source.

[0038] S102. Based on current data, voltage data, current operating temperature data, error compensation models corresponding to multiple temperature-related devices, and preset digital twin models, parameter estimation processing is performed to obtain the power calibration information corresponding to the current moment. The preset digital twin model is a virtual digital twin model that is pre-constructed based on the number of power modules, rated power, operating mode, topology type, and conversion efficiency, and is consistent with the physical system structure of the charging pile's main control system. Current data, voltage data, current operating temperature data, and error compensation models corresponding to multiple temperature-related devices are input into the preset digital twin model for simulation parameter estimation processing to obtain calibrated power calibration information.

[0039] In some embodiments, based on current data, voltage data, current operating temperature data, and error compensation models corresponding to multiple temperature-related devices, a virtual digital twin model consistent with the physical system structure of the charging pile main control system is input to obtain the power. The formula is as follows:

[0040] in, The pre-defined digital twin model is a physical mechanism mapping function and is a white-box model. This is the voltage data collected at the current moment. This is the current data collected at the current moment. This is the resistance temperature drift model corresponding to the sampling resistor, i.e., the resistance data sampled at the current temperature T. This is the resistance temperature drift model corresponding to the sampling resistor. This is the high-current model corresponding to the shunt. For the digital code value corresponding to the analog-to-digital converter sampling module, This is the power module model corresponding to the power module. It is the set of calibration coefficients within the virtual digital twin model.

[0041] S103. Determine the error mirror information at the current moment based on the output power information and power calibration information at the current moment; The error mirror image at the current moment is obtained by performing a difference operation between the power module's output power information and the corresponding power calibration information at the current moment. The formula is as follows:

[0042] in, This refers to the output power information of the power module. This provides power calibration information. Error mirroring information reflects not only measurement errors, but also device aging errors, temperature drift errors, topology loss errors, and sampling link errors.

[0043] S104. Based on the error mirror information, historical state change information and preset neural network model corresponding to the current moment, perform nonlinear change processing to obtain residual prediction information. The historical state change information includes the state information corresponding to multiple moments within the target time period up to the current moment. The state information includes output power information and power calibration information. Based on the error mirror information corresponding to the current moment, historical state change information, and a preset neural network model, nonlinear change processing is performed to obtain residual prediction information, as shown in the following formula:

[0044] in, Predict residuals for black boxes; For neural network models, To preset the model parameters corresponding to the digital twin model, For error mirroring, Enter the target time period; This represents the length of the time window corresponding to the target time period.

[0045]

[0046] X(t) is the system's operating state vector at time t.

[0047] So:

[0048] For example: If k=10 and the sampling period is 1ms, then: In reality, it refers to all state changes within the last 10ms. In a virtual digital twin model, this can be defined as:

[0049] in, The output power of the physical system state. This is the power of the virtual digital twin model. Metering errors have a cumulative effect over time, rather than being instantaneous. For example, shunt temperature rise takes several seconds to accumulate, reference source model drift changes slowly with temperature, DC / DC converter operating mode switching has a transition process, and EMI interference is persistent rather than a single-point impact. Therefore, this model not only utilizes the current state but also the state sequence over the past k sampling periods to learn the evolution of errors. It can compensate for transient errors and predict slowly varying errors caused by thermal effects, power supply state changes, etc.

[0050] S105. Based on the residual prediction information, error mirror information and power calibration information, the target power value corresponding to the current moment is obtained by fusion processing. The target power value at the current moment is obtained by fusing residual prediction information, error mirror information, and power calibration information, as shown in the following formula:

[0051] Gating function:

[0052] in, For the target power value, The power calibration value in the power calibration information. These are the predicted residual values ​​from the residual prediction information. It is a dynamic gating function; This is the sensitivity coefficient; Using the Sigmoid function, an error mirror space is constructed between the physical system and the digital twin system. The error-driven black-box learning system dynamically compensates for this error, enabling the online self-evolution and self-calibration of the econometric model.

[0053] S106. Determine the target metering result for the current moment based on the target power value at the current moment and the electricity metering result at the previous moment.

[0054] The target power value at the current moment is added to the electricity metering result at the previous moment to obtain the target electricity metering result.

