CN113189495B - Battery health state prediction method and device and electronic equipment - Google Patents
Battery health state prediction method and device and electronic equipment Download PDFInfo
- Publication number
- CN113189495B CN113189495B CN202110479505.0A CN202110479505A CN113189495B CN 113189495 B CN113189495 B CN 113189495B CN 202110479505 A CN202110479505 A CN 202110479505A CN 113189495 B CN113189495 B CN 113189495B
- Authority
- CN
- China
- Prior art keywords
- battery
- real
- preset
- time
- deep learning
- 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
- 230000036541 health Effects 0.000 title claims abstract description 82
- 238000000034 method Methods 0.000 title claims abstract description 55
- 238000013136 deep learning model Methods 0.000 claims abstract description 70
- 230000003862 health status Effects 0.000 claims abstract description 18
- 238000005070 sampling Methods 0.000 claims abstract description 11
- 238000012360 testing method Methods 0.000 claims description 43
- 238000012549 training Methods 0.000 claims description 43
- 238000005259 measurement Methods 0.000 claims description 14
- 230000008569 process Effects 0.000 claims description 9
- 238000012545 processing Methods 0.000 claims description 8
- 230000002159 abnormal effect Effects 0.000 claims description 4
- 238000013473 artificial intelligence Methods 0.000 abstract description 2
- 238000004891 communication Methods 0.000 description 6
- 230000007547 defect Effects 0.000 description 3
- 238000010586 diagram Methods 0.000 description 3
- 238000013459 approach Methods 0.000 description 2
- 230000008901 benefit Effects 0.000 description 2
- 230000001351 cycling effect Effects 0.000 description 2
- 238000007599 discharging Methods 0.000 description 2
- 238000007726 management method Methods 0.000 description 2
- 238000011056 performance test Methods 0.000 description 2
- HBBGRARXTFLTSG-UHFFFAOYSA-N Lithium ion Chemical compound [Li+] HBBGRARXTFLTSG-UHFFFAOYSA-N 0.000 description 1
- 230000003044 adaptive effect Effects 0.000 description 1
- 238000013528 artificial neural network Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 239000003990 capacitor Substances 0.000 description 1
- 230000015556 catabolic process Effects 0.000 description 1
- 238000013500 data storage Methods 0.000 description 1
- 238000013135 deep learning Methods 0.000 description 1
- 238000006731 degradation reaction Methods 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 230000002708 enhancing effect Effects 0.000 description 1
- 238000011156 evaluation Methods 0.000 description 1
- 238000001914 filtration Methods 0.000 description 1
- 230000003993 interaction Effects 0.000 description 1
- 229910001416 lithium ion Inorganic materials 0.000 description 1
- 230000007246 mechanism Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000012544 monitoring process Methods 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 230000000750 progressive effect Effects 0.000 description 1
- 230000008439 repair process Effects 0.000 description 1
- 230000003068 static effect Effects 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]
- G01R31/378—Arrangements for testing, measuring or monitoring the electrical condition of accumulators or electric batteries, e.g. capacity or state of charge [SoC] specially adapted for the type of battery or accumulator
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01K—MEASURING TEMPERATURE; MEASURING QUANTITY OF HEAT; THERMALLY-SENSITIVE ELEMENTS NOT OTHERWISE PROVIDED FOR
- G01K13/00—Thermometers specially adapted for specific purposes
-
- 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]
- G01R31/382—Arrangements for monitoring battery or accumulator variables, e.g. SoC
-
- 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]
- G01R31/382—Arrangements for monitoring battery or accumulator variables, e.g. SoC
- G01R31/3842—Arrangements for monitoring battery or accumulator variables, e.g. SoC combining voltage and current measurements
-
- 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]
- G01R31/396—Acquisition or processing of data for testing or for monitoring individual cells or groups of cells within a battery
Landscapes
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Secondary Cells (AREA)
Abstract
The application provides a battery health state prediction method, a battery health state prediction device and electronic equipment, wherein the method comprises the steps of collecting real-time operation parameters of a battery of an electric vehicle under preset driving conditions according to preset sampling conditions; acquiring target operation parameters of the electric vehicle in each preset voltage range according to the real-time operation parameters; predicting battery health states of the batteries respectively corresponding to each preset voltage range according to the target operation parameters by utilizing a trained deep learning model; according to the battery health status respectively corresponding to the batteries in each preset voltage range, the target battery health status of the batteries is determined, and the battery health status prediction method based on artificial intelligence disclosed by the application can realize accurate battery health status prediction.
Description
Technical Field
The present invention relates to the field of batteries, and in particular, to a method and an apparatus for predicting a battery health state, and an electronic device.
Background
With the development of technology, electric vehicles are becoming more and more widely used. In order to ensure the safety and reliability of a Battery Management System (BMS) of an electric vehicle, the robustness and efficiency of a battery-related algorithm must be ensured. Since state of health (SOH) has a great influence on battery operation (such as a rapid charge protocol), state of charge (SOC), and state of power (SOP), the most critical of all algorithms related to the battery are the most important algorithms. Battery capacity and resistance are often considered as battery health indicators, and the prior art has generally used Rate Performance Testing (RPT) to directly measure the capacity and direct current impedance (DCR) of a battery by fully charging and discharging the battery and pulsing the battery at a certain SOC (e.g., 50%). However, the method of estimating the SOH value by fully discharging or charging the battery cannot be applied to an electric vehicle. Therefore, a new method is needed to enable estimation of battery capacity and resistance of an electric vehicle using collected partial charge-discharge operating data. There are two types of SOH estimation methods in the prior art, model-based methods and data-driven methods.
