Equipment remote control platform based on industrial Internet of Things
Through intelligent gateways, multi-layer networking and virtual LAN are realized, communication between devices is optimized, and communication is solved, and the problem of low remote control of industrial equipment is improved, and control efficiency and system flexibility are improved.
Patent Information
- Application Number
- CN202411098398.7
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- Filing Date
- 2024-08-12
- Publication Date
- 2024-11-08
- Estimated Expiration
- 2044-08-12
AI Technical Summary
The communication and coordination between equipment in existing industrial equipment control systems is relatively complex, resulting in inefficient remote control of industrial equipment.
Through intelligent gateways, multi-layer networking and virtual LAN are realized, combining data reading and transmission modules, intelligent decision model building modules and control management modules, optimize communication and decision-making processes between devices and realize adaptive control.
It improves the remote control efficiency of industrial equipment, realizes efficient monitoring and control, simplifies the network structure, and enhances the scalability and flexibility of the system.
Smart Images

Figure CN118625724B_ABST
Abstract
Description
Technical Field
[0001] The present application relates to the technical field of industrial Internet of Things, and in particular to a device remote control platform based on the industrial Internet of Things. Background Art
[0002] The remote control platform for industrial IoT equipment is a system that integrates advanced communication technology, cloud computing and big data analysis, and is designed to achieve remote monitoring, control and maintenance of industrial equipment. With the advancement of Industry 4.0, the application of industrial IoT (IIoT) technology in industrial production is becoming more and more extensive. The industrial IoT integrates sensors, equipment, networks and data analysis to realize the intelligence and automation of industrial production. However, there are still some problems and challenges in the existing industrial IoT technology. In traditional industrial equipment control systems, communication and coordination between devices are often complex, and it is difficult to achieve efficient adaptive regulation. This results in the real-time and accuracy of data transmission being affected during remote control, thereby reducing control efficiency. This problem is particularly prominent in large-scale and complex industrial production environments.
[0003] In summary, the prior art has a technical problem in which the efficiency of remote control of industrial equipment is low due to the relatively complex communication and coordination between devices in traditional industrial equipment control systems. Summary of the invention
[0004] The purpose of this application is to provide an industrial Internet of Things-based equipment remote control platform to solve the technical problem in the prior art that the remote control efficiency of industrial equipment is low due to the complex communication and coordination between devices in traditional industrial equipment control systems.
[0005] In view of the above problems, the present application provides an industrial Internet of Things-based device remote control platform, wherein the industrial Internet of Things-based device remote control platform includes: a networking and connection module, wherein the networking and connection module is used to perform multi-layer networking of pre-controlled industrial equipment based on the device gateway based on the intelligent gateway to generate a virtual local area network, wherein the network access gateway of each industrial equipment is integrated and connected to the intelligent gateway, and the intelligent gateway is connected to the industrial Internet of Things cloud platform; a control rule configuration module, wherein the control rule configuration module is used to mine autonomous control rules based on control scenarios and configure the intelligent gateway; a data reading and transmission module, wherein the data reading and transmission module is used to read the device operation data for the virtual local area network, match the target communication protocol and the downlink channel, and transmit it to the intelligent gateway for over-limit judgment based on the transmission timestamp. Determination and division, combined with the intelligent gateway to make self-regulation decisions, determine the first regulation data, wherein the limit is divided into self-regulation data based on preset variables and decision regulation data; an intelligent decision model construction module, the intelligent decision model construction module is used to perform data-driven modeling and build an intelligent decision model, the intelligent decision model uses spatiotemporal convolution and grid deduction as processing functions, and is embedded in the industrial Internet of Things cloud platform; a decision regulation data transmission module, the decision regulation data transmission module is used to transmit the decision regulation data to the industrial Internet of Things cloud platform, combine the intelligent decision model to perform unit matching, determine the self-attention level and perform decision analysis, and determine the second regulation data; a control management module, the control management module is used to control and manage the pre-control industrial equipment based on the first regulation data and the second regulation data.
[0006] One or more technical solutions provided in this application have at least the following technical effects or advantages:
[0007] Through the networking and connection module, the networking and connection module is used to perform multi-layer networking based on the device gateway for the pre-controlled industrial equipment based on the intelligent gateway to generate a virtual local area network, wherein the network access gateway of each industrial equipment is integrated and connected to the intelligent gateway, and the intelligent gateway is connected to the industrial Internet of Things cloud platform; the control rule configuration module, the control rule configuration module is used to mine autonomous control rules based on control scenarios and configure the intelligent gateway; the data reading and transmission module, the data reading and transmission module is used to read the device operation data for the virtual local area network, and match the target communication protocol and the downlink channel, and transmit it to the intelligent gateway for over-limit judgment and division with the transmission timestamp as a constraint, and combine the intelligent gateway to make self-control decisions to determine the first control Control data, where the limit is divided into self-regulation data based on preset variables and decision-making regulation data; intelligent decision model construction module, the intelligent decision model construction module is used to perform data-driven modeling and build an intelligent decision model, the intelligent decision model uses spatiotemporal convolution and grid deduction as processing functions, and is embedded in the industrial Internet of Things cloud platform; decision-making regulation data transmission module, the decision-making regulation data transmission module is used to transmit the decision-making regulation data to the industrial Internet of Things cloud platform, combine the intelligent decision model to perform unit matching, determine the self-attention level and perform decision analysis, and determine the second regulation data; control management module, the control management module is used to control and manage the pre-control industrial equipment based on the first regulation data and the second regulation data. In other words, by integrating the intelligent gateway to realize multi-layer networking and virtual local area network, efficient remote monitoring and control of industrial equipment is realized, and the technical effect of improving the remote control efficiency of industrial equipment is achieved.
