Intelligent combustion control method and device, equipment and storage medium for garbage incinerator

Abstract

The present disclosure provides a method, device, electronic equipment and computer storage medium for intelligent combustion control of a waste incinerator, and relates to the field of combustion process monitoring. The method includes a distributed control system collecting the input reference quantity required for each control loop in the waste incinerator in real time; transmitting the input reference quantity required for each control loop in the waste incinerator to the intelligent combustion control calculation model corresponding to the control loop to calculate and obtain the operating parameters; transmitting the operating parameters back to the distributed control system and controlling the actions of each actuator of the incinerator during the incineration process. This method overcomes the shortcomings of the traditional ACC system, such as excessive reliance on instrument accuracy, and is a control system that is suitable for my country's waste incineration characteristics and has internationally advanced levels. It aims to achieve unmanned operation of waste incineration control, meet environmental protection standards, safe and stable production requirements, reasonably extend the service life of each equipment, and achieve energy conservation and efficiency goals.

Description

Background Art

[0002] So far, the automatic control of waste incinerators at home and abroad mainly adopts the automatic combustion control system, namely the ACC (Automatic Combustion Control) system. The ACC system technology is mainly introduced from abroad. The technical solution is for the operator to set parameters such as the calorific value of the garbage, the target steam volume, and the specific gravity of the garbage, and to achieve automatic control through the process formula calculation of each loop. The core idea of ​​the technology is process calculation.

[0003] The existing ACC system has certain limitations. For example, the ACC system can only be controlled under certain conditions, and it is difficult to adapt to the characteristics of high moisture content and large fluctuations in composition of domestic garbage. The ACC system is mainly based on formula calculations, and the operator's experience cannot be set into the control system; the ACC system is too dependent on the accuracy of instruments and meters. If some instruments and meters are damaged or the accuracy is not enough, the ACC system is difficult to operate accurately; the ACC system needs to rely on a detailed and accurate garbage calorific value database; this makes it difficult for the ACC system to be widely promoted in domestic garbage incineration plants, and the degree of automation of domestic garbage incineration is low.

[0004] It should be noted that the information disclosed in the above background technology section is only used to enhance the understanding of the background of the present disclosure, and therefore may include information that does not constitute the prior art known to ordinary technicians in the field. Summary of the invention

[0005] In order to solve the above problems, the purpose of the present invention is to provide an intelligent combustion control method and device for a waste incinerator, which can adapt to the characteristics of large inertia, hysteresis, nonlinearity, time-varying, working environment and interference uncertainty of the waste incineration system, improve the uniform heat release of waste in the entire incineration system, and reduce the formation of pollutants.

[0006] Other features and advantages of the present disclosure will become apparent from the following detailed description, or may be learned in part by the practice of the present disclosure.

[0007] According to one aspect of the present disclosure, a method for intelligent combustion control of a waste incinerator includes:

[0008] The distributed control system collects input reference quantities required by each control loop in the waste incinerator in real time;

[0009] The input reference quantity required by each control loop in the waste incinerator is transmitted to the intelligent combustion control calculation model corresponding to the control loop to calculate and obtain the operating parameters;

[0010] The operating parameters are transmitted back to the distributed control system and the actions of the actuators of the incinerator are controlled during the incineration process.

[0011] Furthermore, the waste incinerator intelligent combustion control method further includes:

[0012] Determining the input reference quantity and output controlled quantity required for each control loop in the waste incinerator;

[0013] The input reference quantity and output controlled quantity required for each control loop in the waste incinerator are screened out from the historical combustion condition information, and processed to generate a training set;

[0014] Using the training set to train the intelligent combustion control calculation model of each control loop in the waste incinerator, to obtain the intelligent combustion control calculation model of each control loop in the waste incinerator;

[0015] The calculation model of each control loop in the waste incinerator is combined and packaged as a whole to generate a calculation model of the intelligent combustion control method of the waste incinerator.

[0016] Furthermore, the input reference quantities include: temperature parameters, pressure parameters, load parameters, and pollutant parameters in the incinerator; the output controlled quantities include: control parameters of the feeding system, control parameters of the grate movement cycle, control parameters of the primary air system of the combustion air system, and control parameters of the secondary air system of the combustion air system.

[0017] Furthermore, the input reference quantity also includes: outlet oxygen quantity, garbage layer thickness, and steam drum liquid level.

[0018] Furthermore, the data of the input reference quantity and the output controlled quantity required for collecting each control loop in the waste incinerator need to determine the collection time span and collection frequency.

[0019] Furthermore, the method for processing the data of the input reference quantity and the output controlled quantity required by each control loop in the waste incinerator is to analyze the absolute value and relative trend of each data, and eliminate the data whose absolute value exceeds the limited range.

[0020] Furthermore, the training set and the test set are divided according to chronological order.

[0021] Furthermore, the intelligent combustion control calculation model of each control loop in the waste incinerator is a machine learning model and a neural network model for processing regression problems.

[0022] According to another aspect of the present disclosure, there is provided an intelligent combustion control device for a garbage incinerator, comprising:

[0023] A collection module, used for collecting the input reference quantity and output controlled quantity required by each control loop in the waste incinerator;

[0024] A data processing module, used for processing the input reference quantity and output controlled quantity required by each control loop in the waste incinerator to generate a training set;

[0025] A computing model training module, used for training the learning model of each control loop in the waste incinerator to obtain a computing model of each control loop in the waste incinerator;

[0026] A packaging module, used for combining and packaging the calculation model of each control loop in the waste incinerator as a whole to generate a calculation model of the intelligent combustion control method;

[0027] A calculation module, used to calculate the operating parameters according to the input reference quantity obtained in real time by the distributed control system;

[0028] The communication module is used for data transmission with the distributed control system. The distributed control system obtains the input reference quantity in real time and transmits it to the intelligent combustion control method calculation model for calculation. The calculated operating parameters are transmitted back to the distributed control system and control the actions of various actuators of the incinerator during the incineration process.

