Data processing method and system based on intelligent industrial system

Abstract

The invention discloses a data processing method and system based on an intelligent industrial system, and belongs to the technical field of industrial data processing. The system comprises a cloud processing module which forms a mapping model of an intelligent factory based on a digital twinning technology, realizes monitoring processing of intelligent industrial node data circulation through the mapping model of the intelligent factory, and determines a detection response resource proportion of the intelligent industrial node; the edge operation module integrates data acquisition, application control and data optimization function areas based on a real-time operation system of the intelligent factory, constructs a data storage container, stores transmission data of each function area, and forms data interaction with the cloud processing module; a port control module; and a network circulation module. According to the invention, automatic network monitoring and early warning of each transfer node in an intelligent industrial system can be realized, the resource utilization rate is improved, the system load is reduced, and efficient and collaborative data decision and autonomous optimization processing are realized.

Description

Technical Field

[0001] The present invention relates to the technical field of industrial data processing, and specifically to a data processing method and system based on an intelligent industrial system. Background Art

[0002] With the accelerating evolution of global manufacturing towards digitalization, networking, and intelligence, the intelligent industrial system has become the core driving force for promoting industrial upgrading. This system is based on cutting-edge technologies such as industrial Internet of Things, big data analysis, artificial intelligence, and digital twin, constructing a production environment that combines virtual and real, realizing device interconnection, data-driven decision-making, and autonomous optimization. By embedding sensors and communication modules in industrial equipment to achieve real-time data collection and transmission, combined with edge computing to complete data preprocessing locally, reducing the cloud load and improving the response speed, thus intelligently perceiving changes in production conditions and forming intelligent industrial control with the goal of optimizing operation indicators. However, in the entire intelligent production process, data transmission between various nodes plays a crucial role. Currently, the intelligent industrial systems on the market all adopt real-time resource response detection for network detection, that is, constantly querying the network status under the entire system at all times. This will lead to an extremely heavy network load under the entire intelligent industrial system. However, in fact, for some data nodes with low or almost no data transfer, there is no need for real-time monitoring. Adopting a method of timed detection or automated detection and processing can be more efficient. However, in the face of how to regulate the network system detection process, there is still a lack of a method for realizing network resource regulation according to the particularity of each node. Summary of the Invention

[0003] The purpose of the present invention is to provide a data processing method and system based on an intelligent industrial system to solve the problems raised in the above background art.

[0004] To solve the above technical problems, the present invention provides the following technical solution: A data processing execution system based on an intelligent industrial system, the system includes:

[0005] A cloud processing module, forming a mapping model of an intelligent factory based on digital twin technology, realizing the monitoring and processing of data flow of intelligent industrial nodes through the mapping model of the intelligent factory, and determining the proportion of detection response resources of intelligent industrial nodes;

[0006] An edge operation module, integrating data collection, application control, and data optimization functional areas based on the real-time operating system of the intelligent factory, constructing a data storage container to store the transmission data of each functional area, and forming data interaction with the cloud processing module;

[0007] A port control module, applied to the production ports of the intelligent factory, integrating the control authorities of intelligent sensors, intelligent actuators, and digitalized equipment, and receiving and identifying commands from administrators;

[0008] The network transfer module constructs an IT / OT fusion network with a general IP protocol between modules to achieve real-time data transmission between intelligent industrial nodes, receives the detection response resource command from the cloud processing module to implement network automated detection, and simultaneously sets up an early warning function system to achieve automated alarm during network failures.

[0009] According to the above technical solution, the process of forming the mapping model of the intelligent factory based on digital twin technology includes:

[0010] Install IoT sensors on the physical devices of the intelligent factory, collect real-time data through OPC UA and Modbus protocols, use 3D modeling tools to construct the models of the physical devices and factory production lines of the intelligent factory, simulate the dynamic characteristics of the physical devices of the intelligent factory through a physics engine, and hierarchically construct digital twins from the single-device level to the workshop level and factory level.

[0011] According to the above technical solution, the monitoring and processing of the data flow of intelligent industrial nodes through the mapping model of the intelligent factory includes:

[0012] Create several intelligent industrial nodes based on the mapping model of the intelligent factory. Each intelligent industrial node corresponds to a type of physical device data in the intelligent factory. The physical device data refers to the production data of the physical devices of the intelligent factory. In different project processes, there are several associated intelligent industrial nodes corresponding to any one intelligent industrial node. If there is direct data interaction between the physical device corresponding to any one intelligent industrial node and a certain physical device, the intelligent industrial node corresponding to a certain physical device is the associated intelligent industrial node of any one intelligent industrial node, and mark the data flow directions of each intelligent industrial node through the mapping model of the intelligent factory.

