WO2022110115A1

WO2022110115A1 - Industrial process intelligent control method and system

Info

Publication number: WO2022110115A1
Application number: PCT/CN2020/132679
Authority: WO
Inventors: 王珍珍; 严俊杰; 出口祥啓; 神本崇博
Original assignee: 西安交通大学; 德岛大学
Priority date: 2020-11-30
Filing date: 2020-11-30
Publication date: 2022-06-02
Also published as: CN114846414A; JP2023553375A

Abstract

An industrial process intelligent control method and system. The industrial process intelligent control method comprises the following steps: if a stop condition is not met, acquiring original measurement data of a controlled object (100) (S101); analyzing the original measurement data to obtain analyzed measurement data (S102); learning the analyzed measurement data by means of a deep learning model (50), and determining a control scheme (S103); and controlling the controlled object according to a controlled action amount obtained by the control scheme (S104). By means of a new generation process control platform (30), analysis and judgment are performed according to an error between a given value of the controlled variable and a measured value of the controlled variable and various evaluation indicators of the industrial process of the controlled object (100), such that a control effect which satisfies requirements and expectations is obtained.

Description

Industrial process intelligent control method and system

technical field

The present application relates to the field of industrial process control, and in particular, to an industrial process intelligent control method and system.

Background technique

Process control has a wide range of applications in power, petroleum, chemical, metallurgical and other industrial production. Through the control of process parameters such as temperature, pressure, flow, liquid level, composition, concentration, etc., industrial process efficiency can be improved, energy consumption can be reduced, and output can be increased. With the continuous advancement of scientific and technological innovation, the industrial production process is developing towards deep energy conservation and intelligence.

The fast and accurate measurement of process parameters is the basic premise for realizing industrial process control. As a potential and prospective online analysis technology, non-contact laser measurement technology has significant advantages compared with existing detection technology. High-precision non-contact laser measurement can meet the requirements of accurate and rapid online measurement in high temperature and harsh environments. Its measurement data is the basis for building an integrated and intelligent industrial production system, laying a foundation for efficient integration and intelligent control of information systems and physical systems. Base.

Therefore, laser measurement technologies such as computed tomography-tunable semiconductor laser absorption spectroscopy (CT-TDLAS) and laser-induced breakdown spectroscopy (LIBS) are developed to achieve in-situ, non-contact and high-speed measurement of temperature and material composition in industrial processes. Spatiotemporally resolved online measurements. The industrial process intelligent monitoring and control platform that couples high-precision laser measurement and numerical simulation has become an important development direction of process monitoring and control in the field of industrial measurement and control, and has high practical application value.

However, there are various problems in today's industrial process control. For example, the problems that are prone to occur in measurement are: only point measurement can be achieved instead of surface measurement, non-online measurement, and non-fast; the problems that are prone to occur in control are: Due to the defects of the measurement method, the control is delayed and the adjustment is delayed; CFD simulation needs measurement data to verify and optimize, and the accuracy of the simulation results is insufficient; in addition, there are problems such as insufficient data volume.

For example, the response speed of CFD simulation analysis is slow, the simulation time is too long, and the simulation results are not accurate enough, resulting in problems such as adjustment lag and inaccurate simulation analysis.

SUMMARY OF THE INVENTION

In view of the above problems, an embodiment of the present invention proposes an industrial process intelligent control method and system to solve the problems existing in the prior art.

In order to solve the above problems, an embodiment of the present application discloses an industrial process intelligent control method, which includes the following steps:

If the stop condition is not reached, obtain the original measurement data of the control object;

Analyzing the original measurement data to obtain the analyzed measurement data;

Use a deep learning model to learn the analyzed measurement data to determine a control plan;

The control object is controlled according to the control action amount obtained by the control scheme.

In order to solve the above problem, an embodiment of the present application further discloses a terminal device, including:

one or more processors; and

One or more machine-readable media having instructions stored thereon that, when executed by the one or more processors, cause the terminal device to perform the method as previously described.

In order to solve the above problem, an embodiment of the present application discloses an industrial process intelligent control system, the industrial process intelligent control system includes: a measurement device, an analysis module, a process control platform, and an automatic control device;

The measurement device is used to obtain the original measurement data of the control object under the condition that the stop condition is not reached;

The analysis module is used to analyze the original measurement data to obtain the analyzed measurement data;

The process control platform is used for using the deep learning model to learn the analyzed measurement data to determine a control scheme;

The automatic control device is used for controlling the control object according to the control action amount obtained by the control scheme.

