CN116953547A - Energy storage battery health evaluation method, system, equipment and storage medium - Google Patents
Energy storage battery health evaluation method, system, equipment and storage medium Download PDFInfo
- Publication number
- CN116953547A CN116953547A CN202310646346.8A CN202310646346A CN116953547A CN 116953547 A CN116953547 A CN 116953547A CN 202310646346 A CN202310646346 A CN 202310646346A CN 116953547 A CN116953547 A CN 116953547A
- Authority
- CN
- China
- Prior art keywords
- battery
- charging
- soh
- capacity
- term
- 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.)
- Pending
Links
- 238000004146 energy storage Methods 0.000 title claims abstract description 42
- 230000036541 health Effects 0.000 title claims abstract description 37
- 238000011156 evaluation Methods 0.000 title claims abstract description 36
- 230000007774 longterm Effects 0.000 claims abstract description 34
- 238000000034 method Methods 0.000 claims abstract description 29
- 238000012937 correction Methods 0.000 claims abstract description 28
- 238000007781 pre-processing Methods 0.000 claims abstract description 7
- 238000004364 calculation method Methods 0.000 claims abstract description 6
- 238000006243 chemical reaction Methods 0.000 claims description 36
- 238000007599 discharging Methods 0.000 claims description 33
- 238000012549 training Methods 0.000 claims description 17
- 238000012545 processing Methods 0.000 claims description 15
- 238000004590 computer program Methods 0.000 claims description 10
- 230000002159 abnormal effect Effects 0.000 claims description 7
- 238000003780 insertion Methods 0.000 claims description 6
- 230000037431 insertion Effects 0.000 claims description 6
- 230000000630 rising effect Effects 0.000 claims description 6
- 230000006870 function Effects 0.000 claims description 5
- 238000012360 testing method Methods 0.000 claims description 5
- 230000015654 memory Effects 0.000 claims description 4
- 238000009412 basement excavation Methods 0.000 claims description 3
- 210000002569 neuron Anatomy 0.000 claims description 3
- 230000000694 effects Effects 0.000 abstract description 14
- 238000005065 mining Methods 0.000 abstract description 2
- 238000010276 construction Methods 0.000 abstract 2
- 238000004422 calculation algorithm Methods 0.000 description 5
- 230000008901 benefit Effects 0.000 description 4
- 238000004891 communication Methods 0.000 description 4
- 238000001514 detection method Methods 0.000 description 3
- 238000012986 modification Methods 0.000 description 3
- 230000004048 modification Effects 0.000 description 3
- 230000008569 process Effects 0.000 description 3
- 238000013528 artificial neural network Methods 0.000 description 2
- 238000013461 design Methods 0.000 description 2
- 238000011161 development Methods 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 230000010354 integration Effects 0.000 description 2
- WHXSMMKQMYFTQS-UHFFFAOYSA-N Lithium Chemical compound [Li] WHXSMMKQMYFTQS-UHFFFAOYSA-N 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 239000000969 carrier Substances 0.000 description 1
- 210000004027 cell Anatomy 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 238000003066 decision tree Methods 0.000 description 1
- 230000007423 decrease Effects 0.000 description 1
- 230000003247 decreasing effect Effects 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 230000007613 environmental effect Effects 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 229910052744 lithium Inorganic materials 0.000 description 1
- 230000007787 long-term memory Effects 0.000 description 1
- 238000010801 machine learning Methods 0.000 description 1
- 238000002715 modification method Methods 0.000 description 1
- 238000003062 neural network model Methods 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 230000006403 short-term memory Effects 0.000 description 1
- 238000010200 validation analysis Methods 0.000 description 1
Classifications
-
- 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]
- G01R31/392—Determining battery ageing or deterioration, e.g. state of health
-
- 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
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02E—REDUCTION OF GREENHOUSE GAS [GHG] EMISSIONS, RELATED TO ENERGY GENERATION, TRANSMISSION OR DISTRIBUTION
- Y02E60/00—Enabling technologies; Technologies with a potential or indirect contribution to GHG emissions mitigation
- Y02E60/10—Energy storage using batteries
Landscapes
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Charge And Discharge Circuits For Batteries Or The Like (AREA)
Abstract
The application discloses an energy storage battery health evaluation method which specifically comprises the steps of data acquisition, data preprocessing, maximum battery capacity estimation correction, battery calibration capacity value correction, calculation of corrected battery SOH value, feature mining, construction of a short-term SOH prediction model and construction of a long-term SOH prediction model. According to the method and the system for evaluating the health degree of the energy storage battery, a large amount of historical charge and discharge data of the battery are collected, and based on the charge and discharge historical data of the large amount of energy storage battery, the maximum capacity estimation and the standard capacity value of the battery are corrected, so that the precision of the SOH value of the battery is further improved, the historical data trained by the SOH prediction model is also more accurate, and the prediction precision of the short-term SOH prediction model and the long-term SOH prediction model can be further improved. The energy storage battery health evaluation method can simultaneously realize two modes of short-term SOH evaluation and long-term SOH evaluation, and can achieve better evaluation effect on the battery SOH.
