CN113890162A - Charging and discharging method of high-current discharging device - Google Patents

Charging and discharging method of high-current discharging device Download PDF

Info

Publication number
CN113890162A
CN113890162A CN202111164624.3A CN202111164624A CN113890162A CN 113890162 A CN113890162 A CN 113890162A CN 202111164624 A CN202111164624 A CN 202111164624A CN 113890162 A CN113890162 A CN 113890162A
Authority
CN
China
Prior art keywords
lithium battery
charging
battery pack
super capacitor
temperature
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
Application number
CN202111164624.3A
Other languages
Chinese (zh)
Other versions
CN113890162B (en
Inventor
刘伟政
罗世明
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.)
Aerospace Baykee Guangdong Technology Co ltd
Original Assignee
Aerospace Baykee Guangdong Technology Co ltd
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 Aerospace Baykee Guangdong Technology Co ltd filed Critical Aerospace Baykee Guangdong Technology Co ltd
Priority to CN202111164624.3A priority Critical patent/CN113890162B/en
Publication of CN113890162A publication Critical patent/CN113890162A/en
Application granted granted Critical
Publication of CN113890162B publication Critical patent/CN113890162B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Images

Classifications

    • H—ELECTRICITY
    • H02—GENERATION; CONVERSION OR DISTRIBUTION OF ELECTRIC POWER
    • H02J—CIRCUIT ARRANGEMENTS OR SYSTEMS FOR SUPPLYING OR DISTRIBUTING ELECTRIC POWER; SYSTEMS FOR STORING ELECTRIC ENERGY
    • H02J7/00—Circuit arrangements for charging or depolarising batteries or for supplying loads from batteries
    • H02J7/34—Parallel operation in networks using both storage and other dc sources, e.g. providing buffering
    • H02J7/345—Parallel operation in networks using both storage and other dc sources, e.g. providing buffering using capacitors as storage or buffering devices
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00—Computing arrangements based on biological models
    • G06N3/02—Neural networks
    • G06N3/04—Architecture, e.g. interconnection topology
    • G06N3/045—Combinations of networks
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00—Computing arrangements based on biological models
    • G06N3/02—Neural networks
    • G06N3/08—Learning methods
    • H—ELECTRICITY
    • H02—GENERATION; CONVERSION OR DISTRIBUTION OF ELECTRIC POWER
    • H02J—CIRCUIT ARRANGEMENTS OR SYSTEMS FOR SUPPLYING OR DISTRIBUTING ELECTRIC POWER; SYSTEMS FOR STORING ELECTRIC ENERGY
    • H02J7/00—Circuit arrangements for charging or depolarising batteries or for supplying loads from batteries
    • H02J7/0068—Battery or charger load switching, e.g. concurrent charging and load supply
    • H—ELECTRICITY
    • H02—GENERATION; CONVERSION OR DISTRIBUTION OF ELECTRIC POWER
    • H02J—CIRCUIT ARRANGEMENTS OR SYSTEMS FOR SUPPLYING OR DISTRIBUTING ELECTRIC POWER; SYSTEMS FOR STORING ELECTRIC ENERGY
    • H02J7/00—Circuit arrangements for charging or depolarising batteries or for supplying loads from batteries
    • H02J7/007—Regulation of charging or discharging current or voltage
    • H02J7/0071—Regulation of charging or discharging current or voltage with a programmable schedule
    • H—ELECTRICITY
    • H02—GENERATION; CONVERSION OR DISTRIBUTION OF ELECTRIC POWER
    • H02J—CIRCUIT ARRANGEMENTS OR SYSTEMS FOR SUPPLYING OR DISTRIBUTING ELECTRIC POWER; SYSTEMS FOR STORING ELECTRIC ENERGY
    • H02J7/00—Circuit arrangements for charging or depolarising batteries or for supplying loads from batteries
    • H02J7/007—Regulation of charging or discharging current or voltage
    • H02J7/007188—Regulation of charging or discharging current or voltage the charge cycle being controlled or terminated in response to non-electric parameters
    • H02J7/007192—Regulation of charging or discharging current or voltage the charge cycle being controlled or terminated in response to non-electric parameters in response to temperature
    • H—ELECTRICITY
    • H02—GENERATION; CONVERSION OR DISTRIBUTION OF ELECTRIC POWER
    • H02J—CIRCUIT ARRANGEMENTS OR SYSTEMS FOR SUPPLYING OR DISTRIBUTING ELECTRIC POWER; SYSTEMS FOR STORING ELECTRIC ENERGY
    • H02J7/00—Circuit arrangements for charging or depolarising batteries or for supplying loads from batteries
    • H02J7/007—Regulation of charging or discharging current or voltage
    • H02J7/007188—Regulation of charging or discharging current or voltage the charge cycle being controlled or terminated in response to non-electric parameters
    • H02J7/007192—Regulation of charging or discharging current or voltage the charge cycle being controlled or terminated in response to non-electric parameters in response to temperature
    • H02J7/007194—Regulation of charging or discharging current or voltage the charge cycle being controlled or terminated in response to non-electric parameters in response to temperature of the battery

