Mixing uniformity determination method and mixing uniformity detection system

Abstract

The invention relates to the technical field of batteries, in particular to a material mixing uniformity determination method and a material mixing uniformity detection system.The material mixing uniformity detection system is provided with a dispersion system, a robot and imaging equipment, so that a sample dispersion image of a battery material can be obtained on line in the production process of the battery material; further utilizing computer equipment to perform feature extraction on the acquired dispersed image of the sample to obtain an image feature set, then inputting the image feature set into the trained neural network model to obtain particle features of the dispersed image, and finally obtaining the uniformity of the sample according to the particle features. Therefore, the mixing uniformity can be detected on line in the production process of the battery material, and the production efficiency is improved.

Description

Technical Field

[0001] The present invention relates to the technical field of batteries, and in particular to a mixing uniformity determination method and a mixing uniformity detection system. Background Art

[0002] As an effective energy storage device, lithium-ion batteries have been widely used in people's production and life. In recent years, electric vehicles are rising and developing rapidly. However, lithium-ion batteries also have defects such as slow charging speed, poor performance under low temperature conditions, and safety issues under harsh conditions. In order to solve the above problems, researchers are constantly exploring lithium-ion batteries with better performance. As a key part, the positive electrode material affects many characteristics of lithium-ion batteries, so seeking higher performance and cheaper positive electrode materials has also become the goal pursued by researchers. Common positive electrode materials include LiCoO2, LiFePO4, Li Mn2O4, etc. The ternary positive electrode LiNixCoyMnzO2 has attracted widespread attention from researchers due to its high capacity and low cost. The industrial preparation process of ternary positive electrode materials requires that each metal salt be mixed according to the stoichiometric ratio of the target product, fully mixed by mechanical rotation, and the target product is obtained after high-temperature calcination.

[0003] The uniformity of the mixing process is crucial to the subsequent process. The next step can only be performed after the mixing is uniform. The conventional detection method is to offline analyze the left, middle and right sampling points of the mixer, and judge whether the mixing is uniform based on the range of the three results (maximum value - minimum value). If the mixing is uniform, the next step is performed, otherwise it is mixed and analyzed again, which is time-consuming and restricts the improvement of production efficiency and capacity. Summary of the invention

[0004] In view of this, the present invention provides a method for determining a mixing uniformity and a system for detecting a mixing uniformity, so as to perform online detection of the mixing uniformity in the production process of battery materials and improve production efficiency.

[0005] In a first aspect, the present invention provides a method for determining the uniformity of a mixture, comprising the following steps: obtaining a dispersion image of a sample; performing feature extraction on the dispersion image to obtain an image feature set; inputting the image feature set into a trained neural network model to obtain particle features of the dispersion image; and obtaining the uniformity of the sample based on the particle features.

[0006] The method for determining the uniformity of a mixture provided by the present invention obtains an image feature set by extracting features from a dispersion image of an acquired sample, then inputs the image feature set into a trained neural network model to obtain particle features of the dispersion image, and finally obtains the uniformity of the sample based on the particle features. Thus, the uniformity of the sample can be obtained only by analyzing the dispersion image of the sample, making the detection of the uniformity simple and quick, and the mixing uniformity can be detected online during the production of battery materials, thereby improving production efficiency.

[0007] In an optional implementation, the image feature set includes at least one of the following image features: image brightness feature, image edge feature, image texture feature, image color feature, and diameter of particles in the image.

[0008] Therefore, the image feature set can accurately characterize the particle features of the dispersion image.

[0009] In an optional embodiment, the neural network model includes multiple convolutional layers, each convolutional layer is used to aggregate the features of each node with the features of its neighboring nodes.

[0010] Therefore, the neural network model can use the relationship between nodes for learning and reasoning, and can capture the local structure and global topological features of scattered images, thereby extracting richer feature representations, thereby improving the analysis performance of the neural network model for image feature sets.

