Industrial automatic control data processing system and method based on digital twin

Abstract

The present invention discloses an industrial automatic control data processing system and method based on digital twin, which belongs to the field of industrial automation control technology. The present invention establishes a connection between the edge side and the cloud center through the edge side management module, automatically collects industrial data through the edge collection node, and stores the collected industrial data in the edge device; sends a data request to the cloud center through the data mapping module, and the cloud center receives the industrial data uploaded by the edge side and maps the received industrial data in the digital space based on the digital twin technology; analyzes and feedbacks the data collection status of the edge side through the cloud processing module; updates the data collection strategy of the edge side according to the analysis results fed back by the cloud center through the collaborative control module, and transmits the updated data collection strategy to the edge device, and adjusts the data collection business of the edge collection node. The data in the industrial production process is processed more flexibly, which reduces the resource consumption of operation and maintenance.

Description

Technical Field

[0001] The present invention relates to the field of industrial automation control technology, and specifically to an industrial automatic control data processing system and method based on digital twins. Background Art

[0002] With the development of industrial informatization and the rise of Internet of Things technology, manufacturing has become one of the main application scenarios of digital twins, and the industrial digital twin industry has ushered in accelerated development. After manufacturing companies upload relevant data through Internet of Things technology, they can use digital twin technology to complete production, design, operation and maintenance, and thus achieve control over the entire life cycle of industrial manufacturing.

[0003] In the industrial production process, enterprises use data collection equipment to collect production-related data for a long time, transmit massive data and store it in real-time databases. In the existing technology, most edge computing digital collectors are used to store data on edge devices to reduce data transmission delays and resource consumption. However, the storage space and computing power of edge devices are limited, and they cannot support high-performance computing requirements, which limits the processing efficiency of industrial data. At the same time, the edge computing architecture involves a large number of decentralized devices. When working in collaboration with the cloud, the cloud center needs to receive massive edge-side data, which cannot achieve efficient data aggregation and data transmission. Summary of the invention

[0004] The purpose of the present invention is to provide an industrial automatic control data processing system and method based on digital twins to solve the problems raised in the above background technology.

[0005] In order to solve the above technical problems, the present invention provides the following technical solutions: a method for processing industrial automatic control data based on digital twins, comprising the following steps:

[0006] Step S100: Establish a connection between the edge side and the cloud center, automatically collect industrial data through the edge collection node on the edge side, and store the industrial data collected by the edge collection node to the edge device;

[0007] Step S200: Sending a data request to the cloud center through the edge device. After the cloud center receives the industrial data uploaded by the edge side, it maps the received industrial data in the digital space based on the digital twin technology;

[0008] Step S300: Based on the digital space, the data collection status of the edge side is analyzed through the cloud center, and feedback is given to the data collection strategy of the edge side;

[0009] Step S400: Update the data collection strategy on the edge side according to the analysis results fed back by the cloud center, transmit the updated data collection strategy to the edge device, and adjust the data collection service of the edge collection node.

[0010] Furthermore, in step S100, software programming is performed on the edge acquisition node on the edge side to facilitate automatic data collection and transmission; the network settings of the edge acquisition node are configured, including setting the IP address, subnet mask and gateway. The edge acquisition node is the source of data. The edge acquisition node sends the collected industrial data to the edge device. The edge device can send instructions to the edge acquisition node based on the analysis results, and process and forward the received industrial data; a local storage system is configured on the edge device so that the data collected by the edge acquisition node can be effectively stored; a data synchronization mechanism is established to synchronize the data stored in the edge device to the cloud center to maintain the consistency and integrity of the data points; a connection is established between the edge side and the cloud center to ensure that the edge device can communicate with the cloud center stably;

[0011] The first data processing is performed on the edge device to monitor the industrial data in real time; the first data processing is used to analyze the industrial data stream in real time, detect abnormalities or key events of the industrial data, trigger alarms or automatic responses, summarize the industrial data uploaded by each edge collection node, and generate an edge side data set, denoted as BS(i)={B e ||e∈[1,E i ]};

[0012] Among them, B e Indicates the e-th industrial data uploaded by the i-th edge collection node, E i It represents the total amount of uploaded industrial data corresponding to the i-th edge collection node, i∈[1,n], and n represents the total number of edge collection nodes.

