CN-121997059-A - V2G charge-discharge data self-adaptive calibration method and system for super-charge station

CN121997059ACN 121997059 ACN121997059 ACN 121997059ACN-121997059-A

Abstract

The invention discloses a V2G charge and discharge data self-adaptive calibration method and system for a super-charge station, and relates to the field of electric vehicle interaction. The method comprises the steps of S1, obtaining electric measurement data, generating a battery state observation reference through an independent physical model algorithm, calculating a physical consistency score by combining vehicle state parameters, S2, calculating original credibility and process credibility based on a comparison result of the electric measurement data and the battery state observation reference, S3, fusing the original credibility, the process credibility and the physical consistency score, dynamically evolving by combining historical credibility record of a data source to generate a dynamic maturity parameter, and S4, mapping a corresponding data correction algorithm from a strategy set according to the dynamic maturity parameter, adaptively correcting preset charge and discharge key data and outputting a calibration result. And a closed-loop treatment system is constructed through independent observation reference and dynamic evolution of data credit, so that the credibility guarantee and self-adaptive accurate calibration of the V2G data source are realized.

Inventors

WANG LU
FENG GUIQING
ZHANG XINYONG
WANG WENRUI
HUANG XIAOHUI
XU DI

Assignees

深能源(深圳)创新技术有限公司
深能南京能源控股有限公司
南京赫曦电气有限公司

Dates

Publication Date: 20260508
Application Date: 20251205

Claims (10)