[0013] According to the above technical solution, determining the detection response resources of intelligent industrial nodes includes:

[0014] Determine the total amount of detection resources in the network detection framework, denoted as U;

[0015] Determine the data group of any one intelligent industrial node, and determine the detection response resources of the intelligent industrial node based on the data group of any one intelligent industrial node. The data group of any one intelligent industrial node includes: the number of associated intelligent industrial nodes, the data traffic of each associated intelligent industrial node, where the data traffic of the intelligent industrial node uses time-sharing data acquisition, that is, the system selects a time period and takes the average real-time data traffic within the same time period as the data traffic of the intelligent industrial node; the data group is denoted as: {A, a1, a2,..., a A}, where A represents the number of associated intelligent industrial nodes, a1, a2,..., a Arespectively represent the data traffic of the 1st, 2nd, …, A-th associated intelligent industrial nodes;

[0016] The system sets N data traffic intervals, which can cover the data traffic of all associated intelligent industrial nodes. The endpoints of any data traffic interval include the former but not the latter. A response model is constructed to judge the contribution value of the data traffic interval:

[0017]

[0018] Among them, S i refers to the contribution value of data traffic interval i; F refers to the set of combined characteristics of the data traffic interval; M refers to the subset of characteristics that does not include data traffic interval i among the combined characteristics of the data traffic interval; H refers to the set of characteristics that does not include data traffic interval i among the combined characteristics of the data traffic interval; |M| refers to the number of data traffic intervals existing in M; |F| refers to the total number of data traffic intervals; f(M +i ) refers to the model prediction value when only data traffic interval i is added to M; f(M) refers to the model prediction value when only M is used;

[0019] Determine the contribution values of all data traffic intervals. According to the data group of any intelligent industrial node, determine the sum of the contribution values of the data traffic intervals in the data group of any intelligent industrial node, which is recorded as the first detection response resource factor of any intelligent industrial node, and the number of corresponding associated intelligent industrial nodes is recorded as the second detection response resource factor. Based on the first detection response resource factor and the second detection response resource factor, form the detection response resource score of any intelligent industrial node:

[0020] T = K1 * V1 + K2 * V2

[0021] Among them, T represents the detection response resource score; K1 and K2 represent the coefficients set by the system; V1 and V2 represent the first detection response resource factor and the second detection response resource factor;

[0022] Calculate the detection response resource scores of all intelligent industrial nodes and sum them up. Form the detection response resource ratio of each intelligent industrial node according to the ratio of the detection response resource score of each intelligent industrial node in the sum of the detection response resource scores.

[0023] According to the above technical solution, it further includes that the cloud processing module issues a network detection response resource command based on the determined detection response resource ratio of each intelligent industrial node to realize network automatic detection.

[0024] A data processing method based on an intelligent industrial system, the method includes:

[0025] S1. Form a mapping model of the intelligent factory based on digital twin technology, monitor and process the data flow of intelligent industrial nodes through the mapping model of the intelligent factory, and determine the proportion of detection response resources of intelligent industrial nodes;

[0026] S2. Integrate data acquisition, application control, and data optimization function areas based on the real-time operating system of the intelligent factory, build a data storage container to store the transmission data of each function area, and form data interaction with the cloud processing module;

[0027] S3. Integrate the control permissions of intelligent sensors, intelligent actuators, and digital equipment at the production port of the intelligent factory, and receive and identify the commands of the administrator;

[0028] S4. Build an IT / OT fusion network with a common IP protocol between each module to achieve real-time data transmission between intelligent industrial nodes, receive the detection response resource commands of the cloud processing module, achieve network automation detection, and set up an early warning function system to achieve automatic alarm during network failures.

[0029] According to the above technical solution, the process of forming the mapping model of the intelligent factory based on digital twin technology includes:

[0030] Install IoT sensors on the physical devices of the intelligent factory, collect real-time data through OPC UA and Modbus protocols, use 3D modeling tools to build models of the physical devices of the intelligent factory and the factory production lines, simulate the dynamic characteristics of the physical devices of the intelligent factory through a physical engine, and build digital twins hierarchically from the single-device level to the workshop level and the factory level.

