An industrial control device data processing and scheduling method based on a cloud edge-end architecture

Abstract

The application relates to the technical field of data processing, and provides an industrial control equipment data processing and scheduling method based on a cloud edge end architecture. The method comprises the following steps: performing edge configuration based on industrial cloud edge end node architecture information, obtaining edge control node information, and then deploying a distributed sensor end point network to perform industrial data collection and obtain a control node perception data stream set; performing parallel rectification on the control node perception data stream set based on node data parallel rules to obtain a node parallel perception data stream set, performing edge calculation on the node parallel perception data stream set, obtaining a node industrial control equipment analysis information set, integrating and transmitting the node industrial control equipment analysis information set to an industrial control equipment cloud end for scheduling analysis, obtaining an industrial control equipment collaborative scheduling parameter, and performing equipment regulation and control based on the industrial control equipment collaborative scheduling parameter. The method can realize industrial control equipment data processing by using the cloud edge end architecture, improve process data processing efficiency and scheduling analysis accuracy, and then ensure the scheduling effect of the industrial control equipment.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of data processing, in particular to a kind of industrial control equipment data processing and scheduling method based on cloud edge-end architecture. BACKGROUND

[0002] Industrial control equipment refers to electronic equipment and system specially applied in industrial automation control field, mainly used for monitoring and management industrial automation control system and process, realizes the automation, intelligent control and management of industrial equipment, with high performance, high reliability and anti-interference ability, to cope with complex industrial environment.However, the industrial control equipment of prior art needs to process massive industrial data, which leads to low data processing efficiency, and further affects the scheduling effect of industrial control equipment. SUMMARY

[0003] Therefore, it is necessary to provide an industrial control equipment data processing and scheduling method based on cloud edge-end architecture, which can realize industrial control equipment data processing by using cloud edge-end architecture, improve process data processing efficiency and scheduling analysis accuracy, and further ensure the scheduling effect of industrial control equipment.

[0004] An industrial control equipment data processing and scheduling method based on cloud edge-end architecture, the method comprises: deploying node architecture according to industrial area distribution information, obtaining industrial cloud edge-end node architecture information; based on the industrial cloud edge-end node architecture information, edge configuration is carried out, and edge control node information is obtained; according to the edge control node information, distributed sensor endpoint network is laid out; based on the distributed sensor endpoint network, the edge control node information is respectively carried out industrial data acquisition, and control node perception data stream set is obtained; node data parallel rule is obtained, and the control node perception data stream set is parallel rectified based on the node data parallel rule, and node parallel perception data stream set is obtained; based on the edge control node information, the node parallel perception data stream set is carried out edge calculation, and node industrial control equipment analysis information set is obtained; the node industrial control equipment analysis information set is integrated and transmitted to industrial control equipment cloud for scheduling analysis, and industrial control equipment cooperative scheduling parameter is obtained, and equipment regulation control is carried out based on the industrial control equipment cooperative scheduling parameter.

[0005] The system comprises a node architecture deployment module, an edge configuration module, a sensor endpoint network layout module, an industrial data acquisition module, a parallel rectification module, an edge computing module, and a device regulation control module.

[0006] A computer device comprises a memory and a processor, the memory stores a computer program, and the processor implements the following steps when executing the computer program:

[0007] The node architecture deployment is performed according to the industrial area distribution information, and the industrial cloud edge node architecture information is acquired.

[0008] The edge configuration is performed based on the industrial cloud edge node architecture information, and the edge control node information is obtained.

[0009] The distributed sensor endpoint network is laid out according to the edge control node information.

[0010] The industrial data acquisition is performed based on the distributed sensor endpoint network and the edge control node information, and the control node perception data stream set is acquired.

[0011] The node data parallel rules are acquired, and the parallel rectification is performed on the control node perception data stream set based on the node data parallel rules, so as to obtain the node parallel perception data stream set.

[0012] The edge computing is performed on the node parallel perception data stream set based on the edge control node information, and the node industrial control equipment analysis information set is obtained.

[0013] The node industrial control equipment analysis information set is integrated and transmitted to the industrial control equipment cloud end for scheduling analysis, industrial control equipment cooperative scheduling parameters are obtained, and equipment adjustment control is performed based on the industrial control equipment cooperative scheduling parameters.

[0014] A computer-readable storage medium having a computer program stored thereon, the computer program being executed by a processor to implement the following steps:

[0015] The node architecture is deployed according to the industrial control area distribution information, and industrial cloud edge node architecture information is obtained.