[0008] The above description is only an overview of the technical solution of the present application. In order to more clearly understand the technical means of the present application, it can be implemented according to the contents of the specification, and in order to make the above and other purposes, features and advantages of the present application more obvious and easy to understand, the specific implementation methods of the present application are specifically cited below. It should be understood that the content described in this section is not intended to identify the key or important features of the embodiments of the present application, nor is it intended to limit the scope of the present application. Other features of the present application will become easy to understand through the following description. BRIEF DESCRIPTION OF THE DRAWINGS
[0009] In order to more clearly illustrate the technical solutions in the present application or the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings in the following description are only exemplary, and for ordinary technicians in this field, other drawings can be obtained based on the provided drawings without paying any creative work.
[0010] Figure 1 This is a schematic diagram of the structure of the equipment remote control platform based on the industrial Internet of Things in this application;
[0011] Figure 2 This is a schematic diagram of the process of determining the second control data in the equipment remote control platform based on the industrial Internet of Things in this application.
[0012] Explanation of the reference numerals: networking and connection module 11 , control rule configuration module 12 , data reading and transmission module 13 , intelligent decision model construction module 14 , decision control data transmission module 15 , control management module 16 . DETAILED DESCRIPTION
[0013] This application solves the technical problem in the prior art that the remote control efficiency of industrial equipment is low due to the complex communication and coordination between devices in the traditional industrial equipment control system by providing an equipment remote control platform based on the industrial Internet of Things. By integrating intelligent gateways to realize multi-layer networking and virtual local area networks, efficient remote monitoring and control of industrial equipment is achieved, achieving the technical effect of improving the remote control efficiency of industrial equipment.
[0014] Below, the technical solutions in the present application will be clearly and completely described with reference to the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present application, rather than all of the embodiments of the present application. It should be understood that the present application is not limited to the example embodiments described herein. Based on the embodiments of the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present application. It should also be noted that, for the convenience of description, only the parts related to the present application are shown in the accompanying drawings, rather than all of them.
[0015] For examples, please see the attached Figure 1 The present application provides a device remote control platform based on the industrial Internet of Things, wherein the device remote control platform based on the industrial Internet of Things includes:
[0016] The networking and connection module 11 is used to perform multi-layer networking of pre-controlled industrial equipment based on the device gateway based on the intelligent gateway to generate a virtual local area network, wherein the network access gateway of each industrial equipment is integrated and connected to the intelligent gateway, and the intelligent gateway is connected to the industrial Internet of Things cloud platform.
[0017] Specifically, industrial equipment is often connected to the network independently in the traditional network architecture, and each device needs to configure network parameters separately, which not only increases the complexity of network management, but also limits the information interaction between devices. The multi-layer networking strategy based on the intelligent gateway integrates the network access gateways of all devices to the intelligent gateway to form a unified network access point. In this way, each industrial device is no longer connected to the network independently, but is networked through the medium of the intelligent gateway, which is equivalent to building a local area network at the industrial site. In this process, the intelligent gateway acts as the host of each device gateway, responsible for unified management and control of subordinate devices. First, all pre-control devices on the industrial site are traversed to record their device type, function, location and other information. Next, multi-layer networking planning is carried out according to the control synergy of the equipment. For example, the interdependent devices on the production line are divided into the same level to ensure that their communication delay in the network is minimized, thereby improving production efficiency. On this basis, according to the data characteristics of the equipment, such as data volume, transmission frequency, real-time requirements, etc., a suitable network communication protocol is configured for each device or device group. This step is crucial because it is directly related to the efficiency and reliability of data transmission. Through multi-layer networking, a virtual local area network is generated. This local area network connects all industrial devices together to form an efficient and unified data communication network. The intelligent gateway is not only connected to each industrial device, but also to the industrial IoT cloud platform. In this way, the intelligent gateway can transmit the collected device data to the cloud platform in real time, and receive instructions and control signals from the cloud platform at the same time. It achieves efficient communication and coordination between devices, simplifies the network structure, and improves the scalability and flexibility of the system.
[0018] The control rule configuration module 12 is used to mine autonomous control rules based on control scenarios and configure the intelligent gateway.