An embodiment of the present application also discloses a terminal device, including:

one or more processors; and

One or more machine-readable media having instructions stored thereon, when executed by the one or more processors, cause the terminal device to perform the above-described method.

An embodiment of the present application further discloses one or more machine-readable media on which instructions are stored, and when executed by one or more processors, cause the terminal device to execute the above method.

It can be seen from the above that the embodiments of the present application include the following advantages:

According to the industrial process intelligent control method proposed in the embodiment of the present invention, through the new generation process control platform, according to the error between the given value of the controlled variable and the measured value of the controlled variable and the various parameters of the industrial process of the control object Class evaluation indicators are used to analyze and judge to obtain the control effect that meets the requirements and expectations.

Description of drawings

In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the following briefly introduces the accompanying drawings that need to be used in the description of the embodiments or the prior art. Obviously, the accompanying drawings in the following description These are some embodiments of the present invention. For those of ordinary skill in the art, other drawings can also be obtained according to these drawings without creative efforts.

FIG. 1 is a block diagram of an industrial process intelligent control system according to an embodiment of the present invention.

FIG. 2 is a schematic structural diagram of a deep learning model corresponding to the deep learning process 1 according to an embodiment of the present invention.

FIG. 3 is a schematic structural diagram of a deep learning model corresponding to the deep learning process 2 according to an embodiment of the present invention.

FIG. 4 is a flowchart of an industrial process intelligent control method according to an embodiment of the present invention.

FIG. 5 is a block diagram of an intelligent control system in a thermal power plant according to an embodiment of the present invention.

6 shows a block diagram of an intelligent control system in a semiconductor industry process according to an embodiment of the present invention.

Figure 7 schematically shows a block diagram of a terminal device for carrying out the method according to the invention.

Figure 8 schematically shows a memory unit for holding or carrying program code implementing the method according to the invention.

Detailed ways

The technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the drawings in the embodiments of the present application. Obviously, the described embodiments are only a part of the embodiments of the present application, but not all of the embodiments. All other embodiments obtained by those of ordinary skill in the art based on the embodiments in the present application fall within the protection scope of the present application.

first embodiment

The first embodiment of the present invention proposes an industrial process intelligent control system. FIG. 1 is a block diagram of an industrial process intelligent control system according to an embodiment of the present invention. The industrial process intelligent control system proposed in the embodiment of the present invention has a wide range of uses, for example, it can be applied to measure the temperature field and the concentration field by using a laser. The industrial process intelligent control system is used to control the control object, including: a measuring device 10, an Module 20 , process control platform 30 and automatic control device 40 .

The measurement device 10 is used to obtain the original measurement data of the control object;

The analysis module 20 is configured to analyze the original measurement data to obtain the analyzed measurement data;

The process control platform 30 is configured to determine a control scheme according to the analyzed measurement data;

The automatic control device 40 is configured to control the control object according to the control action amount obtained from the control scheme;

In the case where the stop condition is not reached, the measurement device 10 repeatedly performs the operation of measuring the raw measurement data.

The measurement device 10 is, for example, a laser measurement device that implements various laser measurement techniques such as computed tomography-tunable semiconductor laser absorption spectroscopy and laser-induced breakdown spectroscopy, and may also be a conventional measurement device. The original measurement data is the data obtained by measurement. But it is not limited to this device, other measurement devices that meet the measurement requirements are suitable for the industrial process intelligent control system of the present invention; in the embodiment of the present invention, the original measurement data obtained by the real-time measurement of the laser measurement device The parameters require the analysis module 20 to select the corresponding measurement method. The analysis module 20 may be an analysis model, which analyzes the raw measurement data of the measurement device collected in real time, and obtains the analyzed measurement data, that is, the process parameters of the industrial process to be obtained.

In the embodiment of the present invention, according to the characteristics of the industrial process and the industrial process parameters that need to be measured quickly and accurately, for example, the fields of thermal power plants, semiconductor industries, engines, gas turbines, and metallurgical industries need to obtain temperature, pressure, flow, liquid level, composition, The industrial process of process parameters such as concentration, and the measurement device required to build the control object. The measurement data analyzed by the analysis module 20 in the embodiment of the present invention are, for example, process parameters such as temperature, pressure, flow rate, liquid level, composition, and concentration. This will be described as an example below.

