Method for automatic capacity grading recognition of secondary battery, electronic device, storage medium

Abstract

The application discloses a kind of for secondary battery automatic capacity recognition method, electronic equipment, storage medium, the method includes the following steps: S1, the waste battery package of recycling to storage warehouse is carried out database construction, carries out waste battery package traceability information coding class;S2, sensor network is arranged in storage warehouse;S3, real-time acquisition is in any area in the storage warehouse Abnormal data, and abnormal data is transmitted into database system, and safety prompt is warned;S4, under the premise that storage environment is guaranteed safety, on the traceability information of the single battery of gradient utilization, capacity mark is marked, and capacity mark is imported and constructs battery capacity system;S5, battery information is associated with database, and set capacity threshold range.The application solves the problem of low battery capacity disposal efficiency in the existing waste battery recycling process, simple operation, low cost, strong expandability, suitable for wide application.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of waste battery recycling and disposal, and particularly relates to a method for automatic capacity identification of secondary batteries, an electronic device and a storage medium. BACKGROUND

[0002] The statements in this section merely provide background information related to the present disclosure and do not necessarily constitute the prior art.

[0003] In today's society with insufficient primary energy and increasingly serious environmental problems, people's demand for new energy is increasing day by day. The application of new energy vehicles meets the requirements for sustainable development, but the power battery needs to be replaced after being used for 5-8 years because the battery storage is less than 80%, and cannot provide sufficient power source for the vehicle. In recent years, it has reached the peak of replacing the battery. If the lithium, cobalt, nickel and other materials contained in the battery can be recycled, it will have great economic value and resource conservation, but recycling the metals in the battery requires a complete industrial chain. Battery recycling is both the end of the industrial chain and the beginning of another industry. Battery manufacturers bear the responsibility of producing qualified batteries and cannot shoulder the full responsibility of battery recycling. There is a lack of representative large leading enterprises in the market. The ordinary battery processing process is as follows:

[0004] 1. Waste lithium ion battery package enters the field: the staff counts the number and records the original information of the battery package, such as the original application place, application time, current power status, etc.

[0005] 2. The waste lithium ion battery package enters the warehouse for storage.

[0006] 3. The waste battery package is discharged for disassembly and processing. After the battery package is disassembled, it is a number of single cells, and then the cells are treated differently, such as capacity detection, appearance detection, etc. The single cells that can be used in the gradient utilization enter the gradient utilization section, are arranged and sorted, and are re-packed according to the requirements of installing new battery packages to form new battery packages. After quality detection, it meets the factory qualified. However, many links in this process need to be counted manually, and the safety of the single cells after disassembly is not guaranteed, and there are unsafe factors. In addition, the number of batteries is large, and arranging too many personnel will also increase the investment cost, which is not conducive to the development of enterprises.

[0007] The Chinese invention patent with the patent publication number CN111709539A discloses a step-by-step utilization of power battery management method and system, which can solve the technical problems of low efficiency and low accuracy of existing power battery management mode. It includes the following steps executed by a computer device: obtaining battery information by reading the barcode on the shell of each waste power battery monomer; calculating the data detected in the container cabinet and classifying the battery according to the classification standard; after the classification of waste power battery is completed, the battery monomer that needs to be reassembled is reassembled and the corresponding information is recorded. The patent also discloses a method for detecting and classifying waste power batteries: for the function of detecting and classifying waste power batteries, relevant calculations are performed on the data detected in the container cabinet and the battery is classified according to the corresponding classification standard. Network connection and SQL database are used to centrally control multiple cabinets connected and centrally manage and analyze all data. However, the patent cannot solve the technical problems:

[0008] 1) When detecting the source and classifying the waste power battery, the influence of external environmental factors is not considered, and the safety is low. If the temperature, humidity and other factors outside the container cabinet exceed the normal standard range, it will affect the normal detection of the container cabinet. If abnormal phenomena (such as electrolyte leakage) occur during the source detection and classification detection of waste power batteries, monitoring and early warning cannot be performed.

[0009] 2) Only the source detection and classification detection of waste power battery monomers are performed, which is relatively cumbersome in actual operation.

