PROCESS CONTROL METHOD AND APPARATUS

Technical Field

The present invention mainly relates to the field of process control, in particular to a process control method and apparatus.

Background Art

In industrial control, PID controllers play a dominant role. The control performance of a PID controller depends on the fine adjustment of parameters (proportion, integral, differential) in a controller, wherein, while PID control is usually performed using an independent control loop, if a plurality of PID control loops are present, the PID control loops may influence one another, which will complicate the global PID control. In view of this background, model predictive controllers (MPCs) are introduced to obtain the optimal controller parameters on the basis of a process model, but if the problem of model drift occurs, it will lead to unanticipated and catastrophic consequences . In addition, a variety of production scenarios, such as different input flow rates and quality requirements, may be presented on a production line, and the existing PID controller cannot adapt to variable production scenarios .

Summary of the Invention

In order to solve the above-described technical problems, the present invention provides a process control method and apparatus that allow dynamic adjustment of control parameters of a PID controller, thus improving the accuracy of process control and making the process control globally optimal.

In order to achieve the above-mentioned objective, the present invention proposes a process control method comprising: outputting, with a PID controller, a control value to a plurality of devices in a process, and generating, with the plurality of devices in the process, an output value according to the control value; updating, according to the control value and the output value, the process simulation model corresponding to the process; and optimizing parameters of the PID controller according to the updated process simulation model, and performing process control on a plurality of devices in the process according to the optimized parameters of the PID controller. Therefore, the process simulation model of process control is dynamically updated, and the control parameters of the PID controller will be adjusted accordingly, which can eliminate any offset errors in the process simulation model so that the process, rather than being confronted by the problem of being locally optimal, becomes globally optimal.

Preferably, updating, according to the control value and the output value, the process simulation model corresponding to the process comprises training a reinforcement learning model according to the control value and the output value, and updating the process simulation model with the reinforcement learning model. Thus, updating a process simulation model with a reinforcement learning model allows the process simulation model to be updated more intelligently .

Preferably, the process control method comprises determining a nominal model and a noise model in the process simulation model, and updating the noise model in the process simulation model with the reinforcement learning model . Thus, the efficiency of updating a process simulation model may be improved.

Preferably, optimizing parameters of the PID controller according to the updated process simulation model comprises configuring a plurality of preset process scenarios, generating an optimization parameter set corresponding to the plurality of preset process scenarios, matching the current process scenario with the plurality of preset process scenarios, and determining optimization parameters in the optimization parameter set corresponding to the current process scenario. Thus, the accuracy of process control may be improved by configuring different preset process scenarios. Preferably, the process control method comprises detecting a process scenario of the process in real time, and when the process scenario changes, updating optimization parameters from the optimization parameter set. Thus, the real-timeliness of process control may be improved by dynamically updating optimization parameters according to process scenarios.

The present invention provides a process control apparatus comprising: a data acquisition module for outputting, with a PID controller, a control value to a plurality of devices in a process, and generating, with the plurality of devices in the process, an output value according to the control value; an update module for updating, according to the control value and the output value, the process simulation model corresponding to the process; and an optimization module for optimizing parameters of the PID controller according to the updated process simulation model, and performing process control on a plurality of devices in the process according to the optimized parameters of the PID controller.

Preferably, updating, with the update module, according to the control value and the output value, the process simulation model corresponding to the process comprises training a reinforcement learning model according to the control value and the output value, and updating the process simulation model with the reinforcement learning model.

Preferably, the process control apparatus comprises determining a nominal model and a noise model in the process simulation model, and updating the noise model in the process simulation model with the reinforcement learning model.

Preferably, optimizing, with the optimization module, parameters of the PID controller according to the updated process simulation model comprises configuring a plurality of preset process scenarios, generating an optimization parameter set corresponding to the plurality of preset process scenarios, matching the current process scenario with the plurality of preset process scenarios, and determining optimization parameters in the optimization parameter set corresponding to the current process scenario.

Preferably, the process control apparatus comprises detecting a process scenario of the process in real time, and when the process scenario changes, updating optimization parameters from the optimization parameter set.