[0013] Furthermore, the step S200 specifically includes the following steps:

[0014] S201: The edge device sends a data request to the cloud center according to the preset operation logic, and the request includes the type of data to be uploaded, the upload frequency and the amount of data; the cloud center has a digital twin model, which contains all the parameters and characteristics of industrial production; the cloud center obtains the edge-side data set uploaded by the edge device through the message queue, and maps the received industrial data on the digital twin model based on the digital twin technology to achieve the synchronization of the actual collected data and the parameters of the digital space; the changed data set of the digital twin model is obtained, which is recorded as Alter = {A j |j∈[1,J]},A j represents the mapping data value of the jth changed element in the changed data set, and J represents the total number of changed elements;

[0015] S202: Obtain the change data set corresponding to the digital twin model at T time nodes and generate the function In the function, at any time node t, there is a corresponding mapping data value of the jth changed element. Represents the mapping data value of the jth changed element in the changed data set corresponding to the tth time node, t∈[1,T];

[0016] S203: Analyze the fluctuation of each changed element in the changed data set, and calculate the fluctuation index Z(j) of the j-th changed element according to the following formula:

[0017]

[0018] in, Representation function The second-order derivative value at time node t; the fluctuation of the change element is judged according to the fluctuation index Z(j) of the j-th change element. Specifically, when Z(j)≥r, it is determined that the j-th change element has a high fluctuation within T time nodes; r is the fluctuation threshold pre-set by relevant personnel according to the actual function value;

[0019] The above method can analyze the changes of each change element in the change data set of the digital twin model, which helps to evaluate the operating stability of the model, so as to make a more accurate analysis of the industrial data collection strategy in the subsequent steps.

[0020] Furthermore, in step S300, the cloud center has a cloud processor for analyzing the data collection status of the edge side, which specifically includes the following steps:

[0021] S301: Mark the changed element with high fluctuation as the first element, and mark the changed element without high fluctuation as the second element; record the proportion of industrial data corresponding to the first element in the edge side data set as K1, and record the proportion of industrial data corresponding to the second element in the edge side data set as K2, K1+K2=1;

[0022] S302: Calculate the data collection status score P of the current edge side according to the following formula:

[0023]

[0024] Among them, G represents the standard storage capacity of the edge device, μ represents the reference score of the second element, θ1 and θ2 are weight coefficients, and the parameter table is pre-set by relevant personnel and stored in the cloud database;

[0025] Feedback is provided on the data collection strategy of the edge side according to the data collection status score of the edge side. Specifically, when P ≥ a, it is determined that the current data collection strategy of the edge side does not need to be adjusted, and the current strategy continues to be used; when P < a, it is determined that the current data collection strategy of the edge side needs to be adjusted, and the adjustment requirement is fed back to the management module of the cloud center, and step S400 is executed.

[0026] Furthermore, in the step S400, according to the analysis result fed back by the cloud center, the data collection strategy of the edge side is updated, which specifically includes the following steps:

[0027] S401: Set the filtering time for the edge side data set according to the fluctuation peak value of each change element in the change data set, transmit the updated data collection strategy of the cloud center to the edge device, the edge device extracts the edge collection node code to which the industrial data corresponding to the second element belongs, and marks the extracted edge collection node code;

[0028] S402: Manage the marked edge collection node codes through the edge device; when the edge device summarizes the industrial data uploaded by each edge collection node, store the industrial data uploaded by the marked edge collection node codes in the edge device, filter the edge side data set generated by the industrial data uploaded by the marked edge collection node codes, reduce the data transmission volume between the edge device and the cloud; adjust the data collection service of the edge collection node.

[0029] An industrial automatic control data processing system based on digital twin, the system includes: an edge side management module, a data mapping module, a cloud processing module and a collaborative control module;

[0030] The edge side management module is used to establish a connection between the edge side and the cloud center, automatically collect industrial data through the edge collection nodes on the edge side, and store the industrial data collected by the edge collection nodes in the edge device;

[0031] The data mapping module is used to send a data request to the cloud center through the edge device, the cloud center receives the industrial data uploaded by the edge side, and maps the received industrial data in the digital space based on digital twin technology;

[0032] The cloud processing module is used to analyze the data collection status of the edge side and provide feedback on the data collection strategy of the edge side;

[0033] The collaborative control module updates the data collection strategy of the edge side according to the analysis result fed back by the cloud center, and transmits the updated data collection strategy to the edge device to adjust the data collection service of the edge collection node.

