CN113532137A

CN113532137A - Operation control method and device for reaction furnace, medium and electronic equipment

Info

Publication number: CN113532137A
Application number: CN202110838351.XA
Authority: CN
Inventors: 姚心; 刘海威; 郭天宇; 张瑛华; 骆嘉辉; 贺迪龙; 杨培培; 王禺辰; 欧阳冰玉
Original assignee: China ENFI Engineering Corp
Current assignee: China ENFI Engineering Corp
Priority date: 2021-07-23
Filing date: 2021-07-23
Publication date: 2021-10-22

Abstract

The disclosure provides an operation control method, an operation control device, a medium and electronic equipment of a reaction furnace. The operation control method of the reaction furnace comprises the following steps: collecting image information in the reaction furnace; determining temperature field information and combustion state information in the reaction furnace according to the image information; acquiring combustion condition information of the reaction furnace; and determining the operating parameters of the reaction furnace according to the temperature field information, the combustion state information and the combustion condition information. Through the technical scheme provided by the embodiment of the disclosure, the operation reliability of the reaction furnace is improved, the working efficiency of the reaction furnace is also improved, the energy efficiency utilization rate of the reaction furnace is further improved, and the energy consumption cost is reduced.

Description

Operation control method and device for reaction furnace, medium and electronic equipment

Technical Field

The present disclosure relates to the field of image processing technologies, and in particular, to an operation control method for a reaction furnace, an operation control device for a reaction furnace, a computer-readable storage medium, and an electronic apparatus.

Background

At present, an Automatic Combustion Control (ACC) system introduced from abroad is used to automatically Control the garbage incinerator, an operator sets parameters such as garbage heat value, target steam quantity and garbage specific gravity in the ACC system, and the garbage incinerator is automatically controlled through calculation results of process formulas of each Control loop of the ACC system. The core concept of the ACC technology is process calculation, for example, temperature information is calculated by using a formula.

However, in the related art, the working efficiency of the garbage incinerator adopting the ACC system is low due to the limitation that the ACC system excessively depends on process calculation.

It is to be noted that the information disclosed in the above background art is only for enhancement of understanding of the background of the present disclosure, and thus may include information that does not constitute prior art known to those of ordinary skill in the art.

Disclosure of Invention

An object of the present disclosure is to provide an operation control method of a reaction furnace, an operation control apparatus of a reaction furnace, a medium, and an electronic device for overcoming, at least to some extent, the problem of low operating efficiency of a reaction furnace due to the limitations and disadvantages of the related art.

According to an aspect of the embodiments of the present disclosure, there is provided an operation control method of a reaction furnace, including: collecting image information in the reaction furnace; determining temperature field information and combustion state information in the reaction furnace according to the image information; acquiring combustion condition information of the reaction furnace; and determining the operating parameters of the reaction furnace according to the temperature field information, the combustion state information and the combustion condition information.

In an exemplary embodiment of the present disclosure, the operation control method of the above reaction furnace further includes: determining a temperature field information sample, a combustion state information sample and a combustion condition information sample for training a neural network model; determining a running sample of the reaction furnace; and taking the temperature field information sample, the combustion state information sample and the combustion condition information sample as input samples of the neural network model, taking the operation sample as an output sample of the neural network model, and training the neural network model.

In an exemplary embodiment of the present disclosure, the combustion condition information samples include temperature samples and first air supply samples, the operation samples include first operation samples, the temperature field information samples, the combustion state information samples, and the combustion condition information samples are used as input samples of the neural network model, the operation samples are used as output samples of the neural network model, and training the neural network model includes: determining a first sample according to the temperature field information sample, the combustion state information sample temperature sample and the first air supply sample; and taking the first sample as an input sample of the neural network model, and taking the first running sample as an output sample of the neural network model to train the neural network model.

In an exemplary embodiment of the present disclosure, the first run sample includes at least one of a primary fan frequency sample, a primary air inlet valve sample, a primary air pre-heater opening degree sample, a primary air pre-heater bypass sample, a drying grate primary air valve sample, a combustion grate one-section primary air valve sample, a combustion grate two-section primary air valve sample, a combustion grate three-section primary air valve sample, a combustion grate one-section primary air valve sample, and a combustion grate two-section primary air valve sample.

In an exemplary embodiment of the present disclosure, the combustion condition information samples include a second air supply sample, the operation samples include a second operation sample, the temperature field information sample, the combustion state information sample, and the combustion condition information sample are used as input samples of the neural network model, the operation samples are used as output samples of the neural network model, and training the neural network model further includes: determining a second sample according to the temperature field information sample, the combustion state information sample and the second air supply sample; and taking the second sample as an input sample of the neural network model, and taking the second running sample as an output sample of the neural network model to train the neural network model.

In an exemplary embodiment of the present disclosure, the second operation sample includes at least one of a overfire air frequency sample, an overfire air inlet valve sample, an overfire air pre-heater opening degree sample, and an overfire air pre-heater bypass sample.

In an exemplary embodiment of the present disclosure, the combustion condition information samples include material bed thickness samples, the operation samples include third operation samples, the temperature field information samples, the combustion state information samples, and the combustion condition information samples are used as input samples of the neural network model, the operation samples are used as output samples of the neural network model, and training the neural network model further includes: determining a third sample according to the temperature field information sample, the combustion state information sample and the material layer thickness sample; and taking the third sample as an input sample of the neural network model, and taking the third running sample as an output sample of the neural network model, and training the neural network model.

In an exemplary embodiment of the present disclosure, the third run sample comprises a left pusher proportional valve sample and/or a right pusher proportional valve sample.

In an exemplary embodiment of the present disclosure, the combustion condition information samples include a bed thickness sample and a combustion product sample, the operation samples include a fourth operation sample, the temperature field information sample, the combustion state information sample and the combustion condition information sample are used as input samples of the neural network model, the operation samples are used as output samples of the neural network model, and training the neural network model further includes: determining a fourth sample according to the temperature field information sample, the combustion state information sample, the material layer thickness sample and the combustion product sample; and taking the fourth sample as an input sample of the neural network model, and taking the fourth running sample as an output sample of the neural network model, and training the neural network model.

In an exemplary embodiment of the present disclosure, the fourth run sample includes at least one of a left drying grate motion period sample, a right drying grate motion period sample, a left combustion grate motion period sample, a right combustion grate motion period sample, a left burn-out grate motion period sample, and a right burn-out grate motion period sample.

In an exemplary embodiment of the present disclosure, the operation control method of the reaction furnace according to any one of the above, further includes: respectively sending general execution parameters in the operation parameters to a left side actuator and a right side actuator of the reaction furnace; wherein, the general execution parameter comprises at least one of pushing material parameter, drying parameter, burning parameter and burnout parameter.

In an exemplary embodiment of the present disclosure, the operation control method of the reaction furnace according to any one of the above, further includes: determining a working condition parameter range capable of adjusting the reaction furnace according to the process conditions of the reaction furnace; judging whether a test sample of the reaction furnace meets a working condition parameter range; if the test sample is judged not to meet the working condition parameter range, determining that the reaction furnace is not tested by adopting the test sample; and if the test sample is judged to meet the working condition parameter range, determining to test the reaction furnace by adopting the test sample.

According to another aspect of the embodiments of the present disclosure, there is provided an operation control device of a reaction furnace, including: the acquisition module is used for acquiring image information in the reaction furnace; the first determining module is used for determining temperature field information and combustion state information in the reaction furnace according to the image information; the acquisition module is used for acquiring combustion condition information of the reaction furnace; and the second determining module is used for determining the operating parameters of the reaction furnace according to the temperature field information, the combustion state information and the combustion condition information.

