Intelligent power plant boiler combustion optimization method, system and equipment and storage medium

Abstract

The invention discloses an intelligent power plant boiler combustion optimization method, system and device and a storage medium, and relates to the technical field of intelligent power plant automatic control and energy management, and the method comprises the steps: building a boiler combustion model based on boiler operation parameters and historical working condition data; through data interaction with a DCS, boiler combustion real-time operation parameters are obtained, simulation optimization is executed according to a boiler combustion model, and air distribution proportion, ammonia spraying amount and air-coal ratio parameters are generated; real-time combustion adjustment is executed according to a simulation optimization result, and self-adaptive adjustment of the oxygen amount and the smoke temperature is completed under different load and coal quality conditions; and an optimization result is fed back to the DCS for control instruction execution, and online correction and verification are carried out in the boiler combustion model. According to the method, through closed-loop linkage of the boiler combustion model and the DCS, self-adaptive optimization and online correction of combustion parameters are achieved, the oxygen amount and the smoke temperature are dynamically regulated and controlled, the model is kept consistent with the working condition, and the combustion stability and energy efficiency of the boiler are improved.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of intelligent power plant automation control and energy management, in particular to a boiler combustion optimization method, system, device and storage medium for intelligent power plant. BACKGROUND

[0002] With the promotion of intelligent power plant construction and digital transformation, the boiler combustion control of thermal power units gradually evolves from traditional experience adjustment mode to intelligent and refined control. In the prior art, a distributed control system (DCS) is generally used to centrally monitor and close-loop adjust the boiler operating parameters, and the wind-coal ratio, air distribution ratio and ammonia injection amount are set to maintain stable combustion and meet emission standards. At the same time, with the improvement of sensor technology and industrial data acquisition technology, real-time sampling and trend analysis of combustion parameters can provide data support for combustion efficiency optimization, and some advanced power plants have begun to introduce mechanism modeling and artificial intelligence algorithms to realize data-driven combustion optimization control. However, overall, the current combustion adjustment is still at the stage of static parameter setting and single-point optimization, and lacks the ability of full-process dynamic prediction and self-adaptive regulation.

[0003] However, in actual operation, the boiler combustion process is affected by many uncertain factors such as coal quality fluctuation, load change and equipment aging, and the traditional DCS adjustment logic cannot reflect the dynamic characteristics of complex combustion conditions in real time, which easily leads to problems such as high oxygen content, uneven smoke temperature distribution and NOx emission exceeding the standard. At the same time, the existing combustion modeling mostly uses single mechanism model or static neural network model, which cannot realize online correction and verification of parameters in real-time operation, resulting in gradual decline of model accuracy and difficulty in maintaining effective optimization results for a long time. In view of the above problems, it is urgent to develop an intelligent power plant boiler combustion optimization control method combining digital twin technology, which can build a combustion digital twin model synchronized with the actual working condition, perform simulation optimization, real-time adjustment and online correction, and realize dynamic optimization and accurate control of combustion under different load and coal quality conditions. SUMMARY

[0004] In view of the above problems, the present application is proposed.

[0005] Therefore, the technical problem solved by the present application is that the existing boiler combustion optimization control method has the problems of insufficient combustion model accuracy, inability to reflect the combustion deviation caused by coal quality and load change in real time, inability to continuously correct the optimization results, and lag of control parameter update.

[0006] To solve the above technical problems, the present application provides the following technical solutions: a smart power plant boiler combustion optimization method, comprising: establishing a boiler combustion model based on boiler operating parameters and historical operating condition data; obtaining real-time operating parameters of the boiler combustion through data interaction with a DCS, performing simulation optimization according to the boiler combustion model, and generating air distribution ratio, ammonia injection amount, and air-coal ratio parameters; performing real-time combustion adjustment according to the simulation optimization results, and completing adaptive adjustment of oxygen content and flue gas temperature under different load and coal quality conditions; feeding back the optimization results to the DCS for control instruction execution, and online correction and verification in the boiler combustion model.

[0007] As a preferred scheme of the smart power plant boiler combustion optimization method, the establishment of the boiler combustion model comprises: combining mechanism modeling and neural network modeling, using boiler operating parameters and historical operating condition data to construct a multivariate mapping relationship between coal quantity, primary air quantity, secondary air quantity, oxygen content, steam temperature, and flue gas temperature, and calibrating combustion parameter weights and correlation coefficients through boiler combustion model training.