[0034] Further, the edge side management module includes an edge collection node and an edge device management unit;

[0035] The edge collection node is used to automatically collect industrial data and send it to the edge device, and is controlled by the instructions of the edge device;

[0036] The edge device management unit is used to manage the configuration and business data of the edge device, establish a connection between the edge side and the cloud center, and ensure that the edge device can communicate stably with the cloud center.

[0037] Further, the data mapping module includes a data transmission unit and a digital space update unit;

[0038] The data transmission unit is used to realize data transmission between the edge collection node and the edge device, and data transmission between the edge device and the cloud center;

[0039] The digital space update unit updates the digital twin model in the digital space based on the digital twin technology, maps the industrial data uploaded by the edge device on the digital twin model, and updates the parameters contained in the digital twin model.

[0040] Furthermore, the cloud processing module includes a cloud processor and a data feedback unit;

[0041] The cloud processor exists in the cloud center and is used to analyze the data collection status of the edge side. The data feedback unit is used to provide feedback on the data collection strategy of the edge side based on the cloud processor's scoring result of the data collection status of the edge side. When it is determined that the current data collection strategy of the edge side needs to be adjusted, the adjustment requirement is fed back to the collaborative control module.

[0042] Further, the collaborative control module includes a strategy updating unit and a device adjustment unit;

[0043] The strategy updating unit is used to set the filtering time for the edge side data set according to the fluctuation peak value of each changed element in the changed data set, and transmit the data collection strategy updated by the cloud center to the edge device;

[0044] The device adjustment unit manages the marked edge acquisition node codes through the edge device; when the edge device summarizes the industrial data uploaded by each edge acquisition node, the industrial data uploaded by the marked edge acquisition node codes are stored in the edge device, and the edge side data set generated by the industrial data uploaded by the marked edge acquisition node codes is filtered to reduce the amount of data transmission between the edge device and the cloud.

[0045] Compared with the prior art, the beneficial effects achieved by the present invention are:

[0046] Through automated collection and preliminary analysis on the edge side, the present invention can monitor industrial processes in real time and promptly discover potential problems, thereby achieving rapid response and optimization; pre-processing and analyzing data through edge devices, and transmitting filtered industrial data to the cloud, reducing the amount of data transmission and lowering network bandwidth requirements.

[0047] Based on digital twin technology, the present invention creates virtual copies of physical equipment in the cloud, simulates and analyzes industrial production through digital twin models, and dynamically adjusts the data collection strategy on the edge side according to the data uploaded by the edge device, thereby reducing the consumption of cloud storage and cloud resources, and more flexibly processing data in the industrial production process to adapt to different business needs and environmental changes. It is particularly suitable for industrial application scenarios that require low-latency feedback.

[0048] The present invention monitors the operating status of edge devices in real time through the cloud center, realizes the collaborative work between the cloud and the edge side, forms a two-way interactive and efficient data processing mechanism, can remotely and automatically adjust the data collection strategy on the edge side, reduces the need for manual intervention, realizes centralized management and control of the entire system, and reduces the resource consumption of system operation and maintenance. BRIEF DESCRIPTION OF THE DRAWINGS

[0049] The accompanying drawings are used to provide a further understanding of the present invention and constitute a part of the specification. Together with the embodiments of the present invention, they are used to explain the present invention and do not constitute a limitation of the present invention. In the accompanying drawings:

[0050] Figure 1 It is a structural schematic diagram of an industrial automatic control data processing system based on digital twins of the present invention;

[0051] Figure 2 It is a schematic diagram of the steps of an industrial automatic control data processing method based on digital twins of the present invention. DETAILED DESCRIPTION

[0052] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0053] See also Figure 1 ,In the first embodiment of the present invention, an industrial automatic control data processing system based on digital twin is provided, comprising: an edge-side management module, a data mapping module, a cloud processing module and a collaborative control module;

[0054] The edge management module is used to establish a connection between the edge and the cloud center, automatically collect industrial data through the edge collection node on the edge, and store the industrial data collected by the edge collection node to the edge device; it includes an edge collection node and an edge device management unit;

[0055] Edge collection nodes are used to automatically collect industrial data and send it to edge devices, and are controlled by instructions from edge devices;

[0056] The edge device management unit is used to manage the configuration and business data of edge devices, establish a connection between the edge side and the cloud center, and ensure that the edge devices can communicate stably with the cloud center.

