Intelligent combustion control method, system and device based on feedback mechanism

Abstract

The invention provides an intelligent combustion control method, system and device based on a feedback mechanism, and the method comprises the steps: receiving a hearth combustion state parameter and a Raman coal quality online detection signal, comparing the signals with a preset threshold value, and adopting a feedforward control strategy to control and adjust an air supply system and a powder feeding system, thereby achieving the high-precision combustion control. And the combustion efficiency and emission are optimized. And the model predictive control is utilized to analyze the obtained signal, predict the change trend of the combustion process and dynamically adjust the operation parameters of the combustor, so that the load change is quickly responded, and the dynamic performance of the combustion system is improved. Through real-time monitoring and accurate control, stable combustion under low load is ensured, and NOx generation is reduced. Through a closed-loop control system, feedforward and feedback control strategies are continuously optimized so as to adapt to various disturbances and changes possibly occurring in the combustion process. According to the method, advanced pre-judgment and advanced adjustment of multiple key variables are achieved, the boiler is kept in the optimal combustion state, and the combustion efficiency of the boiler is improved.

Description

Technical Field

[0001] The present invention relates to the field of energy control technology, and in particular to an intelligent combustion control method, system and device based on a feedback mechanism. Background Art

[0002] Under the demand for large-scale new energy consumption, the grid dispatching has stricter assessment standards for the peak-shaving depth and load response speed of thermal power units. The dynamic characteristics of the controlled processes of boilers and steam turbines change significantly under wide load operating conditions. The flexible operation of the units not only requires the control system to have good load tracking performance, anti-disturbance capability and robustness under wide load conditions, but also needs to meet relevant goals and constraints such as safety, environmental protection and economy.

[0003] Traditional combustion control mainly relies on the operator's experience, and combustion is maintained by manually adjusting the air supply and powder supply system. However, this method has limited control accuracy and response speed, and it is difficult to meet the needs of modern industry for efficient and low-pollution combustion. Existing combustion control systems have obvious deficiencies in low-load stable combustion, rapid response, coal type adaptability, and precise control. New intelligent control methods are urgently needed to solve these problems. Summary of the invention

[0004] The present invention provides an intelligent combustion control method, system and device based on a feedback mechanism, which are used to solve many defects in the control of the combustion system in the prior art.

[0005] In a first aspect, the present invention provides an intelligent combustion control method based on a feedback mechanism, comprising: Acquire a furnace combustion detection signal set of the combustion system, pre-process and analyze the furnace combustion detection signal set to obtain a processed signal set; Comparing the processed signal set with a preset combustion state threshold to obtain an initial comparison result, and using a feedforward control strategy to perform a pre-coarse adjustment on the combustion system according to the initial comparison result; Acquire the real-time detection signal of the combustion system after the pre-coarse adjustment, predict the real-time detection signal by the model prediction control module using preset constraints, and output a real-time prediction signal, wherein the preset constraints are determined by the combustion process state matrix and the target evaluation function in the future preset period; If it is determined that the combustion state of the combustion system deviates from the preset target, a feedback control strategy is triggered to adjust the combustion state to a preset reasonable range; The combustion state is monitored in real time through a closed-loop control system, the feedforward control strategy and the feedback control strategy are executed, and the combustion system is continuously optimized and adjusted.

[0006] According to an intelligent combustion control method based on a feedback mechanism provided by the present invention, a furnace combustion detection signal set of a combustion system is obtained, and the furnace combustion detection signal set is preprocessed and analyzed to obtain a processed signal set, including: Receiving furnace combustion state parameter signals, Raman online detection signals and EPR detection signals through the network interface of the combustion system; Based on a filtering algorithm, the furnace combustion state parameter signal, the Raman online detection signal and the EPR detection signal are subjected to denoising processing to obtain a plurality of filtered signals; Data fusion is performed on the multiple filtered signals to obtain the processed signal set.

[0007] According to an intelligent combustion control method based on a feedback mechanism provided by the present invention, the feedforward control strategy includes: Get the current combustion status result; Inputting the furnace combustion state parameter signal, the Raman online detection signal and the EPR detection signal corresponding to the current combustion state result into a server for calculation to obtain a set of adjustment parameters; The adjustment parameter set is respectively input into the air supply controller, the powder supply controller and the burner controller in the combustion system, and a real-time detection signal of the combustion system after the pre-coarse adjustment is output.

