WO2023184184A1

WO2023184184A1 - Industrial control method and apparatus

Info

Publication number: WO2023184184A1
Application number: PCT/CN2022/083844
Authority: WO
Inventors: 于志强; 于琪; 王璐; 杨占宾
Original assignee: 西门子股份公司; 西门子（中国）有限公司
Priority date: 2022-03-29
Filing date: 2022-03-29
Publication date: 2023-10-05

Abstract

The present invention provides an industrial control method, which is used for controlling an industrial production line or an industrial device. The industrial control method comprises: acquiring a first control strategy of an industrial production line or an industrial device, wherein the first control strategy is preset; acquiring real-time data of the industrial production line or the industrial device, and determining a second control strategy of the industrial production line or the industrial device according to the real-time data and historical data; and adjusting the first control strategy by using the second control strategy, and controlling the industrial production line or the industrial device according to the adjusted first control strategy. Embodiments of the present invention provide the industrial control method, combining the first control strategy and the second control strategy, wherein the first control strategy is high in reliability, and the second control strategy is high in real-time performance, so that the reliability and the real-time performance of control are both considered, a flexible control strategy is provided, real-time conditions or emergencies in a production process can be dealt with in time, and the production efficiency is improved.

Description

Industrial control methods and devices

Technical field

The present invention mainly relates to the field of industrial automation, and in particular, to an industrial control method and device.

Background technique

In the field of industrial automation, one or more predefined control strategies are loaded into the automation control system. The automation control system uses the predefined control strategy to control the production line to execute the production process. The control strategy cannot be adjusted during the production process. , cannot respond well to real-time conditions or emergencies during the production process. If adjustments are needed, adjustments can only be made manually after stopping the production line, which seriously hinders the production progress.

Contents of the invention

In order to solve the above technical problems, the present invention provides an industrial control method and device, which can provide flexible control strategies to respond to real-time conditions or emergencies in the production process and improve production efficiency.

In order to achieve the above object, the present invention proposes an industrial control method for controlling an industrial production line or industrial equipment. The industrial control method includes: obtaining a first control strategy of the industrial production line or industrial equipment, so The first control strategy is preset; real-time data of the industrial production line or industrial equipment is obtained, and the second control strategy of the industrial production line or industrial equipment is determined based on the real-time data and historical data; and the second control strategy of the industrial production line or industrial equipment is adopted. The second control strategy adjusts the first control strategy, and controls the industrial production line or industrial equipment according to the adjusted first control strategy. To this end, embodiments of the present invention provide an industrial control method that combines a first control strategy and a second control strategy. The first control strategy has high reliability, and the second control strategy has strong real-time performance, taking into account both control reliability and Real-time performance provides flexible control strategies that can promptly respond to real-time conditions or emergencies in the production process and improve production efficiency.

Optionally, determining the second control strategy of the industrial production line or industrial equipment based on the real-time data and historical data includes: determining the second control strategy of the industrial production line or industrial equipment based on the real-time data and historical data in an edge device. Second control strategy. To this end, the second control policy is generated in the local edge device, which avoids the impact of network communication and improves the speed of policy generation.

Optionally, determining the second control strategy of the industrial production line or industrial equipment according to the real-time data and historical data includes: sending the real-time data and historical data to a cloud, and the cloud determines the second control strategy according to the real-time data and historical data. The data determines a second control strategy for the industrial production line or industrial equipment. To this end, the second control strategy is generated in the cloud, which can provide higher computing power and more services, improving the accuracy and diversity of the strategy.

Optionally, determining the second control strategy of the industrial production line or industrial equipment based on the real-time data and historical data includes: using historical data to train a machine learning model, and using the machine learning model to determine the second control strategy based on the real-time data. Secondary control strategy for industrial production lines or industrial equipment. To this end, by adopting a machine learning model to determine the second control strategy, the intelligence and accuracy of the control can be improved.

Optionally, obtaining the first control strategy of the industrial production line or industrial equipment includes: obtaining historical data and production management data, using the historical data and the production management data combined with the domain knowledge of domain experts to define a preset The first control strategy. To this end, the data sources of the first control strategy are enriched, the impact of production management on production lines and industrial equipment is considered, and the flexibility and accuracy of control are improved.

