Anode mud removing method, system, equipment and medium

Abstract

The invention provides an anode mud removing method, system and device and a medium, and relates to the technical field of hydrometallurgy, the method comprises the steps that a plurality of initial images are obtained, and the initial images correspond to different areas of a to-be-removed plate; performing multi-stage image preprocessing on each initial image to obtain a corresponding preprocessed image; corresponding comprehensive texture features are extracted from the preprocessed images; inputting the comprehensive texture features into a preset classifier to obtain working condition categories corresponding to different areas of the to-be-cleared board; according to the working condition types, the cleaning modes of different areas of the to-be-cleaned plate are determined; and anode mud on different areas of the to-be-cleaned plate is cleaned in the corresponding cleaning mode. The anode mud is automatically removed, and the removing efficiency of the anode mud is improved.

Description

Technical Field

[0001] The present invention relates to the technical field of hydrometallurgy, and in particular to an anode mud removal method, system, equipment and medium. Background Art

[0002] During the electrolytic refining process, anode film and anode slime, as byproducts, adhere to the anode plates. Anode slime, with its complex composition, negatively impacts electrolysis efficiency, while anode film, with its relatively pure composition, improves efficiency. To minimize the amount of anode slime adhering to the anode plates while preserving the anode film, existing techniques rely on manual observation of the anode slime's presence on the plates for targeted removal. This approach is inefficient and can easily lead to damage to the anode film and residual anode slime. Summary of the Invention

[0003] In view of this, the purpose of the present invention is to overcome the deficiencies in the prior art and provide a method, system, equipment and medium for removing anode mud. The present invention provides the following technical solutions:

[0004] In a first aspect, the present application provides an anode mud removal method, the method comprising: acquiring multiple initial images, each of the initial images corresponding to a different area of a plate to be removed; performing multi-level image preprocessing on each of the initial images to obtain a corresponding preprocessed image; extracting corresponding comprehensive texture features from each of the preprocessed images; inputting each of the comprehensive texture features into a preset classifier to obtain a working condition category corresponding to the different areas of the plate to be removed; determining a cleaning mode for the different areas of the plate to be removed according to each of the working condition categories; and removing the anode mud on the different areas of the plate to be removed using the corresponding cleaning mode.

[0005] In one embodiment, each of the initial images is subjected to multi-level image preprocessing to obtain a corresponding preprocessed image, including: performing Gaussian filtering on the initial image to obtain a first filtered image; performing Laplace filtering on the first filtered image to obtain a second filtered image; and superimposing the first filtered image and the second filtered image according to a preset superposition ratio to obtain a preprocessed image corresponding to the initial image.

[0006] In one embodiment, the extracting corresponding comprehensive texture features from each of the preprocessed images includes: extracting corresponding directional gradient histogram features for each of the preprocessed images; converting each of the preprocessed images into a local binary image based on a local binary pattern; determining the grayscale co-occurrence matrix features corresponding to each of the preprocessed images based on each of the local binary images; and concatenating the grayscale co-occurrence matrix features and the directional gradient histogram features to obtain the comprehensive texture features corresponding to the preprocessed image.

[0007] In one embodiment, obtaining the preset classifier includes: obtaining a data set to be trained, the data set to be trained including multiple images to be trained and working condition labels corresponding to each of the images to be trained; dividing the data set to be trained into a training set, a test set, and a validation set according to a preset division ratio; training a support vector classifier based on the training set, the test set, and the validation set to obtain the preset classifier.

[0008] In one embodiment, the system is applied to an anode mud removal system, the anode mud removal system includes a cleaning terminal, and before cleaning the anode mud on different areas of the plate to be removed in the corresponding cleaning mode, the system further includes: transmitting an ultrasonic signal to the area to be removed, determining the actual distance between the cleaning terminal and the area to be removed based on the echo time of the ultrasonic signal; and adjusting the protrusion distance of the cleaning terminal based on the actual distance, the protrusion distance being used to determine the protrusion degree of the cleaning terminal.