[0057] The data mapping module is used to send data requests to the cloud center through the edge device. The cloud center receives the industrial data uploaded by the edge side and maps the received industrial data in the digital space based on the digital twin technology. It includes a data transmission unit and a digital space update unit.

[0058] The data transmission unit is used to realize data transmission between edge collection nodes and edge devices, and data transmission between edge devices and cloud centers;

[0059] The digital space update unit updates the digital twin model in the digital space based on the digital twin technology, maps the industrial data uploaded by the edge device on the digital twin model, and updates the parameters contained in the digital twin model.

[0060] The cloud processing module is used to analyze the data collection status of the edge side and provide feedback on the data collection strategy of the edge side; it includes a cloud processor and a data feedback unit;

[0061] The cloud processor is used to analyze the data collection status of the edge side and exists in the cloud center. In the present invention, the cloud processor refers to the hardware and corresponding software system that perform data processing tasks in the cloud computing environment. The current edge side data collection status score P is calculated according to the following formula:

[0062]

[0063] Among them, E i represents the total amount of uploaded industrial data corresponding to the i-th edge collection node, i∈[1,n], n represents the total number of edge collection nodes; the change element without high fluctuation is marked as the second element, and the proportion of industrial data corresponding to the second element in the edge side data set is recorded as K2; G represents the standard storage capacity of the edge device, μ represents the reference score of the second element, θ1 and θ2 are weight coefficients, and the parameter table is pre-set by relevant personnel and stored in the cloud database;

[0064] The data feedback unit is used to provide feedback on the data collection strategy on the edge side according to the cloud processor's scoring result on the data collection status on the edge side. Specifically, when P≥a, it is determined that the current data collection strategy on the edge side does not need to be adjusted and the current strategy continues to be used; when P<a, it is determined that the current data collection strategy on the edge side needs to be adjusted. When it is determined that the current data collection strategy on the edge side needs to be adjusted, the adjustment requirement is fed back to the collaborative control module.

[0065] The collaborative control module updates the data collection strategy on the edge side according to the analysis results fed back by the cloud center, transmits the updated data collection strategy to the edge device, and adjusts the data collection business of the edge collection node; it includes a strategy update unit and a device adjustment unit;

[0066] The strategy update unit is used to set the filtering time for the edge side data set according to the fluctuation peak value of each changed element in the changed data set, and transmit the data collection strategy updated by the cloud center to the edge device;

[0067] The device adjustment unit manages the marked edge acquisition node codes through the edge device; when the edge device summarizes the industrial data uploaded by each edge acquisition node, the industrial data uploaded by the marked edge acquisition node codes are stored in the edge device, and the edge-side data set generated by the industrial data uploaded by the marked edge acquisition node codes is filtered to reduce the amount of data transmission between the edge device and the cloud.

[0068] See also Figure 2 In the second embodiment, a digital twin-based industrial automatic control data processing system and method are provided, including:

[0069] Step S100: Perform software programming on the edge acquisition node on the edge side to facilitate automatic data collection and transmission; configure the network settings of the edge acquisition node, including setting the IP address, subnet mask and gateway. The edge acquisition node is the source of data. The edge acquisition node sends the collected industrial data to the edge device. The edge device can send instructions to the edge acquisition node based on the analysis results, and process and forward the received industrial data; configure the local storage system on the edge device so that the data collected by the edge acquisition node can be effectively stored; establish a data synchronization mechanism to synchronize the data stored in the edge device to the cloud center to maintain the consistency and integrity of the data points; establish a connection between the edge side and the cloud center to ensure that the edge device can communicate with the cloud center stably; for different industrial equipment and sensors, adjust the edge acquisition node to support multiple communication protocols, achieve seamless conversion between protocols, and ensure that the data can be correctly interpreted and transmitted.

[0070] The first data processing is performed on the edge device to monitor the industrial data in real time; the first data processing is used to analyze the industrial data stream in real time, detect abnormalities or key events of the industrial data, trigger alarms or automatic responses, summarize the industrial data uploaded by each edge collection node, and generate an edge side data set, denoted as BS(i)={B e |e∈[1,E i ]};

[0071] Among them, B e Indicates the e-th industrial data uploaded by the i-th edge collection node, E i It represents the total amount of uploaded industrial data corresponding to the i-th edge collection node, i∈[1,n], and n represents the total number of edge collection nodes.

