CN115524655B - Residual electric quantity prediction calibration method of energy storage battery - Google Patents
Residual electric quantity prediction calibration method of energy storage battery Download PDFInfo
- Publication number
- CN115524655B CN115524655B CN202211262390.0A CN202211262390A CN115524655B CN 115524655 B CN115524655 B CN 115524655B CN 202211262390 A CN202211262390 A CN 202211262390A CN 115524655 B CN115524655 B CN 115524655B
- Authority
- CN
- China
- Prior art keywords
- energy storage
- storage battery
- electric quantity
- residual electric
- temperature
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 238000004146 energy storage Methods 0.000 title claims abstract description 72
- 238000000034 method Methods 0.000 title claims abstract description 20
- 238000013528 artificial neural network Methods 0.000 claims abstract description 29
- 238000012549 training Methods 0.000 claims abstract description 11
- 238000012360 testing method Methods 0.000 claims description 22
- 238000003062 neural network model Methods 0.000 claims description 13
- 238000013527 convolutional neural network Methods 0.000 claims description 2
- 238000012986 modification Methods 0.000 description 3
- 230000004048 modification Effects 0.000 description 3
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000004891 communication Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01R—MEASURING ELECTRIC VARIABLES; MEASURING MAGNETIC VARIABLES
- G01R35/00—Testing or calibrating of apparatus covered by the other groups of this subclass
- G01R35/005—Calibrating; Standards or reference devices, e.g. voltage or resistance standards, "golden" references
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01R—MEASURING ELECTRIC VARIABLES; MEASURING MAGNETIC VARIABLES
- G01R31/00—Arrangements for testing electric properties; Arrangements for locating electric faults; Arrangements for electrical testing characterised by what is being tested not provided for elsewhere
- G01R31/36—Arrangements for testing, measuring or monitoring the electrical condition of accumulators or electric batteries, e.g. capacity or state of charge [SoC]
- G01R31/367—Software therefor, e.g. for battery testing using modelling or look-up tables
Landscapes
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Charge And Discharge Circuits For Batteries Or The Like (AREA)
Abstract
The application discloses a residual electric quantity prediction calibration method of an energy storage battery, which comprises the following steps: s1, collecting multiple groups of state data of an energy storage battery; s2, constructing a neural network prediction model, and training to obtain a mature neural network prediction model; s3, obtaining a residual electric quantity predicted value at a standard temperature; s4, obtaining N residual electric quantity predicted values at different temperatures; s5, generating a temperature ratio table, and storing N different temperatures and corresponding ratios thereof; s6, when the residual electric quantity of the energy storage battery is unknown, the predicted value of the residual electric quantity is calibrated based on the measured ambient temperature and the predicted value of the residual electric quantity. According to the application, the influence of the temperature is considered, and the predicted residual electric quantity is calibrated, so that the residual electric quantity can be more approximate to a true value at the standard temperature, and the prediction accuracy of the residual electric quantity is improved.
Description
Technical Field
The present application relates to an energy storage battery, and more particularly, to a method for predicting and calibrating a remaining power of an energy storage battery.
Background
The residual capacity SOC (State Of Charge) Of the energy storage battery is a core parameter Of the whole battery system, and determining the residual capacity Of the battery can realize reasonable use Of the battery pack, prevent the battery pack from being overcharged and overdischarged, reduce the occurrence probability Of battery faults, improve the service life Of the battery pack and prolong the endurance capacity Of the battery;
in general, although the residual capacity of the energy storage battery can be directly tested, the energy storage battery is distributed and applied to various fields, such as new energy automobiles, communication base stations and the like, and is difficult to test in each application scene by using professional test equipment, so that the estimation is generally performed according to the acquired data after the parameters of the energy storage battery are acquired, but when the parameters of the energy storage battery are acquired, the acquired parameters have larger errors due to the influence of temperature, so that the predicted residual capacity and the actual electric quantity have larger errors, and the accurate estimation of the energy storage battery is not facilitated.
Disclosure of Invention
The application aims to overcome the defects of the prior art and provides a method for predicting and calibrating the residual electric quantity of an energy storage battery, which is used for calibrating the predicted residual electric quantity by considering the influence of temperature, so that the residual electric quantity can be more similar to a true value at a standard temperature, and the prediction accuracy of the residual electric quantity is improved.
