PLC intelligent controller and control method

Abstract

The invention provides a PLC intelligent controller and a control method. The PLC intelligent controller comprises a machine learning runtime dynamic library, a logic control runtime dynamic library and a motion control runtime dynamic library which are deployed in an operating system of the PLC intelligent controller; wherein an AI algorithm model is loaded in the machine learning runtime dynamic library; the PLC intelligent controller is used for outputting a prediction result of a material index based on an AI algorithm model in a machine learning runtime dynamic library; and controlling production line equipment based on the logic control runtime dynamic library, the motion control runtime dynamic library and the prediction result of the material indexes. According to the embodiment of the invention, the material indexes are predicted through the built-in AI algorithm model in the PLC, so that the real-time intelligent control effect is achieved, and the real-time performance and the stability are higher compared with a traditional bypass mode.

Description

Technical Field

[0001] The present invention relates to the technical field of PLC control, and in particular to a PLC intelligent controller and a control method. Background Art

[0002] Against the backdrop of the transformation from industrial automation to intelligence, with the rapid development of AI technology, the application scenarios of "AI+industrial control" are becoming increasingly diverse. How to efficiently integrate AI with programmable logic controllers (PLCs) has become an important research direction in the field of industrial intelligent control.

[0003] At present, a bypass method is usually used for industrial intelligent control, and intelligent analysis and calculation are implemented in the server / edge computing device. This method requires multiple link communications between the bypass device and the PLC to complete the intelligent control, and the real-time performance and stability are poor. Summary of the invention

[0004] The present invention provides a PLC intelligent controller and control method, which predicts material indicators through an AI algorithm model built into the PLC, thereby achieving the effect of real-time intelligent control, and effectively solving the problems of poor real-time performance, poor stability and high cost of industrial control caused by the need for multiple link communications between the bypass device and the PLC in the traditional bypass mode.

[0005] The present invention provides a PLC intelligent controller, comprising: The operating system of the PLC intelligent controller deploys a machine learning runtime dynamic library, a logic control runtime dynamic library, and a motion control runtime dynamic library; wherein, The AI ​​algorithm model has been loaded in the machine learning runtime dynamic library; the PLC intelligent controller is used to output the prediction results of material indicators based on the AI ​​algorithm model in the machine learning runtime dynamic library; and control the production line equipment based on the logic control runtime dynamic library, the motion control runtime dynamic library and the prediction results of the material indicators.

[0006] According to a PLC intelligent controller provided by the present invention, the PLC intelligent controller is used to start a data acquisition process, a prediction and analysis process and a control decision process based on the machine learning runtime dynamic library; wherein the data acquisition process is used to obtain real-time operation data of production line equipment; the prediction and analysis process is used to output the prediction results of material indicators based on the real-time operation data of the production line equipment and the AI ​​algorithm model; the control decision process is used to output the control decision results based on the prediction results of the AI ​​algorithm model.

[0007] According to a PLC intelligent controller provided by the present invention, when the control decision result is logic control, the PLC intelligent controller is used to perform PID operation control based on the dynamic library during the logic control runtime and the prediction result of the material index.

[0008] According to a PLC intelligent controller provided by the present invention, when the control decision result is motion control, the PLC intelligent controller is used to control the operation of the production line equipment based on the dynamic library during the motion control runtime and the prediction result of the material index.

[0009] According to a PLC intelligent controller provided by the present invention, the machine learning runtime dynamic library communicates with the logic control runtime dynamic library and the motion control runtime dynamic library based on a target mode; the target mode includes at least one of the following: shared memory, message queue and semaphore.

[0010] The present invention also provides a control method, comprising: Output the prediction results of material indicators based on the AI ​​algorithm model loaded in the dynamic library during machine learning runtime; The production line equipment is controlled based on the logic control runtime dynamic library, the motion control runtime dynamic library and the prediction results of the material indicators.

[0011] The present invention also provides an electronic device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the control method as described above when executing the program.

[0012] The present invention also provides a non-transitory computer-readable storage medium on which a computer program is stored. When the computer program is executed by a processor, the control method described above is implemented.

[0013] The present invention also provides a computer program product, comprising a computer program, wherein when the computer program is executed by a processor, the control method as described above is implemented.