Because of the complexity of the degradation mechanism of lithium ion batteries, it is very difficult to find a reliable physical model to predict SOH of a battery under various storage and cycling conditions. The physics-based models also involve a large number of nonlinear partial differential equation systems, which makes these models unsuitable for vehicular applications. Therefore, SOH estimation methods based on semi-empirical calendar and cycle life models are more popular. In order to find the correlation between battery capacity and direct current impedance (DCR) and time, energy throughput, SOC and temperature, it is necessary to periodically perform a Reference Performance Test (RPT) during life test and collect a large amount of storage and cycle data. However, the physical model obtained by applying this method may be limited to be applied only in driving scenarios very similar to the test conditions.
Another model-based approach is based on state/parameter observer design, where SOH is predicted as a parameter of a state space model by an adaptive algorithm such as numerical filtering. A state space model commonly used in the art is the Equivalent Circuit Model (ECM), in which the battery is represented as a simple resistor-capacitor circuit network. While these online monitoring methods have the major advantage of closed loop nature, an overly simplified state space model (such as ECMs) will result in significant unmodeled dynamics, making the SOH estimates generated inaccurate.
Disclosure of Invention
In order to solve the defects in the prior art, the main purpose of the invention is to provide a battery health state prediction method, a battery health state prediction device and electronic equipment, so as to solve the technical problems.
To achieve the above object, in a first aspect, the present invention provides a method for predicting a state of health of a battery, the method comprising:
Acquiring real-time operation parameters of a battery of the electric vehicle under a preset driving condition according to a preset sampling condition;
acquiring target operation parameters of the electric vehicle in each preset voltage range according to the real-time operation parameters;
predicting battery health states of the batteries respectively corresponding to each preset voltage range according to the target operation parameters by utilizing a trained deep learning model;
and determining the target battery health state of the battery according to the battery health states of the battery corresponding to the battery in each preset voltage range.
In some embodiments, the real-time operating parameters include real-time current, real-time voltage, and real-time temperature of the battery;
the obtaining the target operation parameters of the electric vehicle in each preset voltage range according to the real-time operation parameters comprises the following steps:
acquiring real-time current, real-time voltage and real-time temperature corresponding to the battery in each preset voltage range;
Determining average current, average voltage, average resistance and average temperature of the battery corresponding to each preset voltage range according to the real-time current, the real-time voltage and the real-time temperature;
Determining the corresponding total throughput of the battery in each preset voltage range according to the real-time current;
And determining the target operation parameter according to the total throughput, the average current, the average voltage, the average resistance and the average temperature.
In some embodiments, the method further comprises a training process of the deep learning model, the training process comprising:
Acquiring a historical data set, wherein the historical data set comprises historical operation parameters of a battery of the electric vehicle in a preset voltage range under the preset driving condition, which are obtained through measurement;
dividing the historical data set into a training data set and a test data set according to a preset dividing rule;
training an initial deep learning model by utilizing the training data set;
And testing the trained initial deep learning model by using the test data set, and determining the trained initial deep learning model as a trained deep learning model when the test result meets the preset condition.
In some embodiments, the determining the target battery state of health of the battery according to the battery state of health corresponding to the battery in each preset voltage range includes:
And determining the target health state of the battery according to the predicted health state of the battery respectively corresponding to each preset voltage range and the preset weight value corresponding to each preset voltage range.
In some embodiments, the method comprises:
and when the target health state does not meet the preset condition, judging that the battery is abnormal and sending out an alarm signal.
In some embodiments, the method comprises:
generating a measurement record comprising the target battery state of health and a generation time;
receiving a battery health state query request sent by a user, wherein the request comprises a request time;
and when the difference value between the request time and the generation time of the measurement record does not exceed a preset time threshold value, returning the target battery health state to the user.
In a second aspect, the present application provides a device for predicting the state of health of a battery, the device comprising:
the acquisition module is used for acquiring real-time operation parameters of a battery of the electric vehicle under preset driving conditions according to preset sampling conditions;
the acquisition module is used for acquiring target operation parameters of the electric vehicle in each preset voltage range according to the real-time operation parameters;
the prediction module is used for predicting the battery health state of the battery respectively corresponding to each preset voltage range according to the target operation parameters by using the trained deep learning model;
and the judging module is used for determining the target battery health state of the battery according to the battery health states of the battery corresponding to the battery in each preset voltage range.
In some embodiments, the real-time operation parameters include a real-time current, a real-time voltage, and a real-time temperature of the battery, and the obtaining module is further configured to obtain the real-time current, the real-time voltage, and the real-time temperature corresponding to the battery in each of the preset voltage ranges; determining average current, average voltage, average resistance and average temperature of the battery corresponding to each preset voltage range according to the real-time current, the real-time voltage and the real-time temperature; determining the corresponding total throughput of the battery in each preset voltage range according to the real-time current; and determining the target operation parameter according to the total throughput, the average current, the average voltage, the average resistance and the average temperature.