The aim of the application is realized by the following technical scheme: a residual electric quantity prediction calibration method of an energy storage battery comprises the following steps:
s1, collecting a plurality of groups of state data of an energy storage battery, wherein each group of state data comprises the residual electric quantity, current, voltage and surface pressure of the energy storage battery;
s2, constructing a neural network prediction model, and training the neural network prediction model by using acquired data to obtain a mature neural network prediction model;
s3, setting a standard temperature T, setting an energy storage battery in a closed test space, adjusting the temperature in the test space to be a test temperature, collecting the current and the voltage of the energy storage battery and the surface pressure of the surface of the energy storage battery, and inputting the current and the voltage and the surface pressure of the surface of the energy storage battery into a mature neural network model to obtain a residual electric quantity predicted value at the standard temperature;
s4, adjusting the temperature value in the test control, enabling the actual residual electric quantity of the energy storage battery to be consistent with the actual residual electric quantity of the energy storage battery in the standard temperature test, collecting the current and the voltage of the energy storage battery and the surface pressure of the surface of the energy storage battery at N different temperatures, and inputting the current and the voltage and the surface pressure of the surface of the energy storage battery into a mature neural network model to obtain N residual electric quantity predicted values at different temperatures, wherein N is an even number;
s5, carrying out ratio operation on the residual electric quantity predicted value at the standard temperature and the N residual electric quantity predicted values at different temperatures respectively to obtain N ratios at different temperatures, generating a temperature ratio table, and storing the N different temperatures and the corresponding ratios thereof;
s6, when the residual electric quantity of the energy storage battery is unknown, testing the current, the voltage and the surface pressure of the energy storage battery, testing the temperature of the environment where the energy storage battery is located, inputting the current, the voltage and the surface pressure of the energy storage battery into a neural network prediction model to obtain a predicted value of the residual electric quantity, and calibrating based on the measured environment temperature and the predicted value of the residual electric quantity.
The beneficial effects of the application are as follows: according to the application, the neural network model is constructed and trained by collecting multiple groups of state data of the energy storage battery, the residual capacity of the energy storage battery is predicted based on the neural network obtained by training, and the predicted residual capacity is calibrated by considering the influence of temperature, so that the residual capacity can be more similar to a true value at a standard temperature, and the prediction accuracy of the residual capacity is improved.
Drawings
FIG. 1 is a flow chart of the method of the present application.
Detailed Description
The technical solution of the present application will be described in further detail with reference to the accompanying drawings, but the scope of the present application is not limited to the following description.
As shown in fig. 1, a method for predicting and calibrating the residual electric quantity of an energy storage battery includes the following steps:
s1, collecting a plurality of groups of state data of an energy storage battery, wherein each group of state data comprises the residual electric quantity, current, voltage and surface pressure of the energy storage battery;
s2, constructing a neural network prediction model, and training the neural network prediction model by using acquired data to obtain a mature neural network prediction model;
s3, setting a standard temperature T, setting an energy storage battery in a closed test space, adjusting the temperature in the test space to be a test temperature, collecting the current and the voltage of the energy storage battery and the surface pressure of the surface of the energy storage battery, and inputting the current and the voltage and the surface pressure of the surface of the energy storage battery into a mature neural network model to obtain a residual electric quantity predicted value at the standard temperature;
s4, adjusting the temperature value in the test control, enabling the actual residual electric quantity of the energy storage battery to be consistent with the actual residual electric quantity of the energy storage battery in the standard temperature test, collecting the current and the voltage of the energy storage battery and the surface pressure of the surface of the energy storage battery at N different temperatures, and inputting the current and the voltage and the surface pressure of the surface of the energy storage battery into a mature neural network model to obtain N residual electric quantity predicted values at different temperatures, wherein N is an even number;
s5, carrying out ratio operation on the residual electric quantity predicted value at the standard temperature and the N residual electric quantity predicted values at different temperatures respectively to obtain N ratios at different temperatures, generating a temperature ratio table, and storing the N different temperatures and the corresponding ratios thereof;
s6, when the residual electric quantity of the energy storage battery is unknown, testing the current, the voltage and the surface pressure of the energy storage battery, testing the temperature of the environment where the energy storage battery is located, inputting the current, the voltage and the surface pressure of the energy storage battery into a neural network prediction model to obtain a predicted value of the residual electric quantity, and calibrating based on the measured environment temperature and the predicted value of the residual electric quantity.
