CN113996564A - Lithium battery echelon utilization and sorting method and device based on characteristic numerical analysis - Google Patents
Lithium battery echelon utilization and sorting method and device based on characteristic numerical analysis Download PDFInfo
- Publication number
- CN113996564A CN113996564A CN202111479576.7A CN202111479576A CN113996564A CN 113996564 A CN113996564 A CN 113996564A CN 202111479576 A CN202111479576 A CN 202111479576A CN 113996564 A CN113996564 A CN 113996564A
- Authority
- CN
- China
- Prior art keywords
- battery
- normal distribution
- label
- sorted
- sorting
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Images
Classifications
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B07—SEPARATING SOLIDS FROM SOLIDS; SORTING
- B07C—POSTAL SORTING; SORTING INDIVIDUAL ARTICLES, OR BULK MATERIAL FIT TO BE SORTED PIECE-MEAL, e.g. BY PICKING
- B07C5/00—Sorting according to a characteristic or feature of the articles or material being sorted, e.g. by control effected by devices which detect or measure such characteristic or feature; Sorting by manually actuated devices, e.g. switches
- B07C5/34—Sorting according to other particular properties
- B07C5/344—Sorting according to other particular properties according to electric or electromagnetic properties
Landscapes
- Secondary Cells (AREA)
- Charge And Discharge Circuits For Batteries Or The Like (AREA)
Abstract
The invention relates to a lithium battery echelon utilization and sorting method and device based on characteristic numerical analysis, wherein the method comprises the following steps: obtaining a change parameter obtained after measuring each battery to be measured for multiple times; according to the open-circuit voltage, screening each battery to be tested for the first time to determine a first sorted battery; performing charge and discharge tests according to the first sorted battery, determining various electrical property parameters, and counting a corresponding normal distribution graph; and classifying the first sorted battery according to the normal distribution diagram based on machine learning, and judging whether the first sorted battery is qualified. The invention extracts various characteristics based on the battery to be tested, and performs corresponding screening for multiple times, thereby ensuring the accuracy and reliability of battery sorting.
Description
Technical Field
The invention relates to the technical field of battery sorting, in particular to a lithium battery echelon utilization sorting method and device based on characteristic numerical analysis.
Background
With the development of new energy, the demand of lithium batteries is increasing, but the performance of lithium batteries is different due to different manufacturing processes and manufacturing materials of different manufacturers. The safe use of the lithium battery is an indispensable prerequisite for using new energy. Under different scenes, the performance requirements of the lithium batteries are different, the lithium batteries need to be effectively sorted, and the requirements of different application scenes are met. In the prior art, the battery sorting technology mainly detects the discharge capacity after constant-voltage charging, the open-circuit voltage after shelving and the 1KHz alternating-current internal resistance of the battery, and performs a plurality of grades of sorting according to the statistical value distribution of the three parameters, however, the sorting mode only combines the traditional three parameters for sorting, is not accurate and efficient enough, has certain deviation, and cannot completely ensure the rapidity and the effectiveness of sorting. Therefore, how to realize a more efficient battery sorting method is an urgent problem to be solved.
Disclosure of Invention
In view of the above, there is a need to provide a method and an apparatus for utilizing and sorting lithium batteries in a echelon manner based on characteristic numerical analysis, so as to overcome the problem in the prior art that target detection is not accurate enough.
The invention provides a lithium battery echelon utilization and sorting method based on characteristic numerical analysis, which comprises the following steps of:
obtaining a change parameter obtained after measuring each battery to be measured for multiple times;
according to the change parameters, performing first screening on each battery to be tested to determine a first sorted battery;
performing charge and discharge tests according to the first sorted battery, determining various electrical property parameters, and counting a corresponding normal distribution graph;
and classifying the first sorted battery according to the normal distribution diagram based on machine learning, and judging whether the first sorted battery is qualified.
Further, the variation parameters include single open-circuit voltage, voltage variation rate and impedance value, the first screening is performed on each battery to be tested according to the variation parameters, and a first sorting battery is determined, including:
acquiring the monomer open-circuit voltage of each battery to be tested, and judging whether the monomer open-circuit voltage meets a first preset condition;
if the first preset condition is met, performing charge and discharge tests on the battery to be tested within preset time, determining the voltage change rate, and judging whether the voltage change rate meets a second preset condition, wherein a first difference value is determined according to the difference between the voltage at the charge and discharge starting moment and the voltage at the charge and discharge ending moment, and the voltage change rate is determined according to the quotient of the first difference value and the preset time;
if the second preset condition is met, judging the impedance values of the battery to be tested in a plurality of frequency points, and judging whether the impedance values meet a third preset condition;
and if the third preset condition is met, judging that the battery is the first sorted battery.
