CN110837058B - Battery pack health state evaluation device and evaluation method based on big data - Google Patents
Battery pack health state evaluation device and evaluation method based on big data Download PDFInfo
- Publication number
- CN110837058B CN110837058B CN201911073725.2A CN201911073725A CN110837058B CN 110837058 B CN110837058 B CN 110837058B CN 201911073725 A CN201911073725 A CN 201911073725A CN 110837058 B CN110837058 B CN 110837058B
- Authority
- CN
- China
- Prior art keywords
- battery
- battery pack
- module
- evaluated
- data
- 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
Images
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]
- G01R31/396—Acquisition or processing of data for testing or for monitoring individual cells or groups of cells within a battery
-
- 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
-
- 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
Landscapes
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Charge And Discharge Circuits For Batteries Or The Like (AREA)
Abstract
The application discloses group battery health status evaluation device based on big data, including battery information acquisition module, customer end, wireless communication module, big data cloud platform, battery protection module and battery balance management module. And the big data cloud platform evaluates and further corrects the health state of the battery pack through the improved BP neural network model according to the acquired parameter information of the battery pack and related data in the big data, displays the fault information through the client and takes protective measures through the battery protection module. On the other hand, the application also discloses an evaluation method based on the evaluation device. The device and the method do not depend on the accuracy of a single battery model, are not limited to a certain specific type of battery, and have high applicability; the big data and cloud computing technology are adopted to meet the requirement on the real-time performance of the algorithm; the method attaches importance to human-computer interaction, and avoids the cost rise caused by randomness in a humanized and flexible way.
Description
Technical Field
The invention relates to battery health state assessment, in particular to a battery pack health state assessment device and method based on big data.
Background
With the development of science and technology and the continuous progress of the technology level, the contradiction between the lack of non-renewable energy and the huge demand of the society for energy is increasingly excited, and the problem of environmental pollution is paid attention by various circles of the society. Meanwhile, the development of emerging technologies provides the possibility for new energy. The storage battery is an essential important component in the field of new energy power, and the battery can not be left in the power utilization fields of photovoltaic power generation, wind power generation and power generation, electric automobiles, emergency power supply and the like.
The reliability and safety of batteries are of greatest concern in battery applications, particularly in high capacity battery applications. The aging of the storage battery is an unavoidable and long-term gradual change process, the health state of the storage battery is influenced by various factors such as temperature, current multiplying power, cut-off voltage and the like, and the attenuation process of the health state of the storage battery is a long-term and complex process. The battery health condition of the storage battery is directly related to the performance of the storage battery in work, so that the service life and the working condition of the storage battery are reflected. The health state of the storage battery can be mastered, so that the normal work of the storage battery can be ensured, the sudden interruption of the whole system is avoided, and the damage or the occurrence of an accident is prevented. The method has important reference for accurately evaluating the health state of the storage battery, judging whether the storage battery needs to be replaced or not and evaluating the value of the storage battery, and has important significance for popularization and generalization of the storage battery.
The current battery state of health evaluation devices for some storage batteries have the following problems: the requirement on the calculation speed is too high, so that the cost of the device is too high; the application range is single only for a certain type of storage battery; the method based on engineering experience data is used, the battery health state of the storage battery cannot be accurately evaluated in real time, and the use value is poor.
Disclosure of Invention
The purpose of the invention is as follows: the application aims to provide a battery pack health state assessment device and method based on big data, and the defects that the existing assessment device cannot accurately assess the health state of a battery pack in real time and is not high in applicability are overcome.