[0009] In one embodiment, the plate to be cleared includes multiple through holes, and the method further includes: obtaining the hole coordinates of each of the through holes, and determining multiple through hole positions based on each of the hole coordinates; sequentially controlling the cleaning end to each of the through hole positions, and performing a preset clearing operation on each of the through holes.

[0010] In one embodiment, the method further includes: if the operating condition category is a preset operating condition category, determining that the corresponding area of the to-be-cleared plate has been cleared.

[0011] In a second aspect, the present application provides an anode mud removal system, the system comprising:

[0012] An image acquisition module, configured to acquire a plurality of initial images, each of the initial images corresponding to a different area of the board to be cleared;

[0013] A preprocessing module, configured to perform multi-level image preprocessing on each of the initial images to obtain a corresponding preprocessed image;

[0014] A feature extraction module, used to extract corresponding comprehensive texture features from each of the pre-processed images;

[0015] A classification module, configured to input each of the comprehensive texture features into a preset classifier to obtain the working condition categories corresponding to different areas of the plate to be cleaned;

[0016] a determination module, configured to determine, according to each of the working condition categories, cleaning modes for different areas of the plate to be cleaned;

[0017] The cleaning module is used to clean the anode mud on different areas of the plate to be cleaned in the corresponding cleaning mode.

[0018] In a third aspect, the present invention provides an electronic device comprising a memory and a processor, wherein the memory stores a computer program, and when the computer program runs on the processor, the anode mud removal method described in the first aspect is executed.

[0019] In a fourth aspect, the present invention provides a computer-readable storage medium storing a computer program, wherein the computer program, when executed by a processor, implements the anode mud removal method described in the first aspect.

[0020] The present application provides an anode mud removal method, system, device and medium, which obtain multiple initial images, each of which corresponds to a different area of a plate to be removed; perform multi-level image preprocessing on each of the initial images to obtain a corresponding preprocessed image; extract corresponding comprehensive texture features from each of the preprocessed images; input each of the comprehensive texture features into a preset classifier to obtain the working condition category corresponding to the different areas of the plate to be removed; determine the removal mode for the different areas of the plate to be removed according to each of the working condition categories; and remove the anode mud from the different areas of the plate to be removed using the corresponding removal mode, thereby achieving automated anode mud removal and improving the anode mud removal efficiency.

[0021] In order to make the above-mentioned objects, features and advantages of the present invention more obvious and easy to understand, preferred embodiments are given below and described in detail with reference to the accompanying drawings. BRIEF DESCRIPTION OF THE DRAWINGS

[0022] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the following briefly introduces the drawings required for use in the embodiments. It should be understood that the following drawings only illustrate certain embodiments of the present invention and therefore should not be regarded as limiting the scope. For ordinary technicians in this field, other relevant drawings can be obtained based on these drawings without paying any creative work.

[0023] Figure 1 A schematic diagram of a process of the anode mud removal method provided in an embodiment of the present application is shown;

[0024] Figure 2 An example diagram of a block of a plate to be cleared provided in an embodiment of the present application is shown;

[0025] Figure 3 Another schematic diagram of the process of the anode mud removal method provided in an embodiment of the present application is shown;

[0026] Figure 4 Another schematic diagram of the process of the anode mud removal method provided in an embodiment of the present application is shown;

[0027] Figure 5 Another schematic diagram of the process of the anode mud removal method provided in an embodiment of the present application is shown;

[0028] Figure 6 Another schematic flow chart of the anode mud removal method provided in an embodiment of the present application is shown;

[0029] Figure 7 A schematic structural diagram of an anode mud removal system provided in an embodiment of the present application is shown;

[0030] Figure 8 A structural schematic diagram of an electronic device provided by an embodiment of the present application is shown.