In a third aspect, the present application provides a computer readable storage medium storing computer instructions which, when run on a processing component of a computer, cause the processing component to perform the steps of the method as described above.
In a fourth aspect, the present application provides an electronic device, including:
one or more processors;
And a memory associated with the one or more processors, the memory for storing program instructions that, when read for execution by the one or more processors, perform the following:
Acquiring real-time operation parameters of a battery of the electric vehicle under a preset driving condition according to a preset sampling condition;
acquiring target operation parameters of the electric vehicle in each preset voltage range according to the real-time operation parameters;
predicting battery health states of the batteries respectively corresponding to each preset voltage range according to the target operation parameters by utilizing a trained deep learning model;
and determining the target battery health state of the battery according to the battery health states of the battery corresponding to the battery in each preset voltage range.
The beneficial effects achieved by the invention are as follows:
The application provides a battery health state prediction method, which comprises the steps of collecting real-time operation parameters of a battery of an electric vehicle under preset driving conditions according to preset sampling conditions; acquiring target operation parameters of the electric vehicle in each preset voltage range according to the real-time operation parameters; predicting battery health states of the batteries respectively corresponding to each preset voltage range according to the target operation parameters by utilizing a trained deep learning model; according to the battery health status respectively corresponding to the batteries in each preset voltage range, the target battery health status of the batteries is determined, and the battery health status prediction method based on artificial intelligence disclosed by the application can simulate and predict the health status of the batteries in corresponding driving situations more accurately and truly because the deep learning model can be obtained by training according to real driving data of the vehicle, thereby avoiding the defect that a physical model can only be applied to driving situations very similar to testing conditions, and the prediction result of the deep learning model trained by a large number of data sets is more accurate compared with the prediction method such as an equivalent circuit model in the prior art, and realizing accurate battery health status prediction.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings required for the description of the embodiments will be briefly described below, and it is apparent that the drawings in the following description are only some embodiments of the present invention, and other drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.
FIG. 1 is a flow chart of a deep learning model prediction provided by an embodiment of the present application;
FIG. 2 is a flow chart of a method provided by an embodiment of the present application;
FIG. 3 is a block diagram of an apparatus according to an embodiment of the present application;
FIG. 4 is a block diagram of an electronic device according to an embodiment of the present application;
Fig. 5 is a schematic diagram of battery operating parameters of an electric vehicle according to an embodiment of the present application.
Detailed Description
For the purpose of making the objects, technical solutions and advantages of the present invention more apparent, the technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present invention, and it is apparent that the described embodiments are only some embodiments of the present invention, not all embodiments of the present invention. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.
As described in the background art, the two types of battery state of health evaluation methods adopted in the prior art have different drawbacks, respectively. In order to solve the technical problems, the application provides a battery health state prediction method, which not only solves the defect that a physical model can only be applied to a driving scene very similar to a test condition in the prior art, but also avoids the problems that the equivalent circuit model and other methods cause obvious unmodeled dynamics and the generated SOH estimated value is inaccurate.
Example 1
Specifically, in order to implement the battery state of health prediction method disclosed by the application, a deep learning model needs to be trained in advance, and the training process of the model comprises the following steps:
s1, acquiring a historical data sample set, and dividing the historical data sample set into a training sample set and a test sample set;
The historical data sample set may be data collected from a real vehicle driving scenario, including operating parameters of the vehicle under corresponding driving conditions and corresponding battery health conditions. Due to the empirical nature of the data driven approach, a large amount of battery life data, i.e., historical samples, is essential to training, validating and testing the neural networks proposed by the present application. Historical samples were obtained by charge/discharge/storage test and Reference Performance Test (RPT), respectively. The test for acquiring life data starts with an initial RPT, i.e. the capacity and DCR of the new battery are measured at 25 ℃. The cells are then either stored at a certain temperature and SOC (storage test) or cycled continuously for 2-4 weeks under certain charge-discharge conditions (cycling test). Subsequently, a second RPT is performed to track the battery capacity and DCR, and then the battery is stored or cycled again for 2-4 weeks in order to obtain a sufficient historical sample of the battery.
Preferably, 70% of the historical samples may be divided into training samples and 30% of the historical samples may be divided into test samples. Assigning 30% of the data to the test can significantly reduce the risk of overfitting, thereby enhancing the robustness of the algorithm to online BMS applications.
Each history sample includes I avg,Vavg,Tavg,Ravg,Tavg,Wherein I avg represents the average current of the battery in the corresponding voltage range and under driving conditions, V avg represents the average voltage of the battery in the corresponding voltage range and under driving conditions, R avg represents the average resistance of the battery in the corresponding voltage range and under driving conditions, T avg represents the average temperature of the battery in the corresponding voltage range and under driving conditions,/>The total throughput of the battery under the corresponding voltage range and the driving condition is represented, namely the total throughput can be calculated according to the real-time current and the duration of the preset voltage range. Specifically, the average resistance RK corresponding to the historical sample K can be expressed as/>If I k+1-Ik > C/10, wherein VK+1 represents the average voltage corresponding to the historical sample K+1, I K+1 represents the average current corresponding to the historical sample K+1, V K represents the average voltage corresponding to the historical sample K, I K represents the average current corresponding to the historical sample K, and C represents a preset constant.
