CN110386027A - The battery for electric automobile management system that cloud computing and edge calculations combine - Google Patents
The battery for electric automobile management system that cloud computing and edge calculations combine Download PDFInfo
- Publication number
- CN110386027A CN110386027A CN201910530965.4A CN201910530965A CN110386027A CN 110386027 A CN110386027 A CN 110386027A CN 201910530965 A CN201910530965 A CN 201910530965A CN 110386027 A CN110386027 A CN 110386027A
- Authority
- CN
- China
- Prior art keywords
- battery
- parameter
- control
- edge calculations
- running state
- 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.)
- Granted
Links
Classifications
-
- 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
- B60L3/00—Electric devices on electrically-propelled vehicles for safety purposes; Monitoring operating variables, e.g. speed, deceleration or energy consumption
- B60L3/04—Cutting off the power supply under fault conditions
-
- 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
-
- 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
Landscapes
- Engineering & Computer Science (AREA)
- Power Engineering (AREA)
- Life Sciences & Earth Sciences (AREA)
- Sustainable Development (AREA)
- Sustainable Energy (AREA)
- Transportation (AREA)
- Mechanical Engineering (AREA)
- Charge And Discharge Circuits For Batteries Or The Like (AREA)
- Secondary Cells (AREA)
- Electric Propulsion And Braking For Vehicles (AREA)
Abstract
The invention discloses the battery for electric automobile management systems that a kind of cloud computing and edge calculations combine, it is related to battery technology field, main purpose is that guarantee electric car can still be operated normally in network failure, improves the stability and safety of battery management system.The system comprises: battery detecting control system, for detecting the running state parameter of battery and being uploaded to edge calculations system；Edge calculations system, for cleaning running state parameter and being uploaded to cloud computing system；Cloud computing system, for according to the running state parameter after cleaning, the battery management model in training cloud to obtain updated model parameter and returns to edge calculations system；Edge calculations system, it is also used to update local battery management model using updated model parameter, and according to the running state parameter and local battery management model after cleaning, it calculates the state of a control parameter of battery and returns to battery detecting control system, controlled with the operating status to battery.
Description
Technical field
The present invention relates to battery technology field, the electric car combined more particularly to a kind of cloud computing and edge calculations
Use battery management system.
Background technique
Core of the battery management system as electric automobile energy management, by the work for acquiring electric car internal cell
Information estimates operating status, remaining mileage and safe condition of battery etc., and then controls battery charging and discharging, battery balanced, battery
Heating and the safety of management battery, can extend battery using battery management system, ensure the safety of battery
Operation.
Currently, most battery for electric automobile management systems carry out cell tube based on the embedded system of electric car local
Reason, is limited, battery management system generally passes through voltage estimate method, ampere-hour by embedded system calculation resources and arithmetic speed
The linear models such as integration method, Kalman filtering method estimate the information such as battery remaining power, cell safety state, but by
It is a complicated chemical reaction process in battery charge and discharge process, carrying out estimation only with simple linear model can generate and estimate
Calculate low precision, the problems such as deviation accumulation and stability are poor.
With wireless communication technique, cloud computing, the development of edge calculations and big data technology, it is based on cloud computing, channel radio
The battery management system of news technology is possibly realized.Battery management system based on cloud computing alleviates the calculating of electric car local
A large amount of calculating work are transferred to cloud computing platform to handle by pressure, and result is anti-by wireless communication mode by treated
It feeds electric car, electric car carries out associated batteries control and management according to the information that platform is fed back.But such mode pair
Communication quality and communication delay requirement are higher, will lead to related control information missing, when network failure so as to cause whole
A system is unable to run.
Summary of the invention
In view of this, the battery for electric automobile management system that the present invention provides a kind of cloud computing and edge calculations combine
It unites, main purpose is to guarantee that electric car can still operate normally in case of a network fault, improves the stabilization of system
Property and safety.
According to the present invention on one side, a kind of cloud computing is provided and battery for electric automobile pipe that edge calculations combine
Reason system, comprising:
Battery detecting control system is uploaded for detecting the running state parameter of battery, and by the running state parameter
To the edge calculations system；
Edge calculations system, for being cleaned to the running state parameter, and by the running state parameter after cleaning
It is uploaded to the cloud computing system；
Cloud computing system, for according to the running state parameter after cleaning, the battery management model in training cloud to be obtained more
Model parameter after new simultaneously returns to the edge calculations system；
Edge calculations system is also used to update local battery management model using the updated model parameter, and
According to the running state parameter and the updated local battery administrative model after the cleaning, the control of the battery is calculated
State parameter, and the state of a control parameter is returned into the battery detecting control system, with the operation shape to the battery
State is controlled.
