Data collection method, device, storage medium and electronic equipment

By using the topology structure and data calculation method of pipe storage data without installing sensors, real-time and accurate collection and early warning of pipe storage data is solved, and the problems of low data acquisition efficiency and high equipment transformation cost are improved. Efficiency and accuracy.

CN114217586BActive Publication Date: 2024-11-12SHAOXING SMART CITY GRP CO LTD
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202111523174.2
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2021-12-13
Publication Date
2024-11-12
Estimated Expiration
2041-12-13

AI Technical Summary

Technical Problem

In the scenario of data acquisition of pipe storage, it is difficult to install sensors inside the pipeline, resulting in low data acquisition efficiency and high equipment transformation costs. The existing technology relies on manual prediction, making it difficult to ensure the accuracy and real-timeness of the data.

Method used

By calculating based on the topology structure and endpoint data of the pipe storage sensor without installing it, real-time and accurate collection of pipe storage data is achieved, and the industrial data of the target equipment is used to forward data to the cloud platform, and based on historical data Train the fluid prediction model and calculate subsequent data in advance.

Benefits of technology

This reduces the equipment transformation cost under Guanhui data collection, improves data acquisition efficiency, realizes real-time monitoring and accurate early warning of Guanhui data, and ensures data accuracy and real-timeness.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN114217586B_ABST
    Figure CN114217586B_ABST
Patent Text Reader

Abstract

The present disclosure relates to a data collection method, device, storage medium and electronic device to realize the collection of industrial manifold data without installing a manifold sensor. The method includes: receiving industrial data sent by a target device in a manifold scenario, the industrial data including data collected by the target device through a sensor; obtaining a manifold topology structure corresponding to the manifold scenario, the manifold topology structure is obtained by scanning the actual manifold in the manifold scenario; based on the industrial data and the manifold topology structure, determining the industrial data of the manifold node and the device node other than the target device in the manifold scenario; forwarding the industrial data of the manifold node and the device node to a cloud platform.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present disclosure relates to the field of industrial technology, and in particular, to a data collection method, device, storage medium and electronic device. Background Art

[0002] With the rapid development of industrial Internet technology, more and more intelligent applications for different industrial processes such as predictive maintenance, production efficiency optimization, safety assurance, and production optimization are being applied to industrial enterprises. The premise of building intelligent applications is to be able to collect industrial data.

[0003] Related technologies mainly collect industrial data through different types of industrial sensors. In the case of collecting manifold data, it is difficult to install sensors inside the pipeline, and due to the large number of pipelines, many sensors need to be installed, so it is difficult to collect manifold data through sensors, which affects the efficiency of manifold data collection. Summary of the invention

[0004] The purpose of the present disclosure is to provide a data acquisition method, device, storage medium and electronic equipment, so as to realize real-time and accurate collection of manifold data by calculating based on the manifold topology structure and manifold endpoint data without installing a manifold sensor, reduce the equipment modification cost under manifold data collection, and improve the efficiency of manifold data collection.

[0005] In order to achieve the above-mentioned object, in a first aspect, the present disclosure provides a method for receiving industrial data sent by a target device in a manifold scenario, wherein the industrial data includes data collected by the target device through a sensor;

[0006] Acquire a manifold topology structure corresponding to the manifold scene, wherein the manifold topology structure is obtained by scanning an actual manifold in the manifold scene;

[0007] Based on the industrial data and the manifold topology, determine the industrial data of the manifold node and the device nodes other than the target device in the manifold scenario;

[0008] The industrial data of the manifold node and the device node are forwarded to the cloud platform.

[0009] Optionally, determining the industrial data of the manifold node and the device nodes other than the target device in the manifold scenario based on the industrial data and the manifold topology structure includes:

[0010] The target device is used as the initial starting point device node, and the following process is executed cyclically:

[0011] Based on the identification information of the starting point device node, a target manifold line with the starting point device node as a starting point is determined in the manifold topology structure, and based on the industrial data of the starting point device node, the industrial data of the intermediate manifold nodes and the device end points included in the target manifold line are determined, wherein the industrial data includes identification information for uniquely identifying the target device, and each node in the manifold topology structure has identification information for uniquely identifying the node;

[0012] If the device endpoint is not the target device endpoint in the manifold scenario, the device endpoint is used as a new starting device node until the device endpoint becomes the target device endpoint in the manifold scenario.

[0013] Optionally, there are multiple target devices, and determining, based on the identification information of the starting point device node, in the manifold topology structure, a target manifold line with the starting point device node as a starting point includes:

[0014] In the case where a plurality of the target devices are used as starting device nodes, based on the identification information of the starting device nodes, a plurality of target manifold lines having the starting device nodes as starting points are determined in the manifold topology structure;

[0015] The step of determining the industrial data of the intermediate manifold nodes and the equipment end points included in the target manifold line based on the industrial data of the starting point equipment node includes:

[0016] When the equipment end points of the multiple target manifold lines are the same, the industrial data of the starting device node is used as the industrial data of the intermediate manifold node in the same manifold line as the starting device node, and the industrial data of the end device is determined based on the industrial data of the multiple starting device nodes, wherein the industrial data is the displacement or operation time.

[0017] Optionally, the industrial data includes a timestamp of the starting device node, and determining the industrial data of the intermediate manifold node and the device end point included in the target manifold line based on the industrial data of the starting device node includes:

[0018] In the target manifold line, determining a first distance between the intermediate manifold node and the starting device node, and determining a second distance between the device end point and the starting device node;

[0019] Calculating a first flow time based on the flow velocity of the fluid in the target manifold line and the first distance, and determining a timestamp of the intermediate manifold node based on the timestamp of the starting device node and the first flow time;

[0020] A second flow time is calculated based on the flow velocity of the fluid in the target manifold line and the second distance, and a timestamp of the device endpoint is determined based on the timestamp of the start device node and the second flow time.

[0021] Optionally, the method further comprises:

[0022] Acquire historical industrial data in the manifold scenario, and determine first fluid data and second fluid data in the historical industrial data, wherein the first fluid data is fluid composition data acquired from the target device, and the second fluid data includes fluid index data in the manifold scenario or fluid composition data in devices and manifolds other than the target device in the manifold scenario;

[0023] Training a fluid prediction model based on the first fluid data and the second fluid data, wherein the fluid prediction model is used to output fluid index data or fluid composition data in corresponding equipment and manifolds according to input fluid composition data obtained from the target equipment;

[0024] The step of determining the industrial data of the intermediate manifold nodes and the equipment end points included in the target manifold line based on the industrial data of the starting point equipment node includes:

[0025] In the industrial data of the starting point equipment node, target fluid data of the same type as the first fluid data is determined, and the target fluid data is input into the trained fluid prediction model to obtain the fluid index data corresponding to the target manifold line or the fluid composition data corresponding to the intermediate manifold nodes and equipment end points included in the target manifold line.