[0008] According to an intelligent combustion control method based on a feedback mechanism provided by the present invention, the combustion process state matrix of the future preset period includes:

[0009]

[0010] Among them, U represents the matrix of input parameters, Y represents the matrix of output parameters, A, B(X), C(X) and D(X) represent the coefficient matrices transformed by the model, and predictions are made within a preset period in the future.

[0011] According to an intelligent combustion control method based on a feedback mechanism provided by the present invention, the objective evaluation function includes a rolling optimization objective function and a multi-objective optimization objective function; The rolling optimization objective function for:

[0012] in, Indicates the amount of coal fed. Indicates burner parameters, Indicates the air supply volume. It indicates the difference between the coal quantity given by the coal feeding controller and the coal feeding instruction of the unit. Indicates the difference between the burner controller parameter and the unit command. Indicates the coal feeding instruction given by the unit. Indicates the burner command given by the unit. Indicates the air supply volume instruction given by the unit; The multi-objective optimization objective function for:

[0013] in, It represents the difference between the optimized NOx concentration and the NOx concentration calculated by the unit. It represents the difference between the optimized boiler combustion efficiency and the efficiency calculated by the unit. Indicates the Nox concentration calculated by the unit, Indicates the boiler combustion efficiency calculated for the unit.

[0014] According to an intelligent combustion control method based on a feedback mechanism provided by the present invention, the feedback control strategy includes: Obtaining combustion state feedback signals generated by the air supply controller, the powder supply controller and the burner controller; After calculating the combustion state feedback signal through the server, a new furnace combustion state parameter signal, a Raman online detection signal and an EPR detection signal are output, and fed back to the air supply controller, the powder supply controller and the burner controller for post-fine adjustment.

[0015] In a second aspect, the present invention further provides an intelligent combustion control system based on a feedback mechanism, comprising: A preprocessing module, used to obtain a furnace combustion detection signal set of the combustion system, preprocess and analyze the furnace combustion detection signal set to obtain a processed signal set; A feedforward adjustment module, used for comparing the processed signal set with a preset combustion state threshold to obtain an initial comparison result, and adopting a feedforward control strategy to perform a forward rough adjustment on the combustion system according to the initial comparison result; A prediction module, used for obtaining a real-time detection signal of the combustion system after the pre-coarse adjustment, and the model prediction control module predicts the real-time detection signal using a preset constraint condition, and outputs a real-time prediction signal, wherein the preset constraint condition is determined by a combustion process state matrix and an objective evaluation function in a future preset period of time; A feedback adjustment module is used to trigger a feedback control strategy to adjust the combustion state to a preset reasonable range if it is determined that the combustion state of the combustion system deviates from a preset target; The closed-loop adjustment module is used to monitor the combustion state in real time through a closed-loop control system, execute the feedforward control strategy and the feedback control strategy, and continuously optimize and adjust the combustion system.

[0016] In a third aspect, the present invention further provides an intelligent combustion control device based on a feedback mechanism, comprising: A furnace combustion state parameter detection module is used to detect furnace combustion state parameter signals; Raman coal quality online detection module, used to detect coal quality and coal flow signals; EPR detection module, used to detect free radical species and concentration signals; A network interface, used for receiving the furnace combustion state detection parameter signal, the coal quality and coal flow signal, and the free radical type and concentration signal, and outputting a receiving signal; A comparison module, used for processing and analyzing the received signal, comparing the received signal with a preset combustion state threshold, and outputting an initial comparison result to evaluate the current combustion state; A model prediction control module is used to analyze the received signal, predict the change trend of each parameter in the combustion process and output a real-time prediction signal; A server, connected to the comparison module and the model prediction control module respectively, for responding to output signals of the comparison module and the model prediction control module to control and adjust the combustion system within a limited control range; The closed-loop control module is used to continuously optimize the feedforward control strategy and feedback control strategy to adapt to various disturbances and changes in the combustion process.

[0017] In a fourth aspect, the present invention further provides an electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the program, an intelligent combustion control method based on a feedback mechanism as described above is implemented.

[0018] In a fifth aspect, the present invention further provides a non-transitory computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements any of the above-described intelligent combustion control methods based on a feedback mechanism.