[0019] Specifically, analyze the behavior and response of the equipment in various control scenarios, including operations such as starting, running, stopping or adjusting parameters of the equipment, and determine the first control scenario. Determine the key control parameters of the equipment operation and analyze how these parameters change over time or environmental changes. Analyze the control trend to determine the trend of equipment operation over time or environmental changes. Based on the control trend, mine autonomous control rules. Autonomous control rules are control strategies generated by data analysis and machine learning algorithms based on control scenarios and control trends, which can automatically adjust control parameters to optimize equipment operation and production efficiency. For example, in the material conveying process, autonomous control rules may include adjusting the speed of the conveyor belt according to the material type to improve the efficiency of material conveying. Configure the intelligent gateway to ensure that the autonomous control rules can be effectively implemented. The intelligent gateway is the core of the entire control system. It is responsible for receiving data from industrial equipment, processing and analyzing this data, and making corresponding control decisions based on preset rules or algorithms. When configuring the intelligent gateway, the mined autonomous control rules need to be embedded in the gateway so that it can automatically adjust the control strategy according to real-time data and control scenarios. For example, during the welding process, the intelligent gateway will collect data such as welding speed, temperature and pressure in real time, and automatically adjust welding parameters according to preset control rules to ensure welding quality. If the welding speed increases, the intelligent gateway will increase the welding temperature and pressure accordingly; if the welding speed decreases, the intelligent gateway will decrease the welding temperature and pressure accordingly. Through the configuration of the intelligent gateway, adaptive control of industrial equipment is achieved, and the intelligent level of control is improved.
[0020] The data reading and transmission module 13 is used to read the device operation data for the virtual local area network, match the target communication protocol and the downlink channel, and transmit it to the intelligent gateway for over-limit judgment and division with the transmission timestamp as a constraint, and combine with the intelligent gateway to make self-regulation decisions to determine the first regulation data, wherein the over-limit division is divided into self-regulation data based on preset variables and decision-making regulation data.
[0021] Specifically, for the virtual LAN, it is necessary to read the operating data of the device, including global data reading and hierarchical data reading. Global data reading means reading the real-time operating data of all devices, while hierarchical data reading selectively reads device data at a specific level based on the networking layer of the device. For example, on a production line, global data reading may include the operating status of all devices, while hierarchical data reading may only focus on the operating data of key devices. Select appropriate communication protocols and downlink channels based on the type, size and real-time requirements of the data. Ensure that the channel can meet the data transmission requirements and reduce communication collisions. At the same time, based on the communication phase, configure the transmission timestamp to ensure the orderly transmission of data and reduce data conflicts and losses.
[0022] The data transmitted by the matching target communication protocol and the downlink channel are sent to the intelligent gateway, which is a key node connecting the industrial site and the cloud and is responsible for data collection, processing and transmission. In the intelligent gateway, the data is judged and divided for over-limit, and the equipment operation data is compared with the preset threshold to determine whether there is an over-limit situation. For example, if the temperature of a device exceeds the preset threshold, the intelligent gateway will determine that this is an over-limit situation. The over-limit division is divided into self-regulation data based on preset variables and decision-making regulation data. Self-regulation data is based on the preset variable threshold, and the control parameters are automatically adjusted to optimize equipment operation and production efficiency. Decision-making regulation data is the control parameters that need to be adjusted manually or by advanced algorithms after decision analysis. Based on the over-limit judgment result, the intelligent gateway will make self-regulation decisions, including front-end self-regulation of the device according to the preset self-regulation rules and scenario functions. For example, if the speed of a device is detected to be too fast, the intelligent gateway may automatically adjust the speed of the device to avoid potential failures or damage. If the variable exceeds the limit or there is a scene switch, the platform will conduct decision analysis and analyze the data and device status in depth to determine whether more complex regulation measures are needed. For example, if the equipment switches from one operating mode to another, the platform may conduct a more detailed decision analysis to determine a new control strategy. It realizes real-time monitoring and analysis of equipment operation data, provides data support for control decisions, and improves the system's response speed and control accuracy.
[0023] The intelligent decision model construction module 14 is used to perform data-driven modeling and construct an intelligent decision model. The intelligent decision model uses spatiotemporal convolution and grid deduction as processing functions and is embedded in the industrial Internet of Things cloud platform.
[0024] Specifically, a mathematical model is established based on historical data and machine learning algorithms, a large amount of actual production data is collected, and this data is used to train the intelligent decision-making model. The intelligent decision-making model is constructed to automatically extract patterns and laws from the data and make intelligent decisions. In this model, spatiotemporal convolution and grid deduction are processing functions. Spatiotemporal convolution is a technology that processes data in the time and space dimensions, which can effectively extract the spatiotemporal features in the data. Grid deduction is a spatial analysis technology based on raster data, which can help the platform perform complex data analysis and decision-making in the spatial dimension. By combining these two technologies, the intelligent decision-making model can more accurately analyze the equipment operation data and generate more intelligent decisions. Embedding the intelligent decision-making model in the industrial Internet of Things cloud platform means that the intelligent decision-making model will be part of the industrial Internet of Things cloud platform and work together with other functional modules of the platform to provide intelligent decision-making support for industrial production. The industrial Internet of Things cloud platform is a platform that integrates a variety of industrial equipment and systems. It can collect and process operation data from various devices. By building an intelligent decision-making model, the intelligence level of decision-making is improved, and intelligent regulation of industrial equipment is realized.