The technical scheme is as follows: the application provides a battery pack health state evaluation device based on big data, which comprises a battery information acquisition module, a client, a wireless communication module, a big data cloud platform, a battery protection module and a battery balance management module; the battery information acquisition module is electrically connected with the client and is used for acquiring parameter information of the battery pack to be evaluated and transmitting the parameter information to the client; the client is used for displaying and storing the received parameter information and the health state of the battery pack and sending the parameter information to the big data cloud platform through the wireless communication module; the big data cloud platform comprises a data exchange module, a data storage module and a data processing module; the data exchange module is used for receiving and sending information needing interaction; the data storage module is used for storing parameter information of the battery pack to be evaluated and data related to the health state of the battery pack to be evaluated in the internet; the data processing module is used for analyzing the health state of the battery to be evaluated according to the information in the data storage module; the battery protection module is electrically connected with the client and the wireless communication module and is used for receiving control instructions sent by the client and the big data cloud platform, disconnecting the fault battery pack and sending fault warning information to the client; the battery balancing module is electrically connected with the client and used for balancing the residual electric quantity of each single battery in the working process of the battery pack and sending a balancing result to the client for displaying.
Further, the parameter information includes: the battery pack comprises a single battery, a battery pack, a battery type, the number of the single batteries, service time, a battery brand and a battery model.
Further, the client can acquire the parameter information of the battery pack to be evaluated in a manual input mode.
Further, the control instruction received by the battery protection module includes: the big data cloud platform monitors an instruction sent out when the fault early warning is carried out, and the client receives an instruction sent out when the health state of the battery is lower than a set value.
Further, the data exchange module comprises a client communication module and an emergency communication module; the client communication module is used for exchanging data with a client; the emergency communication module is used for sending a fault early warning signal to the wireless communication module.
Further, the data storage module comprises a battery database and a cloud database; the battery database is a distributed database and is used for storing all data of the battery pack to be evaluated and the battery pack already evaluated; the cloud database is a distributed database and is used for acquiring and storing data related to the battery pack to be evaluated through the internet.
Further, the data processing module comprises a data screening module, a BP neural network module and an output correction module; the data screening module is used for preprocessing the received power parameters; the BP neural network module takes the preprocessed parameter information and data related to the battery pack to be evaluated in the cloud database as the input of the BP neural network module, and takes the health state of the battery pack to be evaluated as the output of the BP neural network module; and the output correction module is used for correcting the output confidence coefficient of the BP neural network module.
Further, if the corrected confidence coefficient is higher than a threshold value, updating the BP neural network model and the health state of the battery pack to be evaluated, and transmitting the health state of the battery pack to be evaluated to the data exchange module; otherwise, the health state of the battery pack to be evaluated is calculated by utilizing the last effective BP neural network model and is transmitted to the data exchange module.
On the other hand, the application also provides an evaluation method based on the battery pack state of health evaluation device, which comprises the following steps:
(1) acquiring parameter information of a battery pack to be evaluated, wherein the parameter information comprises the highest voltage and the lowest voltage of a single battery, the highest temperature and the lowest temperature of the single battery, the external environment temperature, the total voltage of the battery pack, the total current of the battery pack, the battery type, the number of the single batteries, the service time, the battery brand and the battery model;
(2) preprocessing the parameter information to obtain processed parameter information as an input item for evaluating the health state of the battery pack, and obtaining the health state S of the battery pack to be evaluated according to the information in the cloud databaseiThe calculation of (A) establishes a period T, each period being Ti(i≥1)；
(3) In the period TiEstablishing a BP neural network model M based on an improved BP neural network algorithm according to the input items of the health state evaluation of the battery packiCalculating the period TiState of health output value S 'of internal-to-be-evaluated battery pack'iConfidence of health status is a default value
(4) Deriving T from battery pack usage, operating environment, battery brand, battery type, and battery average life in the cloud databaseiBattery state of health S over a periodiConfidence correction value of
The corrected confidence C is calculated by the following formulaiReducing the error to battery health state S in the calculation processiThe influence of (a):
corrected confidence
Comparing confidence threshold values
And the corrected confidence coefficient CiIf, if
Output value S 'considering battery health status'iEffectively, mixing S'iAs TiState of health S of battery pack during cyclei(ii) a Otherwise, the BP neural network model M in the last period is utilizedi-1BP neural network model M as the present cycleiI.e. Mi＝Mi-1Calculate TiHealth state output value S 'of battery pack to be evaluated in period'iAs TiState of health S of battery pack during cyclei；
(5) The state of health S of the batteryiTransmitting to and receiving data from the client, repeating (1) - (4) and starting next period Ti+1Internal battery state of health Si+1And (4) calculating.