The battery for electric automobile management system that the present invention provides a kind of cloud computing and edge calculations combine, with existing skill
The data that electric car acquires are sent to cloud computing platform and handled by art, and result passes through wireless telecommunications side by treated
Formula feeds back to electric car, and the information that electric car is fed back according to platform carries out associated batteries and controls compared with management, the present invention
Battery detecting control system, edge calculations system are provided at electric car end and beyond the clouds provided with cloud computing system.It is described
Battery detecting control system is uploaded to the side for detecting the running state parameter of battery, and by the running state parameter
Edge computing system；The edge calculations system, for being cleaned to the running state parameter, and by the operation shape after cleaning
State parameter is uploaded to the cloud computing system；The cloud computing system, for according to the running state parameter after cleaning, training cloud
The battery management model at end obtains updated model parameter and returns to the edge calculations system；The edge calculations system
System is also used to update local battery management model using the updated model parameter, and according to the fortune after the cleaning
Row state parameter and the updated local battery administrative model calculate the state of a control parameter of the battery, and will be described
State of a control parameter returns to the battery detecting control system, is controlled with the operating status to the battery.The present invention
A set of operating system independent of cloud computing system calculated result is being established at electric car end using edge calculations mode,
In the case where network breaks down, electric car end still can calculate battery by local edge calculations system in real time
Control parameter increases the stability and safety of battery management system so that it is guaranteed that electric car operates normally.
The above description is only an overview of the technical scheme of the present invention, in order to better understand the technical means of the present invention,
And it can be implemented in accordance with the contents of the specification, and in order to allow above and other objects of the present invention, feature and advantage can
It is clearer and more comprehensible, the followings are specific embodiments of the present invention.
Detailed description of the invention
By reading the following detailed description of the preferred embodiment, various other advantages and benefits are common for this field
Technical staff will become clear.The drawings are only for the purpose of illustrating a preferred embodiment, and is not considered as to the present invention
Limitation.And throughout the drawings, the same reference numbers will be used to refer to the same parts.In the accompanying drawings:
The battery for electric automobile that Fig. 1 shows a kind of cloud computing provided in an embodiment of the present invention and edge calculations combine
Schematic diagram of management system structure；
Fig. 2 shows cloud computing system provided in an embodiment of the present invention-edge calculations overall system architecture schematic diagrames.
The electric car electricity consumption that Fig. 3 shows another cloud computing provided in an embodiment of the present invention and edge calculations combine
Pond schematic diagram of management system structure；
Fig. 4 shows battery detecting control system schematic diagram provided in an embodiment of the present invention；
Fig. 5 shows edge calculations system schematic provided in an embodiment of the present invention；
Fig. 6 shows cloud computing system schematic diagram provided in an embodiment of the present invention；
Fig. 7 shows deep learning training pattern calculating process schematic diagram provided in an embodiment of the present invention.
Specific embodiment
Exemplary embodiments of the present disclosure are described in more detail below with reference to accompanying drawings.Although showing the disclosure in attached drawing
Exemplary embodiment, it being understood, however, that may be realized in various forms the disclosure without should be by embodiments set forth here
It is limited.On the contrary, these embodiments are provided to facilitate a more thoroughly understanding of the present invention, and can be by the scope of the present disclosure
It is fully disclosed to those skilled in the art.
As stated in the background art, currently, most insertions of the battery for electric automobile management system based on electric car local
Formula system carries out battery management, transfers to cloud computing platform to handle calculating work needed for battery management, and will be after processing
Result electric car is fed back to by wireless communication mode, electric car carries out associated batteries control according to the information that platform is fed back
System and management.But such mode is higher to communication quality and communication delay requirement, will lead to correlation when network failure
Loss of learning is controlled, is unable to run so as to cause whole system.
To solve the above-mentioned problems, the embodiment of the invention provides the electronic vapour that a kind of cloud computing and edge calculations combine
Vehicular battery management system, as shown in Figure 1, the system comprises: be arranged in electric car end battery detecting control system 11,
The cloud computing system 13 of edge calculations system 12 and setting beyond the clouds.
The battery detecting control system 11, can be used for detecting the running state parameter of battery, and by the operation shape
State parameter is uploaded to the edge calculations system 12.
The battery detecting control system 11 can specifically include: battery measuring unit (Battery Measurement
Unit, BMU), high voltage unit (High Voltage Unit, HVU) and battery control unit (Battery Control
Unit,BCU)。
The battery detecting control system 11 specifically can be used for detecting the running state parameter of battery, specifically can wrap
It includes: battery cell voltage, battery total voltage, battery charging and discharging electric current, battery temperature, battery insulation resistance etc..
The battery detecting control system 11 specifically can be also used for the running state parameter passing through controller local
The communication modes of net (Controller Area Network, CAN) are uploaded to edge calculations system 12.
The edge calculations system 12 can specifically include physical layer and application layer double-layer structure.
The edge calculations system 12 can be used for carrying out data cleansing to the running state parameter, and will be after cleaning
Running state parameter is uploaded to the cloud computing system 13.
The edge calculations system 12 can be also used for updating local cell tube using the updated model parameter
Model is managed, and according to the running state parameter and the updated local battery administrative model after the cleaning, described in calculating
The state of a control parameter of battery, and the state of a control parameter is returned into the battery detecting control system 11, to described
The operating status of battery is controlled.
The edge calculations system 12, which specifically can be also used for saving at electric car end, can be used for calculating battery control
The battery management model of state parameter.