[0025] The decision-making and control data transmission module 15 is used to transmit the decision-making and control data to the industrial Internet of Things cloud platform, perform unit matching in combination with the intelligent decision model, determine the self-attention level and perform decision analysis to determine the second control data.
[0026] Specifically, the decision-making control data is transmitted to the industrial IoT cloud platform, and the control instructions and strategies generated based on the intelligent decision-making model are transmitted to the cloud platform. Decision-making control data refers to data that needs to be further analyzed after the limit-crossing judgment and division in the intelligent gateway, including the adjustment suggestions of control parameters, early warning information of equipment status, etc. Unit matching is carried out in combination with the intelligent decision-making model. The intelligent decision-making model is a mathematical model established based on historical data and machine learning algorithms. It can predict the behavior and performance of equipment and generate the optimal control strategy based on these predictions. In the unit matching process, the cloud platform will match these predictions and control strategies with the actual production units to ensure that the control instructions can be accurately applied to the corresponding equipment. Decision analysis is carried out in combination with the self-attention level to determine the second control data. The second control data is based on the self-attention level, and the decision-making control data is further analyzed and processed to determine the final control strategy. According to the self-attention level and the prediction of the intelligent decision-making model, the control instructions are further analyzed and adjusted. Through decision analysis, the platform can generate more intelligent control strategies to improve the accuracy and efficiency of control. Through data transmission and unit matching in combination with the intelligent decision-making model, intelligent analysis and processing of control data are realized, which improves the accuracy and efficiency of decision-making.
[0027] The control management module 16 is used to perform control management of the pre-controlled industrial equipment based on the first control data and the second control data.
[0028] Specifically, the first control data refers to the data that needs to be further controlled after the over-limit judgment and division in the intelligent gateway, including the adjustment suggestions of control parameters, the early warning information of equipment status, etc. The second control data is based on the self-attention level, and the decision control data is further analyzed and processed to determine the final control strategy. The second control data can help make adjustments in advance to avoid potential problems and failures. Based on the first control data and the second control data, control management of pre-controlled industrial equipment is carried out, including real-time equipment control according to the first control data, and predictive equipment adjustment according to the second control data. According to the determined control strategy, control management of pre-controlled industrial equipment is carried out, including adjusting control parameters, monitoring equipment operation status, and executing early warning measures. Through this combination of real-time control and predictive control, the platform can realize intelligent management of industrial equipment and improve production efficiency and quality. Through the comprehensive analysis of control data, adaptive control management of industrial equipment is realized, and the stability and efficiency of the system are improved.
[0029] Furthermore, the networking and connection module 11 in the industrial Internet of Things-based equipment remote control platform is also used for:
[0030] Traverse the pre-control industrial equipment, perform multi-layer networking based on control synergy, and determine a first networking result, wherein the networking level corresponds one-to-one to the control synergy class; determine a second networking result based on equipment data characteristics, wherein each second networking result is configured with a network communication protocol; fit the first networking result and the second networking result to determine the virtual local area network.
[0031] Specifically, all pre-controlled industrial equipment are traversed, including but not limited to robots, sensors, actuators, etc. on the production line. For each device, its control requirements are analyzed, including what data it needs to receive, what control instructions it needs to generate, and the collaborative relationship between it and other devices. The devices are divided into different control collaboration classes, and a networking level is determined for each class. The design of the networking level ensures that data can be transmitted efficiently and in real time between devices. Control collaboration refers to the degree to which devices need to work together when performing specific tasks. For example, welding robots and assembly robots may need to work closely together, so they are assigned to the same networking level. The first networking result is determined, and each networking level corresponds to a specific control collaboration class one by one, ensuring that the logical relationship of the device in the network matches the actual production requirements. The second networking result is determined based on the device data characteristics. Device data characteristics include data volume, data type, transmission frequency, and real-time requirements. Configure a suitable network communication protocol for each device or device group, such as which network communication protocol the device should use and which network path the data should be transmitted through. For example, data with high requirements may be transmitted using the TCP protocol to ensure data reliability and real-time performance. In this way, each device or group of devices is configured with the most appropriate network communication protocol, ensuring efficient and reliable data transmission.
[0032] Fit the first networking result with the second networking result to determine the virtual LAN, match the networking level determined based on control synergy with the network communication configuration determined based on device data characteristics, and form a network structure that not only meets the needs of collaborative control but also optimizes data transmission. The fitting process may involve adjustments to network parameters, such as IP address allocation, subnet division, etc., to ensure that all devices can work together efficiently in the virtual LAN. In a simulated environment with 50 industrial devices, multi-layer networking was carried out based on control synergy, and the second networking result was determined based on device data characteristics. By comparing the test data, it was found that after adopting this networking and configuration strategy, the collaborative work efficiency between devices increased by 25%, the data transmission efficiency increased by 20%, and the network stability increased by 15%. The construction of multi-layer networking and virtual LAN based on device gateway not only improves the efficiency of data transmission, but also enhances the scalability and flexibility of the system.
[0033] Furthermore, the networking and connection module 11 in the industrial Internet of Things-based equipment remote control platform is also used for:
[0034] The network communication protocol at least includes a network time protocol class, a network privacy protocol class, a network routing protocol class and a data encapsulation protocol class, and there is protocol adaptive switching and combination.