[0014] The PLC intelligent controller and control method provided by the present invention predict material indicators through the AI ​​algorithm model built into the PLC, thereby achieving the effect of real-time intelligent control, and effectively solving the problems of poor real-time performance, poor stability and high cost of industrial control caused by the need for multiple link communications between the bypass device and the PLC in the traditional bypass mode. BRIEF DESCRIPTION OF THE DRAWINGS

[0015] In order to more clearly illustrate the technical solutions in the present invention or the prior art, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0016] Figure 1 It is a schematic diagram of a PLC intelligent controller in the prior art provided by the present invention.

[0017] Figure 2 It is a schematic diagram of the PLC intelligent controller provided by the present invention.

[0018] Figure 3 It is a flow chart of the PLC intelligent control method provided by the present invention.

[0019] Figure 4 It is a structural schematic diagram of the control device provided by the present invention.

[0020] Figure 5 It is a structural schematic diagram of the electronic device provided by the present invention. DETAILED DESCRIPTION

[0021] In order to make the purpose, technical solution and advantages of the present invention clearer, the technical solution of the present invention will be clearly and completely described below in conjunction with the drawings of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0022] Combine the following Figure 1-Figure 5 The PLC intelligent controller and control method of the present invention are described.

[0023] In order to facilitate a clearer understanding of the technical solutions of the embodiments of the present application, some technical contents related to the embodiments of the present application are first introduced.

[0024] Under the general background of the transformation from industrial automation to intelligence, with the rapid development of AI technology, the application scenarios of "AI+industrial control" are becoming more and more abundant. How to efficiently integrate AI and programmable logic controllers (PLCs) has become one of the main research directions in the field of industrial intelligent control.

[0025] like Figure 1As shown, currently, a bypass method is usually used for industrial intelligent control, and intelligent analysis operations are implemented in the server / edge computing device. This method obtains the real-time data of the production line equipment output by the PLC online through the collection service, and then the intelligent analysis system performs predictive analysis and control decision operations, and then sends the calculation results to the PLC controller through the network to achieve the effect of intelligent control. In this method, multiple link communications are required between the bypass device and the PLC to complete the intelligent control, and the real-time performance and stability are poor. Optionally, the bypass device includes a PC server, an edge gateway box, an embedded computer, a high-performance industrial computer, etc. The main problems of the existing bypass method are as follows: 1. Poor real-time performance: The bypass device needs to communicate with the PLC multiple times to complete intelligent control, which cannot meet the application scenarios with high control accuracy and strong timeliness requirements.

[0026] 2. Poor stability: The communication between the bypass device and the PLC is completed through the network, so there are high requirements for the network deployment method and transmission bandwidth, which makes the stability of intelligent control seriously restricted by the network and server / edge computing device.

[0027] 3. High cost: The bypass method requires servers / edge computing devices, dedicated network, auxiliary devices (such as UPS power supplies, cabinets, etc.), intelligent control software systems, IT / OT deployment personnel, etc.

[0028] Figure 1 Schematic diagram of the PLC intelligent controller provided by the present invention, as follows: The machine learning runtime dynamic library, logic control runtime dynamic library and motion control runtime dynamic library are deployed in the operating system of the PLC intelligent controller; among them, The AI ​​algorithm model has been loaded in the machine learning runtime dynamic library; the PLC intelligent controller is used to output the prediction results of material indicators based on the AI ​​algorithm model in the machine learning runtime dynamic library; and the production line equipment is controlled based on the logic control runtime dynamic library, the motion control runtime dynamic library and the prediction results of material indicators.

[0029] Specifically, in the prior art, a bypass method is usually used for industrial intelligent control. In this method, the bypass device needs to perform multiple link communications with the PLC to complete intelligent control. This method cannot meet application scenarios with high control accuracy and strong timeliness requirements, and its real-time performance and stability are poor.

