Porous carbon preparation method and device based on image recognition and related equipment

Abstract

The invention provides a porous carbon preparation method and device based on image recognition and related equipment, and relates to the technical field of porous carbon preparation, and the method comprises the steps: obtaining a target image which is an image obtained after a porous carbon raw material is crushed; image recognition is conducted on the target image according to a first preset model, a first recognition result is obtained, and the first preset model is used for recognizing the particle size of substances in the image; under the condition that the first identification result indicates that the particle size of the crushed porous carbon raw material is larger than a particle size threshold value, secondary crushing is conducted on the crushed porous carbon raw material, a target material is obtained, and the particle size of the target material is smaller than or equal to the particle size threshold value; and activating according to the target material to obtain the target porous carbon. Through an image recognition mode, whether the particle size of the crushed porous carbon raw material reaches the standard or not can be conveniently monitored, and accordingly, the defective rate of porous carbon products can be reduced by performing porous carbon production.

Description

Technical Field

[0001] The present disclosure relates to the technical field of porous carbon preparation, and in particular to a porous carbon preparation method, device and related equipment based on image recognition. Background Art

[0002] With the continuous breakthroughs in power generation technology, porous carbon, which is closely related to battery negative electrode materials, has received more widespread attention, and the demand for porous carbon in industries such as automobiles, energy storage, and batteries has also been increasing day by day.

[0003] In the raw material processing stage of the porous carbon preparation scheme provided by the relevant technology, it is required to crush the porous carbon raw material (also called precursor) to below a certain particle size, so as to activate the porous carbon material with a larger specific surface area. However, it is found in application that the particle size measurement process is relatively cumbersome and time-consuming. In actual production, the appropriate raw material crushing time is often estimated based on experience and a small amount of test results, and then the raw material crushing time is used for the subsequent raw material crushing process, and the particle size measurement is no longer performed or the particle size sampling is performed periodically.

[0004] Since the relevant technology lacks a convenient means to detect particle size, the particle size of the raw materials sent to the subsequent activation process fluctuates greatly, which results in the specific surface area of ​​the final porous carbon product being lower than expected. Summary of the invention

[0005] The purpose of the present disclosure is to provide a porous carbon preparation method, device and related equipment based on image recognition, which are used to solve the technical problem of low specific surface area of ​​porous carbon products produced by related technologies.

[0006] In a first aspect, an embodiment of the present disclosure provides a method for preparing porous carbon based on image recognition, the method comprising: Acquire a target image, wherein the target image is an image of the porous carbon raw material after being crushed; Performing image recognition on the target image according to a first preset model to obtain a first recognition result, wherein the first preset model is used to identify the particle size of a substance in the image; When the first recognition result indicates that the particle size of the pulverized porous carbon raw material is greater than a particle size threshold, the pulverized porous carbon raw material is subjected to secondary pulverization to obtain a target material, wherein the particle size of the target material is less than or equal to the particle size threshold; The target porous carbon is obtained by activating the target material.

[0007] In a second aspect, the present disclosure provides a porous carbon device based on image recognition, the device comprising: An image acquisition module, used to acquire a target image, wherein the target image is an image of the porous carbon raw material after being crushed; A particle size recognition module, used to perform image recognition on the target image according to a first preset model to obtain a first recognition result, wherein the first preset model is used to identify the particle size of the substance in the image; a secondary crushing module, configured to, when the first recognition result indicates that the particle size of the porous carbon raw material after crushing is greater than a particle size threshold, perform secondary crushing on the crushed porous carbon raw material to obtain a target material, wherein the particle size of the target material is less than or equal to the particle size threshold; The production module is used to activate the target material to obtain the target porous carbon.

[0008] In a third aspect, the present application provides an electronic device, comprising a processor, a memory, and a computer program stored in the memory and executable on the processor, wherein the computer program, when executed by the processor, implements the steps of the method described in the first aspect.

[0009] In a fourth aspect, the present application provides a computer-readable storage medium having a computer program stored thereon, and when the computer program is executed by a processor, the steps of the method described in the first aspect are implemented.

[0010] In a fifth aspect, the present application provides a computer program product, comprising computer instructions, which, when executed by a processor, implement the steps of the method described in the first aspect.