[0035] Specifically, network communication protocols at least include network time protocol, network privacy protocol, network routing protocol and data encapsulation protocol, and have the ability to adaptively switch and combine protocols. The network time protocol (NTP) is responsible for synchronizing the time of devices in the network, which is essential to ensure data consistency and the accuracy of event timestamps. In industrial environments, accurate time synchronization is essential for coordinating device operations, fault analysis and system optimization. The network privacy protocol focuses on protecting privacy and security during data transmission, including encryption algorithms and authentication mechanisms to ensure that data is not accessed or tampered with by unauthorized persons during transmission. The network routing protocol defines the transmission path of data from the source device to the destination device in the network, including selecting the optimal path to reduce transmission delays and automatically switching to alternative paths when network congestion or failure occurs. These protocols must be able to efficiently process large amounts of data in industrial environments while ensuring reliable data transmission. The data encapsulation protocol involves how to package data into a format suitable for transmission in the network, including determining the format, size and structure of the data frame, and how to handle data packet loss and errors. In the industrial Internet of Things, due to the diversity of devices and the complexity of application scenarios, a single communication protocol is often difficult to meet all requirements. Therefore, protocol adaptive switching and combination has become an important technical means. The ability of protocol adaptive switching and combination means that the appropriate protocol can be automatically selected and switched according to the real-time network status and device requirements. For example, if a device needs to transmit a large amount of data, the system may select a protocol that supports large data transmission; if the network suddenly becomes congested, the system may switch to a protocol that can effectively handle the congestion. Through protocol adaptive switching and combination, the system can easily adapt to new devices and application scenarios, improving the flexibility and scalability of the network.
[0036] Furthermore, the control rule configuration module 12 in the industrial Internet of Things-based equipment remote control platform is also used for:
[0037] Determine a first control scenario, and determine a control trend of scenario change under device control, wherein the first control scenario includes at least one pre-controlled industrial device; based on the control trend, determine a self-regulating function, wherein the self-regulating function is a control regulation relationship under a unit scenario variable; and use the self-regulating function as a first autonomous regulation rule for the first control scenario.
[0038] Specifically, an in-depth understanding of industrial production processes includes understanding the production process, equipment functions and the interactions between them. Identify and define a specific production process or operation task that includes at least one pre-controlled industrial equipment. The determination of control scenarios relies on a deep understanding of the production process and an accurate analysis of the equipment functions. The first control scenario may include operations such as starting, running, stopping or adjusting parameters of the equipment. For example, on a production line, the first control scenario may be an "automatic welding" process, which includes a welding robot as a pre-controlled industrial equipment. Analyze how equipment operation changes over time or environmental changes under specific control scenarios, predict future equipment performance under different operating conditions, and determine the control trend of scenario changes under equipment control.
[0039] According to the control trend, the behavior pattern and response characteristics of the equipment are analyzed to determine the self-regulating function. The self-regulating function is a mathematical model that describes the control regulation relationship under the unit scenario variable. It can automatically adjust the control parameters according to the current control scenario and equipment status to optimize equipment performance and production efficiency. For example, if the welding quality of the robot improves with the increase of welding speed, but the quality begins to decline when the speed exceeds a certain threshold, then the self-regulating function can automatically adjust the welding speed to maintain the best welding quality. Using the self-regulating function as the first autonomous control rule for the first control scenario means that in actual operation, when the controlled variable deviates from the predetermined value, the control system will automatically adjust the control variable to return the controlled variable to the predetermined range. By determining the first control scenario and determining the self-regulating function based on the control trend, intelligent control of industrial equipment is achieved.
[0040] Furthermore, the data reading and transmission module 13 in the equipment remote control platform based on the industrial Internet of Things is also used for:
[0041] Data reading includes global data reading and hierarchical data reading; based on the networking layer affiliation, the target communication protocol is matched and determined; based on the real-time state of the channel and the communication collision, the downlink channel of the device operation data is matched; based on the communication phase, the transmission timestamp is configured, wherein the communication phase includes synchronous communication and differential frequency communication.
[0042] Specifically, for virtual LANs, it is necessary to read the operating data of the device, including global data reading and hierarchical data reading. Global data reading means reading the real-time data of all devices, while hierarchical data reading requires selective data collection based on the networking layer of the device to better understand the performance of the device at different working stages. Global data reading can provide a comprehensive view of the production process and help the system identify global problems or trends. For example, by analyzing global data, the system can find efficiency bottlenecks or equipment failures in the entire production line. Hierarchical data reading can provide more refined control to help the system focus on devices or operations at a specific level. For example, the system can focus on analyzing the operating data of a key device to optimize its performance or prevent failures. Based on the networking layer of the device, match and determine the target communication protocol. Different networking levels require different communication protocols to adapt to their data transmission requirements and network environment. For example, data with high real-time requirements may need to use the TCP protocol, while the transmission of large amounts of data may be more suitable for the UDP protocol.
