Edge control device of an industrial control system and industrial control system

Abstract

The application relates to an edge control device of an industrial control system and the industrial control system. The edge control device comprises a data platform kernel, which is used for acquiring original process data of a target device and original peripheral data of multiple dimensions in the industrial control system, performing data fusion or data analysis based on the original process data and the original peripheral data to obtain intermediate data, performing multi-dimensional linkage verification on the original process data based on the intermediate data to obtain the reliability of the original process data, and generating auxiliary control data when the reliability of the original process data is lower than a preset value; and a logic control kernel, which is used for collecting and controlling the target device based on the original process data of the target device, and performing linkage decision control on the target device based on the auxiliary control data and the original process data when the auxiliary control data is received, so as to realize control loop of the industrial control system. The application can realize the control loop of the industrial control system.

Description

Technical Field

[0001] This invention relates to the field of industrial control technology, and in particular to an edge control device and an industrial control system for an industrial control system. Background Technology

[0002] Currently, the industrial control field mostly uses DCS (Distributed Control System) or PLC (Programmable Logic Controller) as the core equipment for data acquisition and field control. These devices include controllers, input / output modules, communication interfaces, monitoring software, and other equipment to monitor and control the process. With the development of modern technology, breakthroughs in cutting-edge intelligent technologies in the IT (Information Technology) industry, research on process mechanism models, and the intersection and integration of various disciplines, the requirements for field control are becoming increasingly higher. The requirements for data acquisition and control are no longer satisfied with the existing conventional acquisition and control of analog input / output and digital input / output. The penetration of intelligence and machine learning enables the solution of prediction and analysis problems that were originally impossible to achieve with PLC and DCS. The development of science and technology has given the original DCS and PLC more possibilities.

[0003] In existing technologies, some industrial sites have introduced machine learning, data prediction, and analysis techniques to verify data in process control. However, this is generally done through a separate server, isolated from the industrial control network. That is, existing industrial control systems primarily use machine learning and data prediction analysis for post-process analysis of industrial control, but cannot influence the currently operating industrial control system in real time. Therefore, they cannot achieve closed-loop management of data acquisition, data analysis, data verification, data linkage, and decision control; they merely serve as a supplementary means of industrial control process monitoring and cannot achieve the goal of comprehensively optimizing on-site control.

[0004] Furthermore, common problems in the field of industrial control, such as inaccurate detection instruments leading to monitoring data failure, equipment malfunctions leading to equipment failure, instrument failures leading to interlocking action failures, and missing data from non-measuring points, have not yet found good solutions, resulting in a constant stream of production safety issues. Summary of the Invention

[0005] (a) Technical problems to be solved

[0006] In view of the above-mentioned shortcomings and deficiencies of the prior art, the present invention provides an edge control device and an industrial control system for an industrial control system, which solves the technical problems of inaccurate data detection and control and inability to verify data in existing industrial field control, thus making it impossible to achieve closed-loop management.

[0007] (II) Technical Solution

[0008] To achieve the above objectives, the main technical solutions adopted by the present invention include:

[0009] In a first aspect, embodiments of the present invention provide an edge control device for an industrial control system, comprising:

[0010] The data platform kernel is used to acquire raw process data and multiple dimensions of raw peripheral data from target equipment in an industrial control system; perform data fusion or data analysis based on the raw process data and the multiple dimensions of raw peripheral data to obtain intermediate data; and perform multi-dimensional linkage verification on the raw process data based on the intermediate data to obtain the reliability of the raw process data; and,

[0011] When the reliability of the original process data is lower than a preset value, auxiliary control data is generated.

[0012] The logic control kernel is used to acquire and control the target device based on its raw process data; and,

[0013] When the auxiliary control data is received, the target device is subjected to linkage decision control based on the auxiliary control data and the original process data to realize the control closed loop of the industrial control system.

[0014] Optionally, the edge control device further includes:

[0015] The mechanism model kernel is used to receive the raw process data and, based on the raw process data, predict the process data of the non-collection points of the target device as intermediate data according to the pre-deployed mechanism model.

[0016] Optionally, the data platform kernel includes:

[0017] Data fusion service is used to acquire raw process data and raw peripheral data from multiple dimensions of the target device;

[0018] Data analysis services are used to preprocess and analyze the raw process data or raw peripheral data to obtain intermediate data;

[0019] The linkage verification service is used to perform multi-dimensional linkage verification on the original process data based on the intermediate data to obtain the reliability of the original process data; and when the reliability of the original process data is lower than a preset value, auxiliary control data is generated.