[0008] As a preferred scheme of the smart power plant boiler combustion optimization method, the simulation optimization according to the boiler combustion model comprises: inputting real-time operating parameters of the boiler into the boiler combustion model, performing simulation calculation on the combustion condition, and using a genetic algorithm to optimize and solve the coal quantity, primary air quantity, secondary air quantity, and ammonia injection amount during the simulation process, to obtain the air distribution ratio and air-coal ratio parameters under the current load and coal quality conditions.

[0009] As a preferred scheme of the smart power plant boiler combustion optimization method, the real-time combustion adjustment according to the simulation optimization results comprises: using the air distribution ratio, ammonia injection amount, and air-coal ratio parameters obtained in the simulation optimization results as combustion adjustment instructions, adjusting the primary air quantity, secondary air quantity, fuel injection quantity, and ammonia injection amount simultaneously according to the furnace temperature, oxygen content, and flue gas composition signals, collecting the main steam temperature, superheater outlet temperature, and flue gas oxygen content in real time during the adjustment process, dynamically updating the model input parameters, and online correcting the combustion state.

[0010] As a preferred scheme of the smart power plant boiler combustion optimization method, the adaptive adjustment of oxygen content and flue gas temperature under different load and coal quality conditions comprises: calculating the corresponding theoretical combustion air quantity based on the real-time load signal and the coal quality parameters of the boiler, dynamically adjusting the total air supply and the air distribution ratio according to the deviation between the theoretical air quantity and the flue gas oxygen content, monitoring the main steam pressure, furnace negative pressure, and flue gas temperature in real time, performing dynamic fitting on the temperature distribution of the combustion zone, and automatically correcting the secondary air quantity and fuel injection rate according to the flue gas oxygen content and flue gas temperature change trend when load changes or coal quality fluctuations are detected.

[0011] As a preferred scheme of the intelligent power plant boiler combustion optimization method, the feedback of the optimization result to the DCS for control instruction execution comprises converting the self-adaptively adjusted air distribution ratio, air-fuel ratio, ammonia injection amount and fuel injection rate into control instruction parameters, distributing the instructions to each air door, coal powder feeding device and ammonia injection valve according to the real-time signals of the boiler operation, and setting execution priority and delay trigger logic in the instruction distribution process to control the main steam pressure, furnace temperature and oxygen content signals to be in a stable interval.

[0012] As a preferred scheme of the intelligent power plant boiler combustion optimization method, the online correction and verification in the boiler combustion model comprises collecting the furnace temperature, steam temperature, oxygen content and flue gas composition signals after the execution of the control instructions, and comparing them with the predicted output of the boiler combustion model in real time, automatically triggering the model parameter correction process when the deviation between the measured parameters and the predicted parameters of the boiler combustion model exceeds the preset threshold, dynamically adjusting the heat release coefficient, air coefficient and fuel reaction rate parameters in the model according to the temperature distribution in the furnace area and the oxygen content trend of the flue gas in the correction process, and after the parameter correction, performing secondary verification on the calculation results of the boiler combustion model and the historical operation samples, calculating the prediction error and updating the weight of the boiler combustion model.

[0013] Another object of the present application is to provide an intelligent power plant boiler combustion optimization system, which can solve the technical problems of model static, parameter lag and inability to adapt to changes in fuel quality in real time in the current traditional boiler combustion control technology through the cooperative operation mechanism of the boiler combustion modeling module, the simulation optimization calculation module, the real-time combustion adjustment module and the online correction and verification module.

[0014] As a preferred scheme of the intelligent power plant boiler combustion optimization system, the scheme comprises a boiler combustion modeling module, a simulation optimization calculation module, a real-time combustion adjustment module and an online correction verification module; the boiler combustion modeling module is used to establish a boiler combustion model based on boiler operation parameters and historical working condition data, to form a boiler combustion model capable of reflecting the characteristics of the boiler combustion by using air volume, coal volume, oxygen volume and temperature, and to provide a calculation basis for subsequent optimization; the simulation optimization calculation module is used to interact with a DCS in real time to obtain current operation state parameters of the boiler, to perform simulation optimization calculation according to the boiler combustion model, to generate optimal air distribution ratio, ammonia injection volume and air-coal ratio, and to guide combustion adjustment; the real-time combustion adjustment module is used to adjust the combustion process of the boiler in real time according to the simulation optimization result, to dynamically correct air volume, coal volume and ammonia injection parameters under different load and coal quality conditions, and to realize adaptive coordinated control of oxygen volume and flue gas temperature; and the online correction verification module is used to collect operation feedback signals after control execution, to compare measured values with model prediction results, to automatically correct model parameters and to re-verify calculation accuracy when the deviation exceeds a threshold value, and to ensure the consistency between the boiler combustion model and actual working conditions.