According to another aspect of the present disclosure, there is provided a computer-readable storage medium having stored thereon a program which, when executed by a processor, implements the operation control method of the reaction furnace as in any one of the above.

According to another aspect of the present disclosure, there is provided an electronic device including: a processor; and a memory for storing executable instructions for the processor; wherein the processor is configured to execute the operation control method of the reaction furnace as any one of the above via execution of the executable instructions.

According to the technical scheme of the embodiment of the disclosure, the image information in the reaction furnace is collected and analyzed to determine the temperature field information and the combustion state information in the reaction furnace, and the operation parameters of the reaction furnace are determined according to the temperature field information, the combustion state information and the combustion condition information, so that the operation reliability of the reaction furnace is improved, the working efficiency of the reaction furnace is also improved, the energy efficiency utilization rate of the reaction furnace is further improved, and the energy consumption cost is reduced.

Furthermore, model training is carried out on the operation parameter sample according to the historical temperature field information, the combustion state information and the historical combustion working condition information of the reaction furnace, the current temperature field information, the current combustion state information and the current combustion working condition information of the reaction furnace are input into the trained neural network model, the output result of the neural network model is used as the operation parameter of the reaction furnace to control each actuator of the reaction furnace, and the control accuracy and the control reliability of the reaction furnace are improved.

According to the technical scheme of the embodiment of the invention, a large amount of working condition data of waste incineration is learned through an AI (Artificial Intelligence) technology, a big data technology, a deep learning technology and an Artificial Intelligence technology, a core control algorithm library of the reaction furnace is formed, the combustion state in the reaction furnace is rapidly judged, intelligently analyzed and a control strategy is automatically adjusted, unmanned operation of incineration control is realized, stable operation of the reaction furnace is ensured, and the aims of energy conservation and efficiency improvement are realized.

It is to be understood that both the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the disclosure.

Drawings

The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the present disclosure and together with the description, serve to explain the principles of the disclosure. It is to be understood that the drawings in the following description are merely exemplary of the disclosure, and that other drawings may be derived from those drawings by one of ordinary skill in the art without the exercise of inventive faculty.

Fig. 1 illustrates a flowchart of an operation control method of a reaction furnace in an exemplary embodiment of the present disclosure;

FIG. 2 is a flowchart illustrating an operation control method of another reaction furnace in an exemplary embodiment of the present disclosure;

FIG. 3 is a flowchart illustrating an operation control method of another reaction furnace in an exemplary embodiment of the present disclosure;

FIG. 4 is a flowchart illustrating an operation control method of another reaction furnace in an exemplary embodiment of the present disclosure;

FIG. 5 is a flowchart illustrating an operation control method of another reaction furnace in an exemplary embodiment of the present disclosure;

FIG. 6 is a flowchart illustrating an operation control method of another reaction furnace in an exemplary embodiment of the present disclosure;

FIG. 7 is a flowchart illustrating an operation control method of another reaction furnace in an exemplary embodiment of the present disclosure;

FIG. 8 is a flowchart illustrating an operation control method of another reaction furnace in an exemplary embodiment of the present disclosure;

FIG. 9 shows a schematic diagram of the control principle of a reaction furnace in an exemplary embodiment of the present disclosure;

FIG. 10 shows a schematic diagram of a control system of a reaction furnace in an exemplary embodiment of the present disclosure;

FIG. 11 is a block diagram illustrating an operation control apparatus of a reaction furnace in an exemplary embodiment of the present disclosure;

FIG. 12 shows a block diagram of an electronic device in an exemplary embodiment of the disclosure.

Detailed Description

Example embodiments will now be described more fully with reference to the accompanying drawings. Example embodiments may, however, be embodied in many different forms and should not be construed as limited to the examples set forth herein; rather, these embodiments are provided so that this disclosure will be thorough and complete, and will fully convey the concept of example embodiments to those skilled in the art. The described features, structures, or characteristics may be combined in any suitable manner in one or more embodiments. In the following description, numerous specific details are provided to give a thorough understanding of embodiments of the disclosure. One skilled in the relevant art will recognize, however, that the subject matter of the present disclosure can be practiced without one or more of the specific details, or with other methods, components, devices, steps, and the like. In other instances, well-known technical solutions have not been shown or described in detail to avoid obscuring aspects of the present disclosure.

Furthermore, the terms "first", "second", etc. are used for descriptive purposes only and are not to be construed as indicating or implying relative importance or implicitly indicating the number of technical features indicated. Thus, a feature defined as "first" or "second" may explicitly or implicitly include one or more of that feature. In the description of the present disclosure, "a plurality" means at least two, e.g., two, three, etc., unless explicitly specifically limited otherwise. The symbol "/" generally indicates that the former and latter associated objects are in an "or" relationship.

In the present disclosure, unless otherwise expressly specified or limited, the terms "connected" and the like are to be construed broadly, e.g., as meaning electrically connected or in communication with each other; may be directly connected or indirectly connected through an intermediate. The specific meaning of the above terms in the present disclosure can be understood by those of ordinary skill in the art as appropriate.

Further, the drawings are merely schematic illustrations of the present disclosure, in which the same reference numerals denote the same or similar parts, and thus, a repetitive description thereof will be omitted. Some of the block diagrams shown in the figures are functional entities and do not necessarily correspond to physically or logically separate entities. These functional entities may be implemented in the form of software, or in one or more hardware modules or integrated circuits, or in different networks and/or processor devices and/or microcontroller devices.

Currently, the limitations of ACC systems are as follows:

(1) the ACC system has poor control effect on the incineration process of garbage with high moisture content and large component fluctuation.

(2) The ACC system relies on formulas for real-time calculation, and the operating experience of an operator cannot be combined in the ACC system.

(3) The ACC system has too high dependence on the precision of instruments and meters, and if the instruments and meters are damaged or the precision is insufficient, the ACC system is difficult to accurately operate.

(4) The ACC system depends on the data of the garbage heat value database, and if the data of the garbage heat value database is not stored, the data loss or data failure occurs, so that the operation accuracy of the ACC system is reduced.

(5) The thermocouple in the ACC system is single-point temperature measurement, the information of a temperature field in the reaction furnace cannot be accurately fed back, and the intuitive identification and judgment of combustion condition information, such as flame deflection, garbage thickness, smoke state and the like, are lacked.

The above limitation reduces the automation degree and the working efficiency of the ACC system applied to the waste incineration plant, and limits the popularization and application range of the waste incineration plant.

In order to overcome the limitations, the present disclosure develops a core Control algorithm based on a process principle of a reactor, Combustion condition information, Control instruction data, and identification information of a flame Combustion state, and develops an ICC (Intelligent Combustion Control) system by using a neural network model of a process calculation technology, an image processing technology, and an artificial intelligence technology, and by matching an automatic Control principle with an industrial data transmission technology.

The key technology included in the ICC system is as follows:

(1) and measuring the temperature of the reaction furnace by adopting an image processing technology and outputting temperature field information and combustion state information.

(2) And identifying the image acquired by adopting an image processing technology to obtain the combustion condition information in the furnace.

(3) The identified temperature field information, Combustion state information, and Combustion condition information are input to an ICC (Intelligent Combustion Control) system as input variables.

(4) And processing the field operation data by adopting a big data analysis method.

(5) And performing model training on the processed field operation data by adopting a machine learning method to obtain a high-precision regulation and control model.