1. The V2G charge-discharge data self-adaptive calibration method for the super-charge station is characterized by comprising the following steps of: S1, acquiring electrical measurement data in real time by utilizing an intelligent ammeter, generating a battery state observation reference through an independent physical model and a state estimation algorithm, and calculating a physical consistency score by combining vehicle state parameters uploaded by a vehicle end; s2, calculating the original credibility and the process credibility based on a comparison result of the electrical measurement data and the battery state observation reference; S3, merging the original credibility, the process credibility and the physical consistency score, and dynamically evolving by combining the historical credibility record of the data source to generate a dynamic maturity parameter; And S4, mapping a corresponding data correction algorithm from a preset strategy set according to the dynamic maturity parameters, carrying out self-adaptive correction on preset charge and discharge key data, and outputting a calibration result with a confidence label.
2. The self-adaptive calibration method for the V2G charge and discharge data of the super-charging station according to claim 1, wherein the S1 comprises a data acquisition step, a state observation step and a consistency calculation step; the data acquisition step comprises the following steps: acquiring a vehicle identifier, a time stamp, transmission delay metadata, a state of charge, total voltage, total current, battery temperature and a battery health value reported by a vehicle battery management system, and constructing vehicle state parameters; and synchronously acquiring electric measurement data including current, voltage, accumulated electric energy, power and power factor by utilizing an intelligent ammeter arranged in the charging pile in real time.
3. The method for adaptively calibrating V2G charge-discharge data for a super-charging station according to claim 2, wherein the state observing step comprises: According to the vehicle identification, obtaining an open-circuit voltage-state-of-charge mapping relation and a nominal capacity of a corresponding vehicle model from a preset battery parameter database; Determining a first state of charge reference point based on voltage data and an open circuit voltage-state of charge mapping in the electrical measurement data during a vehicle rest phase; integrating current data in the electrical measurement data in a charge-discharge stage, and generating a first independent state-of-charge sequence by combining a first state-of-charge reference point and a nominal capacity; Based on the electrical measurement data, estimating a second independent state of charge value and a battery internal resistance value in real time by taking current data as input and voltage data as an observation value and utilizing a battery equivalent circuit model and a state observer; estimating a battery state of health value based on the amount of change in the first independent state of charge sequence and the second independent state of charge value, as compared to a nominal capacity; And combining the second independent state of charge value, the battery internal resistance value and the battery state of health value to jointly construct a battery state observation reference.
4. The method for adaptively calibrating V2G charge-discharge data for a super-charging station according to claim 3, wherein the step of calculating the consistency comprises: Based on the state of charge and the battery state of health value in the vehicle state parameter, a physical consistency score is calculated in combination with the second independent state of charge value and the battery state of health value in the battery state observation reference.
5. The method for adaptively calibrating the charging and discharging data of the V2G facing the super-charging station according to claim 1, wherein the step S2 comprises an original credibility calculation step and a process credibility calculation step; the original credibility calculating step comprises the following steps: Acquiring vehicle identification, a time stamp and transmission delay metadata contained in the vehicle state parameters; Inquiring a preset equipment quality file according to the vehicle identification to obtain a corresponding initial source quality score; calculating the freshness score of the data according to the time stamp and the transmission delay metadata; In a preset time alignment window, respectively carrying out consistency comparison on the total current and the total voltage in the vehicle state parameters and the current and the voltage at corresponding time points in the electric measurement data, marking conflict when the difference value exceeds a preset conflict threshold value, and evaluating the conflict severity according to the difference value; and fusing the evaluation results of the initial source quality score, the freshness score and the conflict severity to generate the original credibility of the electric measurement data and the vehicle state parameters.
6. The method for adaptively calibrating V2G charge-discharge data for a super-charging station according to claim 5, wherein said process reliability calculation step comprises: organizing the electric measurement data attached with the original credibility tag and the vehicle state parameters into time sequence data fragments according to time sequence; normalizing the time sequence data segments, and inputting the time sequence data segments into a pre-trained space-time feature extraction network to obtain high-dimensional feature vectors; inputting the high-dimensional feature vector to a pre-trained normal behavior self-encoder, calculating a reconstruction error of the high-dimensional feature vector, and normalizing the reconstruction error into an error score; performing weighted fusion based on the original credibility and the error score to generate process credibility; And outputting a process abnormality identification when the process reliability is lower than a preset process threshold.
7. The method for adaptively calibrating V2G charge-discharge data for a super-charging station according to claim 1, wherein S3 comprises: obtaining an original credibility, a process credibility and a physical consistency score; inquiring the historical credibility record of the data source in the local file according to the vehicle identification in the vehicle state parameters; According to a preset fusion rule and a historical credibility record, carrying out weighted fusion and dynamic adjustment on the original credibility, the process credibility and the physical consistency score to generate a dynamic maturity parameter candidate value of the current period; determining the maximum allowable variation amplitude of the current evolution according to the data source stability index in the historical credibility record; And calculating the variation amplitude between the dynamic maturity parameter of the previous period and the dynamic maturity parameter candidate value of the current period, and restricting the variation amplitude according to the maximum allowable variation amplitude to generate the final dynamic maturity parameter.
8. The method for adaptively calibrating the V2G charge-discharge data of the super-charging station according to claim 1, wherein the preset charge-discharge key data comprises a state of charge, a total voltage, a total current and a battery health value in vehicle state parameters.
9. The method for adaptively calibrating V2G charge-discharge data for a super-charging station according to claim 8, wherein S4 comprises: inquiring a preset calibration strategy mapping table according to the dynamic maturity parameters, and determining a corresponding target data correction algorithm and a confidence coefficient generation rule; Correcting the state of charge, the total voltage, the total current and the battery health value in the vehicle state parameters by adopting a target data correction algorithm to generate calibrated data; And generating a confidence label corresponding to the calibrated data according to the confidence generation rule and the dynamic maturity parameter.
10. A V2G charge-discharge data adaptive calibration system for a super-charging station, configured to implement a V2G charge-discharge data adaptive calibration method for a super-charging station according to any one of claims 1 to 9, comprising: The observation and verification module is used for acquiring electrical measurement data in real time by utilizing the intelligent ammeter, generating a battery state observation reference through an independent physical model and a state estimation algorithm, and calculating a physical consistency score by combining vehicle state parameters uploaded by a vehicle end; The credibility evaluation module is used for calculating the original credibility and the process credibility based on the comparison result of the electric measurement data and the battery state observation reference; the credit evolution module is used for fusing the original credibility, the process credibility and the physical consistency score, and generating dynamic maturity parameters by combining the dynamic evolution of the historical credibility record of the data source; And the calibration execution module is used for mapping a corresponding data correction algorithm from a preset strategy set according to the dynamic maturity parameters, carrying out self-adaptive correction on preset charge and discharge key data, and outputting a calibration result with a confidence label.