[0072] Exemplarily, the first data processing is used to monitor data collection operations and edge device status in real time, locate and automatically handle faults, and when a fault that cannot be handled automatically is encountered, the data collection strategy is reconfigured so that the edge collection node bypasses the fault point to complete the data collection operation.

[0073] Step S200: Sending a data request to the cloud center through the edge device. After the cloud center receives the industrial data uploaded by the edge side, it maps the received industrial data in the digital space based on the digital twin technology;

[0074] S201: The edge device sends a data request to the cloud center according to the preset operation logic, and the request includes the type of data to be uploaded, the upload frequency and the amount of data; the cloud center has a digital twin model, which contains all the parameters and characteristics of industrial production; the cloud center obtains the edge-side data set uploaded by the edge device through the message queue, and maps the received industrial data on the digital twin model based on the digital twin technology to achieve the synchronization of the actual collected data and the parameters of the digital space; the changed data set of the digital twin model is obtained, which is recorded as Alter = {A j |j∈[1,J]},A j represents the mapping data value of the jth changed element in the changed data set, and J represents the total number of changed elements;

[0075] S202: Obtain the change data set corresponding to the digital twin model at T time nodes and generate the function For example, the function It can be generated through the following steps: clean the acquired data, remove noise and outliers, and fill in missing values; select linear function or exponential function as the function form to approximate the data trend; estimate the parameter value of the function through regression analysis or machine learning algorithm; construct the function according to the selected function form and parameter value, and adjust the function form and parameters through cross-validation;

[0076] In the function, at any time node t, there is a corresponding mapping data value of the jth changed element. Represents the mapping data value of the jth changed element in the changed data set corresponding to the tth time node, t∈[1,T];

[0077] S203: Analyze the fluctuation of each changed element in the changed data set, and calculate the fluctuation index Z(j) of the j-th changed element according to the following formula:

[0078]

[0079] in, Representation function The second-order derivative value at time node t; the fluctuation of the change element is judged according to the fluctuation index Z(j) of the j-th change element. Specifically, when Z(j)≥r, it is determined that the j-th change element has a high fluctuation within T time nodes; r is the fluctuation threshold pre-set by relevant personnel according to the actual function value;

[0080] The above method can analyze the changes of each change element in the change data set of the digital twin model, which helps to evaluate the operating stability of the model, so as to make a more accurate analysis of the industrial data collection strategy in the subsequent steps.

[0081] Step S300: Based on the digital space, the data collection status of the edge side is analyzed through the cloud center, and the data collection strategy of the edge side is fed back; the cloud center has a cloud processor for analyzing the data collection status of the edge side. In the present invention, the cloud processor refers to the hardware and corresponding software system that performs data processing tasks in the cloud computing environment, which specifically includes the following steps:

[0082] S301: Mark the changed element with high fluctuation as the first element, and mark the changed element without high fluctuation as the second element; record the proportion of industrial data corresponding to the first element in the edge side data set as K1, and record the proportion of industrial data corresponding to the second element in the edge side data set as K2, K1+K2=1;

[0083] S302: Calculate the data collection status score P of the current edge side according to the following formula:

[0084]

[0085] Among them, G represents the standard storage capacity of the edge device, μ represents the reference score of the second element, θ1 and θ2 are weight coefficients, and the parameter table is pre-set by relevant personnel and stored in the cloud database; according to the processing power and storage capacity of the edge device, data collection tasks are reasonably allocated to avoid excessive concentration or waste of resources and ensure the stable operation of the collection operation.

[0086] Feedback is provided to the data collection strategy on the edge side based on the data collection status score on the edge side. Specifically, when P≥a, it is determined that the current data collection strategy on the edge side does not need to be adjusted, and the current strategy continues to be used; when P<a, it is determined that the current data collection strategy on the edge side needs to be adjusted, and the adjustment requirements are fed back to the management module of the cloud center, and step S400 is executed.

[0087] Step S400: Update the data collection strategy on the edge side according to the analysis results fed back by the cloud center, transmit the updated data collection strategy to the edge device, and adjust the data collection service of the edge collection node;

[0088] S401: Obtain the fluctuation peak value of each changed element in the changed data set by using a moving window method or a threshold detection method, and set a filtering time for the edge side data set according to the fluctuation peak value of each changed element in the changed data set;

[0089] The average interval time between fluctuation peaks is used as the filtering operation interval, and the data collection strategy updated by the cloud center is transmitted to the edge device. The edge device extracts the edge collection node code corresponding to the second element and marks the extracted edge collection node code.