(6) The model is trained by changing the combination form among the input variables, so that the model learns the change trend of the input variables of the system along with time, and the dependence on the high precision of a single-point single instrument is eliminated.

(7) The system has high robustness, and if a single instrument or an actuator is damaged, the stable operation of other parts of the system is not influenced.

(8) The control idea completely different from that of the existing automatic garbage incineration control system is adopted, dependence on a garbage heat value database is eliminated, and the automatic garbage incineration control system can adapt to the characteristics of high garbage heat value and high organic matter content.

(9) Has high universality and is suitable for various reaction furnaces, including but not limited to mechanical grate reaction furnaces, fluidized bed incinerators and rotary incinerators.

The steps of the operation control method of the reactor according to the exemplary embodiment will be described in more detail with reference to the drawings and examples.

Fig. 1 is a flowchart of an operation control method of a reaction furnace in an exemplary embodiment of the present disclosure.

Referring to fig. 1, the operation control method of the reaction furnace includes:

and step S102, acquiring image information in the reaction furnace.

In an exemplary embodiment of the present disclosure, the reaction furnace includes a reaction furnace for waste incineration and a kiln apparatus for industrial reaction, but is not limited thereto.

In an exemplary embodiment of the present disclosure, the reaction furnaces include, but are not limited to, a solid waste reaction furnace, a gaseous waste reaction furnace, and a liquid waste reaction furnace.

And step S104, determining temperature field information and combustion state information in the reaction furnace according to the image information.

In an exemplary embodiment of the present disclosure, the image information in the reaction furnace reflects the flame temperature in the reaction furnace, and the temperature field information of the flames in the reaction furnace at different times is determined according to the distribution rule of the flame temperature at different times, so that the control accuracy of the reaction furnace is improved.

In an exemplary embodiment of the present disclosure, the image information in the reaction furnace reflects the combustion state information of the flame in the reaction furnace, and the different combustion state information also reflects different stages in the flame combustion process, and the flame state in the reaction furnace is determined according to the combustion state information and the temperature field information, so that the control accuracy of the reaction furnace is improved.

In an exemplary embodiment of the present disclosure, thermometry techniques are used to determine temperature field information within a reactor. The temperature measurement technology detects the temperature field distribution in the reaction furnace in real time by using a plurality of thermocouples on the furnace wall and an infrared thermal imager on the furnace top, or collects flame images by using a single CCD (Charge Coupled Device) camera, realizes the non-contact temperature measurement of the reaction furnace by using a bicolor thermal radiation method, and determines the temperature field distribution in the reaction furnace.

In an exemplary embodiment of the present disclosure, the thermometry techniques include infrared thermometry techniques, thermocouple thermometry techniques, and image thermometry techniques. The infrared temperature measurement technology is that an infrared sensor is used for detecting the radiation intensity of an infrared band emitted by the surface of a measured object, and temperature measurement is carried out according to the relation between the radiation intensity and the temperature. The thermocouple temperature measuring technology is that thermocouples are arranged around the wall of the reaction furnace in a mode of punching holes on the wall of the reaction furnace, and the temperature of a hearth in the reaction furnace is measured through the thermocouples. The image temperature measuring technology is to analyze the collected flame image by a two-color thermal radiation method and determine the temperature in the reaction furnace according to the analysis result.

And S106, acquiring combustion condition information of the reaction furnace.

In an exemplary embodiment of the present disclosure, the combustion condition information of the reaction furnace includes a temperature parameter, a pressure parameter, a load parameter, and a pollutant parameter within the reaction furnace, but is not limited thereto.

In an exemplary embodiment of the present disclosure, the reaction progress of the reaction furnace is controlled by adjusting a temperature parameter, a pressure parameter, a load parameter, and a pollutant parameter within the reaction furnace.

And S108, determining the operation parameters of the reaction furnace according to the temperature field information, the combustion state information and the combustion condition information.

In the above embodiment, the image information in the reaction furnace is collected, the temperature field information and the combustion state information in the reaction furnace are determined according to the image information, the combustion condition information of the reaction furnace is obtained, and the operation parameters of the reaction furnace are determined according to the temperature field information, the combustion state information and the combustion condition information, so that the operation reliability of the reaction furnace is improved, the working efficiency of the reaction furnace is also improved, the energy efficiency utilization rate of the reaction furnace is further improved, and the energy consumption cost is reduced.

As shown in fig. 2, the operation control method of the reaction furnace further includes:

and step S202, determining a temperature field information sample, a combustion state information sample and a combustion condition information sample for training a neural network model.

And step S204, determining an operation sample of the reaction furnace.

And step S206, taking the temperature field information sample, the combustion state information sample and the combustion condition information sample as input samples of the neural network model, taking the operation sample as an output sample of the neural network model, and training the neural network model.

In the above embodiment, the temperature field information sample, the combustion state information sample and the combustion condition information sample used for training the neural network model are determined, the operation sample of the reaction furnace is determined, the temperature field information sample, the combustion state information sample and the combustion condition information sample are used as input samples of the neural network model, and the operation sample is used as an output sample of the neural network model, so that the neural network model is trained, the accuracy of the output sample of the neural network model is improved, the operation reliability of the reaction furnace is improved, and the working efficiency of the reaction furnace is also improved.

As shown in fig. 3, the combustion condition information samples include temperature samples and first air supply samples, the operation samples include first operation samples, the temperature field information samples, the combustion state information samples and the combustion condition information samples are used as input samples of the neural network model, the operation samples are used as output samples of the neural network model, and the training of the neural network model includes:

step S302, a first sample is determined according to the temperature field information sample, the combustion state information sample, the temperature sample and the first air supply sample.

And step S304, taking the first sample as an input sample of the neural network model, taking the first running sample as an output sample of the neural network model, and training the neural network model.

In the embodiment, the first sample is determined according to the temperature field information sample, the combustion state information sample, the temperature sample and the first air supply sample, the first sample is used as an input sample of the neural network model, the first running sample is used as an output sample of the neural network model, the neural network model is trained, the richness of the input sample is improved, and the accuracy of the neural network model is improved.

In an exemplary embodiment of the present disclosure, the reaction furnace includes a primary air control system that provides primary air for a combustion process within the reaction furnace, the primary air entering the furnace from a lower portion of the grate for igniting the reactants and providing the reactants with an amount of air required for combustion thereof.

In an exemplary embodiment of the present disclosure, an air inlet of the primary air control system is controlled to be opened according to the primary air inlet valve sample to input primary air into the reaction furnace, and the rotation frequency of a fan of the primary air control system is controlled according to the primary fan frequency sample to provide primary air with different air quantities.

Wherein the primary air comprises cold primary air, and the cold primary air is input into the reaction furnace to adjust the reaction temperature in the reaction furnace.

In addition, the primary air also comprises hot primary air, the primary air preheater is controlled according to the primary air preheater opening degree sample to preheat the primary air so as to provide preheated main air intake, the primary air is controlled by the primary air preheater branch circuit to preheat the primary air based on the main air intake and the primary air preheater branch circuit sample so as to provide preheated branch circuit air intake, and the sum of the main air intake and the branch circuit air intake is used as hot primary air to be input into the reaction furnace so as to provide air quantity required by combustion of the hot primary air.

In an exemplary embodiment of the present disclosure, the moisture content of the reactant on the drying grate is reduced by controlling the amount of drying air entering the drying grate of the reactor based on the drying grate primary air valve sample.