[0016] The edge configuration is performed based on the industrial cloud edge node architecture information, and edge control node information is obtained.

[0017] According to the edge control node information, a distributed sensor endpoint network is laid out.

[0018] Based on the distributed sensor endpoint network, the edge control node information is respectively collected, and a control node perception data stream set is obtained.

[0019] Node data parallel rules are obtained, and the control node perception data stream set is parallel rectified based on the node data parallel rules, and a node parallel perception data stream set is obtained.

[0020] Based on the edge control node information, the node parallel perception data stream set is edge calculated, and a node industrial control equipment analysis information set is obtained.

[0021] The node industrial control equipment analysis information set is integrated and transmitted to the industrial control equipment cloud end for scheduling analysis, industrial control equipment cooperative scheduling parameters are obtained, and equipment adjustment control is performed based on the industrial control equipment cooperative scheduling parameters.

[0022] The above-mentioned industrial control equipment data processing and scheduling method based on cloud edge architecture solves the technical problem that the existing industrial control equipment needs to process massive industrial data, resulting in low data processing efficiency and affecting the scheduling effect of the industrial control equipment, achieves the technical effect of realizing industrial control equipment data processing by using cloud edge architecture, improving process data processing efficiency and scheduling analysis accuracy, and further ensuring the scheduling effect of the industrial control equipment.

[0023] The above description is only a summary of the technical scheme of the present application, in order to more clearly understand the technical means of the present application, the specific embodiments of the present application can be implemented according to the content 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 following specific embodiments of the present application are described. BRIEF DESCRIPTION OF DRAWINGS

[0024] Figure 1A flowchart of a cloud edge-end architecture-based industrial control device data processing and scheduling method in an embodiment;

[0025] Figure 2 A flowchart of obtaining industrial cloud edge-end node architecture information in a cloud edge-end architecture-based industrial control device data processing and scheduling method in an embodiment;

[0026] Figure 3 A structural block diagram of a cloud edge-end architecture-based industrial control device data processing and scheduling system in an embodiment;

[0027] Figure 4 An internal structure diagram of a computer device in an embodiment.

[0028] Legend: node architecture deployment module 11, edge configuration module 12, sensor endpoint network layout module 13, industrial data acquisition module 14, parallel rectification module 15, edge computing module 16, device regulation and control module 17. DETAILED DESCRIPTION

[0029] In order to make the purpose, technical scheme and advantages of the present application clearer, the present application will be further described in detail below in combination with the drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and not to limit the present application.

[0030] As shown in Figure 1 , the present application provides a cloud edge-end architecture-based industrial control device data processing and scheduling method, which comprises:

[0031] Step S100: deploying node architecture according to industrial control area distribution information to obtain industrial cloud edge-end node architecture information;

[0032] In an embodiment, as shown in Figure 2 , the industrial cloud edge-end node architecture information is obtained, and the step S100 of the present application further comprises:

[0033] Step S110: applying function labeling to the industrial control area distribution information to obtain industrial control area application function information;

[0034] Step S120: determining function area division criteria according to the industrial control area application function information;

[0035] Step S130: hierarchically dividing the industrial control area distribution information based on the function area division criteria to obtain industrial control area function hierarchical information;

[0036] Step S140: encoding the industrial control device set of the industrial control area function hierarchical information to obtain industrial control device hierarchical encoding information;

[0037] Step S150: based on the industrial control device hierarchical coding information, performing node architecture analysis to obtain the industrial cloud edge node architecture information.

[0038] In one embodiment, the industrial control device hierarchical coding information is obtained, and the step S140 of the present application further includes:

[0039] Step S141: constructing an industrial control device feature classifier, wherein the industrial control device feature classifier includes device type attributes, control level attributes, and production level attributes.

[0040] Step S142: based on the industrial control device feature classifier, performing feature labeling on the industrial control device set to obtain an industrial control device attribute feature set.

[0041] Step S143: determining a device hierarchical coding rule according to the industrial control area function hierarchical information and the industrial control device feature classifier.

[0042] Step S144: based on the device hierarchical coding rule, coding the industrial control device set to obtain the industrial control device hierarchical coding information.

[0043] Specifically, the industrial control device refers to an electronic device and system specially applied in the field of industrial automation control, mainly used for monitoring and managing industrial automation control systems and processes, realizing the automation and intelligent control and management of industrial equipment, and having high performance, high reliability, and anti-interference ability to cope with complex industrial environments. To improve the efficiency of industrial control device data processing, the present application adopts a cloud edge architecture to realize industrial data sensing and processing. The cloud edge architecture refers to handing over the storage, transmission, calculation, and security of data to the edge node for processing, and the application program is initiated on the edge side, which can produce faster network service response and meet the needs of various industries in real-time business, application intelligence, security and privacy protection, and other aspects of the cloud platform.

