CN110386027B - Battery management system for electric automobile combining cloud computing and edge computing - Google Patents

Battery management system for electric automobile combining cloud computing and edge computing Download PDF

Info

Publication number
CN110386027B
CN110386027B CN201910530965.4A CN201910530965A CN110386027B CN 110386027 B CN110386027 B CN 110386027B CN 201910530965 A CN201910530965 A CN 201910530965A CN 110386027 B CN110386027 B CN 110386027B
Authority
CN
China
Prior art keywords
battery
state parameters
computing system
control
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.)
Active - Reinstated
Application number
CN201910530965.4A
Other languages
Chinese (zh)
Other versions
CN110386027A (en
Inventor
汤宪宇
俞胜平
付俊
康铭鑫
张泉
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Northeastern University China
Original Assignee
Northeastern University China
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Northeastern University China filed Critical Northeastern University China
Priority to CN201910530965.4A priority Critical patent/CN110386027B/en
Publication of CN110386027A publication Critical patent/CN110386027A/en
Application granted granted Critical
Publication of CN110386027B publication Critical patent/CN110386027B/en
Active - Reinstated legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Images

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)
  • Secondary Cells (AREA)
  • Charge And Discharge Circuits For Batteries Or The Like (AREA)
  • Electric Propulsion And Braking For Vehicles (AREA)

Abstract

The invention discloses a battery management system for an electric vehicle, which combines cloud computing and edge computing, relates to the technical field of batteries, and mainly aims to ensure that the electric vehicle can still normally run when a network fails and improve the stability and the safety of the battery management system. The system comprises: the battery detection control system is used for detecting the running state parameters of the battery and uploading the running state parameters to the edge computing system; the edge computing system is used for cleaning the running state parameters and uploading the parameters to the cloud computing system; the cloud computing system is used for training the battery management model at the cloud end according to the cleaned running state parameters to obtain updated model parameters and transmitting the updated model parameters back to the edge computing system; and the edge computing system is also used for updating the local battery management model by using the updated model parameters, computing the control state parameters of the battery according to the cleaned running state parameters and the local battery management model, and transmitting the control state parameters back to the battery detection control system so as to control the running state of the battery.