[0029] Furthermore, the device may also include a storage module for storing data of input reference quantities, output controlled quantities and operating parameters.

[0030] Furthermore, the device may also include a control module for controlling the operation of the acquisition module, the data processing module, the computing model training module, the encapsulation module, the computing module, the communication module and the storage module.

[0031] According to another aspect of the present disclosure, there is provided a waste incinerator intelligent combustion control device, comprising:

[0032] At least one processor and a memory for communicating with the at least one processor; the memory stores commands that can be executed by the at least one processor, and the commands are executed by the at least one processor so that the at least one processor can execute a waste incinerator intelligent combustion control method as described in the first aspect above.

[0033] According to another aspect of the present disclosure, a computer-readable storage medium is provided, on which a computer program is stored. When the computer program is executed by a processor, the method for intelligent combustion control of a waste incinerator according to the first aspect is implemented.

[0034] According to another aspect of the present disclosure, a computer program product is provided, the computer program product comprising a computer program stored on a computer-readable storage medium, the computer program comprising program instructions, and when the computer program instructions are executed by a processor, the processor executes a waste incinerator intelligent combustion control method as described in the first aspect above.

[0035] The technical solution disclosed in the present invention uses big data technology, deep learning technology and artificial intelligence technology to study the massive operating data of garbage incineration, form an intelligent control algorithm for the incinerator, independently judge and intelligently analyze the combustion state in the incinerator, and automatically adjust the control strategy to realize unmanned operation of incineration control, ensure the stable operation of the incinerator, and achieve the goal of energy saving and efficiency improvement.

[0036] It is to be understood that the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the present disclosure. BRIEF DESCRIPTION OF THE DRAWINGS

[0037] The accompanying drawings herein are incorporated into the specification and constitute a part of the specification, illustrate embodiments consistent with the present disclosure, and together with the specification are used to explain the principles of the present disclosure. Obviously, the accompanying drawings described below are only some embodiments of the present disclosure, and for ordinary technicians in this field, other accompanying drawings can be obtained based on these accompanying drawings without creative work.

[0038] Figure 1 is a flow chart of a method for intelligent combustion control of a waste incinerator provided by an exemplary embodiment of the present application;

[0039] Figure 2 It is a generation process of a calculation model of a waste incinerator intelligent combustion control method provided by an exemplary embodiment of the present application;

[0040] Figure 3 It is a schematic diagram of a device for intelligent combustion control of a garbage incinerator provided by an exemplary embodiment of the present application;

[0041] Figure 4 It is a schematic diagram of an intelligent combustion control device for a waste incinerator provided by an exemplary embodiment of the present application. DETAILED DESCRIPTION

[0042] Example embodiments will now be described more fully with reference to the accompanying drawings. However, example embodiments can be implemented in a variety of forms and should not be construed as limited to the examples set forth herein; rather, these embodiments are provided so that the disclosure will be more comprehensive and complete and to fully convey the concepts of the 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.

[0043] In addition, the accompanying drawings are only schematic illustrations of the present disclosure and are not necessarily drawn to scale. The same reference numerals in the figures represent the same or similar parts, and their repeated description will be omitted. Some of the block diagrams shown in the accompanying drawings are functional entities and do not necessarily correspond to physically or logically independent entities. These functional entities can be implemented in software form, or implemented in one or more hardware modules or integrated circuits, or implemented in different networks and / or processor devices and / or microcontroller devices.

[0044] The scheme provided by this application is a control model that comes from deep learning of massive working condition data of waste incineration. The model has high accuracy and strong computing and processing capabilities for real-time data. It overcomes the shortcomings of traditional systems such as over-reliance on instrument accuracy, and aims to achieve unmanned operation of waste incineration control and achieve energy conservation and efficiency improvement goals. For ease of understanding, several terms involved in this application are first explained below.

[0045] Artificial Intelligence (AI) is the theory, method, technology and application system that uses digital computers or machines controlled by digital computers to simulate, extend and expand human intelligence, perceive the environment, acquire knowledge and use knowledge to obtain the best results. In other words, artificial intelligence is a comprehensive technology in computer science that attempts to understand the essence of intelligence and produce a new intelligent machine that can respond in a similar way to human intelligence. Artificial intelligence is to study the design principles and implementation methods of various intelligent machines so that machines have the functions of perception, reasoning and decision-making.

[0046] Artificial intelligence technology is a comprehensive discipline that covers a wide range of fields, including both hardware-level and software-level technologies. The basic technologies of artificial intelligence generally include sensors, dedicated artificial intelligence chips, cloud computing, distributed storage, big data processing technology, operation / interaction systems, mechatronics and other technologies. Artificial intelligence software technology mainly includes computer vision technology, speech processing technology, natural language processing technology, and machine learning / deep learning.

[0047] Machine Learning (ML) is a multi-disciplinary subject that involves probability theory, statistics, approximation theory, convex analysis, algorithm complexity theory and other disciplines. It specializes in studying how computers simulate or implement human learning behavior to acquire new knowledge or skills and reorganize existing knowledge structures to continuously improve their performance. Machine learning is the core of artificial intelligence and the fundamental way to make computers intelligent. Its applications are spread across all areas of artificial intelligence. Machine learning and deep learning usually include artificial neural networks, belief networks, reinforcement learning, transfer learning, inductive learning, and self-learning.