[0044] First, the distribution information of the industrial control area to be scheduled for processing is obtained, and the node architecture deployment is performed according to the industrial control area distribution information, that is, the data processing node deployment is performed according to the application function distribution of the area. Specifically, the industrial control area distribution information is marked with application functions, such as production area, processing area, raw material process area, power supply area, etc., to obtain the industrial control area application function information. Then, according to the industrial control area application function information, a function area division criterion is determined, which is a specific hierarchical division basis for each application function area and can be self-defined. For example, the production area is hierarchically divided according to the production line. Based on the function area division criterion, the industrial control area distribution information is hierarchically divided to obtain the detailed function hierarchy of each industrial control area, i.e., the industrial control area function hierarchical information.

[0045] To realize the rapid deployment of node architecture, the industrial control device set of the industrial control area function level information is encoded, and an industrial control device feature classifier is constructed. The industrial control device feature classifier is a classification type of industrial control device attribute features, including a device type attribute, i.e., a device production type; a control level attribute, i.e., a device production control level, for example, the control level of a general production line is high; and a production level attribute, i.e., a device production amount level. Based on the industrial control device feature classifier, the industrial control device set is classified and labeled by attributes respectively, and a corresponding industrial control device attribute feature set is obtained, which includes the device type attribute, the control level attribute, and the production level attribute of each industrial control device. According to the industrial control area function level information and the industrial control device feature classifier, a device level coding rule is determined, which is composed of area function level and device feature attribute, and its coding order, coding element, coding bit number, etc. can be regularly set by itself.

[0046] Based on the device level coding rule, the industrial control device set is encoded to obtain corresponding industrial control device level coding information, and based on the industrial control device level coding information, node architecture analysis is performed, i.e., the same node architecture deployment is set for the device area with the same coding preset bit number, and the industrial cloud edge node architecture information is quickly deployed. Through the coding deployment of cloud edge node architecture, it is used for comprehensive coverage of industrial control area data processing, and through the cloud edge architecture, the real-time calculation and analysis process is distributed on each processing node for fast processing, to ensure the real-time performance of data processing, and also reduce the risk of data transmission, realizing the collaborative processing of cloud, edge and end data interaction.

[0047] Step S200: Based on the industrial cloud edge node architecture information, edge configuration is performed to obtain edge control node information;

[0048] Step S300: According to the edge control node information, a distributed sensor endpoint network is laid out;

[0049] Step S400: Based on the distributed sensor endpoint network, the edge control node information is respectively subjected to industrial data collection to obtain a control node perception data stream set;

[0050] Specifically, edge configuration is performed based on the industrial cloud edge node architecture information, the edge configuration is an edge side deployment of cloud computing, and is divided into infrastructure edge and device edge. The edge configuration obtains edge control node information for data processing of the industrial control devices in the edge area. According to the edge control node information, a distributed sensor endpoint network is respectively arranged, the distributed sensor endpoint network is a device terminal data sensing sensor network of each control node, including various sensors such as temperature, humidity, and pressure, for real-time collection of operation data of the node industrial control device. Industrial data collection is performed on the edge control node information based on the distributed sensor endpoint network, a control node sensing data stream set corresponding to each edge node is obtained, and the comprehensiveness and real-time performance of data collection are improved.

[0051] Step S500: Obtain node data parallel rules, and parallel rectify the control node sensing data stream set based on the node data parallel rules to obtain a node parallel sensing data stream set.

[0052] In one embodiment, the node parallel sensing data stream set is obtained, and the step S500 of the present application further includes:

[0053] Step S510: Determine node data shunting rules and node data rectification rules according to the node data parallel rules.

[0054] Step S520: Perform interactive level shunting on the control node sensing data stream set based on the node data shunting rules to determine a node data interactive level flow direction.

[0055] Step S530: Mark the control node sensing data stream set as parallelable according to the node data interactive level flow direction to obtain a parallelable control node data stream set.

[0056] Step S540: Rectify the parallelable control node data stream set based on the node data rectification rules to generate the node parallel sensing data stream set.

[0057] In one embodiment, the parallelable control node data stream set is obtained, and the step S530 of the present application further includes:

[0058] Step S531: Sort the control node sensing data stream set based on the node data interactive level flow direction to determine a control node data upstream and downstream sequence.

