Intelligent environment-friendly organic solid waste resource utilization method and system

Abstract

The invention relates to the technical field of waste treatment, and particularly discloses an intelligent environment-friendly organic solid waste resource utilization method and system. Before organic solid wastes enter a crushing mechanism, the organic solid wastes are identified and classified based on a computer vision technology; the mechanical arm is controlled to remove the impurities when it is detected that the impurities exist in the organic solid waste, then the organic solid waste is fed into the smashing mechanism to be smashed, and the smashed powdery waste is dissolved through a dissolving solution; and separating the liquid in which the organic substance is dissolved and the solid powder from which the organic substance is removed. In this way, the overall process of resource utilization of the organic solid waste is effectively optimized, efficient and pure utilization of the organic solid waste is facilitated, and the waste treatment efficiency and the resource utilization quality are improved.

Description

Technical Field

[0001] This application relates to the technical field of waste treatment, and more specifically, to an intelligent environmental protection organic solid waste resource utilization method and system. Background Art

[0002] With the acceleration of the global industrialization and urbanization processes, the generation amount of organic solid waste is increasing day by day. Organic solid waste includes animal carcasses, crop straws, garden waste, kitchen waste, tail vegetables, human and animal feces, etc. Their large accumulation not only occupies precious land resources and damages the landscape, but also causes serious pollution to the atmosphere, soil and water environment. However, since a large amount of biomass energy is contained in organic solid waste, if this kind of biomass energy can be effectively utilized, it is of great significance to achieve the sustainable development of the environment and economy.

[0003] In the existing organic solid waste treatment technologies, there are various methods that have been widely studied and applied. For example, the invention patent with the publication number CN116765094A proposes an organic solid waste resource utilization method, which crushes the organic solid waste into block-shaped waste, and then pyrolyzes the block-shaped waste to obtain a part of the organic matter that is easily pyrolyzed out, making the brittleness of the block-shaped waste larger after losing a part of the pyrolyzed substances, and thus being more easily crushed into powder. After pyrolysis, the block-shaped waste is crushed to obtain powdery waste, and it is mixed with a dissolving solution to dissolve the organic matter in the powdery waste with the dissolving solution, so as to separate the organic liquid and the inorganic solid powder in the dissolving solution.

[0004] However, this method lacks an effective identification and classification mechanism for the components of organic solid waste at the front end of the treatment process. In the actually collected organic solid waste, various unsuitable impurities, such as metal blocks, plastic sheets, etc., often get mixed. The existence of these impurities may, on the one hand, damage the subsequent crushing, pyrolysis and other treatment equipment, affecting the normal operation and service life of the equipment; on the other hand, the existence of impurities may interfere with the pyrolysis and dissolution processes of organic matter, reducing the extraction efficiency and purity of organic substances, and thus affecting the effect and benefit of the entire resource utilization.

[0005] Therefore, an intelligent environmental protection organic solid waste resource utilization method and system are expected. Summary of the Invention

[0006] To solve the above technical problems, the present application is proposed. Embodiments of the present application provide an intelligent and environmentally friendly method and system for the resource utilization of organic solid waste. Before the organic solid waste enters the crushing mechanism, it is identified and classified based on computer vision technology to determine whether there are impurities that are not suitable for treatment. When impurities are detected in the organic solid waste, the robotic arm is controlled to remove the impurities, and then it is sent to the crushing mechanism for crushing. A dissolving liquid is used to dissolve the crushed powdered waste, and then the liquid dissolved with organic substances and the solid powder with organic substances removed are separated. In this way, the overall process of the resource utilization of organic solid waste is effectively optimized, which helps to achieve the efficient and pure utilization of organic solid waste and improve the waste treatment efficiency and the quality of resource utilization.

[0007] According to one aspect of the present application, there is provided an intelligent and environmentally friendly method for the resource utilization of organic solid waste, which includes:

[0008] Before the organic solid waste enters the crushing mechanism, it is identified and classified based on computer vision to determine whether there are impurities that are not suitable for treatment in the organic solid waste;

[0009] In response to the judgment result that there are impurities that are not suitable for treatment in the organic solid waste, the robotic arm is controlled to remove the impurities to obtain pre-treated organic solid waste;

[0010] The pre-treated organic solid waste is crushed into powdered waste by using a crushing mechanism;

[0011] The powdered waste is mixed with a dissolving liquid, and through solid-liquid dissolution and separation and purification, a liquid dissolved with organic substances and a solid powder with organic substances removed are obtained.

[0012] According to another aspect of the present application, there is provided an intelligent and environmentally friendly system for the resource utilization of organic solid waste, which includes:

[0013] A waste identification and classification module, which is used to identify and classify the organic solid waste based on computer vision before the organic solid waste enters the crushing mechanism to determine whether there are impurities that are not suitable for treatment in the organic solid waste;

[0014] An impurity removal module, which is used to control the robotic arm to remove the impurities in response to the judgment result that there are impurities that are not suitable for treatment in the organic solid waste to obtain pre-treated organic solid waste;

[0015] A waste crushing module, which is used to crush the pre-treated organic solid waste into powdered waste by using a crushing mechanism;

[0016] A solid-liquid dissolution separation and purification module is used to mix the powdery waste with a dissolution liquid, and obtain a liquid in which organic substances are dissolved and solid powder from which organic substances are removed through solid-liquid dissolution and separation and purification.

[0017] Compared with the prior art, for the intelligent environmental protection organic solid waste resource utilization method and system provided by this application, before the organic solid waste enters the crushing mechanism, it is identified and classified based on computer vision technology to determine whether there are impurities that are not suitable for treatment. When impurities are detected in the organic solid waste, the robotic arm is controlled to remove the impurities, and then it is sent to the crushing mechanism for crushing treatment, and a dissolution liquid is used to dissolve the crushed powdery waste, and then a liquid in which organic substances are dissolved and solid powder from which organic substances are removed are separated. In this way, the overall process of organic solid waste resource utilization is effectively optimized, which helps to achieve the efficient and pure utilization of organic solid waste, and improve the waste treatment efficiency and the quality of resource utilization. Brief Description of the Drawings

[0018] By describing the embodiments of this application in more detail in conjunction with the drawings, the above and other objects, features, and advantages of this application will become more obvious. The drawings are used to provide a further understanding of the embodiments of this application, and constitute a part of the specification. Together with the embodiments of this application, they are used to explain this application, and do not constitute a limitation to this application. In the drawings, the same reference numerals generally represent the same components or steps.