[0055] The above technical solution performs metering without requiring additional space on the main control board. The board's size and structure remain the same as before, integrating energy metering into the main control board. This reduces the volume occupied by the original energy meter within the charging station. Compared to the traditional single-calibration method for energy meters, this solution utilizes sampling from the main control module for dynamic metering calibration. Since the system contains multiple different samples, a unified model is established to fuse these samples. A physical mechanism of the devices is introduced to structurally model system errors, while a data-driven method is used to compensate for unmodeled nonlinear error terms, achieving a unified framework of 'interpretable modeling and adaptive correction'. This framework is more physically interpretable in the heavily regulated field of metering, rather than simply relying on data learning which cannot explain the source of errors.

[0056] In some embodiments, the plurality of temperature-correlated devices include a sampling resistor, and the error compensation model corresponding to the plurality of temperature-correlated devices includes a resistance temperature drift model corresponding to the sampling resistor. The method further includes: The resistance temperature drift model corresponding to the sampling resistor is determined based on preset standard resistance data, preset reference temperature data, and current operating temperature data. The formula is as follows:

[0057] in, To preset the nominal resistance data, This is the current operating temperature data. The preset reference temperature data is α, which is the first-order temperature coefficient, and β is the second-order temperature coefficient.

[0058] The change in resistance with temperature is not a perfect straight line, but a slightly curved parabola, and this curvature is captured by introducing a quadratic term β.

[0059] In some embodiments, the plurality of temperature-correlated devices further include a shunt, and the error compensation model corresponding to the plurality of temperature-correlated devices includes a high-current model corresponding to the shunt. The method further includes: Obtain the resistance voltage data corresponding to the sampling resistor; Based on resistance-voltage data, resistance temperature drift model, and current data, determine the high-current model corresponding to the shunt. The formula is as follows:

[0060] in, For resistance voltage data, This is a resistance temperature drift model, where I represents the current data. For current nonlinearity coefficient, This is the temperature coupling coefficient.

[0061] The shunt is not linear under high current. The high current model is as follows:

[0062] The results were:

[0063] This is to sample the voltage data across the resistor. This is the resistance temperature drift model, i.e., the sampling resistor after temperature compensation.

[0064] In some embodiments, the plurality of temperature-correlated devices further include a front-end amplifier and an analog-to-digital converter sampling module, and the error compensation model corresponding to the plurality of temperature-correlated devices includes the analog output voltage corresponding to the front-end amplifier. The method further includes: The analog output voltage corresponding to the analog-to-digital converter sampling module is determined based on voltage data and current operating temperature data, using the following formula:

[0065]

[0066]

[0067] in, To simulate the output voltage, For voltage data, Let be the gain error function. For the input offset voltage function, , This is the calibration value at room temperature. , This is the first-order temperature drift coefficient; It is the second-order temperature drift coefficient.

[0068] Voltage data represents the analog voltage signal input to the analog-to-digital converter sampling module; analog output voltage It can be used for analog front-end output voltage, gain error function This describes the relative error in gain of an operational amplifier or instrumentation amplifier caused by temperature variations. Input offset voltage function. Used to describe the additional bias voltage caused by zero-point drift and temperature drift of a device. Second-order temperature drift coefficient. Used to describe nonlinear changes over a wide temperature range.

[0069] In some embodiments, the error compensation model corresponding to multiple temperature-correlated devices includes the digital code value corresponding to the analog-to-digital converter sampling module, and the method further includes: Obtain the resolution corresponding to the sampling module of the analog-to-digital converter; The digital code value corresponding to the analog-to-digital converter sampling module is determined based on resolution, voltage data, and current operating temperature data, using the following formula:

[0070]

[0071] Where D is the digital code value and N is the resolution. As a reference voltage model, For the quantization error of the digital-to-analog converter, The preset nominal reference voltage; This is the first-order temperature drift coefficient; It is the second-order temperature drift coefficient.

[0072] Reference voltage model To account for the ADC reference voltage after temperature drift, the resolution N is the resolution of the analog-to-digital converter (ADC). The full-scale digital code value of the ADC, and the quantization error of the digital-to-analog converter. Used to describe the errors generated during the discretization of analog signals.

[0073] The above technical solution, by establishing an ADC reference voltage temperature drift model and a quantization error model, can compensate for the analog-to-digital conversion error in the white-box metering link, improve the accuracy of the analog-to-digital signal conversion process, and further enhance the accuracy of charging pile power metering.

