CN113783253A

CN113783253A - Automatic battery charging and replacing device

Info

Publication number: CN113783253A
Application number: CN202111006646.7A
Authority: CN
Inventors: 胡昭; 潘三博; 王旭; 李嫚; 张恒琦; 翟浩云
Original assignee: Shanghai Dianji University
Current assignee: Shanghai Dianji University
Priority date: 2021-08-30
Filing date: 2021-08-30
Publication date: 2021-12-10

Abstract

The invention relates to an automatic battery charging and replacing device, which comprises: the intelligent cabinet comprises a cabinet body, a controller, a charging system, a transmission system and a detection system; the cabinet body comprises a charging bin and a recovery bin, wherein the charging bins are arranged in a matrix form and used for accommodating batteries; the charging system is used for charging the battery in the charging bin; the conveying system comprises a placing plate, a carrier track, a power module, a taking and placing module and a positioning module, wherein the placing plate is used for placing the batteries, the taking and placing module is used for realizing the transfer of the batteries between the placing plate and the charging bin, the carrier track is matched with the placing plate, the power module is used for driving the placing plate to move on the carrier track, and the positioning module is used for realizing the positioning of the placing plate between the charging bins; the detection system comprises an image acquisition device and an identification model. Compared with the prior art, the battery is taken and placed in the charging bin by using the conveying system, a user does not need to manually transfer the battery, physical strength is saved, convenience is higher, more charging bins can be integrated in the cabinet body, and charging efficiency is higher.

Description

Automatic battery charging and replacing device

Technical Field

The invention relates to the technical field of battery charging management, in particular to an automatic battery charging and replacing device.

Background

A general charging station is in the form of a charging cabinet, a plurality of charging bins are arranged on a cabinet body, the charging bins are arranged in a matrix form from top to bottom and from left to right, a battery to be charged is placed into the charging bin for charging, and the charged battery is taken out from the charging bin, for example, an explosion-proof charging cabinet group for batteries is disclosed in chinese patent CN 201910811974.0. The user can open the door of the charging bin through a code scanning or card swiping mode to place the battery, and the battery which is charged is found out through a searching mode and taken out.

Because the battery has a certain weight, if the position of the charging bin is not appropriate, the user can hardly take and put the battery. Therefore, considering the height and physical strength of the user, the height and width of the charging cabinet are generally limited, one charging cabinet generally has 6 to 9 charging bins, the integration degree is low, and the supply requirement cannot be met, namely, the user may not find an empty bin to charge, or after the battery is fed into the charging bin to be charged, the charging cabinet does not have a battery which is completely charged, or the charging is difficult to realize that the charging is not waiting.

Disclosure of Invention

The invention aims to overcome the defects in the prior art and provide the automatic battery charging and replacing device, the batteries are taken and placed in the charging bin by using the conveying system, a user does not need to transfer the batteries manually, physical strength is saved, convenience is higher, more charging bins can be integrated in the cabinet body, and charging efficiency is higher.

The purpose of the invention can be realized by the following technical scheme:

the utility model provides an automatic electric installation that trades that fills of battery for treat the battery that charges, be provided with electronic tags on treating the battery that charges, includes: the intelligent cabinet comprises a cabinet body, a controller, a charging system, a transmission system and a detection system, wherein the controller is in communication connection with the charging system, the transmission system and the detection system;

the cabinet body comprises a plurality of charging bins and a recovery bin, and the charging bins are arranged in a matrix form and used for accommodating batteries; the charging system charges the battery in the charging bin based on a control command of the controller; the conveying system comprises a placing plate, a carrier track, a power module, a taking and placing module and a positioning module, wherein the placing plate is used for placing a battery, the taking and placing module realizes the transfer of the battery between the placing plate and a charging bin based on a control command of a controller, the carrier track is matched with the placing plate, the power module drives the placing plate to move on the carrier track based on the control command of the controller, and the positioning module is used for realizing the positioning of the placing plate between the charging bins;

the detection system comprises an image acquisition device and an identification model, wherein the image acquisition device is used for acquiring images of the battery on the placing plate, the identification model is a pre-trained machine learning model, the state detection result of the battery is output based on the images acquired by the image acquisition device, if the state of the battery meets the preset safety requirement, the battery on the placing plate is sent into the charging bin to be charged based on the control command of the controller, otherwise, the battery on the placing plate is sent into the recycling bin based on the control command of the controller.