Landscapes

  • Engineering & Computer Science (AREA)
  • Power Engineering (AREA)
  • Physics & Mathematics (AREA)
  • Theoretical Computer Science (AREA)
  • General Health & Medical Sciences (AREA)
  • General Engineering & Computer Science (AREA)
  • Biophysics (AREA)
  • Computational Linguistics (AREA)
  • Data Mining & Analysis (AREA)
  • Evolutionary Computation (AREA)
  • Artificial Intelligence (AREA)
  • Molecular Biology (AREA)
  • Computing Systems (AREA)
  • Biomedical Technology (AREA)
  • General Physics & Mathematics (AREA)
  • Mathematical Physics (AREA)
  • Software Systems (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Health & Medical Sciences (AREA)
  • Charge And Discharge Circuits For Batteries Or The Like (AREA)
  • Secondary Cells (AREA)

Abstract

The disclosure relates to the technical field of charge and discharge control, in particular to a charge and discharge method of a high-current discharge device. A method for charging and discharging a high current discharge device, comprising: acquiring the ambient temperature and the temperature of a lithium battery pack; determining the charging current of the lithium battery pack and the charging voltage of the lithium battery pack according to the ambient temperature and the temperature of the lithium battery pack, and controlling a charger to charge the lithium battery pack according to the charging current and the charging voltage; acquiring the temperature of the super capacitor bank; and determining the charging voltage of the super capacitor bank according to the ambient temperature, the temperature of the lithium battery bank and the temperature of the super capacitor bank, and controlling the lithium battery bank to charge the super capacitor bank according to the charging voltage of the super capacitor bank. The charging speed of the lithium battery pack and the super capacitor pack can be increased on the premise of ensuring safety, and the average available time of the large-current discharging device is prolonged.