[0074] In some embodiments, the error compensation model corresponding to the power module is a power module model corresponding to the power module, and the method further includes: Get the number of power supplies corresponding to the power module; Determine the power module model based on output power information and the number of power supplies. The formula is as follows:

[0075]

[0076] in, This provides the output power information for the power module, where n is the number of power supplies. This is a dynamic coefficient.

[0077] The topology of the power converter in a power module affects the time-domain waveform characteristics of voltage and current, introducing non-ideal factors including high-frequency ripple, phase delay, operating mode switching, and multiphase aliasing. This causes traditional metering models based on average values ​​or RMS assumptions to exhibit systematic deviations under dynamic operating conditions, resulting in a topology-dependent error term between the metering results and the actual energy transfer. Efficiency is no longer a constant but a topology-dependent function, as shown in the following formula:

[0078] in, The output power of the power module is T, and the current temperature is T. The switching frequency of the DC / DC converter. This represents the power supply operating mode, where L is the parameter of the main power inductor and C is the parameter of the output filter capacitor.

[0079] In some embodiments, the method further includes: Backpropagation is performed based on error mirror information and a preset digital twin model to obtain gradient parameter information corresponding to the adjustable parameter information in the preset digital twin model. Gradient descent optimization is performed based on gradient parameter information and a preset error threshold to obtain an updated preset digital twin model.

[0080] In some embodiments, backpropagation is performed based on error mirror information and a preset digital twin model to obtain gradient parameter information corresponding to the adjustable parameter information in the preset digital twin model, as shown in the following formula:

[0081] in, The adjustable parameter information, i.e., model parameters, is used to preset the digital twin model. For learning rate, This is an error mirror image.

[0082] In some embodiments, from time t-k1 to time t within a historical time period, the parameters of the current digital twin model are determined within the parameter range defined by device specifications and calibration results, with the objective of minimizing the weighted deviation between the measured power of different metering paths and the predicted power corresponding to the preset digital twin model. The objective function of the preset digital twin model can be expressed as:

[0083] in, Let be the currently identified twin parameters, i.e., the objective function, representing the current optimal digital twin model parameters obtained through constrained parameter identification. The physical parameter constraint space is determined by the device datasheet, factory calibration data, allowable temperature drift range and safe operating range. l is the duration of the historical time period, and K is the number of power metering paths in the charging pile main control system. For example, when there are metering chip paths and main control ADC paths, K=2. Let be the measured power of the r-th path, and let be the observed power of the r-th measurement path directly obtained at time τ. Let be the predicted power of the r-th path, and let represent the power of the corresponding path calculated by the preset digital twin model using candidate parameters θ. The credibility weight of the r-th path is dynamically determined based on path accuracy, stability, communication status, and time consistency. These are constraint coefficients for parameter changes, used to limit abrupt changes in twin parameters that do not conform to the physical laws of the device at adjacent time points. The first term of the objective function is used to reduce the overall deviation between the predicted power and the measured power of multiple metering paths, and the second term is used to constrain the magnitude of the change in the current parameter relative to the previous time point, preventing electromagnetic interference, communication anomalies, or single-point noise from causing erroneous updates to the twin model parameters. Only the temperature drift coefficient, bias parameter, and module efficiency parameter, which are classified as updatable parameters, are identified; fixed parameters such as device topology, rated resistance range, and safety threshold are not included in real-time updates.

[0084] Substitute the identified digital twin model parameters back into the digital twin model to calculate the calibrated power, as shown in the following formula:

[0085] in, Let be the calibrated power at time t. It is the system running state vector input for testing at time t.

[0086] Based on the calibrated power and the original power before calibration, calculate the additive power calibration amount and the multiplicative power calibration factor, as follows:

[0087]

[0088] in, For additive calibration, The original power before calibration. ε is a multiplicative calibration factor used to proportionally correct the output power of the metering path, and ε is a positive number set to prevent the denominator from being zero under zero power or low power conditions.

[0089] Calibration parameters can be uniformly expressed as:

[0090] Where Q_P(t) represents the calibration reliability, determined based on the residual error identified by the parameters, the number of valid metering paths, and whether the parameters are within the allowable range. In actual execution, the additive calibration amount or multiplicative calibration coefficient can be written into the MCU's software compensation parameters, depending on the calibration method supported by the target metering chip, or used to correct the final billing power.

[0091] The above technical solution uses backpropagation of model parameters to make the digital twin model continuously approximate the real physical system as errors occur.