[0026] Optionally, the manifold topology is obtained by:

[0027] receiving actual manifold information scanned in the manifold scene and sent by a scanning terminal;

[0028] Determine endpoint position information and fluid direction marked for each node in the actual manifold information, wherein each node has identification information for uniquely identifying the node, and the endpoint position information is used to indicate that the node is one of a starting point, an intermediate node, and an end point;

[0029] Based on the endpoint position information and the fluid direction corresponding to each node, a manifold topology structure in the form of a two-dimensional table is established, wherein the data in the two-dimensional table is key-value pair data, the key in the key-value pair data is used to represent the endpoint position information of the node, and the value in the key-value pair data is used to represent the identification information of the node.

[0030] Optionally, the receiving industrial data sent by the target device in the manifold scenario includes:

[0031] Receiving industrial data sent by a target device in a manifold scenario through a message queue or a platform gateway of the cloud platform;

[0032] The forwarding of the industrial data of the manifold node and the device node to the cloud platform includes:

[0033] If industrial data sent by a target device in a manifold scenario is received through the message queue, the industrial data of the manifold node and the device node are forwarded to the message queue;

[0034] If the industrial data sent by the target device in the manifold scenario is received through the platform gateway, the industrial data of the manifold node and the device node are forwarded to the platform gateway.

[0035] In a second aspect, the present disclosure provides a data collection device, the device comprising:

[0036] A first receiving module, configured to receive industrial data sent by a target device in a manifold scenario, wherein the industrial data includes data collected by the target device through a sensor;

[0037] A first acquisition module is used to acquire a manifold topology structure corresponding to the manifold scene, wherein the manifold topology structure is obtained by scanning an actual manifold in the manifold scene;

[0038] A first determination module is used to determine the industrial data of the manifold node and the device nodes other than the target device in the manifold scenario based on the industrial data and the manifold topology structure;

[0039] The forwarding module is used to forward the industrial data of the manifold node and the device node to the cloud platform.

[0040] In a third aspect, the present disclosure provides a non-temporary computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the steps of any one of the methods described in the first aspect.

[0041] In a fourth aspect, the present disclosure provides an electronic device, including:

[0042] a memory having a computer program stored thereon;

[0043] A processor is used to execute the computer program in the memory to implement the steps of any one of the methods in the first aspect.

[0044] Through the above technical solution, it is possible to collect manifold data without installing manifold sensors by calculating based on the manifold topology and manifold endpoint data, thereby reducing the equipment modification cost under manifold data collection and improving the efficiency of manifold data collection. Moreover, based on the industrial data of the target device, real-time data collection with the same frequency as the target device can be achieved, thereby more efficiently realizing real-time monitoring and data analysis of manifold data. In addition, based on the industrial data of the target device, the industrial data in the subsequent manifold can be calculated in advance, and in the case of long-distance transmission pipelines, accurate early warning of manifold data can be achieved.

[0045] Other features and advantages of the present disclosure will be described in detail in the following detailed description. BRIEF DESCRIPTION OF THE DRAWINGS

[0046] The accompanying drawings are used to provide a further understanding of the present disclosure and constitute a part of the specification. Together with the following specific embodiments, they are used to explain the present disclosure but do not constitute a limitation of the present disclosure. In the accompanying drawings:

[0047] Figure 1 is a flow chart of a data collection method according to an exemplary embodiment of the present disclosure;

[0048] Figure 2 It is a topological diagram obtained from actual manifold information in a data collection method according to an exemplary embodiment of the present disclosure;

[0049] Figure 3 is a schematic diagram of a manifold line in a data acquisition method according to an exemplary embodiment of the present disclosure;

[0050] Figure 4 is a schematic diagram of a manifold line in a data acquisition method according to another exemplary embodiment of the present disclosure;

[0051] Figure 5 is a schematic diagram of a manifold line in a data acquisition method according to another exemplary embodiment of the present disclosure;

[0052] Figure 6 is a schematic diagram of a manifold line in a data acquisition method according to another exemplary embodiment of the present disclosure;

[0053] Figure 7 is a block diagram of a data acquisition device according to an exemplary embodiment of the present disclosure;

[0054] Figure 8 It is a block diagram of an electronic device according to an exemplary embodiment of the present disclosure. DETAILED DESCRIPTION

[0055] The specific implementation of the present disclosure is described in detail below in conjunction with the accompanying drawings. It should be understood that the specific implementation described herein is only used to illustrate and explain the present disclosure, and is not used to limit the present disclosure.

[0056] In the context of the Industrial 4.0 era, industrial Internet-related technologies are developing rapidly. Equipment-intensive and equipment-centric industrial enterprises have launched intelligent and smart transformation projects, and based on sensor technology, Internet of Things transmission technology, big data computing and other technologies, they have realized the connection and monitoring of industrial equipment, and implemented a series of intelligent applications such as predictive maintenance, production efficiency optimization, safety assurance, and production optimization. The premise of implementing big data analysis and modeling and building intelligent applications is to be able to collect real-time industrial data. Industrial sensors (such as temperature sensors, humidity sensors, pressure sensors, flow sensors, spectral sensors, speed sensors, vibration sensors, etc.) and industrial control systems (such as programmable logic controllers PLC or distributed control systems DCS) are the main means of data collection in the industrial field.

[0057] Specifically, data collection scenarios in the industrial field usually include data collection equipment and cloud platforms. The data collection equipment is deployed with sensors, controllers and transmission modules, so that the data collection equipment collects data through sensors or controllers, and then uploads the collected data to the cloud platform through the transmission module to complete the entire data collection process. For units with slow information development, there is not enough information foundation for equipment transformation. The equipment transformation refers to the intelligent transformation of the equipment, that is, adding sensors, controllers and transmission modules to the equipment that originally did not have data collection, transmission and control functions, so that the data of the equipment can be perceived, the equipment can be controlled, and the data can be uploaded. In the manifold data collection scenario, equipment transformation refers to adding relevant sensors and transmission modules to the manifold.