[0011] In the second aspect, the present invention provides a device for determining the uniformity of a mixture, the device comprising an acquisition module, a feature extraction module, a particle feature determination module and a uniformity determination module; the acquisition module is used to acquire a dispersion image of a sample; the feature extraction module is used to perform feature extraction on the dispersion image to obtain an image feature set; the particle feature determination module is used to input the image feature set into a trained neural network model to obtain particle features of the dispersion image; the uniformity determination module is used to obtain the uniformity of the sample based on the particle features.

[0012] The device for determining the uniformity of a mixture provided by the present invention obtains an image feature set by extracting features from a dispersion image of an acquired sample, then inputs the image feature set into a trained neural network model to obtain particle features of the dispersion image, and finally obtains the uniformity of the sample based on the particle features. Thus, the uniformity of the sample can be obtained only by analyzing the dispersion image of the sample, making the detection of the uniformity simple and quick, and the mixing uniformity can be detected online during the production of battery materials, thereby improving production efficiency.

[0013] In a third aspect, the present invention further provides a computer device, comprising a memory and a processor, the memory and the processor being communicatively connected to each other, the memory storing computer instructions, and the processor executing the method for determining the uniformity of a mixture according to the first aspect or any corresponding embodiment thereof by executing the computer instructions.

[0014] The computer device provided by the present invention obtains an image feature set by extracting features from a dispersion image of the acquired sample, then inputs the image feature set into a trained neural network model to obtain particle features of the dispersion image, and finally obtains the uniformity of the sample based on the particle features. Thus, the uniformity of the sample can be obtained only by analyzing the dispersion image of the sample, making the uniformity detection simple and quick, and the mixing uniformity can be detected online during the production of battery materials, thereby improving production efficiency.

[0015] In a fourth aspect, the present invention further provides a mixing uniformity detection system, comprising a dispersion system, a robot, the computer device of the third aspect and the imaging device; wherein the dispersion system comprises an air pump, a venturi tube and a glass slide holder, the air pump and the venturi tube are connected through an air pipeline, a valve is also provided on the air pipeline, a nozzle is provided at the end of the venturi tube, a sample storage device is provided below the venturi tube, and a sample sampler is provided between the nozzle and the sample storage device; a weight sensor is provided on the glass slide holder; the robot is used to take the sample obtained in the mixer according to the first target running trajectory The sample is placed in the sample storage container and the slide is placed on the slide holder according to the second target running trajectory; the computer device is used to determine whether the slide is placed on the slide holder according to the weight detected by the weight sensor, and when the slide is placed on the slide holder, the air pump is controlled to pressurize and the valve in the air pipeline is opened so that the nozzle sprays the sample in the sample storage container onto the slide; it is also used to transfer the carrier with the dispersed sample to the imaging platform; the imaging device is used to shoot the carrier with the dispersed sample on the imaging platform to obtain a dispersed image.

[0016] The mixing uniformity detection system provided in the embodiment of the present invention can obtain a sample dispersion image of the battery material online during the battery material production process by setting up a dispersion system, a robot and an imaging device, and further use a computer device to analyze the dispersion image of the sample to obtain the uniformity of the battery material sample, so as to perform online detection of the mixing uniformity during the battery material production process and improve production efficiency.

[0017] In an optional embodiment, the robot includes a robotic arm and a grasping structure connected to the robotic arm, and the computer device is also used to obtain the starting point and the ending point of the robotic arm, use a 3-5-3rd order polynomial to interpolate between the initial point and the ending point to obtain the angle range of each interpolation point; constrain the angle range of each interpolation point using a preset constraint condition; determine multiple initial operation trajectories of the robotic arm using the angle range of each interpolation point after the constraint; and optimize the multiple initial operation trajectories with the shortest operation time of the robotic arm to obtain a first target operation trajectory or a second target operation trajectory of the robotic arm.

[0018] In this way, the dual optimum of time and energy can be maintained during the movement of the robot arm.