As shown in FIG. 1 , the process control platform 30 learns the analyzed measurement data through the deep learning model 50 , where the source of the analyzed measurement data is not limited to the laser measurement method, but also includes other process parameters obtained by other measurement methods. . The CFD simulation module 70 of the control object is optimized according to the learning result, and the optimized CFD data is obtained, the CFD database 60 is established, and the CFD big data analysis platform is developed.

The analyzed measurement data is combined with the existing CFD data to obtain optimized CFD data through deep learning of the deep learning model 50, and then a control scheme is provided through the process control platform 30 according to the optimized CFD data;

The automatic control device 40 makes the actuator act according to the control scheme provided by the process control platform 30 , adjusts the control action amount, and then changes the controlled amount of the control object 100 .

When the stop condition is not reached, the measurement device 10 is used to repeatedly measure the controlled object 100, and through the process control platform 30, according to the error between the given value of the controlled variable and the measured value of the controlled variable and the control Analyze and judge various evaluation indicators of the object industrial process, obtain process parameters that meet the conditions, and achieve the expected control effect.

The measurement and control of process parameters in the industrial process are in a state of dynamic adjustment, and the process parameters can be monitored in real time. The index analyzes whether the control object 100 needs to be controlled by the automatic control device 40 .

The evaluation of the industrial process intelligent control system based on laser measurement in the control process can be analyzed from five aspects: 1, the evaluation index of the laser measurement method itself; 2, the evaluation index of the CFD simulation model itself; 3, the measurement results and simulation The error of the result; 4, the error of the measured value of the controlled quantity and the given value of the controlled quantity; and, 5, the comprehensive evaluation index such as the efficiency and energy consumption of the industrial process. When each evaluation index, error and comprehensive evaluation index are globally optimal, the expected control effect is achieved. In some embodiments, the stop condition may be that a desired control condition has been reached, or a production time has been reached, or the like. When it is judged that the stop condition is reached, the cyclic measurement is stopped.

FIG. 1 shows two deep learning processes involved in the process control platform 30 , which are respectively deep learning process 1 and deep learning process 2 marked by dotted lines. The optimization of the measurement data and CFD data of the control object 100 under different operating conditions and the formation of big data from the CFD database is a deep learning process 1. This learning process is a long-term process, with the accumulation of data for several months or years, and the amount of data is very large. Important; optimize CFD data through real-time measurement data and existing CFD data in the CFD database, and then provide a control scheme through the process control platform as deep learning process 2. This learning process is a transient real-time process, and timeliness is very important.

The above two deep learning processes may be performed by different deep learning models respectively, or may be performed in the same deep learning model. In the present invention, only the deep learning model 50 is used to represent the executive body performing the two different deep learning processes 1 and 2 . In other embodiments, for example, deep learning process 2 may be performed by one deep learning model, while deep learning process 1 may be performed by another deep learning model.

For the deep learning process 1 , FIG. 2 is a schematic diagram of the model architecture for the deep learning process 1 . As shown in Figure 2, in the deep learning model, the input layer 1 is the measurement data at different times and the result error of the deep learning process 2, the input layer 2 is the various parameters of the CFD model, and the output layer is the optimized parameters calculated according to the CFD model. of CFD data. According to the output CFD data, establish a CFD database and form CFD big data.

For the deep learning process 2 , FIG. 3 is a schematic diagram of the model architecture for the deep learning process 2 . As shown in Figure 3, the input layer 1 of the deep learning model is the real-time measurement data, the input layer 2 is the CFD data in the existing CFD database, including the results of simple algebraic operations on the existing CFD data, and the output layer is based on the existing CFD data. The optimized CFD data obtained by CFD data calculation, and then provide a control scheme through the process control platform according to the optimized CFD data.

In an optional embodiment, the process control platform may further include a first database unit and a first deep learning model unit for respectively performing the following operations:

The first database unit is used to store a plurality of analyzed measurement data;

The first deep learning model unit is configured to use the first deep learning model to learn the stored multiple analyzed measurement data, and output the CFD data processed by the first deep learning model.

In an optional embodiment, the process control platform may further include a second database unit and a second deep learning model unit for respectively performing the following operations:

The second database unit is used to store a plurality of analyzed measurement data and historical CFD data;

The first deep learning model unit is configured to use the second deep learning model to learn the stored multiple analyzed measurement data and historical CFD data, and to optimize the CFD simulation module.

In an optional embodiment, the analysis module may further include an analysis model determination unit and an analysis unit, respectively configured to perform the following operations:

The analysis model determination unit is used for determining the analysis model according to the raw measurement data of the measurement device collected in real time; and

The analysis unit is used for performing analysis using the determined analysis model to obtain the analyzed measurement data.