[0048] The solution provided in the embodiments of the present application involves technologies such as artificial intelligence combustion process monitoring, which is specifically described by the following embodiments:

[0049] The control principle of the incinerator includes: collecting the working condition data of the incinerator, and using the process calculation formula to calculate the working condition data to obtain the air flow control value and the speed value. Among them, the working condition data 902 includes the garbage calorific value LHV (Low Heat Value), the main steam flow, the main steam pressure, the main steam temperature, the leachate injection flow and the urea water injection flow. The motion cycle of the actuator of the incinerator is adjusted by adjusting the speed value.

[0050] The air flow control value includes the standard air flow of the drying grate, the standard air flow of the combustion grate and the standard air flow of the ember grate. The air flow control value is used to control the air flow entering the drying grate, the combustion grate and the ember grate. The standard air flow is obtained by calculating the working condition data and the excess air parameters according to the process calculation formula. At the same time, the standard air flow of the drying grate, the standard air flow of the combustion grate and the ember grate are obtained according to the standard air flow. The unit of the standard air flow is m 3 N / h.

[0051] In addition, the speed value includes the pusher speed, drying grate speed, combustion grate speed and ember grate speed. The working condition data is calculated according to the process calculation formula to obtain the garbage weight. On the one hand, the garbage layer thickness control value in the incinerator is determined according to the garbage weight. On the other hand, the required garbage volume is calculated according to the garbage weight and the specific gravity of the garbage appearance, and the standard speed value is determined based on the required garbage volume. The pusher speed and drying grate speed are calculated according to the garbage layer thickness control value and the standard speed value, and the combustion grate speed and ember grate speed are determined according to the standard speed.

[0052] The calculation formula for the required volume of garbage Vr to be put into the incinerator based on the garbage weight Wr and the garbage appearance specific gravity Sg is as follows:

[0053] Vr=Wr / Sg (1)

[0054] The unit of the required garbage volume Vr is m 3 / h, the unit of garbage weight Wr is t / h, and the unit of garbage apparent specific gravity Sg is t / m 3 .

[0055] The key technologies included in the intelligent combustion control system are as follows:

[0056] (1) The collected temperature field information, combustion state information and combustion condition information are input into the intelligent combustion control system as input variables through the distributed control system.

[0057] (2) Use big data analysis methods to process on-site operation data.

[0058] (3) Use machine learning methods to train the model on the processed field operation data to obtain a high-precision control model.

[0059] (4) The model is trained by changing the combination of input variables so that the model can learn the changing trend of the system's input variables over time, thereby getting rid of the reliance on the high precision of a single point and a single instrument.

[0060] (5) It is highly robust. If a single instrument or actuator is damaged, it will not affect the stable operation of other parts of the system.

[0061] (6) It adopts a control concept that is completely different from the existing garbage incineration automatic control system, gets rid of the dependence on the garbage calorific value database, and can adapt to the characteristics of high calorific value and high organic matter content of garbage.

[0062] (7) It is highly versatile and applicable to a variety of incinerators, including but not limited to mechanical grate incinerators, fluidized bed incinerators and rotary incinerators.

[0063] Figure 1 This is a flow chart of a method for intelligent combustion control of a waste incinerator provided by an exemplary embodiment of the present application, comprising the following steps:

[0064] S101, the distributed control system collects input reference quantities required by each control loop in the waste incinerator in real time;

[0065] S102, transmitting the input reference quantity required by each control loop in the waste incinerator to the intelligent combustion control calculation model corresponding to the control loop to calculate and obtain the operating parameters;

[0066] S103, transmitting the operating parameters back to the distributed control system and controlling the actions of the actuators of the incinerator during the incineration process.

[0067] like Figure 2 As shown, the above-mentioned intelligent combustion control method of the garbage incinerator also includes:

[0068] S201, determining the input reference quantity and output controlled quantity required for each control loop in the waste incinerator;

[0069] S202, selecting the input reference quantity and output controlled quantity required for each control loop in the waste incinerator from the historical combustion condition information, and processing them to generate a training set;

[0070] S203, using the training set to train the intelligent combustion control calculation model of each control loop in the waste incinerator to obtain the intelligent combustion control calculation model of each control loop in the waste incinerator;

[0071] S204, combining and packaging the calculation model of each control loop in the waste incinerator as a whole to generate a calculation model of the intelligent combustion control method of the waste incinerator.

[0072] In an exemplary embodiment of the present disclosure, by reading the current combustion condition information, several data measurement points containing these data are transmitted to the database for storage through the OPC (Object Linking and Embedding, object connection and embedding for process control) communication protocol, and the variable information of each model is read and the model calculation is performed based on the control algorithm. After the model calculation is completed, the calculation result of the model is output as the operating parameter, and the operating parameter is transferred to the database for storage, and the operating parameter is transferred to the distributed control system to control the actuator. Based on the study of historical combustion condition information, a control algorithm library of the incinerator is formed, which improves the judgment speed of the combustion condition information, improves the information processing efficiency of the incinerator, improves the automation level of the incinerator, improves the operating stability and safety of the incinerator, and improves the energy efficiency utilization rate.

[0073] Among them, the above-mentioned historical combustion operating condition information includes main steam flow, outlet oxygen content, garbage layer thickness, drying grate temperature, upper combustion grate temperature, upper ember grate temperature, furnace average temperature and high-temperature superheater temperature, but is not limited to these.

[0074] Next, the intelligent combustion control method of a waste incinerator is described in conjunction with the following embodiments.

[0075] Step 1: Collect historical combustion condition information.