Description

V2G charge-discharge data self-adaptive calibration method and system for super-charge station Technical Field The invention relates to the field of electric vehicle interaction, in particular to a V2G charge-discharge data self-adaptive calibration method and system for a super-charge station. Background With the rapid development of electric vehicles and super-charging stations, vehicle-to-power grid technologies, namely V2G and V2G technologies, become key means for realizing flexible interaction of power grids and the consumption of renewable energy sources. In the operation of the super-charging station, the charging and discharging states of the vehicle battery are accurately and reliably monitored and metered, and the method is a basis for guaranteeing safe interaction, fair transaction and battery health management of the vehicle network in the V2G mode. At present, the acquisition of related data mainly depends on the reported data of a vehicle battery management system and the metering data of a charging pile. However, in actual operation, the estimation algorithm and sensor accuracy of the vehicle battery management system are different according to the vehicle type and the use state, and the reported battery state data has inherent uncertainty and opacity. Meanwhile, although the metering data of the charging pile is used as a trade settlement basis, the real state inside the battery is difficult to independently verify. Under the complex dynamic working conditions of frequent, rapid and bidirectional power interaction of V2G, the problems of inconsistency and incoordination easily occur among the multi-source data, and the traditional calibration method based on a fixed model or a single data source is difficult to dynamically adapt to the influences of equipment performance attenuation, environmental interference and diversified battery characteristics, so that the precision and reliability of the super-charging station as a distributed flexible resource to participate in power grid regulation are restricted. Therefore, how to realize adaptive and trusted calibration of multi-source heterogeneous charge and discharge data in a V2G scene has become a technical problem to be solved in the art. Disclosure of Invention Based on the above-mentioned shortcomings of the prior art, the present invention aims to provide a method and a system for adaptively calibrating V2G charge-discharge data for a super-charging station, so as to solve the above-mentioned technical problems. In order to achieve the purpose, the invention provides the following technical scheme that the V2G charge-discharge data self-adaptive calibration method for the super-charge station comprises the following steps: S1, acquiring electrical measurement data in real time by utilizing an intelligent ammeter, generating a battery state observation reference through an independent physical model and a state estimation algorithm, and calculating a physical consistency score by combining vehicle state parameters uploaded by a vehicle end; s2, calculating the original credibility and the process credibility based on a comparison result of the electrical measurement data and the battery state observation reference; S3, merging the original credibility, the process credibility and the physical consistency score, and dynamically evolving by combining the historical credibility record of the data source to generate a dynamic maturity parameter; And S4, mapping a corresponding data correction algorithm from a preset strategy set according to the dynamic maturity parameters, carrying out self-adaptive correction on preset charge and discharge key data, and outputting a calibration result with a confidence label. The invention further provides that the S1 comprises a data acquisition step, a state observation step and a consistency calculation step; the data acquisition step comprises the following steps: acquiring a vehicle identifier, a time stamp, transmission delay metadata, a state of charge, total voltage, total current, battery temperature and a battery health value reported by a vehicle battery management system, and constructing vehicle state parameters; and synchronously acquiring electric measurement data including current, voltage, accumulated electric energy, power and power factor by utilizing an intelligent ammeter arranged in the charging pile in real time. The present invention is further configured such that the state observing step includes: According to the vehicle identification, obtaining an open-circuit voltage-state-of-charge mapping relation and a nominal capacity of a corresponding vehicle model from a preset battery parameter database; Determining a first state of charge reference point based on voltage data and an open circuit voltage-state of charge mapping in the electrical measurement data during a vehicle rest phase; integrating current data in the electrical measurement data in a charge-discharge stage, and gene