Further, the first preset condition is that the single open-circuit voltage is greater than or equal to a first preset voltage, or the single open-circuit voltage is less than or equal to a second preset voltage;
the second preset condition is that the ratio of the voltage change rate to the change average value is larger than a first preset ratio, wherein the change average value is the average value of the voltage change rates of all the batteries to be tested meeting the first preset condition;
the third preset condition is that the ratio of the impedance value of each frequency point to the impedance average value is greater than a second preset ratio, wherein the impedance average value is the average value of the impedance values of all the batteries to be tested meeting the second preset condition in each frequency point.
Further, the electrical property parameters include coulombic efficiency and energy efficiency, the performing the charge and discharge test according to the first sorted battery determines a plurality of electrical property parameters, and the counting of the corresponding normal distribution graph includes:
performing constant-current charging and discharging tests according to the first sorted battery, and determining the coulombic efficiency and the energy efficiency which are correspondingly formed in the charging and discharging process;
and counting a corresponding normal distribution diagram according to the coulomb efficiency and the energy efficiency.
Further, the counting a corresponding normal distribution graph according to the coulomb efficiency and the energy efficiency includes:
according to the coulomb efficiency, counting a corresponding coulomb normal distribution diagram;
and counting the corresponding energy normal distribution graph according to the energy efficiency.
Further, the classifying the first sorted battery according to the normal distribution map based on machine learning to determine whether the first sorted battery is qualified includes:
inputting the coulomb normal distribution diagram to a first SVM network with complete training, and outputting a corresponding first classification label;
inputting the energy normal distribution graph to a second SVM network which is completely trained, and outputting a corresponding second classification label;
and judging whether the first sorted battery is qualified or not according to the first sorting label and the second sorting label.
Further, the step of judging whether the first sorted battery is qualified or not according to the first sorting label and the second sorting label includes:
and when the first classification label is a first qualified label and the second classification label is a second qualified label, the first sorted battery is qualified.
Further, the training process of the well-trained first SVM network includes:
acquiring a sample set formed by a coulomb normal distribution diagram with marking information, wherein the marking information is a qualified label or an unqualified label of a battery to be detected corresponding to the coulomb normal distribution diagram;
and inputting the sample set into the constructed first SVM network, and iterating until the parameters converge to form the first SVM network with complete training.
Further, the training process of the second fully trained SVM network includes:
acquiring a sample set formed by an energy normal distribution diagram with marking information, wherein the marking information is a qualified label or an unqualified label of a battery to be detected corresponding to the energy normal distribution diagram;
and inputting the sample set into the constructed first SVM network, and iterating until the parameters converge to form the first SVM network with complete training.
The invention also provides a lithium battery echelon utilization sorting device based on characteristic numerical analysis, which comprises:
the acquiring unit is used for acquiring change parameters obtained after each battery to be measured is measured for multiple times;
the processing unit is used for screening each battery to be tested for the first time according to the open-circuit voltage and determining a first sorted battery; the first sorting battery is used for carrying out charging and discharging tests according to the first sorting battery, determining various electrical property parameters and counting a corresponding normal distribution graph;
and the sorting unit is used for sorting the first sorted battery according to the normal distribution diagram based on machine learning and judging whether the first sorted battery is qualified or not.
Compared with the prior art, the invention has the beneficial effects that: firstly, effectively acquiring the variation parameters of each battery to be measured after multiple measurements; then, carrying out primary screening according to the variation parameters to ensure the accuracy of the primary screening; further, performing charge and discharge tests on the screened first sorted battery, determining various corresponding electrical property parameters, performing corresponding data statistics, and determining a corresponding normal distribution graph; and finally, intelligently classifying the normal distribution map based on machine learning, and quickly judging whether the normal distribution map is qualified. In conclusion, the invention extracts various characteristics based on the battery to be tested, and performs corresponding screening for multiple times, thereby ensuring the accuracy and reliability of battery sorting.