Description

Battery management system for electric automobile combining cloud computing and edge computing
Technical Field
The invention relates to the technical field of batteries, in particular to a battery management system for an electric automobile, which combines cloud computing and edge computing.
Background
The battery management system is used as the core of the energy management of the electric automobile, the running state, the remaining mileage, the safety state and the like of the battery are estimated by collecting the working information of the battery in the electric automobile, so that the charging and discharging of the battery, the battery equalization, the battery heating and the safety of the battery are controlled, the service life of the battery can be prolonged by adopting the battery management system, and the safe running of the battery is guaranteed.
At present, most of battery management systems for electric vehicles perform battery management based on local embedded systems of the electric vehicles, and are limited by embedded system operation resources and operation speed, the battery management systems generally estimate information such as battery residual capacity and battery safety state through linear models such as a voltage estimation method, an ampere-hour integration method and a kalman filtering method, but because a battery charging and discharging process is a complex chemical reaction process, the estimation only by adopting a simple linear model can cause problems such as poor estimation precision, error accumulation and poor stability.
With the development of wireless communication technology, cloud computing, edge computing and big data technology, a battery management system based on cloud computing and wireless communication technology becomes possible. The battery management system based on cloud computing reduces the local computing pressure of the electric automobile, a large amount of computing work is processed by the cloud computing platform, the processed result is fed back to the electric automobile in a wireless communication mode, and the electric automobile controls and manages the related batteries according to the information fed back by the platform. However, this method has high requirements for communication quality and communication delay, and when a network fails, the related control information is lost, so that the entire system cannot operate.
Disclosure of Invention
In view of this, the invention provides a battery management system for an electric vehicle, which combines cloud computing and edge computing, and mainly aims to ensure that the electric vehicle can still normally operate under the condition of network failure, and improve the stability and the safety of the system.
According to an aspect of the present invention, there is provided a battery management system for an electric vehicle, which combines cloud computing and edge computing, including:
the battery detection control system is used for detecting the running state parameters of the battery and uploading the running state parameters to the edge computing system;
the edge computing system is used for cleaning the running state parameters and uploading the cleaned running state parameters to the cloud computing system;
the cloud computing system is used for training a battery management model at the cloud end according to the cleaned running state parameters, obtaining updated model parameters and transmitting the updated model parameters back to the edge computing system;
and the edge computing system is also used for updating a local battery management model by using the updated model parameters, computing control state parameters of the battery according to the cleaned running state parameters and the updated local battery management model, and returning the control state parameters to the battery detection control system so as to control the running state of the battery.
Compared with the prior art that data collected by an electric automobile is sent to a cloud computing platform to be processed, the processed result is fed back to the electric automobile in a wireless communication mode, and the electric automobile performs related battery control and management according to information fed back by the platform, the battery management system for the electric automobile is provided with a battery detection control system and an edge computing system at an electric automobile end and the cloud computing system is provided at a cloud end. The battery detection control system is used for detecting the running state parameters of the battery and uploading the running state parameters to the edge computing system; the edge computing system is used for cleaning the running state parameters and uploading the cleaned running state parameters to the cloud computing system; the cloud computing system is used for training a battery management model at the cloud end according to the cleaned running state parameters, obtaining updated model parameters and transmitting the updated model parameters back to the edge computing system; the edge computing system is further configured to update a local battery management model by using the updated model parameters, calculate control state parameters of the battery according to the cleaned operation state parameters and the updated local battery management model, and transmit the control state parameters back to the battery detection control system to control the operation state of the battery. According to the invention, a set of operation system independent of the calculation result of the cloud computing system is established at the electric automobile end by adopting an edge computing mode, and the electric automobile end can still calculate the control parameters of the battery in real time through the local edge computing system under the condition that the network fails, so that the normal operation of the electric automobile is ensured, and the stability and the safety of the battery management system are improved.
The foregoing description is only an overview of the technical solutions of the present invention, and the embodiments of the present invention are described below in order to make the technical means of the present invention more clearly understood and to make the above and other objects, features, and advantages of the present invention more clearly understandable.
Drawings