Description

Charging and discharging method of high-current discharging device
Technical Field
The disclosure relates to the technical field of charge and discharge control, in particular to a charge and discharge method of a high-current discharge device.
Background
The large current discharge device is a device for supplying a pulsed large current to a load in a low temperature environment, in which a lithium battery and a super capacitor are used. Because the lithium battery and the super capacitor used in the method are unstable electric devices. Especially, when a lithium battery is charged with a large current, if the current for charging the lithium battery is not reasonably regulated, the lithium battery can be burnt and even explode.
For the super capacitor, the improper charging current and charging voltage input to the super capacitor can cause the power consumption of the super capacitor to be abnormally increased and exceed the dissipation power which the super capacitor can bear, and further the internal expansion speed of the capacitor is too high, so that the shell of the super capacitor is instantaneously broken, and the super capacitor is exploded.
Disclosure of Invention
In order to solve the above technical problem or at least partially solve the above technical problem, the present disclosure provides a charging and discharging method of a large current discharging device, which can safely increase an average usable time period of the large current discharging device.
The present disclosure provides a charging and discharging method of a large current discharging device, including:
acquiring the ambient temperature and the temperature of a lithium battery pack;
determining the charging current of the lithium battery pack and the charging voltage of the lithium battery pack according to the ambient temperature and the temperature of the lithium battery pack, and controlling a charger to charge the lithium battery pack according to the charging current and the charging voltage;
acquiring the temperature of the super capacitor bank;
and determining the charging voltage of the super capacitor bank according to the ambient temperature, the temperature of the lithium battery bank and the temperature of the super capacitor bank, and controlling the lithium battery bank to charge the super capacitor bank according to the charging voltage of the super capacitor bank.
Optionally, the charging current of the lithium battery pack and the charging voltage of the lithium battery pack are determined according to a lithium battery pack charging prediction model,
the lithium battery pack charging prediction model is obtained by training according to the following steps:
combining the ambient temperature, the temperature of the lithium battery pack, the charging current of the lithium battery pack corresponding to the temperature and the charging voltage of the lithium battery pack into a group of lithium battery pack charging data set tuples, and collecting a plurality of groups of the data set tuples to form a lithium battery pack charging data set;
dividing the collected lithium battery pack charging data set into a training set and a testing set according to a first preset proportion;
establishing a first fully-connected neural network;
training the first fully-connected neural network in a machine learning frame by using a training set to obtain a trained first fully-connected neural network;
and testing the trained first fully-connected neural network by using a test set, and outputting the trained first fully-connected neural network as a lithium battery pack charging prediction model after the accuracy of the trained first fully-connected neural network reaches a first accuracy preset value.
Optionally, the first preset ratio is 8:2 or 9: 1.
Optionally, the first accuracy preset value is 95%.
Optionally, the first fully-connected neural network includes a 1-layer input layer, a 6-layer hidden layer, and a 1-layer output layer.
Optionally, the charging voltage of the super capacitor bank is determined according to the super capacitor bank charging prediction model,
the charging prediction model of the super capacitor bank is obtained by training according to the following steps:
combining the ambient temperature, the temperature of the lithium battery pack, the temperature of the super capacitor pack and the charging voltage of the super capacitor pack corresponding to the temperature into a super capacitor pack data set tuple, and collecting a plurality of data set tuples to form a super capacitor pack charging data set;
dividing the collected data set into a training set and a testing set according to a second preset proportion;
establishing a second fully-connected neural network;
training the second fully-connected neural network in a machine learning frame by using the training set to obtain a trained second fully-connected neural network;
and testing the trained second fully-connected neural network by using the test set, and outputting the trained second fully-connected neural network as a charging prediction model of the super capacitor bank when the accuracy of the trained second fully-connected neural network reaches a second accuracy preset value.
Optionally, the second preset ratio is 8:2 or 9: 1.
Optionally, the second accuracy preset value is 95%.
Optionally, the second fully-connected neural network includes a 1-layer input layer, a 6-layer hidden layer, and a 1-layer output layer.
Optionally, the machine learning framework is TensorFlow, Keras, or Caffe.
Compared with the prior art, the technical scheme provided by the embodiment of the disclosure has the following advantages:
the basic structure of the large-current discharge device is generally formed by connecting a lithium battery pack and a super capacitor pack in parallel, and the super capacitor can still normally output large current in an ultralow-temperature environment, but the large-current discharge device does not have good energy storage performance. The lithium battery pack has a good energy storage effect, but is difficult to output large current in a low-temperature environment. The super capacitor bank is charged through the lithium battery bank, and then the super capacitor bank is used for outputting to the outside, so that the effect of providing pulse heavy current for the load can be achieved.
In order to pursue the average usable time of the whole high-current discharging device, the charging speed of the lithium battery pack can be increased, and the charging speed of the super capacitor pack can be increased. But both of them are unstable electric devices, so it is necessary to solve the problem of outputting as large current and voltage as possible to charge the lithium battery pack and the super capacitor pack under the condition of ensuring safety.
Compared with the prior art, the charging current and the charging voltage of the lithium battery pack are determined according to the ambient temperature and the temperature of the lithium battery pack. The two parameters of the environment temperature and the temperature of the lithium battery pack are selected, firstly, the difference value of the environment temperature and the temperature of the lithium battery pack determines the heat dissipation speed of the lithium battery pack, and the temperature of the lithium battery pack represents whether the lithium battery pack is in a safe state or not.