Drawings
Fig. 1 is a scene schematic diagram of an embodiment of an application system of a lithium battery echelon utilization sorting method based on characteristic numerical analysis according to the present invention;
fig. 2 is a schematic flow chart of an embodiment of a lithium battery echelon utilization sorting method based on characteristic numerical analysis according to the present invention;
FIG. 3 is a flowchart illustrating an embodiment of step S2 in FIG. 2 according to the present invention;
FIG. 4 is a flowchart illustrating an embodiment of step S3 in FIG. 2 according to the present invention;
FIG. 5 is a flowchart illustrating an embodiment of step S32 in FIG. 4 according to the present invention;
FIG. 6 is a flowchart illustrating an embodiment of step S4 in FIG. 2 according to the present invention;
FIG. 7 is a flowchart illustrating an embodiment of a first SVM network training process provided by the present invention;
FIG. 8 is a flowchart illustrating an embodiment of a second SVM network training process provided by the present invention;
fig. 9 is a schematic structural diagram of an embodiment of a lithium battery echelon utilization sorting device based on characteristic numerical analysis according to the present invention.
Detailed Description
The accompanying drawings, which are incorporated in and constitute a part of this application, illustrate preferred embodiments of the invention and together with the description, serve to explain the principles of the invention and not to limit the scope of the invention.
In the description of the present invention, the terms "first" and "second" are used for descriptive purposes only and are not to be construed as indicating or implying relative importance or implying any number of technical features indicated. Thus, a feature defined as "first" or "second" may explicitly or implicitly include at least one such feature. Further, "plurality" means at least two, e.g., two, three, etc., unless specifically limited otherwise.
Reference throughout this specification to "an embodiment" means that a particular feature, structure, or characteristic described in connection with the embodiment can be included in at least one embodiment of the present invention. The appearances of the phrase in various places in the specification are not necessarily all referring to the same embodiment, nor are separate or alternative embodiments mutually exclusive of other embodiments. It is explicitly and implicitly understood by one skilled in the art that the described embodiments can be combined with other embodiments.
The invention provides a lithium battery echelon utilization sorting method based on characteristic numerical analysis, which integrates multiple aspects of electrical characteristics to perform sorting for multiple times and provides a new idea for further improving the accuracy of battery sorting. The following specific examples are described in detail:
an embodiment of the present invention provides an application system of a lithium battery echelon utilization sorting method based on a characteristic numerical analysis, and fig. 1 is a scene schematic diagram of an embodiment of an application system of a lithium battery echelon utilization sorting method based on a characteristic numerical analysis, where the system may include a server 100, and a lithium battery echelon utilization sorting device based on a characteristic numerical analysis, such as the server in fig. 1, is integrated in the server 100.
The server 100 in the embodiment of the present invention is mainly used for:
obtaining a change parameter obtained after measuring each battery to be measured for multiple times;
according to the change parameters, performing first screening on each battery to be tested to determine a first sorted battery;
performing charge and discharge tests according to the first sorted battery, determining various electrical property parameters, and counting a corresponding normal distribution graph;
and classifying the first sorted battery according to the normal distribution diagram based on machine learning, and judging whether the first sorted battery is qualified.
In this embodiment of the present invention, the server 100 may be an independent server, or may be a server network or a server cluster composed of servers, for example, the server 100 described in this embodiment of the present invention includes, but is not limited to, a computer, a network host, a single network server, a plurality of network server sets, or a cloud server composed of a plurality of servers. Among them, the Cloud server is constituted by a large number of computers or web servers based on Cloud Computing (Cloud Computing).
It is to be understood that the terminal 200 used in the embodiments of the present invention may be a device that includes both receiving and transmitting hardware, i.e., a device having receiving and transmitting hardware capable of performing two-way communication over a two-way communication link. Such a device may include: a cellular or other communication device having a single line display or a multi-line display or a cellular or other communication device without a multi-line display. The specific terminal 200 may be a desktop, a laptop, a web server, a Personal Digital Assistant (PDA), a mobile phone, a tablet computer, a wireless terminal device, a communication device, an embedded device, and the like, and the present embodiment does not limit the type of the terminal 200.
Those skilled in the art can understand that the application environment shown in fig. 1 is only one application scenario of the present invention, and does not constitute a limitation on the application scenario of the present invention, and that other application environments may further include more or fewer terminals than those shown in fig. 1, for example, only 2 terminals are shown in fig. 1, and it can be understood that the application system of the lithium battery echelon utilization sorting method based on eigenvalue analysis may further include one or more other terminals, which is not limited herein.