It can be seen from the above that the industrial process intelligent control system proposed by the first embodiment of the present invention has at least the following technical effects:

According to the industrial process intelligent control system proposed in the embodiment of the present invention, through the new generation process control platform, according to the error between the given value of the controlled variable and the measured value of the controlled variable and the various parameters of the industrial process of the control object Class evaluation indicators are used to analyze and judge to obtain the control effect that meets the requirements and expectations.

In addition, the industrial process intelligent control system proposed in this embodiment at least further includes the following advantages:

According to the industrial process intelligent control system proposed by the embodiment of the present invention, the analyzed measurement data is learned through artificial intelligence algorithms such as deep learning inside the process control platform. The source of the analyzed measurement data here is not limited to the laser measurement method, but also Include other process parameters obtained by other measurement methods. According to the learning results, the CFD simulation module of the control object is optimized, and the optimized CFD data is obtained, the CFD database is established, and the CFD big data analysis platform is developed. The analyzed real-time measurement data is combined with the existing CFD data to obtain optimized CFD data through deep learning of the process control platform, and then a control scheme is provided through the process control platform according to the optimized CFD data. The automatic control device makes the actuator act to adjust the control action amount according to the control scheme provided by the process control platform, thereby changing the controlled amount of the control object. The measurement device is used to repeatedly measure the control object, and through the process control platform, analysis and judgment are made according to the error between the given value of the controlled quantity and the measured value of the controlled quantity and various evaluation indicators of the industrial process of the control object. Obtain the process parameters that meet the conditions to achieve the expected control effect.

The measurement and control of process parameters in the industrial process are in a state of dynamic adjustment, and the process parameters can be monitored in real time. Whether the index analysis needs to control the control object through the automatic control device.

The control system and method of the present invention are not only suitable for thermal power plants and semiconductor industrial processes, but also can be applied to the fields of engines, gas turbines, metallurgical industries, etc., to realize intelligent control of industrial processes. But it is not limited to these fields.

The invention establishes the CFD simulation model of the control object, calculates the CFD data of the control object under different operating conditions, and provides the CFD data obtained by the calculation to the process control platform in the form of a database; the process control platform uses artificial intelligence algorithms such as deep learning inside the process control platform. Accumulate and study the analyzed measurement data, and optimize the CFD simulation module of the control object according to the learning results to obtain the optimized CFD data; establish CFD according to the CFD data of the control object under different operating conditions and the CFD data optimized by deep learning Database, develop CFD big data analysis platform in process control platform. The real-time process parameters of the control object are in a dynamic measurement state, the CFD data optimized by deep learning is also in a dynamic adjustment state, and the established CFD database is constantly being updated and improved. In the process control platform, data analysis is performed between the analyzed measurement data, CFD data and optimized CFD data through artificial intelligence algorithms such as deep learning.

Second Embodiment

The second embodiment of the present invention provides an industrial process intelligent control method. FIG. 4 is a flowchart showing the steps of an industrial process intelligent control method according to a second embodiment of the present invention. As shown in FIG. 4 , the industrial process intelligent control method according to the embodiment of the present invention includes the following steps:

S101, in the case that the stop condition is not reached, obtain the original measurement data of the control object;

In this step, the execution subject is, for example, the measurement device 10 of the industrial process intelligent control system, and the measurement device 10 is, for example, implementing various laser measurement technologies such as computed tomography-tunable semiconductor laser absorption spectroscopy technology, laser-induced breakdown spectroscopy technology, etc. The laser measuring device can also be a traditional measuring device, but it is not limited to this device, and other measuring devices that meet the measurement requirements are suitable for the industrial process intelligent control method described in the present invention. The raw measurement data is, for example, data obtained by measurement.

S102, analyze the original measurement data to obtain the analyzed measurement data;

In this step, the execution subject is, for example, the analysis module 20 of the industrial process intelligent control system. The analysis module 20 may be an analysis model, which analyzes the raw measurement data of the measurement device collected in real time, and obtains the analyzed measurement data, that is, the process parameters of the industrial process to be obtained.

S103, using a deep learning model to learn the analyzed measurement data to determine a control scheme;

In this step, the executive body is, for example, the process control platform 30 of the industrial process intelligent control system. The process control platform 30 learns the analyzed measurement data through the deep learning model 50 , uses the deep learning model to optimize the analyzed measurement data, and generates a control plan according to the optimized CFD data.

S104: Control the control object according to the control action amount obtained by the control scheme.