The invention also proposes an industrial control device for controlling industrial production lines or industrial equipment. The industrial control device includes: a first acquisition module to obtain the first control strategy of the industrial production line or industrial equipment, The first control strategy is preset; the second acquisition module acquires real-time data of the industrial production line or industrial equipment, and determines the second control of the industrial production line or industrial equipment based on the real-time data and historical data. Strategy; a control module that uses the second control strategy to adjust the first control strategy, and controls the industrial production line or industrial equipment according to the adjusted first control strategy. To this end, embodiments of the present invention provide an industrial control method that combines a first control strategy and a second control strategy. The first control strategy has high reliability, and the second control strategy has strong real-time performance, taking into account both control reliability and Real-time performance provides flexible control strategies that can promptly respond to real-time conditions or emergencies in the production process and improve production efficiency.

Optionally, the second acquisition module determines the second control strategy of the industrial production line or industrial equipment based on the real-time data and historical data including: determining the industrial production line or industrial equipment based on the real-time data and historical data in an edge device. Secondary control strategy for production lines or industrial equipment. To this end, the second control strategy is generated in the local edge device, which avoids delays caused by communication and improves the reliability and efficiency of generating the second control strategy.

Optionally, the second acquisition module determines the second control strategy of the industrial production line or industrial equipment based on the real-time data and historical data including: sending the real-time data and historical data to the cloud, and the cloud based on The real-time data and historical data determine a second control strategy for the industrial production line or industrial equipment. to this end,

Optionally, the second acquisition module determines the second control strategy of the industrial production line or industrial equipment based on the real-time data and historical data including: using historical data to train a machine learning model, and using the machine learning model to determine the second control strategy based on the real-time data and historical data. The real-time data determines the second control strategy of the industrial production line or industrial equipment.

Optionally, the first acquisition module acquires the first control strategy of the industrial production line or industrial equipment including: acquiring historical data and production management data, and using the historical data and the production management data combined with the fields of domain experts. Knowledge that defines the first control strategy.

The present invention also proposes an electronic device, including a processor, a memory and instructions stored in the memory, wherein when the instructions are executed by the processor, the above method is implemented.

The present invention also proposes a computer-readable storage medium on which computer instructions are stored, which execute the method as described above when executed.

Description of drawings

The following drawings are only intended to schematically illustrate and explain the present invention and do not limit the scope of the present invention. in,

Figure 1 is a flow chart of an industrial control method according to an embodiment of the present invention;

Figure 2 is an exemplary schematic diagram of an implementation environment of an industrial control method according to an embodiment of the present invention;

Figure 3 is an exemplary flow chart for generating a first control strategy according to an embodiment of the present invention;

Figure 4 is an exemplary flow chart for generating a second control strategy according to an embodiment of the present invention;

Figure 5 is an exemplary flow chart for generating a second control strategy according to another embodiment of the present invention;

Figure 6 is a schematic diagram of an industrial control device according to an embodiment of the present invention;

FIG. 7 is a schematic diagram of an electronic device according to an embodiment of the present invention.

Explanation of reference signs

100 methods

110-130 steps

21 Enterprise Management Center

211 service layer

211a Policy Management Services

211b policy provision services

212 Third-party software

22 Onsite

22A Edge Device

221 interface

222 data acquisition unit

223 data storage unit

224 data processing unit

225 Local Policy Generator

226 policy memory

227 Network Services

228 controller

22B actuator

23 cloud

231 Data Monitor

232 Data Storage

233 Big data analysis services

234 Cloud Strategy Generator

600 industrial control devices

610 First acquisition module

620 Second acquisition module

630 control module

700 Electronic equipment

710 processor

720 memory

Detailed ways

In order to have a clearer understanding of the technical features, purposes and effects of the present invention, the specific embodiments of the present invention will now be described with reference to the accompanying drawings.

Many specific details are set forth in the following description to fully understand the present invention, but the present invention can also be implemented in other ways different from those described here, so the present invention is not limited to the specific embodiments disclosed below.

As shown in this application and claims, words such as "a", "an", "an" and/or "the" do not specifically refer to the singular and may include the plural unless the context clearly indicates an exception. Generally speaking, the terms "comprising" and "comprising" only imply the inclusion of clearly identified steps and elements, and these steps and elements do not constitute an exclusive list. The method or apparatus may also include other steps or elements.

