Preparation method and system of sodium ion battery positive electrode material

Through state recognition model and deep learning technology, the uniformity of the positive electrode material of sodium ion battery is quickly judged, which solves the problem of low preparation efficiency in the prior art, and realizes an efficient preparation process for the positive electrode material of sodium ion battery.

CN119079961AInactive Publication Date: 2024-12-06JIANGSU FENGLEI NEW ENERGY TECHNOLOGY CO LTD
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202411047465.2
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-08-01
Publication Date
2024-12-06
Estimated Expiration
Not applicable · inactive patent

AI Technical Summary

Technical Problem

In the prior art, the method of extending the mixing time during the preparation of the positive electrode material of sodium ion battery in the prior art leads to slow preparation efficiency and the inability to quickly obtain uniformly mixed raw materials.

Method used

The state recognition model combined with deep learning technology is used to determine whether the raw materials are mixed uniformly through the image recognition model, including the YOLO-v5 network, the GAM attention module and the three-dimensional weight generation module. Quickly identify and confirm that the mixing is evenly mixed, and then the mixing operation is stopped and the ball mill is used. and calcination steps optimize material handling.

Benefits of technology

It significantly saves mixing time, improves preparation efficiency, ensures the uniformity and quality of the positive electrode material of sodium ion battery, and shortens the overall preparation process.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN119079961A_ABST
    Figure CN119079961A_ABST
Patent Text Reader

Abstract

The invention provides a sodium ion battery positive electrode material preparation method and system, and the method comprises the steps: screening raw materials, mixing the raw materials, and using a state recognition model to judge whether the raw materials are uniformly mixed; adding the uniformly mixed materials into a reaction container containing absolute ethyl alcohol, then putting the materials into a ball mill for ball milling for 2-6 hours, and then putting the mixed materials into a vacuum drying box for 10-12 hours; after drying is completed, putting the mixed material into a tubular furnace, heating to 320-400 DEG C in an inert gas environment, and calcining for 8-14 hours; after the calcination is finished, mixing the material with cane sugar, then carrying out mixed ball milling, and after the ball milling is finished, drying in a drying box for 10-12 hours; after drying, putting a sample into a tubular furnace, in an inert gas environment, raising the temperature to 560-660 DEG C, and calcining for 6-14 hours; by introducing the state recognition model, whether the raw materials are uniformly mixed or not can be efficiently and quickly judged, the mixing time can be effectively saved, and the preparation efficiency is improved.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present invention belongs to the technical field of battery preparation, and more specifically, relates to a method and system for preparing a positive electrode material for a sodium ion battery. Background Art

[0002] In recent years, countries around the world have been accelerating the development of renewable energy and new energy vehicle industries to cope with the increasingly serious energy crisis and environmental problems. In this process, electrochemical energy storage technology represented by rechargeable batteries with high flexibility, low cost and environmental friendliness has played a vital role. Among them, lithium-ion batteries with high energy density and long service life have been widely used in energy storage and new energy vehicles. However, limited lithium resources restrict the large-scale application of lithium-ion batteries. Therefore, sodium-ion batteries with low cost, high safety and sustainability can play an important role in large-scale energy storage and low-speed electric vehicles. The selection of sodium-ion battery positive electrode materials directly affects the quality of lithium-ion batteries.

[0003] The positive electrode material of sodium ion battery needs to be prepared. It is very necessary to fully mix the raw materials during the preparation process, which directly affects the quality of the positive electrode material of sodium ion battery. In the prior art, the method of extending the mixing time is usually adopted to obtain uniformly mixed raw materials, which leads to an increase in the time of the entire preparation process and the problem of slow preparation efficiency. Summary of the invention

[0004] The object of the present invention is to provide a method and system for preparing a positive electrode material for a sodium ion battery, aiming to solve the technical problem that the method of prolonging the mixing time to obtain uniformly mixed raw materials in the prior art has low preparation efficiency.

