A digital and intelligent monitoring method and system for closed-loop resource utilization of pig farm manure

Abstract

This application provides a digital and intelligent monitoring method and system for closed-loop resource utilization of pig farm manure. By mapping the spatial layout of pig farm manure treatment units and the monitoring range of deployed digital and intelligent sensor terminals, a virtual monitoring domain corresponding to each digital and intelligent sensor terminal is mapped in a digital and intelligent virtual model. Based on the first monitoring coverage information of each virtual monitoring domain in the digital and intelligent virtual model, information on multiple hidden processing units functionally coupled with the monitored and covered processing units in the process flow direction is obtained. A corresponding simulation control mechanism is configured for the monitoring-hidden association combination formed by the first monitoring coverage information and the hidden processing unit information. Based on the virtual monitoring domain and the simulation control mechanism, the virtual processing units in the digital and intelligent virtual model are collaboratively simulated to generate regulatory data for optimizing resource recovery efficiency. The technical solution provided by this application can accurately optimize the resource recovery efficiency in the closed-loop resource utilization of manure even under the influence of blind spots in manure treatment monitoring.

Description

Technical Field

[0001] This application relates to the field of digital and intelligent monitoring technology, and more specifically, to a digital and intelligent monitoring method and system for closed-loop resource utilization of pig farm manure. Background Technology

[0002] Digital and intelligent monitoring is a transformation and upgrade of traditional regulatory systems driven by IoT, big data, and AI technologies. It involves collecting multi-dimensional data in real time through ubiquitous sensor networks and transmitting it to the cloud or edge computing nodes via high-speed networks. It then uses big data platforms to store, process, and analyze massive amounts of data, and integrates appropriate algorithms to achieve intelligent identification of monitored scenarios, automatic early warning of abnormal behavior, and in-depth trend identification. Digital and intelligent monitoring breaks through the limitations of passive recording in traditional monitoring and builds a proactive prevention and control platform that integrates real-time perception, intelligent analysis, accurate early warning, and decision support, significantly improving risk warning capabilities and operational management efficiency.

[0003] In existing digital monitoring systems, the first step is to continuously collect audio, video, and environmental data through a front-end sensing layer. This data is then transmitted in real-time to a central platform via a network transmission layer. The central platform utilizes cloud computing and edge computing for massive data storage and initial processing, and employs artificial intelligence algorithms for deep analysis of the video stream to obtain anomaly analysis results. Finally, the analysis results are visualized and used for early warning through the application layer, thus completing the transformation from passive recording to proactive perception and intervention. However, in the digital monitoring of closed-loop resource utilization of pig farm manure, in the actual scenario of pig farm manure treatment, limitations in sensor cost, installation conditions, and physical layout prevent digital sensing terminals from covering all areas. The processing units create direct monitoring blind spots. The closed-loop resource utilization process of sewage treatment is a highly coupled continuous system. There is a close information connection between each processing unit in the process flow. Traditional monitoring methods rely only on direct monitoring data, which severs this inherent process coupling. It is impossible to perceive the status and assess the impact of hidden processing units (such as sewage treatment transition links, buffer facilities, or indirectly related processing stages) that are not directly equipped with sensors. Consequently, it is impossible to accurately optimize resources in the closed-loop resource utilization of sewage. Therefore, how to accurately optimize the resource recovery efficiency in the closed-loop resource utilization of sewage under the influence of monitoring blind spots has become a difficult problem for the industry. Summary of the Invention

[0004] This application provides a digital and intelligent monitoring method and system for closed-loop resource utilization of pig farm manure, which can accurately optimize the resource recovery efficiency in closed-loop resource utilization of manure under the influence of blind spots in manure treatment monitoring.

[0005] Firstly, this application provides a digital and intelligent monitoring method for the closed-loop resource utilization of pig farm manure, comprising the following steps: Based on the spatial layout and deployment of the pig farm manure treatment unit, the monitoring range of the digital intelligent sensor terminal is mapped in the digital intelligent virtual model of closed-loop resource utilization of manure to the virtual monitoring domain corresponding to each digital intelligent sensor terminal. Spatial analysis is performed on each virtual monitoring domain in the digital intelligent virtual model to obtain first monitoring coverage information. Based on the first monitoring coverage information, topological association analysis is performed on the sewage treatment units in the digital intelligent virtual model that are not covered by the virtual monitoring domains to obtain information on multiple hidden treatment units that are functionally coupled with the monitoring coverage treatment units in the process flow direction. The first monitoring coverage information is coupled with the corresponding hidden processing unit information through process technology to form a monitoring-hidden association combination, and a corresponding simulation control mechanism is configured for each monitoring-hidden association combination. The system identifies virtual processing units corresponding to different stages of pig farm manure treatment in the digital virtual model, and performs collaborative simulation of the operating status of the virtual processing units in the closed-loop resource utilization process of manure based on the virtual monitoring domain and the simulation control mechanism, generating regulatory data for optimizing resource recycling efficiency.

[0006] In some embodiments, based on the spatial layout and deployment of the intelligent sensing terminals of the pig farm manure treatment unit, the mapping of the virtual monitoring domain corresponding to each intelligent sensing terminal in the intelligent virtual model of closed-loop resource utilization of manure specifically includes: Acquire spatial layout data of pig farm manure treatment units and the deployment location and monitoring range of each intelligent sensor terminal; The spatial coordinate system of the digital and intelligent virtual model for closed-loop resource utilization of feces and sewage is constructed based on the spatial layout data; The monitoring range of the digital intelligent sensing terminal is parameterized in the spatial coordinate system to obtain the spatial parameter set of the monitoring range; Based on the deployment location of the digital intelligent sensing terminals, the virtual coordinates of each digital intelligent sensing terminal are located in the spatial coordinate system; Based on the virtual coordinates of each intelligent sensor terminal and the corresponding spatial parameter set of the monitoring range, a virtual monitoring domain corresponding to each intelligent sensor terminal is generated in the intelligent virtual model of closed-loop resource utilization of feces and sewage.

[0007] In some embodiments, spatial parsing is performed on each virtual monitoring domain in the digital intelligent virtual model to obtain the first monitoring coverage information, specifically including: Extract the spatial boundary and topological attribute data of each virtual monitoring domain in the digital intelligent virtual model; Based on the extracted spatial boundary and topological attribute data, a spatial topological relationship network for each virtual monitoring domain is constructed. Based on the spatial topology network, the monitoring coverage processing unit corresponding to each virtual monitoring domain is identified, and then the first monitoring coverage information is generated.

[0008] In some embodiments, based on the first monitoring coverage information, a topological association analysis is performed on the sewage treatment units in the digital virtual model that are not covered by the virtual monitoring domain to obtain information on multiple hidden treatment units that are functionally coupled with the monitored coverage treatment units in the process flow direction. Specifically, this includes: Extract the monitoring coverage processing unit identifier from the first monitoring coverage information, and based on the monitoring coverage processing unit identifier, filter out the sewage treatment units that are not covered by the virtual monitoring domain in the digital virtual model to obtain the dataset of uncovered processing units. Obtain the process flow data of the manure treatment unit in the digital virtual model, and construct the process flow topology model of manure treatment by combining the monitoring coverage treatment unit identifier; Based on the uncovered processing unit dataset and the process flow topology model, the connection relationship between the uncovered processing unit and the monitored covered processing unit in the process flow is identified, and the process correlation matrix is ​​obtained. Based on the process association matrix, uncovered processing units that are functionally coupled with the monitoring and coverage processing unit identifier in the process flow direction are selected to obtain hidden processing unit information.

[0009] In some embodiments, coupling the first monitoring coverage information with the corresponding hidden processing unit information through a process to form a monitoring-hidden association combination specifically includes: Extract the process parameters of the monitoring coverage processing unit in the first monitoring coverage information and the process parameters of the hidden processing unit in the hidden processing unit information to obtain a set of process parameters; Based on the set of process parameters, a correlation benchmark for the coupling of manure treatment processes is constructed; Based on the correlation benchmark of the fecal sewage treatment process coupling, the process flow correlation of the first monitoring coverage information and the hidden treatment unit information is matched to obtain the correlation matching result; Based on the association matching results, the monitoring coverage processing unit and the hidden processing unit that have process coupling relationship are clustered and integrated to form a monitoring-hidden association combination.

[0010] In some embodiments, identifying virtual processing units in the digital virtual model corresponding to different stages of pig farm manure treatment specifically includes: The monitoring scope for different treatment stages of pig farm manure was extracted; For each processing stage, the manure treatment unit within the monitoring range corresponding to the processing stage is extracted from the digital virtual model as a virtual processing unit, thereby obtaining the virtual processing units for different processing stages of pig farm manure.

[0011] In some embodiments, spatial layout data of the pig farm manure treatment unit is obtained through preset CAD engineering drawings of the pig farm manure treatment unit.

[0012] Secondly, this application provides a digital monitoring system for the closed-loop resource utilization of pig farm manure, comprising: The mapping module is used to map the monitoring range of the digital intelligent sensor terminals based on the spatial layout and deployment of the pig farm manure treatment unit, and to map the virtual monitoring domain corresponding to each digital intelligent sensor terminal in the digital intelligent virtual model of closed-loop resource utilization of manure. The processing module is used to perform spatial analysis on each virtual monitoring domain in the digital intelligent virtual model to obtain first monitoring coverage information. Based on the first monitoring coverage information, the module performs topological association analysis on the sewage treatment units in the digital intelligent virtual model that are not covered by the virtual monitoring domains to obtain information on multiple hidden processing units that are functionally coupled with the monitoring coverage processing units in the process flow direction. The processing module is further configured to perform process coupling between the first monitoring coverage information and the corresponding hidden processing unit information to form a monitoring-hidden association combination, and configure a corresponding simulation control mechanism for each monitoring-hidden association combination. The execution module is used to identify virtual processing units in the digital virtual model that correspond to different treatment stages of pig farm manure, and to perform collaborative simulation of the operating status of the virtual processing units in the closed-loop resource utilization process of manure based on the virtual monitoring domain and the simulation control mechanism, thereby generating regulatory data for optimizing resource recycling efficiency.

[0013] Thirdly, this application provides a computer device, which includes a memory and a processor. The memory stores code, and the processor is configured to acquire the code and execute the above-described digital monitoring method for closed-loop resource utilization of pig farm manure.

[0014] Fourthly, this application provides a computer-readable storage medium storing a computer program, which, when executed by a processor, implements the aforementioned digital and intelligent monitoring method for closed-loop resource utilization of pig farm manure.

[0015] The technical solutions provided by the embodiments disclosed in this application have the following beneficial effects: The digital monitoring method and system for closed-loop resource utilization of pig farm manure provided in this application firstly maps a virtual monitoring domain corresponding to each digital sensing terminal in a digital virtual model of closed-loop resource utilization of manure, based on the spatial layout of pig farm manure treatment units and the monitoring range of deployed digital sensing terminals; secondly, spatial analysis is performed on each virtual monitoring domain in the digital virtual model to obtain first monitoring coverage information; based on the first monitoring coverage information, topological association analysis is performed on manure treatment units in the digital virtual model that are not covered by the virtual monitoring domains to obtain multiple monitoring coverage information. The first monitoring coverage information is coupled with the corresponding hidden processing unit information in the process flow direction to form a monitoring-hidden association combination. Then, a corresponding simulation control mechanism is configured for each monitoring-hidden association combination. Finally, the virtual processing units corresponding to different treatment links of pig farm manure in the digital virtual model are identified, and the operating status of the virtual processing units in the closed-loop resource utilization process of manure is collaboratively simulated based on the virtual monitoring domain and the simulation control mechanism to generate regulatory data for optimizing resource recovery efficiency.

[0016] Therefore, this application can precisely optimize the resource recovery efficiency in the closed-loop resource utilization of manure under the influence of blind spots in manure treatment monitoring. First, based on the spatial layout of pig farm manure treatment units and the mapping of the monitoring range of digital sensing terminals to a virtual monitoring domain, a precise association between physical sensing terminals and digital virtual models can be achieved, laying the data mapping foundation for subsequent virtual-level monitoring and simulation. Second, spatial analysis of the virtual monitoring domain yields the first monitoring coverage information, and topological correlation analysis yields the hidden processing unit information. This clarifies the coverage boundaries of each virtual monitoring domain and the corresponding processing units, while accurately identifying unmonitored hidden units that are coupled with the covered units in terms of process function. This effectively compensates for the monitoring blind spots in the entire manure treatment process and avoids misjudgments of process operation status caused by some manure treatment units not being included in the monitoring. Then, the first monitoring coverage information and the hidden processing unit information are coupled in a process-wise manner. This invention combines a monitoring-hidden correlation system with a simulated control mechanism to construct a linkage control system based on process coupling, solving the fragmentation problem of single-unit monitoring and control. This improves the targeting and synergy of control strategies for the resource utilization of manure treatment, avoiding the problem that traditional monitoring methods, relying solely on direct monitoring data, cannot perform state perception and impact assessment on hidden treatment units without directly installed sensors. Finally, by identifying virtual treatment units corresponding to different treatment stages and collaboratively simulating and generating regulatory data based on the virtual monitoring domain and simulated control mechanism, the operating status simulation of the entire virtual unit process of pig farm manure treatment can be achieved. Through forward extrapolation, potential process deviations can be identified in advance, and regulatory data for optimizing resource recovery efficiency can be output. In summary, the technical solution provided in this application can accurately optimize resource recovery efficiency in the closed-loop resource utilization of manure under the influence of blind spots in manure treatment monitoring. Attached Figure Description

[0017] Figure 1 This is an exemplary flowchart of a digital monitoring method for closed-loop resource utilization of pig farm manure according to some embodiments of this application; Figure 2 This is an exemplary flowchart illustrating the determination of first monitoring coverage information according to some embodiments of this application; Figure 3 This is a schematic diagram of the structure of a digital monitoring system for closed-loop resource utilization of pig farm manure according to some embodiments of this application; Figure 4 This is a schematic diagram of the structure of a computer device for implementing a digital monitoring method for closed-loop resource utilization of pig farm manure, according to some embodiments of this application. Detailed Implementation

[0018] To better understand the technical solution of this application, the technical solution of this application will be described in detail below with reference to the accompanying drawings and specific embodiments.

[0019] refer to Figure 1 The figure is an exemplary flowchart of a digital monitoring method for closed-loop resource utilization of pig farm manure according to some embodiments of this application. The digital monitoring method for closed-loop resource utilization of pig farm manure mainly includes the following steps: In step 101, based on the spatial layout of the pig farm manure treatment unit and the monitoring range of the deployed intelligent sensing terminals, the virtual monitoring domain corresponding to each intelligent sensing terminal is mapped in the intelligent virtual model of closed-loop resource utilization of manure.

[0020] In some embodiments, based on the spatial layout of the pig farm manure treatment unit and the monitoring range of the deployed intelligent sensing terminals, mapping the virtual monitoring domain corresponding to each intelligent sensing terminal in the intelligent virtual model of closed-loop resource utilization of manure is achieved through the following steps: Acquire spatial layout data of pig farm manure treatment units and the deployment location and monitoring range of each intelligent sensor terminal; The spatial coordinate system of the digital and intelligent virtual model for closed-loop resource utilization of feces and sewage is constructed based on the spatial layout data; The monitoring range of the digital intelligent sensing terminal is parameterized in the spatial coordinate system to obtain the spatial parameter set of the monitoring range; Based on the deployment location of the digital intelligent sensing terminals, the virtual coordinates of each digital intelligent sensing terminal are located in the spatial coordinate system; Based on the virtual coordinates of each intelligent sensor terminal and the corresponding spatial parameter set of the monitoring range, a virtual monitoring domain corresponding to each intelligent sensor terminal is generated in the intelligent virtual model of closed-loop resource utilization of feces and sewage.

[0021] In specific implementation, firstly, the pre-set CAD engineering drawings of the pig farm manure treatment unit are analyzed to obtain spatial layout data containing the three-dimensional coordinates, structural dimensions, and relative positional relationships of each manure treatment unit. Simultaneously, the deployment location and monitoring range during installation are extracted from the technical specifications of the intelligent sensing terminal. The monitoring range includes the monitoring angle and monitoring distance. The spatial layout data refers to the data set characterizing the spatial distribution of the treatment units. The deployment location and monitoring range parameters define the location and range of the intelligent sensing terminal's monitoring capabilities. The manure treatment unit is an independent functional module with specific treatment functions within the closed-loop resource utilization system of pig farm manure. Secondly, based on the acquired spatial layout data, a [further details are needed for accurate translation]. The method for constructing a Cartesian three-dimensional rectangular coordinate system uses the center point of the feed inlet at the beginning of the manure treatment process as the origin. It sets the X-axis along the horizontal length of the manure treatment unit, the Y-axis along the horizontal width, and the Z-axis along the vertical height. All spatial position data of the manure treatment units are uniformly mapped to this coordinate system, forming the spatial coordinate system of a digital virtual model for the closed-loop resource utilization of manure. This spatial coordinate system refers to a three-dimensional coordinate system with a unified benchmark, used to standardize the spatial position of all elements in the digital virtual model. The digital virtual model is a physical entity based on the closed-loop resource utilization system of pig farm manure, and includes, but is not limited to, each manure treatment unit, digital sensing terminal, and other components. The material conveying pipeline is specifically a three-dimensional visualization simulation model constructed using existing digital replication technology. Furthermore, for the monitoring range of each intelligent sensing terminal, parameterization is performed according to the measurement standards of the aforementioned spatial coordinate system. These measurement standards refer to a unified quantitative specification pre-established to ensure the mapping between spatial data and the physical world in the intelligent virtual model for closed-loop resource utilization of manure and wastewater. For example, the monitoring distance parameter within the monitoring range is converted into a length threshold in the spatial coordinate system, and the monitoring angle parameter is converted into the range of azimuth and elevation angles, thus forming a spatial parameter set for the monitoring range. This spatial parameter set represents the transformation of the physical monitoring range into a calculable boundary of the virtual space. The process involves: first, assembling the data; then, based on the deployment location of the intelligent sensing terminals, converting their physical coordinates according to the definition of the origin and axis of the spatial coordinate system to obtain the three-dimensional coordinate values ​​of each intelligent sensing terminal in the spatial coordinate system, i.e., obtaining the virtual coordinates of each intelligent sensing terminal. The virtual coordinates are the identifiers of the spatial positions of the intelligent sensing terminals in the intelligent virtual model; finally, using the virtual coordinates of each intelligent sensing terminal as the center, substituting the corresponding monitoring range spatial parameter set into a preset spatial geometric equation (such as a spherical spatial equation or a conical spatial equation, which is not limited here), drawing the corresponding spatial region in the intelligent virtual model, and using this spatial region as the virtual monitoring domain corresponding to the intelligent sensing terminal.

[0022] It should be noted that, in this application, the virtual monitoring domain refers to the mapping range of the physical terminal monitoring range in the digital virtual model, which is used to realize the spatial association between the physical monitoring range and the digital virtual model. The virtual monitoring domain can serve as a replicating carrier of the physical monitoring capabilities of the digital sensing terminal in the digital virtual model for closed-loop resource utilization of manure and sewage, thereby realizing the spatial association and binding of monitoring data with virtual processing units.

[0023] In step 102, spatial analysis is performed on each virtual monitoring domain in the digital intelligent virtual model to obtain first monitoring coverage information. Based on the first monitoring coverage information, topological association analysis is performed on the sewage treatment units in the digital intelligent virtual model that are not covered by the virtual monitoring domains to obtain information on multiple hidden treatment units that are functionally coupled with the monitoring coverage treatment units in the process flow direction.

[0024] In some embodiments, reference Figure 2 As shown in the figure, this is an exemplary flowchart of determining the first monitoring coverage information according to some embodiments of this application. In this embodiment, spatial parsing of each virtual monitoring domain in the digital virtual model to obtain the first monitoring coverage information can be achieved by the following steps: In step 1021, the spatial boundary and topological attribute data of each virtual monitoring domain in the digital virtual model are extracted; In step 1022, a spatial topology relationship network for each virtual monitoring domain is constructed based on the extracted spatial boundary and topology attribute data. In step 1023, based on the spatial topology network, the monitoring coverage processing unit corresponding to each virtual monitoring domain is identified, and then the first monitoring coverage information is generated.

[0025] In specific implementation, firstly, using the attribute extraction function built into 3D modeling software (such as AutoCAD) for digital virtual models, spatial entities of virtual monitoring domains are selected, and their spatial boundaries, composed of spatial geometric boundary coordinates, are exported. Topological attribute data representing the spatial relationships between this virtual monitoring domain and other virtual elements (e.g., virtual processing units, other virtual monitoring domains) is also exported. These spatial relationships include inclusion, adjacency, and separation, thus obtaining the spatial boundaries and topological attribute data of each virtual monitoring domain. Then, using the adjacency matrix method, the extracted spatial boundaries and topological attribute data are used as input. Each virtual monitoring domain is treated as a topological node. Based on the spatial relationships represented in the topological attribute data, it is determined whether there are inclusion and adjacency relationships between topological nodes. If so, edges are established between the corresponding topological nodes, thus forming a spatial topological relationship network where topological nodes represent virtual monitoring domains and edges represent spatial relationships. This spatial topological relationship network refers to a visualized... A graphical model presents the spatial association status of virtual monitoring domains. Finally, based on the spatial topology network, the node connection relationships corresponding to each virtual monitoring domain are traversed, and virtual processing unit nodes that have a topological relationship with the virtual monitoring domain nodes are selected. The identification information and the percentage of the covered spatial range of these virtual processing unit nodes are statistically analyzed, thereby generating the first monitoring coverage information. For example, if the spatial boundary data of a certain virtual monitoring domain shows that it is a spherical area with a radius of 5m, and the topological attribute data indicates that it has a spatial overlap with the anaerobic fermentation virtual processing unit and the overlap range accounts for 80% of the volume of the processing unit, when constructing the topology network using the adjacency matrix method, an edge connection with an inclusion relationship will be established between the virtual monitoring domain node and the anaerobic fermentation unit node. After traversing the network, it can be determined that the virtual monitoring domain covers the anaerobic fermentation virtual processing unit, generating the first monitoring coverage information containing "monitoring domain number 001 - covered processing unit: anaerobic fermentation unit - coverage ratio 80%".

[0026] It should be noted that, in this application, the first monitoring coverage information refers to the data set representing the monitoring objects of each virtual monitoring domain. Specifically, the first monitoring coverage information refers to the information set containing multiple monitoring coverage processing units. The determination of the first monitoring coverage information is to establish a precise correspondence between virtual monitoring domains and virtual processing units in the digital and intelligent virtual model, providing basic data support for the digital and intelligent supervision of the closed-loop resource utilization of sewage. It can clearly identify which virtual processing units and the degree of coverage are the monitoring objects of each virtual monitoring domain, ensuring that the monitoring data of the corresponding processing units can be accurately called during subsequent collaborative simulations, avoiding data confusion.

[0027] In some embodiments, the following steps are used to obtain information on multiple hidden processing units that are functionally coupled with the monitored and covered processing units in the process flow direction by performing topological association analysis on the sewage treatment units not covered by the virtual monitoring domain in the digital virtual model based on the first monitoring coverage information: Extract the monitoring coverage processing unit identifier from the first monitoring coverage information, and based on the monitoring coverage processing unit identifier, filter out the sewage treatment units that are not covered by the virtual monitoring domain in the digital virtual model to obtain the dataset of uncovered processing units. Obtain the process flow data of the manure treatment unit in the digital virtual model, and construct the process flow topology model of manure treatment by combining the monitoring coverage treatment unit identifier; Based on the uncovered processing unit dataset and the process flow topology model, the connection relationship between the uncovered processing unit and the monitored covered processing unit in the process flow is identified, and the process correlation matrix is ​​obtained. Based on the process association matrix, uncovered processing units that are functionally coupled with the monitoring and coverage processing unit identifier in the process flow direction are selected to obtain hidden processing unit information.

[0028] In specific implementation, firstly, the monitoring coverage processing unit identifier, such as the unit number, is extracted from the first monitoring coverage information. Using this identifier as a filtering condition, a reverse match is performed in the processing unit database of the digital virtual model to remove monitoring coverage processing units already covered by the virtual monitoring domain. The uncovered manure treatment units in the digital virtual model are retained as uncovered processing units, resulting in an uncovered processing unit dataset. The uncovered processing unit dataset refers to a collection of multiple uncovered processing units. Secondly, the preset process flow diagram in the digital virtual model is parsed to obtain process flow data representing the material input-output relationship and processing sequence between each manure treatment unit. Using the extracted monitoring coverage processing unit identifier as a reference node, each manure treatment unit as a directed graph node, and the material transmission direction represented in the process flow data as directed edges, a process flow topology model presenting the manure treatment process is constructed. The process flow topology model refers to a graphical model that visually represents the process associations of manure treatment units. Then, based on the obtained uncovered processing unit dataset and process flow topology model, by traversing the nodes and directed edges in the process flow topology model, the connection relationship between each uncovered processing unit in the uncovered processing unit dataset and the monitoring covered processing unit in the directed graph is compared one by one. The connection relationship includes direct process connection or no connection. The adjacency matrix construction algorithm is used to quantify this connection relationship into matrix elements (i.e., 1 indicates the existence of direct process connection, 0 indicates no connection), forming a process association matrix with rows representing uncovered processing units and columns representing monitoring covered processing units. The process association matrix is ​​a matrix that characterizes the process association strength between uncovered processing units and monitoring covered processing units. The elements in the process association matrix characterize the process association strength. Finally, based on the process association matrix, uncovered processing units with a matrix element of 1 are selected. These processing units have functional collaboration with the monitoring covered processing units in the process flow and belong to the process function coupling relationship. Then, the hidden processing unit information is obtained by combining the selected uncovered processing units.

[0029] It should be noted that the hidden processing unit information in this application refers to the manure treatment units that have a direct process function coupling relationship with the already monitored and covered manure treatment units in the digital and intelligent virtual model of closed-loop resource utilization of manure. The purpose of identifying the hidden processing unit information is to fill the monitoring blind spots in the digital and intelligent supervision of closed-loop resource utilization of manure. By accurately identifying the uncovered units that have process function coupling with the monitored units, a full-process, blind-spot-free supervision data link can be constructed. This can provide a clear target for supplementing the deployment of the virtual monitoring domain, realize the complete coverage of the entire manure treatment process by the virtual monitoring domain, and avoid supervision gaps caused by the lack of monitoring of key units.

[0030] In step 103, the first monitoring coverage information is coupled with the corresponding hidden processing unit information to form a monitoring-hidden association combination, and a corresponding simulation control mechanism is configured for each monitoring-hidden association combination.

[0031] In some embodiments, the process coupling of the first monitoring coverage information with the corresponding hidden processing unit information to form a monitoring-hidden association combination is achieved through the following steps: Extract the process parameters of the monitoring coverage processing unit in the first monitoring coverage information and the process parameters of the hidden processing unit in the hidden processing unit information to obtain a set of process parameters; Based on the set of process parameters, a correlation benchmark for the coupling of manure treatment processes is constructed; Based on the correlation benchmark of the fecal sewage treatment process coupling, the process flow correlation of the first monitoring coverage information and the hidden treatment unit information is matched to obtain the correlation matching result; Based on the association matching results, the monitoring coverage processing unit and the hidden processing unit that have process coupling relationship are clustered and integrated to form a monitoring-hidden association combination.

[0032] In specific implementation, firstly, process parameters of the monitoring and coverage processing unit are extracted from the first monitoring coverage information. These process parameters include, but are not limited to, processing temperature, material residence time, and reaction pH value. Simultaneously, corresponding process parameters are extracted from the hidden processing unit information, including related parameters that are functionally coupled with the monitoring and coverage processing unit, such as the discharge concentration of the preceding unit and the feed requirements of the subsequent unit. These two types of process parameters are then categorized and summarized according to process stages to form a process parameter set. This process parameter set integrates the process parameters of the monitoring and coverage processing unit and the hidden processing unit, and is used to comprehensively characterize the process operation characteristics and parameter correlation potential of both types of units. Secondly, based on the obtained set of process parameters, and combined with the recognized process coupling standards in the manure treatment industry (e.g., the pH range of the anaerobic fermentation unit and the biogas slurry filtration unit, and the solid moisture content matching requirements of the solid-liquid separation unit and the organic fertilizer processing unit), a threshold setting method is used to determine the effective value range of each associated parameter. For example, the overlapping range of the anaerobic fermentation effluent pH value of 6.5-7.5 and the biogas slurry filtration influent pH value of 6.0-8.0 is defined. Simultaneously, the logical relationship of process parameter transmission in the process flow is clarified, such as the effluent flow rate of the preceding unit needing to match the influent flow rate of the following unit. This leads to the construction of the associated benchmark for manure treatment process coupling. The correlation benchmark for process coupling refers to a quantitative standard based on industry process standards and parameter adaptation rules, consisting of reasonable value ranges for process parameters and logical relationships of process parameter transmission. This standard is used to determine whether two types of treatment units have the feasibility of coupling and linkage at the process level. Then, based on the constructed correlation benchmark for manure treatment process coupling, the process parameters of the monitored treatment units in the first monitoring coverage information are compared one by one with the process parameters of the hidden treatment units to verify whether the parameters fall within the value range set by the correlation benchmark. Simultaneously, the sequential connection relationship between the two in the treatment process is confirmed by combining the process flow topology model, such as a direct predecessor-successor or same-branch collaborative relationship. If the parameters are compatible and the process flow is related, the matching is considered successful. All successful matching results are summarized to form the associated matching result. The associated matching result refers to the set of judgment results formed by summarizing the results after parameter comparison and process flow verification. It is used to clarify the process coupling matching status of the monitoring coverage processing unit and the hidden processing unit. Finally, based on the associated matching result, a hierarchical clustering algorithm is used to group the monitoring coverage processing unit and the hidden processing unit that are successfully matched and whose process association strength reaches the preset threshold into the same cluster. At the same time, the process role and parameter transmission path of each processing unit in the cluster are marked to form a monitoring-hidden associated combination.

[0033] It should be noted that the monitoring-hidden association combination in this application refers to a functionally associated cluster composed of monitoring coverage processing units and hidden processing units that have process coupling relationships. Because the manure treatment process has strong continuity and synergy, each processing unit forms an inseparable process link through material transfer and parameter feedback (for example, the effluent moisture content of the solid-liquid separation unit directly determines the reaction efficiency of the anaerobic fermentation unit, and a failure of the hidden biogas slurry filtration unit will lead to abnormal processing load of the subsequent coverage unit). If only the monitoring coverage unit or the hidden processing unit is focused on, the regulatory data will form "islands" and will not be able to reflect the overall operating status of the process flow. Moreover, during collaborative simulation, due to the lack of associated data of the hidden units, the simulation results are prone to being out of sync with the actual process. Therefore, by indirectly incorporating the hidden processing units into the regulatory system through association combination, the regulatory gap in the process link caused by monitoring blind spots can be avoided, and the digital virtual model can be used to fully represent the entire manure treatment process.

[0034] In some embodiments, configuring a corresponding simulation control mechanism for each monitoring-hiding association combination is achieved through the following steps: Extract the process coupling relationship features and operating threshold parameters of each monitoring-hidden association combination to obtain the cluster feature parameter set; Based on the cluster feature parameter set, determine the control objective function corresponding to each monitoring-hidden association combination; Based on the aforementioned control objective function, design simulation control logic rules that adapt to each monitoring-hidden association combination; Based on the simulation control logic rules, the control threshold parameters and response trigger conditions corresponding to each monitoring-hidden association combination are configured to form a simulation control mechanism.

[0035] In specific implementation, firstly, from each monitoring-hidden association combination, process coupling relationship features characterizing the process coupling mode between the monitoring coverage processing unit and the hidden processing unit are extracted. These process coupling relationship features include parameter transmission paths and process roles. Simultaneously, the upper and lower limits of the process parameters (i.e., operating threshold parameters) for normal operation of each processing unit within the monitoring-hidden association combination are extracted. These two types of data are then categorized and integrated according to the association combination identifier to obtain a cluster feature parameter set. This cluster feature parameter set refers to the data set that integrates the process coupling relationship features of the monitoring-hidden association combination and the operating threshold parameters of each processing unit. Secondly, the operating threshold parameters in the cluster feature parameter set are extracted as... As constraints, control parameters (e.g., temperature or feed rate) of the monitoring-hidden correlation combination are set as decision variables. Combined with the demand conditions for closed-loop resource utilization of manure (i.e., maximizing resource recovery efficiency), the demand conditions are transformed into target indicators. Using existing nonlinear programming modeling methods, the target indicators are used as dependent variables and the control parameters as independent variables. The extracted operational threshold parameters are substituted into the constraint expression, thus forming a control objective function containing the objective expression, decision variables, and constraints. This control objective function refers to a quantitative mathematical model constructed based on the correlation combination operational constraints and processing needs, used to clarify the specific objectives to be achieved by the control behavior. Then, according to... Based on the stated control objective function, a process-oriented rule design method is adopted. Combining the characteristics of process coupling relationships, the control logic when parameters deviate from thresholds is clarified. For example, when the pH value of the monitoring unit is below the lower limit, the acid-base adjustment device of the hidden pretreatment unit is triggered; or when the material transmission flow exceeds the threshold, the feed rate of the preceding unit is adjusted. This forms a simulated control logic rule that includes trigger scenarios and control objects. The simulated control logic rule refers to a set of rules for triggering control behavior and execution processes based on the control objective function and process coupling characteristics. Finally, combining the parameter deviations determined in the simulated control logic rule, the cluster feature parameters corresponding to each monitoring-hidden association combination are analyzed. The upper and lower limit thresholds of process parameters for each sewage treatment unit are extracted from the dataset and decomposed into graded control thresholds. This yields the control threshold parameters corresponding to the monitoring-hidden correlation combination, which are divided into early warning thresholds, routine control thresholds, and emergency control thresholds according to the process risk level. For example, the early warning threshold for pH is set to 6.3-7.7, the routine control threshold to 6.0-8.0, and the emergency control threshold to 5.5-8.5. Further details are omitted here. Trigger conditions are also set for each monitoring-hidden correlation combination, such as if the process parameter exceeds the early warning threshold for 3 consecutive minutes. By combining the graded control thresholds and trigger conditions corresponding to each monitoring-hidden correlation combination, a simulated control mechanism is obtained.

[0036] It should be noted that the simulation control mechanism in this application refers to the system of coordinated control of manure treatment units within the monitoring-hidden association combination. The simulation control mechanism integrates hierarchical control thresholds and quantifies response trigger conditions to achieve the linkage response between the monitoring coverage unit and the hidden treatment unit within the monitoring-hidden association combination. It can simulate the parameter control effect under different working conditions in the digital virtual model based on preset logic, and automatically execute hierarchical control actions according to trigger conditions when the physical system experiences parameter deviations from thresholds or process coordination anomalies. This avoids the imbalance of the entire process caused by the anomaly of a single unit, and ensures the process coupling matching and operational stability of the entire manure treatment process.

[0037] In step 104, virtual processing units corresponding to different stages of pig farm manure treatment in the digital virtual model are identified, and the operating status of the virtual processing units in the closed-loop resource utilization process of manure is simulated collaboratively based on the virtual monitoring domain and the simulation control mechanism to generate regulatory data for optimizing resource recycling efficiency.

[0038] In some embodiments, identifying the virtual processing units corresponding to different stages of pig farm manure treatment in the digital virtual model is achieved through the following steps: The monitoring scope for different treatment stages of pig farm manure was extracted; For each processing stage, the manure treatment unit within the monitoring range corresponding to the processing stage is extracted from the digital virtual model as a virtual processing unit, thereby obtaining the virtual processing units for different processing stages of pig farm manure.

[0039] In practice, firstly, the monitoring range of different treatment stages of pig farm manure is extracted through the industry standard process flow for pig farm manure treatment, which will not be elaborated here; then, for each treatment stage, the manure treatment unit corresponding to the monitoring range of the treatment stage is extracted from the digital virtual model as a virtual treatment unit, thereby obtaining virtual treatment units for different treatment stages of pig farm manure. The virtual treatment unit refers to the manure treatment unit belonging to each treatment stage of pig farm manure, which is used to realize the accurate representation of the entire process of manure treatment by the digital virtual model.

[0040] In some embodiments, the following steps are used to collaboratively simulate the operating status of the virtual processing unit in the closed-loop resource utilization process of fecal waste based on the virtual monitoring domain and the simulation control mechanism, and to generate regulatory data for optimizing resource recovery efficiency: Acquire real-time sensor data streams uploaded by each intelligent sensor terminal to the virtual monitoring domain; The real-time sensing data stream is injected into the corresponding virtual processing unit in the digital virtual model, and the virtual processing unit is driven to generate the current running state set. The virtual simulation control mechanism is used to perform forward state extrapolation on the current operating state set to generate a process state sequence within a future preset time period. By comparing and analyzing the process state sequence with preset process safety thresholds, potential process deviation vectors are identified, thereby obtaining regulatory data for optimizing resource recycling efficiency.

[0041] In specific implementation, firstly, real-time monitoring data of process parameters within the corresponding virtual monitoring domain, uploaded at a preset frequency by each intelligent sensing terminal through a data acquisition interface, is received. This forms a real-time sensing data stream containing parameter acquisition timestamps, parameter values, and the identifier of the virtual monitoring domain. This real-time sensing data stream is a set of real-time monitoring data of process parameters within the corresponding virtual monitoring domain collected and uploaded by the intelligent sensing terminal, used to characterize the real-time operating status of the virtual monitoring domain coverage unit. Secondly, the real-time sensing data stream is injected into the parameter input module of the corresponding virtual processing unit in the intelligent virtual model. The state update engine of the intelligent virtual model synchronously updates the operating parameters of each virtual processing unit, driving the virtual processing unit to generate a current operating status set containing the current operating parameter values ​​and process operation stage identifiers of each virtual processing unit. This current operating status set refers to the set generated by the virtual processing unit driven by the real-time sensing data stream, containing the current operating parameters and operating status of each unit. The process involves several steps. First, a set of state data for each stage is generated. Then, using the difference equation method in the forward state deduction algorithm, the current operating state set is used as the initial input parameter. This is substituted into the control logic rules and threshold parameters in the configured simulation control mechanism. The parameter change trends of each virtual processing unit within a preset time period are deduced according to a preset time step. Simultaneously, the collaborative response effect of the monitoring-hidden association combination is simulated by combining process coupling relationship characteristics, generating a process state sequence arranged in time series. This process state sequence refers to the time-series data set of the operating states of virtual processing units within a preset time period obtained through forward deduction. Finally, the parameter values ​​for each time period in the process state sequence are compared and analyzed against preset process safety thresholds. By calculating the magnitude and direction of parameter deviations from the thresholds, process deviation vectors characterizing abnormal process trends are identified. These vectors are then combined with the virtual processing unit identifiers and deviation time periods corresponding to the process deviation vectors to obtain regulatory data for optimizing resource recovery efficiency.

[0042] It should be noted that the regulatory data used in this application to optimize resource recycling efficiency refers to a dataset that integrates deviation information of the sewage treatment process. The regulatory data can not only present the current operating status of the virtual treatment unit and the process evolution trend in the future preset period in real time, clearly reflect the key indicators of resource recycling and the process synergy effect of the units within the monitoring-hidden correlation combination, but also accurately locate the potential process imbalance risk points in the future through the process deviation vector, realize early warning of abnormal trends, and avoid resource waste or excessive pollutant emissions caused by process runaway.

[0043] Furthermore, in another aspect of this application, in some embodiments, this application provides a digital monitoring system for the closed-loop resource utilization of pig farm manure, referencing... Figure 3 The figure is a schematic diagram of the structure of a digital monitoring system for closed-loop resource utilization of pig farm manure according to some embodiments of this application. The digital monitoring system for closed-loop resource utilization of pig farm manure includes: a mapping module 201, a processing module 202, and an execution module 203, which are described below: The mapping module 201 in this application is mainly used to map the virtual monitoring domain corresponding to each digital sensing terminal in the digital virtual model of closed-loop resource utilization of manure based on the spatial layout and deployment of the pig farm manure treatment unit. Processing module 202, in this application, is mainly used to perform spatial analysis on each virtual monitoring domain in the digital intelligent virtual model to obtain first monitoring coverage information, and to perform topological association analysis on the sewage treatment units in the digital intelligent virtual model that are not covered by the virtual monitoring domains based on the first monitoring coverage information to obtain information on multiple hidden processing units that are functionally coupled with the monitoring coverage processing units in the process flow direction. The processing module 202 is further configured to perform process coupling between the first monitoring coverage information and the corresponding hidden processing unit information to form a monitoring-hidden association combination, and configure a corresponding simulation control mechanism for each monitoring-hidden association combination. The execution module 203 in this application is mainly used to identify the virtual processing units corresponding to different treatment stages of pig farm manure in the digital virtual model, and to perform collaborative simulation of the operating status of the virtual processing units in the closed-loop resource utilization process of manure based on the virtual monitoring domain and the simulation control mechanism, so as to generate regulatory data for optimizing resource recycling efficiency.

[0044] In addition, this application also provides a computer device, which includes a memory and a processor. The memory stores code, and the processor is configured to acquire the code and execute the above-described digital monitoring method for closed-loop resource utilization of pig farm manure.

[0045] In some embodiments, reference Figure 4 The figure is a schematic diagram of the structure of a computer device for implementing a digital monitoring method for closed-loop resource utilization of pig farm manure according to some embodiments of this application. The digital monitoring method for closed-loop resource utilization of pig farm manure in the above embodiments can be achieved through… Figure 4 The computer device shown is used to implement this, and the computer device includes at least one processor 301, a communication bus 302, a memory 303, and at least one communication interface 304.

[0046] The processor 301 can be a general-purpose central processing unit (CPU), an application-specific integrated circuit (ASIC), or one or more digital monitoring methods for controlling the execution of the closed-loop resource utilization of pig farm manure in this application.

[0047] The communication bus 302 can be used to transmit information between the aforementioned components.

[0048] The memory 303 may be a read-only memory (ROM) or other type of static storage device capable of storing static information and instructions, random access memory (RAM) or other type of dynamic storage device capable of storing information and instructions, or electrically erasable programmable read-only memory (EEPROM), compact disc read-only memory (CDROM) or other optical disc storage, optical disc storage (including compressed optical discs, laser discs, optical discs, digital universal optical discs, Blu-ray discs, etc.), magnetic disks or other magnetic storage devices, or any other medium capable of carrying or storing desired program code in the form of instructions or data structures and accessible by a computer, but not limited thereto. The memory 303 may exist independently and be connected to the processor 301 via the communication bus 302. The memory 303 may also be integrated with the processor 301.

[0049] The memory 303 stores program code for executing the scheme of this application, and its execution is controlled by the processor 301. The processor 301 executes the program code stored in the memory 303. The program code may include one or more software modules. In the above embodiments, the determination of the digital monitoring method for closed-loop resource utilization of pig farm manure can be implemented by the processor 301 and one or more software modules in the program code in the memory 303.

[0050] Communication interface 304 uses any transceiver-like device for communicating with other devices or communication networks, such as Ethernet, radio access network (RAN), wireless local area networks (WLAN), etc.

[0051] In a specific implementation, as one example, a computer device may include multiple processors, each of which may be a single-core (single CPU) processor or a multi-core (multi CPU) processor. Here, a processor may refer to one or more devices, circuits, and / or processing cores used to process data (e.g., computer program instructions).

[0052] The aforementioned computer device can be a general-purpose computer device or a special-purpose computer device. In specific implementations, the computer device can be a desktop computer, a portable computer, a network server, a handheld digital assistant (PDA), a mobile phone, a tablet computer, a wireless terminal device, a communication device, or an embedded device. This application does not limit the type of computer device.

[0053] In addition, this application also provides a computer-readable storage medium storing a computer program, which, when executed by a processor, implements the above-mentioned digital and intelligent monitoring method for closed-loop resource utilization of pig farm manure.

[0054] Although preferred embodiments of this application have been described, those skilled in the art, upon learning the basic inventive concept, can make other changes and modifications to these embodiments. Therefore, the appended claims are intended to be interpreted as including the preferred embodiments as well as all changes and modifications falling within the scope of this application.

[0055] Obviously, those skilled in the art can make various modifications and variations to this application without departing from the spirit and scope of this application. Therefore, if such modifications and variations fall within the scope of the claims of this application and their equivalents, this application also intends to include such modifications and variations.

Claims

1. A digital monitoring method for closed-loop resource utilization of pig farm manure, characterized in that, Includes the following steps: Based on the spatial layout and deployment of the pig farm manure treatment unit, the monitoring range of the digital intelligent sensor terminal is mapped in the digital intelligent virtual model of closed-loop resource utilization of manure to the virtual monitoring domain corresponding to each digital intelligent sensor terminal. Spatial analysis is performed on each virtual monitoring domain in the digital intelligent virtual model to obtain first monitoring coverage information. Based on the first monitoring coverage information, topological association analysis is performed on the sewage treatment units in the digital intelligent virtual model that are not covered by the virtual monitoring domains to obtain information on multiple hidden treatment units that are functionally coupled with the monitoring coverage treatment units in the process flow direction. The first monitoring coverage information is coupled with the corresponding hidden processing unit information through process technology to form a monitoring-hidden association combination, and a corresponding simulation control mechanism is configured for each monitoring-hidden association combination. The system identifies virtual processing units corresponding to different stages of pig farm manure treatment in the digital virtual model, and performs collaborative simulation of the operating status of the virtual processing units in the closed-loop resource utilization process of manure based on the virtual monitoring domain and the simulation control mechanism, generating regulatory data for optimizing resource recycling efficiency.

2. The method as described in claim 1, characterized in that, Based on the spatial layout and deployment of pig farm manure treatment units, the monitoring range of digital sensing terminals is mapped in the digital virtual model of closed-loop resource utilization of manure, specifically including the virtual monitoring domain corresponding to each digital sensing terminal, which includes: Acquire spatial layout data of pig farm manure treatment units and the deployment location and monitoring range of each intelligent sensor terminal; The spatial coordinate system of the digital and intelligent virtual model for closed-loop resource utilization of feces and sewage is constructed based on the spatial layout data; The monitoring range of the digital intelligent sensing terminal is parameterized in the spatial coordinate system to obtain the spatial parameter set of the monitoring range; Based on the deployment location of the digital intelligent sensing terminals, the virtual coordinates of each digital intelligent sensing terminal are located in the spatial coordinate system; Based on the virtual coordinates of each intelligent sensor terminal and the corresponding spatial parameter set of the monitoring range, a virtual monitoring domain corresponding to each intelligent sensor terminal is generated in the intelligent virtual model of closed-loop resource utilization of feces and sewage.

3. The method as described in claim 1, characterized in that, Spatial analysis is performed on each virtual monitoring domain in the digitalized virtual model to obtain the first monitoring coverage information, which specifically includes: Extract the spatial boundary and topological attribute data of each virtual monitoring domain in the digital intelligent virtual model; Based on the extracted spatial boundary and topological attribute data, a spatial topological relationship network for each virtual monitoring domain is constructed. Based on the spatial topology network, the monitoring coverage processing unit corresponding to each virtual monitoring domain is identified, and then the first monitoring coverage information is generated.

4. The method as described in claim 1, characterized in that, Based on the first monitoring coverage information, a topological association analysis is performed on the sewage treatment units in the digital virtual model that are not covered by the virtual monitoring domain, resulting in information on multiple hidden treatment units that are functionally coupled with the monitored coverage treatment units in the process flow direction. Specifically, this includes: Extract the monitoring coverage processing unit identifier from the first monitoring coverage information, and based on the monitoring coverage processing unit identifier, filter out the sewage treatment units that are not covered by the virtual monitoring domain in the digital virtual model to obtain the dataset of uncovered processing units. Obtain the process flow data of the manure treatment unit in the digital virtual model, and construct the process flow topology model of manure treatment by combining the monitoring coverage treatment unit identifier; Based on the uncovered processing unit dataset and the process flow topology model, the connection relationship between the uncovered processing unit and the monitored covered processing unit in the process flow is identified, and the process correlation matrix is ​​obtained. Based on the process association matrix, uncovered processing units that are functionally coupled with the monitoring and coverage processing unit identifier in the process flow direction are selected to obtain hidden processing unit information.

5. The method as described in claim 1, characterized in that, The process of coupling the first monitoring coverage information with the corresponding hidden processing unit information to form a monitoring-hidden association combination specifically includes: Extract the process parameters of the monitoring coverage processing unit in the first monitoring coverage information and the process parameters of the hidden processing unit in the hidden processing unit information to obtain a set of process parameters; Based on the set of process parameters, a correlation benchmark for the coupling of manure treatment processes is constructed; Based on the correlation benchmark of the fecal sewage treatment process coupling, the process flow correlation of the first monitoring coverage information and the hidden treatment unit information is matched to obtain the correlation matching result; Based on the association matching results, the monitoring coverage processing unit and the hidden processing unit that have process coupling relationship are clustered and integrated to form a monitoring-hidden association combination.

6. The method as described in claim 1, characterized in that, Identifying the virtual processing units in the digital virtual model corresponding to different stages of pig farm manure treatment specifically includes: The monitoring scope for different treatment stages of pig farm manure was extracted; For each processing stage, the manure treatment unit within the monitoring range corresponding to the processing stage is extracted from the digital virtual model as a virtual processing unit, thereby obtaining the virtual processing units for different processing stages of pig farm manure.

7. The method as described in claim 2, characterized in that, The spatial layout data of the pig farm manure treatment unit is obtained by using the pre-designed CAD engineering drawings of the pig farm manure treatment unit.

8. A digital monitoring system for closed-loop resource utilization of pig farm manure, characterized in that, The system includes: The mapping module is used to map the monitoring range of the digital intelligent sensor terminals based on the spatial layout and deployment of the pig farm manure treatment unit, and to map the virtual monitoring domain corresponding to each digital intelligent sensor terminal in the digital intelligent virtual model of closed-loop resource utilization of manure. The processing module is used to perform spatial analysis on each virtual monitoring domain in the digital intelligent virtual model to obtain first monitoring coverage information. Based on the first monitoring coverage information, the module performs topological association analysis on the sewage treatment units in the digital intelligent virtual model that are not covered by the virtual monitoring domains to obtain information on multiple hidden processing units that are functionally coupled with the monitoring coverage processing units in the process flow direction. The processing module is further configured to perform process coupling between the first monitoring coverage information and the corresponding hidden processing unit information to form a monitoring-hidden association combination, and configure a corresponding simulation control mechanism for each monitoring-hidden association combination. The execution module is used to identify virtual processing units in the digital virtual model that correspond to different treatment stages of pig farm manure, and to perform collaborative simulation of the operating status of the virtual processing units in the closed-loop resource utilization process of manure based on the virtual monitoring domain and the simulation control mechanism, thereby generating regulatory data for optimizing resource recycling efficiency.

9. A computer device, characterized in that, The computer device includes a memory and a processor, the memory storing code, and the processor being configured to acquire the code and execute the digital monitoring method for closed-loop resource utilization of pig farm manure as described in any one of claims 1 to 7.

10. A computer-readable storage medium storing a computer program, characterized in that, When the computer program is executed by the processor, it implements the digital and intelligent monitoring method for closed-loop resource utilization of pig farm manure as described in any one of claims 1 to 7.

Images