[0010] 3) Although relevant calculations are performed on the data detected in the container cabinet and the battery is classified according to the corresponding classification standard, only one classification detection is performed. During the detection process, each monomer battery needs to be placed in the container cabinet, and preliminary classification detection is not performed on the battery pack. The detection efficiency is low, the detection time is long, and the battery container disposal benefit is low. SUMMARY

[0011] The present application provides a method for automatic container identification of secondary batteries, an electronic device and a storage medium to solve the problems in the background art. From the perspective of saving battery recycling cost and safety, the battery is subjected to secondary container identification detection, and the detection efficiency is more efficient.

[0012] The technical solution of the present application is as follows:

[0013] A method for automatic container identification of secondary batteries, comprising the following steps:

[0014] S1, the waste battery pack recovered to the storage warehouse is subjected to database construction, waste battery pack traceability information coding and classification;

[0015] S2, arranging a sensor network in the storage bin;

[0016] S3, performing data fusion processing on the sensor network in step S2, collecting abnormal data in any area of the storage bin in real time, and inputting the abnormal data into a database system to perform alarm safety prompt;

[0017] S4, under the premise of ensuring the safety of the storage environment, according to the completeness of the waste battery pack, marking the traceability information of the single battery in the gradient utilization, introducing and constructing the battery sorting system, and performing automatic sorting and utilization recommendation of the secondary battery;

[0018] S5, associating the battery information with the database in step S1, setting a sorting threshold range, and determining the next processing state of the battery.

[0019] Further optimize the technical scheme, the step S2 is based on the space structure of the storage bin, respectively with the bottom area and the height as the space constraint, along the length direction and the longitudinal direction Arranging a sensor network.

[0020] Further optimize the technical scheme, the sensor network includes one or more types of combination data fusion of humidity sensor, temperature sensor and light sensor.

[0021] Further optimize the technical scheme, the data fusion of the sensor network adopts the way of dynamic Kalman filtering.

[0022] Further optimize the technical scheme, in step S3, the abnormal data is obtained by comparing the difference and extreme change of humidity, temperature and position in any area of the storage bin with the standard data range value.

[0023] Further optimize the technical scheme, the step S4 includes the following steps:

[0024] S41, taking out the secondary battery in the storage bin, investigating the capacity, and recording the total capacity r of each battery pack and the capacity v of each single battery;

[0025] S42, establishing a battery automatic sorting algorithm to obtain a prediction model;

[0026] S43, taking the total capacity of the battery pack as a control group, and exploring the capacity prediction value model taking the battery pack as a unit;

[0027] S44, setting the threshold index of the classification application range through the parameter set of the classification model;

[0028] S45, the measured capacity data of the recycled secondary battery is introduced into the prediction model in step S42 and the capacity prediction value model in step S43 in the unit of battery pack, classification is obtained, and the battery number is fed back, so that the automatic processing process is realized.

[0029] Further optimize the technical scheme, the step S42 comprises the following steps:

[0030] S421, the measured capacity data of the single battery is recorded in the database and numbered as the training data set D of the model;

[0031] S422, a 3-layer multivariate time series neural network model is established according to the characteristics of the secondary battery; wherein the structure of the 3-layer time series neural network model is input layer, hidden layer and output layer, each layer of network is connected with parameters w and b, w represents weight, and b represents initial value:

[0032] f i (x,t)=w T x T t+b

[0033] S423, after connecting each layer of neural network, set the activation function;

[0034] S424, solve the parameter matrix (w T ,b) in the 3-layer multivariate time series neural network model, solve the optimal parameters w and b, and obtain the prediction model trained by the capacity of the secondary battery, wherein alpha represents the learning rate, and b' represents the b value update after gradient descent:

[0035]

[0036] F i (x,t)=w’ T x T t+b’。

[0037] Further optimize the technical scheme, the threshold index of the classification application range is set based on the battery utilization rate, and the threshold index of the classification application range includes waste treatment, repackaging and gradient use.

[0038] An electronic device comprising a processor and a memory; wherein the memory stores at least one instruction, the instruction is loaded and executed by the processor to realize the method for automatic capacity identification of secondary batteries.

[0039] A storage medium, the storage medium stores at least one instruction, the instruction is loaded and executed by the processor to realize the method for automatic capacity identification of secondary batteries.