[0076] The collection of historical combustion condition information requires the determination of the variables to be collected, the collection time span, and the sampling frequency. The variables to be collected are the input and output variables mentioned above. The time span and sampling frequency of collecting samples can be determined according to the performance requirements of the model. The collection time span is an important factor affecting the richness of historical combustion condition information. The richer the historical combustion condition information collected, the higher the generalization of the model.

[0077] Step 2: Train the neural network model.

[0078] (1) Select the input variables of the model: The variables of the input model include the temperature parameters, pressure parameters, load parameters, pollutant parameters, operating state parameters and flame combustion information of the reactor.

[0079] Among them, temperature parameters include furnace temperature, grate temperature, furnace average temperature, high temperature superheater temperature, main steam temperature and ash temperature. Pressure parameters include primary air pressure, secondary air pressure, drum pressure, main steam pressure and furnace pressure. Load parameters include main steam flow, combustion chamber heat load and grate mechanical load. Pollutant parameters include hydrogen chloride, carbon dioxide, nitrogen oxides, particulate matter and carbon monoxide. Operating state parameters include outlet gas oxygen content, garbage layer thickness and drum liquid level.

[0080] There is more than one model involved in the embodiments of the present disclosure. Therefore, there is no data set after the same data processing method is used for the models of different control loops. Instead, a model is established for each control loop separately. The process of establishing the model in the embodiments of the present disclosure is different from the existing methods. The existing methods are to first perform steps such as sample processing and data analysis, and then establish the model. The embodiments of the present disclosure perform the variable selection process and model establishment process of each control loop while performing the data processing process.

[0081] (2) Steps for processing input data: first process the parent set data, then select the subset data. The data set after rough processing of the original data is called the parent set, and the data set corresponding to the variables involved in each control loop is selected as the subset. When processing the parent set data, the overall operating conditions are used as a guide, and non-stable and abnormal operating condition data are eliminated. This extensive processing method results in the deletion of all variables at certain time points. When processing the subset data, the selection process of the subset variables is staggered. When selecting subset variables, the correlation in process logic is used as a guide, supplemented by the results of historical data analysis. The purpose of data processing is to screen out excellent manual experience for the model to perform machine learning. The quality of the data determines the upper and lower limits of the model accuracy, so the data sample should try to select data from skilled boiler operators.

[0082] (3) Building a neural network model: Divide each selected subset into a test set and a training set, and use the training set to train the neural network model. The neural network model includes but is not limited to a neural network model that processes regression problems (i.e., the output is a continuous variable), such as a decision tree regression model, a support vector regression model, a BP (back propagation) neural network model, and a long short-term memory network model.

[0083] The difference between the neural network model building of the present invention and ordinary machine learning is that before the ordinary machine learning model is built, the method of randomly dividing the training set and the test set is adopted. Since ordinary data samples are disordered and independent and do not affect each other, random division is feasible. However, the data sample involved in the present invention is a panel data to be precise, which is a continuous time series on the time axis. The garbage incineration system has a large lag. The working conditions of the previous period have a great influence on the working conditions of the next period, and the working conditions at adjacent time points are highly similar. If the training set and the test set are randomly divided, it will essentially lead to the intersection of the training set and the test set, and the purpose of testing the model effect cannot be achieved. This is an important technical point of the present invention. If the test set and the training set are not divided according to the principle of continuous division, the neural network model will perform well during training, but the effect will be very poor during actual use.

[0084] (4) Simplified neural network model: The complete system output of the embodiment of the present disclosure has 22 outputs in total, which can be appropriately simplified. For example, the operating parameters of the left and right grate motion cycle classes are simplified to the operating parameters of the grate motion cycle class, which can reduce 4 neural network models. The embodiment of the present disclosure performs linkage processing on the operating parameters of the left and right grate motion cycle classes, and only needs to establish neural network models of 18 operating parameters.

[0085] In addition, in addition to the operating parameters of the left and right grate movement cycles, other operating parameters can also be appropriately linked according to the relationship between the operating parameters. By linking appropriate operating parameters to the operating parameters of a single neural network model, the output results of the neural network model are simplified while ensuring the robustness of the system, the complexity of the neural network model is reduced, and the training speed of the neural network model is improved.

[0086] (5) Optimize the input variables and output operating parameters of the neural network model. There are many neural network models, and each neural network model has a large number of parameters. By training the neural network model, the optimal parameter indicators of the neural network model are found, and the historical operating status and the current operating status are mapped to the action of each actuator to achieve continuous stability of the reactor operating conditions.

[0087] The indicators of neural network model performance are different from those of traditional regression machine learning models. The present invention does not directly use loss function values ​​such as MSE (Mean Square Error) as the standard for evaluating the quality of the model. Since the sample data is generated by manual regulation, the selection of specific values ​​often contains certain subjective factors, so the control output within a certain range can achieve similar control effects. Therefore, the present invention defines a new model accuracy indicator, that is, after the neural network model is trained, the difference between the original value and the model calculated value on the test set is calculated, and the proportion of the difference within a certain tolerance range is counted. The higher the proportion within the tolerance, the higher the control accuracy of the neural network model.

[0088] Step 3: Output the operating parameters of the intelligent control system.

[0089] The operating parameters output by the neural network model include operating parameters for controlling the feeding system, operating parameters for controlling the grate movement cycle, operating parameters for controlling the primary air system of the combustion air system, and operating parameters for controlling the secondary air system of the combustion air system.

[0090] (1) The operating parameters of the feeding system include the parameters of the left pusher proportional valve and the right pusher proportional valve.

[0091] (2) The operating parameters of the grate movement cycle include the left drying grate movement cycle parameters, the right drying grate movement cycle parameters, the left burning grate movement cycle parameters, the right burning grate movement cycle parameters, the left ember grate movement cycle parameters and the right ember grate movement cycle parameters.