In an embodiment of the present application, the neural network prediction model in the step S2 is one of a CNN neural network model, an RNN neural network model, or an RBF neural network model.
Wherein, the step S2 includes:
s101, when training a neural network prediction model by utilizing any group of state data, taking the current, the electric quantity and the surface pressure of an energy storage battery of the group of state data as the input of the neural network prediction model, and taking the residual electric quantity of the energy storage battery of the group of data as the expected output of the neural network prediction model so as to realize the training of the neural network prediction model;
s102, repeatedly executing the step S101 for each group of state data, and marking the neural network prediction model at the moment as a mature neural network prediction model after training of each group of data is finished.
In the embodiment of the application, the N different temperatures are uniformly distributed around the temperature T: let the standard temperature be T, given the temperature interval be T, then N different temperatures are respectively: T-Nt/2, …, T-2T, T-T, T+t, T+2t, …, T+Nt/2.
In the embodiment of the present application, the calibration method for the predicted value of the remaining power in step S6 is as follows:
searching a temperature value which has the smallest difference with the measured ambient temperature from N temperatures in the temperature ratio table as a calibration temperature;
searching a ratio corresponding to the calibration temperature from a temperature ratio table, and then calibrating a predicted value of the residual electric quantity by using the ratio: the predicted value of the residual electric quantity is multiplied by the found ratio to be used as the calibrated predicted value of the residual electric quantity.
The residual electric quantity predicted value is converted into the predicted value at the standard temperature to finish calibration, so that errors caused by the change of the measured energy storage battery parameters can be avoided when the temperature is changed, the prediction accuracy can be improved, and the calibrated residual electric quantity predicted value can be directly used as the basis for charge and discharge control and switching.
While the foregoing description illustrates and describes a preferred embodiment of the present application, it is to be understood that the application is not limited to the form disclosed herein, but is not to be construed as limited to other embodiments, but is capable of use in various other combinations, modifications and environments and is capable of changes or modifications within the spirit of the application described herein, either as a result of the foregoing teachings or as a result of the knowledge or skill of the relevant art. And that modifications and variations which do not depart from the spirit and scope of the application are intended to be within the scope of the appended claims.
Claims (5)
1. A residual electric quantity prediction calibration method of an energy storage battery is characterized by comprising the following steps of: the method comprises the following steps:
s1, collecting a plurality of groups of state data of an energy storage battery, wherein each group of state data comprises the residual electric quantity, current, voltage and surface pressure of the energy storage battery;
s2, constructing a neural network prediction model, and training the neural network prediction model by using acquired data to obtain a mature neural network prediction model;
s3, setting a standard temperature T, setting an energy storage battery in a closed test space, adjusting the temperature in the test space to be the standard temperature, collecting the current and the voltage of the energy storage battery and the surface pressure of the surface of the energy storage battery, and inputting the current and the voltage and the surface pressure of the surface of the energy storage battery into a mature neural network model to obtain a residual electric quantity predicted value at the standard temperature;
s4, adjusting the temperature value in the test space, enabling the actual residual electric quantity of the energy storage battery to be consistent with the standard temperature in the test, collecting the current and the voltage of the energy storage battery and the surface pressure of the surface of the energy storage battery at N different temperatures, and inputting the current and the voltage and the surface pressure of the surface of the energy storage battery into a mature neural network model to obtain N residual electric quantity predicted values at different temperatures, wherein N is an even number;
s5, carrying out ratio operation on the residual electric quantity predicted value at the standard temperature and the N residual electric quantity predicted values at different temperatures respectively to obtain N ratios at different temperatures, generating a temperature ratio table, and storing the N different temperatures and the corresponding ratios thereof;
s6, when the residual electric quantity of the energy storage battery is unknown, testing the current, the voltage and the surface pressure of the energy storage battery, testing the temperature of the environment where the energy storage battery is located, inputting the current, the voltage and the surface pressure of the energy storage battery into a neural network prediction model to obtain a predicted value of the residual electric quantity, and calibrating the predicted value of the residual electric quantity based on the measured environment temperature.