[0092] Please see Figure 3 According to a second aspect of this disclosure, a charging pile metering device is provided, applied to a charging pile main control system. The charging pile main control system includes an energy metering module and multiple temperature-correlated devices, the multiple temperature-correlated devices including a power supply module. The device includes: Information acquisition module 10 is used to acquire the current signal characteristic information collected by the power metering module at the current moment, the output power information corresponding to the power module, the current operating temperature data, and the error compensation model corresponding to multiple temperature-related devices. The current signal characteristic information includes current data and voltage data. The white-box processing module 20 is used to perform parameter estimation processing based on current data, voltage data, current operating temperature data, error compensation models corresponding to multiple temperature-related devices, and preset digital twin models to obtain the power calibration information corresponding to the current moment. The error determination module 30 is used to determine the error mirror information corresponding to the current moment based on the output power information and the power calibration information corresponding to the current moment. The residual prediction module 40 is used to perform nonlinear change processing based on the error mirror information corresponding to the current time, historical state change information and preset neural network model to obtain residual prediction information. The historical state change information includes the state information corresponding to multiple times within the target time period up to the current time. The state information includes output power information and power calibration information. The fusion processing module 50 is used to perform fusion processing based on residual prediction information, error mirror information and power calibration information to obtain the target power value corresponding to the current moment. The metering module 60 is used to determine the target metering result for the current time based on the target power value at the current time and the electricity metering result at the previous time.

[0093] In some embodiments, the plurality of temperature-correlated devices include a sampling resistor, and the error compensation model corresponding to the plurality of temperature-correlated devices includes a resistance temperature drift model corresponding to the sampling resistor. The device further includes: The resistance temperature drift model construction module is used to determine the resistance temperature drift model corresponding to the sampling resistor based on preset standard resistance data, preset reference temperature data, and current operating temperature data. The formula is as follows:

[0094] in, To preset the nominal resistance data, This is the current operating temperature data. The preset reference temperature data is α, which is the first-order temperature coefficient, and β is the second-order temperature coefficient.

[0095] In some embodiments, the plurality of temperature-correlated devices further include a shunt, and the error compensation model corresponding to the plurality of temperature-correlated devices includes a high-current model corresponding to the shunt. The device further includes: The resistance voltage data acquisition module is used to acquire the resistance voltage data corresponding to the sampling resistor; The high-current model building module is used to determine the high-current model corresponding to the shunt based on resistance-voltage data, resistance temperature drift model, and current data. The formula is as follows:

[0096] in, For resistance voltage data, This is a resistance temperature drift model, where I represents the current data. For current nonlinearity coefficient, This is the temperature coupling coefficient.

[0097] In some embodiments, the plurality of temperature-correlated devices further include a front-end amplifier and an analog-to-digital converter sampling module, and the error compensation model corresponding to the plurality of temperature-correlated devices includes the analog output voltage corresponding to the front-end amplifier. The device further includes: The analog output voltage model building module is used to determine the analog output voltage corresponding to the analog-to-digital converter sampling module based on voltage data and current operating temperature data, as shown in the following formula:

[0098]

[0099]

[0100] in, To simulate the output voltage, For voltage data, Let be the gain error function. For the input offset voltage function, , This is the calibration value at room temperature. , This is the first-order temperature drift coefficient; It is the second-order temperature drift coefficient.

[0101] In some embodiments, the error compensation model corresponding to the plurality of temperature-correlated devices includes the digital code value corresponding to the analog-to-digital converter sampling module, and the device further includes: The resolution acquisition module is used to acquire the resolution corresponding to the analog-to-digital converter sampling module; The digital code value determination module is used to determine the digital code value corresponding to the analog-to-digital converter sampling module based on resolution, voltage data, and current operating temperature data, using the following formula:

[0102]

[0103] Where D is the digital code value and N is the resolution. As a reference voltage model, For the quantization error of the digital-to-analog converter, The preset nominal reference voltage; This is the first-order temperature drift coefficient; It is the second-order temperature drift coefficient.

[0104] In some embodiments, the error compensation model corresponding to the power module is a power module model corresponding to the power module, and the device further includes: The power supply quantity acquisition module is used to acquire the number of power supplies corresponding to the power supply module. The power module model building module is used to determine the power module model based on output power information and the number of power supplies. The formula is as follows:

[0105]

[0106] in, This provides the output power information for the power module, where n is the number of power supplies. This is a dynamic coefficient.