[0031] According to the above technical solution, the monitoring and processing of the data flow of intelligent industrial nodes through the mapping model of the intelligent factory includes:

[0032] Create several intelligent industrial nodes based on the mapping model of the intelligent factory. Each intelligent industrial node corresponds to a kind of physical device data in the intelligent factory. The physical device data refers to the production data of the physical devices of the intelligent factory. In different project processes, there are several associated intelligent industrial nodes corresponding to any one intelligent industrial node. If there is direct data interaction between the physical device corresponding to any one intelligent industrial node and a certain physical device, the intelligent industrial node corresponding to a certain physical device is the associated intelligent industrial node of any one intelligent industrial node, and mark the data flow directions of each intelligent industrial node through the mapping model of the intelligent factory.

[0033] According to the above technical solution, the determination of the detection response resources of intelligent industrial nodes includes:

[0034] Determine the total amount of detection resources in the network detection framework, denoted as U;

[0035] Determine the data group of any intelligent industrial node, and determine the detection response resources of the intelligent industrial node based on the data group of any intelligent industrial node. The data group of any intelligent industrial node includes: the number of associated intelligent industrial nodes, and the data traffic of each associated intelligent industrial node. Among them, the data traffic of the intelligent industrial node is collected by time-sharing data acquisition, that is, the system selects a time period, and takes the average real-time data traffic within the same time period as the data traffic of the intelligent industrial node; the data group is denoted as: {A, a1, a2, …, a A}, where A represents the number of associated intelligent industrial nodes, and a1, a2, …, a A respectively represent the data traffic of the 1st, 2nd, …, A-th associated intelligent industrial nodes;

[0036] The system sets N data traffic intervals that can cover the data traffic of all associated intelligent industrial nodes. The endpoints of any data traffic interval include the previous one but not the following one, and a response model is constructed to judge the contribution value of the data traffic interval:

[0037]

[0038] where S refers to the contribution value of data traffic interval i; F refers to the combined feature set of the data traffic interval; M refers to the feature subset that does not include data traffic interval i in the combined features of the data traffic interval; H refers to the feature set that does not include data traffic interval i in the combined features of the data traffic interval; |M| refers to the number of data traffic intervals existing in M; |F| refers to the total number of data traffic intervals; f(M +i ) refers to the model prediction value when only data traffic interval i is added to M; f(M) refers to the model prediction value when only M is used;

[0039] Determine the contribution values of all data traffic intervals. According to the data group of any intelligent industrial node, determine the sum of the contribution values of the data traffic intervals in the data group of any intelligent industrial node, denoted as the first detection response resource factor of any intelligent industrial node, and the corresponding number of associated intelligent industrial nodes is denoted as the second detection response resource factor. Based on the first detection response resource factor and the second detection response resource factor, form the detection response resource score of any intelligent industrial node:

[0040] T = K1 * V1 + K2 * V2

[0041] where T represents the detection response resource score; K1 and K2 represent the coefficients set by the system; V1 and V2 represent the first detection response resource factor and the second detection response resource factor;

[0042] Calculate the detection response resource scores of all intelligent industrial nodes, sum them up, and form the proportion of the detection response resources of each intelligent industrial node in the sum of the detection response resource scores.

[0043] According to the above technical solution, it further includes issuing a network detection response resource command based on the determined proportion of the detection response resources of each intelligent industrial node to achieve network automated detection.

[0044] Compared with the prior art, the beneficial effects achieved by the present invention are as follows: Based on the intelligent industrial system, in the case of "one network throughout the whole factory", based on the project's own conditions and the total amount of detection resources in the detection resource framework, the present invention realizes the problems of network automatic monitoring and early warning of each transfer node in the intelligent industrial system, improves resource utilization rate, reduces system load, and realizes efficient collaborative data decision-making and autonomous optimization processing. Brief Description of the Drawings

[0045] The drawings are used to provide a further understanding of the present invention, and constitute a part of the specification. They are used together with the embodiments of the present invention to explain the present invention, and do not constitute a limitation to the present invention.

[0046] Figure 1 It is a schematic diagram of the module connection of a data processing system based on an intelligent industrial system according to the present invention;

[0047] Figure 2 It is a schematic diagram of the steps of a data processing method based on an intelligent industrial system according to the present invention. Detailed Embodiments

[0048] Next, the technical solutions in the embodiments of the present invention will be clearly and completely described in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all of the embodiments. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present invention without creative efforts shall fall within the protection scope of the present invention.