[0058] However, in the manifold scenario, it is difficult to install and deploy sensors inside the pipeline, and the huge amount of pipelines requires a large number of sensors and gateway equipment (i.e., transmission modules), and the cost of equipment modification is high. The inventors have found that for the collection of manifold data, related technologies also use site collection and manual estimation methods. Among them, site collection refers to the collection at the metering stations, booster stations, valve chambers, etc. at both ends of the pipeline, and it is impossible to collect data at the actual manifold. Manual estimation is to estimate the consumption of fluids in the manifold based on experience or make simple calculations to obtain fuzzy manifold industrial data, which requires more manual participation, and different people have different estimation methods, which will lead to differences in the final manifold data, and the efficiency and accuracy of manifold data collection cannot be guaranteed.

[0059] However, in industrial scenarios, the installation and connection of manifolds are often very complicated, the internal components are complex and changeable, the flow and pressure need to be carefully monitored and controlled, and the safety and life management of manifolds are very important for industrial fields such as oil transportation, chemical industry, and drilling. Therefore, how to accurately collect manifold data for analysis in order to conduct safety monitoring, health management, and predictive maintenance of the manifold is particularly important. Furthermore, how to accurately collect manifold data at a low cost is an issue worthy of attention.

[0060] In view of this, the present disclosure provides a data collection method, which realizes real-time and accurate collection of manifold data by calculating based on the manifold topology structure and manifold endpoint data without installing a manifold sensor, reduces the equipment modification cost under manifold data collection, and improves the efficiency of manifold data collection.

[0061] Figure 1 is a flow chart of a data collection method according to an exemplary embodiment of the present disclosure. Figure 1 , the data collection method comprises the following steps:

[0062] Step 101, receiving industrial data sent by a target device in a manifold scenario, where the industrial data includes data collected by the target device through sensors.

[0063] Step 102, obtaining a manifold topology structure corresponding to the manifold scene, wherein the manifold topology structure is obtained by scanning an actual manifold in the manifold scene.

[0064] Step 103, based on the industrial data and the manifold topology, determine the industrial data of the manifold nodes and the device nodes other than the target device in the manifold scenario.

[0065] Step 104, forwarding the industrial data of the manifold node and the device node to the cloud platform.

[0066] For example, the manifold scenario may include various industrial scenarios for fluid transmission through manifold lines, such as hydraulic fracturing, oil transportation, etc., which are not limited in the embodiments of the present disclosure. The target device may be a starting point device in the manifold scenario, which can conveniently deploy various types of sensors for data collection, such as a fracturing truck in a hydraulic fracturing scenario, or a sand mixing truck, water pump, etc. in other industrial scenarios. Industrial data is used to describe relevant information of industrial processes, such as timestamp, longitude, latitude, sand ratio, sand concentration, displacement, liquid addition amount, mixer speed, oil pressure, sand density, fluid temperature, etc., which are not limited in the embodiments of the present disclosure.

[0067] In a possible manner, before step 101, the manifold topology structure can be obtained in the following manner: first, the actual manifold information scanned in the manifold scene and sent by the scanning terminal is received, and then the endpoint position information and fluid direction marked for each node in the actual manifold information are determined, wherein each node has identification information for uniquely identifying the node, and the endpoint position information is used to characterize the node as one of a starting point, an intermediate node, and an end point; finally, based on the endpoint position information and fluid direction corresponding to each node, a manifold topology structure in the form of a two-dimensional table is established, wherein the data of the two-dimensional table is key-value pair data, the key in the key-value pair data is used to characterize the endpoint position information of the node, and the value in the key-value pair data is used to characterize the identification information of the node.

[0068] In other words, the actual manifold information can be scanned by the scanning terminal in the manifold scenario, thereby establishing a manifold topology structure in the form of a two-dimensional table. Therefore, the cloud platform can store the manifold topology structure in the manifold scenario, and then when the cloud platform receives the industrial data sent by the target device in the manifold scenario, it can read the pre-stored manifold topology structure to calculate the subsequent industrial data.

[0069] For example, refer to Figure 2 , the actual manifold information scanned by the scanning terminal can generate a corresponding topological diagram, so as to determine which devices and manifold lines are in the manifold scenario and the connection relationship between the devices and the manifold. However, the cloud platform cannot determine the flow direction of the fluid in the pipeline based on the actual manifold information, and thus cannot determine which nodes are the starting point and which nodes are the end point. The subsequent calculation of the industrial data of the manifold node and each device node requires the clear flow direction of the fluid and the starting point and end point in the pipeline. Therefore, in the embodiment of the present disclosure, the endpoint position information and fluid direction of each node in the actual manifold information can be manually marked through the visual interface.

[0070] It should be understood that a manifold scenario is composed of multiple single manifold lines, the starting point and the end point of a single manifold line are specific device nodes, and there is at least one manifold node between the starting point and the end point. Figure 2 , the manifold scene includes 20 single manifold lines. In order to facilitate the calculation of industrial data of manifold nodes and each device node, the endpoint location information in the embodiment of the present disclosure is for a single manifold line, not for the entire manifold scene. Therefore, in practical applications, after obtaining the actual manifold information, the multiple single manifold lines included in the manifold scene can be determined based on the actual manifold information, and then the endpoint location information and fluid direction can be annotated for the nodes in each single manifold line.

[0071] For example, refer to Figure 3 , a single manifold line from the starting point to the end point. Figure 4, from the starting point to the first terminal equipment is the first line, from the starting point to the second terminal equipment is the second line, the first straight pipe and tee appear in both lines, a total of two single manifold lines. Figure 5 , from the first starting point equipment to the end point is the first line, and from the second starting point equipment to the end point is the second line. The tee, the straight pipe after the tee, and the end point equipment appear in both lines, for a total of two single manifold lines. Figure 6 , including a diverter device, which serves as the end point of the two lines on the left and the starting point of the three lines on the right, for a total of five single manifold lines.

[0072] After obtaining multiple single manifold lines, the endpoint location information and fluid direction can be annotated for each node in the single manifold line. Figure 2 In the single manifold line A1, the starting point is marked as the fracturing truck B1, and the intermediate nodes include 3 elbows ( Figure 2 Curves in the figure), 2 straight tubes ( Figure 2 A plug valve ( Figure 2 In the single manifold line A7, the manifold skid C1 is marked as the starting point, the intermediate nodes include 2 elbows and 1 straight pipe, and the end point is the manifold skid C2.

