Sludge purification method, system and device for intelligent separation of super-hydrophilic and super-oleophobic

Abstract

The present application provides a sludge purification method, system and device for intelligent separation of superhydrophilic and superoleophobic, including: obtaining the original image of sludge particles of the sample to be processed; pre-processing the original image of the sludge particles to obtain the first sludge particle image data; preliminarily separating the water and oil in the sludge through the superhydrophilic and superoleophobic separation membrane assembly; further processing the separated water and oil through the separation membrane module to ensure complete separation; using an intelligent control system to monitor the separation process in real time and adjust the processing parameters to optimize the separation effect; the treated water and oil are collected separately to achieve sludge purification and resource recovery. The present application significantly improves the water-oil separation efficiency by using a special separation membrane and an advanced intelligent control system, and achieves efficient purification and resource recovery of sludge; and is simple to operate, easy to industrialize, and has good economic and environmental benefits.

Description

Technical Field

[0001] The present application belongs to the technical field of sewage treatment, and relates to a sludge purification method, and in particular to a sludge purification method, system and device for intelligent separation of super-hydrophilic and super-oleophobic sludge that comprehensively considers multiple indicators such as economic factors, social demographic factors, resources and environmental factors. Background Art

[0002] In recent years, with the improvement of urbanization, the continuous development of economy and the rapid advancement of industrialization, the amount of sewage generated and treated in my country has shown an upward trend. As a by-product of sewage treatment, the amount of sludge generated has also increased accordingly. In terms of technology, my country has made certain progress in sludge treatment technology. Traditional treatment methods include landfill, incineration, agricultural use, etc. However, in recent years, with the improvement of environmental protection requirements and technological innovation, some new treatment technologies have also been studied and applied, committed to achieving the reduction, stabilization and harmless treatment of sludge, and exploring ways to utilize it as a resource.

[0003] In particular, sludge treatment processes often have the problem of difficulty in separating water-oil mixtures, while traditional chemical and physical treatment methods are inefficient and costly.

[0004] Furthermore, although the existing sludge treatment scale is constantly expanding, it still faces some problems, such as: the construction and planning of sludge treatment facilities in some areas lag behind and cannot meet the growing demand for sludge treatment, resulting in the inability to effectively treat the sludge, posing a threat to the environment; and the sludge treatment technology is uneven and the treatment effect is poor; even secondary pollution may be generated during the sludge treatment process, such as wastewater, waste gas, solid waste, etc., posing a serious threat to the environment.

[0005] At present, a series of studies have been carried out at home and abroad, and it has been found that superhydrophilic and superoleophobic technologies can utilize the surface characteristics of materials to achieve efficient separation of water and oil. It is a green and environmentally friendly sludge treatment technology with broad application prospects.

[0006] Therefore, in the existing sludge purification technology, how to utilize the material surface characteristics of superhydrophilic and superoleophobic technologies to purify sludge and achieve efficient separation of water and oil is an urgent problem to be solved. Summary of the invention

[0007] In view of the shortcomings of the prior art mentioned above, the purpose of the present application is to provide a sludge purification method, system and device for intelligent separation of superhydrophilic and superoleophobic sludge, which is used to solve the problem of low efficiency and high energy consumption of traditional chemical and physical treatment methods in the existing sludge purification technology due to the fact that water and oil are usually mixed and difficult to separate in the sludge treatment process.

[0008] To achieve the above-mentioned purpose and other related purposes, in a first aspect, the present application provides a sludge purification method, system and device for intelligent sorting of superhydrophilic and superoleophobic, comprising the following steps: obtaining an original image of sludge particles of a sample to be processed; preprocessing the original image of the sludge particles to obtain first sludge particle image data; performing preliminary water-oil separation on the first sludge particle image data to obtain first sludge particle preliminary water-oil separation image data; performing deep separation based on the first sludge particle preliminary water-oil separation image data to obtain second sludge particle image data; using an intelligent control method to monitor the process in real time, adjust operating parameters and optimize the separation process; and collecting water and oil based on the second sludge particle image data and the optimization results to complete the complete separation of water and oil.

[0009] In an implementation of the first aspect, obtaining the original image of sludge particles of the sample to be processed includes the following steps: selecting a corresponding separation membrane material according to the characteristics of the sludge particles; performing surface treatment on the separation membrane material to obtain a super-hydrophilic and super-oleophobic separation membrane; dehydrating the sludge of the sample to be processed to obtain a dehydrated sludge sample; chemically treating the dehydrated sludge sample to obtain a pretreated sludge sample; and obtaining the original image of the sludge particles of the sample to be processed based on the pretreated sludge sample.

[0010] In an implementation of the first aspect, the separation membrane material is modified polyvinylidene fluoride.

[0011] In an implementation of the first aspect, preprocessing the original image of the sludge particles to obtain first sludge particle image data includes: graying, scaling, and rotating the original image of the sludge particles to extract the image size; constructing a rotation matrix based on the image size; and performing image edge detection on the rotation matrix to obtain first sludge particle image data.

[0012] In an implementation of the first aspect, performing preliminary water-oil separation on the first sludge particle image data to obtain the first sludge particle preliminary water-oil separation image data includes the following steps: performing image analysis on the first sludge particle image data to obtain water features and oil domain features of the first sludge particle image; segmenting the water features and the oil domain features using an image segmentation algorithm to obtain segmented water features and oil domain features; performing water-oil separation on the segmented water features and oil domain features using an image processing algorithm to obtain simulated separated water features and oil domain features; merging the simulated separated water features and oil domain features respectively to obtain the first sludge particle preliminary water-oil separation image data; wherein, the first sludge particle preliminary water-oil separation image data includes: a water feature image of the first sludge particle image and an oil domain feature image of the first sludge particle image.

[0013] In an implementation of the first aspect, a threshold segmentation algorithm is used to separate water areas and oil areas in an image; including: defining the initial state of the material; setting a threshold; dynamically regulating the material state according to the temperature; including: setting a temperature threshold; when the temperature at a certain moment of collection is greater than or equal to the temperature threshold, the material is hydrophobic; when the temperature at a certain moment of collection is less than the temperature threshold, the material is hydrophilic; according to the selected threshold, the pixels in the image are classified; including: pixels greater than or equal to the threshold are classified as water areas; pixels less than the threshold are classified as oil areas; the segmented image is processed to obtain the segmented water features and oil area features.

[0014] In an implementation of the first aspect, performing deep separation based on the first sludge particle water-oil preliminary separation image data to obtain second sludge particle image data includes the following steps: performing image refinement processing on the first sludge particle water-oil preliminary separation image data to obtain a refined first sludge particle water-oil preliminary separation image; performing image segmentation on the refined first sludge particle water-oil preliminary separation image using an image segmentation deep learning algorithm to obtain a second water area feature and a second oil area feature after segmentation, and generating a corresponding segmentation mask; performing different component analysis on the segmented second water area feature and the second oil area feature according to the segmentation mask to obtain the analyzed second water area feature and the second oil area feature, and marking them; performing deep separation simulation based on the analyzed second water area feature and the second oil area feature; and generating second sludge particle image data based on the second water area feature and the second oil area feature after the deep separation simulation.

[0015] In an implementation of the first aspect, an image segmentation deep learning algorithm is used to perform image segmentation on the refined first sludge particle water-oil preliminary separation image to obtain the segmented second water area feature and the second oil area feature, and a corresponding segmentation mask is generated, including the following steps: based on the refined first sludge particle water-oil preliminary separation image, a deep learning model is constructed; a model training set is obtained; a back propagation algorithm is used to update the model parameters of the model training set, and a validation set is used to monitor the training process; the trained model is used to perform image segmentation on the refined first sludge particle water-oil preliminary separation image to obtain the segmented second water area feature and the second oil area feature; the segmented second water area feature and the second oil area feature are converted into a binary mask image to generate a segmentation mask.

[0016] In the second aspect, the present application provides a sludge purification system for intelligent sorting of super-hydrophilic and super-oleophobic, including: an acquisition module for acquiring the original image of sludge particles of a sample to be processed; a sludge pretreatment module for preprocessing the original image of the sludge particles to obtain first sludge particle image data; a preliminary separation module for performing preliminary water-oil separation on the first sludge particle image data to obtain first sludge particle preliminary water-oil separation image data; a depth separation module for performing depth separation based on the first sludge particle preliminary water-oil separation image data to obtain second sludge particle image data; an optimization and adjustment module for real-time monitoring of the process using an intelligent control method, adjusting operating parameters and optimizing the separation process; a water-oil collection module for collecting water and oil based on the second sludge particle image data to complete the complete separation of water and oil.