[0019] Figure 1 It is a flowchart of the intelligent environmental protection organic solid waste resource utilization method according to the embodiment of this application.

[0020] Figure 2 It is a flowchart of sub-step S1 of the intelligent environmental protection organic solid waste resource utilization method according to the embodiment of this application.

[0021] Figure 3 It is a schematic diagram of data flow of sub-step S1 of the intelligent environmental protection organic solid waste resource utilization method according to the embodiment of this application.

[0022] Figure 4 It is a flowchart of sub-step S12 of the intelligent environmental protection organic solid waste resource utilization method according to the embodiment of this application.

[0023] Figure 5 It is a flowchart of sub-step S13 of the intelligent environmental protection organic solid waste resource utilization method according to the embodiment of this application.

[0024] Figure 6 It is a flowchart of sub-step S133 of the intelligent environmental protection organic solid waste resource utilization method according to the embodiment of this application.

[0025] Figure 7 It is a flowchart of sub-step S1332 of the intelligent environmental protection organic solid waste resource utilization method according to an embodiment of the present application.

[0026] Figure 8 It is a block diagram of the intelligent environmental protection organic solid waste resource utilization system according to an embodiment of the present application. Detailed implementation manners

[0027] As shown in the present application and the claims, unless the context clearly indicates otherwise, words such as "a", "an", "one" and / or "the" are not specifically singular and may also include plural. Generally speaking, the terms "comprising" and "including" only indicate the inclusion of the clearly identified steps and elements, and these steps and elements do not constitute an exclusive list. The method or device may also include other steps or elements.

[0028] Although the present application makes various references to certain modules in the system according to the embodiments of the present application, however, any number of different modules can be used and run on the user terminal and / or the server. The modules are only illustrative, and different aspects of the system and method can use different modules.

[0029] In the present application, flowcharts are used to illustrate the operations performed by the system according to the embodiments of the present application. It should be understood that the operations before or below are not necessarily executed precisely in order. On the contrary, according to needs, various steps can be executed in reverse order or simultaneously. At the same time, other operations can also be added to these processes, or one or several operations can be removed from these processes.

[0030] Next, exemplary embodiments of the present application will be described in detail with reference to the accompanying drawings. Obviously, the described embodiments are only a part of the embodiments of the present application, rather than all the embodiments of the present application. It should be understood that the present application is not limited by the exemplary embodiments described herein.

[0031] It is worth noting that in the present application, all actions of obtaining data are carried out on the premise of complying with the corresponding data protection regulations and policies of the country where the location is located and obtaining the authorization given by the owner of the corresponding device.

[0032] As mentioned in the background technology, patent CN116765094A proposes a method for utilizing organic solid waste resources, which crushes organic solid waste into block waste, and then pyrolyzes the block waste to obtain a portion of organic matter that is easily pyrolyzed, so that the block waste becomes more brittle after losing a portion of the pyrolyzed material, and is easier to crush into powder. After pyrolysis, the block waste is crushed to obtain powdered waste, and the powdered waste is mixed with a dissolving liquid, so that the dissolving liquid dissolves the organic matter in the powdered waste to separate the organic liquid and inorganic solid powder in the dissolving liquid.

[0033] However, in the prior art, there is a lack of effective identification and classification mechanism for the components of organic solid waste at the front end of the processing process, resulting in the actual collection of organic solid waste often mixed with impurities such as metal blocks and plastic pieces. On the one hand, these impurities may damage subsequent processing equipment such as crushing and pyrolysis, affecting the normal operation and service life of the equipment; on the other hand, they will interfere with the pyrolysis and dissolution process of organic matter, reduce the extraction efficiency and purity of organic matter, and thus affect the effect and benefits of the entire resource utilization. In response to the above technical problems, the present application proposes an intelligent and environmentally friendly organic solid waste resource utilization method, which identifies and classifies the organic solid waste based on computer vision technology before the organic solid waste enters the crushing mechanism to determine whether there are impurities that are not suitable for treatment. When impurities are detected in the organic solid waste, the mechanical arm is controlled to remove the impurities, and then sent to the crushing mechanism for crushing treatment, and the powdered waste after crushing is dissolved with a dissolving liquid, thereby separating the liquid dissolved with organic matter and the solid powder without organic matter. In this way, the overall process of organic solid waste resource utilization is effectively optimized, which helps to achieve efficient and pure utilization of organic solid waste, and improve waste treatment efficiency and resource utilization quality.

[0034] Figure 1 Flow chart of the intelligent and environmentally friendly method for utilizing organic solid waste resources according to an embodiment of the present application. Figure 1 As shown, the intelligent and environmentally friendly organic solid waste resource utilization method includes the following steps: S1, before the organic solid waste enters the pulverizing mechanism, the organic solid waste is identified and classified based on computer vision to determine whether there are impurities in the organic solid waste that are not suitable for treatment; S2, in response to the judgment result that there are impurities in the organic solid waste that are not suitable for treatment, the robot arm is controlled to remove the impurities to obtain pre-treated organic solid waste; S3, the pre-treated organic solid waste is pulverized into powdered waste by using the pulverizing mechanism; S4, the powdered waste is mixed with a dissolving liquid, and a liquid containing dissolved organic matter and a solid powder without organic matter are obtained by solid-liquid dissolution and separation and purification.

[0035] In the above-mentioned intelligent and environmentally friendly organic solid waste resource utilization method, in step S1, before the organic solid waste enters the crushing mechanism, the organic solid waste is identified and classified based on computer vision to determine whether there are impurities in the organic solid waste that are not suitable for treatment. It should be understood that in the actual collection scenario, the source of organic solid waste is extremely complex. Taking urban domestic waste as an example, the kitchen waste part is often mixed with impurities such as metal tableware, plastic packaging, and glass fragments. It is difficult to achieve accurate identification by traditional manual sorting or simple screening. If it enters the crushing link directly, metal fragments may damage the tool, and toxic gases such as dioxins will be produced during high-temperature pyrolysis of plastics. Glass fragments may destroy the homogeneity of the dissolution reaction. Traditional pneumatic sorting or magnetic separation can only handle specific categories of impurities (such as magnetic metals), and is ineffective for non-metallic foreign matter (such as plastic tableware), and the sorting accuracy is affected by the bulk density of the material. Therefore, in the initial stage of organic solid waste treatment, the present application first establishes a raw material quality control barrier through computer vision technology to actively remove harmful impurities, thereby ensuring the purity of the raw materials in the subsequent processing flow and avoiding equipment loss and product pollution. Among them, Figure 2 This is a flowchart of sub-step S1 of the intelligent and environmentally friendly organic solid waste resource utilization method according to an embodiment of the present application.