S2, training a preset deep learning model by using a training sample set;
Specifically, 60% of the training samples in the training sample set may be used to train the deep learning model, 20% of the training samples are used to verify the deep learning model, and 20% of the training samples are used to test the deep learning model when training. Preferably, the MATLAB deep learning tool box can be utilized to train, verify and test the deep learning model.
Corresponding battery capacity and DC impedance DCR can be set in each sample of the training sample set and the testing sample set simultaneously for model learning, so that the subsequent model can predict the battery capacity and DC impedance of the battery according to the target operation parameters.
S3, testing the deep learning model by using the test sample set, and determining the deep learning model to be a trained deep learning model when the test result meets the preset condition.
Specifically, after the trained deep learning model is obtained, the deep learning model can be further trained by using the operation parameters acquired under the actual driving scene of the vehicle and the corresponding battery health state, so as to improve the actual prediction effect of the model.
In one embodiment, the vehicle may interact with a deep learning model deployed at the cloud, and the collected real-time operating parameters are uploaded to the deep learning model, so that the deep learning model predicts and eventually generates a corresponding battery state of health and returns to the vehicle. The deep learning model deployed at the cloud can be further trained according to the operation parameters of a large number of vehicles under the real driving conditions, so that the accuracy of the deep learning model is improved.
After obtaining the trained deep learning model, as shown in fig. 1, a process of predicting the state of health of a battery by applying the battery state of health prediction method disclosed by the application comprises the following steps:
step one, acquiring real-time operation parameters of an electric vehicle under preset driving conditions;
The real-time operation parameters comprise real-time current, real-time voltage, real-time resistance, real-time temperature and real-time throughput of the battery, wherein the real-time resistance can be calculated according to the real-time current and the real-time voltage.
Step two, determining the average current, average voltage, average resistance and average temperature of the battery corresponding to each preset voltage range according to the real-time current, the real-time voltage, the real-time resistance and the real-time temperature;
Fig. 5 shows time ranges corresponding to when the electric vehicle is in a driving state and the Voltage of the battery is in preset Voltage ranges R1, R2 and R3, respectively, and real-time Current, real-time Voltage and real-time Temperature corresponding to each time range, respectively. According to the real-time current, the real-time voltage and the real-time temperature, the average current, the average voltage and the average temperature of the battery in the time ranges corresponding to R1, R2 and R3 can be obtained respectively. Meanwhile, corresponding average voltage can be calculated according to the real-time current and the real-time voltage. The total throughput of the battery in the corresponding voltage range can be calculated according to the real-time current and the time range of the preset voltage range.
According to the total throughput, the average current, the average voltage, the average resistance and the average temperature, the target operation parameters corresponding to each preset voltage range can be generated.
Predicting the battery health state of the battery respectively corresponding to each preset voltage range according to the target operation parameters by utilizing a trained deep learning model;
specifically, the predicted state of health SOH of the battery is defined according to the capacity of the battery and the dc impedance DCR, that is:
where SOH C and SOH R represent capacity-based SOH and direct current impedance-based SOH, respectively.
Step four, determining the target health state of the battery according to the predicted health state of the battery respectively corresponding to each preset voltage range and the preset weight value corresponding to each preset voltage range;
specifically, when the target health state does not meet the preset condition, the cloud end or the vehicle-mounted terminal of the vehicle can send an alarm signal to a user through the vehicle-mounted display device or through equipment such as the vehicle-mounted audio device, so that the user can repair or replace the battery in time, and potential safety hazards and driving mileage influence are avoided.
Specifically, the open circuit voltage OCV and current of the battery can be measured after the vehicle stops running for a long enough time, the state of charge corresponding to the open circuit voltage can be determined according to a preset open circuit voltage and state of charge SOC lookup table, and then according to the formulaWhere I represents current, t 2、t1 represents the time of acquisition of OCV 2 and OCV 1, respectively, SOC 2(OCV2) represents SOC 2 readings determined from a look-up table, and SOC 1(OCV1) represents SOC 1 readings determined from a look-up table.
The state of health of the battery is obtained.
At the same time, a health status measurement record including the target battery health status and the generation time may be generated. When a battery health state query request sent by a user of the vehicle is subsequently received and the difference value between the request time and the generation time of the query request does not exceed a preset time threshold, the user can return the target battery health state to be referred by the user.
Based on the battery state of health prediction method disclosed by the application, the vehicle can obtain a more accurate battery state of health (SOH) prediction result so as to further evaluate the state of charge (SOC) and the battery power State (SOP) which have a key influence on the service life of the battery according to the SOH.
Example two
Corresponding to the above embodiment, as shown in fig. 2, the present application discloses a method for predicting a battery state of health, which includes:
210. acquiring real-time operation parameters of a battery of the electric vehicle under a preset driving condition according to a preset sampling condition;
220. acquiring target operation parameters of the electric vehicle in each preset voltage range according to the real-time operation parameters;
Preferably, the real-time operation parameters include real-time current, real-time voltage and real-time temperature of the battery; the obtaining the target operation parameters of the electric vehicle in each preset voltage range according to the real-time operation parameters comprises the following steps:
221. acquiring real-time current, real-time voltage and real-time temperature corresponding to the battery in each preset voltage range;
222. determining average current, average voltage, average resistance and average temperature of the battery corresponding to each preset voltage range according to the real-time current, the real-time voltage and the real-time temperature;
223. determining the corresponding total throughput of the battery in each preset voltage range according to the real-time current;
224. And determining the target operation parameter according to the total throughput, the average current, the average voltage, the average resistance and the average temperature.