2. The method for predicting and calibrating the residual capacity of an energy storage battery according to claim 1, wherein the method comprises the following steps: the neural network prediction model in the step S2 is one of a CNN neural network model, an RNN neural network model, or an RBF neural network model.
3. The method for predicting and calibrating the residual capacity of an energy storage battery according to claim 2, wherein the method comprises the following steps: the step S2 includes:
s101, when training a neural network prediction model by utilizing any group of state data, taking the current, the voltage and the surface pressure of an energy storage battery of the group of state data as the input of the neural network prediction model, and taking the residual electric quantity of the energy storage battery of the group of data as the expected output of the neural network prediction model so as to realize the training of the neural network prediction model;
s102, repeatedly executing the step S101 for each group of state data, and marking the neural network prediction model at the moment as a mature neural network prediction model after training of each group of data is finished.
4. The method for predicting and calibrating the residual capacity of an energy storage battery according to claim 1, wherein the method comprises the following steps: the N different temperatures are uniformly distributed by taking the temperature T as the center: let the standard temperature be T, given the temperature interval be T, then N different temperatures are respectively: T-Nt/2, …, T-2T, T-T, T+t, T+2t, …, T+Nt/2.
5. The method for predicting and calibrating the residual capacity of an energy storage battery according to claim 1, wherein the method comprises the following steps: the calibration method for the predicted value of the residual electric quantity in the step S6 is as follows:
searching a temperature value which has the smallest difference with the measured ambient temperature from N temperatures in the temperature ratio table as a calibration temperature;
searching a ratio corresponding to the calibration temperature from a temperature ratio table, and then calibrating a predicted value of the residual electric quantity by using the ratio: the predicted value of the residual electric quantity is multiplied by the found ratio to be used as the calibrated predicted value of the residual electric quantity.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211262390.0A CN115524655B (en) | 2022-10-14 | 2022-10-14 | Residual electric quantity prediction calibration method of energy storage battery |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211262390.0A CN115524655B (en) | 2022-10-14 | 2022-10-14 | Residual electric quantity prediction calibration method of energy storage battery |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN115524655A CN115524655A (en) | 2022-12-27 |
| CN115524655B true CN115524655B (en) | 2023-11-07 |
Family
ID=84702364
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202211262390.0A Active CN115524655B (en) | 2022-10-14 | 2022-10-14 | Residual electric quantity prediction calibration method of energy storage battery |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115524655B (en) |
Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102230953A (en) * | 2011-06-20 | 2011-11-02 | 江南大学 | Method for predicting left capacity and health status of storage battery |
| CN103616647A (en) * | 2013-12-09 | 2014-03-05 | 天津大学 | Battery remaining capacity estimation method for electric car battery management system |
| CN105759216A (en) * | 2016-02-26 | 2016-07-13 | 同济大学 | Method for estimating state of charge of soft package lithium-ion battery |
| CN105974327A (en) * | 2016-06-12 | 2016-09-28 | 广州市香港科大霍英东研究院 | Lithium battery pack SOC prediction method based on neural network and UKF |
| CN107037373A (en) * | 2017-05-03 | 2017-08-11 | 广西大学 | Battery dump energy Forecasting Methodology based on neutral net |
| KR101992051B1 (en) * | 2018-03-19 | 2019-06-21 | 충북대학교 산학협력단 | Method and system for predicting state of charge of battery |
| CN110045292A (en) * | 2019-05-07 | 2019-07-23 | 东莞理工学院 | Lithium ion battery SOC prediction technique based on big data and bp neural network |
| CN111624491A (en) * | 2019-02-27 | 2020-09-04 | 北京新能源汽车股份有限公司 | Method and device for determining residual electric quantity of battery and battery management system |