[0005] To achieve the above object, the technical solution adopted by the present invention is: to provide a method for preparing a positive electrode material for a sodium ion battery, comprising the following steps:

[0006] Step S1, screening raw materials, mixing the raw materials, and using a state recognition model to determine whether the raw materials are mixed uniformly;

[0007] Step S2, adding the uniformly mixed materials into a reaction container containing anhydrous ethanol, and then placing the mixture in a ball mill for 2-6 hours, and then placing the mixture in a vacuum drying oven for 10-12 hours;

[0008] Step S3, after drying is completed, the mixed material is placed in a tube furnace and heated to 320-400° C. in an inert gas environment for calcination for 8-14 hours;

[0009] Step S4, after the calcination is completed, the material is mixed with sucrose, and then the mixed material is ball-milled. After the ball-milling is completed, the mixed material is placed in a drying oven for 10-12 hours;

[0010] Step S5: After drying, the sample is placed in a tubular furnace under an inert gas environment, heated to 560-660°C and calcined for 6-14 hours.

[0011] Preferably, the screening of raw materials, mixing the raw materials, and using a state recognition model to determine whether the raw materials are uniformly mixed include:

[0012] Weigh ferrous oxalate crystals, lithium carbonate, manganese acetate and ammonium dihydrogen phosphate according to a preset ratio;

[0013] Mixing ferrous oxalate crystals, lithium carbonate, manganese acetate and diammonium phosphate;

[0014] The state recognition model is used to determine whether the raw materials are mixed evenly.

[0015] Preferably, judging whether the raw materials are uniformly mixed by the state recognition model includes:

[0016] The collected mixed image is preprocessed; the mixed image includes raw materials that are uniformly mixed;

[0017] The preprocessed experimental image is input as a sample into a deep learning model for training to obtain an image recognition model, wherein the image recognition model includes: a YOLO-v5 network, a GAM attention module, and a three-dimensional weight generation module; the GAM attention module is introduced into the YOLO-v5 network; the three-dimensional weight generation module is introduced into the YOLO-v5 network to obtain true three-dimensional weights and enhance the network's ability to focus on key features.

[0018] The target image is input into the image recognition model to determine whether it is mixed uniformly.

[0019] Preferably, the GAM attention module includes the following formula:

[0020]

[0021] Among them, M t Represents the weight coefficient of the channel attention module; M k represents the weight coefficient of the spatial attention module; F1 represents the input feature; F1 represents the input feature; F3 represents the output feature.

[0022] Preferably, the collected mixed image is preprocessed, including segmenting the image using an image segmentation model; the image segmentation model includes: a UNet++ network and an additive loss function; the additive loss function is used in the UNet++ network; the expression formula of the additive loss function is:

[0023]

[0024] Where N represents the total number of pixels; g i represents the probability of annotation; p i represents the predicted probability; λ represents a constant, ranging from 0.4 to 0.6.

[0025] Preferably, the three-dimensional weight generation module includes an energy function of a neuron:

[0026]

[0027] Among them, ε t Indicates calculating the average value of all neurons in this channel except t; Indicates calculating the variance of all neurons in the channel except t; t, x i Respectively represent the input features X = R c×h×w The target neuron and other neurons in a single channel of ; i represents the index and on the spatial dimensions; M = h × w represents the number of neurons on the channel.

[0028] Preferably, the raw materials include: ferrous oxalate crystals, lithium carbonate, manganese acetate and diammonium phosphate.

[0029] The present invention also provides a system for preparing a positive electrode material for a sodium ion battery, comprising:

[0030] A mixing component is used to screen raw materials, mix the raw materials, and use a state recognition model to determine whether the raw materials are mixed uniformly; the raw materials include: ferrous oxalate crystals, lithium carbonate, manganese acetate, and diammonium phosphate;

[0031] The first ball milling assembly is used to add the uniformly mixed materials into a reaction vessel containing anhydrous ethanol, and then put them into a ball mill for high-energy ball milling for 2-6 hours, and then put the mixed materials into a vacuum drying oven for 10-12 hours;

[0032] The first calcination component is used to place the mixed material in a tube furnace after drying is completed, and heat it to 320-400°C in an inert gas environment for calcination for 8-14 hours;

[0033] The second ball milling assembly is used to wait until the calcination is completed, then mix the material with sucrose, and then perform mixed ball milling. After the ball milling is completed, the material is placed in a drying oven for drying for 10-12 hours;

[0034] The second calcination component, after drying, the sample is placed in a tube furnace in an inert gas environment, heated to 560-660°C and calcined for 6-14 hours.