[0049] Please refer to Figure 1 , in the first embodiment: Provide a data processing execution system based on an intelligent industrial system, and the system includes:

[0050] A cloud processing module 101, which forms a mapping model of an intelligent factory based on digital twin technology, realizes the monitoring and processing of the data flow of intelligent industrial nodes through the mapping model of the intelligent factory, and determines the proportion of the detection response resources of intelligent industrial nodes;

[0051] The edge operation module 102 integrates data acquisition, application control, and data optimization functional areas based on the real-time operating system of the intelligent factory, constructs a data storage container to store the transmission data of each functional area, and forms data interaction with the cloud processing module 101;

[0052] The port control module 103 is applied to the production ports of the intelligent factory, integrates the control authorities of intelligent sensors, intelligent actuators, and digital equipment, and receives and recognizes the commands of the administrator;

[0053] The network transfer module 104 constructs an IT / OT convergence network with a general IP protocol between various modules to achieve real-time data transmission between intelligent industrial nodes, receives the detection response resource commands of the cloud processing module 101 to implement network automation detection, and simultaneously sets up an early warning function system to achieve automatic alarm during network failures.

[0054] The process of forming a mapping model of the intelligent factory based on digital twin technology includes:

[0055] Install IoT sensors on the physical devices of the intelligent factory, collect real-time data through OPC UA and Modbus protocols, use 3D modeling tools to construct the models of the physical devices and factory production lines of the intelligent factory, simulate the dynamic characteristics of the physical devices of the intelligent factory through a physics engine, and hierarchically construct digital twins from the single-device level to the workshop level and factory level.

[0056] Among them, in the process of constructing the digital twin, the steps of geometric modeling - behavior modeling - hierarchical modeling are generally adopted. First, use 3D modeling tools (such as SolidWorks, Blender) to construct high-fidelity visualization models of equipment and production lines, then simulate the dynamic characteristics of the equipment through a physics engine (such as MATLAB Simulink), or based on machine learning to train data-driven models, and gradually construct digital twins hierarchically from the single-device level to the workshop level and factory level to achieve the function of supporting multi-scale simulation. In the communication framework, protocols such as MQTT and Kafka are used to achieve two-way real-time data interaction between the physical and virtual spaces, ensure the consistency of the virtual model and the physical world state (such as supported by 5G low-latency network) through timestamp alignment for dynamic updates, and use Digital Thread technology to track the data stream to ensure automatic update of model parameters with physical changes.

[0057] The monitoring and processing of data flow of intelligent industrial nodes through the mapping model of the intelligent factory includes: <##

[0058] Create several intelligent industrial nodes based on the mapping model of the intelligent factory. Each intelligent industrial node corresponds to a type of physical device data in the intelligent factory. The physical device data refers to the production data of the physical devices in the intelligent factory. In different project processes, there are several associated intelligent industrial nodes corresponding to any one intelligent industrial node. If there is direct data interaction between the physical device corresponding to any one intelligent industrial node and a certain physical device, the intelligent industrial node corresponding to the certain physical device is the associated intelligent industrial node of any one intelligent industrial node. Mark the data flow directions of each intelligent industrial node through the mapping model of the intelligent factory.

[0059] The detection response resources for determining the intelligent industrial nodes include:

[0060] Determine the total amount of detection resources in the network detection framework, denoted as U;

[0061] Determine the data group of any one intelligent industrial node, and determine the detection response resources of the intelligent industrial node based on the data group of any one intelligent industrial node. The data group of any one intelligent industrial node includes: the number of associated intelligent industrial nodes, the data flow of each associated intelligent industrial node. Among them, the data flow of the intelligent industrial node adopts time-sharing data acquisition, that is, the system selects a time period and takes the average real-time data flow within the same time period as the data flow of the intelligent industrial node; the data group is denoted as: {A, a1, a2,..., a A}, where A represents the number of associated intelligent industrial nodes, and a1, a2,..., a A represent the data flows of the 1st, 2nd,..., A-th associated intelligent industrial nodes respectively;

[0062] In this application, taking 100 as the total amount of detection resources (that is, the data capacity area where the system can share the detection function), determine the associated intelligent industrial nodes of each intelligent industrial node to form different data groups. For example, any data group can be denoted as {3, 45, 60, 90, 70, 100, 105};

[0063] The system sets N data flow intervals that can cover the data flows of all associated intelligent industrial nodes. The endpoints of any one data flow interval include the previous one but not the following one. Build a response model to judge the contribution value of the data flow interval:

[0064]

[0065] Among them, S iRefers to the contribution value of data traffic interval i; F refers to the set of combined characteristics of data traffic intervals; M refers to the subset of characteristics that does not include data traffic interval i among the combined characteristics of data traffic intervals; H refers to the set of characteristics that does not include data traffic interval i among the combined characteristics of data traffic intervals; |M| refers to the number of data traffic intervals in M; |F| refers to the total number of data traffic intervals; f(M +i ) refers to the model prediction value when only data traffic interval i is added to M; f(M) refers to the model prediction value when only M is used;