[0059] Step S532: Determine a parallelable control node data stream according to the control node data upstream and downstream sequence.

[0060] Step S533: Aggregate data numbers of the parallelable control node data stream to obtain parallelable control node aggregation data numbers.

[0061] Step S534: Parallel data marking of the parallelable control node data flow based on the control node data upstream and downstream sequence and the parallelable control node converged data numbering, to obtain the parallelable control node data flow set.

[0062] Specifically, a node data parallel rule is obtained, which is a rule for considering other node perception data flows to be merged when edge control node data is processed. Based on the node data parallel rule, the control node perception data flow set is parallel rectified. First, the node data shunt rule and the node data rectification rule contained in the node data parallel rule are determined according to the node data parallel rule. Based on the node data shunt rule, the control node perception data flow set is interactively shunted. The node data shunt rule shunts according to node data interaction requirements, i.e., marks the next interaction flow direction of each node data, determines the node data interaction flow direction level quantity corresponding to each control node, and exemplarily, the next interaction level of a branch production line is the total production line flow direction, and the interaction level of the total production line is higher.

[0063] The control node perception data flow set is parallelly marked according to the node data interaction level flow direction. Specifically, first, the control node perception data flow set is sorted based on the node data interaction level flow direction, i.e., the perception data is sorted in ascending order of interaction level flow direction, to determine the control node data upstream and downstream sequence, wherein the interaction level of the downstream node is higher, and the corresponding summary perception data quantity is more. According to the control node data upstream and downstream sequence, the control node data that can be considered for summary is determined, for example, the data of the upstream and downstream production lines can be summarized, while the equipment wear data cannot be considered for summary, and the parallelable control node data flow is obtained by screening. The parallelable control node data flow is converged and numbered, i.e., the parallelable summary data is numbered according to the data node upstream and downstream, to obtain the parallelable control node converged data numbering.

[0064] Based on the control node data upstream and downstream sequence and the parallelable control node converged data numbering, the parallelable control node data flow is parallel data marked, i.e., according to the data flow direction association, the perception data flow numbering of other control nodes that can be summarized and processed for each parallelable node data flow is marked, to obtain the corresponding parallelable control node converged data numbering. Based on the node data rectification rule, the parallelable control node data flow set is rectified. The node data rectification rule is a rule for node data merging and rectification, i.e., the node data flows that can be merged are summarized and parallelly connected to generate a node parallel perception data flow set after the parallelable control node data is summarized. By parallel rectification of the control node data, the association comprehensiveness of node data processing is improved, and the edge processing accuracy of node data is further improved.

[0065] Step S600: performing edge computing on the node parallel perception data stream set based on the edge control node information to obtain a node industrial control device analysis information set;

[0066] In one embodiment, the node industrial control device analysis information set is obtained, and the step S600 of the present application further includes:

[0067] Step S610: constructing an industrial control device analysis feature model library through the industrial control device cloud;

[0068] Step S620: performing processing demand analysis on the edge control node information to obtain node data processing demand feature information;

[0069] Step S630: performing feature matching based on the node data processing demand feature information and the industrial control device analysis feature model library respectively to obtain a node industrial control device analysis feature model set;

[0070] Step S640: performing edge computing on the node parallel perception data stream set based on the node industrial control device analysis feature model set respectively to output the node industrial control device analysis information set.

[0071] Specifically, based on the edge control node information, the node parallel perception data stream set is subjected to edge computing, first, an industrial control device analysis feature model library is constructed through the industrial control device cloud, the industrial control device cloud is the cloud computing center node of the architecture and is the management and control end of edge computing of each control node, the industrial control device analysis feature model library is stored in the industrial control device cloud and is a set of industrial control device analysis models obtained by training historical data, which exemplarily includes industrial control device production analysis models, industrial control device running analysis models, industrial control device energy consumption analysis models and various device feature analysis models.

[0072] The edge control node information is subjected to processing demand analysis, that is, device control demand features that need to be processed by the edge control node are integrated, such as device production analysis demand, device production energy consumption analysis demand and the like, and corresponding node data processing demand feature information is obtained. Based on the node data processing demand feature information, feature matching is performed with the industrial control device analysis feature model library respectively to obtain a node industrial control device analysis feature model set matched with the demand features. Based on the node industrial control device analysis feature model set, edge computing analysis is performed on the node parallel perception data stream set respectively to obtain a device control analysis information set of each node, and then a node industrial control device analysis information set is integrated and output. Through model matching analysis based on node processing demand features, edge computing analysis is specified, and thus the data processing efficiency and processing accuracy of the control node are improved.