[0092] (3) The operating parameters of the primary air system of the combustion air system include primary fan frequency parameters, primary air inlet valve parameters, primary air air preheater opening and closing parameters, primary air air preheater branch parameters, drying grate primary air valve parameters, combustion grate first stage primary air valve parameters, combustion grate second stage primary air valve parameters, combustion grate third stage primary air valve parameters, ember grate first stage primary air valve parameters and ember grate second stage primary air valve parameters.

[0093] (4) The operating parameters of the secondary air system of the combustion air system include the secondary fan frequency parameters, the secondary air inlet valve parameters, the secondary air preheater opening and closing parameters and the secondary air preheater branch parameters.

[0094] Step 4: Test the intelligent combustion control system.

[0095] (1) Obtain the required system output control model through the intelligent combustion control system data acquisition and model training module.

[0096] (2) Encapsulate the neural network model and transmit data between the control program and the distributed control system, so that the real-time data of the distributed control system can be transmitted to the core control algorithm. The core control algorithm reads the real-time data into the previously trained neural network model for calculation, and transmits the calculated control instructions back to the distributed control system to command the actions of each actuator in the incineration system.

[0097] (3) Before the system is officially put into use, it is necessary to conduct offline and online tests. Offline testing is to continuously input historical combustion condition information into the core control algorithm, compare the difference between the manual operation value and the algorithm calculation value under the previous working conditions, test several sets of values, and if the difference is within an acceptable range, then online testing can be carried out.

[0098] (4) After the offline test is completed, the system needs to be tested online. The online test needs to make an objective evaluation of the various functions of the combustion control system, preset the functional indicators of the online test effect, and evaluate the online test of the combustion control system based on the indicators. Among them, the functional indicators include the load indicator main steam flow, the temperature indicator furnace average temperature, and the indicator outlet oxygen volume that affects pollutant emissions.

[0099] (5) During online testing, process constraints on process logic are added to ensure that the operating conditions can quickly recover from abnormal to normal. In order to ensure that the system is tested online using the algorithm adjustment capability under normal conditions, it is necessary to add appropriate process constraints for abnormal conditions that exceed the algorithm adjustment capability.

[0100] (6) After the online test is completed, the intelligent combustion control system is able to maintain stability when taking over the waste incineration system. At this time, we also need to make an input interface for the intelligent combustion control system to set the required target steam volume. This target steam volume needs to be combined with the model of the feeding system in the algorithm to complete the high and low regulation of the overall load level of the waste incinerator.

[0101] This disclosure integrates intelligent and efficient big data technology, improves the control accuracy and information processing efficiency of the system through online learning of historical data, and achieves the following control effects:

[0102] (1) The stability of the total steam flow of the boiler is improved.

[0103] (2) The control effect of garbage layer thickness is improved.

[0104] (3) The controllability of the garbage burning location is improved.

[0105] (4) The loss due to thermal ignition is reduced.

[0106] (5) The stability of furnace temperature is improved.

[0107] (6) Improved the environmental compliance rate, safety and stability of operating indicators in production requirements.

[0108] (7) Improved adaptability to garbage with high moisture content and high organic matter content.

[0109] (8) Extend the service life of the equipment and reduce equipment costs.

[0110] (9) Improved energy conservation and efficiency of waste incineration power plants.

[0111] (10) The automated intelligent control effect of waste incineration has been improved.

[0112] (11) The recognition results of flame temperature field by non-contact temperature measurement are improved.

[0113] (12) The speed of determining the flame combustion status and the efficiency of information processing are improved.

[0114] In addition, the incinerator combustion control system disclosed in the present invention combines big data technology and artificial intelligence technology, as well as a distributed control system, to identify and judge the combustion state of the furnace, thereby performing real-time analysis, and at the same time uses artificial intelligence technology to control the combustion state of the incinerator.

[0115] Furthermore, in the intelligent combustion control system, control principles, big data technology and artificial intelligence technology are used to analyze historical data, and the data of the intelligent combustion control system is analyzed and calculated to obtain the optimal operating parameters of each controller variable in the garbage incineration system, and then the optimal operating parameters are returned to the distributed control system to control the intelligent combustion control system. Under the premise of ensuring uniform heat release of garbage, the combustion volume of flue gas and residue is increased, the generation of pollutants is reduced, the harmlessness of garbage treatment is improved, the reduction of garbage treatment is improved, and the energy efficiency of garbage treatment is improved.

[0116] The present disclosure trains neural network models based on advanced process control methods such as fuzzy control, statistical analysis, machine learning technology, deep learning technology and machine vision AI technology, and incorporates the rich operating experience of on-site operators into the model, with high model accuracy and strong applicability. The above technical solutions are only used to illustrate the present disclosure, and are not idle for the protection scope of the present disclosure. Modifications and deformations of the present disclosure through 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 equivalent technologies.

[0117] Corresponding to the above method embodiments, the present disclosure also provides an operation control device of a reactor, which can be used to execute the above method embodiments.

[0118] Figure 3It is an intelligent combustion control device for a waste incinerator in an exemplary embodiment of the present disclosure. In the intelligent combustion control device 300 for a waste incinerator, the following modules are included but are not limited to: an acquisition module 310, a data processing module 320, a computational model training module 330, an encapsulation module 340, a computational module 350, and a communication module 360.

[0119] The acquisition module 310 is used to acquire the input reference quantity and output controlled quantity required by each control loop in the waste incinerator.

[0120] The data processing module 320 is used to process the input reference quantity and the output controlled quantity required by each control loop in the waste incinerator to generate a training set.