[0017] In the last aspect, the present application provides a sludge purification device for intelligently sorting super-hydrophilic and super-oleophobic, comprising: a processor and a memory. The memory is used to store a computer program; the processor is connected to the memory and is used to execute the computer program stored in the memory, so that the sludge purification device for intelligently sorting and treating super-hydrophilic and super-oleophobic sludge performs the sludge purification method for intelligently sorting and treating super-hydrophilic and super-oleophobic sludge.

[0018] As described above, the sludge purification method, system and device for intelligent separation of super-hydrophilic and super-oleophobic sludge of the present application have the following beneficial effects:

[0019] (1) The present application provides a sludge purification method for intelligent separation of superhydrophilic and superoleophobic sludge, which realizes efficient separation of water and oil in sludge through intelligent separation and treatment; the method provided by the present application can realize a small-volume, simple-composition sludge purification process under laboratory conditions, while the composition of the oil-water mixture in the environment is relatively complex;

[0020] (2) The corresponding system provided in this application utilizes specially prepared super-hydrophilic and super-oleophobic materials for sludge treatment, thereby achieving efficient water treatment and oil recovery, and achieving the goal of sludge purification;

[0021] (3) The method provided in this application is a green and environmentally friendly sludge treatment technology with broad application prospects. BRIEF DESCRIPTION OF THE DRAWINGS

[0022] Figure 1 Shown is a schematic flow chart of a sludge purification method for intelligent separation of superhydrophilicity and superoleophobicity described in the present application in one embodiment.

[0023] Figure 2 Shown is a schematic diagram of the operational flow of the sludge purification method for intelligent separation of superhydrophilicity and superoleophobicity described in the present application.

[0024] Figure 3 Shown is a schematic diagram of the separation and control process of a sludge purification method for intelligent separation of superhydrophilicity and superoleophobicity described in the present application in one embodiment.

[0025] Figure 4 Shown is a schematic flow chart of S1 in one embodiment of the sludge purification method for intelligent separation of superhydrophilicity and superoleophobicity described in the present application.

[0026] Figure 5A Shown is a schematic diagram of the lyophilic capillary phenomenon in an embodiment of the sludge purification method for intelligent separation of superhydrophilicity and superoleophobicity described in the present application.

[0027] Figure 5B A schematic diagram of the lyophobic capillary phenomenon in an embodiment of the sludge purification method for intelligent separation of superhydrophilicity and superoleophobicity described in the present application is shown.

[0028] Figure 6 Shown is a schematic flow chart of S2 in one embodiment of the sludge purification method for intelligent separation of superhydrophilicity and superoleophobicity described in the present application.

[0029] Figure 7 Shown is a schematic flow chart of S3 in one embodiment of the sludge purification method for intelligent separation of superhydrophilicity and superoleophobicity described in the present application.

[0030] Figure 8 Shown is a schematic flow chart of S4 in one embodiment of the sludge purification method for intelligent separation of superhydrophilicity and superoleophobicity described in the present application.

[0031] Fig. 9 Shown is a schematic diagram of the principle structure of a sludge purification system for intelligent separation of superhydrophilicity and superoleophobicity described in the present application in one embodiment.

[0032] Fig.10 Shown is a schematic diagram of the principle structure of a sludge purification device for intelligent separation of superhydrophilicity and superoleophobicity described in the present application in one embodiment.

[0033] Component number description

[0034] 91 Get Module 92 Sludge pretreatment module 93 Primary separation module 94 Depth separation module 95 Optimization and adjustment module 96 Water and oil collection module 101 processor 102 Memory DETAILED DESCRIPTION

[0035] The following specific examples are used to illustrate the embodiments described in this application. Those skilled in the art can easily understand the other advantages and effects described in this application from the contents disclosed in this specification. This application can also be implemented or applied through other different specific embodiments, and the details in this specification can also be modified or changed in various ways based on different viewpoints and applications without departing from the spirit described in this application. It should be noted that the following embodiments and features in the embodiments can be combined with each other without conflict.

[0036] It should be noted that the illustrations provided in the following embodiments are only schematic illustrations of the basic concept described in the present application. Therefore, the drawings only show components related to the present application rather than being drawn according to the number, shape and size of components in actual implementation. In actual implementation, the type, quantity and proportion of each component may be changed at will, and the component layout may also be more complicated.

[0037] The following will describe in detail a sludge purification method, system and device for intelligent separation of superhydrophilicity and superoleophobicity provided in the embodiments of the present application in conjunction with the accompanying drawings in the embodiments of the present application.

[0038] See also Figure 1 , Figure 2 and Figure 3 , respectively showing a flow chart of the sludge purification method for intelligent separation of super-hydrophilic and super-oleophobic substances described in the present application in one embodiment, a flow chart of the operation of the sludge purification method for intelligent separation of super-hydrophilic and super-oleophobic substances described in the present application, and a flow chart of the separation and control of the sludge purification method for intelligent separation of super-hydrophilic and super-oleophobic substances described in the present application in one embodiment. Figure 1 , Figure 2 and Figure 3 As shown, this embodiment provides a sludge purification method, system and device for intelligent separation of super-hydrophilicity and super-oleophobicity.

[0039] The sludge purification method for intelligent separation of super-hydrophilic and super-oleophobic sludge specifically comprises the following steps:

[0040] S1, obtain the original image of the sludge particles of the sample to be processed. Figure 4 , which is a schematic diagram of the process of S1 in one embodiment of the sludge purification method for intelligent separation of super-hydrophilicity and super-oleophobicity described in the present application. Figure 4 As shown, the S1 comprises the following steps:

[0041] S11, selecting corresponding separation membrane materials according to the characteristics of the sludge particles;

[0042] S12, performing surface treatment on the separation membrane material to obtain a super-hydrophilic and super-oleophobic separation membrane;

[0043] S13, dehydrating the sludge sample to be processed to obtain a dehydrated sludge sample;

[0044] S14, chemically treating the dehydrated sludge sample to obtain a pretreated sludge sample;

[0045] S15, obtaining an original image of sludge particles of the sample to be processed based on the pretreated sludge sample.

[0046] In this embodiment, according to research requirements, a super-hydrophilic and super-oleophobic separation membrane assembly is used to separate water and oil from the sludge sample.

[0047] The super-hydrophilic and super-oleophobic separation membrane utilizes the special wetting properties of the membrane material surface. When the membrane surface contacts the oil-water mixture, water can quickly wet the hydrophilic membrane surface to form a layer of water film. Due to the immiscibility of water and oil, this layer of water film will prevent oil droplets from passing through the membrane pores, thereby achieving oil-water separation. At the same time, the super-oleophobic properties of the membrane ensure low adhesion and high rolling properties of oil droplets on the membrane surface, further improving the oil-water separation efficiency.

[0048] The superhydrophilic and superoleophobic separation membrane is superoleophobic in air or water, and exhibits extremely low adhesion to oil, with a rolling contact angle of only 1~3°, effectively preventing the adhesion of oil droplets. When oily wastewater contacts the membrane surface, water can continuously penetrate downward, while the surface always maintains superoleophobicity, and the oil is retained on the surface to achieve the effect of oil-water separation. Due to the oleophobicity of the membrane, oil molecules cannot contaminate the membrane surface. It is a truly anti-pollution, long-life separation membrane, which can become the main development direction of oil-water separation membranes in the future.

[0049] See also Figure 5A and Figure 5B , respectively showing a schematic diagram of the lyophilic capillary phenomenon in an embodiment of the sludge purification method for intelligent separation of superhydrophilicity and superoleophobicity described in the present application, and a schematic diagram of the lyophobic capillary phenomenon in an embodiment of the sludge purification method for intelligent separation of superhydrophilicity and superoleophobicity described in the present application.

[0050] The lyophilic capillary phenomenon refers to the phenomenon that when the wetting liquid (i.e., lyophilic) flows in a capillary or a capillary, the liquid rises in the capillary due to the interaction force between the liquid and the solid surface (mainly surface tension). This rise is the result of the combined effect of the attraction between the liquid molecules and the surface tension.