In this step, the executive body is, for example, the automatic control device 40 of the industrial process intelligent control system. The automatic control device 40 makes the actuator act according to the control scheme provided by the process control platform 30 , adjusts the control action amount, and then changes the controlled amount of the control object 100 .

It can be seen from the above that the industrial process intelligent control method proposed by the second embodiment of the present invention has at least the following technical effects:

In addition, the industrial process intelligent control method proposed in this embodiment at least further includes the following advantages:

According to the industrial process intelligent control method proposed in the embodiment of the present invention, the analyzed measurement data is learned through artificial intelligence algorithms such as deep learning inside the process control platform. The source of the analyzed measurement data here is not only limited to the laser measurement method, but also Include other process parameters obtained by other measurement methods. According to the learning results, the CFD simulation module of the control object is optimized, and the optimized CFD data is obtained, the CFD database is established, and the CFD big data analysis platform is developed. The analyzed real-time measurement data is combined with the existing CFD data to obtain optimized CFD data through deep learning of the process control platform, and then a control scheme is provided through the process control platform according to the optimized CFD data. The automatic control device makes the actuator act to adjust the control action amount according to the control scheme provided by the process control platform, thereby changing the controlled amount of the control object. The measurement device is used to repeatedly measure the control object, and through the process control platform, analysis and judgment are made according to the error between the given value of the controlled quantity and the measured value of the controlled quantity and various evaluation indicators of the industrial process of the control object. Obtain the process parameters that meet the conditions to achieve the expected control effect.

Third Embodiment

FIG. 5 is a block diagram of an intelligent control system in a thermal power plant according to an embodiment of the present invention. As shown in Figure 5, the intelligent monitoring and control system and method for coupling laser measurement and numerical simulation of industrial process temperature field and component concentration field are described in detail by taking the boiler control of thermal power plant as an example. Laser absorption spectroscopy technology measures the temperature distribution of boiler furnace and tail flue and the concentration distribution of other components, and realizes the application of high-end technologies such as big data, Internet of Things, cloud platform in thermal power plants, thereby improving the efficiency of thermal power plants and realizing energy saving and reduction in thermal power plants. It can realize intelligent control of thermal power plant process.

The system shown in Figure 5 mainly includes two parts: measurement control system and intelligent monitoring and control platform. In the measurement and control system part, a CT-TDLAS measurement device is built according to the boiler furnace structure and tail flue structure, and the internal temperature field and gas component concentration field of the furnace, the temperature field of the tail flue, and the nitrogen oxides and ammonia before and after the denitrification device are measured respectively. gas concentration field, etc. The original measurement data of each measuring device is collected in real time, and the original measurement data is analyzed by the analysis module to obtain the temperature field and gas concentration field of the measurement section of the furnace and the tail flue, and the analyzed measurement data can be displayed on the display. The control scheme is provided through the analysis of the new generation process control platform, and the powder feeding volume and the secondary air volume of the boiler are adjusted by the automatic control device, so that the furnace and tail flue temperature and gas concentration meet the set values and achieve the expected control effect.

In the part of the intelligent monitoring and control platform, the measurement data of CT-TDLAS is represented by ai, and the CT-TDLAS database Ai is established from the historical measurement data of CT-TDLAS; the CFD simulation model of the combustion process of the boiler under different operating conditions is established according to the boiler structure. The CFD simulation results are obtained by setting the parameters of the CFD model, such as the CFD data of the temperature field and the concentration field, and the CFD database Di is established; according to the laser optical path structure of the CT-TDLAS measurement device, the temperature and concentration of the CT-TDLAS data and the CFD data are obtained respectively. The mean, fluctuation value, and probability density function on each path of the distribution, denoted by Bi and

To represent, compare the database Bi of CT-TDLAS measurement results path statistics with the database of CFD simulation results path statistics

The correction function is formed by the CFD model parameter database Ci and the CFD database Di, as well as the database Bi of the path statistics of the measurement results and the database of the path statistics of the simulation results

The difference constitutes a label. The deep learning method is used to process data preprocessing, feature selection, model construction, parameter optimization and evaluation. When the model error after deep learning is not less than the set value error ε, the deep learning process The model parameters continue to be optimized; when the model error after deep learning is less than the set value error ε, the CFD model parameters with the smallest error between the simulation results and the measurement results are output, and the established model parameter database Ci is updated and improved to obtain the optimized CFD data. Further update and improve the established CFD database Di.