[0011] In the present application, an image of the porous carbon raw material after crushing is collected and image recognition is performed on the image to conveniently obtain the particle size of the porous carbon raw material after crushing. When the image recognition result indicates that the particle size is greater than the set particle size threshold, the crushed porous carbon raw material is subjected to secondary crushing to ensure that the particle size of the raw material entering the subsequent process meets the particle size requirements, thereby avoiding the problem of insufficient specific surface area of ​​the porous carbon after activation due to excessive raw material particle size. This can increase the specific surface area of ​​the porous carbon product finally generated. BRIEF DESCRIPTION OF THE DRAWINGS

[0012] Figure 1 is a schematic flow chart of a method for preparing porous carbon based on image recognition provided in an embodiment of the present disclosure; Figure 2 is a schematic structural diagram of a porous carbon device based on image recognition provided by an embodiment of the present disclosure; Figure 3 It is a schematic diagram of an electronic device provided by an embodiment of the present disclosure. DETAILED DESCRIPTION

[0013] The following will be combined with the drawings in the embodiments of the present disclosure to clearly and completely describe the technical solutions in the embodiments of the present disclosure. Obviously, the described embodiments are part of the embodiments of the present disclosure, rather than all of the embodiments. Based on the embodiments in the present disclosure, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present disclosure.

[0014] The present disclosure provides a method for preparing porous carbon based on image recognition. Figure 1 As shown, the porous carbon preparation method based on image recognition includes: Step 101: Acquire a target image.

[0015] Wherein, the target image is an image of the porous carbon raw material after being crushed.

[0016] Exemplarily, the porous carbon raw material may be char-based bio-based.

[0017] In one example, the target image may be captured by a camera fixedly disposed at the discharge port of the pulverizing device.

[0018] In another example, the target image can also be collected by a mobile robot equipped with a camera. Compared with the method of fixing the camera at the discharge port, the method of mounting the camera on a mobile robot is more flexible and convenient, and can be applied to various complex working conditions without modifying the existing workshop environment.

[0019] Step 102: Perform image recognition on the target image according to a first preset model to obtain a first recognition result.

[0020] The first preset model is used to identify the particle size of the substance in the image.

[0021] The first preset model is a neural network model, such as a feedforward neural network (FNN), a convolutional neural network (CNN), a recurrent neural network (RNN), etc.

[0022] The process of performing image recognition on the target image according to the first preset model is specifically as follows: Performing data preprocessing (such as image size adjustment and image noise removal) on the target image according to the preprocessing module of the first preset model; Extracting image features of the target image after data preprocessing according to the feature extraction module of the first prediction model; The feature mapping module of the first prediction model performs mapping conversion on the image features of the target image after data preprocessing to output a recognition result reflecting the particle size of the porous carbon raw material in the target image.

[0023] Exemplarily, the training process of the first preset model may be: Selecting a plurality of particle size training images including porous carbon raw materials with different crushing degrees, and measuring the particle size of the porous carbon raw materials in each particle size training image, thereby forming a plurality of sets of training data; The initial network model is iteratively trained using the multiple sets of training data, and when the iteration conditions are met, the network model of the last iteration is used as the first preset model, wherein the iteration conditions are: the number of iterations is greater than or equal to a set number threshold, and / or the training loss value of the network model based on the current iteration is less than the set loss threshold, the training loss value is used to represent the difference between the particle size result and the true value result obtained by processing the training image with the network model of the current iteration, and the smaller the training loss value, the smaller the difference.

[0024] In some embodiments, the target image can be first grid-divided to obtain multiple image blocks, and then the multiple image blocks are respectively enlarged to the set size required by the first preset model, thereby obtaining multiple enlarged images corresponding to the multiple image blocks, and then the multiple enlarged images are respectively input into the first preset model to obtain multiple enlarged image recognition results corresponding to the output of the first preset model, and finally the multiple particle size results indicated by the multiple enlarged image recognition results are averaged to form the first recognition result. Compared with the method of directly inputting the target image into the first preset model, the method of grid-dividing the target image and then enlarging them separately and then inputting them into the first preset model can achieve fine-grained extraction of features of each image area of ​​the target image, which can avoid the situation where image features of some image areas in the target image are missed, thereby obtaining a more accurate particle size recognition result, that is, making the obtained first recognition result more accurate and reliable.