Preferably, the cabinet body is made of waterproof materials.

Preferably, charging system includes battery management unit, power supply unit and a plurality of power supply interface, battery management unit and power supply unit and controller communication connection, battery management unit is used for acquireing the charged state of battery, power supply unit provides the power for each power supply interface, power supply interface arranges in the storehouse that charges, and power supply interface includes charging plug and adapter, charging plug is connected with the adapter electricity for charge to the battery.

Preferably, the battery management unit comprises a voltage acquisition module, a current acquisition module, a temperature detection module, a calculation module, a communication module and a storage module, wherein the voltage acquisition module, the current acquisition module and the temperature acquisition module are respectively used for acquiring voltage information, current information and temperature information of the battery, the calculation module estimates the SOC and SOH of the battery based on the voltage information, the current information and the temperature information, the communication module is used for realizing information transmission between the battery management unit and the controller, and the storage module is used for storing the voltage information, the current information, the temperature information and the SOC and SOH of the battery.

Preferably, in the calculation module, the estimation method for estimating the SOC and SOH of the battery is a double-extended kalman filter joint estimation based on a fractional order second-order RC equivalent circuit model, and the method has high accuracy and is closer to an actual value.

Preferably, the carrier track includes a conveyor belt and a slide rail, the placing plate moves horizontally on the conveyor belt under the driving of the power module, the conveyor belt moves up and down along the slide rail under the driving of the power module, the placing plate on the conveyor belt moves up and down along with the up-and-down movement of the conveyor belt, and the power module is a driving motor in communication connection with the controller.

Preferably, the cabinet body comprises a first area, a second area and a third area, the first area comprises a plurality of charging bins arranged in a matrix shape, the second area is arranged below the first area and comprises a recycling bin, the third area is arranged on the side edge of the first area and comprises a taking and placing opening, the taking and placing opening is used for taking and placing a battery, when the conveying belt and the taking and placing opening are at the same height, a path capable of allowing the battery to move is formed between the conveying belt and the taking and placing opening, and the image acquisition device is arranged at the taking and placing opening.

Preferably, the height of the taking and placing opening is designed according to the standard height of a human body.

Preferably, the taking and placing module is a mechanical push handle in communication connection with the controller, the battery is pulled into the charging bin from the placing plate, and the battery is pushed to the placing plate from the charging bin.

Preferably, the inside humidity probe that is equipped with of battery, humidity probe and controller communication connection to can judge whether the weeping takes place according to humidity probe's measured data in the charging process of battery, be equipped with buffer material in the recovery storehouse, the battery that falls can fall into the recovery storehouse safely.

Preferably, the positioning module is a laser module in communication connection with the controller, and includes a laser emitter and a plurality of laser receivers, the laser emitter is arranged on the placing plate, and the plurality of laser receivers are arranged on the cabinet body.

Preferably, the positioning module is a laser module in communication connection with the controller, and includes a plurality of laser transmitters and a laser receiver, the laser receiver is arranged on the placing plate, and the plurality of laser transmitters are arranged on the cabinet body.

Preferably, the identification model is a convolutional neural network, the convolutional neural network comprises a convolutional layer, a pooling layer and a full-connection layer, and the state detection result of the battery comprises a leakage and swelling state.

Preferably, the electronic tag records a unique identification ID number of the battery and main information of the battery, including a generation date, a place of production, and the like, so as to facilitate identification and management of the battery.

Compared with the prior art, the invention has the following beneficial effects:

(1) use conveying system to get the battery and put in the storehouse that charges, the user needn't manual transfer battery, has saved physical power, and the convenience is higher, and the cabinet body can be integrated more storehouse of charging, and charge efficiency is higher.

(2) Before the battery is charged, whether the problem of liquid leakage and bag expansion exists is judged in an image detection mode, and in the charging process of the battery, parameters such as voltage and current are monitored in real time through a battery management unit, so that the safety of the charging process is further improved.

(3) The battery management unit monitors by using a method of jointly estimating SOC and SOH by using double-extended Kalman filtering based on a fractional order second-order RC equivalent circuit model, so that the accuracy is higher and the method is closer to an actual value.