[0066] In the above embodiments, taking 3 data traffic intervals as an example, for example, 40 - 60, 60 - 80, 80 and above, then the above data group can be expressed as: one feature (45) for 40 - 60, two features (60, 70) for 60 - 80, and three features (90, 100, 105) for 80 and above;

[0067] In the above manner, the number of features within each data traffic interval can be obtained. Writing the 3 data traffic intervals as x1, x2, x3, assuming there is a functional relationship between function f and x1, x2, x3. For example, taking simple linear regression as an example, assume f(x) = 2x1 + 3x2 + 5x3. Setting the replacement feature to 0, then according to one feature (45) for 40 - 60, two features (60, 70) for 60 - 80, and three features (90, 100, 105) for 80 and above, it is actually the influence value when judging the data group x = {x1 = 1, x2 = 2, x3 = 3};

[0068] Then, calculating the contribution value of data traffic interval x1 includes:

[0069] Determine H, that is, determine the set of characteristics that does not include data traffic interval x1 among the combined characteristics of data traffic intervals, which are the case of no feature set, only including data traffic interval x2, only including data traffic interval x3, and including both data traffic interval x2 and data traffic interval x3. Calculate them separately:

[0070] In this application, taking the example of only including data traffic interval x2, then x1 and x3 take the replacement feature as 0, f(M +i ) = 2×1 + 3×2 + 0 = 8, f(M) = 0 + 3×2 + 0 = 6;

[0071]

[0072] [f(M +i ) - f(M)] = 2

[0073] After calculating the four cases separately and summing them up, the contribution value of data traffic interval x1 is formed;

[0074] Determine the contribution values of all data traffic intervals. Based on the data set of any intelligent industrial node, determine the sum of the contribution values of the data traffic intervals in the data set of any intelligent industrial node, which is denoted as the first detection response resource factor of any intelligent industrial node, and the corresponding number of associated intelligent industrial nodes is denoted as the second detection response resource factor. Form the detection response resource score of any intelligent industrial node based on the first detection response resource factor and the second detection response resource factor:

[0075] T = K1 * V1 + K2 * V2

[0076] Among them, T represents the detection response resource score; K1 and K2 represent the coefficients set by the system; V1 and V2 represent the first detection response resource factor and the second detection response resource factor;

[0077] Calculate the detection response resource scores of all intelligent industrial nodes and sum them up. Form the proportion of the detection response resources of each intelligent industrial node in the sum of the detection response resource scores.

[0078] According to the above technical solution, it further includes that the cloud processing module issues a network detection response resource command based on the determined proportion of the detection response resources of each intelligent industrial node to achieve network automated detection.

[0079] In this embodiment, as Figure 2 shown, there is also provided a data processing method based on an intelligent industrial system, and the method includes:

[0080] S1. Form a mapping model of the intelligent factory based on digital twin technology, monitor and process the data flow of the intelligent industrial node through the mapping model of the intelligent factory, and determine the proportion of the detection response resources of the intelligent industrial node;

[0081] S2. Integrate the data acquisition, application control, and data optimization function areas based on the real-time operating system of the intelligent factory, construct a data storage container, store the transmission data of each function area, and form data interaction with the cloud processing module;

[0082] S3. At the production port of the intelligent factory, integrate the control authorities of intelligent sensors, intelligent actuators, and digitalized equipment, and receive and identify the commands of the administrator;

[0083] S4. Build an IT / OT convergence network with a general IP protocol between each module to achieve real-time data transmission between intelligent industrial nodes, receive the detection response resource command of the cloud processing module to achieve network automated detection, and at the same time set up an early warning function system to achieve automated alarm during network failures.

[0084] The process of forming the mapping model of the intelligent factory based on digital twin technology includes:

[0085] Install IoT sensors on the physical devices of the intelligent factory, collect real-time data through OPC UA and Modbus protocols, use 3D modeling tools to build models of the physical devices of the intelligent factory and the factory production lines, simulate the dynamic characteristics of the physical devices of the intelligent factory through a physics engine, and build digital twins hierarchically from the single-device level to the workshop level and the factory level.