[0090] S402: Manage the marked edge collection node codes through edge devices, and automatically deploy the updated data collection strategy to the edge collection nodes, thereby reducing the time cost of manual configuration and the risk of manual operation errors.

[0091] When the edge device aggregates the industrial data uploaded by each edge collection node, the industrial data uploaded by the marked edge collection node code is stored in the edge device, and the edge-side data set generated by the industrial data uploaded by the marked edge collection node code is filtered to reduce the amount of data transmission between the edge device and the cloud; the data collection business of the edge collection node is adjusted;

[0092] For example, key parameters need to be collected at a high frequency to ensure that the cloud center can obtain real-time dynamics of key parameters. For less sensitive information, the collection frequency can be reduced based on the analysis results of the cloud center to save communication resources. By identifying and prioritizing the collection of key data sources in industrial production and eliminating redundant data sources, the relevance and effectiveness of industrial data can be ensured.

[0093] It should be noted that, in this article, relational terms such as first and second, etc. are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device.

[0094] Finally, it should be noted that the above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art can still modify the technical solutions described in the aforementioned embodiments or replace some of the technical features therein by equivalents. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention shall be included in the protection scope of the present invention.

Claims

1. A method for processing industrial automatic control data based on digital twins, characterized in that: The following steps are involved: Step S100: Establish a connection between the edge side and the cloud center, automatically collect industrial data through the edge collection node on the edge side, and store the industrial data collected by the edge collection node to the edge device; Step S200: Sending a data request to the cloud center through the edge device. After the cloud center receives the industrial data uploaded by the edge side, it maps the received industrial data in the digital space based on the digital twin technology; Step S300: Based on the digital space, the data collection status of the edge side is analyzed through the cloud center, and feedback is given to the data collection strategy of the edge side; Step S400: Update the data collection strategy on the edge side according to the analysis results fed back by the cloud center, transmit the updated data collection strategy to the edge device, and adjust the data collection service of the edge collection node; The step S200 specifically includes the following steps: S201: The edge device sends a data request to the cloud center according to the preset operation logic, and the request includes the type of data to be uploaded, the upload frequency and the amount of data; the cloud center has a digital twin model, which contains all the parameters of industrial production; the cloud center obtains the edge-side data set uploaded by the edge device through the message queue, and maps the received industrial data to the digital twin model based on the digital twin technology; the changed data set of the digital twin model is obtained, which is recorded as Alter = {A j |j∈[1,J]},A j represents the mapping data value of the jth changed element in the changed data set, and J represents the total number of changed elements; S202: Obtain the change data set corresponding to the digital twin model at T time nodes and generate the function In the function, at any time node t, there is a corresponding mapping data value of the jth changed element. Represents the mapping data value of the jth changed element in the changed data set corresponding to the tth time node, t∈[1,T]; S203: Analyze the fluctuation of each changed element in the changed data set, and calculate the fluctuation index Z(j) of the j-th changed element according to the following formula: in, Representation function The second-order derivative value of at time node t; the fluctuation of the change element is judged according to the fluctuation index Z(j) of the j-th change element. Specifically, when Z(j)≥r, it is determined that the j-th change element has a high fluctuation within T time nodes; r is the fluctuation threshold set in advance by relevant personnel.

2. According to the method for processing industrial automatic control data based on digital twins according to claim 1, it is characterized in that: In the step S100, software programming is performed on the edge acquisition node on the edge side, and the network settings of the edge acquisition node are configured, including setting the IP address, subnet mask and gateway; the collected industrial data is sent to the edge device through the edge acquisition node; a local storage system is configured on the edge device, a data synchronization mechanism is established, the data stored in the edge device is synchronized to the cloud center, and a connection between the edge side and the cloud center is established; The first data processing is performed on the edge device to monitor the industrial data in real time. The first data processing is used to analyze the industrial data stream in real time, summarize the industrial data uploaded by each edge collection node, and generate an edge side data set, which is recorded as BS(i)={B e |e∈[1,E i ]}; Among them, B e Indicates the e-th industrial data uploaded by the i-th edge collection node, E i It represents the total amount of uploaded industrial data corresponding to the i-th edge collection node, i∈[1,n], and n represents the total number of edge collection nodes.