Description
Technical Field
The patent relates to the technical field of energy storage battery management systems, in particular to a battery state of health (SOH) detection and evaluation method.
Background
Along with the gradual shortage of energy and the continuous improvement of environmental protection consciousness of people, various new energy technologies are more and more paid attention to, and the new energy field is in a peak period of development. Energy storage is an important ring in the field of new energy, and research on energy storage batteries serving as energy storage carriers is also continuously in progress. The state of health (SOH) of a battery is an important indicator of the battery, and is an important reference for whether the battery can safely run. SOH estimation is one method used to determine battery health, and is expressed as a percentage of the amount of charge or discharge that a battery can charge or discharge to the nominal capacity of the battery. For new batteries, the value is typically greater than 100%. This value gradually decreases as the battery is used and aged. According to IEEE standard 1188-1996, when the capacity of the power cell drops to 80%, it should be replaced. Therefore, the accuracy of the energy storage battery health evaluation method plays a critical role in the safe use of the battery.
The traditional lithium battery health evaluation method generally comprises the steps of firstly collecting historical data of SOH (state of health) of a battery, then calculating to obtain the charge capacity of a certain charge segment by using an ampere-hour integration method, then dividing the charge capacity by the difference value of the change interval of SOC (current residual capacity of the battery) corresponding to the charge segment to obtain the maximum capacity of the battery, and dividing the maximum capacity of the battery by the calibrated capacity of the battery to obtain the SOH of the battery. The battery state of health (SOH) detection and evaluation method has the problems of low prediction precision, poor real-time performance and the like, and along with the continuous development of battery charging technology, the battery state of health detection and evaluation method can not meet the use requirement, so that it is necessary to design an energy storage battery health evaluation method capable of better realizing accurate prediction of the battery state of health.
Disclosure of Invention
In order to overcome the defects in the prior art, the application aims to design a method for evaluating the health of an energy storage battery more accurately.
An energy storage battery health evaluation method comprises the following steps:
1) And (3) data acquisition: collecting and recording historical battery charging and discharging data according to a certain time interval, wherein the historical battery charging and discharging data comprises battery charging current, battery discharging current, battery charging voltage, battery discharging voltage, battery charging temperature, battery discharging temperature and battery SOC parameters;
2) Data preprocessing: performing data deduplication, null value processing and abnormal value processing on the acquired historical charge and discharge data of the battery;
3) Maximum battery capacity estimation correction: dividing the battery SOC into a plurality of charging intervals according to the historical charging and discharging data of the battery at equal proportion intervals from 0% to 100%, calculating the average value of the actual charging electric quantity of each charging interval, dividing the average value of the charging electric quantity when the battery is fully charged to obtain an estimated conversion factor corresponding table of the charging interval, multiplying the actual charging quantity of each charging interval covered by charging by the estimated conversion factor corresponding to the charging interval, summing, and dividing the summed value by the sum of the estimated conversion factors of the covered charging interval to obtain a corrected maximum capacity estimated value of the battery;
4) Correcting the battery calibration capacity value: dividing the calibrated capacity corresponding to each charging multiplying power and temperature marked when the battery leaves the factory by a battery correction capacity coefficient L to obtain capacity conversion factors corresponding to each charging multiplying power and temperature marked when the battery leaves the factory, calculating the capacity conversion factors at each insertion point between the capacity conversion factors corresponding to two adjacent temperatures of each charging multiplying power by an equal division interpolation method, forming a capacity conversion factor table, and multiplying the capacity conversion factors corresponding to the current environment temperature and the charging rate by the battery correction capacity coefficient L to obtain corrected battery calibrated capacity;
5) Calculating a corrected SOH value of the battery: dividing the corrected maximum battery capacity estimation by the corrected battery calibration capacity;
6) Feature excavation: excavating historical charge and discharge data of the battery to obtain useful characteristics, wherein the useful characteristics comprise calendar days, accumulated use time, charging times, circulation times, deep charge and discharge times, average temperature difference, maximum temperature difference, charging unit temperature rising amount, average temperature difference standard deviation, average pressure difference, maximum pressure difference, average pressure difference standard deviation, charge heavy current record and discharge heavy current record;
7) Constructing a short-term SOH prediction model: constructing a short-term SOH prediction model based on the corrected SOH value of the battery and the mined useful features, and training;
8) Constructing a long-term SOH prediction model: and constructing a long-term SOH prediction model by using SOH time sequence data, and training the long-term SOH prediction model by taking a prediction result of the short-term SOH prediction model as a training sample.
Preferably, in step 7), two prediction models, namely a LightGBM model and a Catboost model, are constructed, short-term SOH values are predicted respectively, and the prediction results of the two models are averaged to obtain a final short-term SOH value.
Preferably, the long-term SOH prediction model constructed in step 8) is an LSTM prediction model.
Preferably, the number of neurons in the LSTM prediction model is 16; the optimizer uses RMSprop, the learning rate is 0.0001 and the loss function is mae.