[0043] According to the real-time status of the channel and the communication collision situation, the downlink channel of the device running data is matched to select the best downlink channel for data transmission. The real-time status of the channel includes parameters such as channel availability, bandwidth, and delay, while communication collision refers to multiple devices trying to send data through the same channel at the same time, resulting in data transmission conflicts. When matching downlink channels, it is necessary to ensure that the channel can meet the data transmission requirements and reduce communication collisions. Communication phase includes synchronous communication and differential frequency communication. Synchronous communication means that devices send data at the same time at a predetermined time interval, while differential frequency communication means that devices send data at different time intervals. When configuring the transmission timestamp, it is necessary to consider the communication phase to ensure the orderly transmission of data and reduce data conflicts and losses. By improving the efficiency and stability of data transmission, the efficiency and stability of data transmission are improved.
[0044] Furthermore, the intelligent decision model construction module 14 in the industrial Internet of Things-based equipment remote control platform is also used for:
[0045] A feature extraction area is constructed with the function of spatiotemporal convolution, and an intelligent decision-making area is constructed with the function of grid deduction. The feature extraction area and the intelligent decision-making area are connected front and back to generate a control analysis unit; the control analysis unit is twinned in parallel to determine the main framework; the main framework is data-driven modeled to generate an intelligent decision-making model.
[0046] Specifically, spatiotemporal convolution is a technology that processes data in time and space dimensions, which can effectively extract spatiotemporal features from data. In the industrial Internet of Things environment, the data generated by the equipment often contains rich spatiotemporal information, such as time series data and spatial distribution data. Through spatiotemporal convolution, the platform can extract features that have an important impact on the status and performance of the equipment from these data, such as the operation mode and abnormal mode of the equipment. Grid deduction is a data processing technology based on grid data structure. It divides spatial data into regular grid units and analyzes and processes the data in each unit to predict and analyze the distribution and change trend of data in space. In the industrial Internet of Things environment, grid deduction can be used to analyze the spatial distribution of equipment, resource allocation and other issues, thereby providing support for intelligent decision-making. The feature extraction area and the intelligent decision-making area are organically combined to form a unified control analysis unit. This front-end and back-end connection design ensures seamless connection between feature extraction and intelligent decision-making. The key features extracted by the feature extraction area will be transmitted to the intelligent decision-making area, which will analyze and make decisions based on these features and generate control instructions.
[0047] Perform parallel twinning on the control analysis unit to determine the main framework. Parallel twinning refers to creating a virtual control system that is parallel to the actual control system. This virtual system is consistent with the actual system in structure and function. Through parallel twinning, the operation of the actual system can be simulated in real time, and it can be analyzed and optimized. Determining the main framework is to extract key decision-making and control logic from the parallel twin system as the basis of the intelligent decision-making model. Perform data-driven modeling on the main framework to generate an intelligent decision-making model. Data-driven modeling is a method of building mathematical models based on historical data and machine learning algorithms. Use a large amount of actual production data to train the intelligent decision-making model. After the intelligent decision-making model is generated, this model can be used to generate the optimal control strategy. These strategies can not only be adjusted according to current production conditions, but also predict future production trends, thereby achieving adaptive control.
[0048] Furthermore, the decision-making and control data transmission module 15 in the equipment remote control platform based on the industrial Internet of Things is also used for:
[0049] Perform a primary attention weighting based on feature importance to determine a first attention distribution; perform a secondary attention weighting based on feature variables to determine a second attention distribution; fit the first attention distribution and the second attention distribution to determine a self-attention level, wherein the self-attention level corresponds to the spatiotemporal convolution feature.
[0050] Specifically, feature importance refers to the degree of influence of a feature on the decision result. By weighting the feature importance, the first attention distribution can be determined, that is, which features have higher attention in the decision process. The attention mechanism is an algorithm that simulates human attention and can weight each feature according to its importance in the data. In the industrial Internet of Things environment, the data generated by the device often contains a large number of features, and these features have different effects on the control decision. By weighting the attention based on the feature importance, the platform can identify the most important features for the control decision and give them higher weights. Feature variables refer to the variables in the decision control data. By weighting the feature variables, the second attention distribution can be determined, that is, which variables have higher attention in the decision process. Further weighting is performed based on the feature variables. In the industrial Internet of Things environment, feature variables may include multiple dimensions such as time, space, and device status. By performing secondary attention weighting based on feature variables, the platform can further optimize the control strategy and improve the accuracy and efficiency of control.
[0051] Fit the first attention distribution with the second attention distribution to determine the self-attention level. The self-attention level corresponds to the spatiotemporal convolution feature, which describes the degree of influence of different features on the control decision. The spatiotemporal convolution feature is a data processing technology that combines the two dimensions of time and space to analyze data. In the industrial Internet of Things environment, the data generated by the equipment often contains rich spatiotemporal information, such as time series data and spatial distribution data. By fitting the first attention distribution with the second attention distribution, the platform can determine the self-attention level, thereby providing a basis for control decisions. Through the analysis of feature importance and feature variables, it is possible to more accurately identify factors that have a significant impact on decision results, thereby improving the accuracy of decisions.