[0051] For example: See Figure 5A, when a lyophilic liquid comes into contact with a capillary, due to the mutual attraction between the liquid and the tube wall, the liquid will rise in the capillary to form a concave liquid surface. In other words, the cohesive force between the liquid molecules in the figure makes the liquid surface tend to shrink; when the liquid comes into contact with a solid, if the liquid can wet the solid, the liquid will spread out on the solid surface to form a smaller contact angle (less than 90 degrees). If the liquid cannot wet the solid, a larger contact angle (greater than 90 degrees) will be formed on the surface. When the diameter of the capillary is very small (usually at the micrometer or nanometer level), the interaction between the liquid and the tube wall becomes significant, causing the liquid to rise or fall in the capillary. Among them, Figure 5A The h in the equation represents the height of the lyophilic liquid rising in the capillary (this height can be calculated). In the lyophilic capillary phenomenon, since the contact angle is less than 90 degrees, the liquid forms a concave liquid surface in the capillary. This concave liquid surface exerts an upward pulling force on the liquid below, causing the liquid to rise along the tube wall. When the pulling force of the liquid rising along the capillary is equal to the gravity of the liquid column in the tube, the liquid stops rising and reaches a state of equilibrium.

[0052] Lyophobic capillary phenomenon refers to the phenomenon that when a non-wetting liquid (i.e. the interaction between the liquid and the solid surface is weak and the contact angle is greater than 90 degrees) flows in a capillary or a capillary tube, the liquid descends in the capillary tube due to surface tension and non-wetting. In contrast to lyophilic capillary phenomenon, in lyophobic capillary phenomenon, the liquid does not rise, but descends.

[0053] See also Figure 5B . Similarly, when a liquid comes into contact with a solid surface, if the liquid cannot wet the solid (i.e., it is lyophobic), the liquid will descend in the capillary to form a convex liquid surface. That is to say, due to the cohesive force between liquid molecules, the liquid surface tends to shrink; when a liquid comes into contact with a solid, if the liquid cannot wet the solid, the liquid will form a larger contact angle (greater than 90 degrees) on the solid surface; when the diameter of the capillary is very small (usually at the micron or nanometer level), the interaction between the liquid and the tube wall becomes significant, causing the liquid to descend in the capillary. Since the contact angle is greater than 90 degrees, the liquid forms a convex liquid surface in the capillary. This convex liquid surface exerts a downward pressure on the liquid below, causing the liquid to descend along the tube wall; when the pressure of the liquid descending along the capillary is equal to the gravity on the liquid column in the tube, the liquid stops descending and reaches a state of equilibrium. In this case, Figure 5B The h in the equation represents the height that the liquid descends in the capillary. Figure 5A and Figure 5B It can be seen that h actually represents the height of the liquid rising or falling in different capillary phenomena (lyophilic or lyophobic).

[0054] Specifically, first, according to the characteristics of the sludge particles in the sludge sample to be detected, the corresponding material with good mechanical properties and chemical stability is selected as the substrate, such as: stainless steel mesh, copper mesh, modified polyvinylidene fluoride (PVDF), etc.; the membrane material is surface treated by chemical treatment, plasma treatment and other methods to make it have super hydrophilic and super oleophobic properties. In this embodiment, modified polyvinylidene fluoride material is preferably used as the separation membrane material. The separation membrane is generated by modified polyvinylidene fluoride.

[0055] Secondly, the surface of the separation membrane material is modified, such as: in the rough layer deposition, a rough layer of titanium dioxide (TiO2) or other nanoparticles is deposited on the substrate material to increase the roughness and specific surface area of ​​the membrane surface; a surfactant is used to introduce reactive functional groups on the surface of the rough layer to provide reaction sites for the subsequent grafting of hydrophilic polymers; hydrophilic polymers such as polyethylene glycol (PEG) and polyacrylamide (PAM) are grafted on the surface of the substrate material through solution polymerization and other methods to give the membrane surface superhydrophilicity and underwater superoleophobicity. The modified membrane material is cut into appropriate sizes and assembled into membrane components for oil-water separation in practical applications.

[0056] Then, the samples to be treated are subjected to sludge pretreatment, including mechanical dehydration and chemical treatment, to obtain pretreated sludge samples. That is, the sludge is dehydrated using a centrifuge or filter press to remove most of the water in the sludge; and agents are added to destroy the oil-water emulsification state in the sludge to facilitate the subsequent separation process.

[0057] Next, the sludge mixture is introduced into the separation membrane assembly, and the sludge mixture is pretreated, such as filtration, sedimentation, etc., to remove large particle impurities and reduce the viscosity of the sludge; and the pretreated sludge (or water-oil mixture) is pumped into the separation membrane assembly.

[0058] Finally, the original image of the sludge particles of the sample to be processed is collected. The original image here refers to the particle image data of the silt particles in the sludge, which shows the distribution of silt particles, water, and oil in the cross section before entering the separation membrane block.

[0059] It should be noted that in the membrane assembly, water molecules can quickly pass through the water film layer formed on the surface of the super-hydrophilic membrane, while oil droplets are retained on the membrane surface. The water passing through the membrane is collected through the water outlet of the membrane assembly, and the oil droplets on the membrane surface can be removed by regular cleaning or scraping. The collected water can be further used for subsequent treatment or reuse, and the removed oil can be recycled or treated. In addition, it is necessary to select suitable membrane materials and membrane assemblies according to the properties and treatment requirements of the sludge; it is necessary to optimize the separation effect by adjusting the operating parameters (such as temperature, pressure, flow rate, etc.); pay attention to regularly monitor the contamination of the membrane assembly and take appropriate cleaning measures to maintain the separation performance of the membrane.

[0060] S2, preprocessing the original image of the sludge particles to obtain first sludge particle image data. Figure 6 , which is a schematic diagram of the process of S2 in one embodiment of the sludge purification method for intelligent separation of super-hydrophilic and super-oleophobic properties described in the present application. Figure 6 As shown, S2 comprises the following steps:

[0061] S21, graying, scaling, and rotating the original image of the sludge particles to extract the image size;

[0062] S22, constructing a rotation matrix based on the image size;

[0063] S23, performing image edge detection on the rotation matrix to obtain first sludge particle image data.

[0064] In this embodiment, the original image of the sludge particles is subjected to image denoising to improve the image quality; then the background in the image is removed by using methods such as threshold segmentation and background modeling, and the relevant parameters are adjusted to achieve the best effect. Then, methods such as histogram equalization and contrast stretching are used to improve the visual effect of the image and make the characteristics of the sludge particles more obvious. Morphological operations such as corrosion, expansion, opening operation, and closing operation are used to change the shape and size of the particles in the image, and further process the sludge particles in the image, such as removing small particles and filling holes. Then, a suitable threshold is selected to perform binarization processing on the image, and the image is converted into a binary image, that is, the pixels in the image have only black and white colors. Then, edge detection algorithms such as Canny operator and Sobel operator are used to extract the edge information of the sludge particles in the image, providing a basis for subsequent analysis and recognition. Finally, the pre-treated original image of the sludge particles is saved as the first sludge particle image data.

[0065] Specifically, Python and OpenCV libraries can be used for image processing.

[0066] It should be noted that when performing image processing, the characteristics of the sludge particle image and the needs of subsequent processing should be fully considered to select appropriate processing methods and parameters; during the processing, attention should be paid to maintaining the integrity and characteristic information of the sludge particles in the image to avoid excessive processing leading to information loss; for different sludge particle images, different preprocessing methods and parameter combinations may be required to achieve the best processing effect.

[0067] S3, performing preliminary water-oil separation on the first sludge particle image data to obtain preliminary water-oil separation image data of the first sludge particle. Figure 7, which is a schematic diagram of the process of S3 in one embodiment of the sludge purification method for intelligent separation of super-hydrophilic and super-oleophobic properties described in the present application. Figure 7 As shown, S3 comprises the following steps:

[0068] The implementation step of performing preliminary water-oil separation on the first sludge particle image data to obtain the first sludge particle preliminary water-oil separation image data can be performed based on image processing and simulation of the super-hydrophilic and super-oleophobic concepts, but it should be noted that it is impossible to perform physical water-oil separation directly on the image data because this requires an actual physical process. However, image processing technology can be used to simulate or identify the effect of water-oil separation.