Drawings

FIG. 1 is a front view of the present invention;

FIG. 2 is a system control diagram of the present invention;

FIG. 3 is a schematic perspective view of the present invention;

FIG. 4 is a schematic perspective view of the present invention;

FIG. 5 is a circuit diagram of voltage acquisition in an embodiment;

FIG. 6 is a circuit diagram of a current collection circuit in an embodiment;

reference numerals: 1. the cabinet body, 101, the storehouse that charges, 102, retrieve the storehouse, 103, get and put mouthful, 2, the controller, 3, charging system, 301, battery management unit, 302, power supply unit, 4, conveying system, 401, power module, 402, get and put the module, 403, power module, 41, conveyer belt, 42, slide rail, 5, detecting system, 6, battery.

Detailed Description

The invention is described in detail below with reference to the figures and specific embodiments. The present embodiment is implemented on the premise of the technical solution of the present invention, and a detailed implementation manner and a specific operation process are given, but the scope of the present invention is not limited to the following embodiments.

In the drawings, structurally identical elements are represented by like reference numerals, and structurally or functionally similar elements are represented by like reference numerals throughout the several views. The size and thickness of each component shown in the drawings are arbitrarily illustrated, and the present invention is not limited to the size and thickness of each component. Parts are exaggerated in the drawing where appropriate for clarity of illustration.

Example 1:

an automatic battery charging and replacing device is used for charging a battery 6 to be charged, an electronic tag is arranged on the battery 6 to be charged, and the structure of the device is shown in fig. 1, fig. 2, fig. 3 and fig. 4, and the device comprises: the cabinet body 1, controller 2, charging system 3, conveying system 4 and detecting system 5, wherein, controller 2 and charging system 3, conveying system 4 and detecting system 5 communication connection.

As shown in fig. 3, the cabinet 1 includes a plurality of charging bins 101 and a recycling bin 102, the charging bins 101 are arranged in a matrix form and used for accommodating the batteries 6, and the cabinet 1 is made of a waterproof material;

the charging system 3 charges the battery 6 in the charging bin 101 based on the control command of the controller 2;

the conveying system 4 comprises a placing plate, a carrier track, a power module 401, a taking and placing module 402 and a positioning module 403, wherein the placing plate is used for placing the battery 6, the taking and placing module 402 realizes the transfer of the battery 6 between the placing plate and the charging bin 101 based on a control command of the controller 2, the carrier track is matched with the placing plate, the power module 401 drives the placing plate to move on the carrier track based on the control command of the controller 2, and the positioning module 403 is used for realizing the positioning of the placing plate between the charging bin 101; use conveying system to get the battery and put in the storehouse that charges, the user needn't shift battery 6 manually, has saved physical power, and the convenience is higher, and more storehouse 101 that charge can be integrated to the cabinet body 1, and charge efficiency is higher.

The detection system 5 comprises an image acquisition device and an identification model, the image acquisition device is used for acquiring images of the batteries 6 on the placing plate, the identification model is a pre-trained machine learning model, the state detection results of the batteries 6 are output based on the images acquired by the image acquisition device, if the states of the batteries 6 meet the preset safety requirements, the batteries 6 on the placing plate are sent into the charging bin 101 to be charged based on the control command of the controller 2, otherwise, the batteries 6 on the placing plate are sent into the recycling bin 102 based on the control command of the controller 2.

The charging system 3 comprises a battery management unit 301, a power supply unit 302 and a plurality of power supply interfaces, the battery management unit 301 and the power supply unit 302 are in communication connection with the controller 2, the battery management unit 301 is used for acquiring the charging state of the battery 6, the power supply unit 302 provides power for each power supply interface, the power supply interfaces are arranged in the charging bin 101, each power supply interface comprises a charging plug and an adapter, and the charging plug is electrically connected with the adapters and used for charging the battery 6.

The battery management unit 301 includes a voltage acquisition module, a current acquisition module, a temperature detection module, a calculation module, a communication module and a storage module, the voltage acquisition module, the current acquisition module and the temperature acquisition module are respectively used for acquiring voltage information, current information and temperature information of the battery 6, the calculation module estimates the SOC and SOH of the battery 6 based on the voltage information, the current information and the temperature information, the communication module is used for realizing information transmission between the battery management unit and the controller 2, and the storage module is used for storing the voltage information, the current information, the temperature information and the SOC and SOH of the battery 6.