It should be noted that the battery management model in the edge calculations system 12 and the cloud computing system 13 has
Original model parameter, the original model parameter battery management system are set manually when producing, the edge meter
Calculation system 12 calculates the available state of a control parameter according to the original model parameter and the running state parameter, but
It is that the precision of the state of a control parameter is lower at this time, is sent as the cloud constantly receives the edge calculations system 12
Running state parameter, the cloud can use the running state parameter and be trained more to the battery management model
Newly, the higher model parameter of precision is obtained.The higher model parameter of the precision is sent to the edge calculations system 12 again,
So as to which the higher state of a control parameter of precision is calculated.
The cloud computing system 13 may include data storage center and model training center.
The cloud computing system 13 specifically can be used for updating the cell tube in cloud according to the running state parameter after cleaning
Model is managed, updated model parameter is obtained and returns to the edge calculations system, as shown in Figure 2.
Further, the embodiment of the invention provides the electric car electricity consumptions that another cloud computing and edge calculations combine
Pond management system, as shown in figure 3, the system comprises: battery detecting control system 21, edge calculations system 22, cloud computing system
System 23:
The battery detecting control system 21 includes: battery detection unit 211 and battery control unit 212, such as Fig. 4 institute
Show, provides battery detecting control system schematic diagram.
The battery detection unit 211, can be used for detecting the running state parameter of battery.The running state parameter packet
Include battery cell voltage, battery total voltage, battery charging and discharging electric current, battery temperature and battery insulation resistance.
It should be noted that being deposited between the monomer voltage of the battery and the battery temperature and the state of a control parameter
Logical relation can be with are as follows: with patrolling between the monomer voltage and the battery temperature and the state of a control parameter SOC
For the relationship of collecting, the monomer voltage can be the external embodiment of the SOC, the monomer of the battery if the SOC increases
Voltage also increases.Similarly, the charging and discharging state of battery temperature and battery also will affect the numerical value of the SOC, such as temperature liter
The SOC increases when high, temperature when reducing the SOC also reduce；The battery is in SOC when charged state and increases, institute
It states battery and is in SOC reduction when discharge condition.
The battery detection unit 211 may include: battery measuring unit 2111 and high voltage unit 2112.
The battery measuring unit 2111 may include battery cell voltage detection circuit 21111, battery temperature detection electricity
Road 21112.
The battery cell voltage detection circuit 21111 specifically can be used for acquiring electricity by universal battery detection chip
The monomer voltage in pond.
The battery temperature detection circuit 21112, specifically can be used for acquiring battery temperature by thermistor.
The high voltage unit 2112 includes total voltage detection circuit 21121, insulation resistance measurement circuit 21122, charge and discharge
Electric current detection circuit 21123.
The total voltage detection circuit 21121 specifically can be used in such a way that electric resistance partial pressure adds insulation amplifier acquiring
Battery total voltage.
The insulation resistance measurement circuit 21122 specifically can be used for by way of double high-voltage isulation MOS switches acquiring
Battery always just, battery always bear insulation impedance between automobile ground.
The charging and discharging currents detection circuit 21123 specifically can be used for acquiring battery by double-range Hall sensor
Charging and discharging currents, and in the case where considering current range guarantee electric current detection accuracy.
The battery measuring unit can also include battery equalizing circuit 21113 and first control circuit 21114.
The battery equalizing circuit 21113 specifically can be used for receiving the equal of the return of battery control unit 212
After weighing apparatus order, balanced discharge is carried out to the battery.
The first control circuit 21114 specifically can be used for the battery cell voltage and the battery temperature
After conversion process, it is uploaded to the battery control unit 212.Wherein, the mode of the conversion process can be with are as follows: communications protocol solution
Analysis or analog-to-digital conversion (Analog-to-Digital Convert, AD conversion), the communications protocol can specifically include: SPI
Communications protocol, IIC communications protocol etc..
The high voltage unit 2112 further includes second control circuit 21124, and the second control circuit 21124 can be used
After by the battery total voltage, the insulation resistance and the charging and discharging currents conversion process, it is uploaded to the battery control
Unit 212.
The battery control unit 212 specifically can be used for the operation to the battery using the state of a control parameter
State is controlled, and the state of a control parameter includes battery remaining power, cell health state, remaining battery power, battery
Remaining capacity etc..
The battery control unit 212 specifically can be also used for passing through battery in the insufficient situation of battery dump energy
Administration interface in advance prompts automobile user, and the mileage that is inputted according to user by battery management interface and described
State of a control parameter carries out path planning.When cell voltage is too low, the battery control unit 212 can be also used for closing electricity
Electrical automobile inner part ancillary equipment is to save electricity.
The battery control unit 212 includes: communicating circuit 2121, control relay circuit 2122, fault detection and peace
Full protection circuit 2123 and third control circuit 2124.
The communicating circuit 2121 specifically can be used for communicating the acquisition operation shape with the battery detection unit 211
State parameter is established to communicate with charger and is charged to the battery, communicated with the edge calculations system 22, by the fortune
Row state parameter is uploaded to the edge calculations system 22, and receives the state of a control parameter.
