CN117154263A - Lithium battery cascade utilization charging and discharging system and control method - Google Patents
Lithium battery cascade utilization charging and discharging system and control method Download PDFInfo
- Publication number
- CN117154263A CN117154263A CN202311345556.XA CN202311345556A CN117154263A CN 117154263 A CN117154263 A CN 117154263A CN 202311345556 A CN202311345556 A CN 202311345556A CN 117154263 A CN117154263 A CN 117154263A
- Authority
- CN
- China
- Prior art keywords
- temperature
- time sequence
- sequence
- feature
- training
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- WHXSMMKQMYFTQS-UHFFFAOYSA-N Lithium Chemical compound [Li] WHXSMMKQMYFTQS-UHFFFAOYSA-N 0.000 title claims abstract description 67
- 229910052744 lithium Inorganic materials 0.000 title claims abstract description 67
- 238000000034 method Methods 0.000 title claims abstract description 46
- 238000007599 discharging Methods 0.000 title description 5
- 230000008439 repair process Effects 0.000 claims abstract description 35
- 239000013598 vector Substances 0.000 claims description 212
- 238000012549 training Methods 0.000 claims description 70
- 238000000605 extraction Methods 0.000 claims description 38
- 238000005070 sampling Methods 0.000 claims description 27
- 230000011218 segmentation Effects 0.000 claims description 15
- 230000014509 gene expression Effects 0.000 claims description 11
- 230000002123 temporal effect Effects 0.000 claims description 7
- 230000004913 activation Effects 0.000 claims description 6
- 238000001514 detection method Methods 0.000 claims description 6
- 230000003213 activating effect Effects 0.000 claims description 3
- 230000004927 fusion Effects 0.000 claims description 2
- 238000005457 optimization Methods 0.000 claims 2
- 238000012545 processing Methods 0.000 abstract description 7
- 230000005856 abnormality Effects 0.000 abstract description 6
- 238000004458 analytical method Methods 0.000 abstract description 2
- 230000008569 process Effects 0.000 description 17
- 230000006870 function Effects 0.000 description 13
- 230000008859 change Effects 0.000 description 11
- 238000010586 diagram Methods 0.000 description 8
- 238000009826 distribution Methods 0.000 description 8
- 238000013507 mapping Methods 0.000 description 6
- QSNQXZYQEIKDPU-UHFFFAOYSA-N [Li].[Fe] Chemical compound [Li].[Fe] QSNQXZYQEIKDPU-UHFFFAOYSA-N 0.000 description 5
- 238000012544 monitoring process Methods 0.000 description 5
- 230000002159 abnormal effect Effects 0.000 description 4
- 238000013528 artificial neural network Methods 0.000 description 4
- 238000005516 engineering process Methods 0.000 description 4
- 230000008713 feedback mechanism Effects 0.000 description 4
- 210000002569 neuron Anatomy 0.000 description 4
- 238000010606 normalization Methods 0.000 description 4
- 230000002829 reductive effect Effects 0.000 description 4
- 230000002441 reversible effect Effects 0.000 description 4
- 238000004891 communication Methods 0.000 description 3
- 230000000694 effects Effects 0.000 description 3
- 238000003487 electrochemical reaction Methods 0.000 description 3
- 230000006872 improvement Effects 0.000 description 3
- 230000015654 memory Effects 0.000 description 3
- 230000010287 polarization Effects 0.000 description 3
- HBBGRARXTFLTSG-UHFFFAOYSA-N Lithium ion Chemical compound [Li+] HBBGRARXTFLTSG-UHFFFAOYSA-N 0.000 description 2
- 230000032683 aging Effects 0.000 description 2
- 239000010405 anode material Substances 0.000 description 2
- 230000008901 benefit Effects 0.000 description 2
- 238000011217 control strategy Methods 0.000 description 2
- 238000013527 convolutional neural network Methods 0.000 description 2
- 238000004146 energy storage Methods 0.000 description 2
- 229910001416 lithium ion Inorganic materials 0.000 description 2
- GELKBWJHTRAYNV-UHFFFAOYSA-K lithium iron phosphate Chemical compound [Li+].[Fe+2].[O-]P([O-])([O-])=O GELKBWJHTRAYNV-UHFFFAOYSA-K 0.000 description 2
- 230000007774 longterm Effects 0.000 description 2
- 238000010801 machine learning Methods 0.000 description 2
- 239000011159 matrix material Substances 0.000 description 2
- 230000007246 mechanism Effects 0.000 description 2
- 230000000306 recurrent effect Effects 0.000 description 2
- SOXUFMZTHZXOGC-UHFFFAOYSA-N [Li].[Mn].[Co].[Ni] Chemical compound [Li].[Mn].[Co].[Ni] SOXUFMZTHZXOGC-UHFFFAOYSA-N 0.000 description 1
- 239000011149 active material Substances 0.000 description 1
- 239000000853 adhesive Substances 0.000 description 1
- 230000001070 adhesive effect Effects 0.000 description 1
- 238000005311 autocorrelation function Methods 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 238000007405 data analysis Methods 0.000 description 1
- 238000013500 data storage Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000018109 developmental process Effects 0.000 description 1
- 239000007772 electrode material Substances 0.000 description 1
- 230000002708 enhancing effect Effects 0.000 description 1
- 238000000265 homogenisation Methods 0.000 description 1
- 230000003993 interaction Effects 0.000 description 1
- 230000002427 irreversible effect Effects 0.000 description 1
- 230000000670 limiting effect Effects 0.000 description 1
- 230000007787 long-term memory Effects 0.000 description 1
- 239000000463 material Substances 0.000 description 1
- 238000005065 mining Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000003058 natural language processing Methods 0.000 description 1
- 238000003062 neural network model Methods 0.000 description 1
- 230000000717 retained effect Effects 0.000 description 1
- 230000006403 short-term memory Effects 0.000 description 1
- 239000007784 solid electrolyte Substances 0.000 description 1
- 239000000126 substance Substances 0.000 description 1
- 230000001960 triggered effect Effects 0.000 description 1
Classifications
-
- H—ELECTRICITY
- H01—ELECTRIC ELEMENTS
- H01M—PROCESSES OR MEANS, e.g. BATTERIES, FOR THE DIRECT CONVERSION OF CHEMICAL ENERGY INTO ELECTRICAL ENERGY
- H01M10/00—Secondary cells; Manufacture thereof
- H01M10/42—Methods or arrangements for servicing or maintenance of secondary cells or secondary half-cells
- H01M10/44—Methods for charging or discharging
-
- H—ELECTRICITY
- H01—ELECTRIC ELEMENTS
- H01M—PROCESSES OR MEANS, e.g. BATTERIES, FOR THE DIRECT CONVERSION OF CHEMICAL ENERGY INTO ELECTRICAL ENERGY
- H01M10/00—Secondary cells; Manufacture thereof
- H01M10/42—Methods or arrangements for servicing or maintenance of secondary cells or secondary half-cells
- H01M10/425—Structural combination with electronic components, e.g. electronic circuits integrated to the outside of the casing
-
- H—ELECTRICITY
- H01—ELECTRIC ELEMENTS
- H01M—PROCESSES OR MEANS, e.g. BATTERIES, FOR THE DIRECT CONVERSION OF CHEMICAL ENERGY INTO ELECTRICAL ENERGY
- H01M10/00—Secondary cells; Manufacture thereof
- H01M10/42—Methods or arrangements for servicing or maintenance of secondary cells or secondary half-cells
- H01M10/48—Accumulators combined with arrangements for measuring, testing or indicating the condition of cells, e.g. the level or density of the electrolyte
-
- H—ELECTRICITY
- H01—ELECTRIC ELEMENTS
- H01M—PROCESSES OR MEANS, e.g. BATTERIES, FOR THE DIRECT CONVERSION OF CHEMICAL ENERGY INTO ELECTRICAL ENERGY
- H01M10/00—Secondary cells; Manufacture thereof
- H01M10/42—Methods or arrangements for servicing or maintenance of secondary cells or secondary half-cells
- H01M10/48—Accumulators combined with arrangements for measuring, testing or indicating the condition of cells, e.g. the level or density of the electrolyte
- H01M10/486—Accumulators combined with arrangements for measuring, testing or indicating the condition of cells, e.g. the level or density of the electrolyte for measuring temperature
-
- H—ELECTRICITY
- H01—ELECTRIC ELEMENTS
- H01M—PROCESSES OR MEANS, e.g. BATTERIES, FOR THE DIRECT CONVERSION OF CHEMICAL ENERGY INTO ELECTRICAL ENERGY
- H01M10/00—Secondary cells; Manufacture thereof
- H01M10/42—Methods or arrangements for servicing or maintenance of secondary cells or secondary half-cells
- H01M10/425—Structural combination with electronic components, e.g. electronic circuits integrated to the outside of the casing
- H01M2010/4271—Battery management systems including electronic circuits, e.g. control of current or voltage to keep battery in healthy state, cell balancing