In the intelligent monitoring and control platform part, there are two types of deep learning processes, long-term accumulation process and transient real-time process. The long-term accumulation process, that is, the CFD database is obtained through the accumulation of measurement data and CFD simulation data to form CFD big data; the transient real-time process is to obtain optimized CFD data based on real-time measurement data and existing CFD data, and then provide a control scheme bi .

In this example, the evaluation of the thermal power plant intelligent control system based on CT-TDLAS laser measurement in the control process, in addition to the model error analysis measurement results and simulation results in the deep learning process, the thermal power plant intelligent control system can also be evaluated from the following aspects To analyze and evaluate:

Evaluation of CT-TDLAS measurement methods such as the accuracy of TDLAS measurement of temperature and concentration and the reconstruction accuracy of CT algorithm; CFD simulation errors such as grid scale error, time step error, iteration error and input parameter error; furnace internal temperature and gas Errors between the measured values of component concentrations, tail flue temperature, nitrogen oxides and ammonia concentrations before and after the denitrification device and the given values; steam consumption and heat consumption of steam turbine units, heat consumption of power plants, power plants Coal consumption and power generation efficiency and other thermal economic indicators of power plants. When each evaluation index, error and comprehensive evaluation index are globally optimal, the expected control effect is achieved.

Fourth Embodiment

6 shows a block diagram of an intelligent control system in a semiconductor industry process according to an embodiment of the present invention. As shown in Figure 6, the intelligent monitoring and control system and method for coupling the laser measurement and numerical simulation of the temperature field and component concentration field of the industrial process are described in detail by taking the control of the film-forming device in the semiconductor manufacturing process as an example. -The tunable semiconductor laser absorption spectroscopy technology measures the temperature field and gas concentration field distribution in the film forming device to achieve the purpose of controlling the performance of semiconductor materials.

It is worth noting that the control system and method of the present invention are not only suitable for thermal power plants and semiconductor industrial processes, but also can be applied to fields such as engines, gas turbines and metallurgical industries to realize intelligent control of industrial processes. But it is not limited to these fields. In addition, the laser measurement technology adopted in the present invention includes not only the computed tomography scanning-tunable semiconductor laser absorption spectroscopy technology, but also the laser-induced breakdown spectroscopy technology and the like.

FIG. 7 is a schematic diagram of a hardware structure of a terminal device according to an embodiment of the present application. As shown in FIG. 7 , the terminal device may include an input device 90 , a processor 91 , an output device 92 , a memory 93 and at least one communication bus 94 . A communication bus 94 is used to enable communication connections between elements. The memory 93 may include a high-speed RAM memory, and may also include a non-volatile memory NVM, such as at least one disk memory. Various programs may be stored in the memory 93 for performing various processing functions and implementing the method steps of this embodiment.

Optionally, the above-mentioned processor 91 may be, for example, a central processing unit (Central Processing Unit, CPU for short), an application specific integrated circuit (ASIC), a digital signal processor (DSP), a digital signal processing device (DSPD), a programmable logic Device (PLD), Field Programmable Gate Array (FPGA), controller, microcontroller, microprocessor or other electronic component implementation, the processor 91 is coupled to the aforementioned input device 90 and output device 92 through wired or wireless connections.

Optionally, the above-mentioned input device 90 may include various input devices, for example, may include at least one of a user-oriented user interface, a device-oriented device interface, a software programmable interface, a camera, and a sensor. Optionally, the device-oriented device interface may be a wired interface for data transmission between devices, or a hardware plug-in interface (such as a USB interface, serial port, etc.) for data transmission between devices. ); optionally, the user-oriented user interface may be, for example, a user-oriented control button, a voice input device for receiving voice input, and a touch sensing device (such as a touch screen with a touch sensing function, a touch sensing device for receiving a user's touch input) board, etc.); optionally, the programmable interface of the above software can be, for example, an entry for a user to edit or modify a program, such as an input pin interface or an input interface of a chip. Audio input devices such as microphones can receive voice data. The output device 92 may include output devices such as a display, an audio system, and the like.

In this embodiment, the processor of the terminal device has a function for executing each module of the data processing apparatus in each device, and the specific functions and technical effects may refer to the above-mentioned embodiments, which will not be repeated here.

FIG. 8 is a schematic diagram of a hardware structure of a terminal device according to another embodiment of the present application. FIG. 8 is a specific embodiment of the implementation process of FIG. 7 . As shown in FIG. 8 , the terminal device in this embodiment includes a processor 101 and a memory 102 .

The processor 101 executes the computer program codes stored in the memory 102 to implement the industrial process intelligent control method shown in FIG. 4 in the above embodiment.