The control relay circuit 2122 specifically can be used for controlling the charge relay of battery, electric discharge relay, add
Electrothermal relay, cooling fan relay, to be managed to battery power status.
The fault detection and safety protective circuit 2123 specifically can be used for information according to the operation state and determine institute
When stating cell malfunctions, exports warning message and disconnect corresponding relay under high-risk level condition, to guarantee
State cell safety；
The third control circuit 2124 specifically can be used for controlling the communicating circuit 2121, relay control
The work that circuit 2122 and the fault detection and safety protective circuit 2123 execute.
The edge calculations system 22 includes: physical layer 221 and application layer 222.As shown in figure 5, providing edge calculations
System schematic.
The data cleansing module 2221, the model execution module 2222 and the wireless communication module 2223 are distinguished
It is set to the application layer.
The data cleansing module 221 specifically can be used for cleaning the running state parameter, and will be described clear
Running state parameter after washing is transmitted to the model execution module 222 and the wireless communication module 223；
The data cleansing module 221, specifically can be also used for the battery data for sending battery detecting control system 21
After carrying out the data cleansings such as duplicate removal, error correction, denoising processing, by the data forwarding after the cleaning to the wireless communication module
222 and the model execution module 223.
The model execution module 222 specifically can be used for updating local battery management using updated model parameter
Model.
The model execution module 222 specifically can be also used for holding for the battery management model that electric car end is locally stored
Row, i.e., calculate according to state of a control parameter of the real-time running state parameter after cleaning to battery.The battery status ginseng
Number can specifically include: battery remaining power (State of charge, SOC), cell health state (State of
Health, SOH), remaining battery power (State of Power, SOP), battery dump energy (State of Energy,
SOE) etc..
The wireless communication module 223 specifically can be used for periodically receiving the updated model parameter of cloud computing system 23.
The wireless communication module 223 specifically can be also used for that the control is calculated when the model execution module 222
After state parameter processed, the state of a control parameter is sent to by the battery detecting control system 21 by CAN.
After the wireless communication module 223 specifically can be used for modulating the running state parameter after the cleaning, through nothing
Gauze network is uploaded to the cloud computing system 23, and periodically receives the cloud computing by communication modes such as wifi, 4G transmission
The model parameter that system 23 returns.
The physical layer 221 includes embedded-type ARM CPU2211, embedded gpu 2212 and wireless parsing module 2213.
The embedded-type ARM CPU2211 specifically can be used for supporting that the data cleansing module 2221 carries out data clear
It washes and the reception and transmission of data.
The embedded gpu 2212 specifically can be used for that the model execution module 2222 is supported to carry out state of a control parameter
Calculating.
What the wireless parsing module 2213 specifically can be used for receiving the wireless communication module 2223 or sending
Data are modulated demodulation.
The embedded-type ARM CPU2211 logic branch processing capacity is strong, specifically can be used for system execute, communication and
Human-computer interaction etc. is controlled.Wherein, the system executes control, may include the operation for controlling entire edge calculations system 22
Process, such as acquisition, cleaning treatment, the forwarding control of data, model running control etc.；The Communication Control, may include from
Battery detecting control system 21 obtains data, and data are sent to the wireless parsing module 2213 by treated；The people
Machine interactive controlling process can specifically include: the user at electric car end can check that battery operation is joined by battery management interface
Number information and control parameter information, and instruction is issued by the battery management interface, the battery management system is controlled
System.
2212 computation capability of embedded gpu is strong, specifically can be used for according to running state parameter and described
The battery management model on ground calculates the state of a control parameter of the battery.
The cloud computing system 23 may include: data storage center 231 and model training center 232, as shown in fig. 6,
Provide the schematic diagram of cloud computing system.
The data storage center 231 can be used for storing the operating status that the edge calculations system 22 uploads
Parameter.
The model training center 232 can be used for parameter real-time update training battery management mould according to the operation state
Type, and obtained updated model parameter is uploaded to the edge calculations system 22.
The model training center 232 specifically can be also used for the battery management model that training updates cloud.For example, as schemed
It shown in 7, is updated using the training that the calculation of deep learning carries out model, deep learning network input layer is the monomer of battery
Voltage Vi, k and battery total voltage Vtotal, k, charging and discharging currents Tk and cycle-index Ncycle, middle layer use depth confidence
Network DBN mode (being divided into RBM layers and BP layers) is to network, according to the parameter information of each node of cloud computing system passback, meter
Calculate the end value of final output layer SOC and SOH.Deepness belief network (Deep Belief Network, the DBN) instruction
The mode of white silk, being limited Boltzmann machine (Restricted Boltzmann Machine, RBM) and one layer using multilayer has supervision net
Network (Back Propagation, BP), two adjacent hidden layers constitute a RBM.The training process of DBN are as follows: setting network layer
The parameters such as number, hidden layer unit number, the entire DBN network parameter of random initializtion；By training sample data to first RBM, adopt
RBM is trained with deep learning algorithm (Contrastive Divergence, CD algorithm), saves network parameter；Will under
The hidden layer output of one layer of RBM is as the input data next RBM of training, until all RBM training finish, by unsupervised
Pre-training, can get entire DBN network parameter；The training for having supervision is carried out using the BP network of the last layer, and is reversely adjusted
The RBM of whole each layer obtains DBN network parameter adjusted.In the training process of DBN network, the core when training of RBM is led to
The layer-by-layer training of RBM is crossed, realizes the initialization of DBN network parameter, although these network parameters are not optimized parameters, they
It often falls near optimal value, can effectively avoid BP algorithm is caused in training classifier due to random initializtion network parameter
Fall into locally optimal solution or training time too long problem.