[0086] The monitoring and processing of the data flow of intelligent industrial nodes through the mapping model of the intelligent factory includes:

[0087] Create several intelligent industrial nodes based on the mapping model of the intelligent factory. Each intelligent industrial node corresponds to a type of physical device data in the intelligent factory. The physical device data refers to the production data of the physical devices in the intelligent factory. In different project processes, there are several associated intelligent industrial nodes corresponding to any one intelligent industrial node. If there is direct data interaction between the physical device corresponding to any one intelligent industrial node and a certain physical device, the intelligent industrial node corresponding to a certain physical device is the associated intelligent industrial node of any one intelligent industrial node, and mark the data flow directions of each intelligent industrial node through the mapping model of the intelligent factory.

[0088] The determination of the detection response resources of intelligent industrial nodes includes:

[0089] Determine the total amount of detection resources in the network detection framework, denoted as U;

[0090] Determine the data group of any one intelligent industrial node, and determine the detection response resources of the intelligent industrial node based on the data group of any one intelligent industrial node. The data group of any one intelligent industrial node includes: the number of associated intelligent industrial nodes, the data flow of each associated intelligent industrial node. Among them, the data flow of the intelligent industrial node uses time-sharing data acquisition, that is, the system selects a time period and takes the average real-time data flow within the same time period as the data flow of the intelligent industrial node; the data group is denoted as: {A, a1, a2,..., a A}, where A represents the number of associated intelligent industrial nodes, and a1, a2,..., a A represent the data flows of the 1st, 2nd,..., A-th associated intelligent industrial nodes respectively;

[0091] The system sets N data flow intervals that can cover the data flows of all associated intelligent industrial nodes. The endpoints of any one data flow interval include the previous one but not the following one, and build a response model to judge the contribution value of the data flow interval:

[0092]

[0093] Among them, S iRefers to the contribution value of data traffic interval i; F refers to the set of combined features of data traffic intervals; M refers to the feature subset that does not include data traffic interval i among the combined features of data traffic intervals; H refers to the set of features that does not include data traffic interval i among the combined features of data traffic intervals; |M| refers to the number of data traffic intervals existing in M; |F| refers to the total number of data traffic intervals; f(M +i ) refers to the model prediction value when only data traffic interval i is added to M; f(M) refers to the model prediction value when only M is used;

[0094] Determine the contribution values of all data traffic intervals. According to the data group of any intelligent industrial node, determine the sum of the contribution values of the data traffic intervals in the data group of any intelligent industrial node, which is denoted as the first detection response resource factor of any intelligent industrial node, and the corresponding number of associated intelligent industrial nodes is denoted as the second detection response resource factor. Based on the first detection response resource factor and the second detection response resource factor, form the detection response resource score of any intelligent industrial node:

[0095] T = K1 * V1 + K2 * V2

[0096] Among them, T represents the detection response resource score; K1 and K2 represent the coefficients set by the system; V1 and V2 represent the first detection response resource factor and the second detection response resource factor;

[0097] Calculate the detection response resource scores of all intelligent industrial nodes and sum them up. Form the proportion of the detection response resource of each intelligent industrial node in the sum of the detection response resource scores according to the detection response resource score of each intelligent industrial node.

[0098] It also includes issuing network detection response resource commands based on the determined proportion of the detection response resource of each intelligent industrial node to achieve network automated detection.

[0099] It should be noted that in this article, relational terms such as first and second are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any actual relationship or order between these entities or operations. Moreover, the term "including", "comprising" or any other variant thereof is intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements not only includes those elements, but also includes other elements not expressly listed, or also includes elements inherent to such process, method, article or device.

[0100] Finally, it should be noted that the above are only the preferred embodiments of the present invention and are not used to limit the present invention. Although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art can still modify the technical solutions described in the foregoing embodiments or perform equivalent replacements for some of the technical features. Any modifications, equivalent replacements, improvements, etc. made within the spirit and principle of the present invention shall be included within the protection scope of the present invention.

Claims

1. A data processing and execution system based on an intelligent industrial system, characterized in that, The system includes: A cloud processing module that forms a mapping model of an intelligent factory based on digital twin technology, monitors and processes the data flow of intelligent industrial nodes through the mapping model of the intelligent factory, and determines the proportion of detection response resources of intelligent industrial nodes; An edge operation module that integrates data acquisition, application control, and data optimization functional areas based on the real-time operating system of the intelligent factory, constructs a data storage container to store the transmission data of each functional area, and forms data interaction with the cloud processing module; A port control module that is applied to the production ports of the intelligent factory, integrates the control authorities of intelligent sensors, intelligent actuators, and digitalized equipment, and receives and identifies the commands of administrators; A network transfer module that constructs an IT / OT fusion network with a general IP protocol among the modules to achieve real-time data transmission between intelligent industrial nodes, receives the detection response resource commands of the cloud processing module to achieve network automated detection, and simultaneously sets up an early warning function system to achieve automated alarm during network failures.