[0121] The computing model training module 330 is used to train the learning model of each control loop in the waste incinerator to obtain the computing model of each control loop in the waste incinerator.

[0122] The encapsulation module 340 is used to combine the calculation model of each control loop in the waste incinerator and encapsulate it as a whole to generate a calculation model of the intelligent combustion control method.

[0123] The calculation module 350 is used to calculate the operating parameters according to the input reference quantity obtained in real time by the distributed control system.

[0124] The communication module 360 ​​is used for data transmission with the distributed control system. The distributed control system obtains the input reference quantity in real time and transmits it to the intelligent combustion control method calculation model for calculation. The calculated operating parameters are transmitted back to the distributed control system and control the actions of the various actuators of the incinerator during the incineration process.

[0125] Preferably, the intelligent combustion control device 300 for a waste incinerator may further include a storage module 370 for storing data of input reference quantities and output controlled quantities.

[0126] Optionally, the intelligent combustion control device 300 for a waste incinerator may also include a control module 380 for controlling the operation of the acquisition module 310, the data processing module 320, the computational model training module 330, the encapsulation module 340, the computational module 350, the communication module 360 ​​and the storage module 370.

[0127] Specifically, the intelligent combustion control device 300 of the waste incinerator collects historical combustion condition information through the acquisition module 310, the data processing module 320 calls the data set of the collected historical combustion condition information after rough processing as the parent set, selects the data set corresponding to the variables involved in each control loop as the subset, the calculation model training module 330 divides each selected subset into a test set and a training set, uses the training set to train the neural network model, the encapsulation module 340 encapsulates the trained neural network model, and transmits data between the control program and the distributed control system through the communication module 360. The acquisition module 310 obtains the current input reference quantity in the distributed control system, that is, the operating state. For example, the key operating parameters at a certain moment are: main steam flow 38.07t / h, outlet oxygen analyzer 6.95%, garbage layer thickness 0.28kpa, combustion grate temperature (A: 167.92℃, B: 175.24℃, C: 160.04℃, D: 170.83℃), combustion grate upper temperature 1069.74℃, burnout grate upper temperature 919.39℃, furnace average temperature 1051.20℃, high-temperature superheater temperature 642.18℃, the communication module 360 ​​transmits several data measurement points containing these data to the database storage through the OPC communication protocol, and the calculation module 350 reads the corresponding data for calculation according to the variable information required by each model. For example, the input variables of the secondary fan frequency regulation model are the outlet oxygen analyzer, the average furnace temperature, and the high-temperature superheater temperature. The current values ​​of these three variables are input into the secondary fan frequency model to obtain the control value of the secondary fan frequency. When all the models are calculated, the output reference quantity under this working condition is obtained, that is, the adjustment quantity should be set to: primary fan frequency 30.5HZ, primary air inlet valve 100%, primary air air preheater inlet valve opening 0%, primary air air preheater branch valve opening 100%, drying grate primary air valve 40%, combustion grate first stage primary air valve 50%, combustion grate second stage primary air valve 50%, combustion grate third stage primary air valve 50%, ember grate first stage primary air valve 80%, ember grate second stage primary air valve 50%, secondary fan frequency 20HZ, secondary air inlet valve 100%, secondary air air preheater inlet valve opening 0%, secondary air air preheater branch valve opening 100%, left and right drying grate movement cycle 80S, left and right combustion grate movement cycle 88S, left and right ember grate movement cycle 150S, left and right pusher proportional valve 38%. The communication module 360 ​​transmits the calculated operating parameters back to the distributed control system and controls the actions of the actuators of the incinerator during the incineration process.

[0128] It should be noted that since the intelligent combustion control device for a waste incinerator in this embodiment and the intelligent combustion control method for a waste incinerator in any of the above embodiments are based on the same inventive concept, the corresponding contents in the method embodiment are also applicable to the system embodiment and will not be described in detail here.

[0129] Figure 4 An exemplary embodiment of the present application provides an intelligent combustion control device for a waste incinerator. The intelligent combustion control device 400 for a waste incinerator can be any type of terminal, such as a mobile phone, a game console, a tablet computer, an e-book reader, smart glasses, an MP4 (Moving Picture Experts Group Audio Layer IV) player, a smart home device, an AR (Augmented Reality) device, a VR (Virtual Reality) device and other mobile terminals, or the intelligent combustion control device 300 for a waste incinerator can also be a personal computer (Personal Computer, PC), such as a laptop computer and a desktop computer, etc., a mobile phone, a tablet computer, a personal computer, etc.

[0130] Among them, the intelligent combustion control device 400 of a waste incinerator can be installed with an application for providing an intelligent combustion control method for a waste incinerator.

[0131] Preferably, the intelligent combustion control device 400 for a waste incinerator comprises: one or more processors 410 and a memory 420, Figure 4 A processor 410 is taken as an example.

[0132] The processor 410 and the memory 420 may be connected via a bus or other means. Figure 4 Take the example of connecting via a bus.

[0133] The memory 420 is a non-transitory computer-readable storage medium that can be used to store non-transitory software programs, non-transitory computer executable programs and units, such as program instructions / units corresponding to a waste incinerator intelligent combustion control device 400 in an embodiment of the present invention, for example, Figure 3 The processor 410 executes various functional applications and data processing of a waste incinerator intelligent combustion control device 300 by running the non-transient software programs, instructions and units stored in the memory 420, that is, implements a waste incinerator intelligent combustion control method of the above method embodiment.