[0015] Still another object of the present application is to provide an intelligent power plant boiler combustion optimization device comprising a memory and a processor, wherein the memory stores a computer program, and the processor executes the computer program to implement the steps of the intelligent power plant boiler combustion optimization method.

[0016] Still another object of the present application is to provide an intelligent power plant boiler combustion optimization storage medium, which stores a computer program, and the computer program is executed by a processor to implement the steps of the intelligent power plant boiler combustion optimization method.

[0017] The intelligent power plant boiler combustion optimization method provided by the present application can realize quantitative description of the characteristics of the boiler combustion by establishing a boiler combustion model based on boiler operation parameters and historical working condition data, and can provide an accurate model basis for subsequent optimization calculation; can realize automatic combustion parameter optimization and energy efficiency improvement in the control system by interacting with a DCS, performing simulation optimization according to the boiler combustion model, and generating air distribution ratio, ammonia injection volume and air-coal ratio parameters; can guarantee the stability and adaptability of the combustion process by performing real-time combustion adjustment according to the simulation optimization result, and dynamically correcting oxygen volume and flue gas temperature under different load and coal quality conditions; and can form a self-learning closed-loop control mechanism by feeding back the optimization result to the DCS to execute control instructions, and performing online correction verification in the boiler combustion model, so as to keep the consistency between the boiler combustion model and actual working conditions, thereby improving the accurate control ability and combustion efficiency of the system. BRIEF DESCRIPTION OF DRAWINGS

[0018] In order to more clearly illustrate the technical solutions of the embodiments of the present application, the following will briefly introduce the drawings needed to be used in the embodiments description. Obviously, the drawings in the following description only some of the embodiments of the present application, and for those skilled in the art, without creative labor, can also obtain other drawings according to these drawings.

[0019] Figure 1 The overall flow chart of a boiler combustion optimization method for a smart power plant provided in embodiment 1. DETAILED DESCRIPTION

[0020] In order to make the above-mentioned purposes, features and advantages of the present application more apparent and easy to understand, the specific embodiments of the present application will be described in detail below with reference to the drawings of the specification. Obviously, the described embodiments are part of the embodiments of the present application, rather than all the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative labor should be within the scope of protection of the present application.

[0021] Embodiment 1, refer to Figure 1 For an embodiment of the present application, a boiler combustion optimization method for a smart power plant is provided, comprising: S1: establishing a boiler combustion model based on boiler operating parameters and historical working condition data.

[0022] Further, the establishment of the boiler combustion model comprises: using a combination of mechanism modeling and neural network modeling, using boiler operating parameters and historical working condition data to construct a multivariate mapping relationship between coal quantity, primary air quantity, secondary air quantity, oxygen quantity, steam temperature and flue gas temperature, and calibrating the combustion parameter weight and correlation coefficient through boiler combustion model training.

[0023] It should be noted that the boiler combustion model is established based on boiler operating parameters and historical working condition data.

[0024] Specifically, the long-term stored operating data in the boiler control system is called, including key combustion parameters such as coal quantity, primary air quantity, secondary air quantity, oxygen quantity, steam temperature and flue gas temperature, the data is cleaned, denoised and standardized to eliminate measurement point errors and abnormal working condition interference. A combination of mechanism modeling and neural network modeling is used to construct a multivariate mapping relationship between coal quantity, primary air quantity, secondary air quantity, oxygen quantity, steam temperature and flue gas temperature. The mechanism model is used to reflect the thermodynamic constraints and energy balance relationship of the combustion process, and the neural network model is used to capture the complex nonlinear characteristics and dynamic coupling relationship in the combustion process.

[0025] The historical working condition data is divided into a training set and a verification set, the boiler combustion model is trained in multiple rounds of iteration, the neural network weight and bias parameters are optimized through the back propagation algorithm, and the error between the predicted temperature and oxygen content output by the boiler combustion model and the measured values is lower than the set threshold. After training, the parameter calibration process is carried out, the real-time running data of the boiler is used to compare and analyze the model output, the weight and correlation coefficient of the model are automatically corrected according to the error distribution, and finally a mixed combustion model which can reflect the boiler combustion characteristics in real time and adapt to different coal qualities and load changes is formed.