In an exemplary embodiment of the present disclosure, the amount of air entering the combustion grate of the reaction furnace is controlled based on at least one of the combustion grate first stage primary air valve sample, the combustion grate second stage primary air valve sample, and the combustion grate third stage primary air valve sample to provide air needed for the reactants to burn.

In an exemplary embodiment of the present disclosure, the amount of air entering the ember grate of the reaction furnace is controlled according to the ember grate one-section primary air valve sample and/or the ember grate two-section primary air valve sample, so as to provide air required for ember burning.

As shown in fig. 4, the combustion condition information samples include a second air supply sample, the operation samples include a second operation sample, the temperature field information sample, the combustion state information sample, and the combustion condition information sample are used as input samples of the neural network model, the operation samples are used as output samples of the neural network model, and the training of the neural network model further includes:

and step S402, determining a second sample according to the temperature field information sample, the combustion state information sample and the second air supply sample.

And S404, taking the second sample as an input sample of the neural network model, taking the second running sample as an output sample of the neural network model, and training the neural network model.

In the embodiment, the second sample is determined according to the temperature field information sample, the combustion state information sample and the second air supply sample, the second sample is used as the input sample of the neural network model, the second running sample is used as the output sample of the neural network model, the neural network model is trained, the diversity of the input sample is improved, and the accuracy of the neural network model is improved.

In an exemplary embodiment of the present disclosure, the reaction furnace includes a secondary air control system that supplements the combustion process in the reaction furnace with the secondary air required to be injected from the top of the grate to disrupt the flow of air to complete the combustion.

In an exemplary embodiment of the disclosure, an air inlet of the secondary air control system is controlled to be opened according to a secondary air inlet valve sample so as to input secondary air into the reaction furnace, and the rotating frequency of a fan of the secondary air control system is controlled according to a secondary fan frequency sample so as to provide secondary air with different air quantities.

In an exemplary embodiment of the present disclosure, in addition, the secondary air preheater is controlled according to the secondary air preheater opening degree sample to preheat the secondary air to provide a preheated main intake air amount, the secondary air preheater branch is controlled to preheat another part of the secondary air based on the main intake air amount and the secondary air preheater branch sample to provide a preheated branch intake air amount, and the sum of the main intake air amount and the branch intake air amount is inputted into the reactor as the secondary air.

As shown in fig. 5, the combustion condition information samples include material bed thickness samples, the operation samples include third operation samples, the temperature field information samples, the combustion state information samples, and the combustion condition information samples are used as input samples of the neural network model, the operation samples are used as output samples of the neural network model, and the training of the neural network model further includes:

and step S502, determining a third sample according to the temperature field information sample, the combustion state information sample and the material layer thickness sample.

And step S504, taking the third sample as an input sample of the neural network model, taking the third running sample as an output sample of the neural network model, and training the neural network model.

In the embodiment, the third sample is determined according to the temperature field information sample, the combustion state information sample and the material layer thickness sample, the third sample is used as the input sample of the neural network model, the third running sample is used as the output sample of the neural network model, the neural network model is trained, the sample types of the input sample are enriched, and the reliability of the neural network model is improved.

In an exemplary embodiment of the present disclosure, the left pusher and/or the right pusher of the feeding system are controlled based on the left pusher proportional valve sample and/or the right pusher proportional valve sample to control the reaction amount of the reactant within the reaction furnace.

As shown in fig. 6, the combustion condition information samples include a bed thickness sample and a combustion product sample, the operation samples include a fourth operation sample, the temperature field information sample, the combustion state information sample and the combustion condition information sample are used as input samples of the neural network model, the operation samples are used as output samples of the neural network model, and the training of the neural network model further includes:

step S602, determining a fourth sample according to the temperature field information sample, the combustion state information sample, the material layer thickness sample and the combustion product sample.

And step S604, taking the fourth sample as an input sample of the neural network model, taking the fourth running sample as an output sample of the neural network model, and training the neural network model.

In the embodiment, the fourth sample is determined according to the temperature field information sample, the combustion state information sample, the material layer thickness sample and the combustion product sample, the fourth sample is used as an input sample of the neural network model, the fourth running sample is used as an output sample of the neural network model, the neural network model is trained, the sample type of the input sample is improved, and the accuracy of the neural network model is improved.

In an exemplary embodiment of the present disclosure, the material layer thickness samples and the combustion product samples affect the grate movement speed of the reaction furnace, and different grate movement speeds have different grate movement cycle samples, so the material layer thickness samples and the combustion product samples affect the grate movement cycle samples differently. In addition, the temperature field information sample also indirectly reflects the grate motion period sample, namely the grate motion period sample of the reaction furnace is more reliably trained by integrating the temperature field information sample, the combustion state information sample, the material layer thickness sample and the combustion product sample.

As shown in fig. 7, the operation control method of the reaction furnace further includes:

and step S702, respectively sending the general execution parameters in the operation parameters to a left side actuator and a right side actuator of the reaction furnace.

Wherein, the general execution parameter comprises at least one of pushing material parameter, drying parameter, burning parameter and burnout parameter.

In the embodiment, the general execution parameters in the operation parameters are respectively sent to the left side actuator and the right side actuator of the reaction furnace, so that the working efficiency of the reaction furnace is improved.

In an exemplary embodiment of the present disclosure, the general execution parameters are sent to the left and right actuators, respectively, to control the left and right actuators within the reactor simultaneously.

In an exemplary embodiment of the present disclosure, the left side actuator includes, but is not limited to, a left pusher proportional valve, a left drying grate, a left combustion grate, and a left burn-out grate.

In an exemplary embodiment of the present disclosure, the right side actuator includes, but is not limited to, a right side pusher proportioning valve, a right side drying grate, a right side combustion grate, and a right side ember grate.

As shown in fig. 8, the operation control method of the reaction furnace according to any one of the above aspects, further includes:

step S802, determining the working condition parameter range capable of adjusting the reaction furnace according to the process conditions of the reaction furnace.

And step S804, judging whether the test sample of the reaction furnace meets the working condition parameter range. If so, the process proceeds to step S808. If not, the process proceeds to step S806.

And step S806, if the test sample is judged not to meet the working condition parameter range, determining that the reaction furnace is not tested by adopting the test sample.

And step S808, if the test sample is judged to meet the working condition parameter range, determining to adopt the test sample to test the reaction furnace.

In the above embodiment, the working condition parameter range which can be adjusted for the reaction furnace is determined according to the process conditions of the reaction furnace, whether the test sample of the reaction furnace meets the working condition parameter range is judged, if the test sample is judged not to meet the working condition parameter range, the reaction furnace is determined not to be tested by adopting the test sample, and if the test sample is judged to meet the working condition parameter range, the reaction furnace is determined to be tested by adopting the test sample, so that the operation reliability of the reaction furnace is improved, and the working efficiency of the reaction furnace is also improved.

In an exemplary embodiment of the present disclosure, the adjustable reaction temperature range is set according to a reaction temperature required for a reactant reaction when the reaction furnace is operated, and the reaction temperature range may be set to [850 ℃, 1000 ℃), for example, in order to provide a reaction temperature for sufficient combustion of garbage. At this time, if it is determined that the reaction temperature in the test sample is 0 ℃, the reaction furnace is not tested using the test sample. And if the reaction temperature in the test sample is determined to be 900 ℃, determining to test the reaction furnace by using the test sample.