[0134] The memory 420 may include a program storage area and a data storage area, wherein the program storage area may store an operating system and an application required by at least one function; the data storage area may store data created according to the use of a waste incinerator intelligent combustion control device 300, etc. In addition, the memory 420 may include a high-speed random access memory, and may also include a non-transitory memory, such as at least one disk storage device, a flash memory device, or other non-transitory solid-state storage device. In some embodiments, the memory 420 may optionally include a memory remotely arranged relative to the processor 410, and these remote memories may be connected to the waste incinerator intelligent combustion control device 300 via a network.

[0135] Optionally, the above-mentioned network connection can be a wireless network or a wired network using standard communication technology and / or protocols. The network is usually the Internet, but it can also be any network, including but not limited to a local area network (LAN), a metropolitan area network (MAN), a wide area network (WAN), a mobile, wired or wireless network, a dedicated network or any combination of a virtual private network). In some embodiments, the data exchanged through the network is represented by technologies and / or formats including Hyper Text Mark-up Language (HTML), Extensible Markup Language (XML), etc. In addition, conventional encryption technologies such as Secure Socket Layer (SSL), Transport Layer Security (TLS), Virtual Private Network (VPN), Internet Protocol Security (IPsec) can also be used to encrypt all or some links. In other embodiments, customized and / or dedicated data communication technologies can also be used to replace or supplement the above-mentioned data communication technologies.

[0136] The one or more units are stored in the memory 420, and when executed by the one or more processors 410, a waste incinerator intelligent combustion control method in any of the above method embodiments is executed. Figure 1 In the method steps S101 to S103, Figure 2 Steps S201 to S204 of the method are implemented Figure 3 The functions of modules 310-360.

[0137] The embodiment of the present invention further provides a computer-readable storage medium, wherein the computer-readable storage medium stores computer-executable instructions, and the computer-executable instructions are executed by one or more processors, for example, Figure 4 The one or more processors 410 in the embodiment of the method may execute the intelligent combustion control method of a waste incinerator in the embodiment of the method, and execute the above-described Figure 1 In the method steps S101 to S103, Figure 2 Steps S201 to S204 of the method are implemented Figure 3 The functions of modules 310-360.

[0138] The embodiment of the present invention further provides a computer program product, the computer program product comprising a computer program stored on a computer-readable storage medium, the computer program comprising program instructions, when the program instructions are executed by a computer, for example, Figure 4 The one or more processors 410 in the embodiment of the present invention may execute the intelligent combustion control method of a waste incinerator in the embodiment of the present invention, for example, executing the above-described Figure 1 In the method steps S101 to S103, Figure 2 Steps S201 to S204 of the method are implemented Figure 3 The functions of modules 310-360.

[0139] A program product for implementing the above method according to an embodiment of the present invention is described, which can adopt a portable compact disk read-only memory (CD-ROM) and include program code, and can be run on a terminal device, such as a personal computer. However, the program product of the present invention is not limited thereto, and in this document, a readable storage medium can be any tangible medium containing or storing a program, which can be used by or in combination with an instruction execution system, an apparatus or a device.

[0140] The program product may use any combination of one or more readable media. The readable medium may be a readable signal medium or a readable storage medium. The readable storage medium may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device or device, or any combination of the above. More specific examples (non-exhaustive list) of readable storage media include: an electrical connection with 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 disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above.

[0141] Computer readable signal media may include data signals propagated in baseband or as part of a carrier wave, in which readable program code is carried. Such propagated data signals may take a variety of forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the above. Readable signal media may also be any readable medium other than a readable storage medium, which may send, propagate, or transmit a program for use by or in conjunction with an instruction execution system, apparatus, or device.

[0142] The program code embodied on the readable medium may be transmitted using any appropriate medium, including but not limited to wireless, wired, optical cable, RF, etc., or any suitable combination of the foregoing.

[0143] Program code for performing the operations of the present invention may be written in any combination of one or more programming languages, including object-oriented programming languages ​​such as Java, C++, etc., and conventional procedural programming languages ​​such as "C" or similar programming languages. The program code may be executed entirely on the user computing device, partially on the user device, as a separate software package, partially on the user computing device and partially on a remote computing device, or entirely on a remote computing device or server. In cases involving a remote computing device, the remote computing device may be connected to the user computing device through any type 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).

[0144] Optionally, the client of the application installed in different devices 400 is the same, or the client of the application installed on the two devices 400 is the client of the same type of application on different control system platforms. Based on the different terminal platforms, the specific form of the client of the application can also be different, for example, the application client can be a mobile client, a PC client or a World Wide Web (Web) client.

[0145] Those skilled in the art will appreciate that the number of the above-mentioned devices 400 may be more or less. For example, the above-mentioned terminal may be only one, or the above-mentioned terminals may be dozens or hundreds, or more. The embodiment of the present application does not limit the number of terminals and device types.

[0146] It should be noted that the above figures are only schematic illustrations of the processes included in the method according to an exemplary embodiment of the present invention, and are not intended to be limiting. It is easy to understand that the processes shown in the above figures do not indicate or limit the time sequence of these processes. In addition, it is also easy to understand that these processes can be performed synchronously or asynchronously, for example, in multiple modules.

[0147] It will be appreciated by those skilled in the art that various aspects of the present invention may be implemented as a system, method or program product. Therefore, various aspects of the present invention may be specifically implemented in the following forms, namely: a complete hardware implementation, a complete software implementation (including firmware, microcode, etc.), or a combination of hardware and software, which may be collectively referred to herein as a "circuit", "module" or "system".

[0148] Through the description of the above implementation, it is easy for those skilled in the art to understand that the example implementation described here can be implemented by software, or by software combined with necessary hardware. Therefore, the technical solution according to the implementation of the present disclosure can be embodied in the form of a software product, which can be stored in a non-volatile storage medium (which can be a CD-ROM, a USB flash drive, a mobile hard disk, etc.) or on a network, including several instructions to enable a computing device (which can be a personal computer, a server, a terminal device, or a network device, etc.) to execute the method according to the implementation of the present disclosure.