In order to achieve the above purpose, the application also discloses an energy storage battery health evaluation system, a data acquisition unit, a data processing unit and a data processing unit, wherein the data acquisition unit is used for acquiring and recording historical battery charging and discharging data according to a certain time interval, and the historical battery charging and discharging data comprises battery charging current, battery discharging current, battery charging voltage, battery discharging voltage, battery charging temperature, battery discharging temperature and battery SOC parameters; the data preprocessing unit is used for carrying out data deduplication, null value processing and abnormal constant value processing on the acquired battery history charge and discharge data; the maximum battery capacity estimation correction unit is used for dividing the battery SOC into a plurality of charging intervals according to the battery historical charge and discharge data at equal proportion intervals, calculating the average value of the actual charge quantity of each charging interval, dividing the average value of the charge quantity of the battery when the battery is fully charged to obtain an estimation conversion factor corresponding table of the charging interval, multiplying the actual charge quantity of each charging interval covered by the charging by the estimation conversion factor corresponding to the charging interval and summing the estimation conversion factors, and dividing the summed value by the sum of the estimation conversion factors of the covered charging intervals to obtain a corrected battery maximum capacity estimation value; the battery calibration capacity value correction unit is used for dividing the calibration capacity corresponding to each charging multiplying power and temperature marked when the battery leaves the factory by a battery correction capacity coefficient L to obtain capacity conversion factors corresponding to each charging multiplying power and temperature marked when the battery leaves the factory, calculating the capacity conversion factors at each insertion point between two adjacent capacity conversion factors corresponding to each charging multiplying power by an equal division interpolation method, forming a capacity conversion factor table, and multiplying the capacity conversion factors corresponding to the current environment temperature and the charging rate by the battery correction capacity coefficient L to obtain corrected battery calibration capacity; the battery SOH value correction calculation unit is used for dividing the corrected maximum battery capacity estimated value by the corrected battery calibration capacity to obtain a battery SOH value corrected value; the characteristic excavating unit is used for excavating historical charge and discharge data of the battery to obtain useful characteristics, wherein the useful characteristics comprise calendar days, accumulated use time, charging times, circulation times, deep charge and discharge times, average temperature difference, maximum temperature difference, unit temperature rising amount of charging, average temperature difference standard deviation, average pressure difference, maximum pressure difference, average pressure difference standard deviation, charge heavy current record and discharge heavy current record; the short-term SOH prediction model is constructed based on the corrected SOH value of the battery and the mined useful features and is used for predicting the short-term SOH of the battery; and the long-term SOH prediction model is constructed by SOH time sequence data, and a prediction result of the short-term SOH prediction model is used as a test sample for training and is used for predicting the long-term SOH.
To achieve the above object, the present application also discloses an energy storage battery health evaluation device, which includes: comprising a memory in which a computer program is stored, and a processor which, when executing the computer program, carries out the steps of the method according to any one of claims 1 to 4.
To achieve the above object, the application also discloses a computer storage medium storing a computer program which, when executed by a processor, implements the steps of the method of any one of claims 1 to 4.
The technical scheme has the following beneficial effects: according to the method and the system for evaluating the health degree of the energy storage battery, a large amount of battery historical charge and discharge data are collected, an estimated conversion factor table of each charging segment of the energy storage battery is constructed based on the charge and discharge historical data of the large amount of energy storage batteries, the estimated maximum capacity of the battery is corrected, and the accuracy of the maximum capacity estimation of the battery is improved; by constructing capacity conversion factors of different temperatures and charging multiplying powers of the energy storage battery, the calibration capacity of the battery is more accurate, so that the precision of the SOH value of the corrected battery is further improved, the historical data of SOH prediction model training is more accurate, and the prediction precision of a short-term SOH prediction model and a long-term SOH prediction model can be further improved. The energy storage battery health evaluation method can simultaneously realize two modes of short-term SOH evaluation and long-term SOH evaluation, and can achieve better evaluation effect on the battery SOH.
Drawings
FIG. 1 is a flowchart of an evaluation method according to an embodiment of the present application.
Fig. 2 is a table example of SOC charging interval estimation conversion factors.
Fig. 3 is a sample of the nominal capacity of the battery as it leaves the factory.
Fig. 4 is a table of battery capacity conversion factor samples.
Fig. 5 is a diagram of a battery short-term SOH prediction model according to an embodiment of the present application.
Fig. 6 is a diagram of a long-term SOH prediction model of a battery according to an embodiment of the present application.
Fig. 7 LightGBM model predicts short-term SOH samples.
FIG. 8 Catboost model predicts short-term SOH samples.
FIG. 9 LSTM model predicts long-term SOH loss function variation graph.
FIG. 10 LSTM model predicts long-term SOH trend graph.
Detailed Description
Further advantages and effects of the present application will become apparent to those skilled in the art from the disclosure of the present application, which is described by the following specific examples.