In addition, as shown in fig. 1, the application system of the lithium battery gradient utilization sorting method based on the characteristic numerical analysis may further include a memory 200 for storing data, such as variation parameters, electrical property parameters, normal distribution maps, and the like.
It should be noted that the scene schematic diagram of the application system of the lithium battery echelon utilization sorting method based on the eigenvalue analysis shown in fig. 1 is only an example, and the application system and the scene of the lithium battery echelon utilization sorting method based on the eigenvalue analysis described in the embodiment of the present invention are for more clearly illustrating the technical solution of the embodiment of the present invention, and do not form a limitation on the technical solution provided in the embodiment of the present invention.
The embodiment of the present invention provides a lithium battery echelon utilization sorting method based on a characteristic numerical analysis, and with reference to fig. 2, fig. 2 is a schematic flow chart of an embodiment of a lithium battery echelon utilization sorting method based on a characteristic numerical analysis, which includes steps S1 to S4, where:
in step S1, obtaining a variation parameter obtained by measuring each battery to be measured for a plurality of times;
in step S2, performing a first screening on each battery to be tested according to the variation parameters, and determining a first sorted battery;
in step S3, performing a charge/discharge test on the first sorted battery, determining a plurality of electrical property parameters, and counting a corresponding normal distribution map;
in step S4, the first sorted battery is classified according to the normal distribution map based on machine learning, and it is determined whether the first sorted battery is qualified.
In the embodiment of the invention, firstly, the change parameters of each battery to be measured after multiple measurements are carried out are effectively obtained; then, carrying out primary screening according to the variation parameters to ensure the accuracy of the primary screening; further, performing charge and discharge tests on the screened first sorted battery, determining various corresponding electrical property parameters, performing corresponding data statistics, and determining a corresponding normal distribution graph; and finally, intelligently classifying the normal distribution map based on machine learning, and quickly judging whether the normal distribution map is qualified.
As a preferred embodiment, referring to fig. 3, fig. 3 is a schematic flowchart of an embodiment of step S2 in fig. 2 provided by the present invention, where the step S2 specifically includes steps S21 to S24, where:
in step S21, acquiring the cell open-circuit voltage of each battery to be tested, and determining whether the cell open-circuit voltage meets a first preset condition;
in step S22, if the first preset condition is satisfied, performing a charge and discharge test on the battery to be tested within a preset time, determining the voltage change rate, and determining whether the voltage change rate satisfies a second preset condition, wherein a first difference value is determined according to a difference between a voltage at a charge and discharge start time and a voltage at a charge and discharge end time, and the voltage change rate is determined according to a quotient of the first difference value and the preset time;
in step S23, if the second preset condition is satisfied, determining whether the impedance value of the battery to be tested at multiple frequency points satisfies a third preset condition;
in step S24, if the third preset condition is satisfied, it is determined that the first sorted battery is the first sorted battery.
In the embodiment of the invention, the single open-circuit voltage, the voltage change rate and the impedance values in a plurality of frequency points are combined to be sequentially screened until the first sorting battery meeting all preset conditions is determined.
As a preferred embodiment, the first preset condition is that the cell open-circuit voltage is greater than or equal to a first preset voltage, or the cell open-circuit voltage is less than or equal to a second preset voltage;
the second preset condition is that the ratio of the voltage change rate to the change average value is larger than a first preset ratio, wherein the change average value is the average value of the voltage change rates of all the batteries to be tested meeting the first preset condition;
the third preset condition is that the ratio of the impedance value of each frequency point to the impedance average value is greater than a second preset ratio, wherein the impedance average value is the average value of the impedance values of all the batteries to be tested meeting the second preset condition in each frequency point.
In the embodiment of the invention, a first preset condition, a second preset condition and a third preset condition are set, whether the single open-circuit voltage, the voltage change rate and the impedance values in a plurality of frequency points are qualified or not is sequentially judged, and corresponding screening is carried out.
As a preferred embodiment, referring to fig. 4, fig. 4 is a schematic flowchart of an embodiment of step S3 in fig. 2 provided by the present invention, where the step S3 specifically includes steps S31 to S32, where:
in step S31, performing a constant current charge and discharge test according to the first sorted battery, and determining the coulomb efficiency and the energy efficiency that are correspondingly formed in the charge and discharge process;
in step S32, a corresponding normal distribution map is counted according to the coulomb efficiency and the energy efficiency.
In the embodiment of the invention, corresponding data statistics is carried out by combining coulomb efficiency and energy efficiency to obtain a normal distribution graph reflecting data statistical characteristics.