The present invention provides an electronic device comprising a processor, a memory, and an instruction stored in the memory, wherein, when the instruction is executed by the processor, the method as described above is implemented.

The present invention proposes a computer-readable storage medium on which a computer instruction is stored, wherein, when the computer instruction is executed, the method as described above is implemented.

Brief Description of the Drawings

The following drawings are only intended to schematically illustrate and explain the present invention, rather than limiting the scope of the present invention. Among the drawings,

Fig. 1 is a flowchart of a process control method according to an embodiment of the present invention;

Fig. 2 is a schematic diagram of a process control method according to an embodiment of the present invention;

Fig. 3 is a schematic diagram of an offline module and an online module with a process control method according to an embodiment of the present invention;

Fig. 4 is a schematic diagram of a process control apparatus according to an embodiment of the present invention; and

Fig. 5 is a schematic diagram of an electronic device according to an embodiment of the present invention.

The reference numerals are as follows:

100: Process control method

110 - 130 : Steps

210: PID controller

220 : Process

230: Model correction module

240: Process simulation model

250: Optimization module

260: Optimization parameter set

270: Optimization parameter

280: Scenario configuration module

A: Edge device 410: Data acquisition module

420: Update module

430: Optimization module

500: Electronic device

510 : Processor

520: Memory

Specific Embodiments

In order to provide a better understanding of the technical features, objectives, and beneficial effects of the present invention, specific embodiments of the present invention will be described below with reference to the drawings.

While great details are provided below to give a fuller understanding of the present invention, the present invention may also be implemented in forms different from those described herein, and, therefore, the present invention is not limited to the specific embodiments disclosed below.

As indicated in the present application and claims, unless otherwise expressly specified in the context, a word like "a", "one", "one type", and/or "said", rather than referring in particular to the singular, may also include the plural. Generally, terms "comprise" and "include" only suggest inclusion of expressly identified steps and elements, but these steps and elements do not constitute an exclusive enumeration, so a method or device may also include other steps or elements.

The present invention proposes a process control method, and Fig. 1 is a flowchart of a process control method 100 according to an embodiment of the present invention. As shown in Fig. 1, the process control method 100 comprises:

Step 110, outputting, with a PID controller, a control value to a plurality of devices in a process, and generating, with the plurality of devices in the process, an output value according to the control value.

A process comprises a plurality of devices, a plurality of devices are connected to each other, and a plurality of devices are connected to form a process. A PID controller outputs a control value to a plurality of devices in a process, the PID controller being capable of controlling a plurality of loops, each loop having a corresponding PID controller, wherein, for example, the process comprises a first reaction tank and a second reaction tank, the first reaction tank and the second reaction tank being interconnected through a valve, the valve controlling the liquid level of the first reaction tank as a first control loop, the valve controlling the liquid level of the second reaction tank as a second control loop, the first control loop being controlled by a first PID controller, the second control loop being controlled by a second PID controller, and a plurality of devices in the process generate an output value according to a control value, wherein, for example, a liquid level sensor of the first reaction tank outputs a first liquid level output value, and a liquid level sensor of the second reaction tank outputs a second liquid level output value. In some cases, the first reaction tank needs a high flow rate, so the flow rate of the valve needs to be increased, but an increase in the flow rate of the valve will lead to a drastic change in the liquid level of the second reaction tank, which renders the second reaction tank unable to meet requirements and thus poses the problem of local optimum .

Fig. 2 is a schematic diagram of a process control method according to an embodiment of the present invention. As shown in Fig. 2, the PID controller 210 controls the process 220, wherein it is comprehensible that the PID controller 210 comprises a plurality of sub-PID controllers, the plurality of sub-PID controllers corresponding to different PID control loops, and the process 220 comprises a plurality of devices and connections among the devices. Step 120, updating, according to the control value and the output value, the process simulation model corresponding to the process. A process simulation model is a simulation model established after a process is simulated, capable of reflecting the topological structure and dynamic relationship of the process, and, after the PID controller outputs a control value to the process, the process outputs an output value according to the control value. The control value and output value are used to update the process simulation model corresponding to the process. In some embodiments, updating, according to a control value and an output value, the process simulation model corresponding to a process comprises training a reinforcement learning model according to the control value and the output value, and updating the process simulation model with the reinforcement learning model. In some embodiments, a nominal model and a noise model in the process simulation model are determined, and the noise model in the process simulation model is updated with a reinforcement learning model.