The present invention proposes an industrial control method for controlling industrial production lines or industrial equipment. Figure 1 is a flow chart of an industrial control method 100 according to an embodiment of the present invention. As shown in Figure 1, industrial control Method 100 includes:

Step 110: Obtain the first control strategy of the industrial production line or industrial equipment. The first control strategy is preset.

The industrial control method of the present invention can be a production line-level control of an industrial production line, where each equipment in the production line is controlled to perform different actions at different times, or it can be a device-level control of industrial equipment, where the control equipment is Different actions are performed at different times. The first control strategy is preset, which can also be called a static control strategy. It is set at the factory and does not need to be adjusted during subsequent use. The first control strategy can be generated based on the domain knowledge of domain experts and is reliable. high. In the embodiment of the present invention, the first control strategy refers to the overall configuration of the control object, which can be stopping or running, or what parameters are used for running. For example, a factory includes production line 1 and For two production lines, production line 2, the first control strategy can be to run both production line 1 and production line 2 from Monday to Friday, only production line 1 to operate on Saturdays, and only production line 2 to operate on Sundays.

Figure 2 is an exemplary schematic diagram of an implementation environment of an industrial control method according to an embodiment of the present invention. As shown in Figure 2, the first control policy is stored in the policy management service 211a and can be retrieved for use in subsequent steps.

In some embodiments, obtaining the first control strategy of the industrial production line or industrial equipment may include: obtaining historical data and production management data, using the historical data and production management data combined with the domain know-how of domain experts, and defining Default first control strategy. As shown in Figure 2, third-party software 212 such as manufacturing execution system MES, enterprise resource planning ERP, and product life cycle management PLM can provide production management data. These production management data can be used to generate the first control strategy, that is, the static control strategy. To this end, the data sources of the first control strategy are enriched, the impact of production management on production lines and industrial equipment is considered, and the flexibility and accuracy of control are improved.

Step 120: Obtain real-time data of the industrial production line or industrial equipment, and determine the second control strategy of the industrial production line or industrial equipment based on the real-time data and historical data.

Industrial equipment can be such as programmable logic controller PLC, computer numerical controller CNC, robot, automatic guided vehicle AGV, sensor, driver, etc. The industrial production line consists of one or more industrial equipment, which can generate A large amount of real-time data, such as the position, speed, acceleration, etc. of the mechanical arm in the robot, can feed back the real-time status of the production line or industrial equipment, and determine the second control strategy of the industrial production line or industrial equipment based on the real-time data. The second control The strategy can also be adapted to the real-time conditions of the production line or industrial equipment. The second control strategy is related to the real-time conditions, so it can also be called a dynamic control strategy with high real-time performance. Historical data refers to the historical operating data of industrial production lines or industrial equipment. Historical data can be used to build data models. It can be understood that the second control strategy is similar to the first control strategy and refers to the overall configuration of the control object. For example, the second control strategy can be to predict that the spraying robot in production line 2 will appear with a high probability based on real-time data. Due to a malfunction, the production line 2 was stopped for maintenance on the same day. As shown in Figure 2, the real-time data of the executor 22B is obtained by the data acquisition unit 222 through the interface 221, stored in the data memory 223, and processed by the data processor 224, and generates a second control strategy accordingly.

In some embodiments, determining the second control strategy of the industrial production line or industrial equipment based on real-time data and historical data includes: determining the second control strategy of the industrial production line or industrial equipment based on real-time data and historical data in the edge device. As shown in FIG. 2 , the local policy generator 225 generates a second control policy according to the data model of the data processor 224 and real-time data, and the local policy generator 225 sends the second control policy to the policy memory 226 .

In some embodiments, determining the second control strategy of the industrial production line or industrial equipment based on real-time data and historical data includes: sending real-time data to the cloud, and the cloud determines the second control strategy of the industrial production line or industrial equipment based on the real-time data and historical data. Control Strategy. As shown in Figure 2, the data in the data storage 223 is sent to the data storage 232. The big data analysis service 233 analyzes and processes the data in the data storage 232 to generate a data model. The cloud policy generator 234 generates a data model according to the data of the big data analysis service 233. The data model and real-time data generate a second control policy, which is sent to the policy memory 226 via the policy providing service 211b and the network service 227.