[0019] In an optional implementation, the imaging device is communicatively connected to the controller, and the computer device is further used to: use a PLC signal to adjust the focus of the lens of the imaging device so that the scattered image meets a preset standard.

[0020] Thus, the lens of the imaging device can be automatically focused so that the scattered image meets the preset standard.

[0021] In a fifth aspect, the present invention further provides a computer-readable storage medium having computer instructions stored thereon, the computer instructions being used to enable a computer to execute the method for determining the uniformity of a mixture according to the first aspect or any corresponding embodiment thereof.

[0022] In a sixth aspect, the present invention further provides a computer program product, comprising computer instructions for causing a computer to execute the method for determining the uniformity of a mixture according to the first aspect or any corresponding embodiment thereof. BRIEF DESCRIPTION OF THE DRAWINGS

[0023] In order to more clearly illustrate the specific implementation methods of the present invention or the technical solutions in the prior art, the drawings required for use in the specific implementation methods or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are some implementation methods of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0024] Figure 1 is a flow chart of a method for determining mixing uniformity according to an embodiment of the present invention;

[0025] Figure 2 is a schematic diagram of an example of a sample dispersion image according to an embodiment of the present invention;

[0026] Figure 3 is a schematic structural diagram of a mixing uniformity detection system according to an embodiment of the present invention;

[0027] Figure 4 is a structural block diagram of a device for determining mixing uniformity according to an embodiment of the present invention;

[0028] Figure 5 It is a schematic diagram of the hardware structure of a computer device according to an embodiment of the present invention. DETAILED DESCRIPTION

[0029] In order to make the purpose, technical solution and advantages of the embodiments of the present invention clearer, the technical solution in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative work are within the scope of protection of the present invention.

[0030] According to an embodiment of the present invention, an embodiment of a method for determining a mixture uniformity is provided. It should be noted that the steps shown in the flowchart of the accompanying drawings can be executed in a computer system such as a set of computer executable instructions, and although a logical order is shown in the flowchart, in some cases, the steps shown or described can be executed in an order different from that shown here.

[0031] In this embodiment, a method for determining the uniformity of a mixture is provided, which can be used in a computer device. Figure 1 is a flow chart of a method for determining mixing uniformity according to an embodiment of the present invention. Figure 1 As shown, the process includes the following steps:

[0032] Step S101: Acquire a dispersion image of a sample.

[0033] Step S102: extract features from the scattered images to obtain an image feature set.

[0034] In an optional implementation, the image feature set includes at least one of the following image features: image brightness feature, image edge feature, image texture feature, image color feature, and diameter of particles in the image.

[0035] That is to say, image feature extraction includes but is not limited to brightness, edge, texture, color, and particle diameter. Specifically, the extraction method is scale-invariant feature transformation, which searches for feature points at different positions of the scattered image and calculates the direction of the feature points, such as the distribution direction of brightness, the direction of the bulge if the edge has one, and the direction of the bulge is mainly used to describe the position of the feature point.

[0036] Step S103: input the image feature set into the trained neural network model to obtain the particle features of the dispersed image.

[0037] In an optional embodiment, the neural network model includes multiple convolutional layers, each convolutional layer is used to aggregate the features of each node with the features of its neighboring nodes.

[0038] In the neural network model, node features are aggregated to its neighboring nodes and the node representation is updated using nonlinear transformation. For example, given a node i and its neighboring node set N(i), the convolutional layer first represents the feature of node i as Vi, and then aggregates it with the features of the neighboring nodes to obtain the updated feature representation V'i of node i. Usually, the aggregation operation uses weighted aggregation, as shown in formula (1):

[0039] V'i=σ(WuVi+b)(1)

[0040] Among them, W and b are learnable parameters, u is the aggregation weight, which is determined by the information of the edge between node i and its neighbor nodes and the characteristics of the node itself, and σ is the activation function.

[0041] Based on the aggregated data, the features of all graph nodes are updated. Similarly, aggregation operations are performed on each node in the graph to update the features of all graph nodes.