As shown in fig. 9, the control principle of the reaction furnace includes: the process control system collects reactor operating condition data 902 and calculates the operating condition data 902 using a process calculation formula 904 to obtain an air flow control value 906 and a velocity value 908. The operating condition data 902 includes a garbage Heat Value LHV (Low Heat Value), a main steam flow, a main steam pressure, a main steam temperature, a leachate injection flow, and a urea water injection flow. The speed value 908 is adjusted to adjust the movement cycle of the actuator of the reactor.

The air flow control value 906 comprises a drying grate standard air flow, a combustion grate standard air flow and an after-fire grate standard air flow, and the air flow control value 906 is used for controlling the air flows entering the drying grate, the combustion grate and the after-fire grate. And calculating the working condition data 902 and the excess air parameter (the set value is 1.3) according to a process calculation formula 904 to obtain standard air flow, and simultaneously obtaining the standard air flow of the drying grate, the standard air flow of the combustion grate and the standard air flow of the burning grate according to the standard air flow. Wherein the standard air flow rate is m³N/h。

In addition, the speed values 908 include a pusher speed, a drying grate speed, a combustion grate speed and an after-fire grate speed, and the working condition data 902 is calculated according to a process calculation formula 904 to obtain the weight of the garbage, on one hand, the thickness control value of the garbage layer in the reaction furnace is determined according to the weight of the garbage. On the other hand, the required garbage volume is calculated according to the garbage weight and the garbage appearance specific gravity, a standard speed value is determined based on the required garbage volume, the pusher speed and the drying grate speed are calculated according to the garbage layer thickness control value and the standard speed value, and the burning grate speed are determined according to the standard speed.

The calculation formula for calculating the volume Vr of the required garbage thrown into the reaction furnace according to the weight Wr and the appearance specific gravity Sg of the garbage is as follows:

Vr＝Wr/Sg (1)

wherein the unit of the volume Vr of the required garbage is m³The unit of the weight Wr of the garbage is t/h, and the unit of the appearance specific gravity Sg of the garbage is t/m³。

In an exemplary embodiment of the disclosure, image information is analyzed by reading current combustion condition information and combining an image temperature measurement technology and a flame combustion state diagnostic device to obtain temperature field information and combustion state information of flame, a plurality of data measuring points containing the data are transmitted to a third-party database for storage through an OPC (Object Linking and Embedding for process Control) communication protocol, variable information of each model is read based on a Control algorithm and model calculation is performed, after the model calculation is completed, a calculation result of the model is output as an operation parameter, the operation parameter is transmitted to the third-party database for storage, and the operation parameter is transmitted to a DCS (Distributed Control System) System Control actuator. Based on the learning of historical working condition data, a control algorithm library of the reaction furnace is formed, the judgment speed of combustion working condition information is increased, the information processing efficiency of the reaction furnace is improved, the automation level of the reaction furnace is improved, the operation stability and safety of the reaction furnace are improved, and the energy efficiency utilization rate is improved.

The combustion condition information includes, but is not limited to, a main steam flow, an outlet oxygen amount, a garbage material layer thickness, a drying grate temperature, a combustion grate upper portion temperature, a furnace mean temperature, and a high-temperature superheater temperature.

Next, the operation control method of the reaction furnace will be explained with reference to the following examples.

The first embodiment is as follows:

the embodiment of the disclosure provides an ICC system of a reaction furnace combined with image processing, and the ICC system comprises image temperature measurement and diagnosis equipment, an ICC system data acquisition module and an ICC system control logic output module. The input reference quantity of the ICC system comprises all input data of the DCS, and flame temperature and combustion condition information of the reaction furnace, which are obtained by analyzing image temperature measuring and diagnosing equipment, and the output controlled quantity of the ICC system comprises feed system control parameters of the reaction furnace, movement period parameters of each section of fire grate, primary air control parameters of a combustion air system and secondary air control parameters of the combustion air system.

As shown in fig. 10, a control system of a reaction furnace includes: the device comprises a feed port 1002, a combustion section 1004, an ember section 1006, ash 1008, a flue gas pipe wall 1010, a PLC (programmable logic controller) control cabinet 1012, a PC (personal computer) end 1014, a cooling air input interface 1016, a CCD (charge coupled device) camera 1018, an automatic advancing and retreating protection device 1020, an observation port 1022, a cooling air output port 1024 and reactants 1026.

Reactants are fed into the reaction furnace through the feeding hole 1002, combustion products of the reactants after combustion in the combustion section 1004 move through a grate of a combustion grate of the combustion section 1004 and then enter the ember section 1006, and the reactants continue to combust on the ember section 1006 to generate ash 1008. In the combustion process, the generated high-temperature flue gas is discharged through a flue gas pipeline, and a thermocouple is arranged on the wall 1010 of the flue gas pipeline to measure the temperature of the flue gas. The CCD camera 1018 enters the observation port 1022 through the automatic forward and backward moving protection device 1020 to collect image information in the reaction furnace, the air cooling system arranged on the automatic forward and backward moving protection device 1020 comprises a cooling air input interface 1016 and a cooling air output port 1024, and the air cooling system provides cooling air for the CCD camera 1018 working at high temperature to ensure the normal work of the CCD camera 1018. When the PLC control cabinet monitors that the working temperature of the CCD camera 1018 is too high, the PLC control cabinet controls the automatic forward and backward movement protection device 1020 to leave the observation port 1022.

The CCD camera 1018 has an interface for transmitting image data, a power supply is connected to the CCD camera 1018 through a camera power switch, the CCD camera 1018 is connected to an industrial personal computer 1014 through a gigabit ethernet line, the CCD camera 1018 also transmits instruction parameters and data to the industrial personal computer 1014 through the gigabit ethernet line, the industrial personal computer 1014 processes the received data through an image software algorithm, and inputs the processed result into the ICC control system.

The working process of the ICC system is specifically analyzed by combining the following steps:

the method comprises the following steps: image information is acquired using image thermometry and diagnostic equipment.

(1) Hardware design of imaging system: the system comprises a matched image sensor, an automatic driving and reversing device, an air cooling system, a PLC (Programmable Logic Controller) control cabinet and an industrial personal computer.

Wherein, supporting image sensor includes CCD camera and mirror pole, uses the mirror pole to provide the fixed point for the CCD camera, is connected so that send the image that the CCD camera was gathered for the industrial computer with the CCD camera through the giga net twine with the industrial computer with the CCD camera, and supporting image sensor's image coverage area includes burning section and burnout section.

The automatic driving and reversing device comprises an air cooling system and is used for ensuring that the CCD camera works within a normal temperature range. The air cooling system comprises a cooling air input interface, and a sensor used for monitoring the air pressure of cooling air is arranged on the cooling air input interface. The automatic advancing and retreating device is also provided with a temperature sensor for monitoring temperature information. The automatic advancing and retreating device is electrically connected with the PLC control cabinet through a connecting wire and is used for sending the temperature information of the monitored air pressure information of the cooling air to the PLC control cabinet. The automatic advancing and retreating device enters the observation port during working, and if the temperature monitored by the PLC control cabinet is higher than 75 ℃ or the air pressure of cooling air is lower than 0.4Mpa, the PLC control cabinet controls the automatic advancing and retreating device to exit the observation port, so that the safety of hardware equipment of the imaging system under abnormal conditions is guaranteed.

(2) The flame images in the reaction furnace are collected in real time through an imaging system, and the flame images are sequentially transmitted into an image processing system.

(3) In an image processing system, the collected flame images are subjected to noise reduction, filtering, normalization, gray value conversion and the like in sequence.