Various other advantages and benefits will become apparent to those of ordinary skill in the art upon reading the following detailed description of the preferred embodiments. The drawings are only for purposes of illustrating the preferred embodiments and are not to be construed as limiting the invention. Also, like reference numerals are used to refer to like parts throughout the drawings. In the drawings:
fig. 1 is a schematic structural diagram of a battery management system for an electric vehicle, which combines cloud computing and edge computing according to an embodiment of the present invention;
fig. 2 is a schematic diagram illustrating an overall framework of a cloud computing system-edge computing system according to an embodiment of the present invention.
Fig. 3 is a schematic structural diagram of another battery management system for an electric vehicle, which combines cloud computing and edge computing according to an embodiment of the present invention;
FIG. 4 is a schematic diagram of a battery test control system according to an embodiment of the present invention;
FIG. 5 is a schematic diagram of an edge computing system provided by an embodiment of the invention;
FIG. 6 is a schematic diagram of a cloud computing system provided by an embodiment of the invention;
FIG. 7 is a schematic diagram illustrating a computation process of a deep learning training model according to an embodiment of the present invention.
Detailed Description
Exemplary embodiments of the present disclosure will be described in more detail below with reference to the accompanying drawings. While exemplary embodiments of the present disclosure are shown in the drawings, it should be understood that the present disclosure may be embodied in various forms and should not be limited to the embodiments set forth herein. Rather, these embodiments are provided so that this disclosure will be thorough and complete, and will fully convey the scope of the disclosure to those skilled in the art.
As described in the background art, currently, most battery management systems for electric vehicles perform battery management based on a local embedded system of the electric vehicle, and send the calculation work required by the battery management to a cloud computing platform for processing, and feed back the processed result to the electric vehicle in a wireless communication manner, and the electric vehicle performs related battery control and management according to the information fed back by the platform. However, this method has high requirements for communication quality and communication delay, and when a network fails, the related control information is lost, so that the entire system cannot operate.
In order to solve the above problem, an embodiment of the present invention provides a battery management system for an electric vehicle, which combines cloud computing and edge computing, and as shown in fig. 1, the system includes: the system comprises a battery detection control system 11 arranged at the electric automobile end, an edge computing system 12 and a cloud computing system 13 arranged at the cloud end.
The battery detection control system 11 may be configured to detect an operation status parameter of the battery, and upload the operation status parameter to the edge computing system 12.
The battery detection control system 11 may specifically include: a Battery Measurement Unit (BMU), a High Voltage Unit (HVU), and a Battery Control Unit (BCU).
The battery detection control system 11 may be specifically configured to detect an operating state parameter of a battery, and specifically may include: the battery cell voltage, the total voltage of the battery, the charging and discharging current of the battery, the temperature of the battery, the insulation resistance of the battery and the like.
The battery detection control system 11 may be further configured to upload the operation state parameter to the edge computing system 12 in a Controller Area Network (CAN) communication manner.
The edge computing system 12 may specifically include a two-layer structure of a physical layer and an application layer.
The edge computing system 12 may be configured to perform data cleaning on the operation state parameters, and upload the cleaned operation state parameters to the cloud computing system 13.
The edge computing system 12 may also be configured to update a local battery management model by using the updated model parameter, calculate a control state parameter of the battery according to the cleaned operation state parameter and the updated local battery management model, and transmit the control state parameter back to the battery detection control system 11, so as to control the operation state of the battery.
The edge computing system 12 may also be used to store, in particular, a battery management model at the electric vehicle end that may be used to calculate battery control state parameters.
It should be noted that the battery management models in the edge computing system 12 and the cloud computing system 13 have initial model parameters, the initial model parameters are manually set during the production of the battery management system, the edge computing system 12 may calculate the control state parameters according to the initial model parameters and the operation state parameters, but at this time, the accuracy of the control state parameters is low, and as the cloud continuously receives the operation state parameters sent by the edge computing system 12, the cloud may train and update the battery management model by using the operation state parameters, so as to obtain model parameters with higher accuracy. And then the model parameters with higher precision are sent to the edge computing system 12, so that the control state parameters with higher precision can be obtained through calculation.
The cloud computing system 13 may include a data storage center and a model training center.
The cloud computing system 13 may be specifically configured to update the cloud-side battery management model according to the cleaned operating state parameters, obtain updated model parameters, and return the updated model parameters to the edge computing system, as shown in fig. 2.
Further, another battery management system for an electric vehicle, which combines cloud computing and edge computing, is provided in an embodiment of the present invention, and as shown in fig. 3, the system includes: battery detection control system 21, edge computing system 22, cloud computing system 23:
the battery detection control system 21 includes: the battery detection unit 211 and the battery control unit 212, as shown in fig. 4, provide a schematic diagram of a battery detection control system.
The battery detection unit 211 may be configured to detect an operating state parameter of the battery. The operation state parameters comprise the voltage of a single battery, the total voltage of the battery, the charging and discharging current of the battery, the temperature of the battery and the insulation resistance of the battery.
It should be noted that, the logical relationship between the cell voltage of the battery, the battery temperature and the control state parameter may be: taking the logic relationship between the cell voltage and the battery temperature and the control state parameter SOC as an example, the cell voltage may be an appearance of the SOC, and if the SOC increases, the cell voltage of the battery also increases. Similarly, the temperature of the battery and the charge-discharge state of the battery also affect the value of the SOC, e.g., the SOC increases as the temperature increases and decreases as the temperature decreases; the SOC increases when the battery is in a charged state and decreases when the battery is in a discharged state.
The battery detection unit 211 may include: a battery measurement unit 2111 and a high voltage unit 2112.
The battery measurement unit 2111 may include a cell voltage detection circuit 21111 and a battery temperature detection circuit 21112.
The battery cell voltage detection circuit 21111 may be specifically configured to collect cell voltages of a battery through a universal battery detection chip.
The battery temperature detection circuit 21112 may be specifically configured to collect a battery temperature through a thermistor.
The high voltage unit 2112 includes a total voltage detection circuit 21121, an insulation resistance measurement circuit 21122, and a charge/discharge current detection circuit 21123.
The total voltage detection circuit 21121 may be specifically configured to collect the total voltage of the battery by a resistor voltage division and an insulation operational amplifier.
The insulation resistance measurement circuit 21122 may be specifically configured to acquire insulation impedances between the total positive and negative of the battery and the ground of the vehicle by using a dual high-voltage insulation MOS switch.
The charging and discharging current detection circuit 21123 can be specifically used for collecting the charging and discharging current of the battery through the double-range hall sensor, and the detection precision of the current is ensured under the condition of considering the current range.
The battery measurement unit may also include a battery equalization circuit 21113 and a first control circuit 21114.
The battery balancing circuit 21113 may be specifically configured to perform balanced discharge on the battery after receiving a balancing command returned by the battery control unit 212.
The first control circuit 21114 may be specifically configured to upload the cell voltage and the battery temperature after the conversion processing to the battery control unit 212. The conversion processing mode may be: the communication protocol analysis or Analog-to-Digital conversion (AD conversion) may specifically include: SPI communication protocol, IIC communication protocol, etc.
The high voltage unit 2112 further includes a second control circuit 21124, and the second control circuit 21124 may be configured to convert the total battery voltage, the insulation resistance, and the charge and discharge current, and then upload the converted voltage to the battery control unit 212.
The battery control unit 212 may be specifically configured to control the operation state of the battery by using the control state parameters, where the control state parameters include a battery remaining capacity, a battery health state, a battery remaining power, a battery remaining capacity, and the like.
The battery control unit 212 may be further configured to prompt a user of the electric vehicle in advance through the battery management interface when the remaining battery power is insufficient, and perform path planning according to the mileage input by the user through the battery management interface and the control state parameter. The battery control unit 212 may also be used to turn off some of the auxiliary devices in the electric vehicle to conserve power when the battery voltage is too low.
The battery control unit 212 includes: a communication circuit 2121, a relay control circuit 2122, a fault detection and safety protection circuit 2123, and a third control circuit 2124.
The communication circuit 2121 may be specifically configured to communicate with the battery detection unit 211 to obtain the operating state parameter, communicate with a charger to charge the battery, and communicate with the edge computing system 22 to upload the operating state parameter to the edge computing system 22 and receive the control state parameter.
The relay control circuit 2122 may be specifically configured to control a charging relay, a discharging relay, a heating relay, and a fan relay of the battery, so as to manage an energy state of the battery.
The fault detection and safety protection circuit 2123 may be specifically configured to, when it is determined that the battery has a fault according to the operating state parameter, output an alarm message and disconnect a corresponding relay under a high risk level condition, so as to ensure safety of the battery;
the third control circuit 2124 may be specifically configured to control operations performed by the communication circuit 2121, the relay control circuit 2122, and the fault detection and safety protection circuit 2123.
The edge computing system 22 includes: a physical layer 221 and an application layer 222. As shown in fig. 5, a schematic diagram of an edge computing system is provided.
The data cleaning module 2221, the model executing module 2222, and the wireless communication module 2223 are respectively disposed in the application layer.
The data cleaning module 221 may be specifically configured to clean the operating state parameters, and forward the cleaned operating state parameters to the model executing module 222 and the wireless communication module 223;
the data cleaning module 221 may be further configured to perform data cleaning processing such as deduplication, error correction, denoising, and the like on the battery data sent by the battery detection control system 21, and then forward the cleaned data to the wireless communication module 222 and the model execution module 223.