In some embodiments, determining the second control strategy of the industrial production line or industrial equipment based on real-time data and historical data includes: using historical data to train a machine learning model, and using the machine learning model to determine the second control strategy of the industrial production line or industrial equipment based on real-time data. 2. Control strategy. The machine learning model can be a recurrent neural network model, etc. By using the machine learning model to determine the second control strategy, the intelligence and accuracy of the control can be improved.

Step 130: Use the second control strategy to adjust the first control strategy, and control the industrial production line or industrial equipment according to the adjusted first control strategy.

Using the second control strategy to adjust the first control strategy means merging the second control strategy and the first control strategy into a total control strategy. In the embodiment of the present invention, the second control strategy and the first control strategy are merged. The second control strategy can be logically operated with the first control strategy. For example, the first control strategy is to run both production line 1 and production line 2 from Monday to Friday, only production line 1 to operate on Saturdays, and only production line 2 to operate on Sundays. The second control strategy is to stop the spraying of production line 2 on the same day. If the robot is shut down for maintenance, then the second control strategy is used to adjust the first control strategy. The result is that production line 1 runs from Monday to Friday, production line 2 stops running on the same day, runs at other times from Monday to Friday, and only production line 1 runs on Saturdays. , only production line 2 is running on Sunday. In FIG. 2 , the first control strategy and the second control strategy are stored in the strategy memory 226 , and adjusting the first control strategy using the second control strategy can be implemented in the controller 228 .

Generating the first control strategy and the second control strategy will be exemplarily described below with reference to Figures 2-5.

Generate first control strategy

FIG. 3 is an exemplary flow chart for generating a first control strategy according to an embodiment of the present invention. The flow chart corresponds to generating a first control strategy, that is, a static control strategy.

Step S301, the controller 228 extracts the control strategy from the strategy memory 226;

Step S302, the controller 228 controls the actuator 22B according to the control strategy;

Step S303, obtain domain knowledge from domain experts;

Step S304, use domain knowledge as the first control strategy, or update the existing first control strategy to the policy management service 211a;

Step S305, the policy management service 211a sends the first control policy to the policy providing service 211b;

Step S306, the policy providing service 211b sends the first control policy to the network service 227;

Step S307, the network service 227 sends the first control policy to the policy memory 226 for storage;

Step S308, the controller 228 extracts the control strategy from the strategy memory 226;

In step S309, the controller 228 controls the actuator 22B according to the control strategy.

Generate the second control strategy one

FIG. 4 is an exemplary flowchart for generating a second control strategy according to an embodiment of the present invention. The flowchart corresponds to locally generating a second control strategy, that is, a dynamic control strategy.

Step S401, the controller 228 extracts the control strategy from the strategy memory 226;

Step S402, the controller 228 controls the actuator 22B according to the control strategy;

Step S403, the data acquisition unit 222 acquires real-time data from the executor 22B;

Step S404, the data acquisition unit 222 stores the real-time data into the data storage unit 223;

Step S405, the data processing unit 224 calls the data in the data storage unit 223 for processing;

Step S406, the data processing unit 224 generates a data model according to the received data;

Step S407, the local policy generator 225 generates a second control policy according to the data model and real-time data of the data processing unit 224;

Step S408, the local policy generator 225 sends the second control policy to the policy memory 226;

Step S409, the controller 228 extracts the control strategy from the strategy memory 226;

In step S410, the controller 228 controls the actuator 22B according to the control strategy.

Generate second control strategy two

FIG. 5 is an exemplary flow chart for generating a second control strategy according to another embodiment of the present invention. The flow chart corresponds to generating a second control strategy in the cloud, that is, a dynamic control strategy.