[0035] An electronic device comprises a bus, a transceiver, a memory, a processor and a computer program stored in the memory and executable on the processor, wherein the transceiver, the memory and the processor are connected via the bus, and wherein the computer program, when executed by the processor, implements the steps in the method for preparing a positive electrode material for a sodium ion battery as described in any one of the above items.

[0036] A computer-readable storage medium having a computer program stored thereon, characterized in that when the computer program is executed by a processor, the steps in the method for preparing a sodium ion battery positive electrode material as described in any one of the above items are implemented.

[0037] The beneficial effect of the method and system for preparing a positive electrode material for a sodium ion battery provided by the present invention is that: compared with the prior art, the method and system for preparing a positive electrode material for a sodium ion battery provided by the present invention can efficiently and quickly judge whether the raw materials are mixed evenly through the introduction of a state recognition model, can effectively save mixing time, and improve preparation efficiency. In the state recognition model, the raw material area is first identified, and then the image recognition model is used for identification. When it is detected that the gap size between the raw materials after mixing meets the preset conditions, it can be determined that it is in a uniformly mixed state, and the mixing operation can be stopped to enter the next preparation process. BRIEF DESCRIPTION OF THE DRAWINGS

[0038] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0039] Figure 1 A flowchart of a method for preparing a positive electrode material for a sodium ion battery provided in an embodiment of the present invention;

[0040] Figure 2 A structural block diagram of a system for preparing a positive electrode material for a sodium ion battery provided in an embodiment of the present invention. DETAILED DESCRIPTION

[0041] In order to make the technical problems, technical solutions and beneficial effects to be solved by the present invention more clearly understood, the present invention is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present invention and are not intended to limit the present invention.

[0042] Please also read Figure 1 to Figure 2 Now, a method for preparing a positive electrode material for a sodium ion battery provided by the present invention is described. The method for preparing a positive electrode material for a sodium ion battery comprises the following steps:

[0043] Step S1, screening raw materials, mixing the raw materials, and using a state recognition model to determine whether the raw materials are uniformly mixed. The raw materials include: ferrous oxalate crystals, lithium carbonate, manganese acetate, and diammonium phosphate;

[0044] In this step, ferrous oxalate crystals, lithium carbonate, manganese acetate and ammonium dihydrogen phosphate are weighed according to the molar ratio of Mn:Fe=A:1-A. Ferrous oxalate crystals are a light yellow crystalline powder; lithium carbonate is a white powder; manganese acetate is a light red transparent monoclinic crystal; and ammonium dihydrogen phosphate is a white crystal.

[0045] The implementation process of step S1 includes:

[0046] Step S1.1, weighing ferrous oxalate crystals, lithium carbonate, manganese acetate and ammonium dihydrogen phosphate according to a preset ratio;

[0047] Step S1.2, mixing ferrous oxalate crystals, lithium carbonate, manganese acetate and diammonium phosphate;

[0048] Step S1.3: Determine whether the raw materials are mixed uniformly through the state recognition model.

[0049] The implementation process of step S1.3 includes:

[0050] Step S1.3.1, the collected mixed image is preprocessed. The mixed image is a color image of the raw materials mixed evenly;

[0051] In this step, the mixed image is preprocessed by segmenting the image to obtain the characteristics of the uniformly mixed raw materials. The mixed image includes a raw material color image and a background. By segmenting the image and extracting the characteristics of the uniformly mixed raw materials, the accuracy of raw material recognition can be improved.

[0052] In this step, an image segmentation model is used to segment the image; the image segmentation model includes: a UNet++ network and an additive loss function; the additive loss function is used in the UNet++ network; the expression formula of the additive loss function is:

[0053]

[0054] Where N represents the total number of pixels; g i represents the probability of annotation; p i represents the predicted probability; λ represents a constant, ranging from 0.4 to 0.6, preferably 0.5.