In this embodiment, the controller 2 uses an STM32F103VET6 chip, the battery management unit 301 uses a BQ76930 chip, and a voltage acquisition circuit and a current acquisition circuit that are matched with the BQ76930 chip are shown in fig. 5 and 6. In fig. 5, CN2 is an interface terminal of a lithium ion battery, U4 is a BQ76930 chip, and voltage acquisition of multiple single power batteries can be realized by measuring an analog signal value of voltage through pins VC0-VC10 on the BQ76930 chip, and since an acquisition circuit of multiple power batteries is too large in space, only a small part of the acquisition circuit is cut out, and an AD converter inside the BQ76930 chip converts an analog signal into a digital signal and stores the digital signal in a register inside the chip for reading; in the same way as in fig. 6, the current is collected by using

pins

28 and 29 of the BQ76930 chip, namely SRP and SRN pins for detection, and the specific principle is that the voltage of the resistor terminals of R2 and R3 is measured, calculated according to kirchhoff's law, and then stored in a register inside the chip, so as to obtain the current magnitude.

The main working process of the fractional order extended Kalman is a process of continuously iterating by using a formula, firstly, corresponding parameters are initialized, secondly, the prior state is estimated, the prior error covariance and the parameters are updated, secondly, the Kalman output gain is calculated, lastly, the posterior state and the error covariance are updated, and finally, a calculation result is obtained by continuously repeating the process within the set sampling time. The principle of the double-extended Kalman filtering is mainly to use two EKFs, consider the aging of the power battery while estimating the state of the power battery, continuously predict and update the parameters of the power battery, and feed the update of the parameters back to the prediction of the state of the power battery, so that the actual condition of the power battery can be estimated more truly. In the calculation module, the estimation method for estimating the SOC and the SOH of the battery 6 is double-extension Kalman filtering joint estimation based on a fractional order second-order RC equivalent circuit model, and the method is high in accuracy and closer to an actual value.

The carrier track comprises a conveyor belt 41 and a slide rail 42, the placing plate moves horizontally on the conveyor belt 41 under the driving of the power module 401, the conveyor belt 41 moves up and down along the slide rail 42 under the driving of the power module 401, the placing plate on the conveyor belt 41 moves up and down along with the up-and-down movement of the conveyor belt 41, and the power module 401 is a driving motor in communication connection with the controller 2.

The cabinet body 1 comprises a first area, a second area and a third area, wherein the first area comprises a plurality of charging bins 101 arranged in a matrix shape, the second area is arranged below the first area and comprises a recovery bin 102, the third area is arranged on the side edge of the first area and comprises a taking and placing opening 103, the taking and placing opening 103 is used for taking and placing the battery 6, when the conveyor belt 41 and the taking and placing opening 103 are at the same height, a path for the battery 6 to move is formed between the conveyor belt 41 and the taking and placing opening 103, and the image acquisition device is arranged at the taking and placing opening 103. The height of the pick-and-place port 103 is designed according to the standard human height.

The taking and placing module 402 is a mechanical push handle in communication connection with the controller 2, pulls the battery 6 into the charging bin 101 from the placing plate, and pushes the battery 6 to the placing plate from the charging bin 101. In other embodiments, the pick-and-place module 402 may be configured as a robot or the like.

The positioning module 403 is a laser module communicatively connected to the controller 2, and includes a laser transmitter and a plurality of laser receivers, the laser transmitter is disposed on the placing board, and the plurality of laser receivers are disposed on the cabinet 1.

The positioning module 403 is a laser module communicatively connected to the controller 2, and includes a plurality of laser transmitters and a laser receiver, the laser receiver is disposed on the placing board, and the plurality of laser transmitters are disposed on the cabinet 1.

The recognition model is convolutional neural network, convolutional neural network includes convolution layer, pooling layer and full tie layer, but first layer convolution layer exclusive use, and the model size can be reduced to second floor pooling layer, improves the computational rate, improves the robustness simultaneously, and the influence that the full tie layer of third layer can reduce the characteristic position and bring to categorised, and battery 6's state detection result includes the weeping swell package state. The images of a plurality of batteries 6 in different states can be collected in advance, marked and used as a training set to train the convolutional neural network to obtain the recognition model. In the training process, an automatic stopping mode can be set by using an early stopping method, the marked samples are divided according to the proportion, and the marked samples are stopped when the performance of the convolutional neural network on the verification machine is reduced, so that overfitting caused by continuous training can be avoided. The recognition model can be arranged at the cloud end or locally in an off-line manner.