Step S501, the controller 228 extracts the control strategy from the strategy memory 226;

Step S502, the controller 228 controls the actuator 22B according to the control strategy;

Step S503, the data acquisition unit 222 acquires real-time data from the executor 22B;

Step S504, the data acquisition unit 222 stores the real-time data into the data storage unit 223;

Step S505, the data in the data storage unit 223 is sent to the data storage 232;

Step S506, the big data analysis service 233 calls the data in the data storage 232;

Step S507, the big data analysis service 233 generates a data model based on the received data;

Step S508, the cloud policy generator 234 generates a second control policy based on the data model and real-time data of the big data analysis service 233;

Step S509, the cloud policy generator 234 sends the second control policy to the policy providing service 211b;

Step S510, the policy providing service 211b sends the second control policy to the network service 227;

Step S511, the network service 227 stores the second control policy into the policy memory 226;

Step S512, the controller 228 extracts the control strategy from the strategy memory 226;

In step S513, the controller 228 controls the actuator 22B according to the control strategy.

Embodiments of the present invention provide an industrial control method that combines a first control strategy and a second control strategy. The first control strategy has high reliability, and the second control strategy has strong real-time performance, taking into account both the reliability and real-time performance of the control. It provides a flexible control strategy that can promptly respond to real-time conditions or emergencies in the production process and improve production efficiency.

The present invention also proposes an industrial control device for controlling industrial production lines or industrial equipment. Figure 6 is a schematic diagram of an industrial control device 600 according to an embodiment of the present invention. As shown in Figure 6, industrial control Device 600 includes:

The first acquisition module 610 acquires the first control strategy of the industrial production line or industrial equipment, and the first control strategy is preset.

The second acquisition module 620 acquires real-time data of the industrial production line or industrial equipment, and determines the second control strategy of the industrial production line or industrial equipment based on the real-time data and historical data.

The control module 630 uses the second control strategy to adjust the first control strategy, and controls the industrial production line or industrial equipment according to the adjusted first control strategy.

In some embodiments, the second acquisition module 620 determines the second control strategy of the industrial production line or industrial equipment based on real-time data and historical data including: determining the second control strategy of the industrial production line or industrial equipment based on real-time data and historical data in the edge device. 2. Control strategy.

In some embodiments, the second acquisition module 620 determines the second control strategy of the industrial production line or industrial equipment based on the real-time data and historical data including: sending the real-time data to the cloud, and the cloud determines the industrial production line or industrial equipment based on the real-time data and historical data. Secondary control strategies for industrial equipment.

In some embodiments, the second acquisition module 620 determines the second control strategy of the industrial production line or industrial equipment based on real-time data and historical data including: using historical data to train a machine learning model, and using the machine learning model to determine the industrial production line based on real-time data. or a secondary control strategy for industrial equipment.

In some embodiments, the first acquisition module 620 acquires the first control strategy of the industrial production line or industrial equipment including: acquiring historical data and production management data, using the historical data and production management data combined with domain knowledge of domain experts to define presets first control strategy.

The present invention also provides an electronic device 700. Figure 7 is a schematic diagram of an electronic device 700 according to an embodiment of the present invention. As shown in FIG. 7 , the electronic device 700 includes a processor 710 and a memory 720 . The memory 720 stores instructions, and when the instructions are executed by the processor 710 , the method 100 as described above is implemented.

The present invention also proposes a computer-readable storage medium on which computer instructions are stored, and when executed, the computer instructions execute the method 100 as described above.

Some aspects of the method and device of the present invention may be executed entirely by hardware, may be entirely executed by software (including firmware, resident software, microcode, etc.), or may be executed by a combination of hardware and software. Each of the above hardware or software may be referred to as a "data block", "module", "engine", "unit", "component" or "system". The processor may be one or more application specific integrated circuits (ASICs), digital signal processors (DSPs), digital signal processing devices (DAPDs), programmable logic devices (PLCs), field programmable gate arrays (FPGAs), processors , controller, microcontroller, microprocessor or combination thereof. Additionally, aspects of the invention may be embodied as a computer product embodied in one or more computer-readable media, the product including computer-readable program code. For example, computer-readable media may include, but are not limited to, magnetic storage devices (e.g., hard disks, floppy disks, magnetic tapes, etc.), optical disks (e.g., compact disks (CD), digital versatile disks (DVD), ...), smart cards and flash memory devices (e.g. cards, sticks, key drives...).

A flowchart is used here to illustrate operations performed by methods according to embodiments of the present application. It should be understood that the preceding operations are not necessarily performed in exact order. Instead, the various steps can be processed in reverse order or simultaneously. At the same time, other operations may be added to these processes, or a step or steps may be removed from these processes.