[0019] The intelligent combustion control method, system and device based on the feedback mechanism provided by the present invention can accurately evaluate the combustion state and respond quickly by real-time monitoring of furnace combustion state parameters and Raman coal quality online detection signals, so as to achieve stability and optimization of the combustion process. Secondly, the system adopts model predictive control technology, which can predict the changing trend of the combustion process and dynamically adjust the operating parameters of the burner according to the prediction results, so as to achieve precise control of the combustion process. In addition, the system also has high-precision data acquisition and analysis capabilities, and realizes the adjustment of control strategies through intelligent algorithms and expert systems, further improving the combustion efficiency and stability. At the same time, the adjustment of the system's feedforward and feedback control strategies improves the effectiveness and adaptability of the control strategies, adapts to the combustion characteristics of different types of coal, reduces the emission of pollutants such as nitrogen oxides, and meets environmental protection requirements. Finally, the automation and intelligent characteristics of the system reduce manual intervention, improve the operating efficiency and reliability of combustion equipment, and provide a more efficient, environmentally friendly and intelligent solution for industrial combustion equipment.

[0020] The present invention can realize the early prediction and advance adjustment of multiple key variables, so as to keep the boiler in the best combustion state and improve the combustion efficiency of the boiler. BRIEF DESCRIPTION OF THE DRAWINGS

[0021] In order to more clearly illustrate the technical solutions in the present invention or the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0022] Figure 1 This is one of the flow charts of the intelligent combustion control method based on the feedback mechanism provided by the present invention; Figure 2 This is the second flow chart of the intelligent combustion control method based on the feedback mechanism provided by the present invention; Figure 3 It is the overall structural diagram of the combustion system provided by the present invention; Figure 4 It is a structural schematic diagram of an intelligent combustion control system based on a feedback mechanism provided by the present invention; Figure 5 It is a structural schematic diagram of the electronic device provided by the present invention. DETAILED DESCRIPTION

[0023] In order to make the purpose, technical solution and advantages of the present invention clearer, the technical solution of the present invention will be clearly and completely described below in conjunction with the drawings of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0024] In view of the problems existing in the prior art, the present invention proposes an intelligent combustion control method based on a feedback mechanism to achieve the stability and optimization of the combustion process, so as to improve the combustion efficiency and reduce the emission of pollutants.

[0025] Figure 1 is one of the flow charts of the intelligent combustion control method based on the feedback mechanism provided by the embodiment of the present invention, such as Figure 1 As shown, including: Step 100: Acquire a furnace combustion detection signal set of a combustion system, pre-process and analyze the furnace combustion detection signal set to obtain a processed signal set; Step 200: Compare the processed signal set with a preset combustion state threshold to obtain an initial comparison result, and adopt a feedforward control strategy to perform a pre-coarse adjustment on the combustion system according to the initial comparison result; Step 300: obtaining a real-time detection signal of the combustion system after the pre-coarse adjustment, predicting the real-time detection signal by a model prediction control module using a preset constraint condition, and outputting a real-time prediction signal, wherein the preset constraint condition is determined by a combustion process state matrix and an objective evaluation function in a future preset period of time; Step 400: If it is determined that the combustion state of the combustion system deviates from the preset target, a feedback control strategy is triggered to adjust the combustion state to within a preset reasonable range; Step 500: Monitor the combustion state in real time through a closed-loop control system, execute the feedforward control strategy and the feedback control strategy, and continuously optimize and adjust the combustion system.

[0026] Specifically, the overall logic is as follows Figure 2 As shown, including: The furnace combustion state parameter signal, Raman coal quality online detection signal and EPR detection free radical signal are received through the network interface, compared with the preset combustion state threshold, and the feedforward control strategy is adopted to control and adjust the air supply system, powder feeding system and burner. At the same time, the input signal variable is fuzzy processed, and the reasoning and prediction analysis are carried out according to the fuzzy control rules formulated by the intelligent combustion model. The acquired signal is analyzed, the change trend of each parameter in the combustion process is predicted and the predicted value is output as the adjustment threshold to limit the control adjustment range, and the preset threshold is corrected at the same time. The server dynamically adjusts the operating parameters and structural parameters of the burner, including: primary and secondary air volume and ratio, air-powder ratio, burner swirl blade angle, nozzle injection angle, etc., to achieve the control effect of air-powder distribution and dynamic adaptation of the burner adjustment mechanism. The adjustment of the actuator affects the key parameter detection system. When the key parameters reach the normal range, the actuator will no longer be adjusted, thereby realizing feedback regulation. Through the closed-loop control system, the feedforward and feedback control strategies are continuously optimized to adapt to various disturbances and changes that may occur in the combustion process.