Has the advantages that: compared with the prior art, the method has the following advantages:
(1) the battery health state model of the battery pack to be evaluated is constructed by adopting a data driving method, the accuracy of a single battery model in the battery pack is not depended on, the battery pack is not limited to a certain specific type of battery, the application range is wide, and the universality is strong;
(2) the battery data set of the battery pack to be evaluated is processed in a large-scale parallel mode by adopting a big data technology, so that the speed of obtaining the health state of the battery is accelerated by data mining, and the data storage module, namely a distributed database, is favorable for exerting the advantages of the data mining technology;
(3) the distributed computing speed of the cloud platform is enough to meet the real-time requirement of the algorithm, the battery health state of the battery pack to be evaluated can be calculated in real time, and the practical value of the evaluation device is improved;
(4) in the aspect of man-machine interaction, a way for manually inputting a system is added for certain information which is difficult to be identified by a machine and is helpful to the calculation of the health state of the battery, and the cost rise of automatic identification of the machine caused by unpredictable and strong random factors such as the use and the use environment of the battery pack to be evaluated is flexibly avoided.
Drawings
FIG. 1 is a schematic diagram of a battery health status evaluation apparatus according to the present invention;
fig. 2 is a flowchart of a battery pack state of health assessment method according to the present invention.
Detailed Description
The present application is further described below with reference to the drawings and examples.
One aspect of the application discloses a battery pack health state assessment device based on big data, as shown in fig. 1, the battery pack health state assessment device comprises a battery information acquisition module, a client, a wireless communication module, a big data cloud platform, a battery protection module and a battery balance management module.
The battery information acquisition module is electrically connected with the client and is used for acquiring parameter information of the battery pack to be evaluated and transmitting the parameter information to the client; the collected parameter information includes: the battery pack comprises a single battery, a battery pack, a battery type, the number of the single batteries, service time, a battery brand and a battery model.
The client is used for displaying and storing the received parameter information and the health state of the battery pack and sending the parameter information to the big data cloud platform through the wireless communication module; under the condition that the battery information acquisition module cannot automatically identify and acquire the battery information, the client can acquire parameter information of the battery pack to be evaluated in a manual input mode, such as information of the use, working environment and the like of the battery pack. When the evaluation device of this embodiment is used for photovoltaic power generation on water, the information such as temperature, humidity and illumination intensity of this photovoltaic power generation platform's on water operational client sends this photovoltaic power generation platform's on water operational environment to big data cloud platform through wireless communication module.
The big data cloud platform comprises a data exchange module, a data storage module and a data processing module. The data exchange module is used for receiving and sending information needing interaction and comprises a client communication module and an emergency communication module; the client communication module is used for exchanging data with the client by means of the wireless communication module; the emergency communication module is used for sending a fault early warning signal to the wireless communication module.
The data storage module is used for storing parameter information of the battery pack to be evaluated and data related to the health state of the battery pack to be evaluated in the internet; the data storage module comprises a battery database and a cloud database; the battery database is a distributed database and is used for storing all data of the battery pack to be evaluated and the battery pack already evaluated; the cloud database is a distributed database and is used for acquiring and storing data related to the battery pack to be evaluated through the internet.
The data processing module is used for analyzing the health state of the battery to be evaluated according to the information in the data storage module and comprises a data screening module, a BP neural network module and an output correction module. The data screening module is used for preprocessing the received power parameters, for example, normalizing the power parameters, and reducing the calculation amount of the data processing module so as to improve the operation speed; the BP neural network module takes the preprocessed parameter information and data related to the battery pack to be evaluated in the cloud database as the input of the BP neural network module, and takes the health state of the battery pack to be evaluated as the output of the BP neural network module; and the output correction module is used for correcting the output confidence coefficient of the BP neural network module.