The memory 102 is configured to store various types of data to support operation at the terminal device. Examples of such data include instructions for any application or method operating on the end device, such as messages, pictures, videos, etc. The memory 102 may include random access memory (RAM for short), and may also include non-volatile memory (non-volatile memory), such as at least one disk storage.

Optionally, the processor 101 is provided in the processing component 100 . The terminal device may further include: a communication component 103, a power supply component 104, a multimedia component 105, an audio component 106, an input/output interface 107 and/or a sensor component 108. Components and the like specifically included in the terminal device are set according to actual requirements, which are not limited in this embodiment.

The processing component 100 generally controls the overall operation of the terminal device. The processing component 100 may include one or more processors 101 to execute instructions to perform all or part of the steps of FIG. 4 described above. Additionally, processing component 100 may include one or more modules to facilitate interaction between processing component 100 and other components. For example, processing component 100 may include a multimedia module to facilitate interaction between multimedia component 105 and processing component 100 .

The power supply assembly 104 provides power to various components of the terminal device. Power components 104 may include a power management system, one or more power supplies, and other components associated with generating, managing, and distributing power to end devices.

The multimedia component 105 includes a display screen that provides an output interface between the terminal device and the user. In some embodiments, the display screen may include a liquid crystal display (LCD) and a touch panel (TP). If the display screen includes a touch panel, the display screen may be implemented as a touch screen to receive input signals from a user. The touch panel includes one or more touch sensors to sense touch, swipe, and gestures on the touch panel. The touch sensor may not only sense the boundaries of a touch or swipe action, but also detect the duration and pressure associated with the touch or swipe action.

Audio component 106 is configured to output and/or input audio signals. For example, the audio component 106 includes a microphone (MIC) that is configured to receive external audio signals when the terminal device is in an operational mode, such as a speech recognition mode. The received audio signal may be further stored in the memory 102 or transmitted via the communication component 103 . In some embodiments, the audio component 106 also includes a speaker for outputting audio signals.

The input/output interface 107 provides an interface between the processing component 100 and a peripheral interface module, which may be a click wheel, a button, or the like. These buttons may include, but are not limited to, volume buttons, start buttons, and lock buttons.

Sensor assembly 108 includes one or more sensors for providing various aspects of the status assessment for the end device. For example, the sensor assembly 108 may detect the open/closed state of the end device, the relative positioning of the assembly, the presence or absence of user contact with the end device. The sensor assembly 108 may include a proximity sensor configured to detect the presence of nearby objects in the absence of any physical contact, including detecting the distance between the user and the end device. In some embodiments, the sensor assembly 108 may also include a camera or the like.

Communication component 103 is configured to facilitate wired or wireless communication between end devices and other devices. Terminal devices can access wireless networks based on communication standards, such as WiFi, 2G or 3G, or a combination thereof. In one embodiment, the terminal device may include a SIM card slot, and the SIM card slot is used for inserting a SIM card, so that the terminal device can log in to the GPRS network and establish communication with the server through the Internet.

As can be seen from the above, the communication component 103, the audio component 106, the input/output interface 107, and the sensor component 108 involved in the embodiment of FIG. 8 can all be implemented as the input device in the embodiment of FIG. 7 .

Embodiments of the present application provide a terminal device, including: one or more processors; and one or more machine-readable media on which instructions are stored, which, when executed by the one or more processors, cause The terminal device executes one or more of the methods described in the embodiments of this application.

The various embodiments in this specification are described in a progressive manner, and each embodiment focuses on the differences from other embodiments, and the same and similar parts between the various embodiments may be referred to each other.

Although the preferred embodiments of the embodiments of the present application have been described, those skilled in the art may make additional changes and modifications to these embodiments once the basic inventive concepts are known. Therefore, the appended claims are intended to be construed to include the preferred embodiments as well as all changes and modifications that fall within the scope of the embodiments of the present application.

Finally, it should also be noted that in this document, relational terms such as first and second are used only to distinguish one entity or operation from another, and do not necessarily require or imply these entities or that there is any such actual relationship or sequence between operations. Moreover, the terms "comprising", "comprising" or any other variation thereof are intended to encompass non-exclusive inclusion such that a process, method, article or terminal device that includes a list of elements includes not only those elements, but also a non-exclusive list of elements. other elements, or also include elements inherent to such a process, method, article or terminal equipment. Without further limitation, an element defined by the phrase "comprises a..." does not preclude the presence of additional identical elements in the process, method, article, or terminal device that includes the element.