[0149] It should be noted that, although several modules or units of the device for action execution are mentioned in the above detailed description, this division is not mandatory. In fact, according to the embodiments of the present disclosure, the features and functions of two or more modules or units described above can be embodied in one module or unit. On the contrary, the features and functions of one module or unit described above can be further divided into multiple modules or units to be embodied.

[0150] In addition, although the steps of the method in the present disclosure are described in a specific order in the drawings, this does not require or imply that the steps must be performed in this specific order, or that all the steps shown must be performed to achieve the desired results. Additionally or alternatively, some steps may be omitted, multiple steps may be combined into one step, and / or one step may be decomposed into multiple steps, etc.

[0151] Through the description of the above implementation, it is easy for those skilled in the art to understand that the example implementation described here can be implemented by software, or by software combined with necessary hardware. Therefore, the technical solution according to the implementation of the present disclosure can be embodied in the form of a software product, which can be stored in a non-volatile storage medium (which can be a CD-ROM, a USB flash drive, a mobile hard disk, etc.) or on a network, including several instructions to enable a computing device (which can be a personal computer, a server, a mobile terminal, or a network device, etc.) to execute the method according to the implementation of the present disclosure.

[0152] Those skilled in the art will readily appreciate other embodiments of the present disclosure after considering the specification and practicing the invention disclosed herein. This application is intended to cover any modification, use or adaptation of the present disclosure, which follows the general principles of the present disclosure and includes common knowledge or customary techniques in the art that are not disclosed in the present disclosure. The specification and examples are intended to be exemplary only, and the true scope and spirit of the present disclosure are indicated by the appended claims.

Claims

1. A method for intelligent combustion control of a waste incinerator, characterized in that: include: The distributed control system collects input reference quantities required by each control loop in the waste incinerator in real time; The input reference quantity and output controlled quantity required for each control loop in the waste incinerator are screened out from the historical combustion condition information, and processed to generate a training set; wherein the training set and the test set are divided according to the principle of continuous division based on the time series; Using the training set to train the intelligent combustion control calculation model of each control loop in the waste incinerator, to obtain the intelligent combustion control calculation model of each control loop in the waste incinerator; The input reference quantity required by each control loop in the waste incinerator is transmitted to the intelligent combustion control calculation model corresponding to the control loop to calculate and obtain the operating parameters; The operating parameters are transmitted back to the distributed control system and the actions of the actuators of the incinerator are controlled during the incineration process.

2. The intelligent combustion control method for a waste incinerator according to claim 1 is characterized in that: Also includes: Determining the input reference quantity and output controlled quantity required for each control loop in the waste incinerator; The calculation model of each control loop in the waste incinerator is combined and packaged as a whole to generate a calculation model of the intelligent combustion control method of the waste incinerator.

3. The intelligent combustion control method for a waste incinerator according to claim 2 is characterized in that: The input reference quantities include: temperature parameters, pressure parameters, load parameters, and pollutant parameters in the incinerator; the output controlled quantities include: control parameters of the feeding system, control parameters of the grate movement cycle, control parameters of the primary air system of the combustion air system, and control parameters of the secondary air system of the combustion air system.

4. The intelligent combustion control method for a waste incinerator according to claim 2 is characterized in that: The input reference quantities also include: outlet oxygen quantity, garbage layer thickness, and drum liquid level.

5. The intelligent combustion control method for a waste incinerator according to claim 2 is characterized in that: The data of the input reference quantity and the output controlled quantity required for collecting each control loop in the waste incinerator need to determine the collection time span and collection frequency.

6. The intelligent combustion control method for a waste incinerator according to claim 2 is characterized in that: The method for processing the data of the input reference quantity and the output controlled quantity required by each control loop in the waste incinerator is to analyze the absolute value and relative trend of each data and eliminate the data whose absolute value exceeds the limited range.

7. The intelligent combustion control method for a waste incinerator according to claim 2 is characterized in that: The intelligent combustion control calculation model of each control loop in the waste incinerator is a machine learning model and a neural network model for processing regression problems.

8. An intelligent combustion control device for a garbage incinerator, characterized in that: Includes the following modules: A collection module, used for collecting the input reference quantity and output controlled quantity required by each control loop in the waste incinerator; A data processing module, used for processing the input reference quantity and output controlled quantity required by each control loop in the waste incinerator to generate a training set; A computing model training module, used for training the learning model of each control loop in the waste incinerator to obtain a computing model of each control loop in the waste incinerator; A packaging module, used for combining and packaging the calculation model of each control loop in the waste incinerator as a whole to generate a calculation model of the intelligent combustion control method; A calculation module, used to calculate the operating parameters according to the input reference quantity obtained in real time by the distributed control system; The communication module is used for data transmission with the distributed control system. The distributed control system obtains the input reference quantity in real time and transmits it to the intelligent combustion control method calculation model for calculation. The calculated operating parameters are transmitted back to the distributed control system and control the actions of various actuators of the incinerator during the incineration process.

9. An intelligent combustion control electronic device for a garbage incinerator, characterized in that: include: at least one processor and a memory for being communicatively coupled to the at least one processor; The memory stores commands that can be executed by the at least one processor, and the commands are executed by the at least one processor so that the at least one processor can execute any one of the intelligent combustion control methods for a waste incinerator in claims 1 to 7.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the intelligent combustion control method for a waste incinerator described in any one of claims 1 to 7 is implemented.

Images