[0073] After marking the endpoint location information and fluid direction, the cloud platform can obtain the endpoint location information and fluid direction marked for each node, and then establish a manifold topology structure in the form of a two-dimensional table. For example, a manifold topology structure in the form of a two-dimensional table can be established as: {(starting point: device 11; manifold: straight pipe 21; manifold: elbow 31; manifold: straight pipe 22; manifold: elbow 32; manifold: straight pipe 33; end point: device 12); (starting point: device 11; manifold: straight pipe 21; manifold: tee 41; manifold: straight pipe 22; end point: device 12); (starting point: device 11; manifold: straight pipe 21; manifold: tee 41; manifold: straight pipe 23; end point: device 13); ...}. The data in the two-dimensional table is a key-value pair data in JSON format, the key (Key) in the key-value pair data is used to represent the endpoint location information of the node, and the value (Value) in the key-value pair data is used to represent the identification information of the node. For example, in the two-dimensional table, the key-value pair "starting point: device 11" has the key "starting point" indicating the endpoint location information, and the value "device 11" indicating identification information.

[0074] Therefore, the manifold topology structure in the manifold scenario is pre-stored in the cloud platform, so that real-time and accurate collection of manifold data can be achieved based on the calculation of the manifold topology structure and the manifold endpoint data, reducing the equipment modification cost under manifold data collection and improving the efficiency of manifold data collection.

[0075] As described above, a manifold scenario is composed of multiple single manifold lines, and the manifold topology structure in the embodiment of the present disclosure can be generated by the endpoint location information marked for the single manifold line. Therefore, when determining the industrial data of the manifold nodes and device nodes other than the target device in the manifold scenario based on the industrial data sent by the target device and the manifold topology structure, calculations can be performed sequentially for the single manifold lines starting from the target device.

[0076] That is to say, in a possible way, based on the industrial data sent by the target device and the manifold topology structure, the industrial data of the manifold node and the device nodes other than the target device in the manifold scenario can be determined as follows: taking the target device as the initial starting device node, and looping through the following process: based on the identification information of the starting device node, determining the target manifold line with the starting device node as the starting point in the manifold topology structure, and based on the industrial data of the starting device node, determining the industrial data of the intermediate manifold nodes and the device endpoints included in the target manifold line, wherein the industrial data includes identification information for uniquely identifying the target device, and each node in the manifold topology structure has identification information for uniquely identifying the node, and if the device endpoint is not the target device endpoint in the manifold scenario, then the device endpoint is used as the new starting device node until the device endpoint is the target device endpoint in the manifold scenario.

[0077] It should be understood that the target equipment end point in the manifold scenario is the node where the fluid ends the production or transmission closed loop, and there is no other manifold after this node, such as the wellhead, recovery container, and distillation tower in the chemical industry in actual applications.

[0078] For example, refer to Figure 2 , if the target device is a fracturing truck B1, then first determine the target manifold line with the fracturing truck as the starting point in the manifold topology based on the identification information of the fracturing truck, that is, the target manifold line is A1, and then determine the industrial data of the three elbows, two straight pipes and one plug valve (i.e., the intermediate manifold node) and the manifold skid C1 (i.e., the equipment end point) included in the target manifold line A1 based on the industrial data of the fracturing truck. Afterwards, it can be determined whether the manifold skid C1 is the target device end point in the manifold scenario. If the manifold skid C1 is the target device end point in the manifold scenario, stop the calculation process, otherwise the manifold skid C1 can be used as the new starting device node to execute the calculation process. Continue to refer to Figure 2, the target device endpoint in this manifold scenario is the wellhead, and the manifold skid C1 is not the target device endpoint, so the manifold skid C1 can be used as a new starting device node, and a new target manifold line can be determined based on the new starting device node, that is, the new target manifold line can be determined as A7. Then, based on the industrial data of the manifold skid C1, the industrial data of each manifold node and device endpoint in the target manifold line A7 can be determined. Similarly, the industrial data of each intermediate manifold node and device node in the subsequent manifold lines can be calculated in sequence.

[0079] It should be understood that the data type of industrial data is different, and the method of calculating the subsequent intermediate manifold nodes and the device end point based on the starting device node is also different. The possible methods are described below.

[0080] For pressure data, since the pressure of all manifolds and equipment on the manifold line is the same, the pressure value of the target equipment can be used as the pressure value of each subsequent intermediate manifold node and equipment end point.

[0081] For displacement or operation time, in a possible manner, if there are multiple target devices, multiple target manifold lines with the starting device node as the starting point are first determined in the manifold topology structure based on the identification information of the starting device node. Then, when the device endpoints of multiple target manifold lines are the same, the industrial data of the starting device node is used as the industrial data of the intermediate manifold node in the same manifold line as the starting device node, and the industrial data of the terminal device is determined based on the industrial data of multiple starting device nodes, where the industrial data is displacement or operation time.

[0082] For example, refer to Figure 2 , the target equipment includes fracturing trucks B1, B2 and B3, then the target manifold lines are A1, A2 and A3. The equipment endpoints of the three target manifold lines are all manifold skids C1. In this case, for the intermediate manifold node of the target manifold line A1, its operation time is the operation time of the corresponding starting equipment node (i.e., fracturing truck B1). Similarly, for the intermediate manifold node of the target manifold line A2, its operation time is the operation time of the corresponding starting equipment node (i.e., fracturing truck B2). For the intermediate manifold node of the target manifold line A3, its operation time is the operation time of the corresponding starting equipment node (i.e., fracturing truck B3). And for the manifold skid C1 (i.e., the equipment endpoint), its operation time is the union of the operation times of the fracturing trucks B1, B2 and B3. For example, the operating time of fracturing truck B1 is from 1:00 to 1:30, the operating time of fracturing truck B2 is from 1:10 to 2:00, and the operating time of fracturing truck B3 is from 1:50 to 2:30. Then the union of the operating times is from 1:00 to 2:30, that is, the operating time of manifold skid C1 is from 1:00 to 2:30.