[0052] Further, as attached Figure 2 As shown, the decision-making and control data transmission module 15 in the equipment remote control platform based on industrial Internet of Things is also used for:
[0053] Based on the self-attention level, in combination with the feature extraction area, the decision control data is subjected to spatiotemporal convolution feature extraction to determine a convolution feature set; the convolution feature set is traversed to generate real-time control data; in combination with a preset feature trend change rate, an out-of-limit feature set is extracted based on the convolution feature set; the out-of-limit feature set is traversed, in combination with the intelligent decision area, feature deduction and prediction within a unit control grid is performed to determine predicted control data, wherein one unit control grid corresponds to at least one out-of-limit feature; based on the real-time control data and the predicted control data, the second control data is determined.
[0054] Specifically, the self-attention level is classified according to the importance of the decision-making control data, which can help the platform identify the most critical data part for the control decision. According to the self-attention level, determine which parts of the decision-making control data are the most important. Combined with the feature extraction area, the decision-making control data is subjected to spatiotemporal convolution feature extraction. Spatiotemporal convolution is a technology that processes data in time and space dimensions, which can effectively extract spatiotemporal features in the data. In the industrial Internet of Things environment, the data generated by the equipment often contains rich spatiotemporal information, such as time series data and spatial distribution data. Through spatiotemporal convolution, features that have an important impact on the equipment status and performance, such as the equipment's operating mode, abnormal mode, etc., are extracted. The convolution feature set is a set of key features extracted by spatiotemporal convolution, which contains the most valuable information in the decision-making control data. Traverse the convolution feature set, generate control instructions and strategies based on the analysis results of the convolution feature set, and obtain real-time control data. Set the preset feature trend change rate according to the normal operating mode and potential failure mode of the equipment, which refers to the speed threshold of the feature value change within a certain time range. By analyzing the convolution feature set, identify abnormal or out-of-limit features. These out-of-limit characteristics indicate that the device has failed or is experiencing performance degradation.
[0055] Traverse the over-limit feature set and analyze each feature to understand their impact on the equipment status and performance. Combined with the intelligent decision area, perform feature deduction and prediction within the unit control grid to determine the predictive control data. The intelligent decision area is a spatial analysis technology based on grid data, which can help the platform perform complex data analysis and decision-making in the spatial dimension. A unit control grid corresponds to at least one over-limit feature, which means that each control grid contains key information related to it. By combining the over-limit feature set and the intelligent decision area, the platform can generate predictive control data that can help make adjustments in advance to avoid potential problems and failures. Predictive control data is a control instruction and strategy generated based on the analysis results of the over-limit feature set and the intelligent decision area, guiding the adjustment and optimization of the production line and improving production efficiency and quality. For example, if it is detected that the operating speed feature of a certain device exceeds the preset threshold, the corresponding control instruction can be generated based on the predictive control data to adjust its speed to avoid potential failures or damage.
[0056] Predictive control analysis is to avoid excessive changes in feature trends and to conduct predictive control analysis in advance. Through predictive control analysis, the platform can promptly discover potential problems in equipment operation and take corresponding measures, thereby avoiding frequent subsequent decision-making analysis. Based on real-time control data and predictive control data, the second control data is determined. The second control data combines real-time data and predictive data to generate more accurate and effective control instructions. This combination takes into account the current equipment status and future predictions, thereby improving the accuracy and efficiency of control. Taking into account the current equipment status and future predictions, thereby improving the accuracy and efficiency of control.
[0057] In summary, the equipment remote control platform based on industrial Internet of Things provided by this application has the following technical effects:
[0058] Through the networking and connection module, the networking and connection module is used to perform multi-layer networking based on the device gateway for the pre-controlled industrial equipment based on the intelligent gateway to generate a virtual local area network, wherein the network access gateway of each industrial equipment is integrated and connected to the intelligent gateway, and the intelligent gateway is connected to the industrial Internet of Things cloud platform; the control rule configuration module, the control rule configuration module is used to mine autonomous control rules based on control scenarios and configure the intelligent gateway; the data reading and transmission module, the data reading and transmission module is used to read the device operation data for the virtual local area network, and match the target communication protocol and the downlink channel, and transmit it to the intelligent gateway for over-limit judgment and division with the transmission timestamp as a constraint, and combine the intelligent gateway to make self-control decisions to determine the first control Control data, where the limit is divided into self-regulation data based on preset variables and decision-making regulation data; intelligent decision model construction module, the intelligent decision model construction module is used to perform data-driven modeling and build an intelligent decision model, the intelligent decision model uses spatiotemporal convolution and grid deduction as processing functions, and is embedded in the industrial Internet of Things cloud platform; decision-making regulation data transmission module, the decision-making regulation data transmission module is used to transmit the decision-making regulation data to the industrial Internet of Things cloud platform, combine the intelligent decision model to perform unit matching, determine the self-attention level and perform decision analysis, and determine the second regulation data; control management module, the control management module is used to control and manage the pre-control industrial equipment based on the first regulation data and the second regulation data. In other words, by integrating the intelligent gateway to realize multi-layer networking and virtual local area network, efficient remote monitoring and control of industrial equipment is realized, and the technical effect of improving the remote control efficiency of industrial equipment is achieved.
