CN112816875A - Electric vehicle battery cloud management system, method, medium and cloud server - Google Patents
Electric vehicle battery cloud management system, method, medium and cloud server Download PDFInfo
- Publication number
- CN112816875A CN112816875A CN202011560426.4A CN202011560426A CN112816875A CN 112816875 A CN112816875 A CN 112816875A CN 202011560426 A CN202011560426 A CN 202011560426A CN 112816875 A CN112816875 A CN 112816875A
- Authority
- CN
- China
- Prior art keywords
- electric vehicle
- soc estimation
- battery
- neural network
- network model
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
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]
- G01R31/367—Software therefor, e.g. for battery testing using modelling or look-up tables
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B60—VEHICLES IN GENERAL
- B60L—PROPULSION OF ELECTRICALLY-PROPELLED VEHICLES; SUPPLYING ELECTRIC POWER FOR AUXILIARY EQUIPMENT OF ELECTRICALLY-PROPELLED VEHICLES; ELECTRODYNAMIC BRAKE SYSTEMS FOR VEHICLES IN GENERAL; MAGNETIC SUSPENSION OR LEVITATION FOR VEHICLES; MONITORING OPERATING VARIABLES OF ELECTRICALLY-PROPELLED VEHICLES; ELECTRIC SAFETY DEVICES FOR ELECTRICALLY-PROPELLED VEHICLES
- B60L3/00—Electric devices on electrically-propelled vehicles for safety purposes; Monitoring operating variables, e.g. speed, deceleration or energy consumption
- B60L3/0023—Detecting, eliminating, remedying or compensating for drive train abnormalities, e.g. failures within the drive train
- B60L3/0046—Detecting, eliminating, remedying or compensating for drive train abnormalities, e.g. failures within the drive train relating to electric energy storage systems, e.g. batteries or capacitors
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B60—VEHICLES IN GENERAL
- B60L—PROPULSION OF ELECTRICALLY-PROPELLED VEHICLES; SUPPLYING ELECTRIC POWER FOR AUXILIARY EQUIPMENT OF ELECTRICALLY-PROPELLED VEHICLES; ELECTRODYNAMIC BRAKE SYSTEMS FOR VEHICLES IN GENERAL; MAGNETIC SUSPENSION OR LEVITATION FOR VEHICLES; MONITORING OPERATING VARIABLES OF ELECTRICALLY-PROPELLED VEHICLES; ELECTRIC SAFETY DEVICES FOR ELECTRICALLY-PROPELLED VEHICLES
- B60L58/00—Methods or circuit arrangements for monitoring or controlling batteries or fuel cells, specially adapted for electric vehicles
- B60L58/10—Methods or circuit arrangements for monitoring or controlling batteries or fuel cells, specially adapted for electric vehicles for monitoring or controlling batteries
- B60L58/12—Methods or circuit arrangements for monitoring or controlling batteries or fuel cells, specially adapted for electric vehicles for monitoring or controlling batteries responding to state of charge [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
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L67/00—Network arrangements or protocols for supporting network services or applications
- H04L67/01—Protocols
- H04L67/02—Protocols based on web technology, e.g. hypertext transfer protocol [HTTP]
- H04L67/025—Protocols based on web technology, e.g. hypertext transfer protocol [HTTP] for remote control or remote monitoring of applications
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02T—CLIMATE CHANGE MITIGATION TECHNOLOGIES RELATED TO TRANSPORTATION
- Y02T10/00—Road transport of goods or passengers
- Y02T10/60—Other road transportation technologies with climate change mitigation effect
- Y02T10/70—Energy storage systems for electromobility, e.g. batteries
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02T—CLIMATE CHANGE MITIGATION TECHNOLOGIES RELATED TO TRANSPORTATION
- Y02T90/00—Enabling technologies or technologies with a potential or indirect contribution to GHG emissions mitigation
- Y02T90/10—Technologies relating to charging of electric vehicles
- Y02T90/16—Information or communication technologies improving the operation of electric vehicles
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02T—CLIMATE CHANGE MITIGATION TECHNOLOGIES RELATED TO TRANSPORTATION
- Y02T90/00—Enabling technologies or technologies with a potential or indirect contribution to GHG emissions mitigation
- Y02T90/10—Technologies relating to charging of electric vehicles
- Y02T90/16—Information or communication technologies improving the operation of electric vehicles
- Y02T90/167—Systems integrating technologies related to power network operation and communication or information technologies for supporting the interoperability of electric or hybrid vehicles, i.e. smartgrids as interface for battery charging of electric vehicles [EV] or hybrid vehicles [HEV]
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y04—INFORMATION OR COMMUNICATION TECHNOLOGIES HAVING AN IMPACT ON OTHER TECHNOLOGY AREAS
- Y04S—SYSTEMS INTEGRATING TECHNOLOGIES RELATED TO POWER NETWORK OPERATION, COMMUNICATION OR INFORMATION TECHNOLOGIES FOR IMPROVING THE ELECTRICAL POWER GENERATION, TRANSMISSION, DISTRIBUTION, MANAGEMENT OR USAGE, i.e. SMART GRIDS
- Y04S30/00—Systems supporting specific end-user applications in the sector of transportation
- Y04S30/10—Systems supporting the interoperability of electric or hybrid vehicles
- Y04S30/12—Remote or cooperative charging
Abstract
The invention provides a cloud management system, a method, a medium and a cloud server for an electric vehicle battery, wherein the method comprises the following steps: the cloud data preprocessing module is used for performing data preprocessing on charging and discharging experiment test data required by the Kalman filtering SOC estimation modeling on the cloud platform to obtain corresponding modeling parameters, downloading the corresponding modeling parameters by the electric vehicle, and performing the Kalman filtering SOC estimation modeling to estimate the SOC of the battery; and/or the neural network model estimation module is used for establishing an SOC estimation neural network model on the cloud platform and carrying out real-time SOC estimation on the electric vehicle battery based on the established SOC estimation neural network model. The scheme provided by the invention can solve the problem of limited computing capacity of the battery management CPU.