[0036] Figure 3 FIG. 1 is a data flow diagram of sub-step S1 of the intelligent and environmentally friendly organic solid waste resource utilization method according to an embodiment of the present application. Figure 2 and Figure 3 As shown, the step S1 includes the steps of: S11, collecting image data of organic solid waste using a high-resolution camera; S12, extracting visual features of suspected impurity targets from the image data of the organic solid waste to obtain a suspected impurity target ROI visual feature map; S13, enhancing the visual feature significance of the suspected impurity target ROI visual feature map to obtain a suspected impurity target ROI visual enhancement feature map; S14, determining the recognition result based on the suspected impurity target ROI visual enhancement feature map.

[0037] Specifically, in step S11, high-resolution cameras are used to collect image data of organic solid waste. It should be understood that since the sizes of impurities such as metal scraps and plastic films mixed in organic solid waste vary significantly (from millimeters to centimeters), traditional low-resolution cameras (such as 720P) are difficult to capture the morphological characteristics of tiny impurities (such as iron wire scraps), and the surface of the waste is often attached with sludge and oil stains, so high-definition images are required to ensure the restoration of details. Therefore, in this application, a high-resolution industrial camera (resolution ≥ 40 million pixels) is installed 30 cm above the conveyor belt, and an appropriate light source system is used to collect image data of organic solid waste, so as to ensure that the collected images have high clarity and can accurately capture the detailed characteristics of organic solid waste and its mixed impurities.

[0038] Specifically, in order to ensure that the collected images have sufficient clarity to accurately reflect the specific conditions of organic solid waste and its mixed impurities, it is crucial to select an appropriate light source system. The selection of the light source should not only consider providing sufficient light to illuminate the entire observation area, but also avoid generating overly strong shadows or light spots, so as not to affect subsequent image analysis. By precisely adjusting the angle and intensity of the light source, the image distortion caused by surface attachment of sludge, oil stains, etc. can be effectively reduced. In addition, by adopting a ring light source layout, the light can be evenly irradiated on the surface of the waste, thus better highlighting the boundary between impurities and the main material and improving the recognition accuracy.

[0039] In the process of specific implementation, the industrial camera needs to be fixed at a specific height to obtain the best viewing angle. This arrangement not only helps to cover the largest possible observation range, but also ensures that the waste at each position can be fully illuminated and photographed. At the same time, considering the variety and different shapes of the waste, the continuous shooting mode can ensure that no possible impurities are missed. By analyzing the continuous frames, not only can the detection accuracy be increased, but also the existence and specific location of impurities can be further confirmed, which provides strong support for the subsequent operation of removing impurities.

[0040] In order to adapt to different types of organic solid waste and the changes in its surface conditions, the industrial camera also needs to have an autofocus function. This enables the camera to quickly adjust the focal length to obtain clear and sharp images regardless of whether the waste is dry and loose or wet and sticky. At the same time, combined with advanced image processing algorithms, such as edge detection, contrast enhancement and other technologies, the problem of image quality degradation caused by environmental factors can be compensated to a certain extent, ensuring that valuable feature information can be extracted even under relatively harsh conditions.

[0041] During the entire image acquisition process, it is equally important to maintain the stability and consistency of the system. This means that in addition to the hardware facilities themselves meeting high standards, the software level also needs to have good compatibility and scalability to adjust parameter settings according to actual situations at any time. For example, according to the characteristics of different batches of waste, key parameters such as exposure time and gain value can be flexibly set to optimize the final imaging effect. In addition, establishing a complete database to store the data collected in previous times is not only beneficial for tracking historical records, but also can be used as the basic data for training machine learning models to continuously improve the accuracy of identification and classification.

[0042] It is worth noting that although high-resolution industrial cameras can greatly improve image quality, in the face of complex and changing actual application scenarios, relying solely on hardware upgrades often cannot completely solve the problem. Therefore, it is particularly necessary to introduce intelligent algorithms to assist image analysis. These algorithms can automatically screen out eligible image segments according to pre-set criteria and deeply mine the information contained therein. For example, using deep learning technology to train a neural network model to learn to distinguish the appearance characteristics of different types of impurities, thereby improving the robustness and adaptability of the overall system.

[0043] To further improve the effect of image acquisition, the method of multi-angle shooting can also be considered. That is, multiple cameras are set at the same position to shoot the same object from different directions. This not only can more comprehensively display the overall structure of the waste, but also helps to discover small or hidden impurities that are difficult to detect from a single angle. By fusing the images from each perspective, a more three-dimensional and detailed three-dimensional view can be obtained, greatly enhancing the reliability of subsequent identification and classification work.

[0044] Figure 4 It is a flowchart of sub-step S12 of the intelligent environmental protection organic solid waste resource utilization method according to an embodiment of the present application. As Figure 4 shown, the step S12 includes steps: S121, inputting the image data of the organic solid waste into a suspected impurity target detection network based on the Mask R-CNN model to obtain a suspected impurity target ROI image and its position data; S122, extracting the visual features of the suspected impurity target ROI image to obtain a suspected impurity target ROI visual feature map.

[0045] More specifically, in step S121, the image data of the organic solid waste is input into a suspected impurity target detection network based on the Mask R-CNN model to obtain a suspected impurity target ROI image and its position data. Specifically, considering that the image data of the organic solid waste contains a large amount of background information related to the organic solid waste, directly performing impurity identification on the entire image is computationally intensive and inefficient. Therefore, to improve the efficiency and accuracy of impurity identification, this application uses the Mask R-CNN model to quickly detect the suspected impurity target areas in the image data of the organic solid waste. Specifically, the Mask R-CNN model is based on the convolutional neural network (CNN) architecture. During the training phase, the model is input with a large number of labeled images containing various organic wastes and common impurities, and the model parameters are continuously adjusted through the backpropagation algorithm to learn the characteristic patterns of different objects. In actual application, after inputting the image data of the organic solid waste, the Mask R-CNN model extracts features from the image through a series of convolutional layers and pooling layers, and generates a series of candidate regions that may contain the target on the extracted feature map. By classifying and performing bounding box regression on each candidate region, it is determined which candidate regions are the real suspected impurity targets, and an accurate segmentation mask is generated for each suspected impurity target through the mask branch, so as to obtain the ROI image of the suspected impurity target and its position data in the original image. In this way, subsequent refined identification processing can be performed only on the detected suspected impurity target areas, thus significantly improving the efficiency and accuracy of impurity identification.