[0031] Description of main component markings:

[0032] 700-anode mud removal system; 710-image acquisition module; 720-preprocessing module; 730-feature extraction module; 740-classification module; 750-determination module; 760-removal module; 800-electronic equipment; 801-transceiver; 802-processor; 803-memory. DETAILED DESCRIPTION

[0033] The following describes embodiments of the present invention in detail. Examples of the embodiments are shown in the accompanying drawings, wherein the same or similar reference numerals throughout represent the same or similar elements or elements having the same or similar functions. The embodiments described below with reference to the accompanying drawings are exemplary and are intended only to explain the present invention and are not to be construed as limiting the present invention.

[0034] Furthermore, the terms "first" and "second" are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of the technical features being referred to. Thus, a feature identified as "first" or "second" may explicitly or implicitly include one or more of the features. In the description of the present invention, "plurality" means two or more, unless otherwise specifically defined.

[0035] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by those skilled in the art to which this application belongs. The terms used in the template description herein are for the purpose of describing specific embodiments only and are not intended to limit the present invention. The term "and / or" as used herein includes any and all combinations of one or more of the associated listed items.

[0036] Example 1

[0037] Anode mud is mainly formed during the refining process of electrolytic copper, lead, zinc and other metals. Taking the zinc electrolytic refining process as an example, the surface of the zinc anode plate comes into contact with the electrolyte and an oxidation reaction occurs. During the reaction, a dense oxide film gradually forms on the surface of the zinc anode plate, and some loose flocs and particles gradually accumulate to form anode mud. The anode film is relatively pure in composition and dense in structure, which can prevent the anode plate from being directly exposed to the electrolyte, reduce unnecessary chemical reactions, and improve electrolysis efficiency. After the anode film is formed, the anode mud gradually accumulates on the zinc anode plate. It has complex composition and loose shape. It is a by-product of the electrolysis process. This layer of material will affect the efficiency of the electrolysis reaction and reduce production efficiency. In order to remove the anode mud attached to the anode plate as much as possible, the existing technology adopts the method of manually observing the adhesion of the anode mud on the anode plate for targeted removal. This removal method relies on manual experience, is highly subjective, has low removal efficiency, and is prone to damage to the anode film and anode mud residue. For this, please refer to Figure 1 , an embodiment of the present application proposes an anode mud removal method, comprising: steps S110 to S160.

[0038] Step S110 , obtaining a plurality of initial images, each of the initial images corresponding to a different area of the board to be cleared.

[0039] In this embodiment, the plate to be cleaned includes: a metal anode plate, such as a zinc anode plate. Due to the large size of the plate to be cleaned, capturing the entire image of the plate at one time will result in unclear texture features of the captured image. Therefore, a block strategy is adopted to divide the plate to be cleaned into multiple different areas, and image capture is performed on each area in turn to obtain multiple initial images. The specific division strategy can be determined according to actual conditions. For example, see Figure 2 , divide the board to be cleared into 9 rectangular areas, each of which has an area of l×w mm 2 This block acquisition method ensures that the image features of each area are clear, which facilitates subsequent image processing and working condition classification.

[0040] Step S120 , performing multi-level image preprocessing on each of the initial images to obtain a corresponding preprocessed image.

[0041] In this embodiment, multi-level image preprocessing includes: removing high-frequency noise in the image through Gaussian filtering, further enhancing the edge details of the image through Laplace filtering, and finally superimposing the two filtering results in proportion for mixed filtering to achieve the effect of balancing denoising and retaining details. The preprocessed image obtained after multi-level image preprocessing can more clearly show the texture features.

[0042] In one embodiment, see Figure 3 , step S120 includes: steps S121 to S123.

[0043] Step S121 , performing Gaussian filtering on the initial image to obtain a first filtered image.