Description
Technical Field
The invention relates to the field of battery management, in particular to a battery cloud management system, method and medium for an electric vehicle and a cloud server.
Background
BMS battery management is one of the core technologies of electric vehicle development, and the state of charge (SOC) estimation of a power battery is very important for battery management, and the accurate SOC estimation can greatly improve the service life of the battery and the performance of the whole vehicle. At present, the SOC estimation methods widely used are a fuzzy control method, a kalman filter method, a gray theory algorithm method, a neural network method, and the like, and among these methods, a neural network model and a fuzzy control method do not depend on a mathematical model of an object, and are suitable for a multi-input and multi-output nonlinear system and are very suitable for SOC estimation. However, the accuracy of the SOC neural network model can be better only by depending on a large amount of sample data, and the data processing capability of a CPU is limited, so that the SOC neural network model cannot be well applied to practice.
Disclosure of Invention
The invention mainly aims to overcome the defects of the prior art and provides a battery cloud management system, a battery cloud management method, a storage medium and a cloud server of an electric vehicle, so as to solve the problems that in the prior art, the CPU data processing capacity is limited, and an SOC neural network model cannot be well applied to practice.
One aspect of the present invention provides a cloud management system for an electric vehicle battery, including: the cloud data preprocessing module is used for performing data preprocessing on charging and discharging experiment test data required by the Kalman filtering SOC estimation modeling on the cloud platform to obtain corresponding modeling parameters, downloading the corresponding modeling parameters by the electric vehicle, and performing the Kalman filtering SOC estimation modeling to estimate the SOC of the battery; and/or the neural network model estimation module is used for establishing an SOC estimation neural network model on the cloud platform and carrying out real-time SOC estimation on the electric vehicle battery based on the established SOC estimation neural network model.
Optionally, the neural network model estimation module performs data preprocessing on charge and discharge experiment test data required by estimating SOC modeling by using a kalman filter method on a cloud platform to obtain corresponding modeling parameters, and includes: acquiring charging and discharging experimental test data of different batteries and preset data processing modes corresponding to the different charging and discharging experimental test data; preprocessing corresponding experimental test data according to the preset data processing mode to obtain modeling parameters required by estimating SOC (system on chip) modeling by using a Kalman filtering method; and/or the neural network model estimation module establishes an SOC estimation neural network model on the cloud platform, and comprises the following steps: receiving battery charging and discharging experiment test data sent by an electric automobile and/or operation parameters of a battery within preset time; carrying out deep learning training on the received battery charging and discharging experiment test data and/or the operation parameters of the battery within the preset time by using a deep learning frame to obtain an SOC estimation neural network model; and/or the neural network model estimation module is used for carrying out real-time SOC estimation on the battery of the electric vehicle based on the established SOC estimation neural network model and comprises the following steps: receiving battery operation parameters sent by an electric automobile in the operation process; and inputting the battery operation parameters into the SOC estimation neural network model, and outputting the real-time SOC estimation value of the electric automobile.
Optionally, the method further comprises: the electric vehicle fault early warning module is used for establishing an electric vehicle fault early warning model on a cloud platform and determining the safety state of the electric vehicle based on the electric vehicle fault early warning model.
Optionally, the electric vehicle fault early warning module establishes an electric vehicle fault early warning model on a cloud platform, and includes: acquiring fault operation parameters within preset time before and after the electric vehicle breaks down; and carrying out model training on the obtained fault operation parameters, and establishing an electric vehicle fault early warning model.
The invention provides a cloud management method for an electric vehicle battery, which comprises the following steps: performing data preprocessing on charging and discharging experiment test data required by Kalman filtering SOC estimation modeling on a cloud platform to obtain corresponding modeling parameters, downloading the corresponding modeling parameters by an electric vehicle, and performing Kalman filtering SOC estimation modeling for SOC estimation of a battery; and/or establishing an SOC estimation neural network model on the cloud platform, and performing real-time SOC estimation on the electric vehicle battery based on the established SOC estimation neural network model.
Optionally, the data preprocessing is performed on the charge and discharge experiment test data required by the estimation of the SOC modeling by the kalman filter method on the cloud platform to obtain corresponding modeling parameters, and the method includes: acquiring charging and discharging experimental test data of different batteries and preset data processing modes corresponding to the different charging and discharging experimental test data; preprocessing corresponding experimental test data according to the preset data processing mode to obtain modeling parameters required by estimating SOC (system on chip) modeling by using a Kalman filtering method; and/or establishing an SOC estimation neural network model on the cloud platform, wherein the SOC estimation neural network model comprises the following steps: receiving battery charging and discharging experiment test data sent by an electric automobile and/or operation parameters of a battery within preset time; carrying out deep learning training on the received battery charging and discharging experiment test data and/or the operation parameters of the battery within the preset time by using a deep learning frame to obtain an SOC estimation neural network model; and/or performing real-time SOC estimation on the battery of the electric vehicle based on the established SOC estimation neural network model, and the method comprises the following steps: receiving battery operation parameters sent by an electric automobile in the operation process; and inputting the battery operation parameters into the SOC estimation neural network model, and outputting the real-time SOC estimation value of the electric automobile.