[0069] Here, the random forest algorithm is used, and random sampling is performed for data analysis to monitor the proportion of oil. That is, the initial parameters of the random forest algorithm are set, such as: n_estimators (number of decision trees), max_features (maximum number of features), max_depth (maximum depth), min_samples_split (minimum number of samples required for node splitting), min_samples_leaf (minimum number of samples for leaf nodes), etc. Then, the random forest model is trained using the training set data; the performance of the model can be evaluated through methods such as cross-validation, and the parameters can be adjusted to optimize the model.

[0070] The deep separation here is based on image analysis technology, so the separation membrane module mainly separates oil and water, which is also a fine separation.

[0071] S31, performing image analysis on the first sludge particle image data to obtain water area characteristics and oil area characteristics of the first sludge particle image.

[0072] In this embodiment, image processing techniques such as color analysis and texture analysis are used to analyze the first sludge particle image data to identify the characteristics of the water area and the oil area.

[0073] Specifically, since images may be affected by noise during acquisition and transmission, it is necessary to denoise the images to improve image quality. This can be achieved through filtering methods such as Gaussian filtering, median filtering, etc. In order to more clearly distinguish between water areas and oil areas, the contrast of the image can be enhanced. This helps to highlight the details and features in the image.

[0074] In addition, water areas and oil fields often have significant differences in color, so color space conversion (such as conversion from RGB to HSV or Lab) can be used to extract color features; and by analyzing the color values ​​of pixels, water areas and oil fields can be preliminarily distinguished. For texture features, water areas and oil fields may also differ in texture; therefore, texture description methods such as gray-level co-occurrence matrix (GLCM) and local binary pattern (LBP) can be used to extract image texture features. For shape features, if there are obvious differences in shape between water areas and oil fields (such as: water areas may be more continuous, oil fields may form isolated patches, etc.), shape analysis methods can be used to extract features.

[0075] It should be noted that since there may be no obvious color contrast between water and oil in the sludge particle images, it is necessary to rely on more complex image processing techniques, such as image segmentation algorithms based on machine learning or deep learning.

[0076] S32, using an image segmentation algorithm to segment the water area feature and the oil area feature to obtain segmented water area feature and oil area feature.

[0077] In this embodiment, the water area and the oil area in the image are separated by image segmentation techniques such as threshold segmentation, edge detection, region growing, clustering algorithm or deep learning; during the segmentation process, it is necessary to adjust the algorithm parameters according to the specific characteristics of the sludge particle image to obtain the best segmentation effect.

[0078] Specifically, the initial state of the material is defined; a threshold is set; the state of the material is dynamically regulated according to the temperature; including: setting a temperature threshold; when the temperature at a certain moment of collection is greater than or equal to the temperature threshold, the material is hydrophobic; when the temperature at a certain moment of collection is less than the temperature threshold, the material is hydrophilic; according to the selected threshold, the pixels in the image are classified; including: pixels greater than or equal to the threshold are classified as water areas; pixels less than the threshold are classified as oil areas; the segmented image is processed to obtain the segmented water area characteristics and oil area characteristics.

[0079] S33, using an image processing algorithm to perform water-oil separation on the segmented water features and oil domain features, to obtain simulated separated water features and oil domain features.

[0080] In this embodiment, based on image segmentation, the process of water-oil separation is simulated by image processing technology. This process can be achieved by drawing separation lines on the image, changing pixel values, or applying specific image processing filters.

[0081] Specifically, a suitable simulation algorithm is selected according to actual needs. Physical models are established, such as models based on fluid mechanics, to simulate the separation process of water and oil phases under specific conditions. However, pure image processing algorithms usually do not simulate physical processes directly, but simulate visual effects through image operations. In the image, the water area and the oil area are regarded as two independent layers or areas; the separation effect is simulated by adding a clear dividing line or dividing area between the two; the image brightness, contrast, saturation and other parameters are adjusted to enhance the visual difference between the water area and the oil area, so as to better simulate the effect after separation.

[0082] It should be noted that this step is actually a simulation at the image level, not a real physical separation.

[0083] S34, merging the water area characteristics and oil area characteristics after simulated separation respectively to obtain the first sludge particle water-oil preliminary separation image data; wherein, the first sludge particle water-oil preliminary separation image data includes: a water area characteristic image of the first sludge particle image and an oil area characteristic image of the first sludge particle image.

[0084] In this embodiment, the simulated separated water area and oil area images are saved or merged into a new image, namely the first sludge particle water-oil preliminary separation image data. In this new image, the boundary between the water area and the oil area can be clearly seen, thereby simulating the effect of preliminary separation of water and oil.

[0085] Specifically, firstly, two new blank images are created according to the size of the original sludge particle image, which are used to store the merged water area feature image and the oil area feature image respectively.

[0086] Then, the water feature image is merged, that is: traverse each pixel of the original sludge particle image; check whether the current pixel is marked as white (or: a specific color) in the water mask; if so, copy the color value (or feature value) of the pixel to the corresponding position in the water feature image; if not, keep the corresponding position in the water feature image blank or set it to the background color (such as: black).

[0087] At the same time, the oil domain feature image is merged. That is, each pixel of the original sludge particle image is traversed; this time, check whether the current pixel is marked as white (or: a specific color) in the oil domain mask; if so, copy the color value (or: feature value) of the pixel to the corresponding position in the oil domain feature image; if not, keep the corresponding position in the oil domain feature image blank or set it to the background color (such as black).

[0088] Next, if the water and oil areas have blurred edges or slight overlap in the original images, these areas are specially processed during the merging process.

[0089] For example, the surface of the separation membrane material has been specially treated to have super hydrophilic and super oleophobic properties, which can effectively separate water and oil in sludge. It is a key component for initial separation in the sludge treatment system.

[0090] S4, performing deep separation based on the first sludge particle water-oil preliminary separation image data to obtain second sludge particle image data. Figure 8 , which is a schematic diagram of the process of S4 in one embodiment of the sludge purification method for intelligent separation of super-hydrophilic and super-oleophobic properties described in the present application. Figure 8 As shown, S4 comprises the following steps:

[0091] S41, performing image thinning processing on the first sludge particle water-oil preliminary separation image data to obtain a thinned first sludge particle water-oil preliminary separation image.

[0092] In this embodiment, the image of the first sludge particle preliminary water-oil separation is subjected to image sharpening and edge enhancement techniques to highlight the detail features in the image, so as to improve the clarity and recognition of different components in the image.

[0093] Specifically, first, a filter (such as a Gaussian filter, a median filter, etc.) can be used to remove noise in the image; the contrast of the image can be adjusted to make the boundaries between the sludge particles and water and oil clearer; and then the image is converted into a binary image, that is, the pixels in the image are either black or white, which is convenient for subsequent processing. Then, an edge detection algorithm (such as: Canny edge detector, Sobel operator, etc.) is used to detect the edges in the image to identify and mark the boundaries between the sludge particles and water and oil. Next, a selection thinning algorithm (such as: Zhang-Suen thinning algorithm, Hilditch thinning algorithm, etc.) can be used to iteratively delete edge pixels while maintaining the connectivity and shape characteristics of the target area; at the same time, the selected thinning algorithm is applied to the image after the above processing to thin the detected edges or target areas into lines or skeletons with a single pixel width; then morphological operations and smoothing methods are used to further optimize and correct the thinned image, and finally the first thinned sludge particle water and oil preliminary separation image is obtained.

[0094] It should be noted that the above steps are based on an overview of general image processing techniques and may need to be adjusted and optimized according to the specific characteristics of the image data of the initial separation of water and oil in sludge particles. In addition, the selection and use of image processing software and tools (such as ImageJ, MATLAB, etc.) will also have an important impact on the effect of the refinement process.

[0095] S42, using an image segmentation deep learning algorithm to perform image segmentation on the refined first sludge particle water-oil preliminary separation image to obtain a second water area feature and a second oil area feature after segmentation, and generate a corresponding segmentation mask.

[0096] In this embodiment, a deep learning model is constructed based on the refined first sludge particle water-oil preliminary separation image; a model training set is obtained; a back propagation algorithm is used to update the model parameters of the model training set, and a validation set is used to monitor the training process; the trained model is used to perform image segmentation on the refined first sludge particle water-oil preliminary separation image to obtain the segmented second water area feature and the second oil area feature; the segmented second water area feature and the second oil area feature are converted into a binary mask image to generate a segmentation mask.