Because the position of the battery 6 at the taking and placing opening 103 is relatively fixed, the image acquisition device only needs to shoot the battery image at a fixed position, the later detection is actually the image classification problem, the convolutional neural network is adopted, the detection speed is high, the accuracy is high, the requirement can be met, the time consumption of the training process is controlled by an early stopping method, and the training cost is reduced.

The electronic tag records the unique identification ID number of the battery 6 and the main information of the battery 6, including the generation date, the place of production, and the like, so as to facilitate identification and management of the battery 6.

The humidity probe is arranged inside the battery 6 and is in communication connection with the controller 2, so that the leakage can be judged according to the measurement data of the humidity probe in the charging process of the battery 6, and the charging safety is further improved. A buffer material is also arranged in the recovery bin 102 to ensure that the fallen batteries 6 can safely fall into the recovery bin 102.

The controller 2 further comprises an input module and an output module, and is used for performing man-machine interaction, for a user, the battery 6 to be charged is placed into the taking and placing port 103, the battery 6 is taken out from the taking and placing port 103, and man-machine interaction including payment, recharging and other operations is performed through modes such as a touch screen.

When a user puts the battery 6 into the taking and placing opening 103, the image acquisition device at the taking and placing opening 103 acquires an image of the battery 6, the identification module quickly judges whether the battery 6 has an appearance-recognizable fault such as bag swelling, liquid leakage and the like, and if so, the battery 6 is directly sent into the recovery bin 102. The recycling bin 102 is arranged at the bottom of the cabinet body 1, can be sent into the recycling bin 102 by the conveying system 4, and can also be directly pushed down to the recycling bin 102, and a buffer material is arranged in the recycling bin 102, so that the damage of the battery 6 can be avoided.

If the detection system 5 does not detect a fault, an idle charging bin 101 is searched, a variable d may be set for each charging bin 101 in programming, the variable is 0 if the charging bin 101 is idle, the variable is 1 if a battery is in the charging bin 101, and a variable may be further set to identify the amount of electricity of the battery 6 in the charging bin 101. Since the charging bins 101 are arranged in a matrix form, the carrier track in the conveying system 4 comprises the horizontal conveying belt 41 and the vertical sliding rail 42, the empty charging bin 101 can be found from the left to the right from the position of the conveying belt 41, or one charging bin 101 can be found according to other modes, then the conveying belt 41 and/or the sliding rail 41 are driven by the power module 401, the placing plate is conveyed to the empty charging bin 101, the positioning module 402 is used for positioning in the process, and the battery 6 is conveyed into the charging bin 101 from the placing plate by the taking and placing module 401.

In the charging process, the power supply unit 302 controls the power supply of each charging bin 101, the battery management unit 301 detects the voltage, the current and the like of the charged battery 6, and the controller 2 can be further provided with a balancing module to control the balancing of each battery 6, prevent overcharging and ensure the balancing of the battery 6 in the charging process.

The foregoing detailed description of the preferred embodiments of the invention has been presented. It should be understood that numerous modifications and variations could be devised by those skilled in the art in light of the present teachings without departing from the inventive concepts. Therefore, the technical solutions available to those skilled in the art through logic analysis, reasoning and limited experiments based on the prior art according to the concept of the present invention should be within the scope of protection defined by the claims.

Claims

1. The utility model provides an automatic electric installation that trades that charges of battery for treating battery (6) that charges is provided with electronic tags on treating battery (6) that charges, its characterized in that includes: the intelligent cabinet comprises a cabinet body (1), a controller (2), a charging system (3), a transmission system (4) and a detection system (5), wherein the controller (2) is in communication connection with the charging system (3), the transmission system (4) and the detection system (5);

the cabinet body (1) comprises a plurality of charging bins (101) and a recovery bin (102), wherein the charging bins (101) are arranged in a matrix form and used for accommodating batteries (6); the charging system (3) charges the battery (6) in the charging bin (101) based on a control command of the controller (2); the conveying system (4) comprises a placing plate, a carrier track, a power module (401), a taking and placing module (402) and a positioning module (403), wherein the placing plate is used for placing the battery (6), the taking and placing module (402) realizes the transfer of the battery (6) between the placing plate and the charging bin (101) based on a control command of the controller (2), the carrier track is matched with the placing plate, the power module (401) drives the placing plate to move on the carrier track based on the control command of the controller (2), and the positioning module (403) is used for realizing the positioning of the placing plate between the charging bin (101);