Optionally, the method further comprises: an electric vehicle fault early warning model is established on a cloud platform, and the safety state of the electric vehicle is determined based on the electric vehicle fault early warning model.
Optionally, establishing an electric vehicle fault early warning model on a cloud platform includes: acquiring fault operation parameters within preset time before and after the electric vehicle breaks down; and carrying out model training on the obtained fault operation parameters, and establishing an electric vehicle fault early warning model.
A further aspect of the invention provides a storage medium having stored thereon a computer program which, when executed by a processor, carries out the steps of any of the methods described above.
In another aspect, the present invention provides a cloud server, including a processor, a memory, and a computer program stored in the memory and operable on the processor, where the processor executes the computer program to implement any of the foregoing method steps.
The invention further provides a cloud server which comprises the electric vehicle battery cloud management system.
According to the technical scheme of the invention, the data required by Kalman filtering modeling can be processed, and the SOC can be estimated on line by using a neural network method; the data preprocessing and model training tasks are distributed to a cloud data platform, so that a larger data volume is obtained, and the problems that the computing capacity of a battery management CPU is limited, and the time requirement of neural network algorithm training and real-time operation cannot be met are solved; data preprocessing of modeling parameters of a Kalman filtering method is placed in a cloud end to shorten the development period; the fault early warning can be carried out by referring to a large amount of past fault information (parameters and correlation when a fault occurs and/or an accident is caused); a large amount of data required when a neural network method is adopted for SOC estimation in a BMS are trained and verified at a cloud end, a large amount of past fault information data of the electric automobile are referred, key parameters of the electric automobile are recorded when a fault occurs, and a fault early warning model is established for fault prediction. And cloud processing is performed on data required by battery modeling to obtain parameters required by modeling, so that the development period is shortened.
Drawings
The accompanying drawings, which are included to provide a further understanding of the invention and are incorporated in and constitute a part of this specification, illustrate embodiments of the invention and together with the description serve to explain the invention and not to limit the invention. In the drawings:
fig. 1 is a block diagram illustrating a structure of an embodiment of a cloud management system for an electric vehicle battery provided in the present invention;
fig. 2 is a system diagram of a cloud management system for an electric vehicle battery provided by the invention;
FIG. 3 is a schematic flow chart illustrating an embodiment of obtaining corresponding modeling parameters by performing data preprocessing on charge and discharge experimental test data required for modeling of Kalman filtering SOC estimation on a cloud platform;
FIG. 4 illustrates a flow diagram of one embodiment of establishing a SOC estimation neural network model at a cloud platform;
FIG. 5 illustrates a flow diagram of one embodiment of a real-time SOC estimation of an electric vehicle battery based on an established SOC estimation neural network model;
FIG. 6 is a schematic flow chart diagram illustrating one embodiment of an electric vehicle fault warning module establishing an electric vehicle fault warning model;
fig. 7 is a method diagram illustrating an embodiment of a cloud management method for a battery of an electric vehicle according to the present invention.
Detailed Description
In order to make the objects, technical solutions and advantages of the present invention more apparent, the technical solutions of the present invention will be clearly and completely described below with reference to the specific embodiments of the present invention and the accompanying drawings. It is to be understood that the described embodiments are merely exemplary of the invention, and not restrictive of the full scope of the invention. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
It should be noted that the terms "first," "second," and the like in the description and claims of the present invention and in the drawings described above are used for distinguishing between similar elements and not necessarily for describing a particular sequential or chronological order. It is to be understood that the data so used is interchangeable under appropriate circumstances such that the embodiments of the invention described herein are capable of operation in sequences other than those illustrated or described herein. Furthermore, the terms "comprises," "comprising," and "having," and any variations thereof, are intended to cover a non-exclusive inclusion, such that a process, method, system, article, or apparatus that comprises a list of steps or elements is not necessarily limited to those steps or elements expressly listed, but may include other steps or elements not expressly listed or inherent to such process, method, article, or apparatus.
The multi-input, multi-output nonlinear system of the neural network model is well suited for SOC estimation, but suffers from the following: 1. the data size of the sample is small and cannot meet the training requirement; 2. the CPU has a limited data computation capability. 3. The Kalman filtering method has large data size during modeling, and the development period is increased.
The invention provides a cloud management system for an electric vehicle battery. The cloud management system is communicated with the electric vehicle in a 5G communication mode, so that the data transmission speed and the real-time performance are improved.
Fig. 1 shows a block diagram of an embodiment of a cloud management system for an electric vehicle battery provided in the present invention. Fig. 2 shows a system scheme diagram of the electric vehicle battery cloud management system provided by the invention. As shown in fig. 1 and 2, the electric vehicle battery cloud management system includes a cloud data preprocessing module and a neural network model estimation module.
The cloud data preprocessing module is used for preprocessing the charging and discharging experiment test data required by the Kalman filtering SOC estimation modeling on the cloud platform to obtain corresponding modeling parameters, the modeling parameters can be downloaded by the electric vehicle, and the Kalman filtering SOC estimation modeling is carried out to be used for SOC estimation of the battery.
Fig. 3 is a schematic flow chart showing a specific embodiment of obtaining corresponding modeling parameters by performing data preprocessing on charge and discharge experimental test data required for the karman filtering method SOC estimation modeling on a cloud platform.