The battery protection module is electrically connected with the client and the wireless communication module and is used for receiving control instructions sent by the client and the big data cloud platform, disconnecting the fault battery pack and sending fault warning information to the client. The control instructions include: the big data cloud platform monitors an instruction sent out when the fault early warning is carried out, and the client receives an instruction sent out when the health state of the battery is lower than a set value (80%). When sending out fault early warning, the big data cloud platform directly transmits the fault early warning to the battery protection module through the wireless communication module, and the battery protection module cuts off the connection between the fault battery pack and an external circuit and sends fault warning information to the client side to remind a user to replace the battery.
The battery balancing module is electrically connected with the client and used for balancing the residual electric quantity of each single battery in the working process of the battery pack, so that the inconsistency among the single batteries is weakened, the charging and discharging quality of the battery pack is improved, the working life of the battery pack is prolonged, the calculation workload of the health state of the battery is reduced, and the balancing result is sent to the client for display.
On the other hand, the application also provides an evaluation method based on the battery pack state of health evaluation device, and the method comprises the following steps:
(1) acquiring parameter information of a battery pack to be evaluated, wherein the parameter information comprises the highest voltage and the lowest voltage of a single battery, the highest temperature and the lowest temperature of the single battery, the external environment temperature, the total voltage of the battery pack, the total current of the battery pack, the battery type, the number of the single batteries, the service time, the battery brand and the battery model;
(2) preprocessing the parameter information to obtain processed parameter information serving as an input item for estimating the health state of the battery pack, and according to the average service life T of batteries of the same brand and the same model of the battery pack to be estimated in the cloud databaselFor the state of health S of the battery to be evaluatediIs calculated to make a period T ═ TlA/100 with each period of Ti(Tl/100≥i≥1)；
(3) In the period TiEstablishing a BP neural network model M based on an improved BP neural network algorithm according to the input items of the health state evaluation of the battery packiCalculating the period TiState of health output value S 'of internal-to-be-evaluated battery pack'iConfidence of health status is a default value
The improved part of the algorithm is only detailed in the 1 st and 2 nd periods, and the establishment of the conventional BP neural network model is not repeated. The specific process is as follows:
when i is 1, i.e. the 1 st period T1The state of health of the battery is not calculated, the occurrence of abnormal data is recorded, and the charging time T of the evaluated battery pack for the Z th time (Z is more than or equal to 1 and less than or equal to Z, and Z is the total charging time of the battery pack in the 1 st period) is recordedczAnd the current capacity B of the battery pack after charging1z: retrieving the current capacity of the battery pack of the same type of battery in the cloud database under the same condition (the z charging in the 1 st period), and if the current capacity B of the battery pack to be evaluated1zIf the deviation from the maximum deviation value Lambda does not exceed the preset maximum deviation value Lambda, the data is considered to be abnormal-free data, i.e. the data is considered to be in the period T1The state of health of the internal battery is 100%; and otherwise, judging that abnormal data appear, sending a fault early warning signal to the client by the big data cloud platform, and cutting off the connection between the battery pack and an external circuit by the battery protection module.
Knowing the rated capacity B of the battery pack to be evaluated, the state of health SOH of the battery pack after the j-th charging is:
starting a second period T when i is 22Calculation of battery state of health within.
The input vector in the BP neural network model is X2＝(x21,x22,……,x2nIn)TWhere nIn is the number of input layer nodes and the hidden layer output vector is Y2＝(y21,y22,……,y2nHide)TWherein nHide is the number of hidden layer nodes and m is equal to nHide, and the output vector of the output layer is O2＝ok，ωaj、νjkThe connection weight between the input layer and the hidden layer and the connection weight between the hidden layer and the output layer are respectively.