the detection system (5) comprises an image acquisition device and an identification model, wherein the image acquisition device is used for acquiring images of the battery (6) on the placing plate, the identification model is a pre-trained machine learning model, the state detection result of the battery (6) is output based on the images acquired by the image acquisition device, if the state of the battery (6) meets the preset safety requirement, the battery (6) on the placing plate is sent into the charging bin (101) to be charged based on the control command of the controller (2), otherwise, the battery (6) on the placing plate is sent into the recycling bin (102) based on the control command of the controller (2).

2. The automatic battery charging and replacing device according to claim 1, wherein the charging system (3) comprises a battery management unit (301), a power supply unit (302) and a plurality of power supply interfaces, the battery management unit (301) and the power supply unit (302) are in communication connection with the controller (2), the battery management unit (301) is used for acquiring the charging state of the battery (6), the power supply unit (302) provides power for each power supply interface, the power supply interfaces are arranged in the charging chamber (101), each power supply interface comprises a charging plug and an adapter, and the charging plug is electrically connected with the adapter and used for charging the battery (6).

3. The device for automatically charging and replacing the battery as claimed in claim 2, wherein the battery management unit (301) comprises a voltage acquisition module, a current acquisition module, a temperature detection module, a calculation module, a communication module and a storage module, the voltage acquisition module, the current acquisition module and the temperature acquisition module are respectively used for acquiring voltage information, current information and temperature information of the battery (6), the calculation module estimates the SOC and SOH of the battery (6) based on the voltage information, the current information and the temperature information, the communication module is used for realizing information transmission between the battery management unit and the controller (2), and the storage module is used for storing the voltage information, the current information, the temperature information and the SOC and SOH of the battery (6).

4. The device as claimed in claim 3, wherein in the calculation module, the estimation method for estimating the SOC and SOH of the battery (6) is a double-extended Kalman filter joint estimation based on a fractional order second order RC equivalent circuit model.

5. The automatic battery charging and replacing device as claimed in claim 1, wherein the carrier track comprises a conveyor belt (41) and a slide rail (42), the placing plate moves horizontally on the conveyor belt (41) under the driving of the power module (401), the conveyor belt (41) moves up and down along the slide rail (42) under the driving of the power module (401), the placing plate on the conveyor belt (41) moves up and down along with the up and down movement of the conveyor belt (41), and the power module (401) is a driving motor in communication connection with the controller (2).

6. The automatic battery charging and replacing device as claimed in claim 5, wherein the cabinet body (1) comprises a first area, a second area and a third area, the first area comprises a plurality of charging bins (101) arranged in a matrix shape, the second area is arranged below the first area and comprises a recycling bin (102), the third area is arranged at a side of the first area and comprises a taking and placing opening (103), the taking and placing opening (103) is used for taking and placing the battery (6), when the conveyor belt (41) and the taking and placing opening (103) are at the same height, a path for the battery (6) to move is formed between the conveyor belt (41) and the taking and placing opening (103), and the image acquisition device is arranged at the taking and placing opening (103).

7. The automatic battery charging and replacing device as claimed in claim 1, wherein the taking and placing module (402) is a mechanical push handle communicatively connected with the controller (2), the battery (6) is pulled into the charging bin (101) from the placing board, and the battery (6) is pushed to the placing board from the charging bin (101).

8. The automatic battery charging and replacing device as claimed in claim 1, wherein the positioning module (403) is a laser module communicatively connected with the controller (2), and comprises a laser emitter and a plurality of laser receivers, the laser emitter is arranged on the placing board, and the plurality of laser receivers are arranged on the cabinet body (1).

9. The automatic battery charging and replacing device as claimed in claim 1, wherein the positioning module (403) is a laser module communicatively connected with the controller (2), and comprises a plurality of laser transmitters and a laser receiver, the laser receiver is arranged on the placing board, and the plurality of laser transmitters are arranged on the cabinet body (1).

10. The automatic battery charging and replacing device as claimed in claim 1, wherein the identification model is a convolutional neural network, the convolutional neural network comprises a convolutional layer, a pooling layer and a full-connection layer, and the state detection result of the battery (6) comprises a leakage and swelling state.