Secondly, in order to make the charging speed of the super capacitor bank faster, the charging voltage of the super capacitor bank is determined according to the environment temperature, the temperature of the lithium battery bank and the temperature of the super capacitor bank under the condition of ensuring the safety of the super capacitor, and the charging voltage is not limited to the charging voltage of the super capacitor bank calibrated when the super capacitor bank leaves a factory. For example, in a low-temperature environment, the charging voltage for the super capacitor bank can be greater than the calibrated charging voltage, so that the increase of the internal resistance of the super capacitor at a low temperature can be counteracted, the super capacitor bank can be charged more quickly, and the average available time of a large-current discharging device is increased.
Drawings
The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the present disclosure and together with the description, serve to explain the principles of the disclosure.
In order to more clearly illustrate the embodiments or technical solutions in the prior art of the present disclosure, the drawings used in the description of the embodiments or prior art will be briefly described below, and it is obvious for those skilled in the art that other drawings can be obtained according to the drawings without inventive exercise.
Fig. 1 is a flowchart illustrating a charging and discharging method of a high current discharging device according to an embodiment of the disclosure;
fig. 2 is a schematic structural diagram of a high-current discharging device according to an embodiment of the disclosure.
Wherein, 1, a charger; 2. a lithium battery pack; 3. a voltage transformation device; 4. a super capacitor bank; 5. a control system; 6. an ambient temperature sensor.
Detailed Description
In order that the above objects, features and advantages of the present disclosure may be more clearly understood, aspects of the present disclosure will be further described below. It should be noted that the embodiments and features of the embodiments of the present disclosure may be combined with each other without conflict.
In the following description, numerous specific details are set forth in order to provide a thorough understanding of the present disclosure, but the present disclosure may be practiced in other ways than those described herein; it is to be understood that the embodiments disclosed in the specification are only a few embodiments of the present disclosure, and not all embodiments.
Fig. 1 is a flowchart of a charging and discharging method of a high-current discharging device according to an embodiment of the present disclosure, and fig. 2 is a schematic structural diagram of a high-current discharging device according to an embodiment of the present disclosure. As shown in fig. 2, a large current discharge device includes a charger 1, a lithium battery pack 2, a transformer 3, a super capacitor pack 4, a control system 5, and an ambient temperature sensor 6, wherein the charger 1 stores electric energy such as commercial power into the lithium battery pack 2, and the lithium battery pack 2 changes a charging voltage for charging the super capacitor pack 4 through the transformer 3. The ambient temperature sensor 6 detects the ambient temperature. The control system 5 stores a charging and discharging method of a high-current discharging device, and is used for determining the charging current of the lithium battery pack 2 and the charging voltage of the lithium battery pack 2 when electric energy such as commercial power is stored in the lithium battery pack 2, and determining the charging voltage of the super capacitor pack 4 which should be charged by the voltage changing device 3 when the lithium battery pack 2 supplies energy to the super capacitor. The control system 5 continuously obtains the ambient temperature, the temperature of the lithium battery pack 2 and the temperature of the super capacitor pack 4 from the lithium battery pack 2, the super capacitor pack 4 and the ambient temperature sensor 6, and continuously adjusts the charging current of the lithium battery pack 2, the charging voltage of the lithium battery pack 2 and the charging voltage for charging the super capacitor pack 4 according to a charging and discharging method of a large-current discharging device.
As shown in fig. 1, a method for charging and discharging a high current discharge device includes:
acquiring the ambient temperature and the temperature of the lithium battery pack 2;
determining the charging current of the lithium battery pack 2 and the charging voltage of the lithium battery pack 2 according to the ambient temperature and the temperature of the lithium battery pack 2, and controlling the charger 1 to charge the lithium battery pack 2 according to the charging current and the charging voltage;
acquiring the temperature of the super capacitor bank 4;
and determining the charging voltage of the super capacitor group 4 according to the ambient temperature, the temperature of the lithium battery pack 2 and the temperature of the super capacitor group 4, and controlling the lithium battery pack 2 to charge the super capacitor group 4 according to the charging voltage of the super capacitor group 4.
Compared with the prior art, the charging current and the charging voltage of the lithium battery pack 2 are determined according to the ambient temperature and the temperature of the lithium battery pack 2. Two parameters of the environment temperature and the temperature of the lithium battery pack 2 are selected, firstly, the difference value of the environment temperature and the temperature of the lithium battery is considered to determine the heat dissipation speed of the lithium battery pack 2, and the temperature of the lithium battery pack 2 represents whether the lithium battery pack 2 is in a safe state or not.
Secondly, in order to make the charging speed of the super capacitor bank 4 faster, the charging voltage of the super capacitor bank 4 is determined according to the environment temperature, the temperature of the lithium battery bank 2 and the temperature of the super capacitor bank 4 under the condition of ensuring the safety of the super capacitor, and the charging voltage is not limited to the charging voltage of the super capacitor bank 4 calibrated when the super capacitor is delivered from a factory. For example, in a low-temperature environment, the charging voltage for the super capacitor bank 4 may be greater than the calibrated charging voltage, so that the increase of the internal resistance of the super capacitor at a low temperature can be offset, the super capacitor bank 4 can be charged more quickly, and the average usable time of the large-current discharging device is increased.
Specifically, the current ambient temperature and the temperature of the lithium battery pack 2 are obtained through the ambient temperature sensor 6 and a temperature sensor built in the lithium battery pack 2.