As a preferred embodiment, referring to fig. 5, fig. 5 is a schematic flowchart of an embodiment of step S32 in fig. 4 provided by the present invention, where the step S32 specifically includes steps S321 to S322, where:
in step S321, according to the coulomb efficiency, a corresponding coulomb normal distribution map is counted;
in step S322, a corresponding energy normal distribution map is counted according to the energy efficiency.
In the embodiment of the invention, the corresponding normal distribution diagram is counted according to the coulomb efficiency and the energy efficiency respectively, and the multi-aspect characteristics of the data are reflected.
As a preferred embodiment, referring to fig. 6, fig. 6 is a schematic flowchart of an embodiment of step S4 in fig. 2 provided by the present invention, where the step S4 specifically includes steps S41 to S43, where:
in step S41, inputting the coulomb normal distribution map to a first fully trained SVM network, and outputting a corresponding first classification label;
in step S42, inputting the energy normal distribution map to a second fully trained SVM network, and outputting a corresponding second classification label;
in step S43, it is determined whether the first sorted battery is qualified or not, based on the first sort label and the second sort label.
In the embodiment of the invention, different SVM networks are respectively utilized to identify and classify the coulomb normal distribution diagram and the energy normal distribution diagram, and the qualification of the first sorted battery is judged by combining the classification results of two times.
As a preferred embodiment, the first classification label includes a first qualified label and a first unqualified label, and the second classification label includes a second qualified label and a second unqualified label, and step S43 specifically includes:
and when the first classification label is a first qualified label and the second classification label is a second qualified label, the first sorted battery is qualified.
In the embodiment of the invention, when the two classifications are qualified, the first sorted battery can be judged to be qualified, so that the accuracy is ensured.
As a preferred embodiment, referring to fig. 7, fig. 7 is a schematic flowchart of an embodiment of a first SVM network training process provided in the present invention, and specifically includes steps S701 to S702, where:
in step S701, a sample set formed by a coulomb normal distribution map with labeling information is obtained, wherein the labeling information is a qualified label or an unqualified label of a battery to be tested corresponding to the coulomb normal distribution map;
in step S702, the sample set is input to the constructed first SVM network, and iterate until parameters converge, so as to form the first SVM network with complete training.
In the embodiment of the invention, the first SVM network is effectively trained by utilizing a sample set formed by the coulomb normal distribution diagram with the marking information.
As a preferred embodiment, referring to fig. 8, fig. 8 is a flowchart illustrating an embodiment of a second SVM network training process provided in the present invention, and specifically includes steps S801 to S802, where:
in step S801, a sample set formed by an energy normal distribution map with labeling information is obtained, wherein the labeling information is a qualified label or an unqualified label of a battery to be tested corresponding to the energy normal distribution map;
in step S802, the sample set is input to the constructed second SVM network, and iterate until parameters converge, thereby forming the second SVM network with complete training.
In the embodiment of the invention, the second SVM network is effectively trained by utilizing the sample set formed by the energy normal distribution diagram with the marking information.
An embodiment of the present invention further provides a lithium battery echelon utilization sorting device based on the eigenvalue analysis, and referring to fig. 9, fig. 9 is a schematic structural diagram of an embodiment of the lithium battery echelon utilization sorting device based on the eigenvalue analysis provided by the present invention, where the lithium battery echelon utilization sorting device 900 based on the eigenvalue analysis includes:
an obtaining unit 901, configured to obtain a variation parameter obtained after multiple measurements are performed on each battery to be tested;
the processing unit 902 is configured to perform a first screening on each battery to be tested according to the open-circuit voltage, and determine a first sorted battery; the first sorting battery is used for carrying out charging and discharging tests according to the first sorting battery, determining various electrical property parameters and counting a corresponding normal distribution graph;
and the sorting unit 903 is used for sorting the first sorted battery according to the normal distribution graph based on machine learning and judging whether the first sorted battery is qualified or not.
The more specific implementation manner of each unit of the lithium battery step utilization sorting device based on the characteristic numerical analysis can be referred to the description of the lithium battery step utilization sorting method based on the characteristic numerical analysis, and has similar beneficial effects, and details are not repeated herein.
The embodiment of the invention also provides a computer readable storage medium, on which a computer program is stored, and when the program is executed by a processor, the method for utilizing and sorting the lithium battery echelon based on the characteristic numerical analysis is realized.