[0040] By adopting the above technical scheme, the application has the following beneficial effects:

[0041] The present application collects original information of different types of batteries that need to be processed by using the Internet of Things technology from the perspective of saving battery recycling cost and safety. And according to the summarized information, the batteries are classified and put into the intelligent warehouse, and the self-checking and screening of the batteries can be realized in the intelligent warehouse. The battery is detected twice, and the detection efficiency is more efficient. The batteries in the intelligent warehouse can be packed and shipped again, and the unqualified products will be sent to the raw material factory for recycling of cobalt and nickel metals. Therefore, the present application has important significance for enterprise development and saving social resources.

[0042] The present application aims at the low efficiency of battery capacity distribution in the existing waste battery recycling process, and combines heuristic algorithm and Internet of Things technology to develop a method for monitoring safety hazards and pre-processing according to capacity in the waste battery processing process, which contains the use of sensors to monitor the environment of the battery storage warehouse after recycling, and the application of battery package classification to battery capacity distribution algorithm. The method is simple to operate, low in cost, strong in expandability, suitable for wide application, and can bring scale benefits to the current secondary battery recycling.

[0043] The present application traces battery information through the traceability idea, so that the subsequent processing accuracy is higher, the labor cost is reduced, and the battery information does not need to be found one by one by manual work.

[0044] The present application accurately arranges the sensor early warning network, refines the environmental abnormal alarm, reduces the maintenance labor cost and the complexity of management difficulty.

[0045] The present application determines the range of the utilization rate of the battery in the battery package based on the time sequence neural network and the multiple regression model, accurately classifies the use, and improves the utilization rate and the process benefit. BRIEF DESCRIPTION OF DRAWINGS

[0046] In order to more clearly illustrate the technical solutions in the embodiments of the present application or the prior art, the following will briefly introduce the drawings needed to be used in the embodiment or prior art description. Obviously, the drawings in the following description only some embodiments of the present application, and for those skilled in the art, other drawings can also be obtained without creative labor.

[0047] Figure 1 The execution flow diagram of the method for automatic capacity distribution recognition of the secondary battery of the present application;

[0048] Figure 2 The battery capacity distribution process diagram of the method for automatic capacity distribution recognition of the secondary battery of the present application. DETAILED DESCRIPTION

[0049] With reference to the accompanying drawings, the technical solutions in the embodiments of the present application will be clearly and completely described below, obviously, the described embodiments are only part of the embodiments of the present application, rather than all the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative work belong to the protection scope of the present application.

[0050] In the present application, the term "comprising", "containing" or any other variant thereof is intended to cover the non-exclusive inclusion, so that the process, method, article or equipment including a series of elements not only includes those elements, but also includes other elements not explicitly listed, or includes the elements inherent to such process, method, article or equipment. Without more limitation, the element defined by the sentence "including a…" does not exclude the presence of other identical elements in the process, method, article or equipment including the element.

[0051] A method for automatic capacity identification of secondary batteries, comprising the following steps:

[0052] S1, the initial product waste battery pack is imported, the waste battery pack recycled to the storage warehouse is constructed with a relational MySQL database, the waste battery pack traceability information coding is performed, and classification is performed.

[0053] The waste battery pack is more specifically a waste lithium ion battery pack, and can also be other types of waste battery pack, which is not limited here.

[0054] The waste battery pack traceability information coding information includes: battery pack source vehicle information (vehicle brand, production year), battery pack original production manufacturer, battery model (positive and negative electrode material), battery pack charge and discharge times, battery pack present power, storage time, shelf location, warehouse storage temperature and humidity.

[0055] The waste battery pack is classified according to the use category: mainly including power battery and 3C battery.

[0056] S2, the storage warehouse should have the functions of cooling, wind protection, rain protection, pollution prevention, prevention of electrolyte leakage, ventilation, etc., the function of real-time monitoring and early warning of the warehouse environment is required, to prevent fire or electrolyte leakage pollution, and each battery pack entering the warehouse is tracked and positioned, and the storage time, storage environment, etc. are recorded in detail.

[0057] In order to the space structure of the storage warehouse based on the present application, the sensor network is arranged along the length direction and the longitudinal direction with the bottom area and the height as the space constraints. More specifically, the sensor network is arranged every 1-3m along the length direction and 5-10cm longitudinally.

[0058] The sensor network comprises one or more types of combined data fusion of humidity sensors, temperature sensors and light sensors.

[0059] S3, the sensor network in step S2 is subjected to data fusion processing, real-time collection of abnormal data in any area of the storage bin is performed, and the abnormal data is transmitted into a database system to perform alarm safety prompting.