The model execution module 222 may be specifically configured to update the local battery management model with the updated model parameters.
The model executing module 222 may be further configured to execute a battery management model locally stored at the electric vehicle, that is, calculate a control state parameter of the battery according to the cleaned real-time running state parameter. The battery state parameters may specifically include: a battery remaining capacity (SOC), a battery State of Health (SOH), a battery remaining Power (SOP), a battery remaining capacity (SOE), and the like.
The wireless communication module 223 may be specifically configured to periodically receive the updated model parameters of the cloud computing system 23.
The wireless communication module 223 may be further configured to send the control state parameter to the battery detection control system 21 through the CAN after the model execution module 222 obtains the control state parameter through calculation.
The wireless communication module 223 can be specifically used for modulating the cleaned running state parameters, uploading the modulated running state parameters to the cloud computing system 23 through a wireless network, and regularly receiving the model parameters returned by the cloud computing system 23 through wifi, 4G transmission and other communication modes.
The physical layer 221 includes an embedded ARM CPU2211, an embedded GPU2212, and a wireless resolution module 2213.
The embedded ARM CPU2211 may be specifically configured to support the data cleaning module 2221 to perform data cleaning and receive and send data.
The embedded GPU2212 may be specifically configured to support the model execution module 2222 to perform calculation of control state parameters.
The wireless analysis module 2213 may be specifically configured to modulate and demodulate data received or transmitted by the wireless communication module 2223.
The embedded ARM CPU2211 has strong logic branch processing capability, and can be specifically used for controlling system execution, communication, human-computer interaction and the like. The system performs control, which may include controlling the operation flow of the entire edge computing system 22, such as data acquisition, cleaning, forwarding control, model operation control, and the like; the communication control may include acquiring data from the battery detection control system 21 and sending the processed data to the wireless analysis module 2213; the human-computer interaction control process may specifically include: a user at the electric automobile end can check battery operation parameter information and control parameter information through a battery management interface and send an instruction to control the battery management system through the battery management interface.
The embedded GPU2212 has strong parallel computing capability, and may be specifically configured to compute the control state parameters of the battery according to the operating state parameters and the local battery management model.
The cloud computing system 23 may include: data storage center 231 and model training center 232, as shown in FIG. 6, provide a schematic diagram of a cloud computing system.
The data storage center 231 may be configured to store the operating state parameters uploaded by the edge computing system 22.
The model training center 232 may be configured to update the training battery management model in real time according to the operating state parameters, and upload the obtained updated model parameters to the edge computing system 22.
The model training center 232 may be further configured to train a battery management model of the update cloud. For example, as shown in fig. 7, a deep learning calculation method is used to train and update the model, the deep learning network input layer is the cell voltage Vi, k of the battery, the total voltage Vtotal, k of the battery, the charge-discharge current Tk, and the cycle number Ncycle, the intermediate layer adopts a deep belief network DBN method (divided into an RBM layer and a BP layer) to the network, and the final output layer SOC and SOH result values are calculated according to the parameter information of each node returned by the cloud computing system. The Deep Belief Network (DBN) training mode adopts a multilayer Restricted Boltzmann Machine (RBM) and a layer of Back Propagation (BP), and two adjacent hidden layers form an RBM. The training process of the DBN is as follows: setting parameters such as the number of network layers, the number of hidden layer units and the like, and randomly initializing the whole DBN network parameter; training the RBM by using training sample data to a first RBM and adopting a continuous learning algorithm (CD algorithm) to store network parameters; training the next RBM by taking the hidden layer output of the next layer of RBM as input data until all RBMs are trained, and obtaining the whole DBN network parameters through unsupervised pre-training; and carrying out supervised training by using the BP network of the last layer, and reversely adjusting the RBMs of all layers to obtain the adjusted DBN network parameters. In the training process of the DBN, the core of RBM during the training realizes the initialization of DBN parameters through the layer-by-layer training of the RBM, the network parameters are not optimal parameters, but the network parameters usually fall near the optimal value, and the problems that the BP algorithm falls into a local optimal solution or the training time is too long due to the random initialization of the network parameters when a classifier is trained can be effectively avoided.
The model training center 232 may be configured to train and update various machine learning models stored in the cloud, such as data mining, deep learning, and neural networks, according to the operating state parameters stored in the data storage center 231, so as to obtain more accurate model parameters. The model parameters may be results obtained by the model training center 232 updating and training the battery management model in real time according to the operating state parameters, taking a deep learning manner as an example: the model parameters may be a w value (weight value) and a b value (offset value) of each node in the deep learning process, and are usually transmitted back to the edge computing system 22 in the form of a matrix, that is, the cloud computing system 23 sends the model parameters to the edge computing system 22, where the form of the model parameters includes a w matrix and a b matrix.