-
- H—ELECTRICITY
- H01—ELECTRIC ELEMENTS
- H01M—PROCESSES OR MEANS, e.g. BATTERIES, FOR THE DIRECT CONVERSION OF CHEMICAL ENERGY INTO ELECTRICAL ENERGY
- H01M10/00—Secondary cells; Manufacture thereof
- H01M10/42—Methods or arrangements for servicing or maintenance of secondary cells or secondary half-cells
- H01M10/425—Structural combination with electronic components, e.g. electronic circuits integrated to the outside of the casing
- H01M2010/4278—Systems for data transfer from batteries, e.g. transfer of battery parameters to a controller, data transferred between battery controller and main controller
-
- 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
- Y02E—REDUCTION OF GREENHOUSE GAS [GHG] EMISSIONS, RELATED TO ENERGY GENERATION, TRANSMISSION OR DISTRIBUTION
- Y02E60/00—Enabling technologies; Technologies with a potential or indirect contribution to GHG emissions mitigation
- Y02E60/10—Energy storage using batteries
Landscapes
- Engineering & Computer Science (AREA)
- Manufacturing & Machinery (AREA)
- Chemical & Material Sciences (AREA)
- Chemical Kinetics & Catalysis (AREA)
- Electrochemistry (AREA)
- General Chemical & Material Sciences (AREA)
- Microelectronics & Electronic Packaging (AREA)
- Secondary Cells (AREA)
Abstract
The application discloses a lithium battery cascade utilization charge-discharge system and a control method, which are characterized in that temperature value data are obtained in real time in the electrochemical repair process of a retired lithium battery, a data processing and analysis algorithm is introduced at the rear end to analyze temperature time sequence information so as to detect whether the charge temperature is normal or not, and corresponding measures are taken to adjust when abnormality is detected, so that the charge temperature is ensured to be proper, the electrochemical repair efficiency is improved, and the cascade utilization efficiency and the product quality of the retired power battery are improved.
Description
Technical Field
The application relates to the field of lithium batteries, in particular to a lithium battery cascade utilization charging and discharging system and a control method.
Background
With the popularization and development of electric automobiles, lithium batteries have been widely used as a main power source. According to the difference of the anode materials, the power battery mainly comprises two major types of ternary power batteries and iron lithium power batteries, and nickel-cobalt-manganese-lithium (NCM) and lithium iron phosphate (LFP) are respectively used as the anode materials. From the aspect of performance analysis, the lithium iron power battery has low capacity and short endurance mileage, but has good safety and long cycle life. The market of the retired lithium iron power battery tends to enter the cascade utilization industry, the residual value of the lithium iron power battery can be fully exerted, the maximization of circular economy is realized, and the construction cost of an energy storage system is reduced. The ternary power battery has high specific capacity and long endurance mileage, but has shorter service life, and the safety performance is inferior to that of an iron lithium power battery, so that the ternary power battery is not suitable for the gradient utilization fields with complex application environments, such as an energy storage power station, a communication base station backup power supply and the like.
In the use process of the battery, the electrochemical reaction can lead to uneven distribution of chemical substances in the lithium ion battery, a solid electrolyte interface layer (SEI layer) is formed on the surface of the electrode, the structure of the electrode material is changed, and the like, and these factors can lead to capacity attenuation of the battery, thus limiting the service life and the performance of the battery. Currently, retired lithium ion batteries are often capacity losses due to dynamic polarization reasons, which are reversible. Reversible capacity loss refers to a decrease in the available capacity of a battery due to some dynamic effects that occur during use of the battery, which can be compensated and repaired, typically by a charge-discharge regime. The battery repairing technology can greatly improve the step utilization efficiency and the product quality of the retired power battery.
The charge-discharge system is a common lithium battery repair method. By periodically charging and discharging the battery, the active material inside the battery can be promoted to be redistributed, thereby reducing polarization and improving the capacity of the battery. In the charging process, it is very important to appropriately control the temperature during the charging process. Too high a temperature accelerates the aging and capacity fade of the battery, while too low a temperature reduces the rate of electrochemical reactions. Maintaining a suitable charging temperature range can improve electrochemical repair efficiency.
However, the conventional system often adopts a fixed temperature control strategy, and cannot be adjusted individually according to the actual conditions of different batteries. That is, the temperature requirements of the batteries of different types and states may be different, and the conventional system cannot flexibly control the temperature according to the characteristics and requirements of the batteries. This limits the improvement of electrochemical repair efficiency. Moreover, conventional systems often lack real-time monitoring and feedback mechanisms to monitor temperature changes during charging. This means that the system cannot detect abnormal temperature conditions in time and take corresponding measures to adjust, and the lack of a real-time monitoring and feedback mechanism can lead to the condition that the temperature exceeds a proper range to continuously exist, so that the electrochemical repair efficiency is affected.
Therefore, an optimized lithium battery cascade utilization charge-discharge system is desired.
Disclosure of Invention
The present application has been made to solve the above-mentioned technical problems. The embodiment of the application provides a lithium battery cascade utilization charge-discharge system and a control method, which are characterized in that temperature value data are obtained in real time in an electrochemical repair process of a retired lithium battery, a data processing and analyzing algorithm is introduced into the rear end to analyze temperature time sequence information so as to detect whether the charging temperature is normal or not, and corresponding measures are taken to adjust when abnormality is detected, so that the charging temperature is proper, the electrochemical repair efficiency is improved, and the cascade utilization efficiency and the product quality of the retired power battery are improved.
According to one aspect of the present application, there is provided a lithium battery cascade utilization charge and discharge system, comprising:
the temperature data acquisition module is used for acquiring temperature values of a plurality of preset time points of the retired lithium battery in a preset time period in the electrochemical repair process;
the temperature time sequence arrangement module is used for arranging the temperature values of the plurality of preset time points into temperature time sequence input vectors according to a time dimension;
the temperature local time sequence multi-scale feature extraction module is used for carrying out multi-scale time sequence feature extraction on the temperature time sequence input vector so as to obtain a sequence of multi-scale temperature part time sequence feature vectors;
the temperature global time sequence associated coding module is used for carrying out associated coding on the sequence of the multi-scale temperature part time sequence feature vectors to obtain context semantic temperature time sequence associated feature vectors;
and the charging temperature anomaly detection module is used for determining whether the charging temperature is normal or not based on the context semantic temperature time sequence correlation feature vector.