Inputting the ambient temperature and the temperature of the lithium battery pack 2 into a lithium battery pack charging prediction model to determine the charging current of the lithium battery pack 2 and the charging voltage of the lithium battery pack 2, and controlling the charger 1 to charge the lithium battery pack 2 according to the charging current and the charging voltage;
acquiring the temperature of the super capacitor bank 4 through a temperature sensor arranged in the super capacitor bank 4;
inputting the ambient temperature, the temperature of the lithium battery pack 2 and the temperature of the super capacitor pack 4 into the super capacitor pack charging prediction model to determine the charging voltage of the super capacitor pack 4, and controlling the voltage transformation device 3 to change the output voltage of the lithium battery pack 2, so that the lithium battery pack 2 charges the super capacitor pack 4 according to the charging voltage of the super capacitor pack 4.
The lithium battery pack 2 charging prediction model is obtained by training by an engineer according to the following steps:
combining the ambient temperature, the temperature of the lithium battery pack 2, the maximum charging current of the lithium battery pack 2 corresponding to the temperature under the condition of ensuring safety and the charging voltage of the lithium battery pack 2 into a group of lithium battery pack charging data set tuples, and collecting 10000 groups of the data set tuples to form a lithium battery pack charging data set;
dividing the collected lithium battery pack charging data set into a first training set and a first testing set according to a first preset proportion; in this embodiment, the first preset ratio is 8:2, and in other embodiments, the first preset ratio may also be 9: 1.
A TensorFlow machine learning framework is used for building a first fully-connected neural network with 1 input layer, 6 hidden layers and 1 output layer; in other embodiments, the first fully-connected neural network may also be replaced by an artificial intelligence algorithm model such as a convolutional neural network, and the machine learning framework may also be implemented by a machine learning Keras or Caffe machine learning framework.
Training a first fully-connected neural network in a TensorFlow machine learning framework by using a first training set to obtain a trained first fully-connected neural network;
and testing the trained first fully-connected neural network by using a first test set, and outputting the trained first fully-connected neural network as a lithium battery pack charging prediction model when the accuracy of the trained first fully-connected neural network reaches a first accuracy preset value of 95%. Otherwise, the engineer continues to supplement the data set, and then repeats the training steps until the accuracy of the first fully-connected neural network trained by the first test set test reaches a first accuracy preset value of 95%.
The charging prediction model of the super capacitor bank is obtained by training according to the following steps:
combining the ambient temperature, the temperature of the lithium battery pack 2, the temperature of the super capacitor bank 4 and the charging voltage of the super capacitor bank 4 corresponding to the ambient temperature and the charging voltage of the super capacitor bank 4 which are the maximum under the condition of ensuring safety into a super capacitor bank 4 data set tuple, and collecting 10000 data set tuples to form a super capacitor bank 4 charging data set;
dividing the collected data set into a second training set and a second testing set according to a second preset proportion; in this embodiment, the second predetermined ratio is 8:2, and in other embodiments, the second predetermined ratio may also be 9: 1.
A TensorFlow machine learning framework is used for building a second fully-connected neural network with 1 input layer, 6 hidden layers and 1 output layer; in other embodiments, the fully-connected neural network may also be replaced by an artificial intelligence algorithm model such as a convolutional neural network, and the machine learning framework may also be implemented by a machine learning Keras or Caffe machine learning framework.
Training the second fully-connected neural network in a TensorFlow machine learning framework by using a second training set to obtain a trained second fully-connected neural network;
and testing the trained second fully-connected neural network by using a second test set, and outputting the trained second fully-connected neural network as a super capacitor bank charging prediction model when the accuracy of the trained second fully-connected neural network reaches a preset value of 95% of the first accuracy. Otherwise, the engineer continues to supplement the data set, and then repeats the training steps until the accuracy of the second fully-connected neural network trained by the second test set test reaches the preset value of the first accuracy of 95%.
Specifically, in other embodiments, the engineer may also create a lithium battery pack charging parameter table corresponding to the ambient temperature, the temperature of the lithium battery pack 2, the charging current of the lithium battery pack 2 and the charging voltage of the lithium battery pack 2, which are maximum under the condition that the safety is ensured, and a super capacitor pack 4 charging parameter table corresponding to the ambient temperature, the temperature of the lithium battery pack 2, the temperature of the super capacitor pack 4 and the charging voltage of the super capacitor pack 4, which is maximum under the condition that the safety is ensured, by collecting a large amount of data. The control system 5 obtains the ambient temperature, the temperature of the lithium battery pack 2 and the temperature of the super capacitor pack 4 from the lithium battery pack 2, the super capacitor pack 4 and the ambient temperature sensor 6, and continuously adjusts the charging current of the lithium battery pack 2, the charging voltage of the lithium battery pack 2 and the charging voltage for the super capacitor pack 4 according to the lithium battery pack charging parameter table and the super capacitor pack charging parameter table.
It is noted that, in this document, relational terms such as "first" and "second," and the like, may be used solely to distinguish one entity or action from another entity or action without necessarily requiring or implying any actual such relationship or order between such entities or actions. Also, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising an … …" does not exclude the presence of other identical elements in a process, method, article, or apparatus that comprises the element.
The foregoing are merely exemplary embodiments of the present disclosure, which enable those skilled in the art to understand or practice the present disclosure. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the generic principles defined herein may be applied to other embodiments without departing from the spirit or scope of the disclosure. Thus, the present disclosure is not intended to be limited to the embodiments shown herein but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.