[0027] The present invention can realize the early prediction and advance adjustment of multiple key variables, so as to keep the boiler in the best combustion state and improve the combustion efficiency of the boiler.

[0028] In one embodiment, when analyzing and processing received signals, the network interface of the present invention uses an advanced filtering algorithm to perform denoising on the signals to eliminate interference during the measurement process and ensure the stability of the control system.

[0029] At the same time, the network interface also uses data fusion technology to comprehensively process signals from different sources to improve the accuracy of combustion state assessment.

[0030] It can be understood that the network interface adopts a high-speed communication protocol to ensure the real-time reception and processing of a large amount of combustion status data, while also having data encryption and security guarantees to protect the stable operation of the system and prevent data leakage.

[0031] In one embodiment, the feedforward control strategy in the present invention is to use the furnace combustion state parameter signal, Raman online detection signal, and EPR detection signal that are used to evaluate the current combustion state results and then calculated by the server for the input of adjustment parameters of the air supply controller, powder supply controller, and burner controller, that is, to perform pre-coarse adjustment of the controller parameters.

[0032] In one embodiment, the model predictive control module (MPC) of the present invention performs real-time analysis on the acquired signal, establishes a state matrix of the combustion process in the future through prediction model derivation, and designs an objective function to evaluate the quality of the future combustion state.

[0033] Among them, the state matrix is ​​the nonlinear equation of the model converted into , In the form of , U represents the matrix of input parameters, Y represents the matrix of output parameters, X represents the matrix of intermediate quantities, A, B(X), C(X), and D(X) represent the matrices of coefficients converted from the model, and the prediction time is set in the model for prediction.

[0034] The model predictive control module designs a rolling optimization objective function , Indicates the amount of coal fed. Indicates burner parameters, Indicates the air supply volume. It indicates the difference between the coal quantity given by the coal feeding controller and the coal feeding instruction of the unit. Indicates the difference between the burner controller parameter and the unit command. Indicates the coal feeding instruction given by the unit. Indicates the burner command given by the unit. Indicates the air supply volume instruction given by the unit.

[0035] The model predictive control module also designs a multi-objective optimization objective function ,in It represents the difference between the optimized NOx concentration and the NOx concentration calculated by the unit. It represents the difference between the optimized boiler combustion efficiency and the efficiency calculated by the unit. Indicates the Nox concentration calculated by the unit, Indicates the boiler combustion efficiency calculated for the unit.

[0036] In one embodiment, the feedback control strategy in the present invention utilizes the combustion state generated after the air supply controller, powder feeding controller, and burner controller work, and obtains the state after combustion through furnace combustion state parameter detection, Raman online detection, and EPR detection, and feeds it back to the server for calculation to perform post-fine adjustment on the air supply controller, powder feeding controller, and burner controller.

[0037] In one embodiment, in combination Figure 2 and Figure 3 As shown, the intelligent combustion control device based on the feedback mechanism provided by the present invention includes: The furnace combustion state parameter detection module is used to detect furnace combustion state parameter signals, including furnace temperature and pressure, flue gas composition, flame image and other signals; Raman coal quality online detection module, used to detect coal quality and coal flow signals; EPR detection module, used to detect free radical species and concentration signals; A network interface, used for receiving the furnace combustion state detection parameter signal, the coal quality and coal flow signal, and the free radical type and concentration signal, and outputting a receiving signal; A comparison module, used for processing and analyzing the received signal, comparing the received signal with a preset combustion state threshold, and outputting an initial comparison result to evaluate the current combustion state; A model prediction control module is used to analyze the received signal, predict the change trend of each parameter in the combustion process and output a real-time prediction signal; A server, connected to the comparison module and the model prediction control module respectively, for responding to output signals of the comparison module and the model prediction control module to control and adjust the combustion system within a limited control range; The closed-loop control module is used to continuously optimize the feedforward control strategy and feedback control strategy to adapt to various disturbances and changes in the combustion process.

[0038] Among them, the model predictive control module also includes linear and discretization processing of the combustion process, and setting constraints on control outputs such as speed and acceleration to improve the accuracy of prediction and the precision of control.

[0039] The collection and analysis of furnace combustion state parameters and Raman coal quality online detection signals are achieved through high-precision sensors and data analysis algorithms to ensure the accuracy and real-time nature of the data.