[0044] In this embodiment, a Gaussian kernel is defined Where σ represents the standard deviation of the Gaussian kernel, which is used to control the width of the Gaussian kernel, and x and y represent the coordinates of the pixels in the initial image. The initial image is convolved with the Gaussian kernel to remove high-frequency noise, and we have: Among them, I G (x, y) represents the pixel value of the initial image at the coordinate (x, y) after Gaussian filtering, I(x, y) represents the pixel value of the initial image at the coordinate (x, y), k represents the radius of the Gaussian kernel, and the value of k is usually 3nσ, where n is an integer used to determine the size of the Gaussian kernel, i and j: index variables used for convolution operations, indicating the offset in the x and y directions.

[0045] In this embodiment, n=1, σ=1, and the Gaussian kernel radius is 3. In other embodiments, the Gaussian kernel radius can be selected according to actual conditions. This is only an example for illustration and is not limiting.

[0046] Step S122: Perform Laplacian filtering on the first filtered image to obtain a second filtered image.

[0047] In this embodiment, a four-neighborhood discrete Laplacian operator is defined, and there exists: Apply the four-neighborhood discrete Laplacian operator to the first filtered image after Gaussian filtering to extract edge details and obtain the second filtered image. The pixel value at the coordinate (x, y) in the second filtered image is

[0048] Step S123 : superimposing the first filtered image and the second filtered image according to a preset superposition ratio to obtain a preprocessed image corresponding to the initial image.

[0049] In this embodiment, the Gaussian filtering result and the Laplace filtering result are superimposed in proportion to perform hybrid filtering to balance denoising and edge preservation. Where α is a scaling factor. A larger value for α results in a more pronounced edge enhancement effect on the preprocessed image, but may introduce noise. A smaller value for α results in a better denoising effect on the preprocessed image, but may blur the edges. In this example, a value of α of 0.5 achieves a good denoising effect. In other embodiments, the value of α may be set based on actual needs.

[0050] Step S130 , extracting corresponding comprehensive texture features from each of the pre-processed images.

[0051] In this embodiment, different texture feature extraction methods are used to extract a variety of texture features from a preset processed image, and the comprehensive texture features of the pre-processed image are determined by combining the multiple texture features.

[0052] It can be understood that different texture feature extraction methods can capture the texture features of the preprocessed image from different angles. By integrating multiple texture features, the accuracy of image analysis is improved, making subsequent image recognition more reliable.

[0053] In one embodiment, see Figure 4 , step S130 includes: steps S131 to S134.

[0054] In step S131 , for each of the pre-processed images, corresponding Histogram of Oriented Gradient (HOG) features are extracted.

[0055] It can be understood that the directional gradient histogram feature is a feature descriptor used for object detection in computer vision and image processing. It constructs features by calculating and counting the gradient direction histogram of the local area of the image. Specifically, extracting the directional gradient histogram feature includes the following steps: (1) Gradient calculation: First, the gradient of the preprocessed image in the horizontal and vertical directions is calculated. These gradients represent the intensity and direction of the pixel change in the preprocessed image. (2) Gradient direction: Calculate the gradient direction value of each pixel position in the preprocessed image. This value represents the direction of the pixel change, usually calculated by the arctan function. (3) Histogram statistics: Divide the preprocessed image into multiple cells, and perform histogram statistics on the gradient direction in each cell to capture local texture features. (4) Normalization: Combine multiple cells into blocks, and normalize the histogram within the block to enhance the robustness of the feature to changes in illumination and contrast. (5) Feature splicing: Splice the normalized histograms of all blocks into a high-dimensional feature vector. This vector is the directional gradient histogram feature corresponding to the preprocessed image. The dimension M of the directional gradient histogram feature can be calculated by the formula Calculate [ ], where w1 and w2 represent the width and height of the detection window, b3 represents the horizontal block movement step, b4 represents the vertical block movement step, n represents the number of gradient directions, c1 represents the cell width, and c2 represents the cell height. By extracting the histogram of oriented gradients (HG) features, we can effectively describe the local shape and edge direction in the image, thereby improving recognition accuracy and robustness. The actual parameter values can be determined based on the actual situation.

[0056] Step S132 : converting each of the pre-processed images into a local binary image based on local binary patterns (LBP).