[0020] Optionally, the raw surrounding data includes at least one of: video data about the target device, voiceprint data about the target device, and monitoring data of the surrounding system of the target device;

[0021] The data analysis service includes at least one of the following components:

[0022] The data statistical analysis component is used to perform statistical analysis based on the original process data or the monitoring data of the surrounding system of the target equipment, to calculate index data, calculate data correlation, or determine the first working state parameter of the target equipment as intermediate data based on the monitoring data of the surrounding system of the target equipment.

[0023] A video analytics component is used to identify second operating status parameters of the target device as intermediate data based on video data from the target device.

[0024] The voiceprint analysis component is used to identify the third operating status parameters of the target device as intermediate data based on the voiceprint data of the target device.

[0025] A text recognition component is used to extract feature parameters about the target device from raw surrounding data as intermediate data;

[0026] A trend prediction component is used to predict trends based on monitoring data from the surrounding systems of the target device, so as to obtain future trend data of the target device as intermediate data.

[0027] The optimization solution component is used to perform optimization solutions based on the original process data or monitoring data of the surrounding systems of the target equipment, in order to determine the optimal control parameters of the target equipment as intermediate data.

[0028] Optionally, in the linked verification service, the step of performing multi-dimensional linked verification on the original process data based on the intermediate data to obtain the reliability of the original process data includes:

[0029] Compare the consistency between the intermediate data and the original process data to calculate the reliability of the original process data; and / or,

[0030] The reliability of the original process data is calculated by evaluating the reliability of the original process data based on the intermediate data; and / or,

[0031] The reliability of the original process data is calculated by performing a feasibility weight evaluation based on the intermediate data.

[0032] Optionally, when the target device is a motor,

[0033] The original process data of the target device includes: process temperature data of the motor;

[0034] The monitoring data of the target equipment's peripheral system includes: voltage and current data of the motor collected by the voltage and current sampling module;

[0035] The video data of the target device includes: optical video data about the motor acquired by the optical image acquisition device and infrared video data about the motor acquired by the infrared image acquisition device.

[0036] In the data analysis service,

[0037] The data statistical analysis component is used to obtain the current first temperature of the motor based on the motor's process temperature data; and

[0038] The first abnormal state of the motor is used as the first operating state parameter to determine the first abnormal state of the motor based on the motor's voltage and current data; the first abnormal state includes: abnormal power supply voltage, overvoltage fault, and overcurrent fault;

[0039] The video analysis component is used to determine the current second temperature of the motor based on the motor's infrared video data; and,

[0040] The second abnormal state of the motor is used as a second operating state parameter to determine the second abnormal state of the motor based on optical video data about the motor; the second abnormal state includes at least one of motor shaft stoppage and process stall.

[0041] Optionally, in the linkage verification service, the step of performing multi-dimensional linkage verification on the original process data based on the intermediate data to obtain the reliability of the original process data; and, when the reliability of the original process data is lower than a preset value, generating auxiliary control data, including:

[0042] The consistency between the first temperature and the second temperature is compared to obtain the comparison result;

[0043] Based on the second temperature, the first abnormal state, and the second abnormal state, a credibility evaluation is performed on the first temperature to obtain a credibility evaluation result.

[0044] The reliability of the process temperature data is calculated based on the comparison results and the reliability evaluation results.

[0045] When the reliability is less than a preset value, auxiliary control data is generated based on the first temperature, the second temperature, and the reliability.

[0046] Optionally, the logic control kernel includes:

[0047] A logic control service is used to generate control parameters based on raw control data, the control parameters being used to control the operation of the target device;

[0048] The linkage control service is used to calibrate the original process data or adjust the control parameters based on the auxiliary control data when the auxiliary control data is received, so as to realize the closed-loop control of the industrial control system.

[0049] Secondly, embodiments of the present invention provide an industrial control system, including an edge control device and a target device, wherein the edge control device is communicatively connected to the target device to control the operation of the target device; wherein the edge control device is the edge control device of the industrial control system described in the first aspect.