[0025] Step 103: When the first recognition result indicates that the particle size of the pulverized porous carbon raw material is greater than a particle size threshold, the pulverized porous carbon raw material is subjected to secondary pulverization to obtain a target material.

[0026] Wherein, the particle size of the target material is less than or equal to the particle size threshold.

[0027] In the application, the time of the secondary crushing is shorter than the time of the initial crushing of the porous carbon raw material, and the time of the secondary crushing can be preset and can also be flexibly adjusted according to actual conditions.

[0028] It should be understood that, when the first recognition result indicates that the particle size of the pulverized porous carbon raw material is less than or equal to the particle size threshold, the pulverized porous carbon raw material is directly determined as the target material.

[0029] For example, the particle size threshold may be 180 mesh, 200 mesh, etc.

[0030] Step 104: Activate the target material to obtain target porous carbon.

[0031] In one example, the process of activating the target material to obtain the target porous carbon may be: The target material is activated with an activation agent (such as KOH) under high temperature conditions to achieve pore formation of the target material (also called carbon precursor). After active agent recovery, acidification balance and drying treatment, the target porous carbon product can be obtained.

[0032] In the present application, an image of the porous carbon raw material after crushing is collected and image recognition is performed on the image to conveniently obtain the particle size of the porous carbon raw material after crushing. When the image recognition result indicates that the particle size is greater than the set particle size threshold, the crushed porous carbon raw material is subjected to secondary crushing to ensure that the particle size of the raw material entering the subsequent process meets the particle size requirements, thereby avoiding the problem of insufficient specific surface area caused by excessive raw material particle size and reducing the defective rate of the porous carbon product finally generated.

[0033] In one embodiment, there are multiple target images, and different target images are acquired at different times. A turning operation is performed in the interval between two target images with adjacent acquisition times. The turning operation is used to turn the crushed porous carbon raw material. Performing image recognition on the target image according to the first preset model to obtain a first recognition result includes: Performing image recognition on the plurality of target images respectively according to the first preset model to obtain a plurality of image recognition results; The first recognition result is obtained by performing mean processing on the multiple particle sizes indicated by the multiple image recognition results.

[0034] In this embodiment, by collecting multiple target images, and performing a material turning operation in the interval period between two target images with adjacent collection times, so that the multiple target images obtained can accurately reflect the image characteristics of the pulverized porous carbon raw material, multiple image recognitions are performed based on this, and the multiple particle sizes indicated by the multiple image recognition results are averaged to form a first recognition result. On the one hand, it can reduce the adverse effects of external interference on the particle size recognition result during the image collection process, and on the other hand, it can enable the final particle size recognition result to accurately characterize the particle size of the pulverized porous carbon raw material; The reason for performing a flipping operation in the interval period between two target images with adjacent acquisition times is to flip the crushed porous carbon raw material so that each part of the crushed porous carbon raw material can be presented in the target image as much as possible, which can further improve the accuracy of the final particle size recognition result (that is, the first recognition result).

[0035] In the application, an electric tipping bucket can be set in the collecting device facing the discharge port of the crushing equipment. At this time, one tipping operation means that the electric tipping bucket rotates once around its rotation axis. The electric tipping bucket can be set to perform a tipping operation at an interval of 3 seconds.

[0036] In one embodiment, before acquiring the target image, the method further includes: Acquiring a raw material image of the porous carbon raw material; Performing image recognition on the raw material image according to a second preset model to obtain a second recognition result, wherein the second preset model is used to identify the shortest crushing time when the material in the image reaches the particle size threshold; The porous carbon raw material is pulverized according to the shortest pulverization time indicated by the second recognition result.

[0037] In this embodiment, compared with the method of manually setting the crushing time based on experience, the interference of human factors can be avoided by collecting the raw material image of the porous carbon raw material and dynamically determining the shortest crushing time after image recognition. It is possible to set a suitable crushing time for each porous carbon raw material, thereby reducing the frequency of secondary crushing. On the premise of ensuring that the specific surface area of ​​the porous carbon product meets expectations, the total time consumed in crushing the raw material in the pretreatment stage is reduced, thereby improving the production rate of the porous carbon product.