[0030] In order to solve the above problems, Figure 2As shown, the operating system of the PLC intelligent controller in the embodiment of the present application is deployed with a machine learning runtime dynamic library, a logic control runtime dynamic library, and a motion control runtime dynamic library; wherein, the machine learning runtime dynamic library has been loaded with an AI algorithm model; the PLC intelligent controller is used to output the prediction results of the material index based on the AI ​​algorithm model in the machine learning runtime dynamic library, and control the production line equipment based on the prediction results of the logic control runtime dynamic library, the motion control runtime dynamic library, and the material index. Optionally, the runtime dynamic library is the Runtime dynamic library, which provides an operating environment for the AI ​​algorithm. Optionally, the AI ​​algorithm model is used to output the prediction results of the material index, such as outputting the moisture prediction results of the material. Optionally, the AI ​​algorithm model can be trained based on a supervised manner, so that the trained AI algorithm model predicts the moisture of the material processed by the production line equipment based on the temperature and humidity of the production line equipment, the operating frequency of the production line equipment, and the current material index data collected in real time by the sensor. Optionally, the logic control runtime dynamic library and the motion control runtime dynamic library are dynamic libraries deployed in the prior art, which are used for the control of the production line equipment, and are not described in detail in the embodiment of the present application. That is, in the embodiment of the present application, different runtime dynamic libraries are created for the prediction of material indicators and the logical control and motion control of production line equipment, so that efficient and accurate calculations can be achieved, and the efficiency and accuracy of intelligent control can be improved. In the embodiment of the present application, the AI ​​algorithm model is built into the machine learning runtime dynamic library in the PLC, and the real-time calculation of the PLC high-performance CPU chip is used to achieve the effect of intelligent control, thereby effectively solving the problems of poor real-time performance, poor stability and high cost in the traditional bypass mode.

[0031] It should be noted that the data collection, model operation, and result feedback of the solution of the embodiment of the present application can be completed inside the PLC and are not affected by the network, which can truly achieve real-time analysis, real-time decision-making, real-time feedback, and real-time control. Moreover, there is no need to deploy computing, storage, network and other hardware resources separately, and it can be used out of the box, which reduces the threshold for use, saves costs, and realizes intelligent control efficiently and accurately.

[0032] The PLC intelligent controller of the above embodiment predicts material indicators through the AI ​​algorithm model built into the PLC, thereby achieving the effect of real-time intelligent control, and effectively solving the problems of poor real-time and stability of industrial control and high cost caused by the need for multiple link communications between the bypass device and the PLC in the traditional bypass mode.

[0033] In one embodiment, the PLC intelligent controller is used to start a data acquisition process, a predictive analysis process, and a control decision process based on a machine learning runtime dynamic library; wherein the data acquisition process is used to obtain real-time operating data of production line equipment; the predictive analysis process is used to output the prediction results of material indicators based on the real-time operating data of the production line equipment and the AI ​​algorithm model; the control decision process is used to output the control decision results based on the prediction results of the AI ​​algorithm model.

[0034] Specifically, in the embodiment of the present application, the PLC intelligent controller is used to start the data acquisition process, the prediction analysis process and the control decision process based on the machine learning runtime dynamic library; wherein, the data acquisition process obtains the real-time data of the production line equipment fed back in the PLC memory through the interface, such as the temperature and humidity of the production line equipment, the operating frequency of the production line equipment and other data. The prediction analysis process enables the AI ​​algorithm model embedded in the machine learning runtime dynamic library, performs prediction analysis operations based on the real-time data of the production line equipment, and outputs the prediction results of the material index, such as the output material moisture prediction results. The control decision process outputs the control decision result according to the prediction analysis result of the built-in AI model, controls the production line equipment, thereby achieving the effect of real-time intelligent control, which is higher in real time and stability than the traditional bypass method. Optionally, the control decision result includes logic control and motion control, wherein the logic control is to achieve the ideal material index result by adjusting the PID parameters; the motion control is to achieve the ideal material index result by adjusting the motion indicators such as the running speed of the production line equipment. Optionally, the control decision result may also include PID parameter adjustment amounts determined based on the prediction results of material indicators and adjustment amounts of motion indicators such as the operating speed of production line equipment. Adjustments based on the above adjustment amounts can achieve rational material indicator results, thereby realizing intelligent control efficiently and accurately.

[0035] The PLC intelligent controller of the above-mentioned embodiment starts the data acquisition process, the predictive analysis process and the control decision process based on the dynamic library during machine learning runtime, obtains the real-time operation data of the production line equipment, and performs predictive analysis calculations based on the built-in AI algorithm model and outputs the control decision results, thereby achieving the effect of real-time intelligent control, which is higher in real time and stability than the traditional bypass method.

[0036] In one embodiment, when the control decision result is logic control, the PLC intelligent controller is used to perform PID operation control based on the prediction results of the dynamic library and material indicators during the operation of the logic control.

[0037] Specifically, when the control decision result is logic control, that is, when the control strategy is logic control, the PLC intelligent controller performs PID operation control based on the logic control runtime dynamic library and the predicted results of the material index, that is, by adjusting the PID parameters to achieve the predicted ideal material index results. It should also be noted that in the embodiment of the present application, different runtime dynamic libraries are created for the prediction of material indicators and the logic control and motion control of production line equipment, so that efficient and accurate calculation and control of production line equipment can be achieved, so that the efficiency and accuracy of intelligent control are effectively improved.