It should be understood that although this specification is described in terms of various embodiments, not each embodiment only contains an independent technical solution. This description of the specification is only for the sake of clarity, and those skilled in the art should take the specification as a whole. , the technical solutions in each embodiment can also be appropriately combined to form other implementations that can be understood by those skilled in the art.

The above descriptions are only illustrative embodiments of the present invention and are not intended to limit the scope of the present invention. Any equivalent changes, modifications and combinations made by those skilled in the art without departing from the concept and principles of the present invention shall fall within the scope of protection of the present invention.

Claims

An industrial control method (100) for controlling industrial production lines or industrial equipment, characterized in that the industrial control method (100) includes:

Obtain the first control strategy of the industrial production line or industrial equipment, where the first control strategy is preset (110);

Obtain real-time data of the industrial production line or industrial equipment, and determine a second control strategy for the industrial production line or industrial equipment based on the real-time data and historical data (120);

The second control strategy is used to adjust the first control strategy, and the industrial production line or industrial equipment is controlled according to the adjusted first control strategy (130).
The industrial control method (100) according to claim 1, characterized in that determining the second control strategy of the industrial production line or industrial equipment based on the real-time data and historical data includes: in an edge device based on the real-time The data and historical data determine the second control strategy of the industrial production line or industrial equipment.
The industrial control method (100) according to claim 1, characterized in that determining the second control strategy of the industrial production line or industrial equipment according to the real-time data and historical data includes: combining the real-time data and historical data Sent to the cloud, the cloud determines the second control strategy of the industrial production line or industrial equipment based on the real-time data and historical data.
The industrial control method (100) according to any one of claims 1 to 3, characterized in that determining the second control strategy of the industrial production line or industrial equipment based on the real-time data and historical data includes: using historical data Train a machine learning model, and use the machine learning model to determine a second control strategy for the industrial production line or industrial equipment based on the real-time data.
The industrial control method (100) according to claim 1, characterized in that, obtaining the first control strategy of the industrial production line or industrial equipment includes: obtaining historical data and production management data, using the historical data, the Production management data is combined with the domain knowledge of domain experts to define a preset first control strategy.
An industrial control device (600) used to control industrial production lines or industrial equipment, characterized in that the industrial control device (600) includes:

The first acquisition module (610) acquires the first control strategy of the industrial production line or industrial equipment, and the first control strategy is preset;

The second acquisition module (620) acquires real-time data of the industrial production line or industrial equipment, and determines the second control strategy of the industrial production line or industrial equipment based on the real-time data and historical data;

The control module (630) uses the second control strategy to adjust the first control strategy, and controls the industrial production line or industrial equipment according to the adjusted first control strategy.
The industrial control device (600) according to claim 6, characterized in that the second acquisition module (620) determines the second control strategy of the industrial production line or industrial equipment according to the real-time data and historical data including : Determine the second control strategy of the industrial production line or industrial equipment in the edge device based on the real-time data and historical data.
The industrial control device (600) according to claim 6, characterized in that the second acquisition module (620) determines the second control strategy of the industrial production line or industrial equipment according to the real-time data and historical data including : Send the real-time data and historical data to the cloud, and the cloud determines the second control strategy of the industrial production line or industrial equipment based on the real-time data and historical data.
The industrial control device (600) according to any one of claims 6-8, characterized in that the second acquisition module (620) determines the value of the industrial production line or industrial equipment based on the real-time data and historical data. The second control strategy includes: using historical data to train a machine learning model, and using the machine learning model to determine the second control strategy of the industrial production line or industrial equipment based on the real-time data.
The industrial control device (600) according to claim 6, characterized in that, the first acquisition module (610) acquiring the first control strategy of the industrial production line or industrial equipment includes: acquiring historical data and production management data. , using the historical data, the production management data and the domain knowledge of domain experts to define the first control strategy.
An electronic device (600), including a processor (610), a memory (620) and instructions stored in the memory (620), wherein the instructions when executed by the processor (610) implement as claimed The method described in any one of 1-5.
A computer-readable storage medium having computer instructions stored thereon which, when executed, perform the method according to any one of claims 1-5.