2. The data processing system based on an intelligent industrial system according to claim 1, wherein The process of forming the mapping model of the intelligent factory based on digital twin technology includes: Install IoT sensors on the physical devices of the intelligent factory, collect real-time data through OPC UA and Modbus protocols, use 3D modeling tools to construct the models of the physical devices of the intelligent factory and the factory production lines, simulate the dynamic characteristics of the physical devices of the intelligent factory through a physical engine, and hierarchically construct digital twins from the single-device level to the workshop level and the factory level.

3. The data processing system based on the intelligent industrial system according to claim 2, characterized in that, The monitoring and processing of the data flow of intelligent industrial nodes through the mapping model of the intelligent factory includes: Create several intelligent industrial nodes based on the mapping model of the intelligent factory. Each intelligent industrial node corresponds to a type of physical device data in the intelligent factory. The physical device data refers to the production data of the physical devices of the intelligent factory. In different project processes, there are several associated intelligent industrial nodes corresponding to any one intelligent industrial node. If there is direct data interaction between the physical device corresponding to any one intelligent industrial node and a certain physical device, then the intelligent industrial node corresponding to a certain physical device is the associated intelligent industrial node of any one intelligent industrial node, and mark the data flow directions of each intelligent industrial node through the mapping model of the intelligent factory.

4. A data processing system based on an intelligent industrial system according to claim 3, characterized in that, The determination of the detection response resources of intelligent industrial nodes includes: Determine the total amount of detection resources in the network detection framework, denoted as U; Determine the data group of any intelligent industrial node, and determine the detection response resources of the intelligent industrial node based on the data group of any intelligent industrial node. The data group of any intelligent industrial node includes: the number of associated intelligent industrial nodes, and the data traffic of each associated intelligent industrial node. Among them, the data traffic of the intelligent industrial node adopts time-sharing data acquisition, that is, the system selects a time period, and takes the average real-time data traffic within the same time period as the data traffic of the intelligent industrial node. The data group is denoted as: {A, a1, a2, …, a A}, where A represents the number of associated intelligent industrial nodes, and a1, a2, …, a A respectively represent the data traffic of the 1st, 2nd, …, A-th associated intelligent industrial nodes; The system sets N data flow intervals that can cover the data flows of all associated intelligent industrial nodes. The endpoints of any one data flow interval include the previous one but not the following one, and construct a response model to judge the contribution value of the data flow interval: Among them, S refers to the contribution value of data traffic interval i; F refers to the set of combined characteristics of data traffic intervals; M refers to the subset of characteristics that do not include data traffic interval i among the combined characteristics of data traffic intervals; H refers to the set of characteristics that do not include data traffic interval i among the combined characteristics of data traffic intervals; |M| refers to the number of data traffic intervals existing in M; |F| refers to the total number of data traffic intervals; f(M +i ) refers to the model prediction value when only data traffic interval i is added to M; f(M) refers to the model prediction value when only M is used; Determine the contribution values of all data flow intervals. According to the data group of any one intelligent industrial node, determine the sum of the contribution values of the data flow intervals in the data group of any one intelligent industrial node, denoted as the first detection response resource factor of any one intelligent industrial node, and the number of corresponding associated intelligent industrial nodes is denoted as the second detection response resource factor. Form the detection response resource score of any one intelligent industrial node based on the first detection response resource factor and the second detection response resource factor: T = K1 * V1 + K2 * V2 Wherein, T represents the detection response resource score; K1 and K2 represent the coefficients set by the system; V1 and V2 represent the first detection response resource factor and the second detection response resource factor; Calculate the detection response resource scores of all intelligent industrial nodes, sum them up, and form the proportion of the detection response resources of each intelligent industrial node in the sum of the detection response resources scores.

5. The data processing system based on an intelligent industrial system according to claim 4, wherein, It further includes that the cloud processing module issues network detection response resource commands based on the determined proportion of the detection response resources of each intelligent industrial node to achieve network automated detection.