[0040] The adjustment of feedforward control strategy and feedback control strategy is realized through intelligent algorithm or expert system to ensure the effectiveness and adaptability of control strategy.

[0041] The server includes a user interface for displaying combustion status information, adjusting preset thresholds, monitoring the control process, etc. The server also has cloud computing capabilities and can handle large-scale data analysis and computing tasks, while supporting multi-user access and remote monitoring functions, making it easy for operators to monitor and adjust the combustion process in real time.

[0042] The controller of the combustion system also includes a user interface for displaying combustion status information, adjusting preset thresholds, monitoring the control process, etc., to improve the convenience of user operation and the intuitiveness of system monitoring.

[0043] The combustion system also includes an actuator connected to the controller, which is used to adjust the operation of the air supply system and the powder supply system according to the instructions of the controller to achieve direct control and execution of the combustion process.

[0044] In summary, the intelligent combustion control method and system based on the feedback mechanism proposed in the present invention receives the furnace combustion state parameters and the Raman coal quality online detection signal, compares them with the preset threshold value, and adopts the feedforward control strategy to control and adjust the air supply system and the powder feeding system, so as to achieve high-precision combustion control and optimize combustion efficiency and emissions. The acquired signal is analyzed by model predictive control to predict the changing trend of the combustion process, and the operating parameters of the burner are dynamically adjusted to achieve rapid response to load changes and improve the dynamic performance of the combustion system. Through real-time monitoring and precise control, stable combustion is ensured under low load and the generation of nitrogen oxides NOx is reduced. Through the closed-loop control system, the feedforward and feedback control strategies are continuously optimized to adapt to various disturbances and changes that may occur in the combustion process.

[0045] The intelligent combustion control system based on the feedback mechanism provided by the present invention is described below. The intelligent combustion control system based on the feedback mechanism described below and the intelligent combustion control method based on the feedback mechanism described above can be referred to each other.

[0046] Figure 4 is a schematic diagram of the structure of an intelligent combustion control system based on a feedback mechanism provided by an embodiment of the present invention, such as Figure 4 As shown, it includes: a preprocessing module 41, a feedforward adjustment module 42, a prediction module 43, a feedback adjustment module 44 and a closed-loop adjustment module 45, wherein: The preprocessing module 41 is used to obtain the furnace combustion detection signal set of the combustion system, preprocess and analyze the furnace combustion detection signal set to obtain a processed signal set; the feedforward adjustment module 42 is used to compare the processed signal set with the preset combustion state threshold to obtain an initial comparison result, and according to the initial comparison result, adopt the feedforward control strategy to perform pre-rough adjustment of the combustion system; the prediction module 43 is used to obtain the real-time detection signal of the combustion system after the pre-rough adjustment, and the model prediction control module uses the preset constraint conditions to predict the real-time detection signal and output the real-time prediction signal, and the preset constraint conditions are determined by the combustion process state matrix and the target evaluation function in the future preset time period; the feedback adjustment module 44 is used to trigger the feedback control strategy if it is determined that the combustion state of the combustion system deviates from the preset target, and adjust the combustion state to a preset reasonable range; the closed-loop adjustment module 45 is used to monitor the combustion state in real time through a closed-loop control system, execute the feedforward control strategy and the feedback control strategy, and continuously optimize and adjust the combustion system.

[0047] Figure 5 An example of a physical structure diagram of an electronic device is shown in FIG. Figure 5As shown, the electronic device may include: a processor (processor) 510, a communication interface (Communications Interface) 520, a memory (memory) 530 and a communication bus 540, wherein the processor 510, the communication interface 520, and the memory 530 communicate with each other through the communication bus 540. The processor 510 can call the logic instructions in the memory 530 to execute an intelligent combustion control method based on a feedback mechanism, which includes: obtaining a furnace combustion detection signal set of the combustion system, preprocessing and analyzing the furnace combustion detection signal set to obtain a processed signal set; comparing the processed signal set with a preset combustion state threshold to obtain an initial comparison result, and based on the initial comparison result, using a feedforward control strategy to perform a pre-rough adjustment on the combustion system; obtaining a real-time detection signal of the combustion system after the pre-rough adjustment, and using a model prediction control module to predict the real-time detection signal using preset constraints, and outputting a real-time prediction signal, wherein the preset constraints are determined by a combustion process state matrix and a target evaluation function in a future preset period of time; if it is determined that the combustion state of the combustion system deviates from a preset target, triggering a feedback control strategy to adjust the combustion state to a preset reasonable range; monitoring the combustion state in real time through a closed-loop control system, executing the feedforward control strategy and the feedback control strategy, and continuously optimizing and adjusting the combustion system.