[0073] Step S700: integrate the node industrial control device analysis information set into the industrial control device cloud for scheduling analysis, obtain industrial control device cooperative scheduling parameters, and perform device adjustment control based on the industrial control device cooperative scheduling parameters.

[0074] In one embodiment, the industrial control device cooperative scheduling parameters are obtained, and the step S700 of the present application further includes:

[0075] Step S710: obtain a global industrial control device scheduling analysis model from the industrial control device cloud, wherein the global industrial control device scheduling analysis model includes an industrial control device abnormality analysis layer and a device cooperative scheduling layer.

[0076] Step S720: perform abnormality identification on the node industrial control device analysis information set based on the industrial control device abnormality analysis layer, and obtain industrial control device abnormality parameter information.

[0077] Step S730: perform scheduling analysis on the industrial control device abnormality parameter information using the device cooperative scheduling layer, and output the industrial control device cooperative scheduling parameters.

[0078] Specifically, the node industrial control device analysis information set is integrated and transmitted to the industrial control device cloud for global scheduling analysis. Specifically, a global industrial control device scheduling analysis model is obtained from the industrial control device cloud, wherein the global industrial control device scheduling analysis model is a neural network structure, is obtained by training historical data, and has a model function layer including an industrial control device abnormality analysis layer and a device cooperative scheduling layer. First, abnormality identification is performed on the node industrial control device analysis information set based on the industrial control device abnormality analysis layer, the industrial control device abnormality analysis layer is used for identifying and marking abnormal data, is obtained by training historical data abnormality labels, and industrial control device abnormality parameter information such as device energy consumption abnormal data and running abnormal data is analyzed and obtained.

[0079] Then, the device cooperative scheduling layer is used to perform scheduling analysis on the industrial control device abnormality parameter information, the device cooperative analysis layer is used for scheduling control analysis of device abnormality parameters, is obtained by training historical device abnormality data, and outputs industrial control device cooperative scheduling parameters, wherein the industrial control device cooperative scheduling parameters are control scheduling parameters of the industrial control device, such as adjusting production line device running time and optimizing industrial control device production parameters. Device adjustment control is performed based on the industrial control device cooperative scheduling parameters, the scheduling analysis accuracy is improved, and the industrial control device scheduling effect is ensured.

[0080] In one embodiment, as Figure 3As shown, a cloud edge architecture-based industrial control device data processing and scheduling system is provided, comprising: a node architecture deployment module 11, an edge configuration module 12, a sensor endpoint network layout module 13, an industrial data acquisition module 14, a parallel rectification module 15, an edge computing module 16, and a device adjustment control module 17, wherein:

[0081] The node architecture deployment module 11 is configured to deploy the node architecture according to the industrial control area distribution information, and obtain industrial cloud edge node architecture information.

[0082] The edge configuration module 12 is configured to perform edge configuration based on the industrial cloud edge node architecture information, and obtain edge control node information.

[0083] The sensor endpoint network layout module 13 is configured to layout a distributed sensor endpoint network according to the edge control node information.

[0084] The industrial data acquisition module 14 is configured to perform industrial data acquisition on the edge control node information based on the distributed sensor endpoint network, and obtain a control node perception data stream set.

[0085] The parallel rectification module 15 is configured to obtain node data parallel rules, perform parallel rectification on the control node perception data stream set based on the node data parallel rules, and obtain a node parallel perception data stream set.

[0086] The edge computing module 16 is configured to perform edge computing on the node parallel perception data stream set based on the edge control node information, and obtain a node industrial control device analysis information set.

[0087] The device adjustment control module 17 is configured to integrate and transmit the node industrial control device analysis information set to an industrial control device cloud for scheduling analysis, obtain industrial control device collaborative scheduling parameters, and perform device adjustment control based on the industrial control device collaborative scheduling parameters.

[0088] In one embodiment, the system further comprises:

[0089] An application function marking unit is configured to mark the application functions of the industrial control area distribution information, and obtain industrial control area application function information.

[0090] A region division criterion determination unit is configured to determine a function region division criterion based on the industrial control area application function information.

[0091] A region hierarchical division unit is configured to hierarchically divide the industrial control area distribution information based on the function region division criterion, and obtain industrial control area function hierarchical information.