Generally, computer instructions for carrying out the methods of the present invention may be carried using any combination of one or more computer-readable storage media. Non-transitory computer readable storage media may include any computer readable medium except for the signal itself, which is temporarily propagating.
A computer readable storage medium may be, for example, but not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination of the foregoing. More specific examples (a non-exhaustive list) of the computer readable storage medium would include the following: an electrical connection having one or more wires, a portable computer diskette, a hard disk, a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing. In the context of this document, a computer readable storage medium may be any tangible medium that can contain, or store a program for use by or in connection with an instruction execution system, apparatus, or device.
Computer program code for carrying out operations for aspects of the present invention may be written in any combination of one or more programming languages, including an object oriented programming language such as Java, Smalltalk, C + +, and conventional procedural programming languages, such as the "C" programming language or similar programming languages, and in particular may employ Python languages suitable for neural network computing and TensorFlow, PyTorch-based platform frameworks. The program code may execute entirely on the user's computer, partly on the user's computer, as a stand-alone software package, partly on the user's computer and partly on a remote computer or entirely on the remote computer or server. In the case of a remote computer, the remote computer may be connected to the user's computer through any type of network, including a Local Area Network (LAN) or a Wide Area Network (WAN), or the connection may be made to an external computer (for example, through the Internet using an Internet service provider).
The embodiment of the invention also provides computing equipment, which comprises a memory, a processor and a computer program which is stored on the memory and can run on the processor, wherein when the processor executes the program, the lithium battery echelon utilization sorting method based on the characteristic numerical analysis is realized.
According to the computer-readable storage medium and the computing device provided by the above embodiments of the present invention, the content specifically described in the above-described lithium battery echelon utilization sorting method based on the characteristic numerical analysis may be implemented with reference to the present invention, and the beneficial effects similar to the above-described lithium battery echelon utilization sorting method based on the characteristic numerical analysis are also provided, and are not described herein again.
The invention discloses a lithium battery echelon utilization sorting method and a device based on characteristic numerical analysis, wherein firstly, change parameters of each battery to be measured after multiple measurements are carried out are effectively obtained; then, carrying out primary screening according to the variation parameters to ensure the accuracy of the primary screening; further, performing charge and discharge tests on the screened first sorted battery, determining various corresponding electrical property parameters, performing corresponding data statistics, and determining a corresponding normal distribution graph; and finally, intelligently classifying the normal distribution map based on machine learning, and quickly judging whether the normal distribution map is qualified.
According to the technical scheme, based on the battery to be tested, various features are extracted, corresponding screening is carried out for multiple times, the accuracy and the reliability of battery sorting are guaranteed, machine learning is utilized, corresponding different features are effectively and rapidly classified and judged, mutual evidence is carried out, and the reliability is further improved.
The above description is only for the preferred embodiment of the present invention, but the scope of the present invention is not limited thereto, and any changes or substitutions that can be easily conceived by those skilled in the art within the technical scope of the present invention are included in the scope of the present invention.
Claims (10)
1. A lithium battery echelon utilization sorting method based on characteristic numerical analysis is characterized by comprising the following steps:
obtaining a change parameter obtained after measuring each battery to be measured for multiple times;
according to the change parameters, performing first screening on each battery to be tested to determine a first sorted battery;
performing charge and discharge tests according to the first sorted battery, determining various electrical property parameters, and counting a corresponding normal distribution graph;
and classifying the first sorted battery according to the normal distribution diagram based on machine learning, and judging whether the first sorted battery is qualified.
2. The echelon utilization sorting method for lithium batteries based on characteristic numerical analysis according to claim 1, wherein the variation parameters include cell open-circuit voltage, voltage variation rate and impedance value, and the first screening of each battery to be tested according to the variation parameters to determine a first sorted battery comprises:
acquiring the monomer open-circuit voltage of each battery to be tested, and judging whether the monomer open-circuit voltage meets a first preset condition;
if the first preset condition is met, performing charge and discharge tests on the battery to be tested within preset time, determining the voltage change rate, and judging whether the voltage change rate meets a second preset condition, wherein a first difference value is determined according to the difference between the voltage at the charge and discharge starting moment and the voltage at the charge and discharge ending moment, and the voltage change rate is determined according to the quotient of the first difference value and the preset time;
if the second preset condition is met, judging the impedance values of the battery to be tested in a plurality of frequency points, and judging whether the impedance values meet a third preset condition;
and if the third preset condition is met, judging that the battery is the first sorted battery.