[0046] More specifically, in step S122, the visual features of the suspected impurity target ROI image are extracted to obtain a suspected impurity target ROI visual feature map. Specifically, in order to focus on the discriminative features of the suspected impurity target itself (such as the regular geometric edges of metals and the translucent textures of plastics), this application further uses a deep feature extraction method to extract features from the suspected impurity target ROI image through a multi-layer convolutional neural network, so as to automatically learn and extract the deep visual information such as the shape, texture, and color of the suspected impurity target by using the deep learning ability of the neural network, and obtain a suspected impurity target ROI visual feature map, thereby providing rich discriminative bases for subsequent impurity identification.

[0047] Specifically, in step S13, the visual feature saliency of the suspected impurity target ROI visual feature map is enhanced to obtain a suspected impurity target ROI visual enhanced feature map. It should be understood that in the suspected impurity target ROI visual feature map of the present application, there may be some low-contrast impurities (such as black plastics and carbonized organic substances) with insufficient distinguishability in the conventional feature space and noise interference, etc., which may lead to inaccurate judgment of impurities in the subsequent recognition process. Therefore, the present application further enhances the visual feature saliency of the suspected impurity target ROI visual feature map to utilize the context information of the suspected impurity target ROI visual feature map, and perform fine-grained enhancement on each pixel feature in the suspected impurity target ROI visual feature map to enhance the expressiveness and distinguishability of impurity features and improve the confidence of classification decisions. Among them, Figure 5 is a flowchart of sub-step S13 of the intelligent environmental protection organic solid waste resource utilization method according to an embodiment of the present application. As Figure 5 shown, step S13 includes steps: S131, performing feature decoupling on the suspected impurity target ROI visual feature map along the channel dimension to obtain a set of suspected impurity target ROI pixel-level visual feature vectors; S132, extracting the suspected impurity target ROI pixel-level visual feature vector at the (i, j) pixel position from the set of suspected impurity target ROI pixel-level visual feature vectors as the suspected impurity target ROI pixel-level visual feature vector to be enhanced; S133, performing context-aware enhancement based on dynamic local receptive field anchoring on the suspected impurity target ROI pixel-level visual feature vector to be enhanced to obtain an enhanced suspected impurity target ROI pixel-level visual feature vector, where the enhanced suspected impurity target ROI pixel-level visual feature vector is the channel feature vector at the (i, j) pixel position of the suspected impurity target ROI visual enhanced feature map.

[0048] More specifically, step S131 is expressed by the formula:

[0049] F∈R H×W×C

[0050]

[0051] where R represents the set of real numbers, H, W, and C respectively represent the height, width, and number of channels of the suspected impurity target ROI visual feature map, F represents the suspected impurity target ROI visual feature map, and v 1,1 、v 1,W 、v H,1 and v H,Wrespectively represent the suspected impurity target ROI pixel-level visual feature vectors at the (1,1), (1,W), (H,1), and (H,W) pixel positions of the suspected impurity target ROI visual feature map, and FeatureDecoupling(·) represents the feature decoupling function.

[0052] That is, by decoupling the suspected impurity target ROI visual feature map along the channel dimension, the multi-channel responses of each pixel are disassembled into independent suspected impurity target ROI pixel-level visual feature vectors, which can eliminate the interference of redundant information between channels and enable the fine-grained features such as material attributes and edge contours carried by each pixel to be independently expressed. In this way, a more accurate feature perception boundary can be constructed, thereby improving the sensitivity to tiny abnormal features.

[0053] More specifically, the step S132 is expressed by the formula:

[0054] v tbs =v i,j ∈R C

[0055] where v i,j represents the suspected impurity target ROI pixel-level visual feature vector at the (i,j) pixel position in the suspected impurity target ROI visual feature map, and v tbs represents the suspected impurity target ROI pixel-level visual feature vector to be enhanced.

[0056] That is, due to the spatial heterogeneity of impurities and organic matrices in visual features, traditional global feature pooling or regional aggregation will blur these key details. In this application, by extracting the suspected impurity target ROI pixel-level visual feature vector at the (i,j) pixel position as the processing anchor point, the calculation granularity is essentially sunk to the pixel level to ensure that the unique information such as the material attributes and texture gradients of each pixel is independently encoded, so that the suspected impurity target ROI pixel-level visual feature vector to be enhanced can highlight the fine-grained features and combine the context features of its surrounding neighborhood to characterize the local material specificity.

[0057] Figure 6 is a flowchart of sub-step S133 of the intelligent environmental protection organic solid waste resource utilization method according to an embodiment of the present application. As Figure 6As shown, the step S133 includes steps: S1331, based on the feature distribution of the pixel-level visual feature vectors of the ROI of the suspected impurity target to be enhanced, perform local receptive field anchoring on the set of pixel-level visual feature vectors of the ROI of the suspected impurity target to filter out the set of pixel-level visual feature vectors of the ROI of the suspected impurity target within the local receptive field; S1332, based on the set of pixel-level visual feature vectors of the ROI of the suspected impurity target within the local receptive field, perform saliency enhancement on the pixel-level visual feature vectors of the ROI of the suspected impurity target to be enhanced to obtain enhanced pixel-level visual feature vectors of the ROI of the suspected impurity target.

[0058] In a specific example of the present application, the step S1331 includes: First, perform information compression on the pixel-level visual feature vectors of the ROI of the suspected impurity target to be enhanced to obtain pixel-level visual distilled feature vectors of the ROI of the suspected impurity target to be enhanced, which is represented by the formula:

[0059]

[0060] where ||·|| represents calculating the norm, and v s represents the pixel-level visual distilled feature vectors of the ROI of the suspected impurity target to be enhanced.

[0061] That is, through information compression based on the knowledge distillation logic, the hidden layer knowledge representing the salient features in the pixel-level visual feature vectors of the ROI of the suspected impurity target to be enhanced is directionally extracted, while suppressing interference signals. Through this information compression method, a physically interpretable low-dimensional feature space can be constructed, enabling the compressed pixel-level visual distilled feature vectors of the ROI of the suspected impurity target to be enhanced to carry tiny but crucial material difference information with a higher signal-to-noise ratio, thereby providing a sparse feature basis for quantitative analysis for the subsequent receptive field adaptive module.