[0107] In some embodiments, the apparatus further includes: The backpropagation processing module is used to perform backpropagation processing based on error mirror information and a preset digital twin model to obtain gradient parameter information corresponding to the adjustable parameter information in the preset digital twin model. The optimization module is used to perform gradient descent optimization based on gradient parameter information and a preset error threshold to obtain an updated preset digital twin model.

[0108] In some embodiments, the functions or modules of the apparatus provided in this disclosure can be used to perform the methods described in the above method embodiments. The specific implementation can be referred to the description of the above method embodiments, and for the sake of brevity, it will not be repeated here.

[0109] This application provides a charging pile metering device, which can be a terminal or a server. The charging pile metering device includes a processor and a memory. The memory stores at least one instruction or at least one program. The at least one instruction or at least one program is loaded and executed by the processor to implement the charging pile metering method provided in the above method embodiments.

[0110] Memory is used to store software programs and modules. The processor executes these stored software programs and modules to perform various functional applications and data processing. Memory can primarily consist of a program storage area and a data storage area. The program storage area stores the operating system, application programs required for functionality, etc.; the data storage area stores data created based on device usage, etc. Furthermore, memory can include high-speed random access memory (RAM) and non-volatile memory, such as at least one disk storage device, flash memory device, or other volatile solid-state storage device. Accordingly, memory can also include a memory controller to provide the processor with access to the memory.

[0111] The methods and embodiments provided in this application can be executed in electronic devices such as mobile terminals, computer terminals, servers, or similar computing devices. Figure 4 This is a hardware structure block diagram of an electronic device for a charging pile metering method provided in an embodiment of this application. For example... Figure 4 As shown, the electronic device 900 can vary considerably due to differences in configuration or performance. It may include one or more Central Processing Units (CPUs) 910 (CPUs 910 may include, but are not limited to, microprocessors such as MCUs or programmable logic devices such as FPGAs), a memory 930 for storing data, and one or more storage media 920 (e.g., one or more mass storage devices) for storing application programs 923 or data 922. The memory 930 and storage media 920 may be temporary or persistent storage. The program stored in the storage media 920 may include one or more modules, each module may include a series of instruction operations on the electronic device. Furthermore, the CPU 910 may be configured to communicate with the storage media 920 and execute the series of instruction operations in the storage media 920 on the electronic device 900. Electronic device 900 may also include one or more power supplies 960, one or more wired or wireless network interfaces 950, one or more input / output interfaces 940, and / or one or more operating systems 921, such as Windows Server™, Mac OS X™, Unix™, Linux™, FreeBSD™, etc.

[0112] The input / output interface 940 can be used to receive or send data via a network. Specific examples of the network described above may include a wireless network provided by the communication provider of the electronic device 900. In one example, the input / output interface 940 includes a network interface controller (NIC), which can connect to other network devices via a base station to communicate with the Internet. In another example, the input / output interface 940 may be a radio frequency (RF) module used for wireless communication with the Internet.

[0113] Those skilled in the art will understand that Figure 4 The structure shown is for illustrative purposes only and does not limit the structure of the electronic device described above. For example, the electronic device 900 may also include... Figure 4 The more or fewer components shown, or having the same Figure 4 The different configurations shown.

[0114] Embodiments of this application also provide a computer-readable storage medium, which can be disposed in an electronic device to store at least one instruction or at least one program related to implementing a charging pile metering method in the method embodiment. The at least one instruction or the at least one program is loaded and executed by the processor to implement the charging pile metering method provided in the above method embodiment.

[0115] Optionally, in this embodiment, the storage medium may be located at at least one of the multiple network servers in a computer network. Optionally, in this embodiment, the storage medium may include, but is not limited to, various media capable of storing program code, such as USB flash drives, read-only memory (ROM), random access memory (RAM), portable hard drives, magnetic disks, or optical disks.

[0116] According to one aspect of this application, a computer program product or computer program is provided, comprising computer instructions stored in a computer-readable storage medium. A processor of a computer device reads the computer instructions from the computer-readable storage medium and executes the computer instructions, causing the computer device to perform the methods provided in the various alternative implementations described above.