By the technical scheme, the electric automobile can still normally run under the condition of network failure. Meanwhile, the battery management model is trained and updated by using the computing power of the cloud and an advanced machine learning algorithm, so that the battery management model with high accuracy, small error and high stability is obtained, and the stability and the safety of the battery management system are improved
In the foregoing embodiments, the descriptions of the respective embodiments have respective emphasis, and for parts that are not described in detail in a certain embodiment, reference may be made to related descriptions of other embodiments.
It will be appreciated that the relevant features of the method and apparatus described above are referred to one another. In addition, "first", "second", and the like in the above embodiments are for distinguishing the embodiments, and do not represent merits of the embodiments.
It is clear to those skilled in the art that, for convenience and brevity of description, the specific working processes of the above-described systems, apparatuses and units may refer to the corresponding processes in the foregoing method embodiments, and are not described herein again.
The algorithms and displays presented herein are not inherently related to any particular computer, virtual machine, or other apparatus. Various general purpose systems may also be used with the teachings herein. The required structure for constructing such a system will be apparent from the description above. Moreover, the present invention is not directed to any particular programming language. It is appreciated that a variety of programming languages may be used to implement the teachings of the present invention as described herein, and any descriptions of specific languages are provided above to disclose the best mode of the invention.
In the description provided herein, numerous specific details are set forth. It is understood, however, that embodiments of the invention may be practiced without these specific details. In some instances, well-known methods, structures and techniques have not been shown in detail in order not to obscure an understanding of this description.
Similarly, it should be appreciated that in the foregoing description of exemplary embodiments of the invention, various features of the invention are sometimes grouped together in a single embodiment, figure, or description thereof for the purpose of streamlining the disclosure and aiding in the understanding of one or more of the various inventive aspects. However, the disclosed method should not be interpreted as reflecting an intention that: that the invention as claimed requires more features than are expressly recited in each claim. Rather, as the following claims reflect, inventive aspects lie in less than all features of a single foregoing disclosed embodiment. Thus, the claims following the detailed description are hereby expressly incorporated into this detailed description, with each claim standing on its own as a separate embodiment of this invention.
Those skilled in the art will appreciate that the modules in the device in an embodiment may be adaptively changed and disposed in one or more devices different from the embodiment. The modules or units or components of the embodiments may be combined into one module or unit or component, and furthermore they may be divided into a plurality of sub-modules or sub-units or sub-components. All of the features disclosed in this specification (including any accompanying claims, abstract and drawings), and all of the processes or elements of any method or apparatus so disclosed, may be combined in any combination, except combinations where at least some of such features and/or processes or elements are mutually exclusive. Each feature disclosed in this specification (including any accompanying claims, abstract and drawings) may be replaced by alternative features serving the same, equivalent or similar purpose, unless expressly stated otherwise.
Furthermore, those skilled in the art will appreciate that while some embodiments described herein include some features included in other embodiments, rather than other features, combinations of features of different embodiments are meant to be within the scope of the invention and form different embodiments. For example, in the following claims, any of the claimed embodiments may be used in any combination.
The various component embodiments of the invention may be implemented in hardware, or in software modules running on one or more processors, or in a combination thereof. Those skilled in the art will appreciate that a microprocessor or Digital Signal Processor (DSP) may be used in practice to implement some or all of the functionality of some or all of the components in accordance with embodiments of the present invention. The present invention may also be embodied as apparatus or device programs (e.g., computer programs and computer program products) for performing a portion or all of the methods described herein. Such programs implementing the present invention may be stored on computer-readable media or may be in the form of one or more signals. Such a signal may be downloaded from an internet website or provided on a carrier signal or in any other form.
It should be noted that the above-mentioned embodiments illustrate rather than limit the invention, and that those skilled in the art will be able to design alternative embodiments without departing from the scope of the appended claims. In the claims, any reference signs placed between parentheses shall not be construed as limiting the claim. The word "comprising" does not exclude the presence of elements or steps not listed in a claim. The word "a" or "an" preceding an element does not exclude the presence of a plurality of such elements. The invention may be implemented by means of hardware comprising several distinct elements, and by means of a suitably programmed computer. In the unit claims enumerating several means, several of these means may be embodied by one and the same item of hardware. The usage of the words first, second and third, etcetera do not indicate any ordering. These words may be interpreted as names.