Establishing a BP neural network model M of a three-layer network structure2As shown in formula:
output layerThere are 1 number of nodes that are,
the hidden layer has m nodes which are,
in the equations (2) and (3), the transformation functions f (x) use unipolar Sigmoid functions, as shown in the following equation:
the weight vij、ωjkAssigned a value of [0,1]，yiThe learning rate η is assigned to a fraction within a (0,1) interval for the elements of the output vector of the hidden layer, and the error E is initialized to zero.
Dividing the electrical parameter data transmitted to the BP neural network module by the data transmission module in the (i-1) th cycle, namely the 1 st cycle, into Z groups according to the charging times, wherein each group of data has n values, and assigning the 1 st group of data as an input item to an input vector X in the 2 nd cycle2＝(x21,x22,……,x2nIn)TWhere Z is nIn with equations (2) and (3), the actual output vector O of the model is calculatedk. The battery state of health in the i-1 th cycle is assigned to the desired output vector D. (
Outputting the layer error signal according to the calculation
And an implicit layer error signal
The calculation formula is as shown in formula (7):
calculating the weight variable quantity according to the formula (8):
updating the weight of each layer according to the formula (9):
and recording the input 1 group of data as the z-th input, wherein z is 1.
When z is<And Z, continuing to input the next group of data, and enabling Z to be Z + 1. Repeating the above process until Z equals Z, that is, completing training of all samples, and ending the period T2The training process for the model.
Using the 2 nd period T2Electrical parameter data transmitted from internal data transmission module to BP neural network module by using BP neural network model MiCalculating the battery state of health S of the evaluated battery pack in the ith (i-2) cyclei(i ═ 2); state of health S of the battery2Is defaulted to
(4) Deriving T from battery pack usage, operating environment, battery brand, battery type, and battery average life in the cloud databaseiBattery state of health S over a periodiConfidence correction value of
The corrected confidence C is calculated by the following formulaiReducing the error to battery health state S in the calculation processiThe influence of (a):
corrected confidence
Comparing confidence threshold values
And the corrected confidence coefficient CiIf, if
Output value S 'considering battery health status'iEffectively, let S' i be TiState of health S of battery pack during cyclei(ii) a Otherwise, the BP neural network model M in the last period is utilizedi-1BP neural network model M as the present cycleiI.e. Mi＝Mi-1Calculate TiHealth state output value S 'of battery pack to be evaluated in period'iAs TiState of health S of battery pack during cyclei；
(5) The state of health S of the batteryiTransmitting to and receiving data from the client, repeating (1) - (4) and starting next period Ti+1Internal battery state of health Si+1And (4) calculating.
As will be appreciated by one skilled in the art, embodiments of the present application may be provided as a method, system, or computer program product. Accordingly, the present application may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present application may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and the like) having computer-usable program code embodied therein.
The present application is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the application. It will be understood that each flow and/or block of the flow diagrams and/or block diagrams, and combinations of flows and/or blocks in the flow diagrams and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
Finally, it should be noted that: the above embodiments are only for illustrating the technical solutions of the present invention and not for limiting the same, and although the present invention is described in detail with reference to the above embodiments, those of ordinary skill in the art should understand that: modifications and equivalents may be made to the embodiments of the invention without departing from the spirit and scope of the invention, which is to be covered by the claims.