Example embodiments will now be described more fully with reference to the accompanying drawings. However, the exemplary embodiments may be embodied in many forms and should not be construed as limited to the examples set forth herein; rather, these embodiments are provided so that this disclosure will be thorough and complete, and will fully convey the concept of the example embodiments to those skilled in the art. The described features, structures, or characteristics may be combined in any suitable manner in one or more embodiments. In the following description, numerous specific details are provided to give a thorough understanding of embodiments of the application. One skilled in the relevant art will recognize, however, that the application may be practiced without one or more of the specific details, or with other methods, components, devices, steps, etc. In other instances, well-known aspects have not been shown or described in detail to avoid obscuring aspects of the application.
As shown in fig. 1, the application discloses a method for evaluating the health of an energy storage battery, which specifically comprises the following steps:
1. and (3) data acquisition:
and collecting historical battery charging and discharging data, wherein the historical battery charging and discharging data comprise battery charging current, battery discharging current, battery charging voltage, battery discharging voltage, battery charging temperature, battery discharging temperature and battery SOC parameters, and the historical battery charging and discharging data are collected at certain time intervals and stored and recorded.
2. Data preprocessing:
the collected battery history charge and discharge data is cleaned, because after the original data is collected, some dirty data, such as missing data, abnormal data and the like, is inevitably present in the data, and the original data needs to be cleaned to perform data deduplication, null value processing and abnormal value processing on the obtained battery history charge and discharge data.
3. Maximum battery capacity estimation correction:
according to the historical charge and discharge data of the battery, the battery SOC is divided into a plurality of charging intervals according to equal proportion, for example, 10% of each interval is taken as one interval, namely, the SOC distribution of the interval is 0% -10%, 10% -20%, the number of the intervals is equal to the number of the intervals, the estimated conversion factors of each interval are calculated, the specific calculation method is that the average value of the actual charge quantity of each interval is calculated based on a large amount of historical charge data of the battery, and then the average value of the charge quantity of the battery when the battery is fully charged is divided, so that the estimated conversion factors of the interval can be obtained, and the SOC interval conversion factor is shown in a table, for example, in fig. 2. When calculating the maximum capacity of the actual battery, assuming that the SOC variation range of the battery charging process covers a plurality of SOC intervals, multiplying the actual charge quantity of each SOC interval by the estimated conversion factor corresponding to the SOC interval, then summing, and dividing the summed value by the sum of the estimated conversion factors of the covered SOC intervals, thus obtaining the final maximum capacity estimated value of the battery.
4. Correcting the battery calibration capacity value:
dividing the calibrated capacity corresponding to each charging multiplying power and temperature marked when the battery leaves the factory by a battery correction capacity coefficient L to obtain capacity conversion factors corresponding to each charging multiplying power and temperature marked when the battery leaves the factory, calculating the capacity conversion factors at each insertion point between the capacity conversion factors corresponding to two adjacent temperatures of each charging multiplying power by an equal division interpolation method, forming a capacity conversion factor table, and multiplying the capacity conversion factors corresponding to the current environment temperature and the charging rate by the battery correction capacity coefficient L to obtain corrected battery calibrated capacity. In order to make the specific modification of this step more clear, the following examples illustrate the modification method.
As shown in fig. 3, a sample of the battery calibration capacity of the energy storage battery when leaving the factory is shown, the charging rate covered by the calibration capacity of the energy storage battery is 0.2C, 0.5C, 1C, 2C and 5C, the temperatures are typically-20 °,0 °, 20 ° and 45 °, the calibration capacity of 25 ° is the highest under the same charging and discharging rate, and the calibration capacities of 0 ° and 45 ° are both lower, and the calibration capacities are respectively decreased to two ends in a gradient manner by taking 25 ° as a center point. Because the temperature range of the battery is relatively wide in the actual charging process, the battery is not limited to the above temperature values, and the temperature value range needs to be expanded so as to be more suitable for the temperature condition in the actual charging process. The value of the battery correction capacity coefficient L may be set according to the capacity of the battery, and generally an integer value close to the battery capacity may be selected, and in this embodiment, the battery correction capacity coefficient L may be set to 38. Dividing the calibrated capacity corresponding to each charging multiplying power and temperature by a battery correction capacity coefficient L to obtain capacity conversion factors corresponding to each charging multiplying power and temperature marked when the battery leaves the factory, calculating the capacity conversion factors at each insertion point between two adjacent capacity conversion factors corresponding to each charging multiplying power by adopting an equal division interpolation method, forming a capacity conversion factor table, and setting the equal division number of the equal division interpolation method according to the required temperature precision.
As shown in fig. 4, in the present application, the temperature interval is thinned to 1 degree, that is, the interval formed by inserting equal division points into the interval formed by the capacity conversion factors corresponding to 20 ° and 0 ° respectively is equally divided into 20 parts, the capacity conversion factor value corresponding to each equal division point is calculated, and the capacity conversion factor values at different charging multiplying powers are calculated according to the same method, so as to obtain the capacity conversion factor table shown in fig. 4. And then multiplying the capacity conversion factor corresponding to the previous environment temperature and the charging rate by the battery correction capacity coefficient L to obtain the corrected current battery calibration capacity.