Claims (8)

1. A battery management system for an electric vehicle combining cloud computing and edge computing, comprising: a battery detection control system arranged at the electric automobile end, an edge computing system and a cloud computing system arranged at the cloud end,
the battery detection control system is used for detecting the running state parameters of the battery and uploading the running state parameters to the edge computing system;
the edge computing system is used for cleaning the running state parameters and uploading the cleaned running state parameters to the cloud computing system;
the cloud computing system is used for training a battery management model at the cloud end according to the cleaned running state parameters, obtaining updated model parameters and transmitting the updated model parameters back to the edge computing system;
the edge computing system is further configured to update a local battery management model by using the updated model parameters, calculate control state parameters of the battery according to the cleaned operation state parameters and the updated local battery management model, and transmit the control state parameters back to the battery detection control system to control the operation state of the battery.
2. The battery management system for an electric vehicle of claim 1, wherein the edge computing system comprises: a data cleaning module, a model execution module and a wireless communication module,
the data cleaning module is used for cleaning the running state parameters and forwarding the cleaned running state parameters to the model execution module and the wireless communication module;
the model execution module is used for calculating the control state parameters of the battery according to the cleaned running state parameters and the updated local battery management model and transmitting the control state parameters back to the battery detection control system;
the wireless communication module is used for modulating the cleaned running state parameters, uploading the modulated running state parameters to the cloud computing system through a wireless network, and periodically receiving the model parameters returned by the cloud computing system.
3. The battery management system for an electric vehicle of claim 2, wherein the edge computing system comprises: a physical layer and an application layer, and,
the data cleaning module, the model execution module and the wireless communication module are respectively arranged on the application layer;
the physical layer comprises an embedded ARM CPU, an embedded GPU and a wireless analysis module, the embedded ARM CPU is used for supporting the data cleaning module to perform data cleaning and data uploading, the embedded GPU is used for supporting the model execution module to perform control state parameter calculation, and the wireless analysis module is used for modulating and demodulating data received or sent by the wireless communication module.
4. The battery management system for an electric vehicle according to claim 1, wherein the battery detection control system includes: a battery detection unit and a battery control unit,
the battery detection unit is used for detecting the running state parameters of the battery, wherein the running state parameters comprise the voltage of a single battery, the total voltage of the battery, the charging and discharging current of the battery, the temperature of the battery and the insulation resistance of the battery;
the battery control unit is used for controlling the running state of the battery by using the control state parameters, and the control state parameters comprise the remaining capacity of the battery, the health state of the battery, the remaining power of the battery and the remaining capacity of the battery.
5. The battery management system for an electric vehicle according to claim 4, wherein the battery detection unit includes: a battery measuring unit and a high voltage unit,
the battery measuring unit comprises a battery monomer voltage detection circuit and a battery temperature detection circuit;
the high-voltage unit comprises a total voltage detection circuit, an insulation resistance measurement circuit and a charging and discharging current detection circuit.
6. The battery management system for an electric vehicle according to claim 5,
the battery measuring unit also comprises a battery equalizing circuit and a first control circuit, wherein the first control circuit is used for converting the battery monomer voltage detected by the battery monomer voltage detection circuit and the battery temperature detected by the battery temperature detection circuit and then uploading the converted battery monomer voltage and the battery temperature to the battery control unit;
the battery equalization circuit is used for performing equalization discharge on the battery after receiving an equalization command returned by the battery control unit;
the high voltage unit further comprises a second control circuit, and the second control circuit is used for uploading the total voltage of the battery detected by the total voltage detection circuit, the insulation resistance detected by the insulation resistance measurement circuit and the charge and discharge current detected by the charge and discharge current detection circuit to the battery control unit after conversion processing.
7. The battery management system for an electric vehicle according to claim 4, wherein the battery control unit includes:
the communication circuit is used for communicating with the battery detection unit to acquire the running state parameters, establishing communication with a charger to charge the battery, and communicating with the edge computing system to upload the running state parameters to the edge computing system and receive the control state parameters;
the relay control circuit is used for controlling a charging relay, a discharging relay, a heating relay and a fan relay of the battery so as to manage the energy state of the battery;
the fault detection and safety protection circuit is used for outputting alarm information and disconnecting a corresponding relay under the condition of high danger level when the battery is determined to be in fault according to the running state parameters so as to ensure the safety of the battery;
and the third control circuit is used for controlling the work executed by the communication circuit, the relay control circuit and the fault detection and safety protection circuit.
8. The battery management system for an electric vehicle according to claim 1, wherein the cloud computing system includes:
the data storage center is used for storing the running state parameters uploaded by the edge computing system;
and the model training center is used for updating and training the battery management model in real time according to the running state parameters and uploading the obtained updated model parameters to the edge computing system.
CN201910530965.4A 2019-06-19 2019-06-19 Battery management system for electric automobile combining cloud computing and edge computing Active - Reinstated CN110386027B (en)