Claims (7)
1. A big data-based battery pack state of health assessment apparatus, characterized in that: the system comprises a battery information acquisition module, a client, a wireless communication module, a big data cloud platform, a battery protection module and a battery balance management module;
the battery information acquisition module is electrically connected with the client and is used for acquiring parameter information of the battery pack to be evaluated and transmitting the parameter information to the client;
the client is used for displaying and storing the received parameter information and the health state of the battery pack and sending the parameter information to the big data cloud platform through the wireless communication module;
the big data cloud platform comprises a data exchange module, a data storage module and a data processing module; the data exchange module is used for receiving and sending information needing interaction; the data storage module is used for storing parameter information of the battery pack to be evaluated and data related to the health state of the battery pack to be evaluated in the internet; the data processing module is used for analyzing the health state of the battery pack to be evaluated according to the information in the data storage module;
the battery protection module is electrically connected with the client and the wireless communication module and is used for receiving control instructions sent by the client and the big data cloud platform, disconnecting the fault battery pack and sending fault warning information to the client;
the battery balancing module is electrically connected with the client and used for balancing the residual electric quantity of each single battery in the working process of the battery pack and sending a balancing result to the client for displaying;
the method for evaluating the health state of the battery pack to be evaluated by the battery pack health state evaluation device based on big data comprises the following steps:
(1) the battery information acquisition module acquires parameter information of a battery pack to be evaluated, wherein the parameter information comprises the highest voltage and the lowest voltage of a single battery, the highest temperature and the lowest temperature of the single battery, the external environment temperature, the total voltage of the battery pack, the total current of the battery pack, the battery type, the number of the single batteries, the service time, the brand of the battery and the model of the battery;
(2) preprocessing the parameter information to obtain processed parameter information serving as an input item for evaluating the health state of the battery pack, and evaluating the health state of the battery pack to be evaluated according to the information in the cloud database
Is calculated to make a period
Each period is
；
(3) In the period
Establishing a BP neural network model based on an improved BP neural network algorithm according to the input items of the health state evaluation of the battery pack
Calculating the period
State of health output value of internal to-be-evaluated battery pack
Confidence of health status is a default value
；
(4) According to the battery pack usage, the working environment, the battery brand, the battery type and the average battery life in the cloud database
State of health of battery pack during cycle
Confidence correction value of
(
) Calculating the corrected confidence by the following formula
Weaken itError versus battery health during calculation
The influence of (a):
corrected confidence
；
Comparing confidence threshold values
And corrected confidence
If, if
Considering the battery pack health status output value
Effective is to
As
State of health of battery pack during cycle
(ii) a Otherwise, the BP neural network model in the last period is utilized
BP neural network model as the present cycle
I.e. by
Calculate out
State of health output value of battery pack to be evaluated in cycle
As
Battery pack health status over a period
；
(5) Health state of battery pack
Transmitting the data to the client and receiving the data from the client, repeating (1) to (4) and starting the next period
State of health of inner battery pack
And (4) calculating.
2. The evaluation device according to claim 1, wherein the client can collect parameter information of the battery pack to be evaluated in a manual entry manner.
3. The evaluation device of claim 1, wherein the control instructions received by the battery protection module comprise: the big data cloud platform monitors an instruction sent out when the fault early warning is carried out, and the client receives an instruction sent out when the health state of the battery pack is lower than a set value.
4. The evaluation device of claim 1, wherein the data exchange module comprises a client communication module and an emergency communication module; the client communication module is used for exchanging data with the client; the emergency communication module is used for sending a fault early warning signal to the wireless communication module.
5. The evaluation device of claim 1, wherein the data storage module comprises a battery database and a cloud database; the battery database is a distributed database and is used for storing all data of the battery pack to be evaluated and the battery pack already evaluated; the cloud database is a distributed database and is used for acquiring and storing data related to the battery pack to be evaluated through the internet.
6. The evaluation device of claim 1, wherein the data processing module comprises a data screening module, a BP neural network module, and an output modification module;
the data screening module is used for preprocessing the received power parameters;
the BP neural network module takes the preprocessed parameter information and data related to the battery pack to be evaluated in the cloud database as the input of the BP neural network module, and takes the health state of the battery pack to be evaluated as the output of the BP neural network module;
and the output correction module is used for correcting the output confidence coefficient of the BP neural network module.