[0042] Then repeat the aggregation and weighting, and perform 4 iterations in total to obtain the training model.

[0043] For example, aggregation can be performed using mean, max, LSTM or other methods.

[0044] Step S104: Obtaining the uniformity of the sample according to the particle characteristics.

[0045] For example, the uniformity calculation process is: Figure 2 Through the image information feature extraction process, the brightness (x1), edge (x2), texture (x3), color RGB (R: x4, G: x5, B: x6), and diameter (x7) of the image are obtained as the input of the image information modeling, and the calculated particle features in the image are the output of the image information modeling. The particle features in the image are calculated as follows:

[0046] Y=(a*x1+b*x2+c*x3+d*x4+e*x5+f*x6)*x7^g

[0047] Among them, a, b, c, d, e, f, and g are calculation model coefficients, and their values ​​are a=0.115~0.22, b=1.3~1.5, c=0.02~0.05, d=0.25~0.35, e=0.5~0.65, f=0.15~0.4, and g=1.1~1.4.

[0048] The input and output data are used to model the image information to obtain the training model Model1. The actual image information x1, x2, x3, x4, x5, x6, x7 obtained by feature extraction are input into the model calculation. The particle feature Y of the actual image is predicted by the training model Model1, and the uniformity of the actual image is calculated as Z = 0.599*exp(1.288*Y).

[0049] The method for determining the uniformity of a mixture provided in the present embodiment obtains an image feature set by extracting features from a dispersion image of the acquired sample, then inputs the image feature set into a trained neural network model to obtain particle features of the dispersion image, and finally obtains the uniformity of the sample based on the particle features. Thus, the uniformity of the sample can be obtained only by analyzing the dispersion image of the sample, making the uniformity detection simple and quick, and the mixing uniformity can be detected online during the production of battery materials, thereby improving production efficiency.

[0050] In this embodiment, a system for detecting the uniformity of a mixture is provided. Figure 3 As shown, the mixing uniformity detection system includes a dispersion system, a robot, the above-mentioned computer equipment and an imaging device.

[0051] The dispersion system includes an air pump, a venturi tube and a slide holder. The air pump and the venturi tube are connected through an air pipeline. A valve is also provided on the air pipeline. A nozzle is provided at the end of the venturi tube. A sample storage container is provided below the venturi tube. A sample sampler is provided between the nozzle and the sample storage container. A weight sensor is provided on the slide holder. The robot is used to place the sample taken from the mixer into the sample storage container according to the first target running trajectory and to place the slide on the slide holder according to the second target running trajectory. The computer device is used to determine whether the slide is placed on the slide holder according to the weight detected by the weight sensor. When the slide is placed on the slide holder, the air pump is pressurized and the valve in the air pipeline is opened so that the nozzle sprays the sample in the sample storage container onto the slide. The computer device is also used to transfer the carrier with the dispersed sample to the imaging platform. The imaging device is used to shoot the carrier with the dispersed sample on the imaging platform to obtain a dispersion image.

[0052] In an optional embodiment, the robot takes a sample from the left, middle and right of the mixer and places it in the dispersion system. The robot includes a mechanical arm and a grasping mechanism, the grasping mechanism includes a base, a group of clamping mechanisms, a sample storage container and at least one longitudinal sliding mechanism, and the longitudinal sliding mechanism has at least two sliders that can be relatively displaced along the y-axis direction.

[0053] For example, Figure 3As shown, the dispersion system includes an air pump, an air pipeline, an electric valve, a venturi tube, a sample storage container, a sample sampler and a slide holder. The air pump is connected to the air pipeline, the electric valve is installed on the air pipeline, the end of the air pipeline is connected to the venturi tube, the end of the venturi tube is installed with a nozzle, the inverted cone sample storage container is placed under the venturi tube, and the sample sampler is installed between the nozzle and the inverted cone sample storage container to connect and inhale the sample. The slide holder is placed vertically 5 to 10 cm in front of the nozzle. The computer equipment receives the electric valve signal and the robot signal through electrical signals to realize the automatic execution of the sampling dispersion process.