Claims (10)

1. A method for charging and discharging a high current discharge device, comprising:
acquiring the ambient temperature and the temperature of a lithium battery pack;
determining the charging current of the lithium battery pack and the charging voltage of the lithium battery pack according to the ambient temperature and the temperature of the lithium battery pack, and controlling a charger to charge the lithium battery pack according to the charging current and the charging voltage;
acquiring the temperature of the super capacitor bank;
and determining the charging voltage of the super capacitor bank according to the ambient temperature, the temperature of the lithium battery bank and the temperature of the super capacitor bank, and controlling the lithium battery bank to charge the super capacitor bank according to the charging voltage of the super capacitor bank.
2. The method of claim 1, wherein the charging current of the lithium battery pack and the charging voltage of the lithium battery pack are determined according to a lithium battery pack charging prediction model,
the lithium battery pack charging prediction model is obtained by training according to the following steps:
combining the ambient temperature, the temperature of the lithium battery pack, the charging current of the lithium battery pack corresponding to the temperature and the charging voltage of the lithium battery pack into a group of lithium battery pack charging data set tuples, and collecting a plurality of groups of the data set tuples to form a lithium battery pack charging data set;
dividing the collected lithium battery pack charging data set into a training set and a testing set according to a first preset proportion;
establishing a first fully-connected neural network;
training the first fully-connected neural network in a machine learning frame by using a training set to obtain a trained first fully-connected neural network;
and testing the trained first fully-connected neural network by using a test set, and outputting the trained first fully-connected neural network as a lithium battery pack charging prediction model after the accuracy of the trained first fully-connected neural network reaches a first accuracy preset value.
3. A method for charging and discharging a high current discharge device according to claim 2, wherein said first predetermined ratio is 8:2 or 9: 1.
4. A method for charging and discharging a high current discharge device according to claim 2, wherein said first predetermined accuracy value is 95%.
5. The method of claim 2, wherein the first fully-connected neural network comprises 1 input layer, 6 hidden layers and 1 output layer.
6. A charging and discharging method of a large current discharging device according to claim 1, wherein the charging voltage of the super capacitor bank is determined according to a super capacitor bank charging prediction model,
the charging prediction model of the super capacitor bank is obtained by training according to the following steps:
combining the ambient temperature, the temperature of the lithium battery pack, the temperature of the super capacitor pack and the charging voltage of the super capacitor pack corresponding to the temperature into a super capacitor pack data set tuple, and collecting a plurality of data set tuples to form a super capacitor pack charging data set;
dividing the collected data set into a training set and a testing set according to a second preset proportion;
establishing a second fully-connected neural network;
training the second fully-connected neural network in a machine learning frame by using the training set to obtain a trained second fully-connected neural network;
and testing the trained second fully-connected neural network by using the test set, and outputting the trained second fully-connected neural network as a charging prediction model of the super capacitor bank when the accuracy of the trained second fully-connected neural network reaches a second accuracy preset value.
7. A method for charging and discharging a high current discharge device according to claim 6, wherein said second predetermined ratio is 8:2 or 9: 1.
8. A method for charging and discharging a high current discharge device according to claim 6, wherein said second predetermined accuracy value is 95%.
9. The method of claim 6, wherein the second fully-connected neural network comprises 1 input layer, 6 hidden layers and 1 output layer.
10. A method of charging and discharging a high current discharge device according to any one of claims 2 to 9, wherein said machine learning framework is TensorFlow, Keras or Caffe.
CN202111164624.3A 2021-09-30 2021-09-30 Charging and discharging method of high-current discharging device Active CN113890162B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202111164624.3A CN113890162B (en) 2021-09-30 2021-09-30 Charging and discharging method of high-current discharging device