With continued reference to Fig. 2, a control value outputted by the PID controller 210 and an output value outputted by the process 220 are sent to a model correction module 230, and the model correction module 230 may be configured with a reinforcement learning model, wherein, for the reinforcement learning model, the process may be used as an environment, while an input to and an output from, that is, an input value and an output value of, the process are used as a state, so that the reinforcement learning model generates an action according to the state and a reward, the action acting on the environment. With a reinforcement learning model, a process simulation model may be updated intelligently, a process simulation model being usually divisible into a nominal model and a noise model, wherein the nominal model is the frame part of the process simulation model, which remains substantially unchanged, and the noise model is the noise part of the process simulation model, which often changes, so that after the nominal model and the noise model in a process simulation model are determined, a reinforcement learning model may be used to update the noise model in the process simulation model, thereby improving the efficiency of updating the process simulation model. Thus, the model correction module 230 has updated the process simulation model 240.

Step 130, optimizing parameters of the PID controller according to the updated process simulation model, and performing process control on a plurality of devices in the process according to the optimized parameters of the PID controller.

After the process simulation model is updated, parameters of the PID controller are optimized according to the updated process simulation model, and process control is performed on a plurality of devices in the process according to the optimized parameters of the PID controller. Therefore, the process simulation model of process control is dynamically updated, and the control parameters of the PID controller will be adjusted accordingly, which can eliminate any offset errors in the process simulation model so that the process, rather than being confronted by the problem of being locally optimal, becomes globally optimal.

In some embodiments, optimizing parameters of a PID controller according to an updated process simulation model comprises configuring a plurality of preset process scenarios, generating an optimization parameter set corresponding to the plurality of preset process scenarios, matching the current process scenario with the plurality of preset process scenarios, and determining optimization parameters in the optimization parameter set corresponding to the current process scenario. In some embodiments, the process control method comprises detecting a process scenario of the process in real time, and when the process scenario changes, updating optimization parameters from the optimization parameter set .

As shown in Fig. 2, an optimization module 250 generates optimization parameters according to the updated process simulation model 240, and corresponding optimization parameters are generated for unused preset process scenarios, these optimization parameters constituting an optimization parameter set 260. For example, a first preset process scenario, a second preset process scenario, and a third preset process scenario may be configured, the first preset process scenario having a flow rate of 5-20 t/h, the second preset process scenario having a flow rate of 20-40 t/h, the third preset process scenario having a flow rate of 40-50 t/h, wherein, in the first preset process scenario, the second preset process scenario, and the third preset process scenario, the corresponding first optimization parameter, second optimization parameter, and third optimization parameter are generated by the optimization module 250, and, comprehensibly, the first optimization parameter, the second optimization parameter and the third optimization parameter are composed of a plurality of parameters. If it is detected that the flow rate of the current process scenario is 35 t/h, then the second optimization parameter corresponding to the second preset process scenario is selected. In addition, when the process scenario of the process 220 is tested in real time, if the flow rate of the process 220 becomes 45 t/h, then the third optimization parameter corresponding to the third preset process scenario is selected. The model correction module 230, the process simulation model 240, the optimization module 250, the optimization parameter set 260, the optimization parameter 270, and the scenario configuration module 280 as shown in Fig. 2 may be fixed into hardware, for example, an edge device A.

Fig. 3 is a schematic diagram of an offline module and an online module with a process control method according to an embodiment of the present invention. To the left of the dashed line is the offline module, and to the right of the dashed line is the online module, which means that the process simulation module 240, the optimization module 250, the optimization parameter set 260, and the scenario configuration module 280 may be fixed in advance and applied to the online module during process control.