5. Calculating a corrected SOH value of the battery:
and dividing the corrected maximum battery capacity estimated value by the corrected battery calibration capacity to obtain a corrected battery SOH value.
6. Feature excavation:
the historical data of the battery charge and discharge data records original characteristics such as current, voltage and temperature, and the useful characteristics for constructing an SOH prediction model are mined through corresponding calculation on the battery historical charge and discharge data, wherein the useful characteristics specifically comprise: calendar days, accumulated use duration, charging times, circulation times, deep charging and discharging times, average temperature difference, maximum temperature difference, unit charging temperature rising amount, average temperature difference standard deviation, average pressure difference, maximum pressure difference, average pressure difference standard deviation, charge heavy current record and discharge heavy current record.
7. Constructing a short-term SOH prediction model:
and constructing a short-term SOH prediction model based on the corrected SOH value of the battery and the mined useful features, and training the model by taking the useful features as input and the corrected SOH value of the battery as output. As shown in fig. 5, in order to further improve the prediction accuracy of the model, the application constructs two types of LightGBM models and CatBoost models to respectively predict short-term SOH values, and averages the prediction results of the two types of models to obtain final short-term SOH values.
LightGBM and CatBoost are both one of the gradient enhancement (gradient boosting) algorithms, both improved versions of the GBDT (Gradient Boosting Decision Tree) algorithm. The LightGBM has the advantages of supporting high-efficiency parallel training, having faster training speed, lower memory consumption, better accuracy and supporting distributed type fast processing of mass data. The Catboost algorithm has the advantages that the classification type features are processed mainly, and the classification type features do not need to be processed through feature engineering before a model is trained; another advantage is that the prediction offset is processed, so that the overfitting of the model is reduced, and the model prediction effect is improved.
8. Constructing a long-term SOH prediction model:
as shown in fig. 6, a long-term SOH prediction model is constructed using the battery history SOH value as time-series data, and the long-term SOH prediction model is trained using the prediction result of the short-term SOH prediction model as a training sample. Thus, the long-term SOH of the battery can be predicted by the long-term SOH prediction model. As a specific embodiment, the Long-Term SOH prediction model adopts an LSTM prediction model, and LSTM (Long Short-Term Memory) is a Long-Term Memory neural network model, is a time-circulating neural network, and improves the Long-Term dependence problem existing in the circulating neural network (RNN). The number of the adopted LSTM model neurons is 16; the optimizer uses RMSprop, the learning rate is 0.0001 and the loss function is mae.
In order to verify the model prediction effect, the model effect test is carried out on the basis of actual energy storage data of a certain company, and the test is divided into two parts, wherein one part is short-term SOH prediction and the other part is long-term SOH prediction.
Short-term SOH prediction effect: respectively training a LightGBM model and a Catoost model, taking an average absolute error as a model evaluation index, and calculating the following results:
TABLE 1 model effect index display
| Model | Average absolute error |
| LightGBM | 0.013 |
| CatBoost | 0.009 |
The LightGBM model prediction results are shown in fig. 7 below; the prediction result of the Catboost model is shown in FIG. 8; from the evaluation index and the prediction sample, the predicted short-term SOH effect is ideal.
Long-term SOH prediction effect: model loss function variation as shown in fig. 9 below, the training loss curve of the model is substantially identical to the validation loss curve. The model prediction effect is shown in fig. 10, wherein the error between the actual historical SOH value and the historical SOH value predicted by the model is small and the stability is good, and as can be seen from the graph, the future SOH value predicted by the model shows a descending trend and accords with the actual condition of the battery, and the model predicts the long-term SOH effect more ideal.