[0054] The air pump achieves the purpose of spraying the sample onto the glass slide under positive pressure by pressurizing the air. The electric valve is installed on the gas pipeline and the pressure is adjusted by adjusting the opening. The function of the venturi tube is to change the air flow in the gas pipeline from large to small, so as to speed up the gas flow rate and form a "vacuum" area behind the venturi outlet. When this vacuum area is close to the sample sampler connected to the nozzle, it will adsorb the material, so as to achieve the purpose of absorbing the sample and spraying it onto the glass slide under positive pressure.

[0055] The computer device connects the server and the robot control signal through the PLC, and the operation process includes the following steps: 1. The robot places the sample taken in the inverted cone sample storage container;

[0056] 2. The robot places the slide on the slide holder, and the slide holder is equipped with a weight sensor;

[0057] 3. After the weight sensor obtains the sample placement signal, it automatically transmits instructions to the server and starts dispersion. The PLC transmits instructions to the electric valve of the gas pipeline. The electric valve opens, the air pump increases pressure, and the nozzle built based on the Venturi tube sucks the sample in the sample storage container into the cavity and sprays it onto the slide.

[0058] In an optional embodiment, the robot includes a mechanical arm and a grasping structure connected to the mechanical arm. The computer device is also used to: obtain the starting point and the ending point of the mechanical arm, use a 3-5-3 degree polynomial to interpolate between the starting point and the ending point to obtain the angle range of each interpolation point; constrain the angle range of each interpolation point using a preset constraint condition; determine multiple initial operation trajectories of the mechanical arm using the angle range of each interpolation point after the constraint; and optimize the multiple initial operation trajectories with the shortest operation time of the mechanical arm to obtain the first target operation trajectory or the second target operation trajectory of the mechanical arm.

[0059] For example, the robot moves between a given starting point and an end point. To maintain the dual optimality of time and energy, it is necessary to plan the interpolation points between the paths. The specific method is:

[0060] Use a 3-5-3rd order polynomial to interpolate between the initial point and the end point of the robot, set 4 interpolation points, and use θij to represent the interpolation angle of joint i, where i represents the number of joints (i=1,2,3,4,5) and j represents the sequence number of the difference point (j=1,2,3,4).

[0061] The general formula of the 3-5-3 spline polynomial of the i-th joint is:

[0062]

[0063] Among them l j1 (t), l j2 (t), l j3 (t) represent the trajectory of the 3-5-3 spline polynomial. The coefficient a in the polynomial can be obtained according to the constraints, and the matrix A can be obtained according to the constraints and constraint boundaries. The constraints and constraint boundaries are only related to time t. ij represents the displacement of the jth interpolation of the ith joint, t1, t2, t3, respectively represent the time of the three-segment polynomial interpolation of the ith joint, formula (2) represents the displacement matrix of the joint angle, and formula (3) is the solution equation of the coefficient a.

[0064]

[0065] θ=[0 0 0 0 0 0x j3 0 0x j0 0 0x j2 x j1 ] T Formula (2)

[0066] a=A -1 θ=[a j13 a j12 a j11 a j10 a j25 a j24 a j23 a j22 a j21 a j20 a j33 a j32 a j31 a j30 ] T Formula (3)

[0067] Among them, the meaning of matrix A is: in joint planning, the joint is planned using a cubic polynomial at time t1, a quintic polynomial at time t2, and a cubic polynomial at time t3.