According to another aspect of the present application, there is provided a lithium battery cascade utilization charge and discharge control method, comprising:
acquiring temperature values of a plurality of preset time points of the retired lithium battery in a preset time period in an electrochemical repair process;
Arranging the temperature values of the plurality of preset time points into temperature time sequence input vectors according to a time dimension;
performing multi-scale time sequence feature extraction on the temperature time sequence input vector to obtain a sequence of multi-scale temperature part time sequence feature vectors;
performing association coding on the sequence of the multi-scale temperature part time sequence feature vectors to obtain context semantic temperature time sequence association feature vectors;
and determining whether the charging temperature is normal or not based on the context semantic temperature time sequence association feature vector.
Compared with the prior art, the lithium battery cascade utilization charge-discharge system and the control method provided by the application have the advantages that temperature value data are obtained in real time in the electrochemical repair process of the retired lithium battery, the temperature time sequence information is analyzed by introducing a data processing and analyzing algorithm at the rear end to detect whether the charge temperature is normal or not, and corresponding measures are taken to adjust when abnormality is detected, so that the charge temperature is proper, the electrochemical repair efficiency is improved, and the cascade utilization efficiency and the product quality of the retired power battery are improved.
Drawings
The above and other objects, features and advantages of the present application will become more apparent by describing embodiments of the present application in more detail with reference to the attached drawings. The accompanying drawings are included to provide a further understanding of embodiments of the application and are incorporated in and constitute a part of this specification, illustrate the application and together with the embodiments of the application, and not constitute a limitation to the application. In the drawings, like reference numerals generally refer to like parts or steps.
Fig. 1 is a block diagram of a lithium battery cascade utilization charge and discharge system according to an embodiment of the present application;
fig. 2 is a system architecture diagram of a lithium battery cascade utilization charge and discharge system according to an embodiment of the present application;
fig. 3 is a block diagram of a training phase of a lithium battery cascade utilization charge and discharge system according to an embodiment of the application;
FIG. 4 is a block diagram of a temperature local time sequence multi-scale feature extraction module in a lithium battery cascade utilization charge-discharge system according to an embodiment of the application;
fig. 5 is a flowchart of a lithium battery cascade utilization charge and discharge control method according to an embodiment of the present application;
fig. 6 is an effect diagram of electrochemical repair according to an embodiment of the present application.
Detailed Description
Hereinafter, exemplary embodiments according to the present application will be described in detail with reference to the accompanying drawings. It should be apparent that the described embodiments are only some embodiments of the present application and not all embodiments of the present application, and it should be understood that the present application is not limited by the example embodiments described herein.
As used in the specification and in the claims, the terms "a," "an," "the," and/or "the" are not specific to a singular, but may include a plurality, unless the context clearly dictates otherwise. In general, the terms "comprises" and "comprising" merely indicate that the steps and elements are explicitly identified, and they do not constitute an exclusive list, as other steps or elements may be included in a method or apparatus.
Although the present application makes various references to certain modules in a system according to embodiments of the present application, any number of different modules may be used and run on a user terminal and/or server. The modules are merely illustrative, and different aspects of the systems and methods may use different modules.
A flowchart is used in the present application to describe the operations performed by a system according to embodiments of the present application. It should be understood that the preceding or following operations are not necessarily performed in order precisely. Rather, the various steps may be processed in reverse order or simultaneously, as desired. Also, other operations may be added to or removed from these processes.
Hereinafter, exemplary embodiments according to the present application will be described in detail with reference to the accompanying drawings. It should be apparent that the described embodiments are only some embodiments of the present application and not all embodiments of the present application, and it should be understood that the present application is not limited by the example embodiments described herein.
The traditional system often adopts a fixed temperature control strategy, and personalized adjustment cannot be carried out according to the actual conditions of different batteries. That is, the temperature requirements of the batteries of different types and states may be different, and the conventional system cannot flexibly control the temperature according to the characteristics and requirements of the batteries. This limits the improvement of electrochemical repair efficiency. Moreover, conventional systems often lack real-time monitoring and feedback mechanisms to monitor temperature changes during charging. This means that the system cannot detect abnormal temperature conditions in time and take corresponding measures to adjust, and the lack of a real-time monitoring and feedback mechanism can lead to the condition that the temperature exceeds a proper range to continuously exist, so that the electrochemical repair efficiency is affected. Therefore, an optimized lithium battery cascade utilization charge-discharge system is desired.
In the technical scheme of the application, a lithium battery cascade utilization charging and discharging system is provided. Fig. 1 is a block diagram of a lithium battery cascade utilization charge and discharge system according to an embodiment of the present application. Fig. 2 is a system architecture diagram of a lithium battery cascade utilization charge and discharge system according to an embodiment of the present application. As shown in fig. 1 and 2, a lithium battery cascade utilization charge and discharge system 300 according to an embodiment of the present application includes: a temperature data acquisition module 310, configured to acquire temperature values of a plurality of predetermined time points of the retired lithium battery in a predetermined time period in an electrochemical repair process; a temperature time sequence arrangement module 320, configured to arrange the temperature values of the plurality of predetermined time points into a temperature time sequence input vector according to a time dimension; a temperature local time sequence multi-scale feature extraction module 330, configured to perform multi-scale time sequence feature extraction on the temperature time sequence input vector to obtain a sequence of multi-scale temperature part time sequence feature vectors; a temperature global time sequence association coding module 340, configured to perform association coding on the sequence of the multi-scale temperature part time sequence feature vectors to obtain context semantic temperature time sequence association feature vectors; the charging temperature anomaly detection module 350 is configured to determine whether the charging temperature is normal based on the context semantic temperature time sequence association feature vector.
In particular, the temperature data acquisition module 310 is configured to acquire temperature values of a plurality of predetermined time points of the retired lithium battery during a predetermined period of time in the electrochemical repair process. It should be appreciated that in the charging process, it is important to properly control the temperature during the charging process. Too high a temperature accelerates the aging and capacity fade of the battery, while too low a temperature reduces the rate of electrochemical reactions. Maintaining a suitable charging temperature range can improve electrochemical repair efficiency. Therefore, in the technical scheme of the application, the temperature values of a plurality of preset time points of the retired lithium battery in the preset time period in the electrochemical repair process are obtained through the temperature sensor.
It is noted that a temperature sensor is a device for measuring the temperature of an environment or object. They typically use sensing elements to detect temperature changes and convert them into readable electrical or digital signals. Temperature sensors are widely used in a variety of fields including industrial automation, weather monitoring, medical equipment, household appliances, and the like. They provide real-time temperature information that helps monitor and control temperature to ensure proper operation of the system or to meet specific needs.