[0097] Specifically, first, you can select a suitable image segmentation algorithm based on the characteristics of the image and the segmentation requirements. Commonly used image segmentation algorithms include threshold segmentation, region growing, edge detection, energy-based methods (such as Graph Cut), and deep learning-based methods (such as U-Net, DeepLab, etc.). Then, set a suitable threshold for segmentation.

[0098] In addition, according to the needs, suitable models can be selected, such as U-Net, DeepLab, Mask R-CNN, etc., for model customization; the architecture of the model can be adjusted according to the specific task requirements, such as modifying the number of network layers, changing the convolution kernel size, adjusting the learning rate, etc. Then the model is trained by configuring the deep learning framework and using the data loader to batch load the refined first sludge particle water-oil preliminary separation image and the corresponding mask data. Then, the model is trained on the training set, the model parameters are updated by the back propagation algorithm, and the training process is monitored using the validation set to prevent overfitting, and then the parameter model is adjusted according to the results of the validation set for model optimization. And the performance and indicators of the model are evaluated using the test set. Then, the trained model is used to segment the new first sludge particle water-oil preliminary separation image to distinguish the second water area and the second oil area, and the segmentation results are converted into binary mask images to represent the second water area characteristics and the second oil area characteristics respectively.

[0099] Through the above steps, the automatic segmentation of the refined first sludge particle water-oil preliminary separation image can be achieved, and an accurate water area and oil area feature segmentation mask can be generated.

[0100] S43, performing different component analysis on the segmented second water area feature and the second oil area feature according to the segmentation mask to obtain analyzed second water area feature and second oil area feature, and marking them.

[0101] In this embodiment, different components in the image are analyzed and labeled according to the segmentation mask, which can be achieved by assigning different colors or labels to different components. In this process, it is necessary to combine the physical and chemical properties of sludge particles and professional knowledge in the field of image processing to ensure the accuracy and reliability of the analysis.

[0102] Specifically, based on the segmentation mask, the extracted second water feature and second oil domain feature are saved as independent images or matrices respectively; the appropriate analysis method is selected according to the needs to analyze the second water feature and the second oil domain feature, such as: when the data is a spectral image (such as: multispectral or hyperspectral image), the reflectivity or emissivity in different bands can be analyzed to infer the composition characteristics of the water and oil domain; the specific chemical composition in the water and oil domain can be determined by laboratory analysis methods (such as: gas chromatography, mass spectrometry, etc.); image processing technology (such as gray level co-occurrence matrix, Hough transform, etc.) can also be used to analyze the texture and shape characteristics of the water and oil domain. Then, the second water feature and the second oil domain feature are analyzed; then, the analysis results are summarized and statistically analyzed to extract key feature information. Finally, the key analysis results are marked and a segmented image with a mark is generated.

[0103] S44, performing a depth separation simulation based on the analyzed second water area characteristics and second oil area characteristics.

[0104] In this embodiment, the process of simulating depth separation at the image level is achieved by drawing finer separation lines on the image, adjusting pixel values ​​of different components, or applying specific image processing filters.

[0105] S45, generating second sludge particle image data based on the second water area characteristics and the second oil area characteristics after the depth separation simulation.

[0106] In this embodiment, according to the characteristics of the sludge particles and the simulation requirements, an image generation algorithm is used and optimized to ensure that the generated image data can accurately reflect the actual morphology and characteristics of the sludge particles. Then, the image data of the sludge particles are generated using the selected image generation algorithm and the sludge particle model. These data may include two-dimensional images, three-dimensional models or video sequences, etc. Then, the generated image data is post-processed, including color correction, contrast adjustment, noise suppression, etc., to improve the quality and authenticity of the image.

[0107] It should be noted that the above implementation steps are based on image-level simulation and processing, and cannot directly replace the physical deep separation process. In practical applications, if deep separation of sludge particles is required, it is also necessary to combine knowledge and technical means of physics, chemistry and other disciplines for comprehensive treatment.

[0108] In addition, the above process can be implemented through Python program.

[0109] For example, python is used to further process the initially separated water and oil to ensure complete separation. The module contains multiple super-hydrophilic and super-oleophobic membrane units.

[0110] The specific code is as follows:

[0111] Python

[0112] class MembraneModule:

[0113] def __init__(self):

[0114] self.membrane_units = []

[0115] def add_membrane_unit(self, membrane):

[0116] self.membrane_units.append(membrane)

[0117] def fully_separate(self, mixture):

[0118] for unit in self.membrane_units:

[0119] mixture = unit.separate_sludge(mixture)

[0120] return mixture

[0121] membrane_module = MembraneModule()

[0122] membrane_module.add_membrane_unit(super_membrane)

[0123] fully_separated = membrane_module.fully_separate(sludge_mixture)

[0124] Note that this example adds a _repr_ method to the SludgeMixture class to make it easier to print the state of its instances. In addition, a SuperHydrophilicOleophobicMembrane class is defined, which has a separate_sludge method to simulate the separation process. Note that this simulation is very simple and only assumes that 90% of the water is extracted, while the oil remains unchanged. In real applications, the process may be more complicated.

[0125] S5 uses intelligent control to monitor the process in real time, adjust operating parameters and optimize the separation process.

[0126] In this embodiment, temperature sensors, pressure sensors, flow sensors and other related equipment and facilities are installed at corresponding positions according to monitoring requirements to monitor the key parameters of the separation process in real time. Then, according to the data fed back by the sensors in the intelligent control system, the intelligent control system automatically adjusts the working parameters of the membrane assembly, such as feed rate, temperature, pressure, etc., to optimize the separation effect. Finally, the system automatically records the efficiency and equipment status of each separation, providing data support for subsequent equipment maintenance and system optimization.

[0127] The intelligent control system is used to monitor the treatment process in real time to ensure the stability and efficiency of the separation effect. It includes sensors and control software to adjust the working parameters of the separation membrane in real time.

[0128] This implementation process can be achieved using Python statements.

[0129] The specific code is as follows:

[0130] Python

[0131] class SmartControlSystem:

[0132] def __init__(self):

[0133] self.sensors = []

[0134] self.control_software = "SeparationOptimizer v1.0"

[0135] def monitor_system(self, membrane_module):

[0136] # Simulate monitoring data

[0137] return {"status": "optimal", "efficiency": 95}

[0138] def adjust_parameters(self):

[0139] # Simulation parameter adjustment

[0140] pass

[0141] smart_system = SmartControlSystem()

[0142] status = smart_system.monitor_system(membrane_module)

[0143] if status["efficiency"]<90:

[0144] smart_system.adjust_parameters()

[0145] As can be seen from the above, process data is collected in real time through sensors and other equipment; real-time data is input into the trained model for prediction or classification; the current process status is evaluated based on the output results of the model to determine whether the operating parameters need to be adjusted; and then the intelligent control strategy is designed based on the process status. For example, when the separation effect is predicted to be poor, the operating parameters such as temperature, pressure, and flow are automatically adjusted. Then, the operating parameters are dynamically adjusted based on the real-time monitoring results and the intelligent control strategy; after adjusting the parameters, the process status continues to be monitored and the adjustment effect is evaluated.

[0146] Through the above steps, the random forest algorithm can be used to realize real-time monitoring, intelligent control, and optimization and adjustment of operating parameters of the process. This method can not only improve the degree of automation of the process, but also significantly improve the control accuracy and efficiency of the process.

[0147] S6, collecting water and oil based on the second sludge particle image data and the optimization result to complete the complete separation of water and oil.

[0148] In this embodiment, first, the water-oil separation operation is performed according to the separation strategy and the adjusted parameters. That is, physical separation is performed using appropriate separation equipment (such as a grease trap, a centrifuge, a filter, etc.). Then, collection and storage are performed, that is, the separated water and oil are collected separately and stored in corresponding containers; cross contamination is avoided during the collection process to maintain the purity of water and oil. Next, the collected water and oil are quality tested, including indicators such as purity, pH value, and oil content; necessary treatment or adjustment is performed according to the test results to ensure that the expected separation effect and quality standards are achieved. Finally, an effect evaluation is performed; that is, the effect of the entire water-oil separation process is evaluated, including separation efficiency, energy consumption, cost, etc.; lessons learned are summarized based on the evaluation results to provide reference and improvement direction for future separation work.