[0060] The data fusion of the sensor network (multi-scale sensor) adopts a dynamic Kalman filtering mode, and the detailed process is as follows:

[0061] The time sequence relationship of the system function is determined, the optimal estimation of the system state is performed through system input and output observation data by using a linear system state equation, wherein x t represents the sensor system state at time t, and exists in the form of a variable matrix, the matrix contains a plurality of sensor information to be fused, U t represents the sensor error affected by the system, ω k represents the process noise, y t represents the sensor reading value, v k represents the observation noise, and A, B and C are coefficient matrices.

[0062] x t =Ax t-1 +BU t +ω k

[0063] y t =Cx t +v k

[0064] Processing is performed based on a Kalman objective function, wherein, represents the filtered sensor data, represents the prior probability, K t represents the Kalman gain, z t represents the sensor state quantity, and H represents a coefficient matrix:

[0065]

[0066] Linear superposition calculation is performed on the system sensor data after filtering and noise reduction to obtain data after information.

[0067] The abnormal data is obtained by comparing the difference and extreme change of humidity, temperature and position in any area of the storage bin with the standard data range value, the normal range of the difference degree is 0.3-0.6 of the original position, and the abnormal data exceeding the range is transmitted into a database system to realize alarm safety prompting.

[0068] Standard data includes: temperature and humidity, wherein:

[0069] Temperature standard range (10℃ ~ 15℃), humidity standard range (20% ~ 30%).

[0070] S4, under the premise of ensuring the safety of the storage environment, that is, without alarm safety prompt when performing steps S2 and S3, the storage environment is ensured to be safe, and whether the waste battery pack can be used in stages is determined according to the completeness of the waste battery pack, that is, a capacity recognition is performed. The incomplete waste battery pack is rejected, and the battery pack that can be used in stages is retained. Among them, the judgment method of using in stages is as follows:

[0071] The capacity of the recycled battery is measured by professional instruments;

[0072] Compare with the database information of the recycled battery:

[0073] Set the stage utilization parameter D ∈ (0, 100%)

[0074]

[0075] D belongs to 0 ~ 40%, 40% ~ 60%, 60% ~ 100% three threshold ranges, respectively representing waste disposal, repackaging or gradient reduction.

[0076] After a capacity recognition, the traceability information of the single battery that can be used in stages is preliminarily judged, and a capacity mark is marked. The capacity mark is imported and constructed into a battery capacity system in the form of data, and a secondary battery automatic capacity recognition and utilization recommendation is performed. Among them, the secondary battery is a waste battery pack or a waste single battery.

[0077] Step S4 is realized by an application program of threshold calculation, including the following steps:

[0078] S41, take out the secondary battery in the storage warehouse, survey the capacity, and record the total capacity r of each battery pack and the capacity v of each single battery.

[0079] S42, establish a battery automatic capacity algorithm to obtain a prediction model. Step S42 includes the following steps:

[0080] S421, enter the measured capacity data of the single battery into the database and number it as the training data set D of the model.

[0081] S422, establish a 3-layer multivariate time series neural network model according to the characteristics of the secondary battery.

[0082] Wherein, the structure of the 3-layer time sequence neural network model is input layer, hidden layer and output layer, each layer of network is connected by parameters w and b, w represents weight, and b represents initial value:

[0083] f i (x,t)=w T x T t+b

[0084] S423, after connecting each layer of neural network, set the activation function, in particular, adopt Sigmoid activation function:

[0085]

[0086] S424, solve the parameter matrix (w T ,b) in 3-layer multivariate time sequence neural network model, solve the optimal parameters w and b by gradient descent method, and the prediction model obtained by training the secondary battery capacity, wherein, alpha represents learning rate, and b' represents b value update after gradient descent:

[0087]

[0088]

[0089] F i (x,t)=w’ T x T t+b’。

[0090] S43, the total capacity of the battery pack is taken as the control group, and the capacity prediction value model of the battery pack is explored.

[0091] S44, the parameter matrix (w T ,b T ) in the trained multivariate time sequence neural network is taken as the parameter set of the classification model, and the threshold index of the classification application range is set.

[0092] S45, the measured capacity data of the recovered secondary battery are imported into the above model, the classification is obtained, and the battery number is fed back, so that the automatic processing process is realized.

[0093] Repeat the above process.