As shown in fig. 3, the data preprocessing of the charging and discharging experiment test data required by the kalman filter SOC estimation modeling by the cloud data preprocessing module on the cloud platform to obtain the corresponding modeling parameters may specifically include step S11 and step S12.
And step S11, acquiring the charge and discharge experiment test data of different batteries and the preset data processing mode corresponding to the charge and discharge experiment test data.
And step S12, preprocessing corresponding experimental test data according to the preset data processing mode to obtain modeling parameters required by the Kalman filtering method SOC estimation modeling.
Specifically, charge and discharge experiment test data of different batteries are obtained from a charge and discharge experiment test database. For example, a charging and discharging test experiment database is established, and the same manufacturer can upload the charging and discharging test data of all batteries of the manufacturer to the database. For example, corresponding data processing modes can be preset for various charging and discharging experimental test data aiming at different development schemes of different manufacturers, the charging and discharging experimental test data in the charging and discharging experimental test database are read, and data preprocessing is carried out according to the corresponding data processing modes to obtain modeling parameters required by SOC (state of charge) estimation through a Kalman filtering method.
In connection with the system solution diagram of the present invention shown in fig. 2, the modeling parameters include, for example: internal resistance and/or second-order RC model parameters, and the like, the model parameters of the second-order RC model may specifically include: cc charge transfer induced capacitance, Rc charge transfer induced resistance, Cd charge diffusion induced capacitance, and Rd charge diffusion induced resistance, and further includes function parameters for function fitting Rc parameters and/or function parameters for function (polynomial) fitting SOC, OCV (open circuit voltage), and cell operating temperature T.
A manufacturer can download modeling parameters required by the preprocessed Kalman filtering method SOC estimation modeling from the cloud data preprocessing module, then perform Kalman filtering method SOC estimation modeling, and establish a Kalman filtering method SOC estimation model through steps of polarization parameter fitting, SOC-OCV-T function relation fitting and the like.
SOCx0 (SOC at the last moment), open-circuit voltage OCV and cell working temperature T are input into the Kalman filtering method SOC estimation model, and then the current SOC value of the battery can be output.
And the neural network model estimation module is used for establishing an SOC estimation neural network model and carrying out real-time SOC estimation on the electric vehicle battery based on the established SOC estimation neural network model.
FIG. 4 is a flow diagram illustrating one embodiment of establishing a SOC estimation neural network model on a cloud platform. With reference to the system scheme diagram of the present invention shown in fig. 4, as shown in fig. 4, the establishing of the SOC estimation neural network model by the neural network model estimation module on the cloud platform may specifically include steps S21 and S22.
And step S21, receiving the battery charge and discharge experiment test data and/or the operation parameters of the battery within the preset time.
And step S22, performing deep learning training on the received battery charging and discharging experiment test data and/or the operation parameters of the battery within the preset time by using a deep learning frame to obtain an SOC estimation neural network model.
For example, in combination with the system scheme diagram of the present invention shown in fig. 2, the electric vehicle sends the charge and discharge test experimental data and the real-time operating parameters (e.g., battery voltage V, current I, cell operating temperature T, charge and discharge internal resistance) of the electric vehicle battery in a period of time to the cloud through 5G high-speed communication, and performs deep learning training on the received data by using a deep learning framework, for example, a currently mainstream free open source deep learning framework, such as cafee, tensoflow, and the like, may be used.
FIG. 5 illustrates a flow diagram of one embodiment of a real-time SOC estimation of an electric vehicle battery based on an established SOC estimation neural network model.
As shown in fig. 5, the real-time SOC estimation of the electric vehicle battery by the neural network model estimation module based on the established SOC estimation neural network model may specifically include steps S31 and S32.
And step S31, receiving the battery operation parameters sent by the electric automobile in the operation process.
And step S32, inputting the battery operation parameters into the SOC estimation neural network model, and outputting the real-time SOC estimation value of the electric automobile.
The battery operation parameters sent by the electric automobile in the operation process and/or the real-time SOC estimated value output by the electric automobile are received and returned, 5G communication can be adopted for transmission, the transmission speed is high, and the real-time performance is good.
The operating parameters include: the battery voltage V, the current I, the cell working temperature T and/or the charge-discharge internal resistance. With reference to the system scheme diagram of the invention shown in fig. 2, in the running process of the electric vehicle, battery running parameters such as battery voltage V, current I, temperature T, charging and discharging internal resistance and the like are sent to a neural network model estimation module of a cloud (cloud platform) through 5G high-speed communication, the trained SOC estimation neural network model is input for processing, and finally, the battery SOC estimation value is output and sent to the electric vehicle end.
Optionally, as shown in fig. 1 and fig. 2, the electric vehicle battery cloud management system further includes an electric vehicle fault early warning module, configured to establish an electric vehicle fault early warning model on a cloud platform, and determine a safety state of the electric vehicle based on the electric vehicle fault early warning model.
Fig. 6 is a flowchart illustrating an embodiment of the electric vehicle fault early warning module establishing an electric vehicle fault early warning model.
As shown in fig. 6, the establishing of the electric vehicle fault early warning model on the cloud platform by the electric vehicle fault early warning module may specifically include step S41 and step S42.
And step S41, acquiring fault operation parameters in preset time before and after the electric vehicle breaks down.
And step S41, performing model training on the acquired fault operation parameters, and establishing an electric vehicle fault early warning model.
For example, if an electric vehicle has a fault, the fault operation parameters (parameters and correlation when the fault or accident occurs) before and after the fault occurs are obtained, and a fault parameter information database is established. And training fault operation parameters in a fault parameter information database by adopting a Logistic regression (Logistic) or a neural network model Support Vector Machine (SVM) algorithm in an open source deep learning framework, and establishing a fault early warning model.