The application also discloses an energy storage battery health evaluation system, which comprises: the data acquisition unit is used for acquiring and recording historical charge and discharge data of the battery according to a certain time interval, wherein the historical charge and discharge data of the battery comprise battery charge current, battery discharge current, battery charge voltage, battery discharge voltage, battery charge temperature, battery discharge temperature and battery SOC parameters;
the data preprocessing unit is used for carrying out data deduplication, null value processing and abnormal value processing on the acquired battery history charge and discharge data;
the maximum battery capacity estimation correction unit is used for dividing the battery SOC into a plurality of charging intervals according to the battery historical charging and discharging data at equal proportion intervals from 0% to 100%, calculating the average value of the actual charging electric quantity of each charging interval, dividing the average value of the charging electric quantity of each charging interval by the average value of the charging electric quantity when the battery is fully charged to obtain an estimation conversion factor corresponding table of the charging interval, multiplying the actual charging quantity of each charging interval covered by the charging by the estimation conversion factor corresponding to the charging interval and summing, and dividing the summed value by the sum of the estimation conversion factors of the covered charging intervals to obtain a corrected battery maximum capacity estimation value;
the battery calibration capacity value correction unit is used for dividing the calibration capacity corresponding to each charging multiplying power and temperature of the battery by the calibration capacity of the battery leaving the factory, then obtaining the conversion factor of each temperature of each charging multiplying power by adopting an equal division interpolation method in each temperature interval of each charging multiplying power, obtaining a conversion factor table of the temperature and charging and discharging multiplying power of the battery for the calibration capacity, multiplying the estimated value of the battery calibration capacity by the conversion factor of the corresponding temperature and charging and discharging multiplying power for the calibration capacity, and obtaining the corrected battery calibration capacity; the battery SOH value correction calculation unit is used for dividing the corrected maximum battery capacity estimated value by the corrected battery calibration capacity to obtain a battery SOH value corrected value;
the characteristic excavating unit is used for excavating historical charge and discharge data of the battery to obtain useful characteristics, wherein the useful characteristics comprise calendar days, accumulated use time, charging times, circulation times, deep charge and discharge times, average temperature difference, maximum temperature difference, unit temperature rising amount of charging, average temperature difference standard deviation, average pressure difference, maximum pressure difference, average pressure difference standard deviation, charge heavy current record and discharge heavy current record;
the short-term SOH prediction model is constructed based on the corrected SOH value of the battery and the mined useful features and is used for predicting the short-term SOH of the battery;
and the long-term SOH prediction model is constructed by SOH time sequence data, and a prediction result of the short-term SOH prediction model is used as a test sample for training and is used for predicting the long-term SOH.
It should be noted that, other corresponding descriptions of each functional unit related to the energy storage battery health evaluation system provided in this embodiment may refer to corresponding descriptions of the energy storage battery health evaluation method, which are not described herein again.
Based on the above energy storage battery health evaluation method, in order to achieve the above objective, the embodiment of the present application further provides an energy storage battery health evaluation device, which may be specifically a personal computer, a server, a network device, etc., where the entity device includes a storage medium and a processor; a storage medium storing a computer program; and the processor is used for executing the computer program to realize the energy storage battery health evaluation method.
Accordingly, the present embodiment also provides a computer storage medium, on which a computer program is stored, which when executed by a processor, implements the above-described energy storage battery health evaluation method. Based on such understanding, the technical solution of the present application may be embodied in the form of a software product, which may be stored in a non-volatile storage medium (may be a CD-ROM, a U-disk, a mobile hard disk, etc.), and includes several instructions for causing a computer device (may be a personal computer, a server, or a network device, etc.) to execute the method described in the respective implementation scenario of the present application. The storage medium may also include an operating system, a network communication module. An operating system is a program that manages the computer device hardware and software resources described above, supporting the execution of information handling programs and other software and/or programs. The network communication module is used for realizing communication among all components in the storage medium and communication with other hardware and software in the entity equipment.
According to the energy storage battery health evaluation method, an SOH prediction model is built by using a machine learning model, a large number of original features and mining features are used, the used models are a LightGBM algorithm and a Catboost algorithm, and the prediction results of the two are averaged, so that the overall effect is optimal. Based on charge and discharge history data of a large number of energy storage batteries, a conversion factor table of each charging segment is constructed, the estimated maximum capacity of the batteries is corrected through an ampere-hour integration method, and the accuracy of maximum capacity estimation of the batteries is improved. By constructing different temperatures and charging multiplying powers, the calibration capacity of the battery is more accurate, and after the accuracy of the maximum capacity estimation and the calibration capacity of the battery is improved, the historical data for the subsequent SOH prediction model training is more accurate.
According to the method and the system for evaluating the health degree of the energy storage battery, a large amount of historical charge and discharge data of the battery are collected, and based on the charge and discharge historical data of the large amount of energy storage battery, the maximum capacity estimation and the standard capacity value of the battery are corrected, so that the precision of the SOH value of the battery is further improved, the historical data trained by the SOH prediction model is also more accurate, and the prediction precision of the short-term SOH prediction model and the long-term SOH prediction model can be further improved. The energy storage battery health evaluation method can simultaneously realize two modes of short-term SOH evaluation and long-term SOH evaluation, and can achieve better evaluation effect on the battery SOH.
The above embodiments are merely illustrative of the principles of the present application and its effectiveness, and are not intended to limit the application. Modifications and variations may be made to the above-described embodiments by those skilled in the art without departing from the spirit and scope of the application. Accordingly, it is intended that all equivalent modifications and variations of the application be covered by the claims, which are within the ordinary skill of the art, be within the spirit and scope of the present disclosure.