[0149] The following is a further explanation using an example of using Python statements to simulate the working principle of superhydrophilic and superoleophobic materials in the intelligent sorting process.

[0150] In this embodiment, the intelligent sorting simulation process is as follows:

[0151] ```Python

[0152] import numpy as np

[0153] import random

[0154] import matplotlib.pyplot as plt

[0155] # Define the initial state of the material

[0156] class SmartMaterial:

[0157] def __init__(self):

[0158] self.hydrophilic = True # The initial state is super hydrophilic

[0159] self.threshold_temp = 50 # Temperature threshold for switching states (assuming temperature control)

[0160] self.water_passed = 0 # Amount of water passed

[0161] self.oil_rejected = 0 # Amount of oil rejected

[0162] def update_state(self, temperature):

[0163] # Dynamically control material state according to temperature

[0164] if temperature>self.threshold_temp:

[0165] self.hydrophilic = False # Beyond the threshold temperature, the material becomes hydrophobic

[0166] else:

[0167] self.hydrophilic = True # Below the threshold temperature, the material is hydrophilic

[0168] def separate(self, water_content, oil_content):

[0169] #Simulate the sorting process

[0170] if self.hydrophilic:

[0171] # In super hydrophilic state

[0172] self.water_passed += water_content

[0173] self.oil_rejected += oil_content

[0174] else:

[0175] # In super oleophobic state

[0176] self.water_passed += water_content * 0.5 # Only part of the water passes

[0177] self.oil_rejected += oil_content * 1.5 # Enhance the rejection effect of oil

[0178] def get_results(self):

[0179] return self.water_passed, self.oil_rejected

[0180] # Initialize materials

[0181] material = SmartMaterial()

[0182] # Define temperature range and mixture composition

[0183] temperature_range = np.linspace(20, 80, 100)

[0184] water_content = [random.uniform(0.4, 0.6) for _ in range(100)]

[0185] oil_content = [random.uniform(0.4, 0.6) for _ in range(100)]

[0186] #Simulate temperature changes and sorting process

[0187] water_results = []

[0188] oil_results = []

[0189] for i, temp in enumerate(temperature_range):

[0190] material.update_state(temp)

[0191] material.separate(water_content[i], oil_content[i])

[0192] water_passed, oil_rejected = material.get_results()

[0193] water_results.append(water_passed)

[0194] oil_results.append(oil_rejected)

[0195] # Visualize the water-oil separation effect

[0196] plt.figure(figsize=(10, 6))

[0197] plt.plot(temperature_range, water_results, label="Water Passed",color="blue")

[0198] plt.plot(temperature_range, oil_results, label="Oil Rejected", color="orange")

[0199] plt.axvline(x=material.threshold_temp, color='r', linestyle='--',label='Threshold Temperature')

[0200] plt.xlabel('Temperature (°C)')

[0201] plt.ylabel('Accumulated Amount')

[0202] plt.title('Smart Material-Based Water-Oil Separation')

[0203] plt.legend()

[0204] plt.show()

[0205] ```

[0206] As can be seen from the above, this example simulates the sorting process of superhydrophilic and superoleophobic materials at different temperatures through code. Although more complex material science and engineering technologies are involved in actual applications, this example provides a basic logical framework that can provide ideas for the development of intelligent sorting systems.

[0207] It should be noted that in this implementation case, only the pollutant COD is used as an example for water environment capacity allocation. In fact, the water environment capacity allocation method and indicator system in the present invention can be applied to pollutants including but not limited to COD.

[0208] The sludge purification method with superhydrophilic and superoleophobic intelligent separation provided in the present application realizes efficient separation of water and oil in sludge through intelligent separation and treatment; the method utilizes specially prepared superhydrophilic and superoleophobic materials for sludge treatment, realizes efficient water treatment and oil recovery, and achieves the goal of sludge purification.

[0209] The protection scope of the sludge purification method for intelligent separation of superhydrophilicity and superoleophobicity described in the embodiment of the present application is not limited to the execution order of the steps listed in this embodiment. All solutions implemented by adding, reducing or replacing steps in the prior art based on the principles of the present application are included in the protection scope of the present application.

[0210] An embodiment of the present application also provides a sludge purification system with intelligent sorting of super hydrophilicity and super oleophobicity, and the sludge purification system with intelligent sorting of super hydrophilicity and super oleophobicity can realize the sludge purification method with intelligent sorting of super hydrophilicity and super oleophobicity described in the present application, but the implementation device of the sludge purification method, system and device with intelligent sorting of super hydrophilicity and super oleophobicity described in the present application includes but is not limited to the structure of the sludge purification system with intelligent sorting of super hydrophilicity and super oleophobicity listed in the present embodiment. All structural deformations and replacements of the prior art made according to the principles of the present application are included in the protection scope of the present application.

[0211] The sludge purification system for intelligent separation of super-hydrophilicity and super-oleophobicity provided in this embodiment will be described in detail below with reference to the drawings.

[0212] This embodiment provides a sludge purification system for intelligent separation of super-hydrophilic and super-oleophobic properties, comprising:

[0213] See also Fig. 9 , which is a schematic diagram of the principle structure of a sludge purification system for intelligent separation of super-hydrophilicity and super-oleophobicity described in this application in one embodiment. Fig. 9 As shown, the sludge purification system for intelligent separation of super-hydrophilicity and super-oleophobicity includes: an acquisition module 91, a sludge pretreatment module 92, a preliminary separation module 93, a deep separation module 94, an optimization and adjustment module 95 and a water-oil collection module 96.

[0214] The acquisition module 91 is used to acquire the original image of the sludge particles of the sample to be processed.

[0215] In this embodiment, according to the characteristics of the sludge particles, a corresponding separation membrane material is selected; the separation membrane material is surface treated to obtain a super hydrophilic and super oleophobic separation membrane; the sludge of the sample to be treated is dehydrated to obtain a dehydrated sludge sample; the dehydrated sludge sample is chemically treated to obtain a pretreated sludge sample; and the original image of the sludge particles of the sample to be treated is obtained based on the pretreated sludge sample.

[0216] Specifically, according to research needs, a super-hydrophilic and super-oleophobic separation membrane assembly is used to separate water and oil from sludge samples.

[0217] The sludge preprocessing module 92 is connected to the acquisition module 91 and is used to preprocess the original image of the sludge particles to obtain first sludge particle image data.

[0218] In this embodiment, the original image of the sludge particles is grayed, scaled, and rotated to extract the image size; a rotation matrix is ​​constructed based on the image size; and image edge detection is performed on the rotation matrix to obtain first sludge particle image data.

[0219] Specifically, the original image of the sludge particles is subjected to image denoising to improve the image quality; then the background in the image is removed by using methods such as threshold segmentation and background modeling, and the relevant parameters are adjusted to achieve the best effect. Then, the visual effect of the image is improved by using methods such as histogram equalization and contrast stretching to make the characteristics of the sludge particles more obvious. Morphological operations such as corrosion, expansion, opening operation, and closing operation are used to change the shape and size of the particles in the image, and the sludge particles in the image are further processed, such as removing small particles and filling holes. Then, a suitable threshold is selected to perform binarization processing on the image, and the image is converted into a binary image, that is, the pixels in the image have only black and white colors. Then, edge detection algorithms such as the Canny operator and the Sobel operator are used to extract the edge information of the sludge particles in the image, providing a basis for subsequent analysis and recognition. Finally, the pre-processed original image of the sludge particles is saved as the first sludge particle image data.

[0220] The preliminary separation module 93 is used to perform preliminary water-oil separation on the first sludge particle image data to obtain the first sludge particle preliminary water-oil separation image data.

[0221] Image analysis is performed on the first sludge particle image data to obtain water area characteristics and oil area characteristics of the first sludge particle image.

[0222] In this embodiment, image processing techniques such as color analysis and texture analysis are used to analyze the first sludge particle image data to identify the characteristics of the water area and the oil area.

[0223] The water area features and the oil area features are segmented by using an image segmentation algorithm to obtain segmented water area features and oil area features.

[0224] In this embodiment, the water area and the oil area in the image are separated by image segmentation techniques such as threshold segmentation, edge detection, region growing, clustering algorithm or deep learning; during the segmentation process, it is necessary to adjust the algorithm parameters according to the specific characteristics of the sludge particle image to obtain the best segmentation effect.