The model training center 232 can be used for the operating status stored according to the data storage center 231
Parameter, to the battery management model of cloud storage, such as data mining, deep learning, the various machine learning models of neural network
It is trained update, to obtain more accurate model parameter.Wherein, the model parameter can be in the model training
The heart 232 according to the operation state parameter real-time update training battery management model obtain as a result, being in a manner of deep learning
Example: the model parameter can be the w value (weighted value) and b value (deviant) of each node during the deep learning, lead to
Chang Suoshu model parameter is back to the edge calculations system 22 with a matrix type, i.e., the described cloud computing system 23 is to the side
22 transmission pattern parameter of edge computing system, the form of the model parameter include w matrix and b matrix.
According to the technical solution of the present invention, it can guarantee that electric car can still operate normally in case of a network fault.
Meanwhile update is trained to battery management model using the computing capability in cloud and advanced machine learning algorithm, in order to
The battery management model that accuracy is high, error is small, stability is high is obtained, the stability and safety of battery management system are improved
In the above-described embodiments, it all emphasizes particularly on different fields to the description of each embodiment, there is no the portion being described in detail in some embodiment
Point, reference can be made to the related descriptions of other embodiments.
It is understood that the correlated characteristic in the above method and device can be referred to mutually.In addition, in above-described embodiment
" first ", " second " etc. be and not represent the superiority and inferiority of each embodiment for distinguishing each embodiment.
It is apparent to those skilled in the art that for convenience and simplicity of description, the system of foregoing description,
The specific work process of device and unit, can refer to corresponding processes in the foregoing method embodiment, and details are not described herein.
Algorithm and display are not inherently related to any particular computer, virtual system, or other device provided herein.
Various general-purpose systems can also be used together with teachings based herein.As described above, it constructs required by this kind of system
Structure be obvious.In addition, the present invention is also not directed to any particular programming language.It should be understood that can use various
Programming language realizes summary of the invention described herein, and the description done above to language-specific is to disclose this hair
Bright preferred forms.
In the instructions provided here, numerous specific details are set forth.It is to be appreciated, however, that implementation of the invention
Example can be practiced without these specific details.In some instances, well known method, structure is not been shown in detail
And technology, so as not to obscure the understanding of this specification.
Similarly, it should be understood that in order to simplify the disclosure and help to understand one or more of the various inventive aspects, In
Above in the description of exemplary embodiment of the present invention, each feature of the invention is grouped together into single implementation sometimes
In example, figure or descriptions thereof.However, the disclosed method should not be interpreted as reflecting the following intention: i.e. required to protect
Shield the present invention claims features more more than feature expressly recited in each claim.More precisely, as following
Claims reflect as, inventive aspect is all features less than single embodiment disclosed above.Therefore,
Thus the claims for following specific embodiment are expressly incorporated in the specific embodiment, wherein each claim itself
All as a separate embodiment of the present invention.
Those skilled in the art will understand that can be carried out adaptively to the module in the equipment in embodiment
Change and they are arranged in one or more devices different from this embodiment.It can be the module or list in embodiment
Member or component are combined into a module or unit or component, and furthermore they can be divided into multiple submodule or subelement or
Sub-component.Other than such feature and/or at least some of process or unit exclude each other, it can use any
Combination is to all features disclosed in this specification (including adjoint claim, abstract and attached drawing) and so disclosed
All process or units of what method or apparatus are combined.Unless expressly stated otherwise, this specification is (including adjoint power
Benefit require, abstract and attached drawing) disclosed in each feature can carry out generation with an alternative feature that provides the same, equivalent, or similar purpose
It replaces.
In addition, it will be appreciated by those of skill in the art that although some embodiments described herein include other embodiments
In included certain features rather than other feature, but the combination of the feature of different embodiments mean it is of the invention
Within the scope of and form different embodiments.For example, in the following claims, embodiment claimed is appointed
Meaning one of can in any combination mode come using.
Various component embodiments of the invention can be implemented in hardware, or to run on one or more processors
Software module realize, or be implemented in a combination thereof.It will be understood by those of skill in the art that can be used in practice
Microprocessor or digital signal processor (DSP) realize one of some or all components according to embodiments of the present invention
A little or repertoire.The present invention is also implemented as setting for executing some or all of method as described herein
Standby or program of device (for example, computer program and computer program product).It is such to realize that program of the invention deposit
Storage on a computer-readable medium, or may be in the form of one or more signals.Such signal can be from because of spy
It downloads and obtains on net website, be perhaps provided on the carrier signal or be provided in any other form.