[0092] A unit for encoding the industrial device set of the industrial area function level information to obtain industrial device level encoding information;

[0093] A node architecture analysis unit for performing node architecture analysis based on the industrial device level encoding information to obtain the industrial cloud edge node architecture information.

[0094] In one embodiment, the system further comprises:

[0095] A feature classifier construction unit for constructing an industrial device feature classifier, the industrial device feature classifier including device type attributes, control level attributes, and production level attributes;

[0096] A feature labeling unit for labeling the industrial device set based on the industrial device feature classifier to obtain an industrial device attribute feature set;

[0097] A level encoding rule determination unit for determining a device level encoding rule according to the industrial area function level information and the industrial device feature classifier;

[0098] A device level encoding obtaining unit for encoding the industrial device set based on the device level encoding rule to obtain the industrial device level encoding information.

[0099] In one embodiment, the system further comprises:

[0100] A node data parallel connection rule obtaining unit for determining node data shunt rules and node data rectification rules according to the node data parallel connection rules;

[0101] An interaction level shunt unit for performing interaction level shunting on the control node perception data stream set based on the node data shunt rules to determine node data interaction level flow directions;

[0102] A parallelizable labeling unit for labeling the control node perception data stream set according to the node data interaction level flow directions to obtain a parallelizable control node data stream set;

[0103] A data rectification unit for rectifying the parallelizable control node data stream set based on the node data rectification rules to generate the node parallel perception data stream set.

[0104] In one embodiment, the system further comprises:

[0105] A data stream sorting unit for sorting the control node perception data stream set based on the node data interaction level flow directions to determine control node data upstream and downstream sequences;

[0106] Parallel data flow determination unit, configured to determine parallel control node data flow according to the control node data upstream and downstream sequence;

[0107] Converged data numbering unit, configured to perform converged data numbering on the parallel control node data flow to obtain parallel control node converged data numbering;

[0108] Parallel data marking unit, configured to perform parallel data marking on the parallel control node data flow based on the control node data upstream and downstream sequence and the parallel control node converged data numbering to obtain the parallel control node data flow set.

[0109] In an embodiment, the system further comprises:

[0110] Characteristic model library construction unit, configured to construct an industrial control equipment analysis characteristic model library through the industrial control equipment cloud;

[0111] Processing demand analysis unit, configured to perform processing demand analysis on the edge control node information to obtain node data processing demand characteristic information;

[0112] Model characteristic matching unit, configured to perform characteristic matching based on the node data processing demand characteristic information and the industrial control equipment analysis characteristic model library respectively to obtain a node industrial control equipment analysis characteristic model set;

[0113] Data flow edge computing unit, configured to perform edge computing on the node parallel perception data flow set based on the node industrial control equipment analysis characteristic model set respectively to output the node industrial control equipment analysis information set.

[0114] In an embodiment, the system further comprises:

[0115] Scheduling analysis model acquisition unit, configured to acquire a global industrial control equipment scheduling analysis model according to the industrial control equipment cloud, the global industrial control equipment scheduling analysis model including an industrial control equipment anomaly analysis layer and a device collaborative scheduling layer;

[0116] Information anomaly identification unit, configured to perform anomaly identification on the node industrial control equipment analysis information set based on the industrial control equipment anomaly analysis layer to obtain industrial control equipment anomaly parameter information;

[0117] Collaborative scheduling parameter output unit, configured to perform scheduling analysis on the industrial control equipment anomaly parameter information by using the device collaborative scheduling layer to output the industrial control equipment collaborative scheduling parameter.

[0118] For specific embodiments of the industrial control equipment data processing and scheduling system based on the cloud edge-end architecture, reference can be made to the embodiments of the industrial control equipment data processing and scheduling method based on the cloud edge-end architecture described above, which will not be repeated here. Each module in the industrial control equipment data processing and scheduling system based on the cloud edge-end architecture described above can be realized by software, hardware, or a combination thereof, in whole or in part. The above-mentioned modules can be embedded in or independent of the processor in the computer device in hardware form, or can be stored in the memory in the computer device in software form, so as to be called and executed by the processor to perform the operations corresponding to each module.

[0119] In one embodiment, a computer device, which can be a server, is provided, and an internal structure diagram of the computer device can be as shown in Figure 4 The computer device includes a processor, a memory, and a network interface connected through a system bus. The processor of the computer device is configured to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program, and a database. The internal memory provides an environment for running the operating system and the computer program in the non-volatile storage medium. The database of the computer device is configured to store news data and time decay factors and other data. The network interface of the computer device is configured to communicate with an external terminal through a network connection. The computer program is executed by the processor to implement an industrial control equipment data processing and scheduling method based on a cloud edge-end architecture.