[0083] As for the calculation of displacement, it is similar to the calculation of operation time. For the intermediate manifold node of the target manifold line A1, its displacement is the displacement of the corresponding starting equipment node (i.e., fracturing truck B1). For the intermediate manifold node of the target manifold line A2, its displacement is the displacement of the corresponding starting equipment node (i.e., fracturing truck B2). For the intermediate manifold node of the target manifold line A3, its displacement is the displacement of the corresponding starting equipment node (i.e., fracturing truck B3). For manifold skid C1 (i.e., the end point of the equipment), its displacement is the sum of the displacements of fracturing trucks B1, B2, and B3. For example, the displacement of fracturing truck B1 is 10 cubic meters per minute, the displacement of fracturing truck B2 is 20 cubic meters per minute, and the displacement of fracturing truck B3 is 15 cubic meters per minute. Then the operation time of manifold skid C1 is the sum of the displacements of the three, that is, 45 cubic meters per minute.

[0084] That is to say, the operation time of the intermediate manifold nodes and the equipment end points on a single manifold line is the same as the operation time of the starting equipment node on the manifold line. When there are the same equipment end points on multiple manifold lines, the union calculation of the operation time can be performed based on the distribution of the manifold lines. For the displacement, similar to the calculation of the operation time, the displacement of the intermediate manifold nodes and the equipment end points on a single manifold line is the same as the displacement of the starting equipment node on the manifold line. When there are the same equipment end points on multiple manifold lines, the displacement is cumulatively calculated based on the distribution of the manifold lines.

[0085] For the timestamp, in a possible manner, the first distance between the intermediate manifold node and the starting device node can be determined in the target manifold line, and the second distance between the device end point and the starting device node can be determined. Then, based on the flow rate of the fluid in the target manifold line and the first distance, the first flow time is calculated, and based on the timestamp of the starting device node and the first flow time, the timestamp of the intermediate manifold node is determined. Finally, based on the flow rate of the fluid in the target manifold line and the second distance, the second flow time is calculated, and based on the timestamp of the starting device node and the second flow time, the timestamp of the device end point is determined.

[0086] That is to say, the flow time from the starting device node to the intermediate manifold node or the device end point can be added to the timestamp of the starting device node to obtain the timestamp of the intermediate manifold node or the device end point. It should be understood that in the first calculation process, the starting device node is the target device, and the target device can be provided with a timer, so that the timestamp of the starting device node can be obtained. In the subsequent calculation process, the starting device node is the device end point in the previous calculation process, and the timestamp of the device end point can be calculated in the previous calculation process, so that the timestamp of the starting device node can be obtained in this calculation process.

[0087] For example, the flow rate calculation formula is: [Volume flow rate (unit: m 3 / h)÷pipe cross-sectional area (unit: m 2 )]÷3600, where the calculation formula for the pipe cross-sectional area is: 3.14×R 2 (R is the radius of the pipe section), the flow time is calculated as: distance (in m) ÷ flow velocity (in m / s), and the timestamp of the corresponding node is the timestamp of the starting device node plus the flow time.

[0088] For fluid composition, in a possible way, historical industrial data in a manifold scenario can be obtained, and the first fluid data and the second fluid data in the historical industrial data can be determined, wherein the first fluid data is the fluid composition data obtained from the target device, and the second fluid data includes the fluid index data in the manifold scenario or the fluid composition data in the equipment and manifold other than the target device in the manifold scenario. Then, a fluid prediction model is trained based on the first fluid data and the second fluid data, and the fluid prediction model is used to output fluid index data or fluid composition data in the corresponding equipment and manifold according to the input fluid composition data obtained from the target device. Accordingly, in the industrial data of the starting device node, the target fluid data of the same type as the first fluid data can be first determined, and then the target fluid data can be input into the trained fluid prediction model to obtain the fluid index data corresponding to the target manifold line or the fluid composition data corresponding to the intermediate manifold node and the device end point included in the target manifold line.

[0089] It should be understood that different fluid compositions in the manifold will cause different degrees of corrosion to the manifold, that is, the composition of the fluid will affect the use status and life of the manifold, so the fluid composition is an important data for calculating the health and life of the manifold. In addition, the evaluation parameters and evaluation indexes of the fluid are important indicators of industrial production. For example, the melt flow rate (MI) in the polymerization reaction in the chemical industry is an important indicator for measuring product quality.

[0090] In general, fluid mixing is carried out in containers or special instruments, such as in buffer tanks or sand mixing trucks. Therefore, the fluid composition in the manifold is consistent with the composition in the container or professional instrument, that is, the fluid composition in the manifold can be determined based on the fluid composition in the container or professional instrument. However, when the fluid composition changes, in most cases the fluid composition in the manifold will change linearly for a period of time. For example, the fluid in the manifold is pure water, and due to work needs, 30% fracturing sand is added to it from 1 o'clock. According to theoretical calculations, the fracturing sand will reach a certain elbow at 1:02. Then, the manual inspection shows that the fracturing sand has indeed reached this elbow at 1:02, but the concentration of the fracturing sand is 20%. Then, at 1:05, the concentration of the fracturing sand at the elbow becomes 30%. The linear change mentioned above refers to the process of the concentration of the fracturing sand at the elbow rising from 20% to 30%.

[0091] In this case, it is necessary to predict when the fluid composition in the manifold will be the same as the fluid composition in the container or professional instrument. For example, in the above example, it is necessary to predict whether it reaches 30% at 1:03 or 1:05, so as to control the manifold more precisely. For another example, in the petrochemical field, during the polymerization reaction, it is necessary to change the composition of the substances involved in the reaction. If the proportion of each component is inaccurate, the product produced will be unqualified. Therefore, more accurate judgment and prediction are needed to achieve adjustments as soon as possible, thereby improving product quality, reducing waste generation, and saving costs.

[0092] However, the related art requires manual regular sampling and testing to determine the fluid data (including fluid composition data and fluid index data) in the manifold, which consumes a lot of manpower and time and is inefficient. Therefore, the disclosed embodiment proposes to train the fluid prediction model through historical industrial data, thereby realizing automated fluid prediction through the fluid prediction model and improving efficiency. In addition, based on the target fluid data of the starting device node, the fluid data in the subsequent manifold can be predicted in advance, and in the case of long-distance transmission pipelines, accurate early warning of the manifold data can be achieved.

[0093] For example, historical industrial data includes first fluid data and second fluid data. Among them, the first fluid data is the fluid composition data obtained from the target device, and the second fluid data includes fluid index data in the manifold scenario or fluid composition data in the equipment and manifold other than the target device in the manifold scenario. For example, in the polypropylene production line in the chemical industry, the first fluid data may include the propylene feed flow rate (PPR), main catalyst flow rate (MCR), auxiliary catalyst flow rate (ACR), kettle temperature (T), pressure (P), liquid level (L), and hydrogen volume concentration (H) in the kettle obtained from the starting device, and the second fluid data may be the melt index (MI).