It should be noted that the above-mentioned embodiments illustrate rather than limit the invention, and ability
Field technique personnel can be designed alternative embodiment without departing from the scope of the appended claims.In the claims,
Any reference symbol between parentheses should not be configured to limitations on claims.Word "comprising" does not exclude the presence of not
Element or step listed in the claims.Word "a" or "an" located in front of the element does not exclude the presence of multiple such
Element.The present invention can be by means of including the hardware of several different elements and being come by means of properly programmed computer real
It is existing.In the unit claims listing several devices, several in these devices can be through the same hardware branch
To embody.The use of word first, second, and third does not indicate any sequence.These words can be explained and be run after fame
Claim.
Claims (8)
1. the battery for electric automobile management system that a kind of cloud computing and edge calculations combine characterized by comprising setting
In the battery detecting control system at electric car end, edge calculations system and setting cloud computing system beyond the clouds,
The battery detecting control system is uploaded for detecting the running state parameter of battery, and by the running state parameter
To the edge calculations system；
The edge calculations system, for being cleaned to the running state parameter, and by the running state parameter after cleaning
It is uploaded to the cloud computing system；
The cloud computing system, for according to the running state parameter after cleaning, the battery management model in training cloud to be obtained more
Model parameter after new simultaneously returns to the edge calculations system；
The edge calculations system is also used to update local battery management model using the updated model parameter, and
According to the running state parameter and the updated local battery administrative model after the cleaning, the control of the battery is calculated
State parameter, and the state of a control parameter is returned into the battery detecting control system, with the operation shape to the battery
State is controlled.
2. system according to claim 1, which is characterized in that the edge calculations system includes: data cleansing module, mould
Type execution module and wireless communication module,
The data cleansing module, for being cleaned to the running state parameter, and by the operating status after the cleaning
Parameter is transmitted to the model execution module and wireless communication module；
The model execution module, for according to the running state parameter and the updated local battery pipe after the cleaning
Model is managed, calculates the state of a control parameter of the battery, and the state of a control parameter is returned into the battery detecting and is controlled
System；
The wireless communication module is used to be uploaded to after the running state parameter modulation after the cleaning through wireless network described
Cloud computing system, and periodically receive the model parameter of the cloud computing system passback.
3. system according to claim 2, which is characterized in that the edge calculations system includes: physical layer and answering
With layer,
The data cleansing module, the model execution module and the wireless communication module are respectively arranged at the application layer；
The physical layer includes embedded-type ARM CPU, embedded gpu and wireless parsing module, and the embedded-type ARM CPU is used for
Support that the data cleansing module carries out data cleansing and data upload, the embedded gpu is for supporting the model to execute
Module carries out the calculating of state of a control parameter, and the wireless parsing module is used to receive the wireless communication module or send
Data be modulated demodulation.
4. system according to claim 1, which is characterized in that the battery detecting control system includes: battery detecting list
Member and battery control unit,
The battery detection unit, for detecting the running state parameter of battery, the running state parameter includes battery cell
Voltage, battery total voltage, battery charging and discharging electric current, battery temperature and battery insulation resistance；
The battery control unit controls the operating status of the battery, institute for utilizing the state of a control parameter
Stating state of a control parameter includes battery remaining power, cell health state, remaining battery power and battery dump energy.
5. system according to claim 4, which is characterized in that the battery detection unit include: battery measuring unit and
High voltage unit,
The battery measuring unit includes battery cell voltage detection circuit, battery temperature detection circuit；
The high voltage unit includes total voltage detection circuit, insulation resistance measurement circuit, charging and discharging currents detection circuit.
6. system according to claim 5, which is characterized in that
The battery measuring unit also includes battery equalizing circuit and first control circuit, and the first control circuit is used for institute
The battery temperature of the battery cell voltage and battery temperature detection circuit detection of stating battery voltage detection circuit detection turns
After changing processing, it is uploaded to the battery control unit；
The battery equalizing circuit, for after receiving the equalization command that the battery control unit returns, to the battery
Carry out balanced discharge；
The high voltage unit further includes second control circuit, and the second control circuit is used for the total voltage detection circuit
The battery total voltage of detection, the insulation resistance of insulation resistance measurement circuit detection, charging and discharging currents detection circuit inspection
The charging and discharging currents surveyed after conversion process, are uploaded to the battery control unit.
7. system according to claim 4, which is characterized in that the battery control unit includes:
Communicating circuit is established with charger and is communicated for obtaining the running state parameter with battery detection unit communication
Charged to the battery, with the edge calculations system communication, the running state parameter is uploaded to the edge
Computing system, and receive the state of a control parameter；
Control relay circuit, the charge relay for controlling battery, electric discharge relay, heating relay, cooling fan relay,
To be managed to battery power status；
Fault detection and safety protective circuit, it is defeated for when information determines the cell malfunctions according to the operation state
Warning message and corresponding relay is disconnected under high-risk level condition out, to guarantee the cell safety
Third control circuit, for controlling the communicating circuit, the control relay circuit and the fault detection and peace
The work that full protection circuit executes.