[0026] It should also be noted that the boiler combustion model is constructed by combining mechanism modeling and neural network modeling, and by fusing thermodynamic mechanism and intelligent learning algorithm, the combustion model can not only maintain the physical interpretability of the boiler thermal process, but also capture the complex nonlinear coupling characteristics in the combustion process, thereby significantly improving the fitting accuracy of the model for the boiler operating state under multiple working conditions.

[0027] S2: Through data interaction with the DCS, real-time running parameters of the boiler combustion are obtained, simulation optimization is performed according to the boiler combustion model, and air distribution ratio, ammonia injection amount and air-coal ratio parameters are generated.

[0028] Further, the simulation optimization according to the boiler combustion model includes inputting the real-time running parameters of the boiler into the boiler combustion model, simulating and calculating the combustion condition, and using a genetic algorithm to optimize and solve the coal quantity, primary air quantity, secondary air quantity and ammonia injection quantity in the simulation process, so as to obtain the air distribution ratio and air-coal ratio parameters under the current load and coal quality conditions.

[0029] It should be noted that the real-time running parameters (including fuel type, coal fineness, coal supply quantity, furnace temperature, oxygen content signal, load instruction and primary and secondary air flow signals) collected by the boiler control system are input into the boiler combustion model. The boiler combustion model establishes a partition heat balance equation according to the geometric structure of the boiler furnace and the characteristics of the combustion area, and determines the combustion state through the coupling calculation of the combustion product concentration and temperature distribution.

[0030] The simulation optimization program is executed, and in the simulation calculation process, a genetic algorithm is used to maximize the boiler thermal efficiency and minimize the emission index as the objective function, and the input variables of coal quantity, primary and secondary air quantity and oxygen injection quantity are optimized in multiple dimensions.

[0031] Specifically, the genetic algorithm first generates an initial population for each optimization parameter, iteratively evolves through selection, crossover and mutation operations, calculates the fitness function value of each candidate solution, and the function is composed of combustion efficiency, flue gas temperature deviation, furnace oxygen content deviation and emission index, and after multiple generations of iteration, when the fitness function reaches the convergence condition, the optimal solution parameter group is output, and the optimal air distribution ratio and air-coal ratio under the current boiler load and coal quality conditions are obtained.

[0032] It should be noted that the genetic algorithm replaces the traditional fixed parameter optimization to realize multi-objective adaptive optimization control in the combustion condition, so as to improve the combustion stability and environmental friendliness while taking into account the thermal efficiency and emissions.

[0033] S3: Real-time combustion adjustment is performed according to the simulation optimization result, and adaptive adjustment of oxygen content and flue gas temperature is completed under different loads and coal quality conditions.

[0034] Further, the real-time combustion adjustment according to the simulation optimization result includes that the air distribution ratio, ammonia injection amount and air-coal ratio parameters obtained in the simulation optimization result are taken as combustion adjustment instructions, the primary air quantity, the secondary air quantity, the fuel injection quantity and the ammonia injection amount are synchronously adjusted according to the furnace temperature, oxygen content and flue gas composition signals, the main steam temperature, the superheater outlet temperature and the flue gas oxygen content are collected in real time during the adjustment process, the model input parameters are dynamically updated, and the combustion state is online corrected.

[0035] It should be noted that in the process of executing real-time combustion adjustment, first, the air distribution ratio, oxygen injection amount and air-coal ratio parameters obtained in the simulation optimization result are used to generate combustion adjustment instructions, and the instructions are input into the boiler combustion control system. The boiler combustion control system synchronously adjusts the primary air quantity, the secondary air quantity, the fuel injection quantity and the oxygen injection amount according to the furnace temperature, oxygen content and flue gas composition signals to realize dynamic matching of the combustion condition.

[0036] During the adjustment process, the main steam temperature, the superheater outlet temperature and the flue gas oxygen content signals are collected in real time, the collected operating parameters are fed back to the boiler combustion model, the boiler combustion model input parameters are dynamically updated, and the combustion state is online corrected.