Accordingly, in one possible implementation, temperature values for a plurality of predetermined time points of the retired lithium battery during a predetermined period of time in an electrochemical repair process may be obtained by: first determining a plurality of predetermined points in time at which you wish to acquire a temperature value; and installing a temperature sensor at a proper position on the retired lithium battery. Ensuring that the sensor is in intimate contact with the battery surface to obtain accurate temperature readings. Depending on the type of sensor, it may be desirable to secure the sensor to the battery using a suitable securing means or adhesive; the temperature sensor is connected with the data acquisition system. This may be accomplished by wires, connectors, or wireless communications, among others. Ensuring stable and reliable connection and checking whether communication between the sensor and the data acquisition system is normal or not; and setting sampling frequency and a data storage mode according to the requirements of a data acquisition system. Ensuring that the data acquisition system can record temperature data at a preset time point and sample the temperature data according to a required time interval; and starting an electrochemical repair process of the retired lithium battery. Performing appropriate operation steps and parameter settings according to the requirements and settings of the repair process; at a predetermined point in time, the data acquisition system will record temperature data. Ensuring the normal operation of the data acquisition system and accurately recording a temperature value at each time point; after the data acquisition is completed, the recorded temperature data are analyzed and recorded. Data analysis software or programming tools can be used to process the data and generate a graph or table of temperature versus time.
In particular, the temperature timing arrangement module 320 is configured to arrange the temperature values at the plurality of predetermined time points into a temperature timing input vector according to a time dimension. Considering that the temperature value of the retired lithium battery is continuously changed in the electrochemical repair process, the retired lithium battery has volatility and uncertainty, and is difficult to fully analyze and characterize through a traditional characteristic extraction mode. Therefore, in the technical scheme of the application, the temperature values at the plurality of preset time points are firstly arranged into temperature time sequence input vectors according to the time dimension, so that the distribution information of the temperature values on the time sequence is integrated.
In particular, the temperature local time sequence multi-scale feature extraction module 330 is configured to perform multi-scale time sequence feature extraction on the temperature time sequence input vector to obtain a sequence of multi-scale temperature part time sequence feature vectors. In particular, in one specific example of the present application, as illustrated in fig. 4, the temperature local time series multi-scale feature extraction module 330 includes: the temperature time sequence vector segmentation unit 331 is configured to perform vector segmentation on the temperature time sequence input vector to obtain a sequence of temperature local time sequence input vectors; an up-sampling unit 332, configured to up-sample each temperature local time sequence input vector in the sequence of temperature local time sequence input vectors to obtain a sequence of up-sampled temperature local time sequence input vectors; a temperature local time sequence feature extraction unit 333 is configured to pass the sequence of up-sampled temperature local time sequence input vectors through a multi-scale temperature time sequence feature extractor based on a multi-scale neighborhood feature extraction module to obtain the sequence of multi-scale temperature part time sequence feature vectors.
Specifically, the temperature time sequence vector splitting unit 331 is configured to perform vector splitting on the temperature time sequence input vector to obtain a sequence of temperature local time sequence input vectors. It should be understood that the variation of the temperature value in the time sequence is weak in the electrochemical repair process of the retired lithium battery, and in order to better capture the time sequence variation characteristic information of the temperature value in the time dimension, vector segmentation is further required to be performed on the temperature time sequence input vector so as to obtain a sequence of the temperature local time sequence input vector, so that the temperature local time sequence detail variation characteristic information in different time periods can be better extracted later.
It is noted that vector slicing refers to a process of dividing one vector into a plurality of sub-vectors according to a certain rule or condition. In vector slicing, the original vector is split into multiple smaller parts, each part called a sub-vector. The rules for segmentation may be based on the index of the vector, the numerical range, the specific segmentation point, etc.
Accordingly, in one possible implementation, the temperature timing input vector may be vector-sliced to obtain a sequence of temperature local timing input vectors, for example, by: the window size for the cut is determined. The window size represents the number of consecutive time steps each local timing input vector contains. For example, a window containing 10 time steps may be selected; a step size is determined for sliding a split window over the temperature timing input vector. The step size determines the time interval between adjacent local timing input vectors. For example, a sliding window of step size 1 may be selected, indicating a difference of 1 time step between each window; starting from the initial position of the temperature time sequence input vector, sequentially sliding the segmentation windows according to the size and the step length of the segmentation windows, and segmenting the temperature data in each window into a local time sequence input vector. For example, starting from a starting position, taking 10 consecutive time steps as a first local timing input vector, then sliding a window according to the step size, taking the next 10 time steps as a second local timing input vector, and so on; and forming a sequence of the local time sequence input vectors obtained by segmentation according to the segmentation order. Such a sequence would contain a plurality of temperature local time sequence input vectors, each representing temperature data within a time window.
Specifically, the upsampling unit 332 is configured to upsample each temperature local time sequence input vector in the sequence of temperature local time sequence input vectors to obtain a sequence of upsampled temperature local time sequence input vectors. In order to further improve the capturing capability of the time sequence fine change feature of the temperature value in the preset time period, in the technical scheme of the application, each temperature local time sequence input vector in the sequence of the temperature local time sequence input vectors is further up-sampled to obtain the sequence of up-sampled temperature local time sequence input vectors, so that the density and smoothness of data are increased, and the time sequence change feature of the temperature data is conveniently and better represented later. In particular, in one specific example of the present application, the up-sampling process based on linear interpolation may be performed on the respective temperature local time sequence input vectors, so as to interpolate data points in the original temperature local time sequence input vectors, and generate more data points. In this way, resolution in the time dimension is facilitated to be increased, making the temporal variations of network traffic more subtle. Meanwhile, the linear interpolation can carry out smooth interpolation among sampling points, so that the influence of noise and abrupt change is reduced, and the continuity and stability of data are improved.
Accordingly, in one possible implementation, each temperature local time series input vector in the sequence of temperature local time series input vectors may be up-sampled to obtain a sequence of up-sampled temperature local time series input vectors, for example, by: a multiple is determined to upsample each temperature local timing input vector. The upsampling multiple represents the number of additional time steps inserted between each time step. For example, the number of time steps per temperature local timing input vector may be chosen to be doubled, i.e. up-sampling by a factor of 2; an appropriate interpolation method is selected to generate new sampling points. Common interpolation methods include linear interpolation, spline interpolation, polynomial interpolation, and the like. Selecting a proper interpolation method according to the characteristics and the requirements of the data; for each temperature local time sequence input vector, taking the temperature value in the temperature local time sequence input vector as an original signal, and carrying out up-sampling by using a selected interpolation method. An appropriate number of new sampling points are inserted between adjacent temperature values according to the upsampling multiple. The values of the new sampling points are calculated by an interpolation method; and forming a new sequence by the up-sampled temperature local time sequence input vector according to the sequence of the original sequence. Such a sequence would contain up-sampled temperature local time series input vectors, each representing up-sampled temperature data over a time window.
Specifically, the temperature local time sequence feature extraction unit 333 is configured to pass the sequence of up-sampled temperature local time sequence input vectors through a multi-scale temperature time sequence feature extractor based on a multi-scale neighborhood feature extraction module to obtain the sequence of multi-scale temperature part time sequence feature vectors. When the time sequence characteristic extraction of the temperature value is carried out, the fluctuation and uncertainty characteristics of the temperature value and the change information of the temperature value in the time dimension are considered to be weak, so that the temperature value can present different time sequence change mode characteristic information in different time periods. Therefore, in the technical scheme of the application, the sequence of the up-sampling temperature local time sequence input vector is subjected to feature mining in a multi-scale temperature time sequence feature extractor based on a multi-scale neighborhood feature extraction module so as to extract local time sequence multi-scale neighborhood associated feature information of the temperature value in different time periods, thereby obtaining the sequence of the multi-scale temperature part time sequence feature vector. Wherein, the multiscale neighborhood feature extraction module comprises: the device comprises a first convolution layer, a second convolution layer parallel to the first convolution layer and a multi-scale feature fusion layer connected with the first convolution layer and the second convolution layer, wherein the first convolution layer uses a one-dimensional convolution kernel with a first length, and the second convolution layer uses a one-dimensional convolution kernel with a second length. More specifically, inputting the sequence of upsampled temperature local timing input vectors into a first convolution layer of the multi-scale temperature timing feature extractor to obtain a sequence of first neighborhood-scale temperature local timing feature vectors, wherein the first convolution layer has a first one-dimensional convolution kernel of a first length; inputting the sequence of up-sampled temperature local time sequence input vectors into a second convolution layer of the multi-scale temperature time sequence feature extractor to obtain a sequence of second neighborhood scale temperature part time sequence feature vectors, wherein the second convolution layer has a second one-dimensional convolution kernel of a second length, and the first length is different from the second length; and cascading the sequence of the first neighborhood scale temperature part time sequence feature vector and the sequence of the second neighborhood scale temperature part time sequence feature vector to obtain the sequence of the multi-scale temperature part time sequence feature vector. Wherein inputting the sequence of upsampled temperature local timing input vectors into a first convolution layer of the multi-scale temperature timing feature extractor to obtain a sequence of first neighborhood-scale temperature local timing feature vectors, comprises: using a first convolution layer of the multi-scale temperature time sequence feature extractor to perform one-dimensional convolution coding on the sequence of the up-sampling temperature local time sequence input vector according to the following one-dimensional convolution formula so as to obtain the sequence of the first neighborhood scale temperature part time sequence feature vector; wherein, the formula is:
Wherein a is the width of a first convolution kernel in the X direction, F (a) is a first convolution kernel parameter vector, G (X-a) is a local vector matrix calculated by a convolution kernel function, w is the size of a first one-dimensional convolution kernel, X represents the sequence of the up-sampling temperature local time sequence input vector, and Cov (X) represents one-dimensional convolution encoding of the sequence of the up-sampling temperature local time sequence input vector; and inputting the sequence of upsampled temperature local timing input vectors into a second convolution layer of the multi-scale temperature timing feature extractor to obtain a sequence of second neighborhood-scale temperature local timing feature vectors, comprising: using a second convolution layer of the multi-scale temperature time sequence feature extractor to perform one-dimensional convolution coding on the sequence of the up-sampling temperature local time sequence input vector according to the following one-dimensional convolution formula so as to obtain a sequence of the second neighborhood scale temperature part time sequence feature vector; wherein, the formula is:
wherein b is the width of the second convolution kernel in the X direction, F (b) is a second convolution kernel parameter vector, G (X-b) is a local vector matrix calculated by a convolution kernel function, m is the size of the second one-dimensional convolution kernel, X represents the sequence of the up-sampling temperature local time sequence input vector, and Cov (X) represents one-dimensional convolution encoding of the sequence of the up-sampling temperature local time sequence input vector.
It should be noted that, in other specific examples of the present application, the multi-scale time sequence feature extraction may be performed on the temperature time sequence input vector in other manners to obtain a sequence of multi-scale temperature portion time sequence feature vectors, for example: the multi-scale range used is determined. The scale may be the size of a time window, representing how long the feature extraction is performed; sliding a fixed size time window on the temperature timing input vector using a sliding window technique; and in each time window, extracting the characteristics of the temperature time sequence data. Various statistical features may be used, such as mean, variance, maximum, minimum, etc. In addition, frequency domain features, wavelet transforms, autocorrelation functions, etc. may also be used for more advanced feature extraction; the features extracted from each time window are combined into a feature vector. The feature vector represents a multi-scale temperature part time sequence feature in the time window; and arranging the characteristic vectors of each time window according to the time sequence to form a sequence of time sequence characteristic vectors of the multi-scale temperature part. Such a sequence would capture the temperature change characteristics at different scales; and (3) carrying out standardization processing on the sequence of the time sequence feature vectors of the multi-scale temperature part according to the requirement. Normalization may allow for comparability of features at different scales, e.g., scaling feature values to a range of 0 to 1; further data analysis and application is performed using a multi-scale temperature portion temporal feature vector sequence. Machine learning algorithms, time series models, etc. may be used for tasks such as prediction, classification, clustering, etc.
In particular, the temperature global timing related encoding module 340 is configured to perform related encoding on the sequence of the multi-scale temperature portion timing feature vectors to obtain a context semantic temperature timing related feature vector. The correlation relationship based on the time sequence whole is considered between local time sequence multi-scale change characteristics in different time periods due to the temperature value of the retired lithium battery in the electrochemical repair process. Therefore, in order to sufficiently capture the forward and backward time sequence correlation between the time sequence pattern feature information of the temperature value in each local time period, in a specific example of the present application, it is necessary to further encode the sequence of the multi-scale temperature portion time sequence feature vector by a temperature time sequence pattern feature sequence encoder based on the LSTM model, so as to extract context correlation feature information based on time sequence global between local time sequence variation features of the temperature value, thereby obtaining a context semantic temperature time sequence correlation feature vector.
Notably, LSTM is a variant of Recurrent Neural Network (RNN) specifically designed for processing sequence data. The LSTM model can effectively solve the problem that the gradient vanishes or gradient explodes easily when the traditional RNN model processes long-term dependency through introducing a gating mechanism. The key components in the LSTM model are LSTM units, and each LSTM unit internally comprises a memory unit and three gates: forget gate, input gate and output gate. The gates control the flow of information through the learned weights, thereby enabling modeling of long-term dependencies in the sequence. In the LSTM unit, the forget gate determines whether the information in the memory unit at the previous time is retained, the input gate determines how the new information input at the current time is added to the memory unit, and the output gate determines the output at the current time. The switching states of these gates are obtained by weighting and activating the input data and the hidden state of the previous moment. The LSTM model constructs a deep network structure by stacking a plurality of LSTM units, thereby enhancing the expression capability of the model. During training, the LSTM model optimizes the weight parameters by a back-propagation algorithm to minimize the gap between the predicted output and the real labels. Due to the gating mechanism of the LSTM model, the LSTM model can effectively process long-sequence data and has good effects in a plurality of sequence modeling tasks, such as natural language processing, voice recognition, time sequence prediction and the like.
It should be noted that, in other specific examples of the present application, the sequence of the multi-scale temperature portion time sequence feature vectors may be further encoded in other manners to obtain a context semantic temperature time sequence associated feature vector, for example: an appropriate associative encoding method is selected to capture associative information between the multi-scale temperature local timing feature vectors. Common associated coding methods include recurrent neural networks, long and short term memory networks, convolutional neural networks, and the like. Selecting a proper associated coding method according to the characteristics and the requirements of the data; and taking the multi-scale temperature local time sequence characteristic vector sequence as an input sequence. Ensuring that the sequences are arranged in the correct order to correctly capture the temporal correlation information; the input sequence is processed using the selected associative coding method. The specific associated coding method will vary depending on the model selected. For example, for RNN or LSTM, the input sequence may be entered into the network step by step, one feature vector processed per time step, and the hidden state of the network preserved to capture the context Wen Yuyi association. For CNN, the input sequence can be used as the input of a convolution layer, and the local association can be captured in a sliding window mode; during the associative coding process, the network processes the input sequence step by step and outputs a context semantic associative feature vector at each time step. These feature vectors capture the associated information in the input sequence and have a higher level semantic representation; and forming a new sequence by the obtained context semantic temperature time sequence associated feature vectors according to the sequence of the original sequence. Such a sequence would contain context semantic association feature vectors, each representing an association feature within a time window.
In particular, the charging temperature anomaly detection module 350 is configured to determine whether the charging temperature is normal based on the context semantic temperature timing related feature vector. In particular, in one specific example of the present application, the context semantic temperature time-series associated feature vector is passed through a classifier to obtain a classification result, which is used to indicate whether the charging temperature is normal. Specifically, using a plurality of full-connection layers of the classifier to perform full-connection coding on the context semantic temperature time sequence associated feature vector so as to obtain a coding classification feature vector; and passing the coding classification feature vector through a Softmax classification function of the classifier to obtain the classification result.
A Classifier (Classifier) refers to a machine learning model or algorithm that is used to classify input data into different categories or labels. The classifier is part of supervised learning, which performs classification tasks by learning mappings from input data to output categories.
The fully connected layer (Fully Connected Layer) is one type of layer commonly found in neural networks. In the fully connected layer, each neuron is connected to all neurons of the upper layer, and each connection has a weight. This means that each neuron in the fully connected layer receives inputs from all neurons in the upper layer, and weights these inputs together, and then passes the result to the next layer.
The Softmax classification function is a commonly used activation function for multi-classification problems. It converts each element of the input vector into a probability value between 0 and 1, and the sum of these probability values equals 1. The Softmax function is commonly used at the output layer of a neural network, and is particularly suited for multi-classification problems, because it can map the network output into probability distributions for individual classes. During the training process, the output of the Softmax function may be used to calculate the loss function and update the network parameters through a back propagation algorithm. Notably, the output of the Softmax function does not change the relative magnitude relationship between elements, but rather normalizes them. Thus, the Softmax function does not change the characteristics of the input vector, but simply converts it into a probability distribution form.
It should be noted that, in other specific examples of the present application, it may also be determined whether the charging temperature is normal based on the context semantic temperature time sequence association feature vector in other manners, for example: acquiring temperature time sequence data in the charging process, and acquiring a multi-scale temperature local time sequence feature vector sequence by using the method; performing associated coding on the multi-scale temperature local time sequence feature vector sequence by using a proper associated coding method to obtain a context semantic temperature time sequence associated feature vector sequence; and extracting features which are helpful for judging whether the charging temperature is normal from the context semantic temperature time sequence associated feature vector sequence. This may include average temperature, rate of temperature change, temperature fluctuation, etc.; the extracted features are normalized to eliminate dimensional differences between different features, ensuring that they have the same dimensions. Common normalization methods include mean normalization and standard deviation normalization; the appropriate threshold is set according to the normal range of the charging temperature and the safety standard. These thresholds may be determined based on actual conditions and domain knowledge; and comparing the normalized characteristics with a set threshold value to judge whether the charging temperature is abnormal. If the characteristic value exceeds the set threshold range, the temperature abnormality can be judged; if a temperature anomaly is detected, corresponding processing measures such as sending out an alarm, stopping charging, adjusting charging parameters and the like can be triggered to ensure the safety of the charging process.
It should be appreciated that the multi-scale temperature temporal feature extractor based on the multi-scale neighborhood feature extraction module, the LSTM model-based temperature temporal pattern feature sequence encoder, and the classifier need to be trained prior to inference using the neural network model described above. That is, the lithium battery cascade utilization charge-discharge system according to the present application further includes a training stage for training the multi-scale temperature sequential feature extractor based on the multi-scale neighborhood feature extraction module, the temperature sequential pattern feature sequence encoder based on the LSTM model, and the classifier.
Fig. 3 is a block diagram of a training phase of a lithium battery cascade utilization charge and discharge system according to an embodiment of the application. As shown in fig. 3, a lithium battery cascade utilization charge and discharge system 300 according to an embodiment of the present application includes: training phase 400, comprising: a training data acquisition unit 410, configured to acquire training data, where the training data includes training temperature values of a plurality of predetermined time points in a predetermined period of time in an electrochemical repair process of the retired lithium battery, and a true value of whether the charging temperature is normal; a training temperature time sequence data arrangement unit 420, configured to arrange training temperature values of the plurality of predetermined time points into training temperature time sequence input vectors according to a time dimension; the training vector segmentation unit 430 is configured to perform vector segmentation on the training temperature time sequence input vector to obtain a sequence of training temperature local time sequence input vectors; a training up-sampling unit 440, configured to up-sample each training temperature local time sequence input vector in the sequence of training temperature local time sequence input vectors to obtain a sequence of training up-sampling temperature local time sequence input vectors; a training temperature local time sequence feature extraction unit 450, configured to pass the sequence of training up-sampling temperature local time sequence input vectors through the multi-scale temperature time sequence feature extractor based on the multi-scale neighborhood feature extraction module to obtain a sequence of training multi-scale temperature part time sequence feature vectors; a training temperature global time sequence associated coding unit 460, configured to pass the sequence of training multi-scale temperature part time sequence feature vectors through the LSTM model-based temperature time sequence mode feature sequence coder to obtain training context semantic temperature time sequence associated feature vectors; the feature activating unit 470 is configured to perform feature rank expression on the training context semantic temperature time sequence associated feature vector to perform feature rank expression on the semantic information uniformity activation to obtain an activated training context semantic temperature time sequence associated feature vector; a classification loss unit 480, configured to pass the activated training context semantic temperature time sequence associated feature vector through the classifier to obtain a classification loss function value; the model training unit 490 is configured to train the multi-scale temperature time series feature extractor based on the multi-scale neighborhood feature extraction module, the temperature time series pattern feature sequence encoder based on the LSTM model, and the classifier based on the classification loss function value and through back propagation of gradient descent.
Particularly, in the technical scheme of the application, when the sequence of the up-sampling temperature local time sequence input vector passes through a multi-scale temperature time sequence feature extractor based on a multi-scale neighborhood feature extraction module, the sequence of the multi-scale temperature part time sequence feature vector expresses multi-scale local time sequence associated features of temperature values in a local time domain. In this way, when the sequence of multi-scale temperature part time sequence feature vectors is extracted through the temperature time sequence mode feature sequence encoder based on the LSTM model, the context semantic temperature time sequence feature vectors are expressed in a context correlation mode of local time domain scale of local time sequence feature. Therefore, when the context semantic temperature time sequence associated feature vector is classified by the classifier, the multi-scale time sequence associated feature based on the context association under the local time sequence scale can also perform class probability mapping of the scale heuristic based on the local time sequence context associated scale in the classification process. However, considering that the difference of the time sequence feature distribution under the time sequence correlation scale with the local time sequence can cause the training efficiency of the classifier to be reduced, the applicant of the present application preferably performs the feature rank expression of the context semantic temperature time sequence correlation feature vector for the semantic information homogenization activation, which is specifically expressed as:
Wherein V is the training context semantic temperature time sequence associated feature vector, V i Is saidTraining the ith eigenvalue, II, V II of the context semantic temperature time sequence associated eigenvector 2 Representing the two norms of the training context semantic temperature time sequence associated feature vector, log is a logarithmic function value based on 2, and alpha is a weight super-parameter, v' i Is the post-activation training context semantic temperature timing associated feature vector. Here, considering that the feature distribution mapping of the context semantic temperature time sequence associated feature vector V in the high-dimensional feature space to the class probability space may present different mapping modes on different feature distribution levels based on the mixed scale time sequence associated feature, so that the optimal efficiency cannot be obtained based on the scale heuristic mapping strategy, and therefore, the rank expression semantic information based on the feature vector norm is uniform instead of scale matching, similar feature rank expressions can be activated in a similar manner, and the correlation between feature rank expressions with larger difference can be reduced, so that the problem that the probability expression mapping efficiency of the feature distribution of the context semantic temperature time sequence associated feature vector V in different space rank expressions is low is solved, and the training efficiency of the context semantic temperature time sequence associated feature vector when classified by the classifier is improved. Therefore, the abnormal charging temperature detection can be carried out based on the actual temperature change condition of the retired lithium battery in the electrochemical repair process, and corresponding measures are taken to adjust when the abnormality is detected, so that the suitability of the charging temperature is ensured, the electrochemical repair efficiency is improved, and the cascade utilization efficiency and the product quality of the retired power battery are improved.
As described above, the lithium battery cascade-utilization charge and discharge system 300 according to the embodiment of the present application can be implemented in various wireless terminals, for example, a server having a lithium battery cascade-utilization charge and discharge control algorithm, or the like. In one possible implementation, lithium battery cascade utilization charge-discharge system 300 according to embodiments of the present application may be integrated into a wireless terminal as a software module and/or hardware module. For example, the lithium battery cascade utilization charge-discharge system 300 may be a software module in the operating system of the wireless terminal, or may be an application developed for the wireless terminal; of course, the lithium battery cascade utilization charge and discharge system 300 can also be one of a plurality of hardware modules of the wireless terminal.
Alternatively, in another example, the lithium battery cascade utilization charge-discharge system 300 and the wireless terminal may be separate devices, and the lithium battery cascade utilization charge-discharge system 300 may be connected to the wireless terminal through a wired and/or wireless network and transmit interaction information in accordance with a agreed data format.
Further, a lithium battery cascade utilization charge and discharge control method is provided.
Fig. 5 is a flowchart of a lithium battery cascade utilization charge and discharge control method according to an embodiment of the present application. As shown in fig. 5, the lithium battery cascade utilization charge and discharge control method according to the embodiment of the application includes the steps of: s1, acquiring temperature values of a plurality of preset time points of a retired lithium battery in a preset time period in an electrochemical repair process; s2, arranging the temperature values of the plurality of preset time points into temperature time sequence input vectors according to a time dimension; s3, performing multi-scale time sequence feature extraction on the temperature time sequence input vector to obtain a sequence of multi-scale temperature part time sequence feature vectors; s4, performing association coding on the sequence of the multi-scale temperature part time sequence feature vectors to obtain context semantic temperature time sequence association feature vectors; s5, determining whether the charging temperature is normal or not based on the context semantic temperature time sequence association feature vector.
In summary, the lithium battery cascade utilization charge-discharge control method according to the embodiment of the application is clarified, temperature value data are obtained in real time in the electrochemical repair process of the retired lithium battery, a data processing and analyzing algorithm is introduced at the rear end to analyze temperature time sequence information so as to detect whether the charging temperature is normal or not, and corresponding measures are taken to adjust when abnormality is detected, so that the charging temperature is proper, the electrochemical repair efficiency is improved, and the cascade utilization efficiency and the product quality of the retired power battery are improved.
In the embodiment of the application, as shown in fig. 6, the capacity loss caused by dynamic polarization reasons belongs to reversible capacity loss, and can be compensated and repaired by a charge-discharge system (see fig. 4); capacity loss caused by material structural fatigue and damage to the internal structure of the battery belongs to irreversible capacity loss, but can be partially recovered through proper physical repair. The battery repairing technology can greatly improve the utilization efficiency and the product quality of the retired power battery cascade, and belongs to a breakthrough core technology of the retired power battery cascade utilization industry.
The foregoing description of the embodiments of the present disclosure has been presented for purposes of illustration and description, and is not intended to be exhaustive or limited to the embodiments disclosed. Many modifications and variations will be apparent to those of ordinary skill in the art without departing from the scope and spirit of the various embodiments described. The terminology used herein was chosen in order to best explain the principles of the embodiments, the practical application, or the improvement of technology in the marketplace, or to enable others of ordinary skill in the art to understand the embodiments disclosed herein.
Claims (9)
1. Lithium battery echelon utilization charge-discharge system, characterized by comprising:
the temperature data acquisition module is used for acquiring temperature values of a plurality of preset time points of the retired lithium battery in a preset time period in the electrochemical repair process;
the temperature time sequence arrangement module is used for arranging the temperature values of the plurality of preset time points into temperature time sequence input vectors according to a time dimension;
the temperature local time sequence multi-scale feature extraction module is used for carrying out multi-scale time sequence feature extraction on the temperature time sequence input vector so as to obtain a sequence of multi-scale temperature part time sequence feature vectors;
the temperature global time sequence associated coding module is used for carrying out associated coding on the sequence of the multi-scale temperature part time sequence feature vectors to obtain context semantic temperature time sequence associated feature vectors;
and the charging temperature anomaly detection module is used for determining whether the charging temperature is normal or not based on the context semantic temperature time sequence correlation feature vector.
2. The lithium battery cascade utilization charge-discharge system of claim 1, wherein the temperature local time sequence multi-scale feature extraction module comprises:
the temperature time sequence vector segmentation unit is used for carrying out vector segmentation on the temperature time sequence input vector to obtain a sequence of temperature local time sequence input vectors;
The up-sampling unit is used for up-sampling each temperature local time sequence input vector in the sequence of the temperature local time sequence input vectors to obtain a sequence of up-sampled temperature local time sequence input vectors;
and the temperature local time sequence feature extraction unit is used for enabling the sequence of the up-sampling temperature local time sequence input vector to pass through a multi-scale temperature time sequence feature extractor based on a multi-scale neighborhood feature extraction module to obtain the sequence of the multi-scale temperature part time sequence feature vector.
3. The lithium battery cascade utilization charge-discharge system of claim 2, wherein the multi-scale neighborhood feature extraction module comprises: the device comprises a first convolution layer, a second convolution layer parallel to the first convolution layer and a multi-scale feature fusion layer connected with the first convolution layer and the second convolution layer, wherein the first convolution layer uses a one-dimensional convolution kernel with a first length, and the second convolution layer uses a one-dimensional convolution kernel with a second length.
4. The lithium battery cascade utilization charge-discharge system of claim 3, wherein the temperature global timing correlation encoding module is configured to: and enabling the sequence of the multi-scale temperature part time sequence feature vectors to pass through a temperature time sequence mode feature sequence encoder based on an LSTM model to obtain the context semantic temperature time sequence correlation feature vectors.
5. The lithium battery cascade utilization charge and discharge system of claim 4, wherein the charge temperature anomaly detection module is configured to: and the context semantic temperature time sequence associated feature vector is passed through a classifier to obtain a classification result, wherein the classification result is used for indicating whether the charging temperature is normal or not.
6. The lithium battery cascade utilization charge-discharge system of claim 5, further comprising a training module for training the multi-scale temperature temporal feature extractor based on the multi-scale neighborhood feature extraction module, the LSTM model based temperature temporal pattern feature sequence encoder, and the classifier.