[0038] Furthermore, before obtaining the raw material image of the porous carbon raw material, the method further includes: Acquire a plurality of training data pairs, wherein each of the training data pairs comprises a training image and a time data, wherein the training image is an image comprising a porous carbon raw material, and different training images comprise different porous carbon raw materials, and the time data is the shortest crushing time when the porous carbon raw material in the corresponding training image reaches the particle size threshold; An initial model is trained according to the multiple training data pairs to obtain the second preset model.

[0039] It should be understood that the different porous carbon raw materials in this embodiment include at least one of the following: different materials of the porous carbon raw materials, different volumes of the porous carbon raw materials, and different initial particle sizes of the porous carbon raw materials.

[0040] Furthermore, both the first preset model and the second preset model are neural network models, and the initial model is a model generated according to a feature extraction module of the first preset model.

[0041] The initial model is generated according to the feature extraction module of the first preset model as follows: The feature extraction module of the first preset model and other modules in the conventional model except the feature extraction module are combined to form the initial model.

[0042] In this embodiment, in view of the situation where both the first preset model and the second preset model involve the extraction of image features, the initial model for training to form the second preset model is constructed by directly reusing the feature extraction module (also called the feature extraction network) of the already trained first preset model, so as to save a lot of time required for training the feature extraction module, so that the initial model can meet the needs of actual applications after being adjusted with a small amount of training data pairs and establishing the mapping logic between image features and the shortest crushing time. This can significantly shorten the training time of the second preset model, speed up the forming efficiency of the second preset model, and reduce the requirement of the second preset model for the number of training data pairs, making the application of the scheme described in the present application more convenient.

[0043] In one embodiment, the time data is data determined based on a corresponding mapping function, and the mapping function is used to represent the mapping relationship between the crushing time of the corresponding porous carbon raw material and the particle size after crushing. The mapping function is a fitting function of the corresponding multiple target data pairs, and each of the target data pairs includes the corresponding crushing time of the porous carbon raw material and the corresponding particle size of the porous carbon raw material after crushing. The particle size of the porous carbon raw material after crushing is obtained based on the first preset model.

[0044] In this embodiment, due to the interference of various factors, the rate of change of the particle size of the porous carbon raw material slows down or even stagnates after it is crushed to a certain particle size. Therefore, compared with the method of crushing the porous carbon raw material for a certain period of time and then taking it out and then measuring the particle size to obtain the corresponding particle size and the shortest crushing time, it is more accurate and reliable to deduce the shortest crushing time when the corresponding porous carbon raw material reaches the particle size threshold requirement by establishing a mapping relationship between the crushing time of the porous carbon raw material and the particle size after crushing.

[0045] Specifically, for each portion of porous carbon raw material, the porous carbon raw material is taken out multiple times by setting a crushing rule, and the particle size is identified by image recognition after it is taken out once, so as to obtain the corresponding data on the change in particle size of the porous carbon raw material with increasing crushing time. Based on this, function fitting is performed to obtain the mapping function corresponding to each portion of porous carbon raw material.

[0046] Among them, the crushing rule can be set to take out and collect corresponding data every 5 minutes within the set crushing time (such as 1 hour or 2 hours) to measure the particle size through image recognition. In the application, it can also be set that when the particle size reaches the set value (such as 80 mesh or 100 mesh), the interval between each taking out can be appropriately shortened, such as reducing the taking out interval from 5 minutes to 3 minutes or even 2 minutes, to adapt to the situation where the particle size change in the middle and late stages of crushing slows down. By shortening the data collection interval, more particle size data can be collected to achieve refined monitoring of particle size changes, so as to improve the simulation effect of the mapping function fitted thereby.