230. Predicting battery health states of the batteries respectively corresponding to each preset voltage range according to the target operation parameters by utilizing a trained deep learning model;
240. and determining the target battery health state of the battery according to the battery health states of the battery corresponding to the battery in each preset voltage range.
Preferably, the determining the target battery health status of the battery according to the battery health status of the battery corresponding to each preset voltage range includes:
241. And determining the target health state of the battery according to the predicted health state of the battery respectively corresponding to each preset voltage range and the preset weight value corresponding to each preset voltage range.
Preferably, the method further comprises a training process of the deep learning model, the training process comprising:
250. acquiring a historical data set, wherein the historical data set comprises historical operation parameters of a battery of the electric vehicle in a preset voltage range under the preset driving condition, which are obtained through measurement;
251. dividing the historical data set into a training data set and a test data set according to a preset dividing rule;
252. training an initial deep learning model by utilizing the training data set;
253. and testing the trained initial deep learning model by using the test data set, and determining the trained initial deep learning model as a trained deep learning model when the test result meets the preset condition.
Preferably, the method comprises;
260. And when the target health state does not meet the preset condition, judging that the battery is abnormal and sending out an alarm signal.
Preferably, the method comprises:
270. Generating a measurement record comprising the target battery state of health and a generation time;
271. receiving a battery health state query request sent by a user, wherein the request comprises a request time;
272. and when the difference value between the request time and the generation time of the measurement record does not exceed a preset time threshold value, returning the target battery health state to the user.
Example III
Corresponding to all the above embodiments, as shown in fig. 3, the present application provides a device for predicting a state of health of a battery, the device comprising:
the acquisition module 310 is configured to acquire real-time operation parameters of a battery of the electric vehicle under a preset driving condition according to a preset sampling condition;
an obtaining module 320, configured to obtain, according to the real-time operation parameters, target operation parameters of the electric vehicle within each preset voltage range;
A prediction module 330, configured to predict, according to the target operation parameter, a battery state of health of the battery corresponding to each preset voltage range, using a trained deep learning model;
The judging module 340 is configured to determine a target battery health status of the battery according to the battery health status of the battery corresponding to each preset voltage range.
Preferably, the real-time operation parameters include a real-time current, a real-time voltage and a real-time temperature of the battery, and the obtaining module 320 is further configured to obtain the real-time current, the real-time voltage and the real-time temperature corresponding to the battery in each preset voltage range; determining average current, average voltage, average resistance and average temperature of the battery corresponding to each preset voltage range according to the real-time current, the real-time voltage and the real-time temperature; determining the corresponding total throughput of the battery in each preset voltage range according to the real-time current; and determining the target operation parameter according to the total throughput, the average current, the average voltage, the average resistance and the average temperature.
Preferably, the device comprises a training module, a control module and a control module, wherein the training module is used for acquiring a historical data set, and the historical data set comprises the measured historical operation parameters of the battery of the electric vehicle in a preset voltage range under the preset driving condition; dividing the historical data set into a training data set and a test data set according to a preset dividing rule; training the deep learning model using the training dataset; and testing the deep learning model by using the test data set, and determining the deep learning model as a trained deep learning model when the test result meets the preset condition.
Preferably, the determining module 340 is further configured to determine the target health status of the battery according to the predicted health status of the battery corresponding to each preset voltage range and the preset weight value corresponding to each preset voltage range.
Preferably, the device further comprises an alarm module, which is used for judging that the battery is abnormal and sending out an alarm signal when the target health state does not meet a preset condition.
Preferably, the device further comprises a processing module for generating a measurement record containing the target battery state of health and a generation time; receiving a battery health state query request sent by a user, wherein the request comprises a request time; and when the difference value between the request time and the generation time of the measurement record does not exceed a preset time threshold value, returning the target battery health state to the user.
Example IV
Corresponding to the method and the device, an embodiment of the application provides an electronic device, which includes:
one or more processors; and a memory associated with the one or more processors, the memory for storing program instructions that, when read for execution by the one or more processors, perform the following:
Acquiring real-time operation parameters of a battery of the electric vehicle under a preset driving condition according to a preset sampling condition;
acquiring target operation parameters of the electric vehicle in each preset voltage range according to the real-time operation parameters;
predicting battery health states of the batteries respectively corresponding to each preset voltage range according to the target operation parameters by utilizing a trained deep learning model;
and determining the target battery health state of the battery according to the battery health states of the battery corresponding to the battery in each preset voltage range.
Fig. 4 illustrates an architecture of an electronic device, which may include a processor 1510, a video display adapter 1511, a disk drive 1512, an input/output interface 1513, a network interface 1514, and a memory 1520, among others. The processor 1510, the video display adapter 1511, the disk drive 1512, the input/output interface 1513, the network interface 1514, and the memory 1520 may be communicatively connected by a communication bus 1530.