With reference to the system scheme shown in fig. 2, in the running process of the electric vehicle, the running parameters are sent to the cloud management system through 5G high-speed communication in real time, and the fault early warning model is input for processing, so that the safety state of the electric vehicle, that is, whether a fault is possible, is obtained.
The invention further provides a cloud management method for the electric vehicle battery.
Fig. 7 is a method diagram illustrating an embodiment of a cloud management method for a battery of an electric vehicle according to the present invention.
As shown in fig. 7, according to an embodiment of the present invention, the management method includes at least step S110 and/or step S120.
And S110, performing data preprocessing on charge and discharge experiment test data required by the Karman filter method SOC estimation modeling on the cloud platform to obtain corresponding modeling parameters. The modeling parameters may be downloaded by the electric vehicle and modeled for SOC estimation by kalman filtering for SOC estimation of the battery.
Fig. 3 is a schematic flow chart showing a specific embodiment of obtaining corresponding modeling parameters by performing data preprocessing on charge and discharge experimental test data required for the karman filtering method SOC estimation modeling on a cloud platform.
As shown in fig. 3, the step of performing data preprocessing on the charge and discharge experimental test data required by the kalman filter SOC estimation modeling on the cloud platform to obtain corresponding modeling parameters may specifically include step S11 and step S12.
And step S11, acquiring the charge and discharge experiment test data of different batteries and the preset data processing mode corresponding to the charge and discharge experiment test data.
And step S12, preprocessing corresponding experimental test data according to the preset data processing mode to obtain modeling parameters required by the Kalman filtering method SOC estimation modeling.
Specifically, charge and discharge experiment test data of different batteries are obtained from a charge and discharge experiment test database. For example, a charging and discharging test experiment database is established, and the same manufacturer can upload the charging and discharging test data of all batteries of the manufacturer to the database. For example, corresponding data processing modes can be preset for various charging and discharging experimental test data aiming at different development schemes of different manufacturers, the charging and discharging experimental test data in the charging and discharging experimental test database are read, and data preprocessing is carried out according to the corresponding data processing modes to obtain modeling parameters required by SOC (state of charge) estimation through a Kalman filtering method.
In connection with the system solution diagram of the present invention shown in fig. 2, the modeling parameters include, for example: internal resistance and/or second-order RC model parameters, and the like, the model parameters of the second-order RC model may specifically include: cc charge transfer induced capacitance, Rc charge transfer induced resistance, Cd charge diffusion induced resistance, and further including function parameters to function fit Rc parameters and/or function parameters to function (polynomial) fit SOC, OCV (open circuit voltage), and cell operating temperature T.
A manufacturer can download modeling parameters required by the preprocessed Kalman filtering method SOC estimation modeling from the cloud data preprocessing module, then perform Kalman filtering method SOC estimation modeling, and establish a Kalman filtering method SOC estimation model through steps of polarization parameter fitting, SOC-OCV-T function relation fitting and the like.
SOCx0 (SOC at the last moment), open-circuit voltage OCV and cell working temperature T are input into the Kalman filtering method SOC estimation model, and then the current SOC value of the battery can be output.
Step S120, an SOC estimation neural network model is built on the cloud platform, and real-time SOC estimation is carried out on the electric vehicle battery based on the built SOC estimation neural network model.
FIG. 4 is a flow diagram illustrating one embodiment of establishing a SOC estimation neural network model on a cloud platform. In conjunction with the system scheme of the present invention shown in fig. 2, as shown in fig. 4, establishing the SOC estimation neural network model may specifically include steps S21 and S22.
And step S21, receiving the battery charge and discharge experiment test data and/or the operation parameters of the battery within the preset time.
And step S22, performing deep learning training on the received battery charging and discharging experiment test data and/or the operation parameters of the battery within the preset time by using a deep learning frame to obtain an SOC estimation neural network model.
For example, in combination with the system scheme diagram of the present invention shown in fig. 2, the electric vehicle sends the charge and discharge test experimental data and the real-time operating parameters (e.g., battery voltage V, current I, cell operating temperature T, charge and discharge internal resistance) of the electric vehicle battery in a period of time to the cloud through 5G high-speed communication, and performs deep learning training on the received data by using a deep learning framework, for example, a currently mainstream free open source deep learning framework, such as cafee, tensoflow, and the like, may be used.
FIG. 5 illustrates a flow diagram of one embodiment of a real-time SOC estimation of an electric vehicle battery based on an established SOC estimation neural network model.
As shown in fig. 5, the real-time SOC estimation of the electric vehicle battery based on the established SOC estimation neural network model may specifically include steps S31 and S32.
And step S31, receiving the battery operation parameters sent by the electric automobile in the operation process.
And step S32, inputting the operation parameters into the SOC estimation neural network model, and outputting the real-time SOC estimation value of the electric automobile.
The running parameters sent by the electric automobile in the running process and/or the real-time SOC estimated value output by the electric automobile are received and returned, 5G communication can be adopted for transmission, the transmission speed is high, and the real-time performance is good.
The operating parameters include: the battery voltage V, the current I, the cell working temperature T and/or the charge-discharge internal resistance. With reference to the system scheme diagram of the invention shown in fig. 2, in the running process of the electric vehicle, the battery running parameters, such as battery voltage V, current I, temperature T, internal resistance of charge and discharge, are sent to the neural network model estimation module of the cloud (cloud platform) through 5G high-speed communication, the trained SOC estimation neural network model is input for processing, and finally the battery SOC estimation value is output and sent to the electric vehicle end.