[0094] S5, associate the battery information with the database in step S1, set the capacity threshold range, and determine the next processing state of the battery. Wherein, the threshold index of the classification application range is set based on the utilization rate of the battery. The threshold index of the classification application range is (x1-x n ), (y1-y n ), (z1-z n), including waste disposal, repackaging, gradient use. x, y, z respectively represent the capacity value of the current measured battery.

[0095] When x≤x1, the battery is disposed; x1≤x≤x n When x≥x n , the battery is used in gradient; and so on.

[0096] Specifically, the battery utilization rate is 0-40%, 40%-60%, and 60%-100%, which respectively corresponds to waste disposal, repackaging, or gradient use.

[0097] Embodiment 1

[0098] S1, the initial product waste lithium ion battery package is imported, and the waste batteries recovered to the storage warehouse are constructed with a relational MySQL database, and the battery package traceability information coding is performed, including: battery package vehicle information (vehicle brand, production year), battery package original production manufacturer, battery model (positive and negative electrode materials), battery package charge and discharge times, battery package current power, storage time, shelf location, warehouse storage temperature and humidity. Classified according to use category: mainly including power battery and 3C battery.

[0099] S2, based on the space structure of the storage warehouse, the space constraints are respectively the bottom area and the height, and the sensor network is arranged every 1m in the length direction and 5cm in the longitudinal direction.

[0100] S3, the multi-scale sensor in step S2 is subjected to data fusion processing, and the differences and extreme changes of humidity, temperature and position in a certain area in the storage warehouse are calibrated. The difference is subtracted from the standard value, and the normal range of the difference is 0.3-0.4 of the original position. The abnormal data exceeding the range is transmitted to the database system to realize the alarm safety prompt.

[0101] S4, under the premise of ensuring the safety of the storage environment, according to the battery package integrity, the capacity marking is marked on the traceability information of the single battery used in gradient utilization. The capacity marking is imported into the battery capacity marking system in the form of data, and the secondary battery automatic capacity marking recognition and utilization recommendation are realized by the threshold value calculation application program.

[0102] S5, the battery information is associated with the database in step S1, and the capacity marking threshold range is set. The battery utilization rate is 0-10%, 10%-40%, and 40%-90%, which respectively corresponds to waste disposal, repackaging, or gradient use.

[0103] Embodiment 2

[0104] S1, the initial product waste lithium ion battery pack enters the field, and the waste batteries recycled to the storage warehouse are constructed with a relational MySQL database, and the battery pack traceability information coding is performed, including: battery pack source vehicle information (vehicle brand, production year), battery pack original manufacturer, battery model (positive and negative electrode material), battery pack charge and discharge times, battery pack current power, storage time, shelf location, warehouse storage temperature and humidity. Classified according to use category: mainly including power battery and 3C battery.

[0105] S2, based on the space structure of the storage warehouse, the space constraints are respectively the bottom area and the height, and the sensor network is arranged every 2m along the length direction and every 6cm longitudinally.

[0106] S3, the multi-scale sensors in step S2 are subjected to data fusion processing, and the differences and extreme changes of humidity, temperature and position in a certain area of the storage warehouse are calibrated. The difference is subtracted from the standard value, and the difference within the normal range of 0.3-0.5 of the original position will be transmitted to the database system to realize the alarm safety prompt.

[0107] S4, under the premise of obtaining safety guarantee in the storage environment, according to the battery pack integrity, the traceability information of the single battery in the gradient utilization is marked, and the marking is introduced into the battery sorting system in the form of data. The application program realizes the automatic sorting identification and utilization recommendation of the secondary battery.

[0108] S5, the battery information is associated with the database in step S1, and the sorting threshold range is set. The battery utilization rate is 0-20%, 20%-50%, and 50%-80%, which respectively corresponds to the abandoned treatment, repackaging or gradient reduction.

[0109] Example 3

[0110] S1, the initial product waste lithium ion battery pack enters the field, and the waste batteries recycled to the storage warehouse are constructed with a relational MySQL database, and the battery pack traceability information coding is performed, including: battery pack source vehicle information (vehicle brand, production year), battery pack original manufacturer, battery model (positive and negative electrode material), battery pack charge and discharge times, battery pack current power, storage time, shelf location, warehouse storage temperature and humidity. Classified according to use category: mainly including power battery and 3C battery.

[0111] S2, based on the space structure of the storage warehouse, the space constraints are respectively the bottom area and the height, and the sensor network is arranged every 3m along the length direction and every 8cm longitudinally.