7. The evaluation device according to claim 1, wherein if the corrected confidence is higher than a threshold value, the BP neural network model and the health state of the battery pack to be evaluated are updated, and the health state of the battery pack to be evaluated is transmitted to the data exchange module; otherwise, the health state of the battery pack to be evaluated is calculated by utilizing the last effective BP neural network model and is transmitted to the data exchange module.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911073725.2A CN110837058B (en) | 2019-11-06 | 2019-11-06 | Battery pack health state evaluation device and evaluation method based on big data |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911073725.2A CN110837058B (en) | 2019-11-06 | 2019-11-06 | Battery pack health state evaluation device and evaluation method based on big data |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN110837058A CN110837058A (en) | 2020-02-25 |
| CN110837058B true CN110837058B (en) | 2021-10-19 |
Family
ID=69574714
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201911073725.2A Active CN110837058B (en) | 2019-11-06 | 2019-11-06 | Battery pack health state evaluation device and evaluation method based on big data |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110837058B (en) |
Families Citing this family (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111428896B (en) * | 2020-04-02 | 2024-02-20 | 硕能(上海)自动化科技有限公司 | Lithium ion capacitor backup power supply device |
| CN111619399B (en) * | 2020-06-10 | 2021-04-27 | 国网浙江电动汽车服务有限公司 | Power battery safety assessment device based on electric automobile fills electric pile management platform |
| CN111856284B (en) * | 2020-06-11 | 2023-06-20 | 国网江苏省电力有限公司电力科学研究院 | Failure analysis method and device for energy storage power station battery |
| JP7314880B2 (en) * | 2020-08-21 | 2023-07-26 | トヨタ自動車株式会社 | BATTERY DIAGNOSTIC APPARATUS, METHOD, PROGRAM AND VEHICLE |
| CN111959281A (en) * | 2020-09-01 | 2020-11-20 | 郑州飞轮威尔实业有限公司 | Electric bicycle battery safety management system based on thing networking |
| CN112433169B (en) * | 2020-11-25 | 2022-11-29 | 北京理工新源信息科技有限公司 | Cloud power battery health degree evaluation system and method |
| CN112816875A (en) * | 2020-12-25 | 2021-05-18 | 珠海格力电器股份有限公司 | Electric vehicle battery cloud management system, method, medium and cloud server |
| CN112677815B (en) * | 2020-12-28 | 2022-04-29 | 北京理工大学 | Battery full life cycle management system |
| CN113488685A (en) * | 2021-06-08 | 2021-10-08 | 北京格睿能源科技有限公司 | Fuel cell health state assessment method and device based on operation big data |
| CN114779098B (en) * | 2022-04-14 | 2022-12-23 | 江苏金锋源新能源有限公司 | State evaluation method and system for lithium ion battery |
| CN115166523B (en) * | 2022-09-06 | 2022-12-02 | 江苏时代新能源科技有限公司 | Mobile battery state detection device, system and method |
| CN116956639B (en) * | 2023-09-15 | 2023-12-01 | 深圳海汇科技有限公司 | High-heat-dissipation storage battery assessment method and system based on data analysis |
Family Cites Families (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US10332508B1 (en) * | 2016-03-31 | 2019-06-25 | Amazon Technologies, Inc. | Confidence checking for speech processing and query answering |
| CN107122594B (en) * | 2017-04-10 | 2020-06-26 | 湖南中车时代电动汽车股份有限公司 | New energy vehicle battery health prediction method and system |
| CN107436411B (en) * | 2017-07-28 | 2019-06-14 | 南京航空航天大学 | Battery SOH On-line Estimation method based on fractional order neural network and dual-volume storage Kalman |
| CN107766643B (en) * | 2017-10-16 | 2021-08-03 | 华为技术有限公司 | Data processing method and related device |
| US11227191B2 (en) * | 2018-02-13 | 2022-01-18 | Slingshot Aerospace, Inc. | Conditional loss function modification in a neural network |
| CN109001631A (en) * | 2018-04-27 | 2018-12-14 | 张家港莫特普数据科技有限公司 | Battery performance online evaluation system and method |
| CN108749607A (en) * | 2018-05-23 | 2018-11-06 | 清华大学深圳研究生院 | A kind of electric automobile power battery management and monitoring system based on cloud computing |