[0057] It can be understood that each pixel in the preprocessed image is taken as the central pixel in turn, and the neighborhood grayscale comparison is performed. If the grayscale value of the neighborhood point is greater than or equal to the central pixel, it is recorded as 1, otherwise it is recorded as 0, thereby generating a unique binary code for each pixel, and then converting the preprocessed image into the corresponding local binary image according to the binary code.

[0058] Step S133 : Based on each of the local binary images, gray-level co-occurrence matrix features corresponding to each of the pre-processed images are determined respectively.

[0059] For each local binary image, the Gray-Level Co-occurrence Matrix (GLCM) is further calculated to extract the image's texture information. The GLCM is a statistical tool used to analyze the co-occurrence probability of grayscale values of pixel pairs in an image at specific directions and distances. This allows for the extraction of texture features such as energy, entropy, and contrast. These features help describe the image's texture structure and facilitate image classification or recognition.

[0060] Step S134 , concatenating the gray-level co-occurrence matrix features and the directional gradient histogram features to obtain the comprehensive texture features corresponding to the preprocessed image.

[0061] It can be understood that the gray-level co-occurrence matrix feature can capture the texture information of the image, such as the distribution and correlation of local grayscale values, while the oriented gradient histogram feature focuses on the directional information of edges and shapes in the image. By concatenating these two features, a vector can be obtained that more comprehensively describes the texture and structural characteristics of the image, which helps improve the performance of image recognition and classification tasks.

[0062] In step S140 , each of the comprehensive texture features is input into a preset classifier to obtain the working condition categories corresponding to different areas of the plate to be cleaned.

[0063] In this embodiment, the preset classifier is a pre-trained support vector machine classifier (SVM), and the working condition categories include: no cleaning required, light residue, and heavy residue. The working condition category corresponding to each area is obtained by inputting the comprehensive texture features of the image corresponding to each different area into the preset classifier.

[0064] In one embodiment, see Figure 5 , obtaining the preset classifier, including: steps S141 to S143.

[0065] Step S141 : obtaining a dataset to be trained, wherein the dataset to be trained includes a plurality of images to be trained and working condition labels corresponding to the images to be trained.

[0066] In this embodiment, the images to be trained are initial images corresponding to different areas of different boards to be cleared, and the working condition labels corresponding to the images to be trained indicate the working condition categories corresponding to the training images.

[0067] Step S142: Divide the dataset to be trained into a training set, a test set, and a validation set according to a preset division ratio.

[0068] For example, the training data set is divided into a training set, a test set, and a validation set according to a preset division ratio of 8:1:1, and a support vector classifier is trained based on the training set, the test set, and the validation set.

[0069] Step S143: training a support vector classifier based on the training set, the test set, and the validation set to obtain the preset classifier.

[0070] In this embodiment, training a support vector classifier based on the training set, the test set, and the validation set includes learning classification rules on the training set, adjusting classifier parameters through the validation set to avoid overfitting, and finally evaluating the classifier performance on the test set, thereby obtaining a preset classifier that can be used for actual classification tasks.

[0071] Step S150: determining the cleaning modes for different areas of the plate to be cleaned according to the types of the working conditions.

[0072] In this embodiment, the operating condition categories include: no cleaning required, light residue, and heavy residue, and the cleaning modes include: crushing cleaning and flexible cleaning. When the operating condition category of the corresponding area is light residue, the cleaning mode is determined to be flexible cleaning. When the operating condition category of the corresponding area is heavy residue, the cleaning mode is determined to be crushing cleaning.

[0073] Step S160: Cleaning the anode mud on different areas of the plate to be cleaned in the corresponding cleaning mode.

[0074] The anode mud removal method provided in the embodiment of the present application is applied to an anode mud removal system, and the anode mud removal system includes a cleaning end, which is used to connect different cleaning tools. Specifically, when the cleaning mode is determined to be a crushing cleaning module, the cleaning end is connected to the crushing tool to crush the anode mud and then the scraper is replaced to scrape the anode mud; when the cleaning mode is determined to be flexible cleaning, the cleaning end is connected to the scraper to remove the anode mud.