[0050] (III) Beneficial Effects

[0051] The edge control device provided in this embodiment of the invention includes a data platform kernel and a logic control kernel. The data platform kernel can acquire raw process data and multi-dimensional raw peripheral data of a target device in an industrial control system; perform data fusion or data analysis based on the raw process data and multi-dimensional raw peripheral data to obtain intermediate data; perform multi-dimensional linkage verification on the raw process data based on the intermediate data to determine the reliability of the raw process data; and generate auxiliary control decisions when the reliability of the raw process data is lower than a preset value. The logic control kernel can collect and control the target device based on the raw process data of the target device; and when it receives auxiliary control decisions, it performs coordinated linkage control on the target device based on the auxiliary control decisions and the raw process data to achieve a closed-loop control of the industrial control system. The data platform kernel collects and analyzes multi-dimensional data about the target device, generates auxiliary control decisions, and sends them to the logic control kernel to influence the logic control kernel's control effect on the target device, thereby achieving closed-loop management of industrial control process data acquisition, data analysis, data verification, data linkage, and decision control, and optimizing the on-site control effect.

[0052] Secondly, the edge control device provided in this embodiment of the invention also includes a mechanism model kernel, which can predict the process data of the non-collection point of the target device as intermediate data based on the original process data and according to the pre-deployed mechanism model of the target device, so as to provide richer data support for data verification and data linkage of the data platform kernel.

[0053] Finally, the edge control device provided in this embodiment of the invention is based on the traditional DCS and PLC framework, further enriching the edge control device's multi-dimensional data acquisition capabilities, multi-dimensional data fusion capabilities, multi-dimensional data analysis capabilities, and multi-dimensional data joint verification capabilities to ensure the safe and reliable operation of field control. Compared with existing technologies, it causes less change to the industrial site, thus having a higher acceptance rate among users and providing greater assurance of reliability and safety. Attached Figure Description

[0054] Figure 1 This is a schematic diagram of the architecture of an edge control device for an industrial control system provided in the embodiment;

[0055] Figure 2 This is a schematic diagram of the architecture of an edge control device for another industrial control system provided in the embodiment. Detailed Implementation

[0056] To better explain and facilitate understanding of the present invention, the present invention will be described in detail below with reference to the accompanying drawings and specific embodiments.

[0057] To better understand the technical solutions provided by this invention, the technical terms involved in this invention are explained below:

[0058] DCS Control System: DCS is the abbreviation for Distributed Control System, also known as a distributed control system in the domestic automatic control industry. A distributed control system, or sometimes referred to as a distributed system, is a new type of computer control system relative to a centralized control system. It is developed and evolved from centralized control systems. It is a multi-level computer system composed of process control and process monitoring levels linked by a communication network. It integrates 4C technologies: computer, communication, display, and control. Its basic principles are distributed control, centralized operation, hierarchical management, flexible configuration, and convenient configuration.

[0059] Industrial process mechanism model: also known as a white-box model. A precise mathematical model established based on the internal mechanisms of an object, production process, or the transmission mechanism of material flow. It is a mathematical model of the object or process obtained based on mass balance equations, energy balance equations, momentum balance equations, phase balance equations, as well as certain physical property equations, chemical reaction laws, and basic circuit laws.

[0060] Multi-dimensional data: Basic data on the same object obtained through various acquisition and collection methods. For example, the pressure at a certain point in a pipeline can be obtained through pressure transmitters, pressure gauges, video, mechanism model calculations, communication access, etc. Data from multiple dimensions can be jointly verified to determine whether it is normal.

[0061] Linkage verification control: Based on the original PLC or DCS interlocking control, multi-dimensional data verification is used to make decisions on whether to execute linkage or whether linkage conditions and values ​​need to be adjusted, so as to control the object based on multi-dimensional data.

[0062] Data Acquisition and Fusion: After multi-dimensional data acquisition, data standards need to be defined and stored in a unified database to facilitate subsequent data retrieval and analysis.

[0063] Edge controllers: In addition to fulfilling the control functions of workstations or production lines, they enhance the interface and computing capabilities of industrial equipment, thereby improving the applicability of industrial equipment.

[0064] To better understand the above technical solutions, exemplary embodiments of the present invention will be described in more detail below with reference to the accompanying drawings. Although exemplary embodiments of the present invention are shown in the drawings, it should be understood that the present invention can be implemented in various forms and should not be limited to the embodiments set forth herein. Rather, these embodiments are provided so that the present invention can be understood more clearly and thoroughly, and that the scope of the present invention can be fully conveyed to those skilled in the art.

[0065] Example 1

[0066] like Figure 1 As shown, this embodiment provides an edge control device for an industrial control system, including: a data platform kernel and a logic control kernel, specifically:

[0067] The data platform kernel is used to acquire raw process data and raw peripheral data of multiple dimensions of target equipment in the industrial control system; and to perform data fusion or data analysis based on the raw process data and raw peripheral data of multiple dimensions to obtain intermediate data; and to perform multi-dimensional linkage verification on the raw process data based on the intermediate data to obtain the reliability of the raw process data; and, when the reliability of the raw process data is lower than a preset value, to generate auxiliary control data.