The processor 1510 may be implemented by a general-purpose CPU (Central Processing Unit ), a microprocessor, an Application SPECIFIC INTEGRATED Circuit (ASIC), or one or more integrated circuits (ics), etc. for executing related programs to implement the technical solution provided by the present application.
The Memory 1520 may be implemented in the form of ROM (Read Only Memory), RAM (Random Access Memory ), static storage, dynamic storage, or the like. The memory 1520 may store an operating system 1521 for controlling the operation of the electronic device 1500, a Basic Input Output System (BIOS) 1522 for controlling the low-level operation of the electronic device 1500. In addition, a web browser 1523, data storage management 1524, and an icon font processing system 1525, etc. may also be stored. The icon font processing system 1525 may be an application program that implements the operations of the foregoing steps in the embodiment of the present application. In general, when the present application is implemented in software or firmware, the relevant program code is stored in the memory 1520 and executed by the processor 1510. The input/output interface 1513 is used for connecting with an input/output module to realize information input and output. The input/output module may be configured as a component in a device (not shown) or may be external to the device to provide corresponding functionality. Wherein the input devices may include a keyboard, mouse, touch screen, microphone, various types of sensors, etc., and the output devices may include a display, speaker, vibrator, indicator lights, etc.
The network interface 1514 is used to connect communication modules (not shown) to enable communication interactions of the present device with other devices. The communication module may implement communication through a wired manner (such as USB, network cable, etc.), or may implement communication through a wireless manner (such as mobile network, WIFI, bluetooth, etc.).
Bus 1530 includes a path for transporting information between various components of the device (e.g., processor 1510, video display adapter 1511, disk drive 1512, input/output interface 1513, network interface 1514, and memory 1520).
In addition, the electronic device 1500 may also obtain information of specific acquisition conditions from the virtual resource object acquisition condition information database 1541 for making condition judgment, and so on.
It is noted that although the above devices illustrate only the processor 1510, video display adapter 1511, disk drive 1512, input/output interface 1513, network interface 1514, memory 1520, bus 1530, etc., the device may include other components necessary to achieve proper functioning in a particular implementation. Furthermore, it will be appreciated by those skilled in the art that the apparatus may include only the components necessary to implement the present application, and not all of the components shown in the drawings.
From the above description of embodiments, it will be apparent to those skilled in the art that the present application may be implemented in software plus a necessary general hardware platform. Based on such understanding, the technical solution of the present application may be embodied essentially or in a part contributing to the prior art in the form of a software product, which may be stored in a storage medium, such as a ROM/RAM, a magnetic disk, an optical disk, etc., including several instructions for causing a computer device (which may be a personal computer, a cloud server, or a network device, etc.) to execute the method described in the embodiments or some parts of the embodiments of the present application.
In this specification, each embodiment is described in a progressive manner, and identical and similar parts of each embodiment are all referred to each other, and each embodiment mainly describes differences from other embodiments. In particular, for a system or system embodiment, since it is substantially similar to a method embodiment, the description is relatively simple, with reference to the description of the method embodiment being made in part. The systems and system embodiments described above are merely illustrative, wherein the elements illustrated as separate elements may or may not be physically separate, and the elements shown as elements may or may not be physical elements, may be located in one place, or may be distributed over a plurality of network elements. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of this embodiment. Those of ordinary skill in the art will understand and implement the present invention without undue burden.
The foregoing description of the preferred embodiments of the invention is not intended to limit the invention to the precise form disclosed, and any such modifications, equivalents, and alternatives falling within the spirit and scope of the invention are intended to be included within the scope of the invention.
Claims (8)
1. A method of predicting a state of health of a battery, the method comprising:
Acquiring real-time operation parameters of a battery of the electric vehicle under a preset driving condition according to a preset sampling condition;
acquiring target operation parameters of the electric vehicle in each preset voltage range according to the real-time operation parameters;
predicting battery health states of the batteries respectively corresponding to each preset voltage range according to the target operation parameters by utilizing a trained deep learning model;
Determining a target health state of the battery according to the predicted health state of the battery respectively corresponding to each preset voltage range and a preset weight value corresponding to each preset voltage range;
the training process of the deep learning model comprises the following steps:
Acquiring a historical data set, wherein the historical data set comprises historical operation parameters of a battery of the electric vehicle in a preset voltage range under the preset driving condition, which are obtained through measurement;
dividing the historical data set into a training data set and a test data set according to a preset dividing rule;
training an initial deep learning model by utilizing the training data set;
Testing the trained initial deep learning model by using the test data set, determining the trained initial deep learning model as a trained deep learning model when a test result meets a preset condition, and deploying the trained deep learning model to a cloud;
and transmitting the real-time operation parameters of the batteries of the plurality of electric vehicles under the preset driving conditions into the trained deep learning model for training to obtain a final trained deep learning model.
2. The prediction method according to claim 1, wherein the real-time operating parameters include real-time current, real-time voltage, and real-time temperature of the battery;
the obtaining the target operation parameters of the electric vehicle in each preset voltage range according to the real-time operation parameters comprises the following steps:
acquiring real-time current, real-time voltage and real-time temperature corresponding to the battery in each preset voltage range;
Determining average current, average voltage, average resistance and average temperature of the battery corresponding to each preset voltage range according to the real-time current, the real-time voltage and the real-time temperature;
Determining the corresponding total throughput of the battery in each preset voltage range according to the real-time current;
And determining the target operation parameter according to the total throughput, the average current, the average voltage, the average resistance and the average temperature.