[0038] In one embodiment, when the control decision result is motion control, the PLC intelligent controller is used to control the operation of the production line equipment based on the prediction results of the dynamic library and material indicators during the motion control runtime.

[0039] Specifically, when the control decision result is motion control, that is, when the control strategy is motion control, the PLC intelligent controller is used to control the operation of the production line equipment based on the motion control runtime dynamic library and the prediction results of the material index, that is, by adjusting the motion indexes such as the running speed of the production line equipment, so as to achieve the predicted ideal material index results. It should also be noted that in the embodiment of the present application, different runtime dynamic libraries are created for the prediction of material indicators and the logical control and motion control of the production line equipment, so as to achieve efficient and accurate calculation and control of the production line equipment, so that the efficiency and accuracy of intelligent control are effectively improved.

[0040] In one embodiment, the machine learning runtime dynamic library communicates with the logic control runtime dynamic library and the motion control runtime dynamic library based on a target mode; the target mode includes at least one of the following: shared memory, message queue and semaphore.

[0041] Specifically, in an embodiment of the present application, the machine learning runtime dynamic library transmits the material indicators predicted by the built-in AI model to the logic control Runtime dynamic library for PID operation control, or transmits it to the motion control Runtime dynamic library to guide position, direction, and speed control through communication methods such as shared memory, message queue, or semaphore, thereby achieving efficient communication between the machine learning runtime dynamic library, the logic control runtime dynamic library, and the motion control runtime dynamic library, thereby effectively improving the efficiency and accuracy of PLC intelligent control.

[0042] In the method of the above embodiment, the machine learning runtime dynamic library communicates with the logic control runtime dynamic library and the motion control runtime dynamic library through communication methods such as shared memory, message queue or semaphore, thereby realizing efficient communication between the machine learning runtime dynamic library, the logic control runtime dynamic library and the motion control runtime dynamic library, thereby achieving the effect of real-time intelligent control and effectively improving the efficiency and accuracy of PLC intelligent control.

[0043] Exemplarily, an embodiment of the present application further provides a control method, including: Output the prediction results of material indicators based on the AI ​​algorithm model loaded in the dynamic library during machine learning runtime; The production line equipment is controlled based on the prediction results of the logic control runtime dynamic library, the motion control runtime dynamic library and the material indicators.

[0044] Specifically, in the prior art, a bypass method is usually used for industrial intelligent control. In this method, the bypass device needs to perform multiple link communications with the PLC to complete intelligent control. This method cannot meet application scenarios with high control accuracy and strong timeliness requirements, and its real-time performance and stability are poor.

[0045] In order to solve the above problems, the AI ​​algorithm model built in the machine learning runtime dynamic library outputs the prediction results of material indicators and performs intelligent control in the embodiment of the present application. That is, in the embodiment of the present application, the AI ​​algorithm model has been loaded in the machine learning runtime dynamic library, and the PLC intelligent controller outputs the prediction results of material indicators based on the AI ​​algorithm model in the machine learning runtime dynamic library. Optionally, the runtime dynamic library is the Runtime dynamic library, which provides an operating environment for the AI ​​algorithm. Optionally, the AI ​​algorithm model is used to output the prediction results of material indicators, such as outputting the moisture prediction results of the material. Optionally, the AI ​​algorithm model can be trained based on a supervised manner, so that the trained AI algorithm model accurately predicts the moisture of the processed material based on the data such as the temperature and humidity of the production line equipment and the operating frequency of the production line equipment collected in real time by the sensor. Optionally, the logic control runtime dynamic library and the motion control runtime dynamic library are dynamic libraries that have been deployed in the prior art and are used for the control of the production line equipment, which will not be repeated in the embodiment of the present application. That is, in the embodiment of the present application, different runtime dynamic libraries are created for the prediction of material indicators and the logic control and motion control of the production line equipment, so that efficient and accurate calculations can be achieved, and the efficiency and accuracy of intelligent control can be improved. In the embodiment of the present application, the AI ​​algorithm model is built into the machine learning runtime dynamic library in the PLC, and the real-time calculation of the PLC high-performance CPU chip is used to achieve the effect of intelligent control, thereby effectively solving the problems of poor real-time performance, poor stability and high cost in the traditional bypass mode.