[0068] The aforementioned multi-dimensional raw peripheral data refers to data collected or acquired by peripheral systems used to support or monitor the target equipment, in addition to the direct process data of the target equipment included in the main industrial process. For example, in the oil and gas storage field, the main industrial process is a valve and pump control system used to control the flow of oil and gas; the target equipment is the valve or pump; and the peripheral systems of the target equipment include the station's safety instrument system, gas system, compressor control system of the compressor station, air compressor control system of the gas storage facility, nitrogen generator control system, metering system, tank metering system, electrical SCADA, etc., and may also include third-party systems such as perimeter security, inspection, and personnel positioning. The aforementioned raw peripheral data can be accessed through the communication interface of the edge controller. The communication interface can be an industrial interface such as an Ethernet interface, serial port, or 5G wireless interface.

[0069] The logic control kernel is used to collect and control the target device based on the raw process data of the target device; and when the auxiliary control data is received, to perform linkage decision control on the target device based on the auxiliary control data and the raw process data, so as to realize the control closed loop of the industrial control system.

[0070] More specifically, the data platform kernel includes: data fusion service, data analysis service, and linkage verification service, as detailed below:

[0071] The data fusion service is used to acquire raw process data and raw peripheral data from multiple dimensions of the target device. It is primarily used for the aggregation of multi-dimensional data, and to facilitate subsequent data retrieval and management, it can also perform format standardization processing on the aforementioned dimensional data.

[0072] The data analysis service is used to preprocess and analyze the raw process data or raw peripheral data to obtain intermediate data. The preprocessing includes data cleaning, data integration, data reduction, and data transformation, and may specifically include handling missing values, outlier removal, and noise reduction.

[0073] The linkage verification service is used to perform multi-dimensional linkage verification on the original process data based on the intermediate data to obtain the reliability of the original process data; and when the reliability of the original process data is lower than a preset value, auxiliary control data is generated.

[0074] Specifically, the auxiliary control data may be first reference data used to calibrate the original process data, or second reference data used to calibrate the control parameters output by the logic control kernel.

[0075] The logic control kernel includes:

[0076] A logic control service is used to generate control parameters based on raw control data, which are used to control the operation of the target device.

[0077] The linkage control service is used to calibrate the original process data or adjust the control parameters based on the auxiliary control data when the auxiliary control data is received, so as to realize the closed-loop control of the industrial control system.

[0078] In a preferred embodiment of this invention, the raw peripheral data includes at least one of: video data of the target device, voiceprint data of the target device, and monitoring data of the target device's peripheral system. The monitoring data is determined based on the target device's peripheral system. For example, if the target device's peripheral system is a pressure monitoring system, the monitoring data is pressure data; if the target device's monitoring system is a metering system, the monitoring data is metering data; if the target device's peripheral system is an electrical monitoring system, the monitoring data is electrical data, which further includes voltage data, current data, power data, etc.

[0079] Based on the aforementioned raw surrounding data, the data analysis service and the linkage verification service are configured as follows:

[0080] The data analysis service includes at least one of the following components: data statistical analysis, video analysis, voiceprint analysis, text recognition, trend prediction, and optimization solution, as detailed below:

[0081] The data statistical analysis component is used to perform statistical analysis based on the original process data or monitoring data from the surrounding system of the target equipment. This analysis calculates indicator data, data correlation, or uses the monitoring data from the surrounding system as intermediate data to determine the first operating state parameters of the target equipment. Specifically, the indicator data can be calculated based on the original process data and surrounding data according to a preset indicator formula. This indicator data is used to determine whether the current industrial control system meets corresponding control indicators, such as energy utilization rate or raw material utilization rate. The data correlation refers to the correlation between multi-dimensional data; for example, for a pipeline, its outlet pressure is positively correlated with its inlet pressure, therefore the inlet pressure data and outlet pressure data of this pipeline have a high correlation.

[0082] The video analytics component is used to identify second operating status parameters of the target device as intermediate data based on the target device's video data.

[0083] The voiceprint analysis component is used to identify the third operating status parameters of the target device as intermediate data based on the voiceprint data of the target device.

[0084] A text recognition component is used to extract feature parameters about the target device from raw surrounding data as intermediate data. The text recognition component may be a publicly available text interpretation tool.

[0085] The trend prediction component is used to predict trends based on monitoring data from the surrounding systems of the target device, obtaining future trend data of the target device as intermediate data. Specifically, the trend prediction component can be a machine learning model, a deep learning model, or other statistically based prediction model.