[0068] Formula (3) can also be written as Aa = θ, so the corresponding matrices can be multiplied to get the θ matrix. First, the first three rows of matrix A are multiplied by matrix a. It can be found that the first row is the displacement of the cubic polynomial, and there is a -1 behind it, which is the displacement of the quintic polynomial when time is equal to 0; the second row is the acceleration, and the -1 behind it is the speed of the quintic polynomial when time is equal to 0; the third row is the acceleration, and the -2 behind it is the acceleration of the quintic polynomial when time is equal to 0. The same is true for the fourth to sixth rows. The seventh to ninth rows are the so-called third segment, so 1 or 2 is not subtracted, so the displacement is equal to xj3. The tenth row represents aj10 = 0, which is at the initial point, time is zero, so the displacement of the first segment is also zero. In the cubic polynomial planning, this formula can be obtained when time is zero. The eleventh row represents aj11 = 0. In the first segment of the cubic polynomial planning, this formula can be obtained by substituting the speed function when time is zero. The twelfth line shows that aj12=0. In the first cubic polynomial planning, when the time is zero, the acceleration function is substituted to get this formula. The thirteenth line shows that aj30=xj2. In the third cubic polynomial planning, when the time is zero, the displacement function is substituted to get this formula. The fourteenth line shows that aj20=xj1. In the third cubic polynomial planning, when the time is zero, the displacement function is substituted to get this formula.

[0069] In an optional embodiment, the imaging device is connected to the controller for communication, and the computer device is further used to: use the PLC signal to adjust the focus of the lens of the imaging device so that the scattered image meets a preset standard. For example, the preset standard may be that the number of particles in the scattered image is greater than 10,000.

[0070] Among them, the imaging device includes an LED transmission / reflection light source and a lens. The lens includes but is not limited to a microscope imaging lens and an infrared imaging lens. The lens can be a standard objective lens with a magnification of 5X or 10X.

[0071] The mixing uniformity detection system provided in this embodiment can obtain the sample dispersion image of the battery material online during the battery material production process by setting up a dispersion system, a robot and an imaging device, and further use computer equipment to analyze the sample dispersion image to obtain the uniformity of the battery material sample, so as to perform online detection of the mixing uniformity during the battery material production process and improve production efficiency.

[0072] In this embodiment, a device for determining the uniformity of a mixture is also provided, which is used to implement the above-mentioned embodiments and preferred embodiments, and the descriptions that have been made will not be repeated. As used below, the term "module" can implement a combination of software and / or hardware of a predetermined function. Although the devices described in the following embodiments are preferably implemented in software, the implementation of hardware, or a combination of software and hardware, is also possible and conceivable.

[0073] This embodiment provides a device for determining the uniformity of a mixture. Figure 4 As shown, including:

[0074] The acquisition module 401 is used to acquire a dispersion image of the sample.

[0075] The feature extraction module 402 is used to extract features from the scattered images to obtain an image feature set.

[0076] The particle feature determination module 403 is used to input the image feature set into the trained neural network model to obtain the particle features of the dispersed image.

[0077] The uniformity determination module 404 is used to obtain the uniformity of the sample according to the particle characteristics.

[0078] In some optional embodiments, the image feature set includes at least one of the following image features: image brightness feature, image edge feature, image texture feature, image color feature, and diameter of particles in the image.

[0079] In some optional embodiments, the neural network model includes multiple convolutional layers, each convolutional layer is used to aggregate the features of each node with the features of its neighboring nodes.

[0080] The further functional description of each of the above modules and units is the same as that of the above corresponding embodiments and will not be repeated here.

[0081] The mixing uniformity determination device in this embodiment is presented in the form of a functional unit, where the unit refers to an ASIC (Application Specific Integrated Circuit) circuit, a processor and memory that executes one or more software or fixed programs, and / or other devices that can provide the above functions.

[0082] The embodiment of the present invention also provides a computer device having the above Figure 4 The device for determining the uniformity of the mixture is shown.