[0075] In one embodiment, the anode mud removal method is applied to an anode mud removal system, wherein the anode mud removal system includes a removal terminal, see Figure 6 , steps S171 to S172 are also included before step S160.

[0076] Step S171 , transmitting an ultrasonic signal to the area to be cleared, and determining the actual distance between the clearing end and the area to be cleared according to the echo time of the ultrasonic signal.

[0077] It is understood that the actual distance between the cleaning end and the area to be cleaned on the plate to be cleaned can be calculated based on the echo time of the ultrasonic signal and the ultrasonic velocity. The area to be cleaned is the current cleaning area on the plate to be cleaned.

[0078] Step S172: adjusting the protruding distance of the cleaning end according to the actual distance, wherein the protruding distance is used to determine the protruding degree of the cleaning end.

[0079] It should be noted that in the process of removing the anode mud from different areas of the plate to be removed one by one, due to the uneven characteristics of the plate to be removed, the protrusion distance of the cleaning end needs to be dynamically adjusted when cleaning different areas to avoid damaging the plate to be removed during the cleaning process.

[0080] In one embodiment, the plate to be cleared includes multiple through holes, and the method further includes: obtaining the hole coordinates of each of the through holes, and determining multiple through hole positions based on each of the hole coordinates; sequentially controlling the cleaning end to each of the through hole positions, and performing a preset clearing operation on each of the through holes.

[0081] It is understood that the plate to be cleaned includes multiple circular through-holes. After the anode mud on the surface of the plate to be cleaned is removed according to the corresponding cleaning mode, the circular through-hole positions need to be cleaned separately. Specifically, the through-hole positions on the plate to be cleaned are located according to the hole coordinates of each through-hole, and then the through-holes are cleared.

[0082] In one embodiment, the method further includes: if the operating condition category is a preset operating condition category, determining that the corresponding area of the to-be-cleared plate has been cleared.

[0083] In this embodiment, the preset working condition category is: no need to clean. When it is determined that the working condition category of the corresponding area is no need to clean, it is determined that the corresponding area meets the target cleaning standard and the corresponding area is cleaned.

[0084] The anode mud removal method provided in the embodiment of the present application obtains multiple initial images, each of the initial images corresponds to a different area of the plate to be removed; multi-level image preprocessing is performed on each of the initial images to obtain a corresponding preprocessed image; corresponding comprehensive texture features are extracted from each of the preprocessed images; each of the comprehensive texture features is input into a preset classifier to obtain the working condition category corresponding to the different areas of the plate to be removed; according to each of the working condition categories, a cleaning mode for the different areas of the plate to be removed is determined; and the anode mud on the different areas of the plate to be removed is removed using the corresponding cleaning mode, thereby realizing automated anode mud removal and improving anode mud removal efficiency.

[0085] Example 2

[0086] Also, see Figure 7 The present embodiment further provides an anode mud removal system 700, the system comprising:

[0087] An image acquisition module 710 is configured to acquire a plurality of initial images, each of the initial images corresponding to a different area of the board to be cleared;

[0088] A preprocessing module 720 is configured to perform multi-level image preprocessing on each of the initial images to obtain a corresponding preprocessed image;

[0089] A feature extraction module 730 is used to extract corresponding comprehensive texture features from each of the pre-processed images;

[0090] A classification module 740 is used to input each of the comprehensive texture features into a preset classifier to obtain the working condition categories corresponding to different areas of the plate to be cleaned;

[0091] A determination module 750 is configured to determine, according to each of the working condition categories, cleaning modes for different areas of the plate to be cleaned;

[0092] The cleaning module 760 is used to clean the anode mud on different areas of the plate to be cleaned in the corresponding cleaning mode.