[0117] As can be seen from the embodiments of the charging pile metering method, device, equipment, terminal, server, storage medium, or computer program provided in this application, this application reduces the size of the charging pile by embedding an energy metering module within the charging pile main control system; by performing parameter estimation processing on current data, voltage data, current operating temperature data, error compensation models corresponding to multiple temperature-related devices, and a preset digital twin model, the power calibration information corresponding to the current moment is obtained, and a digital twin model corresponding to the physical metering system is constructed to realize a bidirectional mapping between the physical system and the virtual system. Error mirror information corresponding to the current moment is determined based on the output power information and power calibration information corresponding to the current moment; an error mirror model is constructed based on the difference between the outputs of the physical system and the virtual system, establishing a real-time, bidirectional, closed-loop data channel between the physical system and the virtual system. By performing nonlinear transformation processing based on the error mirror information corresponding to the current moment, historical state change information, and a preset neural network model, residual prediction information is obtained. Historical state change information includes state information corresponding to multiple moments within the target time period up to the current moment, including output power information and power calibration information. A black-box learning method is used to model the dynamic evolution of the error, which can compensate for transient errors and predict slowly varying errors caused by thermal effects, power state changes, etc. The residual prediction information, error mirror information, and power calibration information are fused to obtain the target power value corresponding to the current moment. Based on the target power value corresponding to the current moment and the electricity metering result corresponding to the previous moment, the target metering result corresponding to the current moment is determined. The detected metering results are corrected, achieving high-precision modeling and robustness improvement of the charging pile metering system under complex operating conditions.

[0118] It should be noted that the order of the embodiments described above is merely for descriptive purposes and does not represent the superiority or inferiority of the embodiments. Furthermore, the above description focuses on specific embodiments of this application. Other embodiments are within the scope of the appended claims. In some cases, the actions or steps described in the claims can be performed in a different order than that shown in the embodiments and still achieve the desired results. Additionally, the processes depicted in the drawings do not necessarily require a specific or sequential order to achieve the desired results. In some implementations, multitasking and parallel processing are also possible or may be advantageous.

[0119] The various embodiments in this application are described in a progressive manner. Similar or identical parts between embodiments can be referred to mutually. Each embodiment focuses on describing the differences from other embodiments. In particular, the device, equipment, and storage medium embodiments are basically similar to the method embodiments, so the descriptions are relatively simple; relevant parts can be referred to the descriptions of the method embodiments.

[0120] Those skilled in the art will understand that all or part of the steps of the above embodiments can be implemented by hardware, or by a program instructing the relevant hardware to implement them. The program can be stored in a computer-readable storage medium, such as a read-only memory, a disk, or an optical disk.

[0121] The above description is only a preferred embodiment of this application and is not intended to limit this application. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of this application should be included within the protection scope of this application.

Claims

1. A metering method for charging piles, characterized in that, The method is applied to a charging pile main control system, the charging pile main control system including an energy metering module and multiple temperature correlation devices, the multiple temperature correlation devices including a power supply module, the method comprising: The current signal feature information collected by the power metering module at the current moment, the output power information corresponding to the power module, the current operating temperature data, and the error compensation model corresponding to the multiple temperature-related devices are obtained. The current signal feature information includes current data and voltage data. Based on the current data, voltage data, current operating temperature data, error compensation models corresponding to the multiple temperature-related devices, and the preset digital twin model corresponding to the charging pile main control system, parameter estimation processing is performed to obtain the power calibration information corresponding to the current moment. The error mirror information corresponding to the current moment is determined based on the output power information and the power calibration information corresponding to the current moment. Based on the error mirror information, historical state change information and preset neural network model corresponding to the current moment, nonlinear change processing is performed to obtain residual prediction information. The historical state change information includes state information corresponding to multiple moments within the target time period up to the current moment. The state information includes output power information and power calibration information. Based on the fusion processing of the residual prediction information, the error mirror information and the power calibration information, the target power value corresponding to the current moment is obtained; The target metering result for the current moment is determined based on the target power value at the current moment and the electricity metering result at the previous moment.

2. The method according to claim 1, characterized in that, The plurality of temperature-correlated devices include a sampling resistor, and the error compensation model corresponding to the plurality of temperature-correlated devices includes a resistance temperature drift model corresponding to the sampling resistor. The method further includes: Based on preset standard resistance data, preset reference temperature data, and the current operating temperature data, the resistance temperature drift model corresponding to the sampling resistor is determined. The formula is as follows: in, To preset the nominal resistance data, This is the current operating temperature data. The preset reference temperature data is α, which is the first-order temperature coefficient, and β is the second-order temperature coefficient.