[0094] Model training can be performed after obtaining the first fluid data and the second fluid data. It should be understood that in order to improve the efficiency of model training, the first fluid data and the second fluid data can be preprocessed and analyzed first. Specifically, considering that the data obtained in general have missing values ​​to varying degrees, the missing values ​​can be filled first to improve the data quality and thus improve the efficiency of model training. For example, when there are many missing values ​​in the temperature T and the main catalyst flow rate MCR, they can be filled by means of mean interpolation, cluster interpolation, etc. In addition, it is also possible to determine whether there are outlier points in the first fluid data and the second fluid data. If there are outlier points, they can be eliminated to improve the data quality, thereby improving the efficiency of model training.

[0095] Furthermore, the preprocessing of the fluid data can also include performing correlation analysis between parameters through the Pearson algorithm, determining multiple data with strong linear correlation in the fluid data, and then performing dimensionality reduction processing on the multiple data to reduce the correlation between features. For example, in the above example, the first fluid data includes propylene feed flow rate (PPR), main catalyst flow rate (MCR), and hydrogen volume concentration (H) in the kettle. Then, the Pearson algorithm can be used to determine that there is a strong linear correlation between the propylene feed flow rate (PPR), the main catalyst flow rate (MCR), and the hydrogen volume concentration (H) in the kettle. Then, these data can be subjected to dimensionality reduction processing to reduce the correlation between features. Afterwards, the principal component analysis method can also be used to reduce the dimension of the fluid data. For example, the principal component analysis method is used to retain 3 data in the first fluid data as principal component data for subsequent model training.

[0096] It should be noted that the specific contents of the Pearson algorithm and the principal component analysis method can be referred to the relevant technologies and will not be described in detail here.

[0097] Afterwards, the fluid prediction model can be trained based on the preprocessed first fluid data and the second fluid data. It should be understood that in the embodiments of the present disclosure, since there are many types of fluid data input to the model and the influence between the data is complex, the selection of linear regression models, logistic regression models, etc. may produce large result errors. The data distribution corresponding to the generalized linear model is the exponential distribution family, and different regression models can be obtained under different data distributions. For example, when the data distribution obeys the Gaussian distribution, the linear least squares regression model is obtained, and when the data distribution obeys the Bernoulli distribution, the logistic regression model is obtained. In addition, the generalized linear model can be expanded from continuous data to discrete data, and has a stronger spectrum. Therefore, in the embodiments of the present disclosure, the generalized linear model (Generalized Linear Models, GLM) can be selected as the fluid prediction model for model training.

[0098] After the fluid prediction model is trained, the target fluid data of the same type as the first fluid data can be determined in the industrial data of the starting device node (such as the target device). For example, in the above example, the first fluid data includes the propylene feed flow rate (PPR), main catalyst flow rate (MCR), auxiliary catalyst flow rate (ACR), kettle temperature (T), pressure (P), liquid level (L), and hydrogen volume concentration (H) in the kettle obtained from the starting device, and the target fluid data also includes these types of data. Then the target fluid data is input into the trained fluid prediction model, and the fluid prediction model can output the fluid index data corresponding to the target manifold line or the fluid composition data corresponding to the intermediate manifold node and the equipment end point included in the target manifold line. In this way, automated fluid prediction can be achieved through the fluid prediction model to improve efficiency. In addition, based on the target fluid data of the starting device node, the fluid data in the subsequent manifold can be predicted in advance, and in the case of long-distance transmission pipelines, accurate early warning of manifold data can be achieved.

[0099] Through the above method, the industrial data of the manifold node and the device nodes other than the target device in the manifold scenario can be determined based on the industrial data and the manifold topology. Afterwards, the industrial data of the manifold node and the device node can be forwarded to the cloud platform, and the manifold data can be collected by simulating the data source, reducing the equipment modification cost under the manifold data collection and improving the efficiency of manifold data collection.

[0100] In a possible manner, receiving the industrial data sent by the target device in the manifold scenario may be receiving the industrial data sent by the target device in the manifold scenario through a message queue or a platform gateway of the cloud platform. Accordingly, forwarding the industrial data of the manifold node and the device node to the cloud platform may be: if the industrial data sent by the target device in the manifold scenario is received through a message queue, the industrial data of the manifold node and the device node are forwarded to the message queue; if the industrial data sent by the target device in the manifold scenario is received through a platform gateway, the industrial data of the manifold node and the device node are forwarded to the platform gateway.

[0101] That is to say, the target device first sends the industrial data to the message queue, and the cloud platform can obtain the corresponding industrial data from the message queue. After the cloud platform calculates the industrial data of the manifold node and the device nodes other than the target device in the manifold scenario, the calculated industrial data is forwarded to the message queue, thereby simulating the data upload operation of the manifold data source or the device data source, realizing the real-time and accurate collection of industrial data, reducing the equipment transformation cost under the manifold data collection, and improving the efficiency of manifold data collection.

[0102] Alternatively, the target device can first send the industrial data to the platform gateway, and the cloud platform can obtain the corresponding industrial data from the platform gateway. After the cloud platform calculates the industrial data of the manifold nodes and device nodes other than the target device in the manifold scenario, the calculated industrial data is forwarded to the platform gateway, thereby simulating the data upload operation of the manifold data source or the device data source, realizing the real-time and accurate collection of industrial data, reducing the equipment transformation cost under the manifold data collection, and improving the efficiency of manifold data collection.

[0103] Based on the same inventive concept, the embodiment of the present disclosure also provides a data acquisition device, which can become part or all of an electronic device (such as the cloud platform described above) through software, hardware, or a combination of both. Figure 7 , the data acquisition device 700 comprises:

[0104] A first receiving module 701 is used to receive industrial data sent by a target device in a manifold scenario, where the industrial data includes data collected by the target device through a sensor;

[0105] A first acquisition module 702 is used to acquire a manifold topology structure corresponding to the manifold scene, wherein the manifold topology structure is obtained by scanning an actual manifold in the manifold scene;

[0106] A first determination module 703 is used to determine the industrial data of the manifold node and the device nodes other than the target device in the manifold scenario based on the industrial data and the manifold topology structure;

[0107] The forwarding module 704 is used to forward the industrial data of the manifold node and the device node to the cloud platform.