6. A data processing method based on an intelligent industrial system, characterized in that, The method includes: S1. Form a mapping model of the intelligent factory based on digital twin technology, monitor and process the data flow of intelligent industrial nodes through the mapping model of the intelligent factory, and determine the proportion of the detection response resources of intelligent industrial nodes; S2. Integrate the data acquisition, application control, and data optimization function areas based on the real-time operating system of the intelligent factory, construct a data storage container, store the transmission data of each function area, and form data interaction with the cloud processing module; S3. At the production port of the intelligent factory, integrate the control authorities of intelligent sensors, intelligent actuators, and digitalized equipment, and receive and identify the commands of the administrator; S4. Build an IT / OT fusion network with a general IP protocol among each module to achieve real-time data transmission between intelligent industrial nodes, receive the detection response resource commands of the cloud processing module to achieve network automated detection, and at the same time set up an early warning function system to achieve automated alarm during network failures.

7. A data processing method based on an intelligent industrial system according to claim 6, characterized in that The process of forming the mapping model of the intelligent factory based on digital twin technology includes: Install IoT sensors on the physical devices of the intelligent factory, collect real-time data through OPCUA and Modbus protocols, use 3D modeling tools to build models of the physical devices of the intelligent factory and the factory production lines, simulate the dynamic characteristics of the physical devices of the intelligent factory through a physical engine, and build digital twins hierarchically from the single-device level to the workshop level and the factory level.

8. A data processing method based on an intelligent industrial system according to claim 7, characterized in that The monitoring and processing of the data flow of intelligent industrial nodes through the mapping model of the intelligent factory includes: Create several intelligent industrial nodes based on the mapping model of the intelligent factory. Each intelligent industrial node corresponds to a type of physical device data in the intelligent factory. The physical device data refers to the production data of the physical devices of the intelligent factory. In different project processes, there are several associated intelligent industrial nodes corresponding to any one intelligent industrial node. If there is direct data interaction between the physical device corresponding to any one intelligent industrial node and a certain physical device, then the intelligent industrial node corresponding to a certain physical device is the associated intelligent industrial node of any one intelligent industrial node, and mark the data flow directions of each intelligent industrial node through the mapping model of the intelligent factory.

9. A data processing method based on an intelligent industrial system according to claim 8, characterized in that, The determination of the detection response resources of intelligent industrial nodes includes: Determine the total amount of detection resources in the network detection framework, denoted as U; Determine the data group of any intelligent industrial node, and determine the detection response resources of the intelligent industrial node based on the data group of any intelligent industrial node. The data group of any intelligent industrial node includes: the number of associated intelligent industrial nodes, and the data traffic of each associated intelligent industrial node. Among them, the data traffic of the intelligent industrial node adopts time-sharing data acquisition, that is, the system selects a time period, and takes the average real-time data traffic within the same time period as the data traffic of the intelligent industrial node; the data group is denoted as: {A, a1, a2, …, a A}, where A represents the number of associated intelligent industrial nodes, and a1, a2, …, a A represent the data traffic of the 1st, 2nd, …, A-th associated intelligent industrial nodes respectively; The system sets N data flow intervals that can cover the data flows of all associated intelligent industrial nodes. The endpoints of any one data flow interval include the previous one but not the following one, and construct a response model to judge the contribution value of the data flow interval: Among them, S i refers to the contribution value of data traffic interval i; F refers to the set of combined features of data traffic intervals; M refers to the feature subset that does not include data traffic interval i among the combined features of data traffic intervals; H refers to the set of features that do not include data traffic interval i among the combined features of data traffic intervals; |M| refers to the number of data traffic intervals existing in M; |F| refers to the total number of data traffic intervals; f(M +i ) refers to the model prediction value when only data traffic interval i is added to M; f(M) refers to the model prediction value when only M is used; Determine the contribution values of all data traffic intervals. Based on the data set of any intelligent industrial node, determine the sum of the contribution values of the data traffic intervals in the data set of any intelligent industrial node, which is denoted as the first detection response resource factor of any intelligent industrial node, and the corresponding number of associated intelligent industrial nodes is denoted as the second detection response resource factor. Form the detection response resource score of any intelligent industrial node based on the first detection response resource factor and the second detection response resource factor: T = K1 * V1 + K2 * V2 Among them, T represents the detection response resource score; K1 and K2 represent the coefficients set by the system; V1 and V2 represent the first detection response resource factor and the second detection response resource factor; Calculate the detection response resource scores of all intelligent industrial nodes and sum them up. Form the detection response resource proportion of each intelligent industrial node according to the proportion of the detection response resource score of each intelligent industrial node in the sum of the detection response resource scores.

10. A data processing method based on an intelligent industrial system according to claim 9, characterized in that, It also includes issuing a network detection response resource command based on the determined detection response resource proportion of each intelligent industrial node to achieve network automated detection.

Images