Claims (7)
1. The energy storage battery health evaluation method is characterized by comprising the following steps of:
and (3) data acquisition: collecting and recording historical battery charging and discharging data according to a certain time interval, wherein the historical battery charging and discharging data comprises battery charging current, battery discharging current, battery charging voltage, battery discharging voltage, battery charging temperature, battery discharging temperature and battery SOC parameters;
data preprocessing: performing data deduplication, null value processing and abnormal value processing on the acquired historical charge and discharge data of the battery;
maximum battery capacity estimation correction: dividing the battery SOC into a plurality of charging intervals according to the historical charging and discharging data of the battery at equal proportion intervals from 0% to 100%, calculating the average value of the actual charging electric quantity of each charging interval, dividing the average value of the charging electric quantity when the battery is fully charged to obtain an estimated conversion factor corresponding table of the charging interval, multiplying the actual charging quantity of each charging interval covered by charging by the estimated conversion factor corresponding to the charging interval, summing, and dividing the summed value by the sum of the estimated conversion factors of the covered charging interval to obtain a corrected maximum capacity estimated value of the battery;
correcting the battery calibration capacity value: dividing the calibrated capacity corresponding to each charging multiplying power and temperature marked when the battery leaves the factory by a battery correction capacity coefficient L to obtain capacity conversion factors corresponding to each charging multiplying power and temperature marked when the battery leaves the factory, calculating the capacity conversion factors at each insertion point between the capacity conversion factors corresponding to two adjacent temperatures of each charging multiplying power by an equal division interpolation method, forming a capacity conversion factor table, and multiplying the capacity conversion factors corresponding to the current environment temperature and the charging rate by the battery correction capacity coefficient L to obtain corrected battery calibrated capacity;
calculating a corrected SOH value of the battery: dividing the corrected maximum battery capacity estimation by the corrected battery calibration capacity;
feature excavation: excavating historical charge and discharge data of the battery to obtain useful characteristics, wherein the useful characteristics comprise calendar days, accumulated use time, charging times, circulation times, deep charge and discharge times, average temperature difference, maximum temperature difference, charging unit temperature rising amount, average temperature difference standard deviation, average pressure difference, maximum pressure difference, average pressure difference standard deviation, charge heavy current record and discharge heavy current record;
constructing a short-term SOH prediction model: constructing a short-term SOH prediction model based on the corrected SOH value of the battery and the mined useful features, and training;
constructing a long-term SOH prediction model: and constructing a long-term SOH prediction model by using SOH time sequence data, and training the long-term SOH prediction model by taking a prediction result of the short-term SOH prediction model as a training sample.
2. The method for evaluating the health of an energy storage battery according to claim 1, wherein in the step 7), two prediction models, namely a LightGBM model and a CatBoost model, are constructed, short-term SOH values are predicted respectively, and the prediction results of the two models are averaged to obtain a final short-term SOH value.
3. The method of claim 1, wherein the long-term SOH prediction model constructed in step 8) is an LSTM prediction model.
4. The method for estimating health of an energy storage battery according to claim 3, wherein the number of neurons in the LSTM prediction model is 16; the optimizer uses RMSprop, the learning rate is 0.0001 and the loss function is mae.
5. An energy storage battery health assessment system, comprising:
the data acquisition unit is used for acquiring and recording historical battery charging and discharging data according to a certain time interval, wherein the historical battery charging and discharging data comprises battery charging current, battery discharging current, battery charging voltage, battery discharging voltage, battery charging temperature, battery discharging temperature and battery SOC parameters;
the data preprocessing unit is used for carrying out data deduplication, null value processing and abnormal constant value processing on the acquired battery history charge and discharge data;
the maximum battery capacity estimation correction unit is used for dividing the battery SOC into a plurality of charging intervals according to the battery historical charge and discharge data at equal proportion intervals, calculating the average value of the actual charge quantity of each charging interval, dividing the average value of the charge quantity of the battery when the battery is fully charged to obtain an estimation conversion factor corresponding table of the charging interval, multiplying the actual charge quantity of each charging interval covered by the charging by the estimation conversion factor corresponding to the charging interval and summing the estimation conversion factors, and dividing the summed value by the sum of the estimation conversion factors of the covered charging intervals to obtain a corrected battery maximum capacity estimation value;
the battery calibration capacity value correction unit is used for dividing the calibration capacity corresponding to each charging multiplying power and temperature marked when the battery leaves the factory by a battery correction capacity coefficient L to obtain capacity conversion factors corresponding to each charging multiplying power and temperature marked when the battery leaves the factory, calculating the capacity conversion factors at each insertion point between the capacity conversion factors corresponding to two adjacent temperatures of each charging multiplying power by an equal division interpolation method, forming a capacity conversion factor table, and multiplying the capacity conversion factors corresponding to the current environment temperature and the charging rate by the battery correction capacity coefficient L to obtain corrected battery calibration capacity;
the battery SOH value correction calculation unit is used for dividing the corrected maximum battery capacity estimated value by the corrected battery calibration capacity to obtain a battery SOH value corrected value;
the characteristic excavating unit is used for excavating historical charge and discharge data of the battery to obtain useful characteristics, wherein the useful characteristics comprise calendar days, accumulated use time, charging times, circulation times, deep charge and discharge times, average temperature difference, maximum temperature difference, unit temperature rising amount of charging, average temperature difference standard deviation, average pressure difference, maximum pressure difference, average pressure difference standard deviation, charge heavy current record and discharge heavy current record;
the short-term SOH prediction model is constructed based on the corrected SOH value of the battery and the mined useful features and is used for predicting the short-term SOH of the battery;
and the long-term SOH prediction model is constructed by SOH time sequence data, and a prediction result of the short-term SOH prediction model is used as a test sample for training and is used for predicting the long-term SOH.