[0046] The control method of the above embodiment predicts material indicators through the AI ​​algorithm model built into the PLC, thereby achieving the effect of real-time intelligent control, and effectively solving the problem that multiple link communications are required between the bypass device and the PLC in the traditional bypass mode, resulting in poor real-time performance, poor stability and high cost of industrial control.

[0047] Optionally, a control method is also provided in the embodiment of the present application, specifically as follows Figure 3 As shown: (1) Use the algorithm programming environment IDE to compile and package the developed AI algorithm model program into the machine learning Runtime dynamic library.

[0048] (2) Deploy the machine learning runtime dynamic library to the PLC operating system RTOS environment through the network or USB flash drive. Then, the PLC intelligent controller can output the prediction results of material indicators based on the AI ​​algorithm model in the machine learning runtime dynamic library, thereby achieving the effect of real-time intelligent control.

[0049] (3) Machine Learning Runtime starts: the data acquisition process runs, the prediction and analysis process runs, and the control and decision-making process runs.

[0050] (4) The data acquisition process obtains the real-time data of production line equipment parameters fed back from the PLC memory through the interface.

[0051] (5) The predictive analysis process enables the AI ​​algorithm model, performs predictive analysis operations based on the acquired real-time data, and outputs the operation results.

[0052] (6) The control decision process starts the AI ​​algorithm model, performs control decision operations based on the prediction analysis results, and outputs the operation results.

[0053] (7) If the control strategy is logic control, the index recommended values ​​are passed to the logic control runtime through the established shared memory, message queue or semaphore communication channel for PID operation control. If the control strategy is motion control, the index recommended values ​​are passed to the motion control runtime through the established shared memory, message queue or semaphore communication channel to guide position, direction and speed control, realizing efficient communication between the machine learning runtime dynamic library, the logic control runtime dynamic library and the motion control runtime dynamic library, so as to achieve the effect of real-time intelligent control and effectively improve the efficiency and accuracy of PLC intelligent control.

[0054] Exemplarily, the PLC intelligent controller in the embodiment of the present application can be applied to the following scenarios: A cigarette factory uses the built-in constant algorithm model (preset neural network algorithm) of the Yuansambu IO Site Z5001 intelligent controller (PLC) to achieve adaptive control of the thin plate drying process, replacing the current operation mode that relies on manual intervention and adjustment during the non-steady-state stage of the process. It realizes intelligent and unmanned control of non-steady-state process parameters such as the head and tail of the material and external disturbances in each key process of silk making, reducing the uncertainty of manual intervention.

[0055] The control device provided by the present invention is described below. The control device described below and the control method described above can be referred to in correspondence with each other. Figure 4 As shown, including: Prediction module 410, used to output the prediction result of material index based on the AI ​​algorithm model loaded in the dynamic library during machine learning runtime; The control module 420 is used to control the production line equipment based on the logic control runtime dynamic library, the motion control runtime dynamic library and the prediction results of the material indicators.

[0056] Optionally, the prediction module 410 is specifically used to start a data acquisition process, a prediction analysis process and a control decision process based on a machine learning runtime dynamic library; wherein the data acquisition process is used to obtain real-time operating data of production line equipment; the prediction analysis process is used to output the prediction results of material indicators based on the real-time operating data of production line equipment and the AI ​​algorithm model; the control decision process is used to output the control decision results based on the prediction results of the AI ​​algorithm model.

[0057] Optionally, the prediction module 410 is specifically used to perform PID operation control based on the prediction results of the dynamic library and material indicators when the logic control is running when the control decision result is logic control.

[0058] Optionally, the prediction module 410 is specifically used to control the operation of the production line equipment based on the prediction results of the dynamic library and material indicators during the motion control operation when the control decision result is motion control.

[0059] Optionally, the machine learning runtime dynamic library communicates with the logic control runtime dynamic library and the motion control runtime dynamic library based on a target mode; the target mode includes at least one of the following: shared memory, message queue and semaphore.

[0060] Figure 5An example of a physical structure diagram of an electronic device is provided, which may include: a processor 510, a communications interface 520, a memory 530, and a communication bus 540, wherein the processor 510, the communications interface 520, and the memory 530 communicate with each other through the communication bus 540. The processor 510 may call the logic instructions in the memory 530 to execute a control method, which includes: outputting a prediction result of a material index based on an AI algorithm model loaded in a machine learning runtime dynamic library; and controlling the production line equipment based on a logic control runtime dynamic library, a motion control runtime dynamic library, and a prediction result of a material index.