[0055] The image segmentation model provided by the present invention has clear boundary divisions for the segmentation results, and can accurately segment the target object from the background.

[0056] Step S1.3.2, input the preprocessed experimental image as a sample into the deep learning model for training to obtain an image recognition model, wherein the image recognition model includes: a YOLOv5 network, a GAM attention module, and a three-dimensional weight generation module; the GAM attention module is introduced into the YOLOv5 network; the three-dimensional weight generation module is introduced into the YOLOv5 network to obtain true three-dimensional weights and enhance the network's ability to focus on key features.

[0057] In this step, the GAM attention module is introduced into the Backbone part and Neck part of the YOLO-v5 network structure.

[0058] The GAM attention module includes the following formula:

[0059]

[0060] Among them, M t Represents the weight coefficient of the channel attention module; M k represents the weight coefficient of the spatial attention module; F1 represents the input feature; F1 represents the input feature; F3 represents the output feature.

[0061] M t The acquisition method is: permute the input of dimension C×W×H to W×H×C through three-dimensional channel permutation, then amplify the cross-dimensional channel-space dependency through a double-layer MLP, and finally obtain the weight coefficient through the activation function.

[0062] M k The acquisition method is: after inputting the features, the channels are rearranged first. The channels are reduced by a 7*7 convolutional layer with a reduction rate of r to extract the spatial common key feature information, and then a 7*7 convolutional layer is used to restore the number of feature channels, and finally the weight coefficient is obtained through the activation function.

[0063] In this step, the pooling layer in the YOLOv5 network introduces a three-dimensional weight generation module.

[0064] The three-dimensional weight generation module includes the energy function of the neuron:

[0065]

[0066] Among them, ε t Indicates calculating the average value of all neurons in this channel except t; Indicates calculating the variance of all neurons in the channel except t; t, x i Respectively represent the input features X = R c×h×w The target neuron and other neurons in a single channel of ; i represents the index and on the spatial dimensions; M = h × w represents the number of neurons on the channel.

[0067] Step S1.3.3: input the target image into the image recognition model to determine whether it is mixed evenly.

[0068] The state recognition model provided by the present invention can better capture the detailed information of the gaps between the raw materials, and then determine whether the raw materials are mixed evenly, and can complete the recognition operation efficiently and accurately.

[0069] Step S2, adding the uniformly mixed materials into a reaction vessel containing anhydrous ethanol, and then placing the mixture in a ball mill for high-energy ball milling for 2-6 hours, and then placing the mixture in a vacuum drying oven for 10-12 hours;

[0070] Step S3, after drying is completed, the mixed material is placed in a tube furnace and heated to 320-400° C. in an inert gas environment for calcination for 8-14 hours;

[0071] In this step, nitrogen is preferably used as the inert gas.

[0072] Step S4, after the calcination is completed, the material is mixed with sucrose, and then the mixed material is ball-milled. After the ball-milling is completed, the mixed material is placed in a drying oven for 10-12 hours;

[0073] Step S5: After drying, the sample is placed in a tubular furnace under an inert gas environment, heated to 560-660°C and calcined for 6-14 hours.

[0074] Example 1

[0075] The raw materials are screened, mixed evenly, and a state recognition model is used to determine whether the raw materials are evenly mixed; the raw materials are ferrous oxalate crystals, lithium carbonate, manganese acetate, and diammonium phosphate.

[0076] The uniformly mixed materials were added into a reaction vessel containing anhydrous ethanol, and then placed into a ball mill for high-energy ball milling for 3 h. The mass ratio of the added materials to the balls was 1:10.

[0077] After ball milling, the mixture was placed in a vacuum drying oven at 80 °C for 12 h.

[0078] After drying, the mixture was placed in a tube furnace and heated to 350°C for calcination for 10 hours under nitrogen.

[0079] After the calcination is completed, the material is mixed with sucrose and then mixed and ball-milled. Sucrose can be used as a carbon source after the secondary calcination. After the ball-milling is completed, it is placed in a drying oven and dried for 12 hours.