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202111164624.3A CN113890162B (en) 2021-09-30 2021-09-30 Charging and discharging method of high-current discharging device

Publications (2)

Publication Number Publication Date
CN113890162A true CN113890162A (en) 2022-01-04
CN113890162B CN113890162B (en) 2023-08-22

Family

ID=79005006

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202111164624.3A Active CN113890162B (en) 2021-09-30 2021-09-30 Charging and discharging method of high-current discharging device

Country Status (1)

Country Link
CN (1) CN113890162B (en)

Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN205646918U (en) * 2016-05-12 2016-10-12 广州泓淮能源科技有限公司 Wind -powered electricity generation becomes oar control system battery life extended protection device
KR101701425B1 (en) * 2015-07-31 2017-02-02 (주) 큐알온텍 Apparatus for controlling auxiliary battery using black box
KR20180104873A (en) * 2017-03-14 2018-09-27 주식회사 베가에너지 Lithium battery protection system
CN110716148A (en) * 2019-10-18 2020-01-21 兰州交通大学 Real-time safety monitoring system for composite power energy storage
CN112886692A (en) * 2021-02-02 2021-06-01 黄国平 Power supply system

Patent Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
KR101701425B1 (en) * 2015-07-31 2017-02-02 (주) 큐알온텍 Apparatus for controlling auxiliary battery using black box
CN205646918U (en) * 2016-05-12 2016-10-12 广州泓淮能源科技有限公司 Wind -powered electricity generation becomes oar control system battery life extended protection device
KR20180104873A (en) * 2017-03-14 2018-09-27 주식회사 베가에너지 Lithium battery protection system
CN110716148A (en) * 2019-10-18 2020-01-21 兰州交通大学 Real-time safety monitoring system for composite power energy storage
CN112886692A (en) * 2021-02-02 2021-06-01 黄国平 Power supply system

Also Published As

Publication number Publication date
CN113890162B (en) 2023-08-22

Similar Documents

Publication Publication Date Title
CN104617330B (en) Recognition method of micro-short circuiting of batteries
CN106463985B (en) Balance correction control device, balance correction system, and electricity storage system
CN112217243B (en) Inter-module balancing method, device and equipment based on bidirectional active balancing
CN107733007A (en) A kind of direct equalizing circuit of battery pack Bi-objective and equalization methods
CN103413981A (en) method and apparatus for battery pack capacity
CN110303945A (en) A kind of battery group electricity adaptive optimization balance control method
CN109347173B (en) Battery pack balance control circuit and method based on switched capacitor
CN104124726A (en) Charging device and charging method
CN107276171A (en) A kind of battery pack equilibrium method based on sliding formwork control
CN111487532B (en) Retired battery screening method and system based on analytic hierarchy process and entropy method
CN112467717A (en) Hybrid energy system real-time load distribution method based on fuzzy control
Chuang et al. Study on fast charging method of series connected lithium-ion battery strings with intelligent control
Elmouatamid et al. Towards a Demand/Response Control Approach for Micro-grid Systems
CN113890162A (en) Charging and discharging method of high-current discharging device
CN112152286A (en) Active equalization device and method for series lithium ion capacitor system
CN108075533A (en) Battery charging circuit and battery charging method
CN209001618U (en) A kind of active equalization framework of battery management system
CN107623343A (en) The active equalization method and device of a kind of lithium ion battery
CN116598618A (en) Rural distribution network energy storage battery charging optimization method based on battery SOC state
CN112054575B (en) LC energy storage based series-parallel battery pack integrated equalization method
CN115208026A (en) Active energy balancing method for source-load separation between battery packs
CN114447456A (en) Portable expandable energy storage unit and application method thereof
Ab Halim et al. Evaluation of Charging Profile of Lead Acid Battery used in Electrical Scooter
JPWO2020262655A5 (en)
Jiang et al. An artificial potential field-based lithium-ion battery SOC equilibrium method in electric vehicles

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