7. The lithium battery cascade utilization charge-discharge system of claim 6, wherein the training module comprises:
the training data acquisition unit is used for acquiring training data, wherein the training data comprise training temperature values of a plurality of preset time points in a preset time period in the electrochemical repair process of the retired lithium battery and true values of whether the charging temperature is normal or not;
the training temperature time sequence data arrangement unit is used for arranging training temperature values of the plurality of preset time points into training temperature time sequence input vectors according to a time dimension;
The training vector segmentation unit is used for carrying out vector segmentation on the training temperature time sequence input vector so as to obtain a sequence of training temperature local time sequence input vector;
the training up-sampling unit is used for up-sampling each training temperature local time sequence input vector in the training temperature local time sequence input vector sequence to obtain a training up-sampling temperature local time sequence input vector sequence;
the training temperature local time sequence feature extraction unit is used for enabling the sequence of the training up-sampling temperature local time sequence input vector to pass through the multi-scale temperature time sequence feature extractor based on the multi-scale neighborhood feature extraction module to obtain a sequence of training multi-scale temperature part time sequence feature vectors;
the training temperature global time sequence associated coding unit is used for enabling the sequence of the training multi-scale temperature part time sequence feature vectors to pass through the LSTM model-based temperature time sequence mode feature sequence coder to obtain training context semantic temperature time sequence associated feature vectors;
the feature activating unit is used for carrying out semantic information uniform activation of feature rank expression on the training context semantic temperature time sequence associated feature vector so as to obtain an activated training context semantic temperature time sequence associated feature vector;
The classification loss unit is used for enabling the activated training context semantic temperature time sequence associated feature vector to pass through the classifier to obtain a classification loss function value;
and the model training unit is used for training the multi-scale temperature time sequence feature extractor based on the multi-scale neighborhood feature extraction module, the temperature time sequence mode feature sequence encoder based on the LSTM model and the classifier based on the classification loss function value and through back propagation of gradient descent.
8. The lithium battery cascade utilization charge-discharge system according to claim 7, wherein the feature activation unit is configured to: carrying out feature rank expression semantic information uniform activation on the training context semantic temperature time sequence associated feature vector by using the following optimization formula to obtain the activated training context semantic temperature time sequence associated feature vector;
wherein, the optimization formula is:
wherein V is the training context semantic temperature time sequence associated feature vector, V i Is the ith eigenvalue of the training context semantic temperature timing related eigenvector, V 2 Representing the two norms of the training context semantic temperature time sequence associated feature vector, log is a logarithmic function value based on 2, and alpha is a weight super-parameter, v i ' is the post-activation training context semantic temperature timing associated feature vector.
9. The lithium battery echelon utilization charge and discharge control method is characterized by comprising the following steps of:
acquiring temperature values of a plurality of preset time points of the retired lithium battery in a preset time period in an electrochemical repair process;
arranging the temperature values of the plurality of preset time points into temperature time sequence input vectors according to a time dimension;
performing multi-scale time sequence feature extraction on the temperature time sequence input vector to obtain a sequence of multi-scale temperature part time sequence feature vectors;
performing association coding on the sequence of the multi-scale temperature part time sequence feature vectors to obtain context semantic temperature time sequence association feature vectors;
and determining whether the charging temperature is normal or not based on the context semantic temperature time sequence association feature vector.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311345556.XA CN117154263A (en) | 2023-10-17 | 2023-10-17 | Lithium battery cascade utilization charging and discharging system and control method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311345556.XA CN117154263A (en) | 2023-10-17 | 2023-10-17 | Lithium battery cascade utilization charging and discharging system and control method |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN117154263A true CN117154263A (en) | 2023-12-01 |
Family
ID=88912345
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311345556.XA Pending CN117154263A (en) | 2023-10-17 | 2023-10-17 | Lithium battery cascade utilization charging and discharging system and control method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117154263A (en) |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117419828A (en) * | 2023-12-18 | 2024-01-19 | 南京品傲光电科技有限公司 | New energy battery temperature monitoring method based on optical fiber sensor |
| CN118017066A (en) * | 2024-04-10 | 2024-05-10 | 深圳市杰成镍钴新能源科技有限公司 | Control method for gradient utilization of retired battery pack |
| CN118054111A (en) * | 2024-02-27 | 2024-05-17 | 武汉怡特环保科技有限公司 | Lithium battery pack safety management method and device, storage medium and electronic equipment |
| CN118017066B (en) * | 2024-04-10 | 2024-07-02 | 深圳市杰成镍钴新能源科技有限公司 | Control method for gradient utilization of retired battery pack |
-
2023
- 2023-10-17 CN CN202311345556.XA patent/CN117154263A/en active Pending
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117419828A (en) * | 2023-12-18 | 2024-01-19 | 南京品傲光电科技有限公司 | New energy battery temperature monitoring method based on optical fiber sensor |
| CN117419828B (en) * | 2023-12-18 | 2024-05-03 | 南京品傲光电科技有限公司 | New energy battery temperature monitoring method based on optical fiber sensor |
| CN118054111A (en) * | 2024-02-27 | 2024-05-17 | 武汉怡特环保科技有限公司 | Lithium battery pack safety management method and device, storage medium and electronic equipment |
| CN118017066A (en) * | 2024-04-10 | 2024-05-10 | 深圳市杰成镍钴新能源科技有限公司 | Control method for gradient utilization of retired battery pack |
| CN118017066B (en) * | 2024-04-10 | 2024-07-02 | 深圳市杰成镍钴新能源科技有限公司 | Control method for gradient utilization of retired battery pack |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108881196B (en) | Semi-supervised intrusion detection method based on depth generation model | |
| CN107797067B (en) | Lithium ion battery life migration prediction method based on deep learning | |
| CN117154263A (en) | Lithium battery cascade utilization charging and discharging system and control method | |
| CN114358152A (en) | Intelligent power data anomaly detection method and system | |
| Ma et al. | Degradation prognosis for proton exchange membrane fuel cell based on hybrid transfer learning and intercell differences | |
| KR102540027B1 (en) | Power control system and method characterized in that possible to predict power demand and detect abnormalities | |
| Hong et al. | Sequential application of denoising autoencoder and long-short recurrent convolutional network for noise-robust remaining-useful-life prediction framework of lithium-ion batteries | |
| CN114648076A (en) | Unsupervised learning battery production process abnormal fluctuation detection method | |
| Wang et al. | Dynamic early recognition of abnormal lithium-ion batteries before capacity drops using self-adaptive quantum clustering | |
| CN114581699A (en) | Transformer state evaluation method based on deep learning model in consideration of multi-source information | |
| CN114118460A (en) | Low-voltage transformer area line loss rate abnormity detection method and device based on variational self-encoder | |
| Liu et al. | State of health estimation of lithium-ion batteries based on multi-feature extraction and temporal convolutional network | |
| Ye et al. | A novel self-supervised learning-based anomalous node detection method based on an autoencoder for wireless sensor networks | |
| CN113033898A (en) | Electrical load prediction method and system based on K-means clustering and BI-LSTM neural network | |
| Wang et al. | Assessing the Performance Degradation of Lithium‐Ion Batteries Using an Approach Based on Fusion of Multiple Feature Parameters | |
| CN117171702A (en) | Multi-mode power grid fault detection method and system based on deep learning | |
| CN116383747A (en) | Anomaly detection method for generating countermeasure network based on multi-time scale depth convolution | |
| CN111816404B (en) | Demagnetization method and system | |
| CN114219118A (en) | Method and system for predicting service life of intelligent electric meter based on D-S evidence theory | |
| CN117439146B (en) | Data analysis control method and system for charging pile | |
| CN110837932A (en) | Thermal power prediction method of solar heat collection system based on DBN-GA model | |
| Xiang et al. | Two-level battery health diagnosis using encoder-decoder framework and Gaussian mixture ensemble learning based on relaxation voltage | |
| CN117117923B (en) | Big data-based energy storage control grid-connected management method and system | |
| CN117543791B (en) | Power supply detection method, device, equipment and storage medium for power supply | |
| Li et al. | Research on Load State Identification Method Based on CNN-Transformer |
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 |