[0080] After drying, the sample was placed in a tube furnace under a nitrogen atmosphere and heated to 600° C. for calcination for 12 hours. After calcination, the positive electrode material was obtained.

[0081] The present invention also provides a system for preparing a positive electrode material for a sodium ion battery. Figure 1 to Figure 2 , including: a mixing component 1, a first ball milling component 2, a first calcining component 3, a second ball milling component 4 and a second calcining component 5, the mixing component 1 is used to screen the raw materials, mix the raw materials, and use the state recognition model to judge whether the raw materials are mixed uniformly; the raw materials include: ferrous oxalate crystals, lithium carbonate, manganese acetate and ammonium dihydrogen phosphate; the first ball milling component 2 is used to add the mixed materials to a reaction container containing anhydrous ethanol, and then put them into a ball mill for high-energy ball milling for 2-6 hours, and then put the mixed materials into a vacuum dryer The first calcination component 3 is used to wait until the drying is completed, place the mixed material in a tubular furnace, and heat it to 320-400°C in an inert gas environment for calcination for 8-14 hours; the second ball milling component 4 is used to wait until the calcination is completed, mix the material with sucrose, and then perform mixed ball milling. After the ball milling is completed, place it in a drying oven for drying for 10-12 hours; the second calcination component 5 is used to place the dried sample in a tubular furnace in an inert gas environment, heat it to 560-660°C and calcine it for 6-14 hours.

[0082] The present invention provides a method and system for preparing a positive electrode material for a sodium ion battery. Compared with the prior art, the introduction of a state recognition model can efficiently and quickly determine whether the raw materials are evenly mixed, effectively save mixing time, and improve preparation efficiency. In the state recognition model, the raw material area is first identified, and then the image recognition model is used for identification. When it is detected that the gap size between the raw materials after mixing meets the preset conditions, it can be determined that they are in a state of even mixing, and the mixing operation can be stopped to enter the next preparation process.

[0083] The present invention also provides an electronic device, comprising a bus, a transceiver, a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the transceiver, the memory, and the processor are connected via the bus, and wherein the computer program, when executed by the processor, implements the steps in the above-mentioned method for preparing a positive electrode material for a sodium ion battery.

[0084] Compared with the prior art, the beneficial effects of the electronic device provided by the present invention are the same as the beneficial effects of the method for preparing a sodium ion battery positive electrode material described in the above technical solution, and will not be described in detail here.

[0085] The present invention also provides a computer-readable storage medium having a computer program stored thereon, characterized in that when the computer program is executed by a processor, the steps in the above-mentioned method for preparing a positive electrode material for a sodium ion battery are implemented.

[0086] Compared with the prior art, the beneficial effects of a computer-readable storage medium provided by the present invention are the same as the beneficial effects of a method for preparing a sodium ion battery positive electrode material described in the above technical solution, and will not be repeated here.

[0087] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions and improvements made within the spirit and principles of the present invention should be included in the protection scope of the present invention.

Claims

1. A method for preparing a positive electrode material for a sodium ion battery, characterized in that: The following steps are involved: Step S1, screening raw materials, mixing the raw materials, and using a state recognition model to determine whether the raw materials are mixed uniformly; Step S2, adding the uniformly mixed materials into a reaction container containing anhydrous ethanol, and then placing the mixture in a ball mill for 2-6 hours, and then placing the mixture in a vacuum drying oven for 10-12 hours; Step S3, after drying is completed, the mixed material is placed in a tube furnace and heated to 320-400° C. in an inert gas environment for calcination for 8-14 hours; Step S4, after the calcination is completed, the material is mixed with sucrose, and then the mixed material is ball-milled. After the ball-milling is completed, the mixed material is placed in a drying oven for 10-12 hours; Step S5: After drying, the sample is placed in a tubular furnace under an inert gas environment, heated to 560-660°C and calcined for 6-14 hours.