3. The method according to claim 2, characterized in that, The multiple temperature-correlated devices also include a shunt, and the error compensation model corresponding to the multiple temperature-correlated devices includes a high-current model corresponding to the shunt. The method further includes: Obtain the resistance voltage data corresponding to the sampling resistor; Based on the resistance voltage data, the resistance temperature drift model, and the current data, the high-current model corresponding to the shunt is determined. The formula is as follows: in, For resistance voltage data, This is a resistance temperature drift model, where I represents the current data. For current nonlinearity coefficient, This is the temperature coupling coefficient.

4. The method according to claim 1, characterized in that, The plurality of temperature-correlated devices further include a front-end amplifier and an analog-to-digital converter sampling module. The error compensation model corresponding to the plurality of temperature-correlated devices includes the analog output voltage corresponding to the front-end amplifier. The method further includes: The analog output voltage corresponding to the analog-to-digital converter sampling module is determined based on the voltage data and the current operating temperature data, using the following formula: in, To simulate the output voltage, For voltage data, Let be the gain error function. For the input offset voltage function, , This is the calibration value at room temperature. , This is the first-order temperature drift coefficient; It is the second-order temperature drift coefficient.

5. The method according to claim 4, characterized in that, The error compensation model corresponding to the multiple temperature-correlated devices includes the digital code value corresponding to the analog-to-digital converter sampling module, and the method further includes: Obtain the resolution corresponding to the analog-to-digital converter sampling module; The digital code value corresponding to the analog-to-digital converter sampling module is determined based on the resolution, the voltage data, and the current operating temperature data, using the following formula: Where D is the digital code value and N is the resolution. As a reference voltage model, For the quantization error of the digital-to-analog converter, The preset nominal reference voltage; This is the first-order temperature drift coefficient; It is the second-order temperature drift coefficient.

6. The method according to claim 1, characterized in that, The error compensation model corresponding to the power module is the power module model corresponding to the power module, and the method further includes: Obtain the number of power supplies corresponding to the power module; The power module model is determined based on the output power information and the number of power supplies. The formula is as follows: in, This provides the output power information for the power module, where n is the number of power supplies. This is a dynamic coefficient.

7. The method according to claim 1, characterized in that, The method further includes: Backpropagation is performed based on the error mirror information and the preset digital twin model to obtain the gradient parameter information corresponding to the adjustable parameter information in the preset digital twin model. Based on the gradient parameter information and the preset error threshold, gradient descent optimization is performed to obtain the updated preset digital twin model.

8. A charging pile metering device, characterized in that, An application is made in a charging pile main control system, the charging pile main control system including an energy metering module and multiple temperature correlation devices, the multiple temperature correlation devices including a power supply module, the device comprising: The information acquisition module is used to acquire the current signal feature information collected by the power metering module at the current moment, the output power information corresponding to the power supply module, the current operating temperature data, and the error compensation model corresponding to the multiple temperature-related devices. The current signal feature information includes current data and voltage data. The white-box processing module is used to perform parameter estimation processing based on the current data, the voltage data, the current operating temperature data, the error compensation models corresponding to the multiple temperature-related devices, and the preset digital twin model corresponding to the charging pile main control system, to obtain the power calibration information corresponding to the current moment. An error determination module is used to determine the error mirror information corresponding to the current time based on the output power information and the power calibration information corresponding to the current time. The residual prediction module is used to perform nonlinear change processing based on the error mirror information, historical state change information and preset neural network model corresponding to the current time to obtain residual prediction information. The historical state change information includes state information corresponding to multiple times within the target time period up to the current time. The state information includes output power information and power calibration information. The fusion processing module is used to perform fusion processing based on the residual prediction information, the error mirror information and the power calibration information to obtain the target power value corresponding to the current moment. The metering module is used to determine the target metering result corresponding to the current time based on the target power value corresponding to the current time and the electricity metering result corresponding to the previous time.

9. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores at least one instruction or at least one program, which is loaded and executed by a processor to implement the charging pile metering method as described in any one of claims 1-7.

10. An electronic device, characterized in that, It includes at least one processor and a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor, and the at least one processor implements the charging pile metering method as described in any one of claims 1-7 by executing the instructions stored in the memory.

Images