[0062] Then, based on the structural characteristics of the feature distribution space of the pixel-level visual distilled feature vectors of the ROI of the suspected impurity target to be enhanced, determine the size of the feature receptive field of the pixel-level visual distilled feature vectors of the ROI of the suspected impurity target to be enhanced, which is represented by the formula:

[0063]

[0064] where log2(·) represents the logarithmic function with base 2, and r represents the half side length of the feature receptive field of the pixel-level visual distilled feature vectors of the ROI of the suspected impurity target to be enhanced.

[0065] That is, since the suspected impurity target ROI to-be-strengthened pixel-level visual distillation feature vector after distillation compression has encoded key attributes, but its spatial distribution pattern implies the target physical scale information, therefore, the present application establishes an implicit mapping relationship between the feature space topology structure and the actual physical scale through the spatial structure characteristics of the feature distribution, to quantify the neighborhood highest semantic correlation points of the suspected impurity target ROI to-be-strengthened pixel-level visual distillation feature vector, so that the model can adaptively match the best context awareness range for each pixel point.

[0066] Finally, based on the size of the feature receptive field, a set of suspected impurity target ROI pixel-level visual feature vectors within the local receptive field is screened out from the set of suspected impurity target ROI pixel-level visual feature vectors, which is expressed by the formula:

[0067]

[0068] where, v i-r,j 、v i+r,j 、v i,j+r and v i+r,j+r respectively represent the suspected impurity target ROI pixel-level visual feature vectors at the (i-r,j), (i+r,j), (i,j+r) and (i+r,j+r) positions in the suspected impurity target ROI visual feature map, and W represents the set of suspected impurity target ROI pixel-level visual feature vectors within the local receptive field.

[0069] That is, by constructing a matrix-type neighborhood according to the size of the feature receptive field of the suspected impurity target ROI to-be-strengthened pixel-level visual distillation feature vector, the feature tensor is projected onto the local coordinate system with the central pixel as the origin to eliminate the feature distribution offset noise. In this way, based on the generated suspected impurity target ROI pixel-level visual feature vectors within the local receptive field, the complementary nature of the neighborhood features can be utilized to enhance the recognition robustness of sub-millimeter impurity edges and improve the detection sensitivity of the model to impurity feature singular points.

[0070] Figure 7 It is a flowchart of sub-step S1332 of the intelligent environmental protection organic solid waste resource utilization method according to an embodiment of the present application. As Figure 7As shown, step S1332 includes steps: S13321. Based on the feature correlation between each local receptive field suspected impurity target ROI pixel-level visual feature vector in the set of local receptive field suspected impurity target ROI pixel-level visual feature vectors and the suspected impurity target ROI pixel-level visual feature vector to be enhanced, perform saliency aggregation on the set of local receptive field suspected impurity target ROI pixel-level visual feature vectors to obtain a local receptive field suspected impurity target ROI pixel-level visual feature saliency aggregation coding vector; S13322. Fuse the local receptive field suspected impurity target ROI pixel-level visual feature saliency aggregation coding vector and the suspected impurity target ROI pixel-level visual feature vector to be enhanced to obtain the enhanced suspected impurity target ROI pixel-level visual feature vector.

[0071] In a specific example of the present application, step S13321 is represented by the formula:

[0072]

[0073] where v m,n represents the local receptive field suspected impurity target ROI pixel-level visual feature vector at the (m,n) position in the set of local receptive field suspected impurity target ROI pixel-level visual feature vectors, (·) T represents the transpose of the vector, represents vector multiplication, softmax(·) represents the softmax normalization function, θ(v m,n ) represents the saliency weight of v m,n , and V s represents the local receptive field suspected impurity target ROI pixel-level visual feature saliency aggregation coding vector.

[0074] That is, by calculating the correlation between each local receptive field suspected impurity target ROI pixel-level visual feature vector and the suspected impurity target ROI pixel-level visual feature vector to be enhanced, an attention weight map based on context correlation is constructed in the feature space. This weight relationship can effectively represent the characteristic consistency law of the impurity target area in spatial distribution, can use the feature correlation as a dynamic modulation coefficient to co-enhance the pixel-level features with similar material properties in the spatial domain, and at the same time suppress the pseudo-feature response caused by non-significant interference terms, so as to enhance the generalization ability of the impurity recognition model for working conditions such as surface fouling and shadow occlusion of waste.

[0075] In a preferred example of the present application, the step S13322 includes: First, based on the conformal fusion constraint of the set of pixel-level visual feature vectors of the suspected impurity target ROI within the local receptive field, calculate the modulation weighting coefficients of the pixel-level visual feature saliency aggregation coding vector of the suspected impurity target ROI within the local receptive field and the pixel-level visual feature vector to be enhanced of the suspected impurity target ROI, which is expressed by the formula:

[0076]

[0077] ||v m,n (3) -v m,n (2) ||2 = ω × α × β

[0078] Wherein, sin(·) represents the sine function, v m,n (3) represents the volume space representation vector of the set of pixel-level visual feature vectors of the suspected impurity target ROI within the local receptive field, v m,n (2) represents the boundary representation vector of the set of pixel-level visual feature vectors of the suspected impurity target ROI within the local receptive field, α and β respectively represent the modulation weighting coefficients of the pixel-level visual feature saliency aggregation coding vector of the suspected impurity target ROI within the local receptive field and the pixel-level visual feature vector to be enhanced of the suspected impurity target ROI, ω represents the equal proportion scaling coefficient, and ||·||2 represents calculating the two-norm.

[0079] That is, by introducing the conformal commutation constraint mechanism between the volume space representation vector and the boundary representation vector of the set of pixel-level visual feature vectors of the suspected impurity target ROI within the local receptive field, the feature coding distortion caused by the geometric topological distortion of the significant region and the non-significant region within the local receptive field during the feature fusion process is eliminated. In this way, by establishing the regularity specification standard of the boundary surface type-volume space tensor, the set of pixel-level visual feature vectors of the suspected impurity target ROI within the local receptive field can meet the conformal representation requirements during fusion, and through the feature space commutation optimization under the regularization constraint, the robustness of the impurity detection model under complex working conditions is enhanced.