[0061] In addition, the logic instructions in the above-mentioned memory 530 can be implemented in the form of a software functional unit and can be stored in a computer-readable storage medium when it is sold or used as an independent product. Based on such an understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art or the part of the technical solution, can be embodied in the form of a software product, and the computer software product is stored in a storage medium, including a number of instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present invention. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), disk or optical disk, etc. Various media that can store program codes.

[0062] On the other hand, the present invention also provides a computer program product, which includes a computer program. The computer program can be stored on a non-transitory computer-readable storage medium. When the computer program is executed by a processor, the computer can execute the control method provided by the above-mentioned methods, which includes: outputting the prediction results of material indicators based on the AI ​​algorithm model loaded in the machine learning runtime dynamic library; controlling the production line equipment based on the logic control runtime dynamic library, the motion control runtime dynamic library and the prediction results of material indicators.

[0063] On the other hand, the present invention also provides a non-transitory computer-readable storage medium having a computer program stored thereon. When the computer program is executed by a processor, it is implemented to execute the control method provided by the above-mentioned methods, and the method includes: outputting the prediction results of material indicators based on the AI ​​algorithm model loaded in the machine learning runtime dynamic library; controlling the production line equipment based on the logic control runtime dynamic library, the motion control runtime dynamic library and the prediction results of material indicators.

[0064] The device embodiments described above are merely illustrative, wherein the units described as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, they may be located in one place, or they may be distributed on multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the scheme of this embodiment. Ordinary technicians in this field can understand and implement it without paying creative labor.

[0065] Through the description of the above implementation methods, those skilled in the art can clearly understand that each implementation method can be implemented by means of software plus a necessary general hardware platform, and of course, can also be implemented by hardware. Based on this understanding, the above technical solution is essentially or the part that contributes to the prior art can be embodied in the form of a software product, and the computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, a disk, an optical disk, etc., including a number of instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to execute the methods described in each embodiment or some parts of the embodiments.

[0066] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit it. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A PLC intelligent controller, characterized in that: include: The operating system of the PLC intelligent controller deploys a machine learning runtime dynamic library, a logic control runtime dynamic library, and a motion control runtime dynamic library; wherein, The AI ​​algorithm model has been loaded in the machine learning runtime dynamic library; the PLC intelligent controller is used to output the prediction results of material indicators based on the AI ​​algorithm model in the machine learning runtime dynamic library; and control the production line equipment based on the logic control runtime dynamic library, the motion control runtime dynamic library and the prediction results of the material indicators.

2. The PLC intelligent controller according to claim 1 is characterized in that: The PLC intelligent controller is used to start the data acquisition process, the prediction and analysis process and the control decision process based on the machine learning runtime dynamic library; wherein, the data acquisition process is used to obtain the real-time operation data of the production line equipment; the prediction and analysis process is used to output the prediction results of the material indicators based on the real-time operation data of the production line equipment and the AI ​​algorithm model; the control decision process is used to output the control decision results based on the prediction results of the AI ​​algorithm model.

3. The PLC intelligent controller according to claim 2 is characterized in that: In the case where the control decision result is logic control, the PLC intelligent controller is used to perform PID operation control based on the dynamic library during the logic control runtime and the predicted results of the material index.

4. The PLC intelligent controller according to claim 2 is characterized in that: In the case where the control decision result is motion control, the PLC intelligent controller is used to control the operation of the production line equipment based on the dynamic library during the motion control runtime and the prediction result of the material index.

5. The PLC intelligent controller according to any one of claims 1 to 4, characterized in that: The machine learning runtime dynamic library communicates with the logic control runtime dynamic library and the motion control runtime dynamic library based on a target mode; the target mode includes at least one of the following: shared memory, message queue and semaphore.

6. A control method, characterized in that: include: Output the prediction results of material indicators based on the AI ​​algorithm model loaded in the dynamic library during machine learning runtime; The production line equipment is controlled based on the logic control runtime dynamic library, the motion control runtime dynamic library and the prediction results of the material indicators.

7. A control device, Its features include: The prediction module is used to output the prediction results of material indicators based on the AI ​​algorithm model loaded in the dynamic library during machine learning runtime; The control module is used to control the production line equipment based on the logic control runtime dynamic library, the motion control runtime dynamic library and the prediction results of the material indicators.

8. A non-transitory computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the control method according to claim 6 is implemented.

9. A computer program product having executable instructions stored thereon, characterized in that: When the instruction is executed by a processor, the processor implements the control method as claimed in claim 6.

Images