[0047] See also Figure 2 , Figure 2 is a porous carbon device based on image recognition provided by an embodiment of the present disclosure, such as Figure 2 As shown, the porous carbon preparation device 200 based on image recognition includes: An image acquisition module 201 is used to acquire a target image, wherein the target image is an image of the porous carbon raw material after being crushed; The particle size recognition module 202 is used to perform image recognition on the target image according to a first preset model to obtain a first recognition result, wherein the first preset model is used to identify the particle size of the substance in the image; A secondary crushing module 203 is used for, when the first recognition result indicates that the particle size of the porous carbon raw material after crushing is greater than a particle size threshold, performing secondary crushing on the crushed porous carbon raw material to obtain a target material, wherein the particle size of the target material is less than or equal to the particle size threshold; The production module 204 is used to activate the target material to obtain target porous carbon.

[0048] In one embodiment, the image acquisition module 201 is further used to: acquire a raw material image of the porous carbon raw material; The porous carbon preparation device 200 based on image recognition further includes: a time length recognition module, used for performing image recognition on the raw material image according to a second preset model to obtain a second recognition result, wherein the second preset model is used to identify the shortest pulverization time when the material in the image reaches the particle size threshold; A raw material crushing module is used to crush the porous carbon raw material according to the shortest crushing time indicated by the second recognition result.

[0049] In one embodiment, the porous carbon preparation device 200 based on image recognition further includes a model training module, and the model training module is used to: Acquire a plurality of training data pairs, wherein each of the training data pairs comprises a training image and a time data, wherein the training image is an image comprising a porous carbon raw material, and different training images comprise different porous carbon raw materials, and the time data is the shortest crushing time when the porous carbon raw material in the corresponding training image reaches the particle size threshold; An initial model is trained according to the multiple training data pairs to obtain the second preset model.

[0050] In one embodiment, the first preset model and the second preset model are both neural network models, and the initial model is a model generated according to a feature extraction module of the first preset model.

[0051] In one embodiment, the time data is data determined based on a corresponding mapping function, and the mapping function is used to represent the mapping relationship between the crushing time of the corresponding porous carbon raw material and the particle size after crushing. The mapping function is a fitting function of the corresponding multiple target data pairs, and each of the target data pairs includes the corresponding crushing time of the porous carbon raw material and the corresponding particle size of the porous carbon raw material after crushing. The particle size of the porous carbon raw material after crushing is obtained based on the first preset model.

[0052] In one embodiment, there are multiple target images, and different target images are acquired at different times. A turning operation is performed in the interval between two target images with adjacent acquisition times. The turning operation is used to turn the crushed porous carbon raw material. The particle size identification module 202 is specifically used for: Performing image recognition on the plurality of target images respectively according to the first preset model to obtain a plurality of image recognition results; The first recognition result is obtained by performing mean processing on the multiple particle sizes indicated by the multiple image recognition results.

[0053] The porous carbon preparation device 200 based on image recognition provided in the embodiment of the present disclosure can realize each process in the above-mentioned porous carbon preparation method embodiment based on image recognition, and will not be described again here to avoid repetition.

[0054] According to an embodiment of the present disclosure, the present disclosure also provides an electronic device and a readable storage medium.

[0055] Figure 3A schematic block diagram of an example electronic device 300 that can be used to implement an embodiment of the present disclosure is shown. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device can also represent various forms of mobile devices, such as personal digital processing, cellular phones, smart phones, wearable devices, and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely examples and are not intended to limit the implementation of the present disclosure described and / or required herein.

[0056] like Figure 3 As shown, the device 300 includes a computing unit 301, which can perform various appropriate actions and processes according to a computer program stored in a read-only memory (ROM) 302 or a computer program loaded from a storage unit 308 to a random access memory (RAM) 303. In the RAM 303, various programs and data required for the operation of the device 300 can also be stored. The computing unit 301, the ROM 302, and the RAM 303 are connected to each other via a bus 304. An input / output (I / O) interface 305 is also connected to the bus 304.

[0057] A number of components in the device 300 are connected to the I / O interface 305, including: an input unit 306, such as a keyboard, a mouse, etc.; an output unit 307, such as various types of displays, speakers, etc.; a storage unit 308, such as a disk, an optical disk, etc.; and a communication unit 309, such as a network card, a modem, a wireless communication transceiver, etc. The communication unit 309 allows the device 300 to exchange information / data with other devices through a computer network such as the Internet and / or various telecommunication networks.