[0080] Then, based on the modulation weighting coefficients, perform weighted fusion on the pixel-level visual feature saliency aggregation coding vector of the suspected impurity target ROI within the local receptive field and the pixel-level visual feature vector to be enhanced of the suspected impurity target ROI to obtain the enhanced pixel-level visual feature vector of the suspected impurity target ROI, which is expressed by the formula:

[0081] v' i,j = α·v i,j + β·Vs

[0082] Among them, v' i,j represents the enhanced suspected impurity target ROI pixel-level visual feature vector.

[0083] That is, by introducing a modulation weighting coefficient, the suspected impurity target ROI pixel-level visual feature saliency aggregation coding vector in the local receptive field and the suspected impurity target ROI pixel-level visual feature vector to be enhanced are dynamically fused, so as to adaptively adjust the contribution weights of the global context information and the local micro-structure features according to the key discriminant features of the impurity target at different spatial scales, thereby constructing an enhanced suspected impurity target ROI pixel-level visual feature vector with multi-scale perception ability, enabling the model to more accurately identify impurities with complex shapes, and significantly reducing the false detection rate and missed detection rate caused by incomplete feature expression.

[0084] Specifically, in a specific example of the present application, the step S14 includes: inputting the suspected impurity target ROI visual enhancement feature map into an impurity recognizer based on a classifier to obtain the recognition result, where the recognition result includes the impurity type label and its confidence. Specifically, an impurity recognizer based on a classifier usually adopts classification algorithms such as support vector machine (SVM). In the training stage, a large number of visual feature map samples with labeled impurity types are used to train the classifier, so that it learns the feature patterns and classification boundaries corresponding to different impurity types. In actual application, the suspected impurity target ROI visual enhancement feature map is input into the trained classifier, and the classifier makes a classification judgment on the input feature map according to the learned feature patterns and classification boundaries, and outputs the impurity type label (such as metal, plastic, glass, etc.) and its corresponding confidence. The confidence reflects the accuracy degree of the classifier's judgment on the impurity type. A high confidence indicates that the classifier's judgment on this impurity type has a high reliability. For the recognition result with a confidence lower than the preset threshold, secondary analysis or manual review can be performed to ensure the accuracy of the recognition result.

[0085] In the above intelligent environmental protection organic solid waste resource utilization method, in the step S2, in response to the judgment result that there are impurities in the organic solid waste that are not suitable for treatment, the robotic arm is controlled to remove the impurities to obtain the pretreated organic solid waste. Specifically, when the classifier outputs the impurity classification result, if the impurity type belongs to the preset impurity category that is not suitable for treatment (such as impurities like metal, plastic, glass, etc. that may damage the subsequent treatment equipment or affect the product quality), the impurity removal mechanism is immediately triggered. The control system sends an instruction to the robotic arm according to the position data of the suspected impurity target ROI image obtained in the above target detection process, controls the robotic arm to locate and grab the impurities, and removes them from the organic solid waste to ensure the safety of the subsequent treatment process and the product quality.

[0086] In the process of specific implementation, in order to achieve efficient impurity removal, the design of the robotic arm needs to fully consider flexibility and precision. A robotic arm with a multi-degree-of-freedom design can move freely in three-dimensional space, ensuring that no matter where the impurity is located in the waste pile, it can be quickly and accurately located. At the same time, the selection of the end effector is equally crucial. Considering that various types of impurities need to be processed, such as irregularly shaped metal blocks, soft plastic sheets, or fragile glass fragments, an end effector equipped with a multi-functional grasping tool is usually selected. This tool can not only adapt to objects of different sizes and hardnesses but also avoid causing unnecessary damage to the waste itself while ensuring sufficient grasping force.

[0087] Once the robotic arm receives the instruction sent by the control system, it starts to act according to the pre-set path planning algorithm. The path planning should not only consider the shortest time to reach the target position but also avoid collisions with other operating devices. When the robotic arm successfully locates the impurity, the actual grasping process follows. Based on the previously obtained target information, the control system will guide the end effector to adopt an appropriate grasping method. For larger and heavier metal blocks, a strongly magnetic adsorption device may be selected to directly lift them; while for lightweight plastic films, a vacuum suction cup may be needed to ensure stable grasping without damaging the material. Each grasping method requires precise control of the force magnitude and action time to achieve the purpose of effectively removing the impurity without having a negative impact on the surrounding environment.

[0088] After the grasping is completed, the robotic arm needs to move the impurity to the designated recycling area along the predetermined path. During this period, the control system continues to monitor the entire process to ensure that the impurity is correctly placed in a position that will not interfere with subsequent operations. At the same time, in order to maintain the continuity and efficiency of the overall process, after one impurity is successfully removed, the system should be able to quickly reset and be ready to handle the next possible impurity situation. This requires the system to have a fast response ability and an efficient task scheduling mechanism to ensure that every step can be seamlessly connected, minimizing downtime and resource waste to the greatest extent.

[0089] In the above intelligent environmental protection organic solid waste resource utilization method, in step S3, a crushing mechanism is used to crush the pretreated organic solid waste into powdered waste. It should be understood that although the purity of the organic solid waste after impurity removal has been improved, it still maintains a relatively large size. In the subsequent dissolution process, due to the limited contact area, it is difficult for organic substances to dissolve quickly and fully into the dissolution liquid, which will not only prolong the dissolution reaction time, reduce the treatment efficiency, but also may cause some organic substances to not be completely dissolved, affecting the integrity and efficiency of resource extraction. Therefore, it is necessary to further use a crushing mechanism to crush the pretreated organic solid waste, transforming the organic solid waste from a relatively large size into fine powder, increasing its contact area with the dissolution liquid, thereby significantly improving the dissolution rate and dissolution degree of organic substances in the subsequent dissolution process.

[0090] In the above intelligent environmental protection organic solid waste resource utilization method, in step S4, the powdered waste is mixed with a dissolution liquid, and a liquid containing dissolved organic substances and solid powder with organic substances removed are obtained through solid-liquid dissolution and separation and purification. That is, by utilizing the specific solubility of the dissolution liquid for organic substances, after mixing the powdered waste and the dissolution liquid in a certain proportion, under conditions such as stirring and heating, organic substance molecules gradually break away from the solid matrix and dissolve into the dissolution liquid to form a homogeneous solution. Subsequently, solid-liquid separation techniques such as filtration and centrifugation are used to separate the insoluble solid powder from the solution based on the physical property differences between the solid powder and the solution, such as different densities. In addition, for the obtained solution containing organic substances, purification methods such as distillation and extraction can be used to further improve the purity of the organic substance solution by utilizing the differences in boiling point, solubility, etc. between the organic substance, the dissolution liquid, and other impurities. In this way, organic substances can be efficiently extracted from organic solid waste, providing high-quality raw materials for subsequent resource recovery and utilization. It should be understood that mixing the powdered waste with the dissolution liquid and obtaining a liquid containing dissolved organic substances and solid powder with organic substances removed can be achieved by using the method disclosed in Chinese Patent CN116765094A. Of course, other methods can also be used for the dissolution and separation of the powdered waste, and this is not limited to this application.