[0086] The optimization solution component is used to perform optimization solutions based on the original process data or monitoring data of the surrounding systems of the target equipment, in order to determine the optimal control parameters of the target equipment as intermediate data.

[0087] Based on the above components, the intermediate data in this embodiment may include one or more of the following: indicator data about the target device, data correlation, first working state parameters, second working state parameters, third working state parameters, feature parameters, future trend data, and optimal control parameters.

[0088] More specifically, based on the aforementioned intermediate data, in the aforementioned collaborative verification service, the step of performing multi-dimensional collaborative verification on the original process data based on the intermediate data to obtain the reliability of the original process data specifically includes:

[0089] The reliability of the original process data is calculated by comparing the consistency between the intermediate data and the original process data; and / or, the reliability of the original process data is calculated by evaluating the credibility of the original process data based on the intermediate data; and / or, the reliability of the original process data is calculated by evaluating the feasible weights of the original process data based on the intermediate data.

[0090] In another preferred embodiment of this invention, in order to provide the data platform kernel with more dimensions of data support, the edge control device further includes a mechanism model kernel.

[0091] The mechanism model kernel is used to receive the raw process data and, based on the raw process data, predict the process data of the non-collection points of the target device as intermediate data according to the pre-deployed mechanism model of the target device.

[0092] Specifically, the mechanism model can be a process model, equipment model, or physical property model, used to perform process analysis calculations, equipment analysis calculations, physical property analysis calculations, etc., on the main industrial process, so as to realize the calculation, analysis and prediction of process data that cannot be collected in traditional industrial control systems, and provide in-depth data services.

[0093] The mechanism model kernel can be integrated with the data platform kernel and the logic control kernel into the same physical device, or it can be distributed at the edge or in the cloud.

[0094] When the mechanism model kernel is distributed across the edge or cloud, the mechanism models deployed within the kernel can undergo version control and updates, and the mechanism model data can be coordinated with cloud model data, based on a cloud-edge collaboration mechanism. The coordinated data consists of the process data from the edge mechanism model's completed calculations, which interacts with multiple mechanism model data in the cloud, achieving unification of any edge or cloud mechanism model data. Simultaneously, after acquiring edge data, the cloud model can significantly reduce the computation time and network bandwidth required for cloud model operations.

[0095] In this embodiment of the invention, the problem of single data source and inability of multi-dimensional data analysis to participate in logical operations in traditional process industries is addressed by integrating the data platform kernel, logic control kernel, and mechanism model kernel, and enabling data exchange between the kernels through a reliable bus. This improves the reliability and safety of the entire device, and allows auxiliary control data calculated based on the data platform kernel and mechanism model kernel to be transmitted to the logic control kernel through the internal data bus to complete linkage control under multi-dimensional data verification.

[0096] In the edge control device provided in this embodiment of the invention, the data platform kernel collects and analyzes multi-dimensional data about the target device, generates auxiliary control decisions, and sends them to the logic control kernel to influence the control effect of the logic control kernel on the target device. This achieves closed-loop management of industrial control process data collection, data analysis, data verification, data linkage, and decision control, optimizing the on-site control effect. The mechanism model kernel, based on the original process data and according to a pre-deployed mechanism model of the target device, predicts process data from non-collection points of the target device as intermediate data, providing richer data support for data verification and data linkage of the data platform kernel.

[0097] Example 2

[0098] To better understand the edge control device in Embodiment 1, this embodiment will be described in detail in the context of the oil and gas storage field.

[0099] like Figure 2 As shown, the edge control device provided in this embodiment includes a data platform kernel, a logic control kernel, and a mechanism model kernel, as detailed below:

[0100] The data platform kernel is used to acquire raw process data and raw peripheral data of multiple dimensions of target equipment in the industrial control system; and to perform data fusion or data analysis based on the raw process data and raw peripheral data of multiple dimensions to obtain intermediate data; and to perform multi-dimensional linkage verification on the raw process data based on the intermediate data to obtain the reliability of the raw process data; and, when the reliability of the raw process data is lower than a preset value, to generate auxiliary control data.