[0058] The computing unit 301 may be a variety of general and / or special processing components with processing and computing capabilities. Some examples of the computing unit 301 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various dedicated artificial intelligence (AI) computing chips, various computing units running machine learning model algorithms, digital signal processors (DSP), and any appropriate processors, controllers, microcontrollers, etc. The computing unit 301 performs the various methods and processes described above, such as the porous carbon preparation method based on image recognition. For example, in some embodiments, the porous carbon preparation method based on image recognition may be implemented as a computer software program, which is tangibly contained in a machine-readable medium, such as a storage unit 308. In some embodiments, part or all of the computer program may be loaded and / or installed on the device 300 via the ROM 302 and / or the communication unit 309. When the computer program is loaded into the RAM 303 and executed by the computing unit 301, one or more steps of the porous carbon preparation method based on image recognition described above may be performed. Alternatively, in other embodiments, the computing unit 301 may be configured to execute the porous carbon preparation method based on image recognition in any other appropriate manner (for example, by means of firmware).

[0059] Various embodiments of the systems and techniques described above herein may be implemented in digital electronic circuit systems, integrated circuit systems, field-programmable gate arrays (FPGAs), application-specific integrated circuits (ASICs), application-specific standard products (ASSPs), systems on chips (SOCs), complex programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various embodiments may include: being implemented in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which may be a dedicated or general-purpose programmable processor that can receive data and instructions from a storage system, at least one input device, and at least one output device, and transmit data and instructions to the storage system, the at least one input device, and the at least one output device.

[0060] The program code for implementing the method of the present disclosure may be written in any combination of one or more programming languages. These program codes may be provided to a processor or controller of a general-purpose computer, a special-purpose computer, or other programmable data processing device, so that the program code, when executed by the processor or controller, enables the functions / operations specified in the flow chart and / or block diagram to be implemented. The program code may be executed entirely on the machine, partially on the machine, partially on the machine and partially on a remote machine as a stand-alone software package, or entirely on a remote machine or server.

[0061] In the context of the present disclosure, a machine-readable medium may be a tangible medium that may contain or store a program for use by or in conjunction with an instruction execution system, device, or equipment. A machine-readable medium may be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium may include, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, device, or device, or any suitable combination of the foregoing. A more specific example of a machine-readable storage medium may include an electrical connection based on one or more lines, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

[0062] As used herein, the term "machine-readable medium" refers to any computer program product, apparatus, and / or device (e.g., disk, optical disk, memory, programmable logic device (PLD)) for providing machine instructions and / or data to a programmable processor, including a machine-readable medium that receives machine instructions as a machine-readable signal. The term "machine-readable signal" refers to any signal for providing machine instructions and / or data to a programmable processor.

[0063] To provide interaction with a user, the systems and techniques described herein can be implemented on a computer having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user; and a keyboard and pointing device (e.g., a mouse or trackball) through which the user can provide input to the computer. Other types of devices can also be used to provide interaction with the user; for example, the feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including acoustic input, voice input, or tactile input).

[0064] The systems and techniques described herein may be implemented in a computing system that includes back-end components (e.g., as a data server), or a computing system that includes middleware components (e.g., an application server), or a computing system that includes front-end components (e.g., a user computer with a graphical user interface or a web browser through which a user can interact with implementations of the systems and techniques described herein), or a computing system that includes any combination of such back-end components, middleware components, or front-end components. The components of the system may be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include: a local area network (LAN), a wide area network (WAN), and the Internet.

[0065] A computer system may include a client and a server. The client and the server are generally remote from each other and usually interact through a communication network. The relationship of client and server is generated by computer programs running on respective computers and having a client-server relationship with each other. The server may be a cloud server, a server of a distributed system, or a server combined with a blockchain.

[0066] The present application also provides a computer program product, including computer instructions, which, when executed by a processor, implement the above Figure 1 The various processes of the method embodiment shown can achieve the same technical effect, and will not be described again here to avoid repetition.

[0067] It should be understood that the various forms of processes shown above can be used to reorder, add or delete steps. For example, the steps recorded in this disclosure can be executed in parallel, sequentially or in different orders, as long as the desired results of the technical solutions disclosed in this disclosure can be achieved, and this document does not limit this.