[0225] Image processing algorithm is used to separate the segmented water area features and oil area features to obtain simulated separated water area features and oil area features.

[0226] In this embodiment, based on image segmentation, the process of water-oil separation is simulated by image processing technology. This process can be achieved by drawing separation lines on the image, changing pixel values, or applying specific image processing filters.

[0227] The water area characteristics and oil area characteristics after simulated separation are merged respectively to obtain the first sludge particle water-oil preliminary separation image data; wherein, the first sludge particle water-oil preliminary separation image data includes: the water area characteristic image of the first sludge particle image and the oil area characteristic image of the first sludge particle image.

[0228] In this embodiment, the simulated separated water area and oil area images are saved or merged into a new image, namely the first sludge particle water-oil preliminary separation image data. In this new image, the boundary between the water area and the oil area can be clearly seen, thereby simulating the effect of preliminary separation of water and oil.

[0229] The depth separation module 94 is used to perform depth separation based on the first sludge particle water-oil preliminary separation image data to obtain second sludge particle image data.

[0230] The image data of the first sludge particle preliminary water-oil separation is subjected to image refinement processing to obtain a refined first sludge particle preliminary water-oil separation image.

[0231] In this embodiment, the image of the first sludge particle preliminary water-oil separation is subjected to image sharpening and edge enhancement techniques to highlight the detail features in the image, so as to improve the clarity and recognition of different components in the image.

[0232] An image segmentation deep learning algorithm is used to perform image segmentation on the refined first sludge particle water-oil preliminary separation image to obtain the segmented second water area features and second oil area features, and generate corresponding segmentation masks.

[0233] In this embodiment, a deep learning model is constructed based on the refined first sludge particle water-oil preliminary separation image; a model training set is obtained; a back propagation algorithm is used to update the model parameters of the model training set, and a validation set is used to monitor the training process; the trained model is used to perform image segmentation on the refined first sludge particle water-oil preliminary separation image to obtain the segmented second water area feature and the second oil area feature; the segmented second water area feature and the second oil area feature are converted into a binary mask image to generate a segmentation mask.

[0234] The segmented second water area feature and the second oil area feature are subjected to different component analysis according to the segmentation mask to obtain the analyzed second water area feature and the second oil area feature, and mark them.

[0235] In this embodiment, different components in the image are analyzed and labeled according to the segmentation mask, which can be achieved by assigning different colors or labels to different components. In this process, it is necessary to combine the physical and chemical properties of sludge particles and professional knowledge in the field of image processing to ensure the accuracy and reliability of the analysis.

[0236] A depth separation simulation is performed based on the analyzed characteristics of the second water area and the second oil area.

[0237] In this embodiment, the process of simulating depth separation at the image level is achieved by drawing finer separation lines on the image, adjusting pixel values ​​of different components, or applying specific image processing filters.

[0238] Based on the second water area characteristics and the second oil area characteristics after the depth separation simulation, second sludge particle image data is generated.

[0239] In this embodiment, according to the characteristics of the sludge particles and the simulation requirements, an image generation algorithm is used and optimized to ensure that the generated image data can accurately reflect the actual morphology and characteristics of the sludge particles. Then, the image data of the sludge particles are generated using the selected image generation algorithm and the sludge particle model. These data may include two-dimensional images, three-dimensional models or video sequences, etc. Then, the generated image data is post-processed, including color correction, contrast adjustment, noise suppression, etc., to improve the quality and authenticity of the image.

[0240] The optimization and adjustment module 95 is used to monitor the process in real time by adopting an intelligent control method, and to adjust the operating parameters and optimize the separation process.

[0241] In this embodiment, temperature sensors, pressure sensors, flow sensors and other related equipment and facilities are installed at corresponding positions according to monitoring requirements to monitor the key parameters of the separation process in real time. Then, according to the data fed back by the sensors in the intelligent control system, the intelligent control system automatically adjusts the working parameters of the membrane assembly, such as feed rate, temperature, pressure, etc., to optimize the separation effect. Finally, the system automatically records the efficiency and equipment status of each separation, providing data support for subsequent equipment maintenance and system optimization.

[0242] The intelligent control system is used to monitor the treatment process in real time to ensure the stability and efficiency of the separation effect. It includes sensors and control software to adjust the working parameters of the separation membrane in real time.

[0243] The water-oil collection module 96 is used to collect water and oil based on the second sludge particle image data to achieve complete separation of water and oil.

[0244] In this embodiment, first, the water-oil separation operation is performed according to the separation strategy and the adjusted parameters. That is, physical separation is performed using appropriate separation equipment (such as a grease trap, a centrifuge, a filter, etc.). Then, collection and storage are performed, that is, the separated water and oil are collected separately and stored in corresponding containers; cross contamination is avoided during the collection process to maintain the purity of water and oil. Next, the collected water and oil are quality tested, including indicators such as purity, pH value, and oil content; necessary treatment or adjustment is performed according to the test results to ensure that the expected separation effect and quality standards are achieved. Finally, an effect evaluation is performed; that is, the effect of the entire water-oil separation process is evaluated, including separation efficiency, energy consumption, cost, etc.; lessons learned are summarized based on the evaluation results to provide reference and improvement direction for future separation work.

[0245] The sludge purification model of super-hydrophilic and super-oleophobic intelligent separation builds a sludge purification system of super-hydrophilic and super-oleophobic intelligent separation. By using a special separation membrane and an advanced intelligent control system, the water-oil separation efficiency is significantly improved, and efficient purification and resource recovery of sludge are achieved. The invention is simple to operate, easy to industrialize, and has good economic and environmental benefits.

[0246] It should be noted that it should be understood that the division of the various modules of the above system is only a division of logical functions. In actual implementation, they can be fully or partially integrated into one physical entity, or they can be physically separated. And these modules can all be implemented in the form of software called by processing elements; they can also be all implemented in the form of hardware; some modules can also be implemented in the form of software called by processing elements, and some modules can be implemented in the form of hardware. For example, each module can be a separately established processing element, or it can be integrated in a chip of the above system. In addition, it can also be stored in the memory of the above system in the form of program code, and called and executed by a processing element of the above system. The implementation of other modules is similar. In addition, these modules can be fully or partially integrated together, or they can be implemented independently. The processing element described here can be an integrated circuit with signal processing capabilities. In the implementation process, each step of the above method or each module above can be completed by an integrated logic circuit of hardware in the processor element or instructions in the form of software.

[0247] The above modules may be one or more integrated circuits configured to implement the above methods, such as one or more application specific integrated circuits (ASIC), or one or more digital signal processors (DSP), or one or more field programmable gate arrays (FPGA). For another example, when a module is implemented in the form of a processing element scheduling program code, the processing element may be a general-purpose processor, such as a central processing unit (CPU) or other processor that can call program code. For another example, these modules may be integrated together and implemented in the form of a system-on-a-chip (SOC).

[0248] See also Fig.10 , which is a schematic diagram of the principle structure of a sludge purification device for intelligent separation of super-hydrophilicity and super-oleophobicity described in the present application in one embodiment. Fig.10 As shown, the present embodiment provides a sludge purification device for intelligent sorting of super hydrophilicity and super oleophobicity, and the sludge purification device for intelligent sorting of super hydrophilicity and super oleophobicity comprises: a processor 101 and a memory 102; the memory 102 is used to store a computer program; the processor 101 is connected to the memory 102, and is used to execute the computer program stored in the memory 102, so that the sludge purification device for intelligent sorting of super hydrophilicity and super oleophobicity performs each step of the sludge purification method for intelligent sorting of super hydrophilicity and super oleophobicity as described above.

[0249] Preferably, the memory may include a random access memory (RAM), and may also include a non-volatile memory (non-volatile memory), such as at least one disk memory.

[0250] The above-mentioned processor can be a general-purpose processor, including a central processing unit (CPU), a network processor (NP), etc.; it can also be a digital signal processor (DSP), an application specific integrated circuit (ASIC), a field programmable gate array (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components.