8. system according to claim 1, which is characterized in that the cloud computing system includes:
Data storage center, the running state parameter uploaded for storing the edge calculations system；
Model training center for the training battery management model of parameter real-time update according to the operation state, and will obtain
Updated model parameter is uploaded to the edge calculations system.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910530965.4A CN110386027B (en) | 2019-06-19 | 2019-06-19 | Battery management system for electric automobile combining cloud computing and edge computing |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910530965.4A CN110386027B (en) | 2019-06-19 | 2019-06-19 | Battery management system for electric automobile combining cloud computing and edge computing |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN110386027A true CN110386027A (en) | 2019-10-29 |
| CN110386027B CN110386027B (en) | 2021-03-02 |
Family
ID=68285592
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910530965.4A Active - Reinstated CN110386027B (en) | 2019-06-19 | 2019-06-19 | Battery management system for electric automobile combining cloud computing and edge computing |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110386027B (en) |
Cited By (13)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110719210A (en) * | 2019-12-05 | 2020-01-21 | 赣江新区智慧物联研究院有限公司 | Industrial equipment predictive maintenance method based on cloud edge cooperation |
| CN111160616A (en) * | 2019-12-05 | 2020-05-15 | 广东工业大学 | Kitchen electrical equipment predictive maintenance system and method based on edge cloud cooperation |
| CN111273179A (en) * | 2020-02-21 | 2020-06-12 | 深圳普瑞赛思检测技术有限公司 | Electric vehicle detection method and system |
| CN111559277A (en) * | 2020-05-08 | 2020-08-21 | 淮安信息职业技术学院 | Current and temperature control system for battery pack of new energy electric automobile |
| CN112306689A (en) * | 2020-11-02 | 2021-02-02 | 时代云英(深圳)科技有限公司 | Edge calculation system and method |
| CN112881930A (en) * | 2021-01-19 | 2021-06-01 | 北京昆兰新能源技术有限公司 | Energy storage battery health management prediction method and system based on Internet of things |
| CN113093043A (en) * | 2021-04-01 | 2021-07-09 | 苏州睿锂物联科技有限公司 | Battery edge computing terminal, data communication method, storage medium, and electronic device |
| CN113097580A (en) * | 2021-03-23 | 2021-07-09 | 苏州恒电能源动力科技有限公司 | Police paddle battery pack based on edge calculation |
| 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 |
| CN113829952A (en) * | 2021-09-29 | 2021-12-24 | 华人运通(江苏)技术有限公司 | Battery control method and system of electric automobile and electric automobile |
| CN115097336A (en) * | 2022-05-30 | 2022-09-23 | 中国第一汽车股份有限公司 | Battery state of charge value estimation system, method, electronic equipment and medium |
| TWI825686B (en) * | 2022-04-22 | 2023-12-11 | 大葉大學 | Intelligent power management edge estimation system and construction method |
| CN117523940A (en) * | 2024-01-08 | 2024-02-06 | 深圳风向标教育资源股份有限公司 | Power battery management system and practical training teaching platform |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20140236404A1 (en) * | 2013-02-18 | 2014-08-21 | Ford Global Technologies, Llc | Method and Apparatus for Route Completion Likelihood Display |
| CN107959708A (en) * | 2017-10-24 | 2018-04-24 | 北京邮电大学 | A kind of car networking service collaboration computational methods and system based on high in the clouds-marginal end-car end |
| US20180182188A1 (en) * | 2011-07-26 | 2018-06-28 | Gogoro Inc. | Apparatus, method and article for reserving power storage devices at reserving power storage device collection, charging and distribution machines |
| CN108279383A (en) * | 2017-11-30 | 2018-07-13 | 深圳市科列技术股份有限公司 | battery life predicting method, battery data server and battery data processing system |
| CN208754041U (en) * | 2018-07-13 | 2019-04-16 | 深圳市中安华讯智能科技有限公司 | A kind of smart battery system |
-
2019
- 2019-06-19 CN CN201910530965.4A patent/CN110386027B/en active Active - Reinstated
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20180182188A1 (en) * | 2011-07-26 | 2018-06-28 | Gogoro Inc. | Apparatus, method and article for reserving power storage devices at reserving power storage device collection, charging and distribution machines |
| US20140236404A1 (en) * | 2013-02-18 | 2014-08-21 | Ford Global Technologies, Llc | Method and Apparatus for Route Completion Likelihood Display |
| CN107959708A (en) * | 2017-10-24 | 2018-04-24 | 北京邮电大学 | A kind of car networking service collaboration computational methods and system based on high in the clouds-marginal end-car end |
| CN108279383A (en) * | 2017-11-30 | 2018-07-13 | 深圳市科列技术股份有限公司 | battery life predicting method, battery data server and battery data processing system |
| CN208754041U (en) * | 2018-07-13 | 2019-04-16 | 深圳市中安华讯智能科技有限公司 | A kind of smart battery system |