[0048] In addition, the logic instructions in the above-mentioned memory 530 can be implemented in the form of a software functional unit and can be stored in a computer-readable storage medium when it is sold or used as an independent product. Based on such an understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art or the part of the technical solution, can be embodied in the form of a software product, and the computer software product is stored in a storage medium, including a number of instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present invention. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), disk or optical disk, etc. Various media that can store program codes.

[0049] On the other hand, the present invention also provides a non-transitory computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, is implemented to execute the intelligent combustion control method based on the feedback mechanism provided by the above-mentioned methods, the method comprising: obtaining a furnace combustion detection signal set of the combustion system, preprocessing and analyzing the furnace combustion detection signal set to obtain a processed signal set; comparing the processed signal set with a preset combustion state threshold to obtain an initial comparison result, and according to the initial comparison result, using a feedforward control strategy to perform a pre-coarse adjustment on the combustion system; obtaining a real-time detection signal of the combustion system after the pre-coarse adjustment, and using a model prediction control module to predict the real-time detection signal using preset constraints, and outputting a real-time prediction signal, wherein the preset constraints are determined by a combustion process state matrix and an objective evaluation function in a future preset period of time; if it is determined that the combustion state of the combustion system deviates from a preset target, triggering a feedback control strategy to adjust the combustion state to a preset reasonable range; monitoring the combustion state in real time through a closed-loop control system, executing the feedforward control strategy and the feedback control strategy, and continuously optimizing and adjusting the combustion system.

[0050] The device embodiments described above are merely illustrative, wherein the units described as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, they may be located in one place, or they may be distributed on multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the scheme of this embodiment. Ordinary technicians in this field can understand and implement it without paying creative labor.

[0051] Through the description of the above implementation methods, those skilled in the art can clearly understand that each implementation method can be implemented by means of software plus a necessary general hardware platform, and of course, can also be implemented by hardware. Based on this understanding, the above technical solution is essentially or the part that contributes to the prior art can be embodied in the form of a software product, and the computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, a disk, an optical disk, etc., including a number of instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to execute the methods described in each embodiment or some parts of the embodiments.

[0052] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit it. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. An intelligent combustion control method based on feedback mechanism, characterized in that: include: Acquire a furnace combustion detection signal set of the combustion system, pre-process and analyze the furnace combustion detection signal set to obtain a processed signal set; Comparing the processed signal set with a preset combustion state threshold to obtain an initial comparison result, and using a feedforward control strategy to perform a pre-coarse adjustment on the combustion system according to the initial comparison result; Acquire the real-time detection signal of the combustion system after the pre-coarse adjustment, predict the real-time detection signal by the model prediction control module using preset constraints, and output a real-time prediction signal, wherein the preset constraints are determined by the combustion process state matrix and the target evaluation function in the future preset period; If it is determined that the combustion state of the combustion system deviates from the preset target, a feedback control strategy is triggered to adjust the combustion state to a preset reasonable range; The combustion state is monitored in real time through a closed-loop control system, the feedforward control strategy and the feedback control strategy are executed, and the combustion system is continuously optimized and adjusted.

2. The intelligent combustion control method based on feedback mechanism according to claim 1 is characterized in that: Acquire a furnace combustion detection signal set of the combustion system, pre-process and analyze the furnace combustion detection signal set to obtain a processed signal set, including: Receiving furnace combustion state parameter signals, Raman online detection signals and EPR detection signals through the network interface of the combustion system; Based on a filtering algorithm, the furnace combustion state parameter signal, the Raman online detection signal and the EPR detection signal are subjected to denoising processing to obtain a plurality of filtered signals; Data fusion is performed on the multiple filtered signals to obtain the processed signal set.

3. The intelligent combustion control method based on feedback mechanism according to claim 2 is characterized in that: The feedforward control strategy includes: Get the current combustion status result; Inputting the furnace combustion state parameter signal, the Raman online detection signal and the EPR detection signal corresponding to the current combustion state result into a server for calculation to obtain a set of adjustment parameters; The adjustment parameter set is respectively input into the air supply controller, the powder supply controller and the burner controller in the combustion system, and a real-time detection signal of the combustion system after the pre-coarse adjustment is output.