(4) The imaging system is calibrated through the black body furnace, based on a calibration database and a two-color temperature measurement principle, a neural network is utilized to train, verify and test a sample, and finally a process algorithm suitable for calculating the flame temperature of the waste incineration and diagnosing the combustion state is established.

(5) The influence of smoke dust in the reaction furnace is automatically removed in the process algorithm.

(6) The method comprises the steps of converting a flame image into temperature field information in real time through a process algorithm of an image processing system, and meanwhile, rapidly diagnosing whether the garbage incineration flame is in working conditions of normal combustion, partial combustion, too thick garbage layer, abnormal smoke, too small flame area and the like to obtain corresponding combustion state information.

(7) And inputting a result obtained by image processing into a DCS data acquisition module.

Step two: and training the neural network model.

(1) Selecting input variables of the model: the variables input into the model include temperature parameters, pressure parameters, load parameters, pollutant parameters, operating condition state parameters and flame combustion information of the reactor.

Wherein the temperature parameters comprise furnace temperature, grate temperature, furnace average temperature, high-temperature superheater temperature, main steam temperature, ash temperature and the like. The pressure parameters comprise primary air pressure, secondary air pressure, steam drum pressure, main steam pressure, hearth pressure and the like. The load parameters comprise main steam flow, combustion chamber heat load, grate mechanical load and the like. Contaminant parameters include hydrogen chloride, carbon dioxide, nitrogen oxides, particulates, carbon monoxide, and the like. The working condition state parameters comprise the oxygen content of outlet gas, the thickness of a garbage material layer, the liquid level of a steam drum and the like. The flame combustion information comprises in-furnace flame temperature field information and combustion state information output by the image processing module.

The model related in the embodiment of the disclosure is more than one, so that a data set after the same set of data processing method is not adopted for models of different control loops, but models are respectively established for the models of each control loop, and the process of establishing the models in the embodiment of the disclosure is different from the existing method, the existing method comprises the steps of firstly performing sample processing, data analysis and the like, and then establishing the models, and the embodiment of the disclosure performs the variable selection process of each control loop and the model establishment process of each control loop while performing the data processing process.

(2) Processing input data: the parent set of data is processed first and then the subset of data is selected. The data set of the raw data after rough processing is called a mother set, and the data set corresponding to the variable related to each control loop is selected as a subset.

When the data of the mother set is processed, the working condition data of an unstable state and an abnormal state are removed by taking the whole working condition as a guide, and all variables at certain time points are deleted due to the extensive processing mode. In processing the subset data, the selection process of the subset variables is performed by interleaving. The subset variables are selected with the aid of the results of the historical data analysis, guided by the correlation in the process logic.

(3) Building a neural network model: each selected subset is divided into a test set and a training set, and a neural network model is trained using the training set, the neural network model including, but not limited to, a neural network model that handles regression problems (i.e., outputs are continuous variables), such as a decision tree regression model, a support vector regression model, a BP (back propagation) neural network model, a long-term and short-term memory network model, and the like.

(4) Simplifying the neural network model: the total output of the complete system of the embodiment of the disclosure is 22, and the simplification processing can be properly carried out, for example, the operation parameters of the grate motion cycles on the left side and the right side are simplified into the operation parameters of the grate motion cycles, and 4 neural network models can be reduced. The embodiment of the disclosure carries out linkage processing on the operation parameters of the left and right side grate motion cycle classes, and only a neural network model of 18 operation parameters needs to be established.

In addition, except for the running parameters of the grate motion cycles on the left side and the right side, other running parameters can be properly linked according to the relation among the running parameters, and the running parameters of a single neural network model are linked with proper running parameters, so that the robustness of the system is guaranteed, the output result of the neural network model is simplified, the complexity of the neural network model is reduced, and the training speed of the neural network model is increased.

(5) Optimizing input variables and output operation parameters of the neural network model, wherein the number of the neural network models is large, the number of the parameters of each neural network model is large, the optimal parameter index of the neural network model is found by training the neural network models, and the historical working condition state and the current working condition state are mapped to the action of each actuator, so that the continuous stability of the working condition of the reaction furnace is achieved.

Step three: and outputting the operating parameters of the ICC system.

The operation parameters output by the neural network model comprise operation parameters for controlling a feeding system, operation parameters for controlling a grate movement period, operation parameters for controlling a primary air system of a combustion air system and operation parameters for controlling a secondary air system of the combustion air system.

(1) The operating parameters of the feeding system comprise the left-side pusher proportional valve parameters and the right-side pusher proportional valve parameters.

(2) The running parameters of the grate motion period comprise a left side drying grate motion period parameter, a right side drying grate motion period parameter, a left side combustion grate motion period parameter, a right side combustion grate motion period parameter, a left side burn-out grate motion period parameter and a right side burn-out grate motion period parameter.

(3) The operation parameters of the primary air system of the combustion air system comprise a primary fan frequency parameter, a primary air inlet valve parameter, a primary air pre-heater opening degree parameter, a primary air pre-heater branch parameter, a drying grate primary air valve parameter, a combustion grate first-section primary air valve parameter, a combustion grate second-section primary air valve parameter, a combustion grate third-section primary air valve parameter, a combustion grate first-section primary air valve parameter and a combustion grate second-section primary air valve parameter.

(4) The operation parameters of the secondary air system of the combustion air system comprise secondary fan frequency parameters, secondary air inlet valve parameters, secondary air pre-heater opening degree parameters and secondary air pre-heater branch parameters.

Step four: the ICC system was tested.

(1) And obtaining a required system output control model through an ICC system data acquisition and model training module.

(2) And packaging the neural network model, transmitting data between the control program and the DCS system, transmitting DCS real-time data to a core control algorithm, reading the real-time data into the trained neural network model by the core control algorithm, calculating, and transmitting a calculated control instruction back to the DCS system to command the action of each actuator in the incineration system.

(3) Before the system is put into use formally, the system needs to be tested off-line and on-line. The off-line test is to continuously input the previous working condition data to the core control algorithm, compare the difference between the manual operation value and the algorithm calculated value under the previous working condition, and test several groups of values, if the difference is in the acceptable range, the on-line test can be carried out.

(4) After the off-line test is completed, the system also needs to be tested on line. The on-line test needs to make objective evaluation for each function of the combustion control system, preset the function index of the on-line test effect, and evaluate the on-line test of the combustion control system according to the index, wherein the function index comprises load index main steam flow, temperature index furnace average temperature and index outlet oxygen quantity influencing pollutant emission.

(5) And during on-line test, adding process constraint conditions on process logic to ensure that the working condition can be quickly recovered to be normal from abnormity. In order to ensure that the system is tested on line by using the algorithm adjusting capability under the normal working condition, a proper amount of process constraint needs to be added aiming at the abnormal working condition which exceeds the algorithm adjusting capability.

The intelligent and efficient big data technology is fused, the control accuracy and the information processing efficiency of the system are improved through online learning of historical data, and the following control effects are achieved:

(1) the stability of the total flow of the steam of the boiler is improved.

(2) The control effect of the thickness of the garbage layer is improved.

(3) The controllability of the garbage burning position is improved.

(4) The loss degree of the hot scorch is reduced.

(5) The stability of the furnace temperature is improved.

(6) The environmental protection standard reaching rate, the safety and the stability of the operation indexes in the production requirement are improved.

(7) The adaptability to high water content and high organic matter content of garbage is improved.

(8) The service life of the equipment is prolonged, and the cost of the equipment is reduced.

(9) The energy saving and efficiency increasing of the waste incineration power plant are improved.

(10) The automatic intelligent control effect of the waste incineration is improved.