[0091] In summary, the intelligent environmental protection organic solid waste resource utilization method based on the embodiments of the present application is elucidated. Before the organic solid waste enters the crushing mechanism, the organic solid waste is identified and classified based on computer vision technology to determine whether there are impurities that are not suitable for treatment. When impurities are detected in the organic solid waste, the robotic arm is controlled to remove the impurities, and then it is sent to the crushing mechanism for crushing treatment. A dissolving solution is used to dissolve the crushed powdery waste, and then the liquid dissolved with organic substances and the solid powder with organic substances removed are separated. In this way, the overall process of organic solid waste resource utilization is effectively optimized, which helps to achieve the efficient and pure utilization of organic solid waste and improve the waste treatment efficiency and the quality of resource utilization.

[0092] Furthermore, an intelligent environmental protection organic solid waste resource utilization system is also provided.

[0093] Figure 8 The block diagram of the intelligent environmental protection organic solid waste resource utilization system according to the embodiments of the present application is shown as Figure 8 shown. As shown, the intelligent environmental protection organic solid waste resource utilization system 100 according to the embodiments of the present application includes: a waste identification and classification module 110, which is used to identify and classify the organic solid waste based on computer vision before the organic solid waste enters the crushing mechanism to determine whether there are impurities that are not suitable for treatment in the organic solid waste; an impurity removal module 120, which is used to control the robotic arm to remove the impurities in response to the judgment result that there are impurities that are not suitable for treatment in the organic solid waste to obtain the pre-treated organic solid waste; a waste crushing module 130, which is used to crush the pre-treated organic solid waste into powdery waste by using a crushing mechanism; a solid-liquid dissolution, separation and purification module 140, which is used to mix the powdery waste with a dissolving solution and obtain the liquid dissolved with organic substances and the solid powder with organic substances removed through solid-liquid dissolution and separation and purification.

[0094] Here, those skilled in the art can understand that the specific operations of each module in the above intelligent environmental protection organic solid waste resource utilization system have been introduced in detail in the description of the intelligent environmental protection organic solid waste resource utilization method above, and therefore, the repeated description thereof will be omitted. Figures 1 to 7 of the intelligent environmental protection organic solid waste resource utilization method, and thus, the repeated description thereof will be omitted.

[0095] The basic principles of the present invention have been described above in connection with specific embodiments. However, it should be noted that the advantages, benefits, effects, etc. mentioned in the present invention are merely examples and not limitations, and it cannot be considered that these advantages, benefits, effects, etc. are essential for each embodiment of the present invention. In addition, the specific details of the above embodiments are only for the purpose of illustration and facilitating understanding, rather than limitations. The above details do not limit the present invention to necessarily adopt the above specific details for implementation.

[0096] In the above embodiments, the descriptions of each embodiment have their own focuses. For parts not detailed or recorded in a certain embodiment, reference can be made to the relevant descriptions of other embodiments. In the several embodiments provided by the present invention, it should be understood that the disclosed systems and methods can be implemented in other ways. For example, the system embodiments described above are merely illustrative. For example, the unit division is only a logical function division, and there can be other division methods in actual implementation. The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they can be located in one place or distributed to multiple network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0097] For those skilled in the art, it is obvious that the present invention is not limited to the details of the above exemplary embodiments, and the present invention can be implemented in other specific forms without departing from the spirit or basic characteristics of the present invention. Therefore, from any point of view, the embodiments should be regarded as exemplary and non-limiting. The scope of the present invention is defined by the appended claims rather than the above description. Therefore, all changes falling within the meaning and scope of the equivalent elements of the claims are intended to be embraced within the present invention. Any reference signs in the claims should not be regarded as limiting the claimed rights.

[0098] In addition, it is obvious that the word "comprising" does not exclude other units or steps, and the singular does not exclude the plural. The multiple units stated in the system claims can also be implemented by one unit through software or hardware.

[0099] Finally, it should be noted that the above description has been given for the purpose of illustration and description. In addition, the above embodiments are only used to illustrate the technical solutions of the present invention and not to limit them. Although the present invention has been described in detail with reference to the preferred embodiments, those of ordinary skill in the art should understand that the technical solutions of the present invention can be modified or equivalently replaced without departing from the spirit and scope of the technical solutions of the present invention.

Claims

1. An intelligent environmental protection organic solid waste resource utilization method, characterized in that, Comprising: Before the organic solid waste enters the crushing mechanism, identifying and classifying the organic solid waste based on computer vision to determine whether there are impurities that are not suitable for treatment in the organic solid waste; In response to the judgment result that there are impurities that are not suitable for treatment in the organic solid waste, controlling the robotic arm to remove the impurities to obtain pre-treated organic solid waste; Using a crushing mechanism to crush the pre-treated organic solid waste into powdered waste; Mixing the powdered waste with a dissolving solution, and obtaining a liquid in which organic substances are dissolved and a solid powder from which organic substances are removed through solid-liquid dissolution and separation and purification.

2. The intelligent environmental protection organic solid waste resource utilization method according to claim 1, wherein Identifying and classifying the organic solid waste based on computer vision to determine whether there are impurities that are not suitable for treatment in the organic solid waste, including: Collecting image data of the organic solid waste using a high-resolution camera; Extracting visual features of suspected impurity targets from the image data of the organic solid waste to obtain a visual feature map of the suspected impurity target ROI; Enhancing the visual feature saliency of the visual feature map of the suspected impurity target ROI to obtain an enhanced visual feature map of the suspected impurity target ROI; Based on the enhanced visual feature map of the suspected impurity target ROI, determining the recognition result.

3. The intelligent environmental protection organic solid waste resource utilization method according to claim 2, characterized in that, Extracting visual features of suspected impurity targets from the image data of the organic solid waste to obtain a visual feature map of the suspected impurity target ROI, including: Inputting the image data of the organic solid waste into a suspected impurity target detection network based on the Mask R-CNN model to obtain a suspected impurity target ROI image and its position data; Extracting the visual features of the suspected impurity target ROI image to obtain a visual feature map of the suspected impurity target ROI.

4. The intelligent environmental protection organic solid waste resource utilization method according to claim 3, characterized in that, Enhancing the visual feature saliency of the visual feature map of the suspected impurity target ROI to obtain an enhanced visual feature map of the suspected impurity target ROI, including: Decoupling features of the visual feature map of the suspected impurity target ROI along the channel dimension to obtain a set of pixel-level visual feature vectors of the suspected impurity target ROI; Extracting the pixel-level visual feature vector of the suspected impurity target ROI at the (i, j) pixel position from the set of pixel-level visual feature vectors of the suspected impurity target ROI as the pixel-level visual feature vector to be enhanced of the suspected impurity target ROI; Performing context-aware enhancement based on dynamic local receptive field anchoring on the pixel-level visual feature vector to be enhanced of the suspected impurity target ROI to obtain an enhanced pixel-level visual feature vector of the suspected impurity target ROI, wherein the enhanced pixel-level visual feature vector of the suspected impurity target ROI is the channel feature vector at the (i, j) pixel position of the enhanced visual feature map of the suspected impurity target ROI.

5. The intelligent environmental protection organic solid waste resource utilization method according to claim 4, characterized in that, Performing context-aware enhancement based on dynamic local receptive field anchoring on the pixel-level visual feature vector to be enhanced of the suspected impurity target ROI to obtain an enhanced pixel-level visual feature vector of the suspected impurity target ROI, including: Based on the feature distribution of the suspected impurity target ROI to-be-strengthened pixel-level visual feature vectors, perform local receptive field anchoring on the set of suspected impurity target ROI pixel-level visual feature vectors to filter out the set of suspected impurity target ROI pixel-level visual feature vectors within the local receptive field; Based on the set of suspected impurity target ROI pixel-level visual feature vectors within the local receptive field, perform saliency enhancement on the suspected impurity target ROI to-be-strengthened pixel-level visual feature vectors to obtain enhanced suspected impurity target ROI pixel-level visual feature vectors.

6. The intelligent environmental protection organic solid waste resource utilization method according to claim 5, characterized in that Based on the feature distribution of the suspected impurity target ROI to-be-strengthened pixel-level visual feature vectors, performing local receptive field anchoring on the set of suspected impurity target ROI pixel-level visual feature vectors to filter out the set of suspected impurity target ROI pixel-level visual feature vectors within the local receptive field includes: Perform information compression on the suspected impurity target ROI to-be-strengthened pixel-level visual feature vectors to obtain suspected impurity target ROI to-be-strengthened pixel-level visual distilled feature vectors; Based on the characteristic distribution space structure characteristics of the suspected impurity target ROI to-be-strengthened pixel-level visual distilled feature vectors, determine the size of the characteristic receptive field of the suspected impurity target ROI to-be-strengthened pixel-level visual distilled feature vectors; Based on the size of the characteristic receptive field, filter out the set of suspected impurity target ROI pixel-level visual feature vectors within the local receptive field from the set of suspected impurity target ROI pixel-level visual feature vectors.

7. The intelligent environmental protection organic solid waste resource utilization method according to claim 6, wherein, Based on the set of suspected impurity target ROI pixel-level visual feature vectors within the local receptive field, performing saliency enhancement on the suspected impurity target ROI to-be-strengthened pixel-level visual feature vectors to obtain enhanced suspected impurity target ROI pixel-level visual feature vectors includes: Based on the feature correlation of each suspected impurity target ROI pixel-level visual feature vector within the local receptive field in the set of suspected impurity target ROI pixel-level visual feature vectors within the local receptive field with respect to the suspected impurity target ROI to-be-strengthened pixel-level visual feature vectors, perform saliency aggregation on the set of suspected impurity target ROI pixel-level visual feature vectors within the local receptive field to obtain a local receptive field suspected impurity target ROI pixel-level visual feature saliency aggregation coding vector; Fuse the local receptive field suspected impurity target ROI pixel-level visual feature saliency aggregation coding vector and the suspected impurity target ROI to-be-strengthened pixel-level visual feature vectors to obtain the enhanced suspected impurity target ROI pixel-level visual feature vectors.

8. The intelligent environmental protection organic solid waste resource utilization method according to claim 7, characterized in that, Fusing the local receptive field suspected impurity target ROI pixel-level visual feature saliency aggregation coding vector and the suspected impurity target ROI to-be-strengthened pixel-level visual feature vectors to obtain the enhanced suspected impurity target ROI pixel-level visual feature vectors includes: Based on the conformal fusion constraint of the set of pixel-level visual feature vectors of the suspected impurity target ROI within the local receptive field, calculate the modulation weighting coefficients of the pixel-level visual feature saliency aggregation coding vector of the suspected impurity target ROI within the local receptive field and the pixel-level visual feature vector to be enhanced of the suspected impurity target ROI; Based on the modulation weighting coefficients, perform weighted fusion on the pixel-level visual feature saliency aggregation coding vector of the suspected impurity target ROI within the local receptive field and the pixel-level visual feature vector to be enhanced of the suspected impurity target ROI to obtain the enhanced pixel-level visual feature vector of the suspected impurity target ROI.

9. The intelligent environmental protection organic solid waste resource utilization method according to claim 8, wherein Based on the visually enhanced feature map of the suspected impurity target ROI, determine the recognition result, including: Input the visually enhanced feature map of the suspected impurity target ROI into an impurity recognizer based on a classifier to obtain the recognition result, where the recognition result includes an impurity type label and its confidence level.

10. An intelligent environmental protection organic solid waste resource utilization system, characterized in that, Including: A waste recognition and classification module, configured to, before the organic solid waste enters the crushing mechanism, perform recognition and classification on the organic solid waste based on computer vision to determine whether there are impurities that are not suitable for treatment in the organic solid waste; An impurity removal module, configured to, in response to a determination result that there are impurities that are not suitable for treatment in the organic solid waste, control the robotic arm to remove the impurities to obtain pre-treated organic solid waste; A waste crushing module, configured to use a crushing mechanism to crush the pre-treated organic solid waste into powdered waste; A solid-liquid dissolution, separation, and purification module, configured to mix the powdered waste with a dissolution liquid, and obtain a liquid in which organic substances are dissolved and a solid powder from which organic substances are removed through solid-liquid dissolution and separation and purification.

Images