[0101] Specifically, the data platform kernel is used to perform data prediction based on bad data, optimization solutions based on big data, video recognition based on video data, and statistical analysis based on historical data based on the original process data and original surrounding data to obtain intermediate data. This intermediate data is used to perform multi-dimensional linkage verification on the original process data to determine its reliability. When the reliability of the original process data is lower than a preset value, auxiliary control data is generated to assist the logic control kernel in improving the control effect on the target device. More specifically, the data platform control kernel can perform linkage verification on the original process data based on the results of video recognition, or perform multi-dimensional verification based on multi-dimensional data provided by a third-party system; the auxiliary control data can be a chain warning based on a built-in diagnostic system, or an interlocking decision based on multi-verification.

[0102] The logic control kernel is used to collect and control the target device based on its raw process data; and, when receiving the auxiliary control data, to perform coordinated decision-making control on the target device based on the auxiliary control data and the raw process data, thereby achieving a closed-loop control of the industrial control system. Specifically, the logic control kernel can adjust the raw process data or the control parameters output by the logic control kernel according to the auxiliary control data.

[0103] The mechanism model kernel is used to receive the raw process data and, based on the raw process data, predict the process data of the non-collection points of the target device as intermediate data according to the pre-deployed mechanism model of the target device.

[0104] Specifically, the mechanism kernel model includes one or more of the following for property calculation: natural gas property parameter calculation model, standard state gas property parameter calculation model, crude oil viscosity-temperature characteristic analysis model, and crude oil temperature characteristic analysis model; one or more of the following for process analysis: liquid pipeline water hammer analysis model, hot oil pipeline temperature distribution model, shutdown temperature drop time calculation model, gas pipeline friction temperature distribution model, shutdown venting time calculation model, and heating furnace process calculation model; and one or more of the following for equipment analysis: centrifugal pump characteristic dynamic analysis model, centrifugal pump performance conversion model, compressor characteristic dynamic analysis model, compressor characteristic dynamic analysis model, compressor performance conversion model, dome tank evaporation loss calculation model, and floating roof tank breathing loss model.

[0105] In a preferred embodiment of this invention, the target device is a motor used in a pump for controlling the flow of oil and gas in the field of oil and gas storage. Based on the aforementioned edge controller, its working principle is specifically explained as follows:

[0106] When the target device is a motor

[0107] The raw process data of the target device includes: process temperature data of the motor.

[0108] The monitoring data of the target device's peripheral system includes: voltage and current data of the motor collected by the voltage and current sampling module.

[0109] The video data of the target device includes: optical video data about the motor acquired by the optical image acquisition device and infrared video data about the motor acquired by the infrared image acquisition device.

[0110] In the data analysis service of the data platform kernel,

[0111] The data statistical analysis component is used to obtain the current first temperature of the motor based on the motor's process temperature data; and to determine the first abnormal state of the motor as the first operating state parameter based on the motor's voltage and current data; the first abnormal state includes: abnormal power supply voltage, overvoltage fault, and overcurrent fault.

[0112] The video analysis component is used to determine the current second temperature of the motor based on the infrared video data of the motor; and to determine the second abnormal state of the motor as a second operating state parameter based on the optical video data of the motor; the second abnormal state includes at least one of motor shaft stoppage and process stall.

[0113] In the aforementioned linkage verification service, the process of performing multi-dimensional linkage verification based on the first temperature, second temperature, first operating state parameter, and second operating state parameter, and the process of generating auxiliary control data specifically include:

[0114] A1. Compare the consistency between the first temperature and the second temperature to obtain the comparison result.

[0115] A2. Based on the second temperature, the first abnormal state, and the second abnormal state, a reliability evaluation is performed on the first temperature to obtain a reliability evaluation result. Specifically, the reliability evaluation result can be determined based on the error rate between the first temperature and the second temperature. The higher the error rate, the lower the reliability of the process temperature data. The specific reliability evaluation value can be determined according to a preset evaluation standard.

[0116] A3. Calculate the reliability of the process temperature data based on the comparison results and reliability evaluation results.

[0117] Specifically, the reliability can be obtained by weighted average of the comparison results and the credibility evaluation results, or by other calculation methods.

[0118] A4. Determine whether the reliability is less than a preset value.

[0119] If not, proceed to A1 to perform linkage verification of the new process temperature data;

[0120] If so, auxiliary control data is generated based on the first temperature, the second temperature, and the reliability, and the auxiliary control data is sent to the logic control kernel to assist in adjusting its output control parameters.