[0120] Those skilled in the art can understand that Figure 4 The structure shown in the above-mentioned figure is only a block diagram of part of the structure related to the scheme of the present application, and does not constitute a limitation on the computer device to which the scheme of the present application is applied. The specific computer device can include more or fewer components than those shown in the figure, or combine certain components, or have a different arrangement of components.

[0121] In one embodiment, a computer device is provided, comprising a memory and a processor, the memory storing a computer program, the processor implementing the following steps when executing the computer program: deploying a node architecture according to industrial control area distribution information, obtaining industrial cloud edge node architecture information; configuring an edge based on the industrial cloud edge node architecture information, obtaining edge control node information; deploying a distributed sensor endpoint network according to the edge control node information; collecting industrial data based on the distributed sensor endpoint network for the edge control node information, obtaining a control node perception data stream set; obtaining node data parallel rule, parallel rectifying the control node perception data stream set based on the node data parallel rule, obtaining a node parallel perception data stream set; performing edge computing on the node parallel perception data stream set based on the edge control node information, obtaining a node industrial control equipment analysis information set; integrating and transmitting the node industrial control equipment analysis information set to an industrial control equipment cloud end for scheduling analysis, obtaining an industrial control equipment collaborative scheduling parameter, and performing equipment regulation control based on the industrial control equipment collaborative scheduling parameter.

[0122] In one embodiment, a computer readable storage medium is provided, storing a computer program, the computer program being executed by a processor to implement the following steps: deploying a node architecture according to industrial control area distribution information, obtaining industrial cloud edge node architecture information; configuring an edge based on the industrial cloud edge node architecture information, obtaining edge control node information; deploying a distributed sensor endpoint network according to the edge control node information; collecting industrial data based on the distributed sensor endpoint network for the edge control node information, obtaining a control node perception data stream set; obtaining node data parallel rule, parallel rectifying the control node perception data stream set based on the node data parallel rule, obtaining a node parallel perception data stream set; performing edge computing on the node parallel perception data stream set based on the edge control node information, obtaining a node industrial control equipment analysis information set; integrating and transmitting the node industrial control equipment analysis information set to an industrial control equipment cloud end for scheduling analysis, obtaining an industrial control equipment collaborative scheduling parameter, and performing equipment regulation control based on the industrial control equipment collaborative scheduling parameter. Each technical feature of the above embodiments can be combined arbitrarily, in order to make the description concise, each technical feature in the above embodiments has not been described all possible combinations, however, as long as the combination of these technical features does not exist contradictory, it should be considered as the scope of the present disclosure.

[0123] The above-described embodiments are merely illustrative of several embodiments of the present application, which are described in more detail and in a specific and detailed manner, but should not be construed as limiting the scope of the patent. It should be noted that for those skilled in the art, several modifications and improvements can be made without departing from the concept of the present application, and these all belong to the protection scope of the present application. Therefore, the protection scope of the patent of the present application should be subject to the appended claims.

Claims

1. A cloud edge architecture-based industrial control device data processing and scheduling method, characterized in that, The method comprises: According to the industrial control area distribution information, the node architecture deployment is carried out, and the industrial cloud edge node architecture information is obtained; Based on the industrial cloud edge node architecture information, edge configuration is carried out, and edge control node information is obtained; According to the edge control node information, a distributed sensor endpoint network is laid out; Based on the distributed sensor endpoint network, the edge control node information is respectively collected, and a control node perception data stream set is obtained; Get node data parallel rule, based on the node data parallel rule, the control node perception data stream set is parallel rectified, and a node parallel perception data stream set is obtained; The node parallel perception data stream set is obtained, comprising: According to the node data parallel rule, the node data shunt rule and the node data rectification rule are determined; Based on the node data shunt rule, the control node perception data stream set is interactively shunted, and the node data interaction level flow direction is determined; According to the node data interaction level flow direction, the control node perception data stream set is marked as parallelable, and a parallelable control node data stream set is obtained; Based on the node data rectification rule, the parallelable control node data stream set is rectified, and the node parallel perception data stream set is generated; The parallelable control node data stream set is obtained, comprising: Based on the node data interaction level flow direction, the control node perception data stream set is sorted, and the control node data upstream and downstream sequence is determined; According to the control node data upstream and downstream sequence, the parallelable control node data stream is determined; The parallelable control node data stream is gathered and numbered, and the parallelable control node gathering data number is obtained; Based on the control node data upstream and downstream sequence and the parallelable control node gathering data number, the parallelable control node data stream is marked as parallel data, and the parallelable control node data stream set is obtained; Based on the edge control node information, the node parallel perception data stream set is edge calculated, and a node industrial control equipment analysis information set is obtained; The node industrial control equipment analysis information set is integrated and transmitted to the industrial control equipment cloud end for scheduling analysis, the industrial control equipment cooperative scheduling parameter is obtained, and the equipment adjustment control is carried out based on the industrial control equipment cooperative scheduling parameter.