[0112] S3, the multi-scale sensor in step S2 is subjected to data fusion processing, the differences and extreme changes of humidity, temperature and position in a certain area in the storage bin are calibrated, and the differences are subtracted from the standard value, the normal range of the difference is 0.3-0.5 of the original position, and the abnormal data exceeding the range is transmitted into the database system to realize alarm safety prompt.

[0113] S4, under the premise that the storage environment is safe, according to the battery pack integrity, the traceability information of the single battery in the gradient utilization is marked, the marking is introduced into the battery sorting system in the form of data, and the application program of threshold calculation realizes automatic sorting identification and utilization recommendation of the secondary battery.

[0114] S5, the battery information is associated with the database in step S1, the sorting threshold range is set, the battery utilization rate is 0-30%, 30%-60% and 60%-90%, which respectively correspond to waste treatment, repackaging or gradient reduction.

[0115] Example 4

[0116] S1, the initial product waste lithium ion battery pack enters the market, the waste batteries recycled to the storage bin are constructed with a relational MySQL database, and the battery pack traceability information coding is performed, including: battery pack vehicle information (vehicle brand, production year), battery pack original manufacturer, battery model (positive and negative electrode material), battery pack charge and discharge times, battery pack present power, storage time, shelf position, warehouse storage temperature and humidity. According to the use category, it is classified into power battery and 3C battery.

[0117] S2, based on the space structure of the storage bin, the space is constrained by the bottom area and height, and the sensor network is arranged every 3m in length and 10cm in longitudinal direction.

[0118] S3, the multi-scale sensor in step S2 is subjected to data fusion processing, the differences and extreme changes of humidity, temperature and position in a certain area in the storage bin are calibrated, and the differences are subtracted from the standard value, the normal range of the difference is 0.4-0.5 of the original position, and the abnormal data exceeding the range is transmitted into the database system to realize alarm safety prompt.

[0119] S4, under the premise that the storage environment is safe, according to the battery pack integrity, the traceability information of the single battery in the gradient utilization is marked, the marking is introduced into the battery sorting system in the form of data, and the application program of threshold calculation realizes automatic sorting identification and utilization recommendation of the secondary battery.

[0120] S5, associate the battery information with the database in step S1, set the capacity threshold range, the battery utilization rate is 0-10%, 10%-50%, 50%-90% three threshold ranges, respectively corresponding to the abandoned treatment, repackaging or gradient use.

[0121] In conclusion, the application provides a method for automatic capacity identification of secondary batteries, which traces the battery recycling information to the battery capacity utilization recommendation process, and has good practicability and economy. In another aspect, the application also provides an electronic device comprising a processor and a memory; wherein the memory stores at least one instruction which is loaded and executed by the processor to implement the above method. The electronic device can have a large difference due to different configurations or performances, and can include one or more processors (central processing units, CPUs) and one or more memories, wherein the memory stores at least one instruction which is loaded and executed by the processor to implement the above method.

[0122] In another aspect, the application also provides a computer-readable storage medium, which stores at least one instruction which is loaded and executed by the processor to implement the above method. The computer-readable storage medium can be a ROM, a random access memory, a CD-ROM, a magnetic tape, a floppy disk, and an optical data storage device, etc. The instructions stored therein can be loaded and executed by the processor in the terminal to implement the above method.

[0123] Embodiments of the application are described with reference to flowcharts and / or block diagrams according to the method, terminal device (system), and computer program product of the embodiments of the application. It should be understood that each flow and / or block in the flowcharts and / or block diagrams, and the combination of the flows and / or blocks in the flowcharts and / or block diagrams can be implemented by computer program instructions. These computer program instructions can be provided to a general-purpose computer, embedded processor, or other programmable data processing terminal device to produce a machine, so that the instructions executed by the computer or other programmable data processing terminal device produce a device that implements the functions specified in the flowcharts and / or block diagrams. Figure 1 The functions specified in one flow or multiple flows and / or blocks Figure 1 The device that implements the functions specified in one flow or multiple flows and / or blocks.