[0121] In existing technologies, motor control is typically based solely on process temperature data. For example, when the process temperature exceeds 70°C, a stop command is used to halt the motor. This control method has the following drawbacks: ① The reliability of process temperature data from a single source is unknowable; ② It is impossible to determine whether the temperature detection loop used to collect the process temperature data is malfunctioning; ③ It is impossible to determine whether the motor has already executed a stop command and entered a stopped state. The edge controller provided in this embodiment, based on the above working principle, can perform linkage verification of process temperature data using infrared video data. The verification results can verify the abnormal state of the temperature detection loop and verify the motor's operating state using optical video data, motor voltage data, and current data. Furthermore, it can determine the abnormal state of the motor using the motor's first and second operating state parameters, thereby providing more comprehensive reference information for the logic control kernel.

[0122] Furthermore, this embodiment also provides an industrial control system, including an edge control device and a target device, wherein the edge control device is communicatively connected to the target device to control the operation of the target device; wherein the edge control device is the edge control device of the industrial control system described in Embodiment 1 or 2.

[0123] Since the edge control device provided in this embodiment of the invention is based on the traditional DCS and PLC framework, it further enriches the edge control device's multi-dimensional data acquisition capabilities, multi-dimensional data fusion capabilities, multi-dimensional data analysis capabilities, and multi-dimensional data joint verification capabilities to ensure the safe and reliable operation of field control. Therefore, it makes minimal changes to existing industrial control systems, resulting in higher user acceptance and greater assurance of reliability and security.

[0124] Since the systems / devices described in the above embodiments of the present invention are systems / devices used to implement the methods of the above embodiments of the present invention, those skilled in the art can understand the specific structure and modifications of the systems / devices based on the methods described in the above embodiments of the present invention, and therefore will not be repeated here. All systems / devices used in the methods of the above embodiments of the present invention fall within the scope of protection of the present invention.

[0125] Those skilled in the art will understand that embodiments of the present invention can be provided as methods, systems, or computer program products. Therefore, the present invention can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, the present invention can take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0126] This invention is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the invention. It will be understood that each block of the flowchart illustrations and / or block diagrams, as well as combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions.

[0127] It should be noted that any reference numerals placed between parentheses in the claims should not be construed as limiting the claims. The word "comprising" does not exclude the presence of components or steps not listed in the claims. The word "a" or "an" preceding a component does not exclude the presence of a plurality of such components. The invention can be implemented by means of hardware comprising several different components and by means of a suitably programmed computer. In claims that enumerate several means, several of these means may be embodied by the same hardware. The use of the terms first, second, third, etc., is merely for convenience of expression and does not indicate any order. These terms can be understood as part of the component names.

[0128] Furthermore, it should be noted that in the description of this specification, the terms "one embodiment," "some embodiments," "embodiment," "example," "specific example," or "some examples," etc., refer to specific features, structures, materials, or characteristics described in connection with that embodiment or example, which are included in at least one embodiment or example of the present invention. In this specification, the illustrative expressions of the above terms do not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials, or characteristics described may be combined in any suitable manner in one or more embodiments or examples. Furthermore, without contradiction, those skilled in the art can combine and integrate the different embodiments or examples described in this specification, as well as the features of different embodiments or examples.

[0129] Although preferred embodiments of the invention have been described, those skilled in the art, upon learning the basic inventive concept, can make other changes and modifications to these embodiments. Therefore, the claims should be interpreted to include both the preferred embodiments and all changes and modifications falling within the scope of the invention.

[0130] Obviously, those skilled in the art can make various modifications and variations to this invention without departing from its spirit and scope. Therefore, if these modifications and variations fall within the scope of the claims of this invention and their equivalents, then this invention should also include these modifications and variations.

Claims

1. An edge control device for an industrial control system, characterized in that, include: The data platform kernel is used to acquire raw process data and raw peripheral data from multiple dimensions of target equipment in industrial control systems. Intermediate data is obtained by performing data fusion or data analysis based on the original process data and original peripheral data from multiple dimensions. The mechanism model kernel is used to receive the raw process data and, based on the raw process data, predict the process data of the non-collection points of the target device as intermediate data according to the pre-deployed mechanism model. The data platform kernel is also used to perform multi-dimensional linkage verification on the original process data based on the intermediate data obtained from the data fusion or data analysis, in order to obtain the reliability of the original process data; wherein, the intermediate data can also be obtained based on the mechanism model kernel; the intermediate data includes one or more of the following: indicator data of the target device, data correlation degree, first working state parameters, second working state parameters, third working state parameters, characteristic parameters, future trend data, and optimal control parameters; and, When the reliability of the original process data is lower than a preset value, auxiliary control data is generated. The logic control kernel is used to acquire raw process data from the target device and generate control parameters based on the raw control data; and, When the auxiliary control data is received, the original process data is calibrated or the control parameters are adjusted based on the auxiliary control data to perform linkage decision control on the target device, so as to realize the control closed loop of the industrial control system. The mechanism model kernel, the data platform kernel, and the logic control kernel are integrated in the same edge control device. The mechanism model deployed in the mechanism model kernel is version controlled and updated based on the cloud-edge collaboration mechanism. The mechanism model data and the cloud model data are collaborative. The collaborative data is the process data calculated by the edge mechanism model and interacts with multiple mechanism model data in the cloud to achieve the unification of any edge mechanism model data or cloud mechanism model data.