Optionally, as shown in fig. 7, the method further includes step S130.
Step S130, an electric vehicle fault early warning model is built on the cloud platform, and the safety state of the electric vehicle is determined based on the electric vehicle fault early warning model.
Fig. 6 is a flowchart illustrating an embodiment of establishing an electric vehicle fault warning model on a cloud platform.
As shown in fig. 6, establishing the electric vehicle fault early warning model on the cloud platform may specifically include step S41 and step S42.
And step S41, acquiring fault operation parameters in preset time before and after the electric vehicle breaks down.
And step S41, performing model training on the acquired fault operation parameters, and establishing an electric vehicle fault early warning model.
For example, if an electric vehicle has a fault, the fault operation parameters (parameters and correlation when the fault or accident occurs) before and after the fault occurs are obtained, and a fault parameter information database is established. And training fault operation parameters in a fault parameter information database by adopting a Logistic regression (Logistic) or a neural network model Support Vector Machine (SVM) algorithm in an open source deep learning framework, and establishing a fault early warning model.
With reference to the system scheme shown in fig. 2, in the running process of the electric vehicle, the running parameters are sent to the cloud management system through 5G high-speed communication in real time, and the fault early warning model is input for processing, so that the safety state of the electric vehicle, that is, whether a fault is possible, is obtained.
The invention also provides a storage medium corresponding to the electric vehicle battery cloud management method, and a computer program is stored on the storage medium, and when the computer program is executed by a processor, the computer program realizes the steps of any one of the methods.
The invention further provides a cloud server corresponding to the electric vehicle battery cloud management method, and the cloud server comprises a processor, a memory and a computer program which is stored in the memory and can run on the processor, wherein when the processor executes the computer program, the steps of any one of the methods are realized.
The invention further provides a cloud server corresponding to the electric vehicle battery cloud management system, and the cloud server comprises any one of the electric vehicle battery cloud management systems.
According to the scheme provided by the invention, the data preprocessing and model training tasks are distributed to the cloud data platform, so that a larger data volume is obtained, the problems that the computing capacity of a battery management CPU is limited, the time requirement of neural network algorithm training cannot be met and real-time operation is solved, and the data preprocessing of the modeling parameters of the Kalman filtering method is arranged at the cloud end to shorten the development period; the fault early warning can be carried out by referring to a large amount of past accident information (parameters and correlation when an accident occurs); a large amount of data required when a neural network method is adopted for SOC estimation in a BMS are trained and verified at a cloud end, a large amount of past fault information data of the electric automobile are referred, key parameters of the electric automobile are recorded when a fault occurs, and a fault early warning model is established for fault prediction. And cloud processing is performed on data required by battery modeling to obtain parameters required by modeling, so that the development period is shortened.
The functions described herein may be implemented in hardware, software executed by a processor, firmware, or any combination thereof. If implemented in software executed by a processor, the functions may be stored on or transmitted over as one or more instructions or code on a computer-readable medium. Other examples and implementations are within the scope and spirit of the invention and the following claims. For example, due to the nature of software, the functions described above may be implemented using software executed by a processor, hardware, firmware, hardwired, or a combination of any of these. In addition, each functional unit may be integrated into one processing unit, or each unit may exist alone physically, or two or more units are integrated into one unit.
In the embodiments provided in the present application, it should be understood that the disclosed technology can be implemented in other ways. The above-described embodiments of the apparatus are merely illustrative, and for example, the division of the units may be a logical division, and in actual implementation, there may be another division, for example, multiple units or components may be combined or integrated into another system, or some features may be omitted, or not executed. In addition, the shown or discussed mutual coupling or direct coupling or communication connection may be an indirect coupling or communication connection through some interfaces, units or modules, and may be in an electrical or other form.
The units described as separate parts may or may not be physically separate, and the parts serving as the control device may or may not be physical units, may be located in one place, or may be distributed on a plurality of units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of the embodiment.
The integrated unit, if implemented in the form of a software functional unit and sold or used as a stand-alone product, may be stored in a computer readable storage medium. Based on such understanding, the technical solution of the present invention may be embodied in the form of a software product, which is stored in a storage medium and includes instructions for causing a computer device (which may be a personal computer, a server, or a network device) to execute all or part of the steps of the method according to the embodiments of the present invention. And the aforementioned storage medium includes: a U-disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), a removable hard disk, a magnetic or optical disk, and other various media capable of storing program codes.
The above description is only an example of the present invention, and is not intended to limit the present invention, and it is obvious to those skilled in the art that various modifications and variations can be made in the present invention. Any modification, equivalent replacement, or improvement made within the spirit and principle of the present invention should be included in the scope of the claims of the present invention.
Claims (10)
1. The utility model provides an electric vehicle battery high in clouds management system which characterized in that includes:
the cloud data preprocessing module is used for performing data preprocessing on charging and discharging experiment test data required by the Kalman filtering SOC estimation modeling on the cloud platform to obtain corresponding modeling parameters, downloading the corresponding modeling parameters by the electric vehicle, and performing the Kalman filtering SOC estimation modeling to estimate the SOC of the battery;
and/or the presence of a gas in the gas,
the neural network model estimation module is used for establishing an SOC estimation neural network model on the cloud platform and carrying out real-time SOC estimation on the electric vehicle battery based on the established SOC estimation neural network model.