[0124] These computer program instructions can also be stored in a computer-readable memory that can guide the computer or other programmable data processing terminal device to work in a specific way, so that the instructions stored in the computer-readable memory produce a product comprising instruction devices that implement the functions specified in the flowcharts and / or block diagrams. Figure 1 The functions specified in one flow or multiple flows and / or blocks Figure 1the functions specified in the flow block or blocks. These computer program instructions can also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer-implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flow block or blocks. Figure 1 the flow block or blocks and / or the functions specified in the flow block or blocks. Figure 1 the flow block or blocks and / or the functions specified in the flow block or blocks.

[0125] Those skilled in the art will further appreciate that the functionality of the examples described herein can be implemented in electronic hardware, computer software, or combinations of both. For purposes of illustration, the examples described herein are primarily described in terms of methods and algorithms implemented in computer software, although implementations in hardware, or combinations of hardware and software, are also possible. Any feature described herein as a software implemented alternative can be equivalently implemented in terms of hardware, and vice versa; any feature described herein as a software implemented alternative can be implemented in terms of hardware, and vice versa. The implementation details are left to the discretion of the designer, as is known in the art, and various implementation details should become apparent to those skilled in the art upon reading the above description. It is intended that the scope of the application be defined by the claims and not necessarily by the explicit description above. It will be appreciated that the above description is intended to be illustrative, and not restrictive. Many other implementations will be apparent to those skilled in the art in view of the above description.

[0126] The above description of disclosed embodiments provides examples, and is not intended to be limiting. Numerous alternatives will become apparent to those skilled in the art without departing from the scope of the present application. The scope of the present application encompasses any and all steps, features, compositions of matter, or implementations thereof described herein.

Claims

1. A method for automatic capacity grading and identification of secondary batteries, characterized by, It comprises the following steps: S1, the waste battery pack recovered into the storage bin is subjected to database construction, waste battery pack traceability information coding, and classification; S2, a sensor network is arranged in the storage bin; S3, the sensor network in step S2 is subjected to data fusion processing, real-time collection of abnormal data in any area of the storage bin, and transmission of the abnormal data into the database system for alarm safety prompt; S4, under the premise that the storage environment is ensured to be safe, according to the completeness of the waste battery pack, a capacity marking is made on the traceability information of the single battery in the gradient utilization, the capacity marking is introduced and a battery capacity marking system is constructed, and secondary battery automatic capacity marking identification and utilization recommendation are performed; the step S4 comprises the following steps: S41, the secondary battery in the storage bin is taken out, the capacity is surveyed, and the total capacity r of each battery pack and the capacity v of each single battery are recorded respectively; S42, a battery automatic capacity marking algorithm is established, and a prediction model is obtained; S43, the total capacity of the battery pack is taken as a control group, and a capacity prediction value model taking the battery pack as a unit is explored; S44, through the parameter set of the classification model, a threshold index of the classification application range is set; S45, the measured capacity data of the recycled secondary battery are introduced into the prediction model in step S42 and the capacity prediction value model taking the battery pack as a unit in step S43, classification is obtained, and the battery number is fed back, so that the automatic processing process is realized; S5, the battery information is associated with the database in step S1, the capacity marking threshold range is set, and the next processing state of the battery is determined.

2. The method for automatic sorting and identifying of secondary batteries according to claim 1, wherein The step S2 is based on the spatial structure of the storage bin, and the sensor network is arranged along the length direction and the longitudinal direction with the bottom area and the height as the space constraints.

3. The method for automatic sorting and identifying of secondary batteries according to claim 2, wherein The sensor network comprises one or more types of combined data fusion of humidity sensor, temperature sensor and light sensor.

4. The method for automatic sorting and identifying of secondary batteries according to claim 3, wherein The data fusion of the sensor network adopts a dynamic Kalman filtering mode.

5. The method for automatic sorting and identifying of secondary batteries according to claim 1, wherein In the step S3, the abnormal data are obtained by comparing the differences and extreme changes of humidity, temperature and position in any area of the storage bin with the standard data range value.

6. The method for automatic sorting and identifying of secondary batteries according to claim 1, wherein The threshold index of the classification application range is set based on the battery utilization rate, and the threshold index of the classification application range includes waste treatment, repackaging, and gradient use.

7. An electronic device, characterized by The storage medium stores at least one instruction, which is loaded and executed by the processor to realize the method for automatic capacity marking identification of secondary batteries according to any one of claims 1 to 6.

8. Storage medium, characterized in that The storage medium stores at least one instruction, which is loaded and executed by the processor to realize the method for automatic capacity marking identification of secondary batteries according to any one of claims 1 to 6.

Images