[0083] See also Figure 5 , Figure 5 is a schematic diagram of the structure of a computer device provided by an optional embodiment of the present invention, such as Figure 5As shown, the computer device includes: one or more processors 10, a memory 20, and interfaces for connecting various components, including high-speed interfaces and low-speed interfaces. Various components are connected to each other using different buses for communication, and can be installed on a common mainboard or installed in other ways as needed. The processor can process the instructions executed in the computer device, including instructions stored in or on the memory to display the graphical information of the GUI on an external input / output device (such as, a display device coupled to the interface). In some optional embodiments, if necessary, multiple processors and / or multiple buses can be used together with multiple memories and multiple memories. Similarly, multiple computer devices can be connected, and each device provides some necessary operations (for example, as a server array, a group of blade servers, or a multi-processor system). Figure 5 A processor 10 is taken as an example.

[0084] The processor 10 may be a central processing unit, a network processor or a combination thereof. The processor 10 may further include a hardware chip. The hardware chip may be a dedicated integrated circuit, a programmable logic device or a combination thereof. The programmable logic device may be a complex programmable logic device, a field programmable gate array, a general purpose array logic or any combination thereof.

[0085] The memory 20 stores instructions executable by at least one processor 10, so that at least one processor 10 executes the method shown in the above embodiment.

[0086] The memory 20 may include a program storage area and a data storage area, wherein the program storage area may store an operating system, an application required for at least one function; the data storage area may store data created according to the use of the computer device, etc. In addition, the memory 20 may include a high-speed random access memory, and may also include a non-transient memory, such as at least one disk storage device, a flash memory device, or other non-transient solid-state storage device. In some optional embodiments, the memory 20 may optionally include a memory remotely arranged relative to the processor 10, and these remote memories may be connected to the computer device via a network. Examples of the above-mentioned network include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and combinations thereof.

[0087] The memory 20 may include a volatile memory, such as a random access memory; the memory may also include a non-volatile memory, such as a flash memory, a hard disk or a solid state drive; the memory 20 may also include a combination of the above types of memory.

[0088] The computer device also includes an input device 30 and an output device 40. The processor 10, the memory 20, the input device 30 and the output device 40 may be connected via a bus or other means. Figure 5 The example of connecting through bus is taken in the following.

[0089] The input device 30 can receive input digital or character information, and generate key signal input related to the user settings and function control of the computer device, such as a touch screen, a keypad, a mouse, a track pad, a touch pad, an indicator bar, one or more mouse buttons, a trackball, a joystick, etc. The output device 40 may include a display device, an auxiliary lighting device (e.g., an LED) and a tactile feedback device (e.g., a vibration motor), etc. The above-mentioned display device includes but is not limited to a liquid crystal display, a light emitting diode, a display and a plasma display. In some optional embodiments, the display device can be a touch screen.

[0090] The embodiment of the present invention also provides a computer-readable storage medium. The method according to the embodiment of the present invention can be implemented in hardware, firmware, or can be implemented as a computer code that can be recorded in a storage medium, or can be implemented as a computer code that is originally stored in a remote storage medium or a non-temporary machine-readable storage medium and will be stored in a local storage medium through a network download, so that the method described herein can be stored in such software processing on a storage medium using a general-purpose computer, a dedicated processor, or programmable or dedicated hardware. Among them, the storage medium can be a magnetic disk, an optical disk, a read-only storage memory, a random access memory, a flash memory, a hard disk or a solid-state hard disk, etc.; further, the storage medium can also include a combination of the above types of memories. It can be understood that a computer, a processor, a microprocessor controller, or programmable hardware includes a storage component that can store or receive software or computer code. When the software or computer code is accessed and executed by a computer, a processor, or hardware, the method shown in the above embodiment is implemented.

[0091] A part of the present invention may be applied as a computer program product, such as a computer program instruction, which, when executed by a computer, can call or provide the method and / or technical solution according to the present invention through the operation of the computer. Those skilled in the art should understand that the existence of the computer program instruction in a computer-readable medium includes, but is not limited to, a source file, an executable file, an installation package file, etc., and accordingly, the way in which the computer program instruction is executed by the computer includes, but is not limited to: the computer directly executes the instruction, or the computer compiles the instruction and then executes the corresponding compiled program, or the computer reads and executes the instruction, or the computer reads and installs the instruction and then executes the corresponding installed program. Here, the computer-readable medium may be any available computer-readable storage medium or communication medium accessible to the computer.