An embodiment of the present invention provides a process control method, wherein the process simulation model of process control is dynamically updated, and the control parameters of the PID controller will be adjusted accordingly, which can eliminate any offset errors in the process simulation model so that the process, rather than being confronted by the problem of being locally optimal, becomes globally optimal.

The present invention further provides a process control apparatus, and Fig. 4 is a schematic diagram of a process control apparatus 400 according to an embodiment of the present invention, the process control apparatus 400 comprising: a data acquisition module 410 for outputting, with a PID controller, a control value to a plurality of devices in a process, and generating, with the plurality of devices in the process, an output value according to the control value; an update module 420 for updating, according to the control value and the output value, the process simulation model corresponding to the process; and an optimization module 430 for optimizing parameters of the PID controller according to the updated process simulation model, and performing process control on a plurality of devices in the process according to the optimized parameters of the PID controller.

In some embodiments, updating, with an update module, according to a control value and an output value, the process simulation model corresponding to a process comprises training a reinforcement learning model according to the control value and the output value, and updating the process simulation model with the reinforcement learning model.

In some embodiments, the process control apparatus 400 comprises determining a nominal model and a noise model in the process simulation model, and updating the noise model in the process simulation model with a reinforcement learning model.

In some embodiments, optimizing, with the optimization module 430, parameters of a PID controller according to an updated process simulation model comprises configuring a plurality of preset process scenarios, generating an optimization parameter set corresponding to the plurality of preset process scenarios, matching the current process scenario with the plurality of preset process scenarios, and determining optimization parameters in the optimization parameter set corresponding to the current process scenario .

In some embodiments, the process control apparatus 400 comprises detecting a process scenario of the process in real time, and when the process scenario changes, updating optimization parameters from the optimization parameter set.

The present invention further provides an electronic device 400. Fig. 4 is a schematic diagram of an electronic device 400 according to an embodiment of the present invention. As shown in Fig. 4, the electronic device 400 comprises a processor 410 and a memory 420, an instruction being stored in the memory 420, wherein, when the instruction is executed by the processor 410, the method 100 as described above is implemented.

The present invention further proposes a computer-readable storage medium on which a computer instruction is stored, wherein, when the computer instruction is executed, the method 100 as described above is implemented.

Some aspects of a method and apparatus of the present invention may be performed entirely by hardware, entirely by software (including firmware, resident software, and microcode) , or by a combination of hardware and software. The above-mentioned hardware or software may be referred to as a "data block" , "module" , "engine" , "unit", "component" or "system" . A processor may be one or more application-specific integrated circuits (ASICs) , digital signal processors (DSPs) , digital signal processing devices (DAPDs) , programmable logic devices (PLDs) , field programmable gate arrays (FPGAs) , processors, controllers, microcontrollers, microprocessors, or a combination thereof. Further, aspects of the present invention may be embodied as a computer product located in one or more computer-readable media, the product comprising computer-readable program code. For example, computer-readable media may include, but are not limited to, magnetic storage devices such as hard disks, floppy disks, and magnetic tapes, optical disks such as compact discs (CDs) and digital versatile discs (DVDs) , and smart cards and flash memory devices such as card, stick, and key drives .

Flowcharts are used herein to explain operations performed with a method according to an embodiment of the present application. It should be understood that the preceding operations are not necessarily performed in exact order. On the contrary, various steps may be performed in reverse order or concurrently. In addition, other operations may also be added to these processes, or one or more steps may be removed from these processes.

It should be understood that although the embodiments are described separately herein, an embodiment does not contain only one independent technical solution, that such a method of description is only for the sake of clarity, that those of ordinary skill in the art should treat the description as a whole, and that the technical solutions provided in the embodiment s may be appropriately combined into other embodiment s that those of ordinary skill in the art understand .

The above-described specific embodiment s are only illustrative of the present invention, rather than limiting the scope of the present invention . Any equivalent variations , modifications , or combinations made by any of those of ordinary skill in the art without departing from the spirit or principle of the present invention shall fall into the scope of the present invention .