(11) The identification result of the flame temperature field by non-contact temperature measurement is improved.

(12) The judgment speed and the information processing efficiency of the flame combustion state are improved.

In addition, this disclosed reactor combustion control system combines image temperature measurement and diagnosis, machine vision technique, big data technique and artificial intelligence technique to and combine DCS system and ICC system, through supporting image temperature measurement and diagnosis equipment, discern and judge the temperature field of furnace and flame combustion state, thereby carry out real-time analysis to the flame image, include converting the flame image into real-time temperature information, and adopt artificial intelligence technique to carry out quick diagnosis to the combustion state of flame (including normal combustion state, partial combustion state, rubbish layer super-thick state, smog abnormal state, flame area undersize state etc.) simultaneously.

Furthermore, in the ICC system, the control principle, the big data technology and the artificial intelligence technology are used for analyzing historical data, analyzing and calculating data of the DCS and data of image temperature measurement and diagnosis, obtaining the optimal operation parameters of all controller variables in the waste incineration system, and then returning the optimal operation parameters to the DCS so as to control the ICC system. Under the even release thermal prerequisite of assurance rubbish, improved the burnout volume of flue gas and residue, reduced the formation volume of pollutant, improved refuse treatment's innoxious degree, improved refuse treatment's minimizing degree to refuse treatment's efficiency utilization ratio has been improved.

The neural network model is trained based on advanced process control methods such as fuzzy control and the like, statistical analysis, a machine learning technology, a deep learning technology and a machine vision AI technology, abundant operation experience of field operators is integrated into the model, and the model is high in precision and strong in applicability. The above technical solutions are only used for illustrating the present disclosure, and are not idle in the scope of the present disclosure, and modifications and variations of the present disclosure by other intelligent control methods, machine learning methods and deep learning methods also fall within the scope of the claims of the present disclosure and their equivalents.

Corresponding to the method embodiment, the present disclosure also provides an operation control device of a reaction furnace, which can be used for executing the method embodiment.

Fig. 11 is a block diagram of an operation control apparatus of a reaction furnace in an exemplary embodiment of the present disclosure.

Referring to fig. 11, the operation control apparatus 1100 of the reaction furnace includes:

the acquisition module 1102 is used for acquiring image information in the reaction furnace;

a first determining module 1104, configured to determine temperature field information and combustion state information in the reaction furnace according to the image information;

an obtaining module 1106, configured to obtain combustion condition information of the reactor;

and a second determining module 1108 for determining the operating parameters of the reaction furnace according to the temperature field information, the combustion state information and the combustion condition information.

Since the functions of the apparatus 1100 have been described in detail in the corresponding method embodiments, the disclosure is not repeated herein.

It should be noted that although in the above detailed description several modules or units of the device for action execution are mentioned, such a division is not mandatory. Indeed, the functionality and features of two or more of the modules or units described above may be embodied in one module or unit, in accordance with embodiments of the present disclosure. Conversely, the functions and functionalities of one module or unit described above may be further divided into embodiments by a plurality of modules or units.

In an exemplary embodiment of the present disclosure, an electronic device capable of implementing the above method is also provided.

As will be appreciated by one skilled in the art, aspects of the present disclosure may be embodied as a system, method or program product. Accordingly, various aspects of the present disclosure may be embodied in the form of: an entirely hardware embodiment, an entirely software embodiment (including firmware, microcode, etc.) or an embodiment combining hardware and software aspects that may all generally be referred to herein as a "circuit," module "or" system.

An electronic device 1200 according to this embodiment of the disclosure is described below with reference to fig. 12. The electronic device 1200 shown in fig. 12 is only an example and should not bring any limitation to the functions and the scope of use of the embodiments of the present disclosure.

As shown in fig. 12, the electronic device 1200 is embodied in the form of a general purpose computing device. The components of the electronic device 1200 may include, but are not limited to: the at least one processing unit 1210, the at least one memory unit 1220, and a bus 1230 connecting the various system components including the memory unit 1220 and the processing unit 1210.

Wherein, the storage unit stores program codes, and the program codes can be executed by the processing unit 1210, so that the processing unit 1210 executes the steps according to various exemplary embodiments of the disclosure described in the above "exemplary method" of the present specification. For example, the processing unit 1210 described above may perform a method as shown in the embodiments of the present disclosure.

The storage unit 1220 may include a readable medium in the form of a volatile memory unit, such as a random access memory unit (RAM)12201 and/or a cache memory unit 12202, and may further include a read only memory unit (ROM) 12203.

Storage unit 1220 may also include a program/utility 12204 having a set (at least one) of program modules 122011, such program modules 122011 including, but not limited to: an operating system, one or more application programs, other program modules, and program data, each of which, or some combination thereof, may comprise an implementation of a network environment.

Bus 1230 may be one or more of several types of bus structures, including a memory unit bus or memory unit controller, a peripheral bus, an accelerated graphics port, a processing unit, or a local bus using any of a variety of bus architectures.

The electronic device 1200 may also communicate with one or more external devices 1300 (e.g., keyboard, pointing device, bluetooth device, etc.), with one or more devices that enable a user to interact with the electronic device 1200, and/or with any devices (e.g., router, modem, etc.) that enable the electronic device 1200 to communicate with one or more other computing devices. Such communication can occur via input/output (I/O) interfaces 12110. Also, the electronic device 1200 may communicate with one or more networks (e.g., a Local Area Network (LAN), a Wide Area Network (WAN), and/or a public network, such as an internet) via the network adapter 12120. As shown, the network adapter 12120 communicates with the other modules of the electronic device 1200 via the bus 1230. It should be appreciated that although not shown, other hardware and/or software modules may be used in conjunction with the electronic device 1200, including but not limited to: microcode, device drivers, redundant processing units, external magnetic disk drive arrays, RAID systems, tape drives, and data backup storage systems, among others.

Through the above description of the embodiments, those skilled in the art will readily understand that the exemplary embodiments described herein may be implemented by software, or by software in combination with necessary hardware. Therefore, the technical solution according to the embodiments of the present disclosure may be embodied in the form of a software product, which may be stored in a non-volatile storage medium (which may be a CD-ROM, a usb disk, a removable hard disk, etc.) or on a network, and includes several instructions to enable a computing device (which may be a personal computer, a server, a terminal device, or a network device, etc.) to execute the method according to the embodiments of the present disclosure.

In an exemplary embodiment of the present disclosure, there is also provided a computer-readable storage medium having stored thereon a program product capable of implementing the above-described method of the present specification. In some possible embodiments, various aspects of the disclosure may also be implemented in the form of a program product comprising program code for causing a terminal device to perform the steps according to various exemplary embodiments of the disclosure described in the above-mentioned "exemplary methods" of the present description, when the program product is run on the terminal device.

A program product for implementing the above method according to an embodiment of the present disclosure may employ a portable compact disc read only memory (CD-ROM) and include program code, and may be run on a terminal device, such as a personal computer. However, the program product of the present disclosure is not limited thereto, and in this document, a readable storage medium may be any tangible medium that can contain, or store a program for use by or in connection with an instruction execution system, apparatus, or device.

The program product may employ any combination of one or more readable media. The readable medium may be a readable signal medium or a readable storage medium. A readable storage medium may be, for example, but not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination of the foregoing. More specific examples (a non-exhaustive list) of the readable storage medium include: an electrical connection having one or more wires, a portable disk, a hard disk, a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

A computer readable signal medium may include a propagated data signal with readable program code embodied therein, for example, in baseband or as a carrier wave. Such a propagated data signal may take many forms, including, but not limited to, electro-magnetic, optical, or any suitable combination thereof. A readable signal medium may also be any readable medium that is not a readable storage medium and that can communicate, propagate, or transport a program for use by or in connection with an instruction execution system, apparatus, or device.