2. The method of claim 1, wherein, The industrial cloud edge node architecture information is obtained, comprising: The application function of the industrial control area distribution information is marked, and the industrial control area application function information is obtained; According to the industrial control area application function information, the function area division criterion is determined; Based on the function area division criterion, the industrial control area distribution information is hierarchically divided, and the industrial control area function level information is obtained; The industrial control equipment set of the industrial control area function level information is encoded, and the industrial control equipment level encoding information is obtained; Based on the industrial control equipment level encoding information, the node architecture analysis is carried out, and the industrial cloud edge node architecture information is obtained.

3. The method of claim 2, wherein, The industrial control equipment level encoding information is obtained, comprising: The industrial control equipment feature classifier is constructed, and the industrial control equipment feature classifier comprises device type attribute, control level attribute and production grade attribute; Based on the industrial control equipment feature classifier, the industrial control equipment set is labeled with features to obtain an industrial control equipment attribute feature set; According to the industrial control area function level information and the industrial control equipment feature classifier, a device level coding rule is determined; Based on the device level coding rule, the industrial control equipment set is coded to obtain the industrial control equipment level coding information.

4. The method of claim 1, wherein, The node industrial control equipment analysis information set is obtained, including: Through the industrial control equipment cloud, an industrial control equipment analysis feature model library is constructed; The edge control node information is processed and demand analysis is performed to obtain node data processing demand feature information; Based on the node data processing demand feature information, feature matching is respectively performed with the industrial control equipment analysis feature model library to obtain a node industrial control equipment analysis feature model set; Based on the node industrial control equipment analysis feature model set, edge calculation is respectively performed on the node parallel sensing data stream set to output the node industrial control equipment analysis information set.

5. The method of claim 1, wherein, The industrial control equipment cooperative scheduling parameter is obtained, including: According to the industrial control equipment cloud, a global industrial control equipment scheduling analysis model is obtained, including an industrial control equipment abnormality analysis layer and a device cooperative scheduling layer; Based on the industrial control equipment abnormality analysis layer, abnormality recognition is performed on the node industrial control equipment analysis information set to obtain industrial control equipment abnormality parameter information; Using the device cooperative scheduling layer, scheduling analysis is performed on the industrial control equipment abnormality parameter information to output the industrial control equipment cooperative scheduling parameter.

6. An industrial control device data processing and scheduling system based on a cloud edge architecture, characterized in that, A cloud edge architecture-based industrial control equipment data processing and scheduling method for implementing any one of claims 1-5, the system comprising: A node architecture deployment module for deploying a node architecture according to industrial control area distribution information to obtain industrial cloud edge node architecture information; An edge configuration module for performing edge configuration based on the industrial cloud edge node architecture information to obtain edge control node information; A sensor endpoint network layout module for laying out a distributed sensor endpoint network according to the edge control node information; An industrial data acquisition module for performing industrial data acquisition on the edge control node information based on the distributed sensor endpoint network to obtain a control node sensing data stream set; A parallel rectification module for obtaining node data parallel rules and performing parallel rectification on the control node sensing data stream set based on the node data parallel rules to obtain a node parallel sensing data stream set; An edge calculation module for performing edge calculation on the node parallel sensing data stream set based on the edge control node information to obtain a node industrial control equipment analysis information set; A device regulation control module for integrating and transmitting the node industrial control equipment analysis information set to the industrial control equipment cloud for scheduling analysis to obtain an industrial control equipment cooperative scheduling parameter and performing device regulation control based on the industrial control equipment cooperative scheduling parameter. 7.A computer device, comprising a memory and a processor, wherein the memory stores a computer program, and the computer device is configured to perform the method according to any one of claims 1-6 when the computer program is executed by the processor. The processor executes the computer program to implement the steps of the method of any one of claims 1 to 5.

8. A computer-readable storage medium having stored thereon a computer program, characterized in that, The computer program is executed by the processor to implement the steps of the method of any one of claims 1 to 5.

Images