[0093] The anode mud removal system 700 provided in the embodiment of the present application can execute the anode mud removal method provided in the above-mentioned method embodiment 1, and will not be described again here to avoid repetition.

[0094] The anode mud removal system provided in the embodiment of the present application acquires multiple initial images through an image acquisition module, and each of the initial images corresponds to a different area of the plate to be removed; the preprocessing module performs multi-level image preprocessing on each of the initial images to obtain a corresponding preprocessed image; the feature extraction module extracts corresponding comprehensive texture features from each of the preprocessed images; the classification module inputs each of the comprehensive texture features into a preset classifier to obtain the working condition category corresponding to the different areas of the plate to be removed; the determination module determines the cleaning mode for the different areas of the plate to be removed according to each of the working condition categories; the cleaning module removes the anode mud on the different areas of the plate to be removed in the corresponding cleaning mode, thereby realizing automatic removal of the anode mud and improving the efficiency of anode mud removal.

[0095] Example 3

[0096] In addition, an embodiment of the present invention provides an electronic device, including a memory and a processor, wherein the memory stores a computer program, and when the computer program runs on the processor, the anode mud removal method provided in Example 1 is executed.

[0097] For details, see Figure 8 The electronic device 800 includes: a transceiver 801, a bus interface and a processor 802, wherein the processor 802 is configured to obtain a plurality of initial images, each of the initial images corresponding to a different area of the plate to be cleared; perform multi-level image preprocessing on each of the initial images to obtain a corresponding preprocessed image; extract corresponding comprehensive texture features from each of the preprocessed images; input each of the comprehensive texture features into a preset classifier to obtain a working condition category corresponding to the different area of the plate to be cleared; determine a clearing mode for the different area of the plate to be cleared according to each of the working condition categories; and clear the anode mud on the different area of the plate to be cleared using the corresponding clearing mode.

[0098] In the embodiment of the present invention, the electronic device 800 further includes a memory 803. Figure 8 In the embodiment, the bus architecture can include any number of interconnected buses and bridges, specifically linking together various circuits of one or more processors represented by processor 802 and memory represented by memory 803. The bus architecture can also link together various other circuits such as peripheral devices, voltage regulators, and power management circuits, which are all well known in the art and therefore will not be further described herein. The bus interface provides an interface. The transceiver 801 can be multiple components, that is, including a transmitter and a receiver, providing a unit for communicating with various other devices on a transmission medium. The processor 802 is responsible for managing the bus architecture and general processing, and the memory 803 can store data used by the processor 802 when performing operations.

[0099] The electronic device 800 provided in the embodiment of the present invention can execute the anode mud removal method provided in the above-mentioned method embodiment 1, which will not be described again here to avoid repetition.

[0100] Example 4

[0101] In addition, an embodiment of the present invention provides a computer-readable storage medium, on which a computer program is stored. When the computer program is executed by a processor, the anode mud removal method provided in Example 1 is implemented.

[0102] In this embodiment, the computer-readable storage medium may be a read-only memory (ROM), a random access memory (RAM), a magnetic disk, or an optical disk.

[0103] The computer-readable storage medium provided in this embodiment can implement the anode mud removal method provided in Example 1, and will not be described again here to avoid repetition.

[0104] In all examples shown and described herein, any specific values should be interpreted as merely exemplary and not limiting, and thus other examples of the exemplary embodiments may have different values.

[0105] It should be noted that similar reference numerals and letters denote similar items in the following drawings, and therefore, once an item is defined in one drawing, it does not need to be further defined or explained in subsequent drawings.

[0106] The above-described embodiments merely illustrate several implementations of the present invention, and while the descriptions are relatively specific and detailed, they should not be construed as limiting the scope of the present invention. It should be noted that variations and modifications are possible without departing from the scope of the present invention, and such variations and modifications are fully within the scope of protection of the present invention.