[0108] Optionally, the first determining module 703 is used to:

[0109] The target device is used as the initial starting point device node, and the following process is executed cyclically:

[0110] Based on the identification information of the starting point device node, a target manifold line with the starting point device node as a starting point is determined in the manifold topology structure, and based on the industrial data of the starting point device node, the industrial data of the intermediate manifold nodes and the device end points included in the target manifold line are determined, wherein the industrial data includes identification information for uniquely identifying the target device, and each node in the manifold topology structure has identification information for uniquely identifying the node;

[0111] When the device endpoint is not the target device endpoint in the manifold scenario, the device endpoint is used as a new starting device node until the device endpoint becomes the target device endpoint in the manifold scenario.

[0112] Optionally, there are multiple target devices, and the first determining module 703 is used to:

[0113] In the case where a plurality of the target devices are used as starting device nodes, based on the identification information of the starting device nodes, a plurality of target manifold lines having the starting device nodes as starting points are determined in the manifold topology structure;

[0114] When the equipment end points of the multiple target manifold lines are the same, the industrial data of the starting device node is used as the industrial data of the intermediate manifold node in the same manifold line as the starting device node, and the industrial data of the end device is determined based on the industrial data of the multiple starting device nodes, wherein the industrial data is the displacement or operation time.

[0115] Optionally, the industrial data includes a timestamp of the starting device node, and the first determining module 703 is used to:

[0116] In the target manifold line, determining a first distance between the intermediate manifold node and the starting device node, and determining a second distance between the device end point and the starting device node;

[0117] Calculating a first flow time based on the flow velocity of the fluid in the target manifold line and the first distance, and determining a timestamp of the intermediate manifold node based on the timestamp of the starting device node and the first flow time;

[0118] A second flow time is calculated based on the flow velocity of the fluid in the target manifold line and the second distance, and a timestamp of the device endpoint is determined based on the timestamp of the start device node and the second flow time.

[0119] Optionally, the device 700 further includes:

[0120] A second acquisition module is used to acquire historical industrial data in the manifold scenario, and determine first fluid data and second fluid data in the historical industrial data, wherein the first fluid data is fluid composition data acquired from the target device, and the second fluid data includes fluid index data in the manifold scenario or fluid composition data in devices and manifolds other than the target device in the manifold scenario;

[0121] A training module, configured to train a fluid prediction model based on the first fluid data and the second fluid data, wherein the fluid prediction model is configured to output fluid index data or fluid composition data in a corresponding device and a manifold according to input fluid composition data obtained from the target device;

[0122] The first determining module 703 is used for:

[0123] In the industrial data of the starting point equipment node, target fluid data of the same type as the first fluid data is determined, and the target fluid data is input into the trained fluid prediction model to obtain the fluid index data corresponding to the target manifold line or the fluid composition data corresponding to the intermediate manifold nodes and equipment end points included in the target manifold line.

[0124] Optionally, the manifold topology is obtained through the following modules:

[0125] A second receiving module is used to receive actual manifold information scanned in the manifold scene and sent by a scanning terminal;

[0126] A second determination module is used to determine the endpoint position information and fluid direction marked for each node in the actual manifold information, wherein each node has identification information for uniquely identifying the node, and the endpoint position information is used to indicate that the node is one of a starting point, an intermediate node, and an end point;

[0127] A module is established for establishing a manifold topology structure in the form of a two-dimensional table based on the endpoint position information and the fluid direction corresponding to each node, wherein the data in the two-dimensional table is key-value pair data, the key in the key-value pair data is used to represent the endpoint position information of the node, and the value in the key-value pair data is used to represent the identification information of the node.

[0128] Optionally, the first receiving module 701 is used to:

[0129] Receiving industrial data sent by a target device in a manifold scenario through a message queue or a platform gateway of the cloud platform;

[0130] The forwarding module 704 is used for:

[0131] When receiving industrial data sent by a target device in a manifold scenario through the message queue, forwarding the industrial data of the manifold node and the device node to the message queue;

[0132] When the industrial data sent by the target device in the manifold scenario is received through the platform gateway, the industrial data of the manifold node and the device node are forwarded to the platform gateway.

[0133] Regarding the device in the above embodiment, the specific manner in which each module performs operations has been described in detail in the embodiment of the method, and will not be elaborated here.

[0134] Based on the same concept, the present disclosure also provides an electronic device, including:

[0135] a memory having a computer program stored thereon;

[0136] A processor is used to execute the computer program in the memory to implement the steps of any of the above data collection methods.

[0137] In a possible manner, the electronic device 800 can be provided as a server. Figure 8 The electronic device 800 includes a processor 822, which may be one or more, and a memory 832 for storing a computer program executable by the processor 822. The computer program stored in the memory 832 may include one or more modules, each corresponding to a set of instructions. In addition, the processor 822 may be configured to execute the computer program to perform the above-mentioned data collection method.

[0138] In addition, the electronic device 800 may further include a power supply component 826 and a communication component 850. The power supply component 826 may be configured to perform power management of the electronic device 800, and the communication component 850 may be configured to implement communication of the electronic device 800, for example, wired or wireless communication. In addition, the electronic device 800 may further include an input / output (I / O) interface 858. The electronic device 800 may operate based on an operating system stored in the memory 832, such as Windows Server 2000. TM , Mac OSX TM , Unix TM , Linux TM etc.

[0139] In another exemplary embodiment, a computer-readable storage medium including program instructions is also provided, and when the program instructions are executed by the processor, the steps of the above-mentioned data collection method are implemented. For example, the non-transitory computer-readable storage medium can be the above-mentioned memory 832 including program instructions, and the above-mentioned program instructions can be executed by the processor 822 of the electronic device 800 to complete any of the above-mentioned data collection methods.

[0140] In another exemplary embodiment, a computer program product is also provided. The computer program product includes a computer program that can be executed by a programmable device. The computer program has a code portion for executing any of the above data collection methods when executed by the programmable device.

[0141] The preferred embodiments of the present disclosure are described in detail above in conjunction with the accompanying drawings; however, the present disclosure is not limited to the specific details in the above embodiments. Within the technical concept of the present disclosure, a variety of simple modifications can be made to the technical solution of the present disclosure, and these simple modifications all fall within the protection scope of the present disclosure.