4. The intelligent combustion control method based on feedback mechanism according to claim 1 is characterized in that: The future preset period combustion process state matrix includes: Among them, U represents the matrix of input parameters, Y represents the matrix of output parameters, A, B(X), C(X) and D(X) represent the coefficient matrices transformed by the model, and predictions are made within a preset period in the future.

5. The intelligent combustion control method based on feedback mechanism according to claim 1 is characterized in that: The objective evaluation function includes a rolling optimization objective function and a multi-objective optimization objective function; The rolling optimization objective function for: in, Indicates the amount of coal fed. Indicates burner parameters, Indicates the air supply volume. It indicates the difference between the coal quantity given by the coal feeding controller and the coal feeding instruction of the unit. Indicates the difference between the burner controller parameter and the unit command. Indicates the coal feeding instruction given by the unit. Indicates the burner command given by the unit. Indicates the air supply volume instruction given by the unit; The multi-objective optimization objective function for: in, It represents the difference between the optimized NOx concentration and the NOx concentration calculated by the unit. It represents the difference between the optimized boiler combustion efficiency and the efficiency calculated by the unit. Indicates the Nox concentration calculated by the unit, Indicates the boiler combustion efficiency calculated for the unit.

6. The intelligent combustion control method based on feedback mechanism according to claim 3 is characterized in that: The feedback control strategy includes: Obtaining combustion state feedback signals generated by the air supply controller, the powder supply controller and the burner controller; After calculating the combustion state feedback signal through the server, a new furnace combustion state parameter signal, a Raman online detection signal and an EPR detection signal are output, and fed back to the air supply controller, the powder supply controller and the burner controller for post-fine adjustment.

7. An intelligent combustion control system based on a feedback mechanism, based on the intelligent combustion control method based on a feedback mechanism as claimed in any one of claims 1 to 6, characterized in that: include: A preprocessing module, used to obtain a furnace combustion detection signal set of the combustion system, preprocess and analyze the furnace combustion detection signal set to obtain a processed signal set; A feedforward adjustment module, used for comparing the processed signal set with a preset combustion state threshold to obtain an initial comparison result, and adopting a feedforward control strategy to perform a forward rough adjustment on the combustion system according to the initial comparison result; A prediction module, used for obtaining a real-time detection signal of the combustion system after the pre-coarse adjustment, and the model prediction control module predicts the real-time detection signal using a preset constraint condition, and outputs a real-time prediction signal, wherein the preset constraint condition is determined by a combustion process state matrix and an objective evaluation function in a future preset period of time; A feedback adjustment module is used to trigger a feedback control strategy to adjust the combustion state to a preset reasonable range if it is determined that the combustion state of the combustion system deviates from a preset target; The closed-loop adjustment module is used to monitor the combustion state in real time through a closed-loop control system, execute the feedforward control strategy and the feedback control strategy, and continuously optimize and adjust the combustion system.

8. An intelligent combustion control device based on feedback mechanism, used to execute the intelligent combustion control method based on feedback mechanism as claimed in any one of claims 1 to 6, characterized in that: include: A furnace combustion state parameter detection module is used to detect furnace combustion state parameter signals; Raman coal quality online detection module, used to detect coal quality and coal flow signals; EPR detection module, used to detect free radical species and concentration signals; A network interface, used for receiving the furnace combustion state detection parameter signal, the coal quality and coal flow signal, and the free radical type and concentration signal, and outputting a receiving signal; A comparison module, used for processing and analyzing the received signal, comparing the received signal with a preset combustion state threshold, and outputting an initial comparison result to evaluate the current combustion state; A model prediction control module is used to analyze the received signal, predict the change trend of each parameter in the combustion process and output a real-time prediction signal; A server, connected to the comparison module and the model prediction control module respectively, for responding to output signals of the comparison module and the model prediction control module to control and adjust the combustion system within a limited control range; The closed-loop control module is used to continuously optimize the feedforward control strategy and feedback control strategy to adapt to various disturbances and changes in the combustion process.

9. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein: When the processor executes the program, the intelligent combustion control method based on the feedback mechanism as described in any one of claims 1 to 6 is implemented.

10. A non-transitory computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the intelligent combustion control method based on the feedback mechanism as claimed in any one of claims 1 to 6 is implemented.

Images