3. The industrial automatic control data processing method based on digital twin according to claim 2 is characterized in that: In step S300, the cloud center has a cloud processor for analyzing the data collection status of the edge side, which specifically includes the following steps: S301: Mark the changed element with high fluctuation as the first element, and mark the changed element without high fluctuation as the second element; record the proportion of industrial data corresponding to the first element in the edge side data set as K1, and record the proportion of industrial data corresponding to the second element in the edge side data set as K2; S302: Calculate the data collection status score P of the current edge side according to the following formula: Among them, G represents the standard storage capacity of the edge device, μ represents the reference score of the second element, θ1 and θ2 are weight coefficients; when P≥a, it is determined that the current data collection strategy on the edge side does not need to be adjusted, and the current strategy continues to be used; when P<a, it is determined that the current data collection strategy on the edge side needs to be adjusted, and the adjustment requirements are fed back to the management module of the cloud center, and step S400 is executed.

4. The industrial automatic control data processing method based on digital twin according to claim 3 is characterized in that: In step S400, the data collection strategy on the edge side is updated according to the analysis results fed back by the cloud center, which specifically includes the following steps: S401: according to the fluctuation peak value of each changed element in the changed data set, set the filtering time for the edge side data set, transmit the updated data collection strategy of the cloud center to the edge device, and the edge device extracts the edge collection node code of the industrial data corresponding to the second element, and marks the extracted edge collection node code; S402: Manage the marked edge acquisition node codes through the edge device; when the edge device aggregates the industrial data uploaded by each edge acquisition node, store the industrial data uploaded by the marked edge acquisition node codes in the edge device, and filter the edge-side data set generated by the industrial data uploaded by the marked edge acquisition node codes.

5. An industrial automatic control data processing system based on digital twins, executing an industrial automatic control data processing method based on digital twins as claimed in any one of claims 1 to 4, characterized in that: The system includes: an edge-side management module, a data mapping module, a cloud processing module and a collaborative control module; The edge side management module is used to establish a connection between the edge side and the cloud center, automatically collect industrial data through the edge collection node on the edge side, and store the industrial data collected by the edge collection node to the edge device; The data mapping module is used to send data requests to the cloud center through the edge device, and the cloud center receives the industrial data uploaded by the edge side and maps the received industrial data in the digital space based on the digital twin technology; The cloud processing module is used to analyze the data collection status of the edge side and provide feedback on the data collection strategy of the edge side; The collaborative control module updates the data collection strategy on the edge side according to the analysis results fed back by the cloud center, transmits the updated data collection strategy to the edge device, and adjusts the data collection service of the edge collection node.

6. The industrial automatic control data processing system based on digital twin according to claim 5 is characterized in that: The edge side management module includes an edge collection node and an edge device management unit; The edge collection node is used to automatically collect industrial data and send it to the edge device, and is controlled by the instructions of the edge device; The edge device management unit is used to manage the configuration and business data of the edge device and establish a connection between the edge side and the cloud center.

7. The industrial automatic control data processing system based on digital twin according to claim 5 is characterized in that: The data mapping module includes a data transmission unit and a digital space update unit; The data transmission unit is used to realize data transmission between the edge collection node and the edge device, and data transmission between the edge device and the cloud center; The digital space update unit updates the digital twin model in the digital space based on the digital twin technology, maps the industrial data uploaded by the edge device on the digital twin model, and updates the parameters contained in the digital twin model.

8. The industrial automatic control data processing system based on digital twin according to claim 5 is characterized in that: The cloud processing module includes a cloud processor and a data feedback unit; The cloud processor exists in the cloud center and is used to analyze the data collection status of the edge side; the data feedback unit is used to provide feedback on the data collection strategy of the edge side based on the cloud processor's scoring result of the data collection status of the edge side. When it is determined that the current data collection strategy of the edge side needs to be adjusted, the adjustment requirement is fed back to the collaborative control module.

9. The industrial automatic control data processing system based on digital twin according to claim 5 is characterized in that: The collaborative control module includes a strategy updating unit and a device adjustment unit; The strategy updating unit is used to set the filtering time for the edge side data set according to the fluctuation peak value of each changed element in the changed data set, and transmit the data collection strategy updated by the cloud center to the edge device; The device adjustment unit manages the marked edge acquisition node codes through the edge device; when the edge device summarizes the industrial data uploaded by each edge acquisition node, the industrial data uploaded by the marked edge acquisition node codes are stored in the edge device, and the edge side data set generated by filtering the industrial data uploaded by the marked edge acquisition node codes.

Images