2. The method for preparing a positive electrode material for a sodium ion battery according to claim 1, characterized in that: The screening of raw materials, mixing the raw materials, and using a state recognition model to determine whether the raw materials are uniformly mixed include: Weigh ferrous oxalate crystals, lithium carbonate, manganese acetate and ammonium dihydrogen phosphate according to a preset ratio; Mixing ferrous oxalate crystals, lithium carbonate, manganese acetate and diammonium phosphate; The state recognition model is used to determine whether the raw materials are mixed evenly.

3. The method for preparing a positive electrode material for a sodium ion battery according to claim 2, characterized in that: The determining whether the raw materials are mixed uniformly by the state recognition model includes: The collected mixed image is preprocessed; the mixed image includes raw materials that are uniformly mixed; The preprocessed experimental image is input as a sample into a deep learning model for training to obtain an image recognition model, wherein the image recognition model includes: a YOLO-v5 network, a GAM attention module, and a three-dimensional weight generation module; the GAM attention module is introduced into the YOLO-v5 network; the three-dimensional weight generation module is introduced into the YOLO-v5 network to obtain true three-dimensional weights and enhance the network's ability to focus on key features. The target image is input into the image recognition model to determine whether it is mixed uniformly.

4. The method for preparing a positive electrode material for a sodium ion battery according to claim 3, characterized in that: The GAM attention module includes the following formula: Among them, M t Represents the weight coefficient of the channel attention module; M k represents the weight coefficient of the spatial attention module; F1 represents the input feature; F1 represents the input feature; F3 represents the output feature.

5. The method for preparing a positive electrode material for a sodium ion battery according to claim 4, characterized in that: The collected mixed image is preprocessed, including segmenting the image using an image segmentation model; the image segmentation model includes: a UNet++ network and an additive loss function; the additive loss function is used in the UNet++ network; the expression formula of the additive loss function is: Where N represents the total number of pixels; g i represents the probability of annotation; p i represents the predicted probability; λ represents a constant, ranging from 0.4 to 0.

6.

6. The method for preparing a positive electrode material for a sodium ion battery according to claim 5, characterized in that: The three-dimensional weight generation module includes the energy function of the neuron: Among them, ε t Indicates calculating the average value of all neurons in this channel except t; Indicates calculating the variance of all neurons in the channel except t; t, x i Respectively represent the input features X = R c×h×w The target neuron and other neurons in a single channel of ; i represents the index and on the spatial dimensions; M = h × w represents the number of neurons on the channel.

7. The method for preparing a positive electrode material for a sodium ion battery according to claim 5, characterized in that: The raw materials include: ferrous oxalate crystals, lithium carbonate, manganese acetate and diammonium phosphate.

8. A system for preparing a positive electrode material for a sodium ion battery, characterized in that: include: A mixing component (1) is used to screen raw materials, mix the raw materials, and use a state recognition model to determine whether the raw materials are mixed uniformly; the raw materials include: ferrous oxalate crystals, lithium carbonate, manganese acetate, and diammonium phosphate; The first ball milling assembly (2) is used to add the uniformly mixed materials into a reaction container containing anhydrous ethanol, and then put the mixed materials into a ball mill for high-energy ball milling for 2-6 hours, and then put the mixed materials into a vacuum drying oven for 10-12 hours; The first calcining assembly (3) is used to place the mixed material in a tube furnace after drying is completed, and heat it to 320-400° C. in an inert gas environment for calcination for 8-14 hours; The second ball milling assembly (4) is used to wait until the calcination is completed, mix the material with sucrose, and then perform mixed ball milling. After the ball milling is completed, place it in a drying oven for drying for 10-12 hours; The second calcination assembly (5) is to place the dried sample in a tubular furnace under an inert gas environment and heat it to 560-660°C for calcination for 6-14 hours.

9. An electronic device, comprising a bus, a transceiver, a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the transceiver, the memory, and the processor are connected via the bus, wherein: When the computer program is executed by the processor, the steps in the method for preparing a sodium ion battery positive electrode material as described in any one of claims 1 to 7 are implemented.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps in the method for preparing a sodium ion battery positive electrode material as described in any one of claims 1 to 7 are implemented.