[0092] Although the embodiments of the present invention have been described in conjunction with the accompanying drawings, those skilled in the art may make various modifications and variations without departing from the spirit and scope of the present invention, and such modifications and variations are all within the scope defined by the appended claims.

Claims

1. A method for determining mixing uniformity, characterized in that: include: Acquire a dispersion image of the sample; Performing feature extraction on the scattered images to obtain an image feature set; Inputting the image feature set into the trained neural network model to obtain particle features of the dispersed image; The uniformity of the sample is obtained based on the particle characteristics.

2. The method according to claim 1, characterized in that The image feature set includes at least one of the following image features: image brightness feature, image edge feature, image texture feature, image color feature, and diameter of particles in the image.

3. The method according to claim 1, characterized in that The neural network model includes multiple convolutional layers, each of which is used to aggregate the features of each node with the features of its neighboring nodes.

4. A device for determining mixing uniformity, characterized in that: The device comprises: An acquisition module, used for acquiring a dispersion image of a sample; A feature extraction module, used to extract features from the scattered images to obtain an image feature set; A particle feature determination module, used for inputting the image feature set into a trained neural network model to obtain particle features of the dispersed image; The uniformity determination module is used to obtain the uniformity of the sample according to the particle characteristics.

5. A computer device, characterized in that: include: A memory and a processor, wherein the memory and the processor are communicatively connected to each other, the memory stores computer instructions, and the processor executes the method for determining the uniformity of a mixture according to any one of claims 1 to 3 by executing the computer instructions.

6. A mixing uniformity detection system, characterized in that: include: The dispersion system comprises an air pump, a venturi tube and a slide holder, wherein the air pump and the venturi tube are connected through an air pipeline, a valve is provided on the air pipeline, a nozzle is provided at the end of the venturi tube, a sample storage device is provided below the venturi tube, and a sample sampler is provided between the nozzle and the sample storage device; a weight sensor is provided on the slide holder; A robot, used to place the sample taken from the mixer into the sample storage container according to the first target running trajectory, and to place the slide on the slide holder according to the second target running trajectory; The computer device of claim 5, used to determine whether the glass slide is placed on the glass slide holder according to the weight detected by the weight sensor, and when the glass slide is placed on the glass slide holder, control the air pump to pressurize and the valve in the air pipeline to open, so that the nozzle sprays the sample in the sample storage container onto the glass slide; It is also used to transfer the slide with the dispersed sample to the imaging platform; The imaging device is used to photograph the carrier sheet with the dispersed sample on the imaging platform to obtain a dispersed image.

7. The mixing uniformity detection system according to claim 6, characterized in that: The robot comprises a mechanical arm and a grasping structure connected to the mechanical arm, and the computer device is further used for: Obtaining the starting point and the ending point of the robotic arm, and using a 3-5-3 degree polynomial to interpolate between the starting point and the ending point to obtain the angle range of each interpolation point; Constraining the angle range of each interpolation point using a preset constraint condition; Determine a plurality of initial operation trajectories of the robot arm by using the constrained angle range of each interpolation point; The first target running trajectory or the second target running trajectory of the robot arm is obtained by searching for the one with the shortest running time of the robot arm among multiple initial running trajectories.

8. The mixing uniformity detection system according to claim 6, characterized in that: The imaging device is communicatively connected to the controller, and the computer device is further used for: The PLC signal is used to adjust the focus of the lens of the imaging device so that the scattered image meets the preset standard.

9. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores computer instructions, and the computer instructions are used to enable a computer to execute the method for determining the uniformity of a mixture according to any one of claims 1 to 3.

10. A computer program product, characterized in that The method comprises computer instructions, wherein the computer instructions are used to enable a computer to execute the method for determining the uniformity of a mixture according to any one of claims 1 to 3.

Images