6. An energy storage battery health assessment device, comprising: comprising a memory and a processor, the memory having stored therein a computer program, characterized in that the processor, when executing the computer program, carries out the steps of the method according to any of claims 1 to 4.
7. A computer storage medium storing a computer program, characterized in that the computer program when executed by a processor implements the steps of the method of any one of claims 1 to 4.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310646346.8A CN116953547A (en) | 2023-06-02 | 2023-06-02 | Energy storage battery health evaluation method, system, equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310646346.8A CN116953547A (en) | 2023-06-02 | 2023-06-02 | Energy storage battery health evaluation method, system, equipment and storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN116953547A true CN116953547A (en) | 2023-10-27 |
Family
ID=88446915
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310646346.8A Pending CN116953547A (en) | 2023-06-02 | 2023-06-02 | Energy storage battery health evaluation method, system, equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116953547A (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117517993A (en) * | 2023-11-02 | 2024-02-06 | 安徽智途科技有限公司 | Intelligent vehicle battery energy management method and system based on battery cell performance evaluation |
| CN117761541A (en) * | 2023-12-25 | 2024-03-26 | 广州邦禾检测技术有限公司 | Battery energy state detection method for battery management system |
| CN118091471A (en) * | 2024-04-25 | 2024-05-28 | 中汽研新能源汽车检验中心(天津)有限公司 | Power battery evaluation method and system |
-
2023
- 2023-06-02 CN CN202310646346.8A patent/CN116953547A/en active Pending
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117517993A (en) * | 2023-11-02 | 2024-02-06 | 安徽智途科技有限公司 | Intelligent vehicle battery energy management method and system based on battery cell performance evaluation |
| CN117517993B (en) * | 2023-11-02 | 2024-05-17 | 安徽智途科技有限公司 | Intelligent vehicle battery energy management method and system based on battery cell performance evaluation |
| CN117761541A (en) * | 2023-12-25 | 2024-03-26 | 广州邦禾检测技术有限公司 | Battery energy state detection method for battery management system |
| CN117761541B (en) * | 2023-12-25 | 2024-06-07 | 广州邦禾检测技术有限公司 | Battery energy state detection method for battery management system |
| CN118091471A (en) * | 2024-04-25 | 2024-05-28 | 中汽研新能源汽车检验中心(天津)有限公司 | Power battery evaluation method and system |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN112034356B (en) | GP-UKF-based online SOH estimation method for electric vehicle power battery | |
| CN110068774B (en) | Lithium battery health state estimation method and device and storage medium | |
| CN107957562B (en) | Online prediction method for residual life of lithium ion battery | |
| CN116953547A (en) | Energy storage battery health evaluation method, system, equipment and storage medium | |
| CN113219343A (en) | Lithium battery health state prediction method, system, equipment and medium based on elastic network | |
| CN105911476B (en) | A kind of battery energy storage system SOC prediction techniques based on data mining | |
| CN115902647B (en) | Intelligent battery state monitoring method | |
| CN114818831B (en) | Bidirectional lithium ion battery fault detection method and system based on multi-source perception | |
| Mian Qaisar | A proficient Li-ion battery state of charge estimation based on event-driven processing | |
| CN115201686B (en) | Lithium ion battery health state assessment method under incomplete charge and discharge data | |
| CN114879046B (en) | Lithium battery life prediction method and system based on Kalman filtering | |
| CN115015789A (en) | Lithium ion battery health state estimation method and device based on incremental capacitance curve | |
| CN116148670A (en) | Method and device for estimating service life of battery of electrochemical energy storage power station | |
| CN114545275A (en) | Indirect prediction method for remaining service life of lithium ion battery | |
| You et al. | Capacity Estimation of lithium battery based on charging data and Long Short-term Memory Recurrent Neural Network | |
| Shin et al. | Feature construction for on-board early prediction of electric vehicle battery cycle life | |
| Dong et al. | State of health estimation and remaining useful life estimation for Li-ion batteries based on a hybrid kernel function relevance vector machine | |
| CN117110884A (en) | Lithium battery remaining service life prediction method based on multi-core correlation vector machine | |
| CN112418564A (en) | Charging and battery replacing load prediction method for charging and battery replacing station based on LSTM and related components thereof | |
| CN115312895A (en) | Method for monitoring steady state of battery pack of new energy vehicle | |
| CN115248390A (en) | Lithium ion battery SOH estimation method based on random short-term charging data | |
| Gaga et al. | Methods for estimating lithium-ion battery state of charge for use in electric vehicles: a review | |
| CN114545271A (en) | Lithium battery remaining life detection method and system based on direct current resistance detection | |
| Rao et al. | A Hyperparameter-tuned LSTM Technique-based Battery Remaining Useful Life Estimation Considering Incremental Capacity Curves | |
| CN211086535U (en) | Lithium ion power battery charge state prediction circuit |
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 |