[0142] It should also be noted that the various specific technical features described in the above specific embodiments can be combined in any suitable manner without contradiction. In order to avoid unnecessary repetition, the present disclosure will not further describe various possible combinations.

[0143] In addition, various embodiments of the present disclosure may be arbitrarily combined, and as long as they do not violate the concept of the present disclosure, they should also be regarded as the contents disclosed by the present disclosure.

Claims

1. A data collection method, characterized in that: The method comprises: Receiving industrial data sent by a target device in a manifold scenario, where the industrial data includes data collected by the target device through a sensor; Acquire a manifold topology structure corresponding to the manifold scenario, wherein the manifold topology structure is obtained by scanning an actual manifold in the manifold scenario; Taking the target device as the initial starting device node, the following process is executed cyclically: based on the identification information of the starting device node, determining the target manifold line with the starting device node as the starting point in the manifold topology structure, and based on the industrial data of the starting device node, determining the industrial data of the intermediate manifold nodes and the device end points included in the target manifold line, wherein the industrial data includes identification information for uniquely identifying the target device, and each node in the manifold topology structure has identification information for uniquely identifying the node; if the device end point is not the target device end point in the manifold scenario, taking the device end point as the new starting device node until the device end point is the target device end point in the manifold scenario; The industrial data of the manifold node and the device node are forwarded to the cloud platform.

2. The method according to claim 1, characterized in that There are multiple target devices, and determining a target manifold line with the start point device node as a start point in the manifold topology structure based on the identification information of the start point device node includes: In the case where a plurality of the target devices are used as starting device nodes, based on the identification information of the starting device nodes, a plurality of target manifold lines having the starting device nodes as starting points are determined in the manifold topology structure; The step of determining the industrial data of the intermediate manifold nodes and the equipment end points included in the target manifold line based on the industrial data of the starting point equipment node includes: When the equipment end points of the multiple target manifold lines are the same, the industrial data of the starting device node is used as the industrial data of the intermediate manifold node in the same manifold line as the starting device node, and the industrial data of the equipment end point is determined based on the industrial data of the multiple starting device nodes, wherein the industrial data is the displacement or operation time.

3. The method according to claim 1, characterized in that The industrial data includes a timestamp of the starting point device node, and the industrial data of the intermediate manifold node and the device end point included in the target manifold line is determined based on the industrial data of the starting point device node, including: In the target manifold line, determining a first distance between the intermediate manifold node and the starting device node, and determining a second distance between the device end point and the starting device node; Calculating a first flow time based on the flow velocity of the fluid in the target manifold line and the first distance, and determining a timestamp of the intermediate manifold node based on the timestamp of the starting device node and the first flow time; A second flow time is calculated based on the flow velocity of the fluid in the target manifold line and the second distance, and a timestamp of the device endpoint is determined based on the timestamp of the start device node and the second flow time.

4. The method according to claim 1, characterized in that The method further comprises: Acquire historical industrial data in the manifold scenario, and determine first fluid data and second fluid data in the historical industrial data, wherein the first fluid data is fluid composition data acquired from the target device, and the second fluid data includes fluid index data in the manifold scenario or fluid composition data in devices and manifolds other than the target device in the manifold scenario; Training a fluid prediction model based on the first fluid data and the second fluid data, wherein the fluid prediction model is used to output fluid index data or fluid composition data in corresponding equipment and manifolds according to input fluid composition data obtained from the target equipment; The step of determining the industrial data of the intermediate manifold nodes and the equipment end points included in the target manifold line based on the industrial data of the starting point equipment node includes: In the industrial data of the starting point equipment node, target fluid data of the same type as the first fluid data is determined, and the target fluid data is input into the trained fluid prediction model to obtain the fluid index data corresponding to the target manifold line or the fluid composition data corresponding to the intermediate manifold nodes and equipment end points included in the target manifold line.

5. The method according to any one of claims 1 to 4, characterized in that: The manifold topology is obtained in the following manner: receiving actual manifold information scanned in the manifold scene and sent by a scanning terminal; Determine endpoint position information and fluid direction marked for each node in the actual manifold information, wherein each node has identification information for uniquely identifying the node, and the endpoint position information is used to indicate that the node is one of a starting point, an intermediate node, and an end point; Based on the endpoint position information and the fluid direction corresponding to each node, a manifold topology structure in the form of a two-dimensional table is established, wherein the data in the two-dimensional table is key-value pair data, the key in the key-value pair data is used to represent the endpoint position information of the node, and the value in the key-value pair data is used to represent the identification information of the node.

6. The method according to any one of claims 1 to 4, characterized in that: The industrial data sent by the target device in the receiving manifold scenario includes: Receiving industrial data sent by a target device in a manifold scenario through a message queue or a platform gateway of the cloud platform; The forwarding of the industrial data of the manifold node and the device node to the cloud platform includes: If industrial data sent by a target device in a manifold scenario is received through the message queue, the industrial data of the manifold node and the device node are forwarded to the message queue; If the industrial data sent by the target device in the manifold scenario is received through the platform gateway, the industrial data of the manifold node and the device node are forwarded to the platform gateway.

7. A data acquisition device, characterized in that: The device comprises: A first receiving module, configured to receive industrial data sent by a target device in a manifold scenario, wherein the industrial data includes data collected by the target device through a sensor; A first acquisition module is used to acquire a manifold topology structure corresponding to the manifold scene, wherein the manifold topology structure is obtained by scanning an actual manifold in the manifold scene; The first determination module is used to take the target device as the initial starting device node and cyclically execute the following process: based on the identification information of the starting device node, determine the target manifold line with the starting device node as the starting point in the manifold topology structure, and based on the industrial data of the starting device node, determine the industrial data of the intermediate manifold nodes and device endpoints included in the target manifold line, wherein the industrial data includes identification information for uniquely identifying the target device, and each node in the manifold topology structure has identification information for uniquely identifying the node; if the device endpoint is not the target device endpoint in the manifold scenario, take the device endpoint as a new starting device node until the device endpoint is the target device endpoint in the manifold scenario; The forwarding module is used to forward the industrial data of the manifold node and the device node to the cloud platform.

8. A non-transitory computer-readable storage medium having a computer program stored thereon, characterized in that: When the program is executed by a processor, the steps of the method described in any one of claims 1 to 6 are implemented.

9. An electronic device, characterized in that: include: a memory having a computer program stored thereon; A processor, configured to execute the computer program in the memory to implement the steps of the method according to any one of claims 1 to 6.