3. The echelon utilization sorting method for lithium batteries based on the eigenvalue analysis of claim 2 wherein the first preset condition is that the cell open-circuit voltage is greater than or equal to a first preset voltage or the cell open-circuit voltage is less than or equal to a second preset voltage;
the second preset condition is that the ratio of the voltage change rate to the change average value is larger than a first preset ratio, wherein the change average value is the average value of the voltage change rates of all the batteries to be tested meeting the first preset condition;
the third preset condition is that the ratio of the impedance value of each frequency point to the impedance average value is greater than a second preset ratio, wherein the impedance average value is the average value of the impedance values of all the batteries to be tested meeting the second preset condition in each frequency point.
4. The echelon utilization sorting method for lithium batteries based on characteristic numerical analysis according to claim 1, wherein the electrical property parameters include coulombic efficiency and energy efficiency, and the step of performing a charge and discharge test according to the first sorted battery to determine a plurality of electrical property parameters and counting a corresponding normal distribution graph comprises:
performing constant-current charging and discharging tests according to the first sorted battery, and determining the coulombic efficiency and the energy efficiency which are correspondingly formed in the charging and discharging process;
and counting a corresponding normal distribution diagram according to the coulomb efficiency and the energy efficiency.
5. The lithium battery echelon utilization sorting method based on the eigenvalue analysis as recited in claim 4, wherein the counting of the corresponding normal distribution graph according to the coulomb efficiency and the energy efficiency comprises:
according to the coulomb efficiency, counting a corresponding coulomb normal distribution diagram;
and counting the corresponding energy normal distribution graph according to the energy efficiency.
6. The echelon utilization sorting method for lithium batteries based on eigenvalue analysis as recited in claim 5, wherein the step of classifying the first sorted battery according to the normal distribution graph based on machine learning to determine whether the first sorted battery is qualified comprises:
inputting the coulomb normal distribution diagram to a first SVM network with complete training, and outputting a corresponding first classification label;
inputting the energy normal distribution graph to a second SVM network which is completely trained, and outputting a corresponding second classification label;
and judging whether the first sorted battery is qualified or not according to the first sorting label and the second sorting label.
7. The echelon utilization sorting method for lithium batteries based on characteristic numerical analysis according to claim 6, wherein the first sorting label includes a first qualified label and a first unqualified label, the second sorting label includes a second qualified label and a second unqualified label, and the determining whether the first sorted battery is qualified according to the first sorting label and the second sorting label includes:
and when the first classification label is a first qualified label and the second classification label is a second qualified label, the first sorted battery is qualified.
8. The echelon utilization sorting method for lithium batteries based on feature numerical analysis as claimed in claim 6, wherein the training process of the well-trained first SVM network comprises:
acquiring a sample set formed by a coulomb normal distribution diagram with marking information, wherein the marking information is a qualified label or an unqualified label of a battery to be detected corresponding to the coulomb normal distribution diagram;
and inputting the sample set into the constructed first SVM network, and iterating until the parameters converge to form the first SVM network with complete training.
9. The echelon utilization sorting method for lithium batteries based on feature numerical analysis as claimed in claim 6, wherein the training process of the second SVM network with complete training comprises:
acquiring a sample set formed by an energy normal distribution diagram with marking information, wherein the marking information is a qualified label or an unqualified label of a battery to be detected corresponding to the energy normal distribution diagram;
and inputting the sample set into the constructed second SVM network, and iterating until the parameters converge to form the second SVM network with complete training.