Claims

1. A method for removing anode mud, characterized in that: The method comprises: Acquiring a plurality of initial images, each of the initial images corresponding to a different area of the board to be cleared; Performing multi-level image preprocessing on each of the initial images to obtain a corresponding preprocessed image; Extracting corresponding comprehensive texture features from each of the preprocessed images; Inputting each of the comprehensive texture features into a preset classifier to obtain the working condition categories corresponding to different areas of the plate to be cleaned; Determining the cleaning modes for different areas of the plate to be cleaned according to the types of working conditions; The anode mud on different areas of the plate to be removed is removed in the corresponding removal mode.

2. The anode mud removal method according to claim 1, characterized in that: The performing multi-level image preprocessing on each of the initial images to obtain a corresponding preprocessed image includes: Performing Gaussian filtering on the initial image to obtain a first filtered image; performing Laplace filtering on the first filtered image to obtain a second filtered image; The first filtered image and the second filtered image are superimposed according to a preset superposition ratio to obtain a preprocessed image corresponding to the initial image.

3. The anode mud removal method according to claim 1, characterized in that: The extracting corresponding comprehensive texture features from each of the pre-processed images comprises: For each of the preprocessed images, extracting corresponding directional gradient histogram features; Converting each of the preprocessed images into a local binary image based on a local binary pattern; Based on each of the local binary images, respectively determining gray-level co-occurrence matrix features corresponding to each of the pre-processed images; The gray-level co-occurrence matrix feature and the directional gradient histogram feature are connected in series to obtain the comprehensive texture feature corresponding to the preprocessed image.

4. The anode mud removal method according to claim 1, characterized in that: Obtaining the preset classifier includes: Acquire a dataset to be trained, the dataset to be trained including a plurality of images to be trained and working condition labels corresponding to the images to be trained; Divide the training data set into a training set, a test set, and a validation set according to a preset division ratio; A support vector classifier is trained based on the training set, the test set, and the validation set to obtain the preset classifier.

5. The anode mud removal method according to claim 1, characterized in that: Applicable to an anode mud removal system, the anode mud removal system includes a removal terminal, and before removing the anode mud on different areas of the plate to be removed in the corresponding removal mode, further includes: transmitting an ultrasonic signal to the area to be cleared, and determining the actual distance between the cleaning end and the area to be cleared based on the echo time of the ultrasonic signal; The protrusion distance of the cleaning end is adjusted according to the actual distance, and the protrusion distance is used to determine the protrusion degree of the cleaning end.

6. The anode mud removal method according to claim 5, characterized in that: The plate to be cleared comprises a plurality of through holes, and the method further comprises: Obtaining hole coordinates of each through hole, and determining a plurality of through hole positions according to each hole coordinate; The cleaning end is controlled to move to the position of each through hole in sequence, and a preset dredging operation is performed on each through hole.

7. The anode mud removal method according to claim 6, characterized in that: The method further comprises: If the working condition category is a preset working condition category, it is determined that the corresponding area of the to-be-cleared plate has been cleared.

8. An anode mud removal system, characterized in that: The system comprises: An image acquisition module, configured to acquire a plurality of initial images, each of the initial images corresponding to a different area of the board to be cleared; A preprocessing module, configured to perform multi-level image preprocessing on each of the initial images to obtain a corresponding preprocessed image; A feature extraction module, used to extract corresponding comprehensive texture features from each of the pre-processed images; A classification module, configured to input each of the comprehensive texture features into a preset classifier to obtain the working condition categories corresponding to different areas of the plate to be cleaned; a determination module, configured to determine, according to each of the working condition categories, cleaning modes for different areas of the plate to be cleaned; The cleaning module is used to clean the anode mud on different areas of the plate to be cleaned in the corresponding cleaning mode.

9. An electronic device, characterized in that: The method comprises a memory and a processor, wherein the memory stores a computer program, and when the computer program is run on the processor, the anode mud removal method according to any one of claims 1 to 7 is executed.

10. 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 anode slime removal method according to any one of claims 1 to 7 is implemented.

Images