2. The edge control device according to claim 1, characterized in that, The data platform kernel includes: Data fusion service is used to acquire raw process data and raw peripheral data from multiple dimensions of the target device; Data analysis services are used to preprocess and analyze the raw process data or raw peripheral data to obtain intermediate data; The linkage verification service is used to perform multi-dimensional linkage verification on the original process data based on the intermediate data to obtain the reliability of the original process data; and when the reliability of the original process data is lower than a preset value, auxiliary control data is generated.

3. The edge control device according to claim 2, characterized in that, The original surrounding data includes at least one of the following: video data about the target device, voiceprint data about the target device, and monitoring data of the surrounding system of the target device. The data analysis service includes at least one of the following components: The data statistical analysis component is used to perform statistical analysis based on the original process data or the monitoring data of the target equipment's surrounding system, to calculate index data, calculate data correlation, or determine the first working state parameter of the target equipment as intermediate data based on the monitoring data of the target equipment's surrounding system. A video analytics component is used to identify second operating status parameters of the target device as intermediate data based on video data from the target device. The voiceprint analysis component is used to identify the third operating status parameters of the target device as intermediate data based on the voiceprint data of the target device. A text recognition component is used to extract feature parameters about the target device from raw surrounding data as intermediate data; A trend prediction component is used to predict trends based on monitoring data from the surrounding systems of the target device, so as to obtain future trend data of the target device as intermediate data. The optimization solution component is used to perform optimization solutions based on the original process data or monitoring data of the surrounding systems of the target equipment, in order to determine the optimal control parameters of the target equipment as intermediate data.

4. The edge control device according to claim 2 or 3, characterized in that, In the aforementioned collaborative verification service, the multi-dimensional collaborative verification of the original process data based on the intermediate data to obtain the reliability of the original process data includes: Compare the consistency between the intermediate data and the original process data to calculate the reliability of the original process data; and / or, The reliability of the original process data is evaluated based on the intermediate data to calculate the reliability of the original process data; and / or, The reliability of the original process data is calculated by performing a feasibility weight evaluation based on the intermediate data.

5. The edge control device according to claim 3, characterized in that, When the target device is a motor The original process data of the target device includes: process temperature data of the motor; The monitoring data of the target equipment's peripheral system includes: voltage and current data of the motor collected by the voltage and current sampling module; The video data of the target device includes: optical video data about the motor acquired by the optical image acquisition device and infrared video data about the motor acquired by the infrared image acquisition device. In the data analysis service, The data statistical analysis component is used to obtain the current first temperature of the motor based on the motor's process temperature data; and The first abnormal state of the motor is used as the first operating state parameter to determine the first abnormal state of the motor based on the motor's voltage and current data; the first abnormal state includes: abnormal power supply voltage, overvoltage fault, and overcurrent fault; The video analysis component is used to determine the current second temperature of the motor based on the motor's infrared video data; and, The second abnormal state of the motor is used as a second operating state parameter to determine the second abnormal state of the motor based on optical video data about the motor; the second abnormal state includes at least one of motor shaft stoppage and process stall.

6. The edge control device according to claim 5, characterized in that, In the aforementioned linkage verification service, the original process data is subjected to multi-dimensional linkage verification based on the intermediate data to obtain the reliability of the original process data. And, when the reliability of the original process data is lower than a preset value, auxiliary control data is generated, including: The consistency between the first temperature and the second temperature is compared to obtain the comparison result; Based on the second temperature, the first abnormal state, and the second abnormal state, the credibility of the first temperature is evaluated, and the credibility evaluation result is obtained. The reliability of the process temperature data is calculated based on the comparison results and the reliability evaluation results. When the reliability is less than a preset value, auxiliary control data is generated based on the first temperature, the second temperature, and the reliability.

7. An industrial control system, characterized in that, It includes an edge control device and a target device, wherein the edge control device is communicatively connected to the target device to control the operation of the target device; The edge control device is the edge control device of the industrial control system according to any one of claims 1 to 6.

Images