[0059] The above description of the disclosed embodiments enables those skilled in the art to implement or use the present application. Various modifications to these embodiments will be apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the present application. Therefore, the present application will not be limited to the embodiments shown herein, but will conform to the widest scope consistent with the principles and novel features disclosed herein.
[0060] Obviously, those skilled in the art can make various changes and modifications to the present application without departing from the spirit and scope of the present application. Thus, if these modifications and variations of the present application belong to the scope of the present application and its equivalent technology, the present application is also intended to include these modifications and variations.
Claims
1. The equipment remote control platform based on industrial Internet of Things is characterized by: include: A networking and connection module, which is used to perform multi-layer networking of pre-controlled industrial equipment based on the device gateway based on the intelligent gateway to generate a virtual local area network, wherein the network access gateway of each industrial equipment is integrated and connected to the intelligent gateway, and the intelligent gateway is connected to the industrial IoT cloud platform; A control rule configuration module, which is used to mine autonomous control rules based on control scenarios and configure the intelligent gateway; A data reading and transmission module, the data reading and transmission module is used to read the device operation data for the virtual local area network, match the target communication protocol and the downlink channel, and transmit the data to the intelligent gateway for over-limit determination and division based on the transmission timestamp, and make a self-regulation decision in conjunction with the intelligent gateway to determine the first regulation data, wherein the over-limit division is divided into self-regulation data and decision-making regulation data based on preset variables; An intelligent decision model construction module, which is used to perform data-driven modeling and construct an intelligent decision model. The intelligent decision model uses spatiotemporal convolution and grid deduction as processing functions and is embedded in the industrial IoT cloud platform; A decision-making control data transmission module, which is used to transmit the decision-making control data to the industrial IoT cloud platform, perform unit matching in combination with the intelligent decision model, determine the self-attention level and perform decision analysis to determine the second control data; A control management module, wherein the control management module is used to perform control management of the pre-controlled industrial equipment based on the first control data and the second control data.
2. The equipment remote control platform based on industrial Internet of Things according to claim 1, characterized in that: The networking and connection module is also used for: Traversing the pre-controlled industrial equipment, performing multi-layer networking based on control synergy, and determining a first networking result, wherein the networking levels correspond to the control synergy classes one by one; Determine a second networking result based on the device data characteristics, wherein each second networking result is configured with a network communication protocol; The first networking result and the second networking result are fitted to determine the virtual local area network.
3. The equipment remote control platform based on industrial Internet of Things as claimed in claim 2, characterized in that: The network communication protocol at least includes a network time protocol class, a network privacy protocol class, a network routing protocol class and a data encapsulation protocol class, and there is protocol adaptive switching and combination.
4. The equipment remote control platform based on industrial Internet of Things according to claim 1, characterized in that: The control rule configuration module is also used for: Determine a first control scenario, and determine a control trend of scenario change under device control, wherein the first control scenario includes at least one pre-controlled industrial device; Based on the control trend, determining a self-regulating function, wherein the self-regulating function is a control regulating relationship under a unit scene variable; The self-regulating function is used as the first autonomous regulating rule of the first control scenario.
5. The device remote control platform based on industrial Internet of Things according to claim 1, characterized in that: The data reading and transmission module is also used for: Data reading includes global data reading and hierarchical data reading; Based on the networking layer attribution, matching and determining the target communication protocol; Matching the downlink channel of the device operation data based on the real-time state of the channel and the communication collision; The transmission timestamp is configured based on a communication phase, wherein the communication phase includes synchronous communication and differential frequency communication.
6. The equipment remote control platform based on industrial Internet of Things according to claim 1, characterized in that: The intelligent decision model building module is also used for: A feature extraction area is constructed with spatiotemporal convolution as a function, and an intelligent decision-making area is constructed with grid deduction as a function, and the feature extraction area and the intelligent decision-making area are connected front and back to generate a control analysis unit; Performing parallel twinning on the control and analysis unit to determine the main framework; The main framework is subjected to data-driven modeling to generate an intelligent decision-making model.
7. The equipment remote control platform based on industrial Internet of Things according to claim 1, characterized in that: The decision-making control data transmission module is also used for: Perform an attention weighting based on the feature importance and determine the first attention distribution; Perform secondary attention weighting based on the feature variables and determine the second attention distribution; The first attention distribution and the second attention distribution are fitted to determine a self-attention level, wherein the self-attention level corresponds to the spatiotemporal convolution feature.
8. The equipment remote control platform based on industrial Internet of Things as claimed in claim 6, characterized in that: The decision-making control data transmission module is also used for: Based on the self-attention level, the decision control data is subjected to spatiotemporal convolution feature extraction in combination with the feature extraction area to determine a convolution feature set; Traversing the convolution feature set to generate real-time control data; In combination with a preset feature trend change rate, an out-of-limit feature set is extracted based on the convolution feature set; Traversing the limit-crossing feature set, combining with the intelligent decision-making area, performing feature deduction and prediction within the unit control grid, and determining prediction and control data, wherein one unit control grid corresponds to at least one limit-crossing feature; The second control data is determined based on the real-time control data and the predicted control data.