[0068] The above specific implementations do not constitute a limitation on the protection scope of the present disclosure. It should be understood by those skilled in the art that various modifications, combinations, sub-combinations and substitutions can be made according to design requirements and other factors. Any modification, equivalent substitution and improvement made within the spirit and principle of the present disclosure shall be included in the protection scope of the present disclosure.

Claims

1. A method for preparing porous carbon based on image recognition, characterized in that: The method comprises: Acquire a target image, wherein the target image is an image of the porous carbon raw material after being crushed; Performing image recognition on the target image according to a first preset model to obtain a first recognition result, wherein the first preset model is used to identify the particle size of a substance in the image; When the first recognition result indicates that the particle size of the pulverized porous carbon raw material is greater than a particle size threshold, the pulverized porous carbon raw material is subjected to secondary pulverization to obtain a target material, wherein the particle size of the target material is less than or equal to the particle size threshold; The target porous carbon is obtained by activating the target material.

2. The method according to claim 1, characterized in that Before acquiring the target image, the method further includes: Acquiring a raw material image of the porous carbon raw material; Performing image recognition on the raw material image according to a second preset model to obtain a second recognition result, wherein the second preset model is used to identify the shortest crushing time when the material in the image reaches the particle size threshold; The porous carbon raw material is pulverized according to the shortest pulverization time indicated by the second recognition result.

3. The method according to claim 2, characterized in that Before obtaining the raw material image of the porous carbon raw material, the method further includes: Acquire a plurality of training data pairs, wherein each of the training data pairs comprises a training image and a time data, wherein the training image is an image comprising a porous carbon raw material, and different training images comprise different porous carbon raw materials, and the time data is the shortest crushing time when the porous carbon raw material in the corresponding training image reaches the particle size threshold; An initial model is trained according to the multiple training data pairs to obtain the second preset model.

4. The method according to claim 3, characterized in that The first preset model and the second preset model are both neural network models, and the initial model is a model generated according to a feature extraction module of the first preset model.

5. The method according to claim 1, characterized in that There are multiple target images, and different target images are collected at different times. A turning operation is performed once in the interval between two target images with adjacent collection times, and the turning operation is used to turn the crushed porous carbon raw material; Performing image recognition on the target image according to the first preset model to obtain a first recognition result includes: Performing image recognition on the plurality of target images respectively according to the first preset model to obtain a plurality of image recognition results; The first recognition result is obtained by performing mean processing on the multiple particle sizes indicated by the multiple image recognition results.

6. The method according to claim 3, characterized in that The time data is data determined based on a corresponding mapping function, and the mapping function is used to represent the mapping relationship between the crushing time of the corresponding porous carbon raw material and the particle size after crushing. The mapping function is a fitting function of the corresponding multiple target data pairs, and each of the target data pairs includes the corresponding crushing time of the porous carbon raw material and the corresponding particle size of the porous carbon raw material after crushing. The particle size of the porous carbon raw material after crushing is obtained based on the first preset model.

7. A porous carbon device based on image recognition, characterized in that: The device comprises: An image acquisition module, used to acquire a target image, wherein the target image is an image of the porous carbon raw material after being crushed; A particle size recognition module, used to perform image recognition on the target image according to a first preset model to obtain a first recognition result, wherein the first preset model is used to identify the particle size of the substance in the image; a secondary crushing module, configured to, when the first recognition result indicates that the particle size of the porous carbon raw material after crushing is greater than a particle size threshold, perform secondary crushing on the crushed porous carbon raw material to obtain a target material, wherein the particle size of the target material is less than or equal to the particle size threshold; The production module is used to activate the target material to obtain the target porous carbon.

8. An electronic device, characterized in that: The method comprises a processor, a memory, and a computer program stored in the memory and executable on the processor, wherein the computer program implements the steps of the method according to any one of claims 1 to 6 when executed by the processor.

9. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 6 are implemented.

10. A computer program product, characterized in that The method comprises computer instructions, which, when executed by a processor, implement the steps of the method according to any one of claims 1 to 6.

Images