Cited By (15)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111160616B (en) * | 2019-12-05 | 2021-09-07 | 广东工业大学 | Kitchen electrical equipment predictive maintenance system and method based on edge cloud cooperation |
| CN111160616A (en) * | 2019-12-05 | 2020-05-15 | 广东工业大学 | Kitchen electrical equipment predictive maintenance system and method based on edge cloud cooperation |
| CN110719210A (en) * | 2019-12-05 | 2020-01-21 | 赣江新区智慧物联研究院有限公司 | Industrial equipment predictive maintenance method based on cloud edge cooperation |
| CN111273179A (en) * | 2020-02-21 | 2020-06-12 | 深圳普瑞赛思检测技术有限公司 | Electric vehicle detection method and system |
| CN111559277A (en) * | 2020-05-08 | 2020-08-21 | 淮安信息职业技术学院 | Current and temperature control system for battery pack of new energy electric automobile |
| CN112306689A (en) * | 2020-11-02 | 2021-02-02 | 时代云英(深圳)科技有限公司 | Edge calculation system and method |
| CN112881930A (en) * | 2021-01-19 | 2021-06-01 | 北京昆兰新能源技术有限公司 | Energy storage battery health management prediction method and system based on Internet of things |
| CN113097580A (en) * | 2021-03-23 | 2021-07-09 | 苏州恒电能源动力科技有限公司 | Police paddle battery pack based on edge calculation |
| CN113093043A (en) * | 2021-04-01 | 2021-07-09 | 苏州睿锂物联科技有限公司 | Battery edge computing terminal, data communication method, storage medium, and electronic device |
| 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 |
| CN113829952A (en) * | 2021-09-29 | 2021-12-24 | 华人运通(江苏)技术有限公司 | Battery control method and system of electric automobile and electric automobile |
| TWI825686B (en) * | 2022-04-22 | 2023-12-11 | 大葉大學 | Intelligent power management edge estimation system and construction method |
| CN115097336A (en) * | 2022-05-30 | 2022-09-23 | 中国第一汽车股份有限公司 | Battery state of charge value estimation system, method, electronic equipment and medium |
| CN117523940A (en) * | 2024-01-08 | 2024-02-06 | 深圳风向标教育资源股份有限公司 | Power battery management system and practical training teaching platform |
| CN117523940B (en) * | 2024-01-08 | 2024-04-19 | 深圳风向标教育资源股份有限公司 | Power battery management system and practical training teaching platform |
Also Published As
| Publication number | Publication date |
|---|---|
| CN110386027B (en) | 2021-03-02 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110386027A (en) | The battery for electric automobile management system that cloud computing and edge calculations combine | |
| CN110370983A (en) | Battery for electric automobile management system based on 5G mobile communication | |
| JP6757602B2 (en) | Battery state estimation device and method | |
| US20240266856A1 (en) | Systems and methods of applying artificial intelligence to battery technology | |
| CN103969585B (en) | Assess method and apparatus, related system and the vehicle of the behaviour in service of battery | |
| WO2022193899A1 (en) | Balance monitoring control system and method for power battery, server, and storage medium | |
| CN108780413B (en) | TYPE-C factory and special manipulation mode are supported | |
| CN106058857B (en) | Meter and the active distribution network reliability estimation method of load transfer and cutting load | |
| CN105912448A (en) | Intelligent method for calibrating battery capacity | |
| CN109888414B (en) | Management method, device and system of power battery | |
| CN111762054B (en) | Charging station management method and management system | |
| CN105977558A (en) | Extensible hybrid battery management system | |
| CN108923082A (en) | distributed battery management system and battery pack | |
| CN110120559A (en) | A kind of charging method of lithium ion battery, device and terminal device | |
| CN116381494A (en) | Method and device for predicting maximum available capacity of battery, electronic equipment and storage medium | |
| CN107878243A (en) | A kind of battery management system and method | |
| CN109713762A (en) | A kind of charge control method, device and terminal device | |
| CN111178423A (en) | Fault early warning method and device | |
| CN109941149A (en) | Multi-source battery pack charging/discharging thereof, device, electronic equipment, storage medium | |
| CN104553850B (en) | A kind of data acquisition unit of battery management system | |
| CN106571495B (en) | Accumulating system and charge accumulating method | |
| CN109363660A (en) | Rhythm of the heart method and server based on BP neural network | |
| CN108461836A (en) | Batteries of electric automobile managing device and system | |
| CN115407217B (en) | Online estimation method and system for state of charge of lithium battery of electric vehicle | |
| CN106828150A (en) | A kind of discrete battery management system |
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 | ||
| CF01 | Termination of patent right due to non-payment of annual fee |
Granted publication date: 20210302 Termination date: 20210619 |
|
| CF01 | Termination of patent right due to non-payment of annual fee | ||
| RR01 | Reinstatement of patent right |
Former decision: Termination of patent right without annual fee Former decision publication date: 20220603 |
|
| RR01 | Reinstatement of patent right |