3. A prediction method according to claim 1 or 2, characterized in that the method comprises:
and when the target health state does not meet the preset condition, judging that the battery is abnormal and sending out an alarm signal.
4. A prediction method according to claim 1 or 2, characterized in that the method comprises:
generating a measurement record comprising the target health status and a generation time;
receiving a battery health state query request sent by a user, wherein the request comprises a request time;
And when the difference value between the request time and the generation time of the measurement record does not exceed a preset time threshold value, returning the target health state to the user.
5. A battery state of health prediction apparatus, the apparatus comprising:
the acquisition module is used for acquiring real-time operation parameters of a battery of the electric vehicle under preset driving conditions according to preset sampling conditions;
the acquisition module is used for acquiring target operation parameters of the electric vehicle in each preset voltage range according to the real-time operation parameters;
the prediction module is used for predicting the battery health state of the battery respectively corresponding to each preset voltage range according to the target operation parameters by using the trained deep learning model;
The judging module is used for determining the target health state of the battery according to the predicted health state of the battery corresponding to each preset voltage range and the preset weight value corresponding to each preset voltage range;
the training process of the deep learning model comprises the following steps:
Acquiring a historical data set, wherein the historical data set comprises historical operation parameters of a battery of the electric vehicle in a preset voltage range under the preset driving condition, which are obtained through measurement;
dividing the historical data set into a training data set and a test data set according to a preset dividing rule;
training an initial deep learning model by utilizing the training data set;
Testing the trained initial deep learning model by using the test data set, and determining the trained initial deep learning model as a trained deep learning model when a test result meets a preset condition; deploying the trained deep learning model to a cloud;
and transmitting the real-time operation parameters of the batteries of the plurality of electric vehicles under the preset driving conditions into the trained deep learning model for training to obtain a final trained deep learning model.
6. The prediction apparatus according to claim 5, wherein the real-time operation parameters include a real-time current, a real-time voltage, and a real-time temperature of the battery, and the obtaining module is further configured to obtain the real-time current, the real-time voltage, and the real-time temperature corresponding to the battery in each of the preset voltage ranges; determining average current, average voltage, average resistance and average temperature of the battery corresponding to each preset voltage range according to the real-time current, the real-time voltage and the real-time temperature; determining the corresponding total throughput of the battery in each preset voltage range according to the real-time current; and determining the target operation parameter according to the total throughput, the average current, the average voltage, the average resistance and the average temperature.
7. A computer readable storage medium storing computer instructions which, when run on a processing component of a computer, cause the processing component to perform the steps of the method of any of claims 1-4.
8. An electronic device, the electronic device comprising:
one or more processors;
And a memory associated with the one or more processors, the memory for storing program instructions that, when read for execution by the one or more processors, perform the following:
Acquiring real-time operation parameters of a battery of the electric vehicle under a preset driving condition according to a preset sampling condition;
acquiring target operation parameters of the electric vehicle in each preset voltage range according to the real-time operation parameters;
predicting battery health states of the batteries respectively corresponding to each preset voltage range according to the target operation parameters by utilizing a trained deep learning model;
Determining a target health state of the battery according to the predicted health state of the battery respectively corresponding to each preset voltage range and a preset weight value corresponding to each preset voltage range;
the training process of the deep learning model comprises the following steps:
Acquiring a historical data set, wherein the historical data set comprises historical operation parameters of a battery of the electric vehicle in a preset voltage range under the preset driving condition, which are obtained through measurement;
dividing the historical data set into a training data set and a test data set according to a preset dividing rule;
training an initial deep learning model by utilizing the training data set;
Testing the trained initial deep learning model by using the test data set, and determining the trained initial deep learning model as a trained deep learning model when a test result meets a preset condition; deploying the trained deep learning model to a cloud;
and transmitting the real-time operation parameters of the batteries of the plurality of electric vehicles under the preset driving conditions into the trained deep learning model for training to obtain a final trained deep learning model.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110479505.0A CN113189495B (en) | 2021-04-30 | 2021-04-30 | Battery health state prediction method and device and electronic equipment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110479505.0A CN113189495B (en) | 2021-04-30 | 2021-04-30 | Battery health state prediction method and device and electronic equipment |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN113189495A CN113189495A (en) | 2021-07-30 |