| CN109581239A (en) * | 2018-11-26 | 2019-04-05 | 漳州市华威电源科技有限公司 | A kind of accumulator management device and monitoring system |
| CN109921110A (en) * | 2019-03-05 | 2019-06-21 | 安徽力高新能源技术有限公司 | A kind of battery management system and method based on big data cloud platform |
| CN110335222B (en) * | 2019-06-18 | 2021-09-17 | 清华大学 | Self-correction weak supervision binocular parallax extraction method and device based on neural network |
| CN110308397B (en) * | 2019-07-30 | 2021-04-02 | 重庆邮电大学 | Lithium battery multi-class fault diagnosis modeling method driven by hybrid convolutional neural network |
-
2019
- 2019-11-06 CN CN201911073725.2A patent/CN110837058B/en active Active
Also Published As
| Publication number | Publication date |
|---|---|
| CN110837058A (en) | 2020-02-25 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110837058B (en) | Battery pack health state evaluation device and evaluation method based on big data | |
| CN114372417A (en) | Electric vehicle battery health state and remaining life evaluation method based on charging network | |
| CN103048625B (en) | The status predication system and method for battery | |
| JP6635743B2 (en) | Storage battery maintenance device and storage battery maintenance method | |
| CN103679282B (en) | The Forecasting Methodology of wind power climbing | |
| CN111581850A (en) | Full-period power battery management system applying digital twinning technology | |
| CN113022378B (en) | Temperature consistency prediction method, temperature consistency prediction device, prediction equipment and storage medium | |
| CN107330573B (en) | State evaluation method and device for photovoltaic system key equipment | |
| CN104779608B (en) | Safe stable on-line additional emergency control method of power system based on off-line strategy | |
| US11385631B2 (en) | Method and system for detecting faults in a charging infrastructure system for electric vehicles | |
| CN104316879A (en) | Method for forecasting service life of lead-acid storage battery | |
| CN112700144B (en) | Transformer substation operation state risk assessment method, device, equipment and storage medium | |
| CN114295983A (en) | Battery thermal runaway early warning method and device, vehicle, equipment and storage medium | |
| CN117013606A (en) | Intelligent energy storage control system for photovoltaic power generation based on artificial intelligence | |
| CN112881930A (en) | Energy storage battery health management prediction method and system based on Internet of things | |
| CN114285058B (en) | Parameter setting method of energy storage system and energy storage system | |
| CN113112114A (en) | Energy storage power station online evaluation method and device | |
| CN115042665A (en) | Cloud-assisted safety control method and system for intelligent battery pack of electric bicycle | |
| CN109159684A (en) | A kind of charging station system of cell health state battery altering | |
| CN117078113B (en) | Outdoor battery production quality management system based on data analysis | |
| CN102095953A (en) | On-line detection method for performance of accumulator charger | |
| CN116361377A (en) | Load prediction system, method and medium based on industrial Internet of things service platform | |
| CN112394293A (en) | Online evaluation device, method and system for performance and state of energy storage system | |
| CN117129899A (en) | Battery health state prediction management system and method | |
| CN116626524A (en) | Battery state evaluation method, battery state evaluation device, electronic equipment and storage 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 | ||
| CB03 | Change of inventor or designer information |
Inventor after: Dai Xiaoqiang Inventor after: Zhao Yang Inventor after: Shen Kuicheng Inventor after: Lu Zhen Inventor after: Wu Fei Inventor before: Zhao Yang Inventor before: Dai Xiaoqiang Inventor before: Shen Kuicheng Inventor before: Lu Zhen Inventor before: Wu Fei |
|
| CB03 | Change of inventor or designer information |