[0251] In summary, the sludge purification method, system and device for intelligent separation of super-hydrophilic and super-oleophobic sludge provided in the present application have the following beneficial effects:

[0252] (1) The present application provides a sludge purification method, system and device for intelligent separation of superhydrophilic and superoleophobic sludge, which realizes efficient separation of water and oil in sludge through intelligent separation and treatment; the method provided by the present application can realize a small-volume, simple-composition sludge purification process under laboratory conditions, while the composition of the oil-water mixture in the environment is relatively complex;

[0253] (2) The corresponding system provided in this application utilizes specially prepared super-hydrophilic and super-oleophobic materials for sludge treatment, thereby achieving efficient water treatment and oil recovery, and achieving the goal of sludge purification;

[0254] (3) The method provided in this application is a green and environmentally friendly sludge treatment technology with broad application prospects.

[0255] The above embodiments are merely illustrative of the principles and effects of the present application and are not intended to limit the present application. Anyone familiar with the technology may modify or change the above embodiments without violating the spirit and scope of the present application. Therefore, all equivalent modifications or changes made by a person of ordinary skill in the art without departing from the spirit and technical ideas disclosed in the present application shall still be covered by the claims of the present application.

Claims

1. A sludge purification method for intelligent separation of super-hydrophilic and super-oleophobic, characterized in that: The following steps are involved: Obtaining the original image of the sludge particles of the sample to be processed; comprising: selecting the corresponding separation membrane material according to the characteristics of the sludge particles; performing surface treatment on the separation membrane material to obtain a super-hydrophilic and super-oleophobic separation membrane; dehydrating the sludge of the sample to be processed to obtain a dehydrated sludge sample; chemically treating the dehydrated sludge sample to obtain a pretreated sludge sample; obtaining the original image of the sludge particles of the sample to be processed based on the pretreated sludge sample; the separation membrane material adopts modified polyvinylidene fluoride; Preprocessing the original image of the sludge particles to obtain first sludge particle image data; Performing preliminary water-oil separation on the first sludge particle image data to obtain the first sludge particle preliminary water-oil separation image data; including: performing image analysis on the first sludge particle image data to obtain the water area characteristics and oil area characteristics of the first sludge particle image; using an image segmentation algorithm to segment the water area characteristics and the oil area characteristics to obtain the segmented water area characteristics and oil area characteristics; using an image processing algorithm to perform water-oil separation on the segmented water area characteristics and oil area characteristics to obtain the simulated separated water area characteristics and oil area characteristics; merging the simulated separated water area characteristics and oil area characteristics respectively to obtain the first sludge particle preliminary water-oil separation image data; wherein, the first sludge particle preliminary water-oil separation image data includes: a water area characteristic image of the first sludge particle image and an oil area characteristic image of the first sludge particle image; Based on the first sludge particle water-oil preliminary separation image data, deep separation is performed to obtain second sludge particle image data; including: performing image refinement processing on the first sludge particle water-oil preliminary separation image data to obtain the refined first sludge particle water-oil preliminary separation image; using an image segmentation deep learning algorithm to perform image segmentation on the refined first sludge particle water-oil preliminary separation image to obtain the segmented second water area feature and the second oil area feature, and generate a corresponding segmentation mask; performing different component analysis on the segmented second water area feature and the second oil area feature according to the segmentation mask to obtain the analyzed second water area feature and the second oil area feature, and marking them; performing deep separation simulation based on the analyzed second water area feature and the second oil area feature; generating second sludge particle image data based on the second water area feature and the second oil area feature after the deep separation simulation; Adopt intelligent control method to monitor the process in real time, adjust operating parameters and optimize the separation process; Water and oil are collected based on the second sludge particle image data and the optimization result to complete the complete separation of water and oil.

2. The sludge purification method for intelligent separation of super-hydrophilic and super-oleophobic according to claim 1, characterized in that: Preprocessing the original image of the sludge particles to obtain first sludge particle image data includes: Graying, scaling and rotating the original image of the sludge particles to extract the image size; constructing a rotation matrix based on the image size; Image edge detection is performed on the rotation matrix to obtain first sludge particle image data.

3. The sludge purification method for intelligent separation of super-hydrophilic and super-oleophobic according to claim 1, characterized in that: The threshold segmentation algorithm is used to separate the water area and oil area in the image; including: Define the initial state of the material; Set a threshold; Dynamically regulating the state of the material according to the temperature; including: setting a temperature threshold; when the temperature at a certain time of collection is greater than or equal to the temperature threshold, the material is hydrophobic; when the temperature at a certain time of collection is less than the temperature threshold, the material is hydrophilic; According to the selected threshold, the pixels in the image are classified; including: pixels greater than or equal to the threshold are classified as water areas; pixels less than the threshold are classified as oil areas; The segmented images are processed to obtain the segmented water area features and oil area features.

4. The sludge purification method for intelligent separation of super-hydrophilic and super-oleophobic according to claim 1, characterized in that: The image segmentation deep learning algorithm is used to segment the first sludge particle water-oil preliminary separation image after refinement, obtain the segmented second water area feature and the second oil area feature, and generate the corresponding segmentation mask, including the following steps: Based on the refined water-oil preliminary separation image of the first sludge particles, a deep learning model is constructed; Get the model training set; Using a back propagation algorithm to update model parameters of the model training set, and using a validation set to monitor the training process; Using the trained model, image segmentation is performed on the first sludge particle preliminary water-oil separation image after refinement to obtain a second water area feature and a second oil area feature after segmentation; The segmented second water area features and second oil area features are converted into binary mask images to generate a segmentation mask.

5. A sludge purification system for intelligent separation of super-hydrophilic and super-oleophobic properties, characterized in that: include: The acquisition module is used to acquire the original image of the sludge particles of the sample to be processed; comprising: selecting the corresponding separation membrane material according to the characteristics of the sludge particles; performing surface treatment on the separation membrane material to obtain a super-hydrophilic and super-oleophobic separation membrane; dehydrating the sludge of the sample to be processed to obtain a dehydrated sludge sample; chemically treating the dehydrated sludge sample to obtain a pretreated sludge sample; acquiring the original image of the sludge particles of the sample to be processed based on the pretreated sludge sample; the separation membrane material adopts modified polyvinylidene fluoride; A sludge preprocessing module, used for preprocessing the original image of the sludge particles to obtain first sludge particle image data; A preliminary separation module is used to perform preliminary water-oil separation on the first sludge particle image data to obtain the first sludge particle preliminary water-oil separation image data; including: performing image analysis on the first sludge particle image data to obtain the water area characteristics and oil area characteristics of the first sludge particle image; using an image segmentation algorithm to segment the water area characteristics and the oil area characteristics to obtain the segmented water area characteristics and oil area characteristics; using an image processing algorithm to perform water-oil separation on the segmented water area characteristics and oil area characteristics to obtain the simulated separated water area characteristics and oil area characteristics; merging the simulated separated water area characteristics and oil area characteristics respectively to obtain the first sludge particle preliminary water-oil separation image data; wherein, the first sludge particle preliminary water-oil separation image data includes: a water area characteristic image of the first sludge particle image and an oil area characteristic image of the first sludge particle image; A depth separation module is used to perform depth separation based on the first sludge particle water-oil preliminary separation image data to obtain second sludge particle image data; including: performing image refinement processing on the first sludge particle water-oil preliminary separation image data to obtain a refined first sludge particle water-oil preliminary separation image; using an image segmentation deep learning algorithm to perform image segmentation on the refined first sludge particle water-oil preliminary separation image to obtain segmented second water area characteristics and second oil area characteristics, and generate a corresponding segmentation mask; performing different component analysis on the segmented second water area characteristics and second oil area characteristics according to the segmentation mask to obtain analyzed second water area characteristics and second oil area characteristics, and marking them; performing depth separation simulation based on the analyzed second water area characteristics and second oil area characteristics; generating second sludge particle image data based on the second water area characteristics and the second oil area characteristics after the depth separation simulation; Optimization and adjustment module, used to monitor the process in real time using intelligent control, and to adjust operating parameters and optimize the separation process; The water-oil collection module is used to collect water and oil based on the second sludge particle image data and the optimization result to complete the complete separation of water and oil.

6. A sludge purification device for intelligent separation of super-hydrophilic and super-oleophobic, characterized in that: include: Processor and memory; The memory is used to store computer programs; The processor is connected to the memory and is used to execute the computer program stored in the memory so that the super-hydrophilic and super-oleophobic intelligent separation sludge purification device performs the super-hydrophilic and super-oleophobic intelligent separation sludge purification method according to any one of claims 1 to 4.

Images