10. The utility model provides a lithium cell echelon utilizes sorting unit based on characteristic numerical analysis which characterized in that includes:
the acquiring unit is used for acquiring change parameters obtained after each battery to be measured is measured for multiple times;
the processing unit is used for screening each battery to be tested for the first time according to the open-circuit voltage and determining a first sorted battery; the first sorting battery is used for carrying out charging and discharging tests according to the first sorting battery, determining various electrical property parameters and counting a corresponding normal distribution graph;
and the sorting unit is used for sorting the first sorted battery according to the normal distribution diagram based on machine learning and judging whether the first sorted battery is qualified or not.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111479576.7A CN113996564A (en) | 2021-12-02 | 2021-12-02 | Lithium battery echelon utilization and sorting method and device based on characteristic numerical analysis |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111479576.7A CN113996564A (en) | 2021-12-02 | 2021-12-02 | Lithium battery echelon utilization and sorting method and device based on characteristic numerical analysis |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN113996564A true CN113996564A (en) | 2022-02-01 |
Family
ID=79931377
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202111479576.7A Pending CN113996564A (en) | 2021-12-02 | 2021-12-02 | Lithium battery echelon utilization and sorting method and device based on characteristic numerical analysis |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113996564A (en) |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105728352A (en) * | 2016-03-30 | 2016-07-06 | 张家港绿锂动力技术有限公司 | Battery sorting method |
| CN107330474A (en) * | 2017-07-12 | 2017-11-07 | 北京科技大学 | A kind of lithium battery cascade utilization screening method |
| GB201906150D0 (en) * | 2019-05-02 | 2019-06-19 | Siemens Plc | A method and apparatus for detecting defective cells within a battery |
| CN111906036A (en) * | 2020-07-22 | 2020-11-10 | 上海快卜新能源科技有限公司 | Detection apparatus based on battery is utilized to echelon |
| CN113490556A (en) * | 2019-02-27 | 2021-10-08 | 锂工科技股份有限公司 | Method and system for intelligent battery collection, sorting and packaging |
-
2021
- 2021-12-02 CN CN202111479576.7A patent/CN113996564A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105728352A (en) * | 2016-03-30 | 2016-07-06 | 张家港绿锂动力技术有限公司 | Battery sorting method |
| CN107330474A (en) * | 2017-07-12 | 2017-11-07 | 北京科技大学 | A kind of lithium battery cascade utilization screening method |
| CN113490556A (en) * | 2019-02-27 | 2021-10-08 | 锂工科技股份有限公司 | Method and system for intelligent battery collection, sorting and packaging |
| GB201906150D0 (en) * | 2019-05-02 | 2019-06-19 | Siemens Plc | A method and apparatus for detecting defective cells within a battery |
| CN111906036A (en) * | 2020-07-22 | 2020-11-10 | 上海快卜新能源科技有限公司 | Detection apparatus based on battery is utilized to echelon |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107290679B (en) | The Intelligentized battery method for detecting health status of charging pile is shared for electric car | |
| CN113589189B (en) | Lithium battery health condition prediction method and device based on charging and discharging data characteristics | |
| CN113138340A (en) | Method for establishing battery equivalent circuit model and method and device for estimating state of health | |
| CN110161425A (en) | A kind of prediction technique of the remaining life divided based on lithium battery catagen phase | |
| CN111816936B (en) | Battery echelon utilization grouping method and system, terminal equipment and storage medium | |
| CN110031761B (en) | Battery screening method, battery screening device and terminal equipment | |
| CN115248393A (en) | Battery consistency sorting method, device, equipment and storage medium | |
| US20250085355A1 (en) | Method and system for monitoring hybrid energy storage state of battery based on big data processing | |
| CN117289167A (en) | Battery remaining life prediction method, device and medium based on multiple neural network | |
| CN114210604B (en) | Multi-characteristic echelon utilization power battery sorting method, device and storage medium | |
| CN115166532A (en) | Method and device for predicting capacity of nickel-metal hydride battery, electronic device and storage medium | |
| CN112084459A (en) | Method, device, electronic terminal, and storage medium for predicting battery charge-discharge cycle life | |
| CN118549840A (en) | A battery health status monitoring method, device, equipment and medium | |
| CN115656834A (en) | Battery capacity prediction method and device and electronic equipment | |
| CN115754726A (en) | Battery life prediction and maintenance method, electronic equipment and storage medium | |
| CN119087221A (en) | Evaluation model construction method, battery health status evaluation method, device and equipment | |
| CN115494396B (en) | Method, device, equipment and medium for evaluating performance of battery in service | |
| CN116027213A (en) | Decommissioned battery grouping method, device, electronic equipment and readable storage medium | |
| CN115902641A (en) | Method and device for predicting battery capacity diving and storage medium | |
| CN117148165B (en) | Testing and analyzing method and system for polymer lithium ion battery | |
| CN108629079A (en) | A kind of spacecraft lithium-ions battery group life cycle management health status evaluation method | |
| CN113996564A (en) | Lithium battery echelon utilization and sorting method and device based on characteristic numerical analysis | |
| CN117259262A (en) | Sorting method and device of power battery, electronic equipment and storage medium | |
| WO2025043869A1 (en) | Method and apparatus for testing aging performance of supercapacitor, device and storage medium | |
| CN115905720A (en) | A method for recommending equipment combination schemes for combat missions |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20220201 |