| CN113189495B true CN113189495B (en) | 2024-05-28 |
Family
ID=76982927
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110479505.0A Active CN113189495B (en) | 2021-04-30 | 2021-04-30 | Battery health state prediction method and device and electronic equipment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113189495B (en) |
Families Citing this family (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114200334A (en) * | 2021-11-24 | 2022-03-18 | 三一汽车起重机械有限公司 | Storage battery early warning method and device, vehicle and medium |
| CN114355224B (en) * | 2022-03-17 | 2022-06-28 | 深圳市信润富联数字科技有限公司 | Battery health state prediction method and device, electronic device and readable storage medium |
| CN115184805A (en) * | 2022-06-21 | 2022-10-14 | 东莞新能安科技有限公司 | Battery health state acquisition method, device, equipment and computer program product |
| WO2024000145A1 (en) * | 2022-06-28 | 2024-01-04 | 宁德时代新能源科技股份有限公司 | Battery soh detection method and apparatus, device, and storage medium |
| CN116400227A (en) * | 2023-06-08 | 2023-07-07 | 长安大学 | SOH prediction method, system, equipment and medium for power battery of electric automobile |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105158699A (en) * | 2015-09-14 | 2015-12-16 | 北京新能源汽车股份有限公司 | Battery health state detection method and apparatus |
| KR20170142451A (en) * | 2016-06-17 | 2017-12-28 | 주식회사 엘지화학 | Battery management system, battery pack and method for charging battery |
| CN109633452A (en) * | 2018-12-24 | 2019-04-16 | 广东省智能制造研究所 | A kind of battery health degree detection method and detection device |
| CN110118944A (en) * | 2019-06-05 | 2019-08-13 | 杭州华塑加达网络科技有限公司 | The estimating system and method for cell health state |
| CN110542867A (en) * | 2019-08-05 | 2019-12-06 | 燕山大学 | Battery health state evaluation method and device and storage medium |
| CN111832220A (en) * | 2020-06-16 | 2020-10-27 | 天津大学 | Lithium ion battery health state estimation method based on codec model |
-
2021
- 2021-04-30 CN CN202110479505.0A patent/CN113189495B/en active Active
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105158699A (en) * | 2015-09-14 | 2015-12-16 | 北京新能源汽车股份有限公司 | Battery health state detection method and apparatus |
| KR20170142451A (en) * | 2016-06-17 | 2017-12-28 | 주식회사 엘지화학 | Battery management system, battery pack and method for charging battery |
| CN109633452A (en) * | 2018-12-24 | 2019-04-16 | 广东省智能制造研究所 | A kind of battery health degree detection method and detection device |
| CN110118944A (en) * | 2019-06-05 | 2019-08-13 | 杭州华塑加达网络科技有限公司 | The estimating system and method for cell health state |
| CN110542867A (en) * | 2019-08-05 | 2019-12-06 | 燕山大学 | Battery health state evaluation method and device and storage medium |
| CN111832220A (en) * | 2020-06-16 | 2020-10-27 | 天津大学 | Lithium ion battery health state estimation method based on codec model |
Non-Patent Citations (3)
| Title |
|---|
| 基于IACA-SVR的电池SOH预测研究;康道新 等;电力电子技术;54(09);62-66 * |
| 基于卷积神经网络的锂离子电池SOH估算;李超然 等;电工技术学报(19);4106-4119 * |
| 基于极限学习机的锂电池健康状态预测;陈婕 等;软件(第02期);191-196 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN113189495A (en) | 2021-07-30 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN113189495B (en) | Battery health state prediction method and device and electronic equipment | |
| Li et al. | Online capacity estimation of lithium-ion batteries with deep long short-term memory networks | |
| Chen et al. | A new state-of-health estimation method for lithium-ion batteries through the intrinsic relationship between ohmic internal resistance and capacity | |
| Dong et al. | Dynamic Bayesian network-based lithium-ion battery health prognosis for electric vehicles | |
| Sbarufatti et al. | Adaptive prognosis of lithium-ion batteries based on the combination of particle filters and radial basis function neural networks | |
| Dong et al. | Data-driven battery health prognosis using adaptive Brownian motion model | |
| CN108254696B (en) | Battery health state evaluation method and system | |
| Berecibar et al. | State of health estimation algorithm of LiFePO4 battery packs based on differential voltage curves for battery management system application | |
| Jiang et al. | An adaptive capacity estimation approach for lithium-ion battery using 10-min relaxation voltage within high state of charge range | |
| CN112068004A (en) | Method and device for determining battery abnormity and battery charging remaining time | |
| CN109100655B (en) | Data processing method and device for power battery | |
| CN114371409B (en) | Training method of battery state prediction model, battery state prediction method and device | |
| CN108205114B (en) | Method and system for predicting service life of battery | |
| Zhu et al. | The SOH estimation of LiFePO4 battery based on internal resistance with Grey Markov Chain | |
| CN113728242A (en) | Characterization of lithium evolution in rechargeable batteries | |
| CN116609676B (en) | Method and system for monitoring state of hybrid energy storage battery based on big data processing | |
| KR20220007028A (en) | Apparatus for Mining Battery Characteristic Data Having Sensitivity to Solid Phase Diffusion Coefficient of Battery Electrode and Method thereof | |
| CN113219357A (en) | Battery pack health state calculation method and system and electronic equipment | |
| Xue et al. | Battery degradation modelling and prediction with combination of machine learning and semi-empirical methods | |
| CN114879070A (en) | Battery state evaluation method and related equipment | |
| Liu et al. | Capacity evaluation and degradation analysis of lithium-ion battery packs for on-road electric vehicles | |
| KR20230080112A (en) | Battery diagnostic device for predicting the current state of the battery | |
| Ko et al. | Using tens of seconds of relaxation voltage to estimate open circuit voltage and state of health of lithium ion batteries | |
| CN116031508A (en) | Lithium ion battery management system and method based on deep learning | |
| CN116080470A (en) | Power battery monitoring method and device for electric automobile, server and medium |
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 |