Program code embodied on a readable medium may be transmitted using any appropriate medium, including but not limited to wireless, wireline, optical fiber cable, RF, etc., or any suitable combination of the foregoing.

Program code for carrying out operations for the present disclosure may be written in any combination of one or more programming languages, including an object oriented programming language such as Java, C + + or the like and conventional procedural programming languages, such as the "C" programming language or similar programming languages. The program code may execute entirely on the user's computing device, partly on the user's device, as a stand-alone software package, partly on the user's computing device on a remote computing device, or entirely on the remote computing device or server. In the case of a remote computing device, the remote computing device may be connected to the user computing device through any kind of network, including a Local Area Network (LAN) or a Wide Area Network (WAN), or may be connected to an external computing device (e.g., through the internet using an internet service provider).

Furthermore, the above-described figures are merely schematic illustrations of processes included in methods according to exemplary embodiments of the present disclosure, and are not intended to be limiting. It will be readily understood that the processes shown in the above figures are not intended to indicate or limit the chronological order of the processes. In addition, it is also readily understood that these processes may be performed synchronously or asynchronously, e.g., in multiple modules.

Other embodiments of the disclosure will be apparent to those skilled in the art from consideration of the specification and practice of the disclosure disclosed herein. This application is intended to cover any variations, uses, or adaptations of the disclosure following, in general, the principles of the disclosure and including such departures from the present disclosure as come within known or customary practice within the art to which the disclosure pertains. It is intended that the specification and examples be considered as exemplary only, with a true scope and spirit of the disclosure being indicated by the following claims.

Claims

1. A method for controlling an operation of a reaction furnace, comprising:

collecting image information in the reaction furnace;

determining temperature field information and combustion state information in the reaction furnace according to the image information;

acquiring combustion condition information of the reaction furnace;

and determining the operating parameters of the reaction furnace according to the temperature field information, the combustion state information and the combustion condition information.

2. The operation control method of the reaction furnace according to claim 1, further comprising:

determining a temperature field information sample, a combustion state information sample and a combustion condition information sample for training a neural network model;

determining a running sample of the reaction furnace;

and training the neural network model by taking the temperature field information sample, the combustion state information sample and the combustion working condition information sample as input samples of the neural network model and taking the operation sample as an output sample of the neural network model.

3. The operation control method of the reaction furnace according to claim 2, wherein the combustion condition information samples include temperature samples and first air supply samples, the operation samples include first operation samples, the temperature field information samples, the combustion state information samples and the combustion condition information samples are input samples of the neural network model, and the operation samples are output samples of the neural network model, and training the neural network model includes:

determining a first sample according to the temperature field information sample, the combustion state information sample, the temperature sample and the first air supply sample;

and taking the first sample as an input sample of the neural network model, taking a first running sample as an output sample of the neural network model, and training the neural network model.

4. The operation control method of the reactor according to claim 3, wherein the first operation sample includes at least one of a primary air fan frequency sample, a primary air inlet valve sample, a primary air pre-heater opening degree sample, a primary air pre-heater bypass sample, a drying grate primary air valve sample, a combustion grate one-stage primary air valve sample, a combustion grate two-stage primary air valve sample, a combustion grate three-stage primary air valve sample, a combustion grate one-stage primary air valve sample, and a combustion grate two-stage primary air valve sample.

5. The operation control method of the reaction furnace according to claim 2, wherein the combustion condition information samples include a second supply air sample, the operation samples include a second operation sample, the temperature field information samples, the combustion state information samples, and the combustion condition information samples are input samples of the neural network model, and the operation samples are output samples of the neural network model, and training the neural network model further comprises:

determining a second sample according to the temperature field information sample, the combustion state information sample and the second air supply sample;

and taking the second sample as an input sample of the neural network model, and taking a second running sample as an output sample of the neural network model, and training the neural network model.

6. The operation control method of the reaction furnace according to claim 5, wherein the second operation sample includes at least one of a overfire air frequency sample, an overfire air inlet valve sample, an overfire air pre-heater opening degree sample, and an overfire air pre-heater bypass sample.

7. The operation control method of the reaction furnace according to claim 2, wherein the combustion condition information samples include material bed thickness samples, the operation samples include third operation samples, the temperature field information samples, the combustion state information samples, and the combustion condition information samples are input samples of the neural network model, and the operation samples are output samples of the neural network model, and training the neural network model further comprises:

determining a third sample according to the temperature field information sample, the combustion state information sample and the material layer thickness sample;

and taking the third sample as an input sample of the neural network model, and taking a third running sample as an output sample of the neural network model, and training the neural network model.

8. The operation control method of the reaction furnace as set forth in claim 7, wherein the third operation sample includes a left-side pusher proportional valve sample and/or a right-side pusher proportional valve sample.

9. The operation control method of the reaction furnace according to claim 2, wherein the combustion condition information samples include a bed thickness sample and a combustion product sample, the operation samples include a fourth operation sample, the temperature field information sample, the combustion state information sample and the combustion condition information sample are used as input samples of the neural network model, the operation samples are used as output samples of the neural network model, and the training of the neural network model further comprises:

determining a fourth sample according to the temperature field information sample, the combustion state information sample, the material layer thickness sample and the combustion product sample;

and taking the fourth sample as an input sample of the neural network model, and taking a fourth running sample as an output sample of the neural network model, and training the neural network model.

10. The operation control method of the reaction furnace according to claim 9, wherein the fourth operation sample includes at least one of a left drying grate movement period sample, a right drying grate movement period sample, a left combustion grate movement period sample, a right combustion grate movement period sample, a left burn-out grate movement period sample, and a right burn-out grate movement period sample.

11. The operation control method of the reaction furnace according to any one of claims 1 to 10, further comprising:

respectively sending general execution parameters in the operation parameters to a left side actuator and a right side actuator of the reaction furnace;

wherein the general execution parameter comprises at least one of a material pushing parameter, a drying parameter, a combustion parameter and an ember parameter.

12. The operation control method of the reaction furnace according to any one of claims 1 to 10, further comprising:

determining a working condition parameter range capable of adjusting the reaction furnace according to the process conditions of the reaction furnace;

judging whether the test sample of the reaction furnace meets the working condition parameter range or not;

if the test sample is judged not to meet the working condition parameter range, determining not to adopt the test sample to test the reaction furnace; and if the test sample is judged to meet the working condition parameter range, determining to adopt the test sample to test the reaction furnace.

13. An operation control device of a reaction furnace, comprising:

the acquisition module is used for acquiring image information in the reaction furnace;

the first determining module is used for determining temperature field information and combustion state information in the reaction furnace according to the image information;

the acquisition module is used for acquiring combustion condition information of the reaction furnace;

and the second determining module is used for determining the operating parameters of the reaction furnace according to the temperature field information, the combustion state information and the combustion working condition information.

14. A computer-readable storage medium on which a computer program is stored, wherein the computer program, when executed by a processor, implements an operation control method of a reaction furnace according to any one of claims 1 to 12.

15. An electronic device, comprising:

a processor; and

a memory for storing executable instructions of the processor;

wherein the processor is configured to perform the operation control method of the reaction furnace according to any one of claims 1 to 12 via execution of the executable instructions.