2. The system of claim 1, wherein the neural network model estimation module performs data preprocessing on charge and discharge experimental test data required by estimation of SOC modeling by a Kalman filtering method on a cloud platform to obtain corresponding modeling parameters, and the data preprocessing comprises:
acquiring charging and discharging experimental test data of different batteries and preset data processing modes corresponding to the different charging and discharging experimental test data;
preprocessing corresponding experimental test data according to the preset data processing mode to obtain modeling parameters required by estimating SOC (system on chip) modeling by using a Kalman filtering method;
and/or the presence of a gas in the gas,
the neural network model estimation module establishes an SOC estimation neural network model on a cloud platform, and comprises the following steps:
receiving battery charging and discharging experiment test data and/or operation parameters of a battery within preset time;
carrying out deep learning training on the received battery charging and discharging experiment test data and/or the operation parameters of the battery within the preset time by using a deep learning frame to obtain an SOC estimation neural network model;
and/or the presence of a gas in the gas,
the neural network model estimation module performs real-time SOC estimation on the electric vehicle battery based on the established SOC estimation neural network model, and comprises:
receiving battery operation parameters sent by an electric automobile in the operation process;
and inputting the battery operation parameters into the SOC estimation neural network model, and outputting the real-time SOC estimation value of the electric automobile.
3. The system of claim 1 or 2, further comprising:
the electric vehicle fault early warning module is used for establishing an electric vehicle fault early warning model on a cloud platform and determining the safety state of the electric vehicle based on the electric vehicle fault early warning model.
4. The system of claim 3, wherein the electric vehicle fault early warning module establishes an electric vehicle fault early warning model on a cloud platform, and comprises:
acquiring fault operation parameters within preset time before and after the electric vehicle breaks down;
and carrying out model training on the obtained fault operation parameters, and establishing an electric vehicle fault early warning model.
5. A cloud management method for an electric vehicle battery is characterized by comprising the following steps:
performing data preprocessing on charging and discharging experiment test data required by Kalman filtering SOC estimation modeling on a cloud platform to obtain corresponding modeling parameters, downloading the corresponding modeling parameters by an electric vehicle, and performing Kalman filtering SOC estimation modeling for SOC estimation of a battery;
and/or the presence of a gas in the gas,
establishing an SOC estimation neural network model on the cloud platform, and performing real-time SOC estimation on the electric vehicle battery based on the established SOC estimation neural network model.
6. The method of claim 5, wherein the data preprocessing of the charging and discharging experiment test data required by the Kalman filtering method for SOC modeling estimation on the cloud platform to obtain corresponding modeling parameters comprises:
acquiring charging and discharging experimental test data of different batteries and preset data processing modes corresponding to the different charging and discharging experimental test data;
preprocessing corresponding experimental test data according to the preset data processing mode to obtain modeling parameters required by estimating SOC (system on chip) modeling by using a Kalman filtering method;
and/or the presence of a gas in the gas,
establishing an SOC estimation neural network model on a cloud platform, comprising:
receiving battery charging and discharging experiment test data and/or operation parameters of a battery within preset time;
carrying out deep learning training on the received battery charging and discharging experiment test data and/or the operation parameters of the battery within the preset time by using a deep learning frame to obtain an SOC estimation neural network model;
and/or the presence of a gas in the gas,
performing real-time SOC estimation on an electric vehicle battery based on the established SOC estimation neural network model, including:
receiving battery operation parameters sent by an electric automobile in the operation process;
and inputting the battery operation parameters into the SOC estimation neural network model, and outputting the real-time SOC estimation value of the electric automobile.
7. The method of claim 5 or 6, further comprising:
an electric vehicle fault early warning model is established on a cloud platform, and the safety state of the electric vehicle is determined based on the electric vehicle fault early warning model.
8. The method of claim 7, wherein establishing the electric vehicle fault early warning model at the cloud platform comprises:
acquiring fault operation parameters within preset time before and after the electric vehicle breaks down;
and carrying out model training on the obtained fault operation parameters, and establishing an electric vehicle fault early warning model.
9. A storage medium, having stored thereon a computer program which, when being executed by a processor, carries out the steps of the method of any one of claims 1 to 4.