| DE102019218591A1 (en) * | 2019-11-29 | 2021-06-02 | Robert Bosch Gmbh | Method for estimating the state of an energy storage device |
| CN113297129A (en) * | 2021-04-28 | 2021-08-24 | 北京天启鸿源新能源科技有限公司 | SOC (System on chip) calculation method and system of energy storage system |
-
2022
- 2022-10-14 CN CN202211262390.0A patent/CN115524655B/en active Active
Patent Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102230953A (en) * | 2011-06-20 | 2011-11-02 | 江南大学 | Method for predicting left capacity and health status of storage battery |
| CN103616647A (en) * | 2013-12-09 | 2014-03-05 | 天津大学 | Battery remaining capacity estimation method for electric car battery management system |
| CN105759216A (en) * | 2016-02-26 | 2016-07-13 | 同济大学 | Method for estimating state of charge of soft package lithium-ion battery |
| CN105974327A (en) * | 2016-06-12 | 2016-09-28 | 广州市香港科大霍英东研究院 | Lithium battery pack SOC prediction method based on neural network and UKF |
| CN107037373A (en) * | 2017-05-03 | 2017-08-11 | 广西大学 | Battery dump energy Forecasting Methodology based on neutral net |
| KR101992051B1 (en) * | 2018-03-19 | 2019-06-21 | 충북대학교 산학협력단 | Method and system for predicting state of charge of battery |
| CN111624491A (en) * | 2019-02-27 | 2020-09-04 | 北京新能源汽车股份有限公司 | Method and device for determining residual electric quantity of battery and battery management system |
| CN110045292A (en) * | 2019-05-07 | 2019-07-23 | 东莞理工学院 | Lithium ion battery SOC prediction technique based on big data and bp neural network |
| DE102019218591A1 (en) * | 2019-11-29 | 2021-06-02 | Robert Bosch Gmbh | Method for estimating the state of an energy storage device |
| CN113297129A (en) * | 2021-04-28 | 2021-08-24 | 北京天启鸿源新能源科技有限公司 | SOC (System on chip) calculation method and system of energy storage system |
Also Published As
| Publication number | Publication date |
|---|---|
| CN115524655A (en) | 2022-12-27 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107020251B (en) | The screening technique of battery and battery pack | |
| CN108132442B (en) | storage battery joint state estimation method based on off-line data driving | |
| Kim et al. | State-of-charge estimation and state-of-health prediction of a Li-ion degraded battery based on an EKF combined with a per-unit system | |
| CN101034141B (en) | Method and device for detecting inner state of chargeable cell and equipment with the same | |
| CN110703121A (en) | Lithium ion battery health state prediction method | |
| CN107632272B (en) | Battery discharge state of charge accurate estimation method based on battery core temperature prediction | |
| CN105903692A (en) | Lithium ion battery consistency screening method | |
| CN111562501A (en) | Lithium ion battery SOC-OCV relation curve calibration method | |
| KR20100019256A (en) | Apparatus and method for cell balancing based on battery's voltage variation pattern | |
| KR20120065293A (en) | Apparatus and method for cell balancing based on battery's voltage variation pattern | |
| CN110221210B (en) | Method for rapidly predicting cycle life of lithium ion battery | |
| Thingvad et al. | Characterization of nmc lithium-ion battery degradation for improved online state estimation | |
| CN109946610A (en) | A kind of prediction technique of Vehicular battery cycle life | |
| Qiu et al. | Battery hysteresis modeling for state of charge estimation based on Extended Kalman Filter | |
| CN108064391A (en) | A kind of method for quick predicting of battery cycle life and its fast prediction device | |
| CN110632520A (en) | Estimation device and estimation method for SOC of power battery | |
| CN113777501A (en) | SOH estimation method of battery module | |
| Wu et al. | State-of-charge and state-of-health estimating method for lithium-ion batteries | |
| CN115524655B (en) | Residual electric quantity prediction calibration method of energy storage battery | |
| CN115663980B (en) | Aircraft battery management system, method, computer equipment and storage medium | |
| CN104849670A (en) | Test method for lithium ion battery life prediction | |
| CN110687469B (en) | Lithium ion battery constant volume method | |
| CN114152890A (en) | Method for predicting battery life | |
| CN113761716B (en) | Lithium ion battery cycle life prediction method and application thereof | |
| CN114137414A (en) | Method for calibrating SOP of lithium ion battery |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |