Pig farm sand table modeling and synchronizing method based on digital twinning

Abstract

The invention relates to the technical field of intelligent breeding, in particular to a pig farm sand table modeling and synchronizing method based on digital twinning, which comprises the following steps: constructing a basic model of a digital twinning sand table through a three-dimensional modeling technology according to dynamic topological relation data; in the moving process of the twin body, detecting path conflicts on the moving path of the twin body in real time, and after the conflicts are detected, through virtual elastic deformation modeling processing, adjusting the position and posture of the twin body to avoid the path conflicts; when the physical sand table generates an operation instruction and the state is changed, the related information sends a first synchronization instruction to the digital twin platform through the Internet of Things; and updating the state, namely the topological relation, of the corresponding twinborn body in the digital twinborn sand table according to the correction parameters. According to the method, the dynamic association strength between the devices is calculated by using the topological weight algorithm, the generated dynamic topological relation data accurately reflects the actual relation between the devices, and a solid data basis is provided for subsequent modeling and analysis.

Description

Technical Field

[0001] The present invention relates to the field of intelligent breeding technology, and in particular to a pig farm sandbox modeling and synchronization method based on digital twins. Background Art

[0002] In the context of the rapid development of animal husbandry today, pig farming, as an important part of the agricultural field, has been continuously increasing in scale and intensiveness. With the rapid development of information technology, digital twin technology, as an emerging technical means, has provided new ideas and methods for the intelligent upgrading of pig farm management. The traditional pig farm management model faces many challenges, such as the lag in monitoring and regulation of the breeding environment, the difficulty of disease prevention and control, and the inefficiency of breeding resource utilization, which seriously restricts the improvement of pig farm breeding efficiency and sustainable development. Summary of the invention

[0003] In view of the technical problems existing in the prior art, the present invention provides a pig farm sand table modeling and synchronization method based on digital twins.

[0004] The technical solution of the present invention to solve the above technical problems is as follows: a pig farm sandbox modeling and synchronization method based on digital twins, comprising the following steps: S101. Based on dynamic topological relationship data, construct the basic model of the digital twin sandbox through 3D modeling technology; S102, during the movement of the twins, the path conflict on the moving path is detected in real time. After the conflict is detected, the position and posture of the twins are adjusted through virtual elastic deformation modeling to avoid the path conflict; S103: When the physical sandbox generates an operation instruction and the state changes, the relevant information sends a first synchronization instruction to the digital twin platform through the Internet of Things; S104: Update the status and topological relationship of the corresponding twin in the digital twin sandbox according to the correction parameters.

[0005] In a preferred embodiment, in the physical pig farm sandbox, multimodal sensors are deployed in various physical devices in S101, a data acquisition system is built, an IoT gateway is used as the core device, the scattered sensors are connected to the gateway, the data acquisition system is started, and the equipment operation data, environmental parameters and physical connection status between the equipment are continuously collected. The dynamic association strength between the equipment is comprehensively considered through a preset topological weight algorithm, and the weight algorithm includes a device distance attenuation factor , Data interaction frequency and operational dependencies ,and + + =1, set the preset threshold of association strength , used to filter high-priority topological links, extract the distance data, data interaction frequency and operation dependency between devices from the data storage server, clean these data, remove outliers and duplicate data, and calculate the dynamic association strength between each pair of devices according to the topological weight algorithm for each pair of devices. Suppose the distance between device A and device B is , the data interaction frequency is , the operation dependency is o , then the strength of association S The specific calculation consensus is as follows:

[0006] in, and They represent the maximum values ​​of data interaction frequency and operation dependence, respectively, which are obtained by counting the data of all devices and comparing the calculated association strength of each pair of devices with the preset threshold. For comparison, when the correlation strength S> , the device pair is marked as a high-priority topological link, and the device numbers, association strength values, and related parameters of these links are recorded to generate a dynamic topological map. In the map, nodes represent devices, edges represent the connection relationships between devices, and different weights and color labels are assigned to edges according to the association strength.

[0007] In a preferred embodiment, in S102, according to the acquired dynamic topological relationship data, the preset adaptive topological mapping rules are followed, and the three-dimensional modeling technology is used to build a digital twin sandbox basic model that is mapped 1:1 with the physical sandbox. In the modeling process, a unique identification rule is defined for each physical device and the corresponding twin. Suppose the device type set is , each device type corresponds to a unique code, and the serial number set is , for physical devices , whose entity device type is , the serial number is , then the entity device number The calculation formula is:

[0008] in, Identify the jth specific device type in the device type set T. In the 3D modeling software, add an adaptive attribute to each device model to store its corresponding physical device number. Add an attribute to each twin in the digital twin sandbox to store its identification. Establish a dynamic two-way binding relationship between the physical device number and the twin identification to ensure that when the physical device number changes, the corresponding twin identification in the digital twin sandbox can also be automatically updated to ensure one-to-one correspondence between virtual and real devices. When the position of the physical device changes, use the binding relationship to trigger the autonomous path-finding algorithm of the twin in the digital twin sandbox. Call the autonomous path-finding algorithm to calculate the collision-free path of the twin from the current position to the new position. During the movement of the twin, use the collision detection algorithm to detect in real time whether there is a spatial overlap area with other twins and obstacles on its path. Use the space segmentation algorithm to detect conflicts. Divide the space of the digital twin sandbox into an octree structure, where each node represents a subspace. Suppose the twin Located at the octree node , twin Located at the octree node ,when and When the two twins are the same node and they have a common ancestor node, it means that there is a conflict between the two twins. When a conflict is detected, the spatial overlapping area on the twin movement path is modeled with virtual elastic deformation through the conflict resolution strategy. The twins in conflict can be regarded as elastic bodies, and the force F and deformation amount The proportional coefficient is the elastic coefficient k. The specific formula is as follows:

[0009] The negative sign indicates that the direction of the force is opposite to the direction of the deformation variable. In the digital twin space, the displacement vector of the twin is , then the force vector is:

[0010] in, Represents the force vector. By calculating the force vector and combining it with Newton's second law, we can get the acceleration vector , where m represents the mass of the twin. According to the kinematic formula, the velocity update formula and position update formula are calculated: The velocity update formula is the velocity vector = ,in, represents the acceleration vector of the twin, and the update formula of the position ,in, represents the position vector at time t, represents the position vector of the twin at time t+1, that is, the new position vector of the twin after a time interval, represents the velocity vector of the twin at time t+1, Represents the time interval, and adjusts the position and posture of the twin according to the position update formula, so that it moves along the virtual elastic path, generates a collision-free migration trajectory, and synchronizes the trajectory time and space parameters in reverse to the physical sandbox actuator to build a closed-loop feedback control of the virtual and real sandbox.

[0011] In a preferred embodiment, the operation instructions and state changes of the physical sandbox are monitored in real time in S103, a unique code is assigned to each operation type, and the device number involved in the operation is recorded. The first synchronization instruction including the operation type and the device number is sent to the digital twin platform through the Internet of Things, and the digital twin platform receives the first synchronization instruction from the Internet of Things platform; A digital twin sandbox preview model is built based on LSTM. The edge computing node uses the preview model, inputs the current historical synchronization instruction sequence and device response delay data, predicts the type of operation instruction and the corresponding device number that may be triggered in the next time window, and loads the 3D model resources of the relevant twin from the resource library of the digital twin platform to the edge cache in advance according to the prediction results. The loaded 3D model resource type is pre-rendered and a pre-rendering queue is generated. During the pre-rendering process, lighting, material, and texture factors are considered to improve the rendering results. Collect the transmission delay of the first synchronization instruction from the physical sandbox to the digital twin platform and the processing delay of the digital twin platform processing the instruction. Suppose the transmission delay of the first synchronization instruction from the physical sandbox to the digital twin platform is , the processing delay of the digital twin platform for processing instructions is , record the time when the command is sent through the timestamp , receiving time and processing completion time , the specific calculation formulas for transmission delay and processing delay are as follows: =

[0012]

[0013] Based on the collected delay data and the predicted instruction information, the delay compensation calculation is performed. The time deviation between the physical sandbox and the digital twin sandbox is , by measuring the transmission delay and processing delay multiple times to calculate the average time deviation , based on the predicted instruction information and delay data, calculate the predicted arrival time The actual arrival time Compare and generate synchronization deviation correction parameters , the specific calculation formula is as follows:

[0014] Correction parameters based on generated synchronization deviation , correct the timestamp of the first synchronization instruction, and set the original timestamp to , the corrected timestamp is:

[0015] in, It represents the corrected timestamp. According to the generated synchronization deviation correction parameter, the first synchronization instruction is corrected, and the corrected instruction is sent to the digital twin sandbox to drive the relevant twins to perform corresponding operations to achieve synchronization of virtual and real scenes.

[0016] In a preferred embodiment, the deviation correction parameters are obtained in S104, and the position, posture, and operating parameters of the corresponding twin in the digital twin sandbox are modified according to the correction parameters. According to the corrected twin state, combined with a preset topological weight algorithm, the dynamic association strength between devices is recalculated, and the topological relationship data in the digital twin sandbox is updated, including the connection status between devices and the association strength value.

[0017] The beneficial effects of the present invention are as follows: the present invention uses a topological weight algorithm to calculate the dynamic association strength between devices, and the generated dynamic topological relationship data accurately reflects the actual relationship between the devices, providing a solid data foundation for subsequent modeling and analysis. Based on the dynamic topological relationship data, the three-dimensional modeling technology is used to construct a digital twin sandbox basic model, and a dynamic two-way binding relationship between the physical device number and the twin identifier is established, ensuring the precise mapping between the physical sandbox and the digital twin sandbox. The use of autonomous path-finding algorithms and conflict resolution strategies enables the digital twin sandbox to flexibly respond to changes in the position of physical devices, realizes closed-loop feedback control of the virtual and real sandboxes, improves the adaptability and accuracy of the model, performs resource preparation and delay compensation operations in advance, effectively reduces the synchronization delay between the digital twin sandbox and the physical sandbox, and improves the real-time and accuracy of the system. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] Figure 1 is a flow chart of the present invention; Figure 2 A flowchart constructed for the digital twin sandbox of the present invention; Figure 3 It is a schematic diagram of the conflict resolution process of the present invention. DETAILED DESCRIPTION

[0019] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative work are within the scope of protection of this application.

[0020] In the description of this application, the terms "first" and "second" are used for descriptive purposes only and should not be understood as indicating or implying relative importance or implicitly indicating the number of technical features indicated. Thus, a feature defined as "first" or "second" may explicitly or implicitly include one or more of the features. In the description of this application, "plurality" means two or more, unless otherwise clearly and specifically defined.

[0021] In the description of the present application, the term "for example" is used to mean "used as an example, illustration or description". Any embodiment described as "for example" in the present application is not necessarily to be construed as being more preferred or advantageous than other embodiments. The following description is given to enable any technician in the field to implement and use the present invention. In the following description, details are listed for the purpose of explanation. It should be understood that a person of ordinary skill in the art can recognize that the present invention can be implemented without using these specific details. In other examples, well-known structures and processes will not be elaborated in detail to avoid unnecessary details to obscure the description of the present invention. Therefore, the present invention is not intended to be limited to the embodiments shown, but is consistent with the widest scope consistent with the principles and features disclosed in the present application.

[0022] like Figure 1-3 , this embodiment provides: a pig farm sandbox modeling and synchronization method based on digital twins, specifically comprising the following steps: S101. Based on dynamic topological relationship data, construct the basic model of the digital twin sandbox through 3D modeling technology; Furthermore, in the physical pig farm sandbox, multimodal sensors are deployed in various physical devices, including feed feeding machines, environmental control equipment and monitoring cameras, and a data acquisition system is built. The Internet of Things gateway is used as the core device, and the scattered sensors are connected to the gateway. The data acquisition system is started to continuously collect equipment operation data, environmental parameters and physical connection status between devices, and store them in the data storage server. The dynamic association strength between devices is comprehensively considered through the preset topological weight algorithm. The weight algorithm includes the device distance attenuation factor , Data interaction frequency and operational dependencies ,and + + =1, set the preset threshold of association strength , used to filter high-priority topological links, extract the distance data, data interaction frequency and operation dependency between devices from the data storage server, clean these data, remove outliers and duplicate data, and calculate the dynamic association strength between each pair of devices according to the topological weight algorithm for each pair of devices. Suppose the distance between device A and device B is , the data interaction frequency is , the operation dependency is o , then the strength of association S The specific calculation consensus is as follows:

[0023] in, and They represent the maximum values ​​of data interaction frequency and operation dependence, respectively, which are obtained by counting the data of all devices and comparing the calculated association strength of each pair of devices with the preset threshold. For comparison, when the correlation strength S> , the device pair is marked as a high-priority topological link, and the device numbers, association strength values, and related parameters of these links are recorded to generate a dynamic topological map. In the map, nodes represent devices, edges represent the connection relationships between devices, and different weights and color labels are assigned to edges according to the association strength.

[0024] It should be noted that the preset threshold of association strength By analyzing a large amount of collected equipment operation data, environmental parameters, and physical connection status between devices, we can first calculate the association strength between all pairs of devices, and then observe the distribution of these association strength values, for example, draw a histogram or probability density function curve of the association strength, find some characteristic points in the data distribution, such as inflection points, mode, etc., and use them as references for thresholds, or use statistical analysis methods, such as setting a percentage, and using the association strength value corresponding to a percentage higher than the percentage as the threshold, that is, the device pairs with a higher level of association strength are considered to be high-priority topological links.

[0025] S102, during the movement of the twins, the path conflict on the moving path is detected in real time. After the conflict is detected, the position and posture of the twins are adjusted through virtual elastic deformation modeling to avoid the path conflict; Furthermore, based on the acquired dynamic topological relationship data and following the preset adaptive topological mapping rules, the 3D modeling technology is used to construct a digital twin sandbox basic model that is mapped 1:1 with the physical sandbox. In the modeling process, a unique identification rule is defined for each physical device and the corresponding twin. Suppose the device type set is , each device type corresponds to a unique code, and the serial number set is , for physical devices , whose entity device type is , the serial number is , then the entity device number The calculation formula is:

[0026] in, Identify the jth specific device type in the device type set T. In the 3D modeling software, add an adaptive attribute to each device model to store its corresponding physical device number. Add an attribute to each twin in the digital twin sandbox to store its identification. Establish a dynamic two-way binding relationship between the physical device number and the twin identification to ensure that when the physical device number changes, the corresponding twin identification in the digital twin sandbox can also be automatically updated to ensure one-to-one correspondence between virtual and real devices. When the position of the physical device changes, use the binding relationship to trigger the autonomous path-finding algorithm of the twin in the digital twin sandbox. Call the autonomous path-finding algorithm to calculate the collision-free path of the twin from the current position to the new position. During the movement of the twin, use the collision detection algorithm to detect in real time whether there is a spatial overlap area with other twins and obstacles on its path. Use the space segmentation algorithm to detect conflicts. Divide the space of the digital twin sandbox into an octree structure, where each node represents a subspace. Suppose the twin Located at the octree node , twin Located at the octree node ,when and When the two twins are the same node and they have a common ancestor node, it means that there is a conflict between the two twins. When a conflict is detected, the spatial overlapping area on the twin movement path is modeled with virtual elastic deformation through the conflict resolution strategy. The twins in conflict can be regarded as elastic bodies, and the force F and deformation amount The proportional coefficient is the elastic coefficient k. The specific formula is as follows:

[0027] The negative sign indicates that the direction of the force is opposite to the direction of the deformation variable. In the digital twin space, the displacement vector of the twin is , then the force vector is:

[0028] in, Represents the force vector. By calculating the force vector and combining it with Newton's second law, we can get the acceleration vector , where m represents the mass of the twin. According to the kinematic formula, the velocity update formula and position update formula are calculated: The velocity update formula is the velocity vector = ,in, represents the acceleration vector of the twin, and the update formula of the position ,in, represents the position vector at time t, represents the position vector of the twin at time t+1, that is, the new position vector of the twin after a time interval, represents the velocity vector of the twin at time t+1, Represents the time interval, and adjusts the position and posture of the twin according to the position update formula, so that it moves along the virtual elastic path, generates a collision-free migration trajectory, and synchronizes the trajectory time and space parameters in reverse to the physical sandbox actuator to build a closed-loop feedback control of the virtual and real sandbox.

[0029] It should be noted that the adaptive topology mapping rule clusters devices with similar characteristics into one category by performing cluster analysis on the information such as the strength of association between devices and spatial coordinates in the dynamic topology relationship data. For example, based on factors such as the function, location and data interaction frequency of the equipment, functionally related devices in the same area are clustered together, and then corresponding topology mapping rules are formulated for each type of equipment to ensure that the same type of equipment has similar topological structures and mapping methods in the digital twin sandbox. The association rule mining algorithm is used to discover potential association rules between devices from the dynamic topology relationship data. For example, by analyzing the data, it is found that when the feed feeder is running, some environmental control equipment will also adjust parameters accordingly. According to this association rule, the topological connection and mapping relationship between the two types of equipment in the digital twin sandbox can be determined, that is, when the feed feeder model in the digital twin sandbox is in operation, the corresponding environmental control equipment model should also make corresponding state changes.

[0030] Furthermore, the self-help routing algorithm comprises the following steps: S1. Represented as a digital twin sandbox environment, where V is a node set, representing various locations in the sandbox scene. These locations can be any location that the twin may reach, such as different areas of the pig house, the location of the equipment, and E is an edge set, which represents the connection relationship between the locations, that is, the path that the twin can move from one location to another; S2. First, determine a starting node Q, which is the initial position of the twin. For the distance from the starting node Q to itself, initialize it to For all other nodes v, they belong to node V but not including the starting node Q, we initialize their distance to the starting node Q to infinity, using ; S3. During the operation of the algorithm, starting from the starting node Q, gradually explore its adjacent nodes. For the node u currently being explored, check all the nodes v adjacent to it. Each edge connecting node u and node v has a weight , this weight represents the cost of moving from node u to node v, such as the actual distance between them and the time required for movement. When the total distance from the starting node Q through the current node u to node v is found When it is less than the distance d(v) from the currently recorded node v to the starting node Q, it means that we have found a shorter path to reach node v. At this time, we can update the value of d(v) and set it to ,By continuously checking adjacent nodes and updating the distances, we can gradually find shorter paths from the starting node to other nodes; S4. In each iteration, there are two node sets, one is the node set to be explored, which contains nodes whose shortest paths to the starting nodes have not yet been determined, and the other is the explored node set, which contains nodes whose shortest paths have been determined. We select the node with the smallest d(v) value from the node set to be explored. This node means that we have found the shortest path from the starting node to it, so we move it from the node set to be explored to the node set to the explored node set, and use this newly determined shortest path node as the current node u. Repeat the above process of updating distance and selecting nodes until the node set to be explored is empty. At this time, we have found the shortest path from the starting node to all nodes in the digital twin sandbox environment, thereby realizing the autonomous path finding of the twin in this environment.

[0031] S103: When the physical sandbox generates an operation instruction and the state changes, the relevant information sends a first synchronization instruction to the digital twin platform through the Internet of Things; Furthermore, the operation instructions and state changes of the physical sandbox are monitored in real time, a unique code is assigned to each operation type, and the device number involved in the operation is recorded. The first synchronization instruction including the operation type and the device number is sent to the digital twin platform through the Internet of Things, and the digital twin platform receives the first synchronization instruction from the Internet of Things platform; A digital twin sandbox preview model is built based on LSTM. The edge computing node uses the preview model, inputs the current historical synchronization instruction sequence and device response delay data, predicts the type of operation instruction and the corresponding device number that may be triggered in the next time window, and loads the 3D model resources of the relevant twin from the resource library of the digital twin platform to the edge cache in advance according to the prediction results. The loaded 3D model resource type is pre-rendered and a pre-rendering queue is generated. During the pre-rendering process, lighting, material, and texture factors are considered to improve the rendering results. Collect the transmission delay of the first synchronization instruction from the physical sandbox to the digital twin platform and the processing delay of the digital twin platform processing the instruction. Suppose the transmission delay of the first synchronization instruction from the physical sandbox to the digital twin platform is , the processing delay of the digital twin platform for processing instructions is , record the time when the command is sent through the timestamp , receiving time and processing completion time , the specific calculation formulas for transmission delay and processing delay are as follows: =

[0032]

[0033] Based on the collected delay data and the predicted instruction information, the delay compensation calculation is performed. The time deviation between the physical sandbox and the digital twin sandbox is , by measuring the transmission delay and processing delay multiple times to calculate the average time deviation , based on the predicted instruction information and delay data, calculate the predicted arrival time The actual arrival time Compare and generate synchronization deviation correction parameters , the specific calculation formula is as follows:

[0034] Correction parameters based on generated synchronization deviation , correct the timestamp of the first synchronization instruction, and set the original timestamp to , the corrected timestamp is:

[0035] in, It represents the corrected timestamp. According to the generated synchronization deviation correction parameter, the first synchronization instruction is corrected, and the corrected instruction is sent to the digital twin sandbox to drive the relevant twins to perform corresponding operations to achieve synchronization of virtual and real scenes.

[0036] It should be noted that the prediction of the operation instruction type and the corresponding device number that may be triggered in the next time window is based on linear weighting. Suppose the number of times the operation instruction type appears in the historical synchronization instruction sequence of the past N time steps is { }, k is the total number of operation instruction types, and the number of times the device number appears is { }, l represents the total number of device numbers, and the average response delay of the devices in the past N practice units is recorded as , set a basic weight for each operation instruction type , and consider the influencing factors of the average response delay of the device , calculate the prediction score for each operation instruction type :

[0037] Select the operation instruction type with the highest score as the prediction result, that is, the predicted operation instruction type O=arg , set a basic weight for each device number , and consider the influencing factors of the average response delay of the device , calculate the prediction score for each operation instruction type :

[0038] Select the operation device number with the highest score as the prediction result, that is, the predicted operation instruction type E=arg .

[0039] S104, updating the state and topological relationship of the corresponding twin in the digital twin sandbox according to the correction parameters; Furthermore, the deviation correction parameters are obtained, and the position, posture, and operating parameters of the corresponding twin in the digital twin sandbox are modified according to the correction parameters. According to the corrected twin state and combined with the preset topological weight algorithm, the dynamic association strength between devices is recalculated, and the topological relationship data in the digital twin sandbox is updated, including the connection status between devices and the association strength value.

[0040] It should be noted that in the above embodiments, the description of each embodiment has its own emphasis, and for parts that are not described in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0041] It will be appreciated by those skilled in the art that embodiments of the present invention may be provided as methods, systems, or computer program products. Therefore, the present invention may take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Furthermore, the present invention may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0042] The present invention is described with reference to flowcharts and / or block diagrams of methods, devices (systems), and computer program products according to embodiments of the present invention. It should be understood that each process and / or block in the flowchart and / or block diagram, as well as the combination of processes and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded computer, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0043] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0044] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process in the computer or other programmable device. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0045] Although the preferred embodiments of the present invention have been described, those skilled in the art may make other changes and modifications to these embodiments once they have learned the basic creative concept. Therefore, the appended claims are intended to be interpreted as including the preferred embodiments and all changes and modifications that fall within the scope of the present invention.

[0046] Obviously, those skilled in the art can make various changes and modifications to the present invention without departing from the spirit and scope of the present invention. Thus, if these modifications and variations of the present invention fall within the scope of the claims of the present invention and their equivalents, the present invention is also intended to include these modifications and variations.

Claims

1. The pig farm sandbox modeling and synchronization method based on digital twin is characterized by: The following steps are involved: S101. Based on dynamic topological relationship data, construct the basic model of the digital twin sandbox through 3D modeling technology; S102, during the movement of the twins, the path conflict on the moving path is detected in real time. After the conflict is detected, the position and posture of the twins are adjusted through virtual elastic deformation modeling to avoid the path conflict; S103: When the physical sandbox generates an operation instruction and the state changes, the relevant information sends a first synchronization instruction to the digital twin platform through the Internet of Things; S104: Update the status and topological relationship of the corresponding twin in the digital twin sandbox according to the correction parameters.

2. The pig farm sandbox modeling and synchronization method based on digital twin according to claim 1 is characterized in that: In S101, in the physical pig farm sandbox, multimodal sensors are deployed in various physical devices, a data collection system is built, and the Internet of Things gateway is used as the core device. The scattered sensors are connected to the gateway, and the data collection system is started to continuously collect equipment operation data, environmental parameters, and physical connection status between devices. The dynamic association strength between devices is comprehensively considered through the preset topological weight algorithm. The weight algorithm includes the device distance attenuation factor , Data interaction frequency and operational dependencies ,and + + =1, set the preset threshold of association strength , used to filter high-priority topological links, extract distance data, data interaction frequency, and operation dependencies between devices from the data storage server, clean these data, remove outliers and duplicate data, and for each pair of devices, calculate the dynamic association strength between each pair of devices based on the topological weight algorithm.

3. The pig farm sandbox modeling and synchronization method based on digital twin according to claim 2 is characterized in that: The dynamic association strength is calculated by assuming that the distance between device A and device B is , the data interaction frequency is , the operation dependency is o , then the strength of association S The specific calculation consensus is as follows: in, and They represent the maximum values ​​of data interaction frequency and operation dependence, respectively, which are obtained by counting the data of all devices and comparing the calculated association strength of each pair of devices with the preset threshold. For comparison, when the correlation strength S> When the device pair is marked as a high-priority topological link, the device numbers, association strength values ​​and related parameters of these links are recorded to generate a dynamic topological map.

4. The pig farm sandbox modeling and synchronization method based on digital twin according to claim 1 is characterized in that: In S102, based on the acquired dynamic topological relationship data and following the preset adaptive topological mapping rules, a digital twin sandbox basic model with a 1:1 mapping to the physical sandbox is constructed using 3D modeling technology. During the modeling process, a unique identification rule is defined for each physical device and the corresponding twin. Suppose the device type set is , each device type corresponds to a unique code, and the serial number set is , for physical devices , whose entity device type is , the serial number is , then the entity device number The calculation formula is: in, Identify the j-th specific device type in the device type set T. In the 3D modeling software, add an adaptive attribute to each device model to store its corresponding physical device number. Add an attribute to each twin in the digital twin sandbox to store its identification. Establish a dynamic two-way binding relationship between the physical device number and the twin identification. When changes in the physical device number and position are detected, trigger the autonomous path-finding algorithm of the corresponding twin in the digital twin sandbox.

5. The pig farm sandbox modeling and synchronization method based on digital twin according to claim 4 is characterized in that: The execution of the autonomous path-finding algorithm involves dividing the space of the digital twin sandbox into an octree structure, where each node represents a subspace. Located at the octree node , twin Located at the octree node ,when and When the two twins are the same node and they have a common ancestor node, it means that there is a conflict between the two twins. When a conflict is detected, the spatial overlapping area on the twin movement path is modeled with virtual elastic deformation through the conflict resolution strategy. The twins in conflict can be regarded as elastic bodies, and the force F and deformation amount The proportional coefficient is the elastic coefficient k. The specific formula is as follows: The negative sign indicates that the direction of the force is opposite to the direction of the deformation variable. In the digital twin space, the displacement vector of the twin is , then the force vector is: in, Represents the force vector. By calculating the force vector and combining it with Newton's second law, we can get the acceleration vector , where m represents the mass of the twin. According to the kinematic formula, the velocity update formula and position update formula are calculated: The velocity update formula is the velocity vector = ,in, represents the acceleration vector of the twin, and the update formula of the position ,in, represents the position vector at time t, represents the position vector of the twin at time t+1, that is, the new position vector of the twin after a time interval, represents the velocity vector of the twin at time t+1, Represents the time interval, and the position and posture of the twin are adjusted according to the position update formula.

6. The pig farm sandbox modeling and synchronization method based on digital twin according to claim 1 is characterized in that: In S103, the operation instructions and state changes of the physical sandbox are monitored in real time, and a unique code is assigned to each operation type; Sending a first synchronization instruction to the digital twin platform through the Internet of Things, where the first synchronization instruction includes an operation type and a device number; A digital twin sandbox rehearsal model is built based on LSTM, and the current historical synchronization instruction sequence and device response delay data are input to predict the type of operation instruction and the corresponding device number that may be triggered in the next time window. According to the prediction results, the 3D model resources of the relevant twins are loaded from the resource library of the digital twin platform to the edge cache in advance.

7. The pig farm sandbox modeling and synchronization method based on digital twin according to claim 6 is characterized in that: Collect the transmission delay of the first synchronization instruction from the physical sandbox to the digital twin platform and the processing delay of the digital twin platform processing the instruction. Suppose the transmission delay of the first synchronization instruction from the physical sandbox to the digital twin platform is , the processing delay of the digital twin platform for processing instructions is , record the time when the command is sent through the timestamp , receiving time and processing completion time , the specific calculation formulas for transmission delay and processing delay are as follows: = Based on the collected delay data and combined with the predicted instruction information, delay compensation calculation is performed.

8. The pig farm sandbox modeling and synchronization method based on digital twin according to claim 7 is characterized in that: The delay compensation calculation is performed by assuming that the time deviation between the physical sandbox and the digital twin sandbox is , by measuring the transmission delay and processing delay multiple times to calculate the average time deviation , based on the predicted instruction information and delay data, calculate the predicted arrival time The actual arrival time Compare and generate synchronization deviation correction parameters , the specific calculation formula is as follows: Correction parameters based on generated synchronization deviation , correct the timestamp of the first synchronization instruction, and set the original timestamp to , the corrected timestamp is: in, Indicates the corrected timestamp.

9. The on-site sandbox modeling and synchronization method based on digital twin according to claim 8 is characterized in that: According to the generated synchronization deviation correction parameters, the first synchronization instruction is corrected, and the corrected instruction is sent to the digital twin sandbox to drive the relevant twins to perform corresponding operations to achieve synchronization of virtual and real scenes.

10. The pig farm sandbox modeling and synchronization method based on digital twin according to claim 1 is characterized in that: In S104, the deviation correction parameters are obtained, and the position, posture, and operating parameters of the corresponding twin in the digital twin sandbox are modified according to the correction parameters. According to the corrected twin state and combined with the preset topological weight algorithm, the dynamic association strength between devices is recalculated, and the topological relationship data in the digital twin sandbox is updated, including the connection status between devices and the association strength value.

Images