10. Cloud server, comprising a processor, a memory, and a computer program stored in the memory and operable on the processor, wherein the processor executes the computer program to implement the steps of the method according to any one of claims 1 to 4, and the cloud management system for electric vehicle batteries according to any one of claims 5 to 8.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011560426.4A CN112816875A (en) | 2020-12-25 | 2020-12-25 | Electric vehicle battery cloud management system, method, medium and cloud server |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011560426.4A CN112816875A (en) | 2020-12-25 | 2020-12-25 | Electric vehicle battery cloud management system, method, medium and cloud server |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN112816875A true CN112816875A (en) | 2021-05-18 |
Family
ID=75853812
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202011560426.4A Pending CN112816875A (en) | 2020-12-25 | 2020-12-25 | Electric vehicle battery cloud management system, method, medium and cloud server |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112816875A (en) |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113655384A (en) * | 2021-08-19 | 2021-11-16 | 山东浪潮科学研究院有限公司 | Battery state computing method for cloud edge side computing |
| CN113673712A (en) * | 2021-10-25 | 2021-11-19 | 深圳达人高科电子有限公司 | Method and device for calculating residual electric quantity value, server and storage medium |
| CN113960476A (en) * | 2021-09-23 | 2022-01-21 | 北京理工大学 | Power battery fault monitoring method and system based on information physical fusion technology |
| CN115144756A (en) * | 2022-06-27 | 2022-10-04 | 深圳市冰旭科技有限公司 | New energy safety early warning management system and method based on 5GNB-IOT technology |
| CN117148161A (en) * | 2023-08-29 | 2023-12-01 | 深圳市今朝时代股份有限公司 | Battery SOC estimation method and device based on cloud neural network |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106671785A (en) * | 2016-10-12 | 2017-05-17 | 西安科技大学 | Electric vehicle battery management system and method |
| CN108490361A (en) * | 2018-03-22 | 2018-09-04 | 深圳库博能源科技有限公司 | A kind of state-of-charge SoC computational methods based on high in the clouds feedback |
| CN109634820A (en) * | 2018-11-01 | 2019-04-16 | 华中科技大学 | A kind of fault early warning method, relevant device and the system of the collaboration of cloud mobile terminal |
| CN110837058A (en) * | 2019-11-06 | 2020-02-25 | 江苏科技大学 | Battery pack health state evaluation device and evaluation method based on big data |
| CN111190111A (en) * | 2020-01-14 | 2020-05-22 | 北京智芯微电子科技有限公司 | Electrochemical energy storage battery state of charge estimation method, device and system |
-
2020
- 2020-12-25 CN CN202011560426.4A patent/CN112816875A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106671785A (en) * | 2016-10-12 | 2017-05-17 | 西安科技大学 | Electric vehicle battery management system and method |
| CN108490361A (en) * | 2018-03-22 | 2018-09-04 | 深圳库博能源科技有限公司 | A kind of state-of-charge SoC computational methods based on high in the clouds feedback |
| CN109634820A (en) * | 2018-11-01 | 2019-04-16 | 华中科技大学 | A kind of fault early warning method, relevant device and the system of the collaboration of cloud mobile terminal |
| CN110837058A (en) * | 2019-11-06 | 2020-02-25 | 江苏科技大学 | Battery pack health state evaluation device and evaluation method based on big data |
| CN111190111A (en) * | 2020-01-14 | 2020-05-22 | 北京智芯微电子科技有限公司 | Electrochemical energy storage battery state of charge estimation method, device and system |
Cited By (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113655384A (en) * | 2021-08-19 | 2021-11-16 | 山东浪潮科学研究院有限公司 | Battery state computing method for cloud edge side computing |
| CN113960476A (en) * | 2021-09-23 | 2022-01-21 | 北京理工大学 | Power battery fault monitoring method and system based on information physical fusion technology |
| CN113960476B (en) * | 2021-09-23 | 2023-10-17 | 北京理工大学 | Power battery fault monitoring method and system based on information physical fusion technology |
| CN113673712A (en) * | 2021-10-25 | 2021-11-19 | 深圳达人高科电子有限公司 | Method and device for calculating residual electric quantity value, server and storage medium |
| CN113673712B (en) * | 2021-10-25 | 2022-01-28 | 深圳达人高科电子有限公司 | Method and device for calculating residual electric quantity value, server and storage medium |
| CN115144756A (en) * | 2022-06-27 | 2022-10-04 | 深圳市冰旭科技有限公司 | New energy safety early warning management system and method based on 5GNB-IOT technology |
| CN117148161A (en) * | 2023-08-29 | 2023-12-01 | 深圳市今朝时代股份有限公司 | Battery SOC estimation method and device based on cloud neural network |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN112816875A (en) | Electric vehicle battery cloud management system, method, medium and cloud server | |
| CN110873841B (en) | Battery life prediction method based on combination of data driving and battery characteristics | |
| US20190178945A1 (en) | Battery state of charge prediction method and system | |
| CN110208706A (en) | A kind of power battery health status online evaluation system and method based on car networking | |
| CN109001640B (en) | Data processing method and device for power battery | |
| CN109100655B (en) | Data processing method and device for power battery | |
| CN112068004A (en) | Method and device for determining battery abnormity and battery charging remaining time | |
| CN113696786B (en) | Battery equalization method and system | |
| CN113189495A (en) | Method and device for predicting health state of battery and electronic equipment | |
| Sadabadi et al. | Model-based state of health estimation of a lead-acid battery using step-response and emulated in-situ vehicle data | |
| KR101996943B1 (en) | Apparatus and method for estimating of battery state-of-charge | |
| Li et al. | Real-time estimation of lead-acid battery parameters: A dynamic data-driven approach | |
| CN115407211B (en) | Online prediction method and system for health state of lithium battery of electric vehicle | |
| CN112083346B (en) | LSTM-based parallel battery pack internal current distribution estimation method and system | |
| CN115097312A (en) | Lithium ion battery fusion life prediction model combining data driving model and empirical model | |
| CN113406496B (en) | Battery capacity prediction method, system, device and medium based on model migration | |
| CN111142038A (en) | Storage battery health state assessment method and device | |
| CN115407217B (en) | Online estimation method and system for state of charge of lithium battery of electric vehicle | |
| CN108845267B (en) | Data processing method and device for power battery | |
| CN116500458B (en) | Power battery capacity evaluation method and device, vehicle and electronic device | |
| CN116224127A (en) | Battery state of health estimation method based on big data analysis | |
| CN114300763B (en) | Battery internal resistance abnormality monitoring method, device and storage medium based on vehicle cloud coordination | |
| CN111199104A (en) | Battery residual performance analysis method, device, equipment and storage medium | |
| CN115759434A (en) | Method, system, computer device and storage medium for predicting battery capacity in real time | |
| CN115291113A (en) | Unified joint estimation method and system for SOC, SOH and RUL of lithium ion battery |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20210518 |
|
| RJ01 | Rejection of invention patent application after publication |