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 CN110386027A (en) 2019-10-29
CN110386027B true 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)

Families Citing this family (13)

* Cited by examiner, † Cited by third party
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
CN110719210B (en) * 2019-12-05 2020-08-28 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
CN112306689B (en) * 2020-11-02 2021-05-11 时代云英(深圳)科技有限公司 Edge calculation system and method
CN112881930B (en) * 2021-01-19 2023-07-18 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
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

Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
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

Family Cites Families (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
EP2736759B1 (en) * 2011-07-26 2018-09-05 Gogoro Inc. Apparatus, method and article for providing vehicle diagnostic data
US9713963B2 (en) * 2013-02-18 2017-07-25 Ford Global Technologies, Llc Method and apparatus for route completion likelihood display

Patent Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
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

Also Published As

Publication number Publication date
CN110386027A (en) 2019-10-29

Similar Documents

Publication Publication Date Title
CN110386027B (en) Battery management system for electric automobile combining cloud computing and edge computing
CN110370983B (en) Battery management system for electric automobile based on 5G mobile communication
US20220111758A1 (en) Supplying power to an electric vehicle
JP6757602B2 (en) Battery state estimation device and method
US20220065940A1 (en) Battery failure prediction
CN108923082B (en) Distributed battery management system and battery pack
KR20190070837A (en) Battery state of charge prediction mehod and system
CN103091633A (en) Estimating device and method of lead-acid storage battery level
US20210053459A1 (en) Electric power system and vehicle
CN113696786B (en) Battery equalization method and system
CN110712528B (en) Real-time monitoring method and device for power battery pack
JP7366975B2 (en) Battery deterioration estimation device, battery deterioration estimation system, battery deterioration estimation method, and program
CN103986205B (en) 16 series lithium battery group multi-mode balance control methods of dynamic adaptation
CN110554329A (en) battery internal resistance measuring method and device
WO2016200319A1 (en) A method and a monitoring unit for monitoring a battery system
CN116500458B (en) Power battery capacity evaluation method and device, vehicle and electronic device
CN107181288A (en) Electric automobile and its charge control method and battery management system
CN111487545A (en) Secondary battery state detection system, detection device and detection method
CN207366715U (en) A kind of battery SOC estimation device based on CAN bus
CN114597990A (en) Battery system control method, device, electronic equipment and storage medium
EP3217510B1 (en) Dc power control device, dc power control method, and dc power control system
US20230266399A1 (en) Battery management system, calculation system, battery degradation prediction method, and battery degradation prediction program
CN110646740A (en) Monitoring method and monitoring device for battery pack
US11518269B2 (en) Management apparatus, management method, and program
JP7044085B2 (en) Monitoring 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
CF01 Termination of patent right due to non-payment of annual fee

Granted publication date: 20210302

Termination date: 20210619

RR01 Reinstatement of patent right
RR01 Reinstatement of patent right

Former decision: Termination of patent right without annual fee

Former decision publication date: 20220603