A method and system for intelligent control of an industrial process provided by the present application have been introduced in detail above. The principles and implementations of the present application are described with specific examples in this paper. The method of the application and its core idea; at the same time, for those skilled in the art, according to the idea of the application, there will be changes in the specific implementation and application scope. In summary, the content of this description should not be understood to limit this application.

Claims

An industrial process intelligent control method, characterized in that it includes:

If the stop condition is not reached, obtain the original measurement data of the control object;

Analyzing the original measurement data to obtain the analyzed measurement data;

Use the deep learning model to learn the analyzed measurement data to determine the control plan;

The control object is controlled according to the control action obtained by the control scheme.
The industrial process intelligent control method according to claim 1, wherein the step of using a deep learning model to learn the analyzed measurement data, and determining a control scheme comprises:

storing a plurality of analyzed measurement data in the first database;

Using the first deep learning model to learn the stored multiple analyzed measurement data, and output the CFD data processed by the first deep learning model.
The industrial process intelligent control method according to claim 2, wherein the step of using a deep learning model to learn the analyzed measurement data, and determining a control scheme further comprises:

storing a plurality of analyzed measurement data and historical CFD data in a second database;

The second deep learning model is used to learn the stored multiple analyzed measurement data and historical CFD data to optimize the CFD simulation module.
The method for intelligent control of an industrial process according to claim 1, wherein the step of analyzing the original measurement data and obtaining the analyzed measurement data comprises:

Determine the analysis model according to the original measurement data of the measurement device collected in real time;

The analysis is performed using the determined analysis model, and the analyzed measurement data is obtained.
The intelligent control method for an industrial process according to claim 1, wherein the raw measurement data includes at least one of temperature, pressure, flow rate, liquid level, composition, and concentration.
The industrial process intelligent control method according to claim 1, wherein the measurement device comprises a laser measurement device.
The industrial process intelligent control method according to claim 1, wherein the measurement device is a laser measurement device of computed tomography-tunable semiconductor laser absorption spectrum.
The intelligent control method for an industrial process according to claim 1, wherein the stop condition includes one of the end of production time or the achievement of a control target.
An industrial process intelligent control system for controlling a control object, characterized in that the industrial process intelligent control system comprises: a measuring device, an analysis module, a process control platform and an automatic control device;

The measurement device is used to obtain the original measurement data of the control object under the condition that the stop condition is not reached;

The analysis module is used to analyze the original measurement data to obtain the analyzed measurement data;

The process control platform is used for using the deep learning model to learn the analyzed measurement data to determine a control scheme;

The automatic control device is used for controlling the control object according to the control action amount obtained by the control scheme.
The industrial process intelligent control system according to claim 9, wherein the process control platform comprises:

a first database unit for storing a plurality of analyzed measurement data;

The first deep learning model unit is configured to use the first deep learning model to learn the stored multiple analyzed measurement data, and output the CFD data processed by the first deep learning model.
The industrial process intelligent control system according to claim 10, wherein the process control platform further comprises:

a second database unit for storing a plurality of analyzed measurement data and historical CFD data;

The first deep learning model unit is configured to use the second deep learning model to learn from the stored multiple analyzed measurement data and historical CFD data, and to optimize the CFD simulation module.
The industrial process intelligent control system according to claim 9, wherein the analysis module comprises:

an analysis model determination unit for determining an analysis model according to the raw measurement data of the measurement device collected in real time; and

The analysis unit is configured to perform analysis by using the determined analysis model to obtain the analyzed measurement data.
The intelligent control method for an industrial process according to claim 9, wherein the raw measurement data includes at least one of temperature, pressure, flow rate, liquid level, composition, and concentration.
The industrial process intelligent control method according to claim 9, wherein the measurement device comprises a laser measurement device.
The industrial process intelligent control method according to claim 9, wherein the measuring device is a laser measuring device based on computed tomography-tunable semiconductor laser absorption spectroscopy technology or a laser measuring device using laser induced breakdown spectroscopy technology.
The method for intelligent control of an industrial process according to claim 9, wherein the stop condition comprises one of the end of production time or the achievement of a control target.
A terminal device, characterized in that it includes:

one or more processors; and

One or more machine-readable media having instructions stored thereon which, when executed by the one or more processors, cause the terminal device to perform the method of one or more of claims 1-9.
One or more machine-readable media having stored thereon instructions which, when executed by one or more processors, cause a terminal device to perform a method as claimed in one or more of claims 1-9.