[0037] It should be noted that through the dynamic feedback adjustment mechanism, the combustion model can maintain accuracy and real-time performance under different loads and operating conditions, ensure that the combustion condition is always in the optimal control state, and realize continuous optimization and steady-state operation control of the boiler combustion process.

[0038] Further, the adaptive adjustment of oxygen content and flue gas temperature under different loads and coal quality conditions includes that based on the real-time load signal and the coal quality parameters of the boiler, the corresponding theoretical combustion air quantity is calculated, the total air supply quantity and the air distribution ratio are dynamically adjusted according to the deviation of the theoretical air quantity and the flue gas oxygen content, the main steam pressure, the furnace negative pressure and the flue gas temperature are monitored in real time, the dynamic fitting of the combustion zone temperature distribution is performed, and when the load change or the coal quality fluctuation is detected, the secondary air quantity and the fuel injection rate are automatically corrected according to the flue gas oxygen content and the flue gas temperature change trend.

[0039] ​It should be noted that in the process of self-adaptive adjustment of oxygen content and flue gas temperature under different loads and coal quality conditions, based on the real-time load signal and the coal quality parameters of the boiler, the corresponding theoretical combustion air quantity is calculated, and the deviation value of the theoretical air quantity and the oxygen content of the flue gas is obtained. The control system dynamically adjusts the total air supply and the air distribution ratio according to the deviation, so that the combustion air matches the actual fuel supply.

[0040] By real-time monitoring of parameters such as main steam pressure, furnace negative pressure and flue gas temperature, the temperature distribution change of the combustion zone is obtained, and the dynamic fitting of the temperature field of the combustion zone is carried out. When the boiler load change or coal quality fluctuation is detected, the secondary air quantity and the fuel supply rate are automatically corrected according to the change trend of the oxygen content and the flue gas temperature, so as to realize the self-adaptive adjustment of the combustion condition, and keep the consistency of the combustion stability and the thermal efficiency under different operating loads and coal quality conditions.

[0041] It should be further noted that by coupling the theoretical combustion model with the actual operation signal to form a closed-loop self-adjusting structure, unlike the traditional control method which only relies on experience curve or fixed threshold, the two-way dynamic matching of combustion air quantity and fuel supply is realized.

[0042] S4: The optimization result is fed back to the DCS for control instruction execution, and is online corrected and verified in the boiler combustion model.100.

[0043] Further, the feedback of the optimization result to the DCS for control instruction execution includes converting the self-adaptive adjusted air distribution ratio, air-fuel ratio, ammonia injection amount and fuel supply rate into control instruction parameters, and executing instruction distribution to each air door, coal powder feeding device and ammonia injection valve according to the real-time signal of the boiler operation. In the instruction distribution process, the execution priority and the delay trigger logic are set to control the main steam pressure, the furnace temperature and the oxygen content signal to be in the stable interval.

[0044] It should be noted that in the process of feeding back the optimization result to the DCS for control instruction execution, the self-adaptive adjusted air distribution ratio, air-fuel ratio, ammonia injection amount and fuel supply rate are first converted into control instruction parameters and input into the DCS control system. The DCS system executes instruction distribution to each air door, coal powder feeding device and ammonia injection valve according to the real-time signal of the boiler operation, so that the combustion adjustment instruction can accurately act on the corresponding execution mechanism.

[0045] In the instruction distribution process, the control system sets the execution priority and the delay trigger logic according to the output result of the optimization model to prevent system oscillation caused by simultaneous adjustment of multiple parameters. The DCS system monitors the main steam pressure, the furnace temperature and the oxygen content signal in real time, judges whether they are in the stable interval, and automatically fine tunes when they deviate, to ensure that the adjustment response of the combustion process matches the stability of the system operation.

[0046] It should be noted that the real-time collaborative closed loop between the combustion optimization result and the control system execution layer is realized, so that the combustion control is no longer dependent on static empirical parameters, but automatically adjusts the execution instruction according to the model dynamic output result, thereby improving the accuracy and response speed of the combustion regulation from the source.

[0047] Further, the online correction and verification 100 in the boiler combustion model includes collecting the furnace temperature, steam temperature, oxygen content and flue gas composition signals after the execution of the control instruction, and comparing them with the boiler combustion model prediction output in real time. When the deviation between the detected parameters and the boiler combustion model prediction parameters is detected to exceed the preset threshold, the model parameter correction process is automatically triggered. In the correction process, the heat release coefficient, air coefficient and fuel reaction rate parameters in the model are dynamically adjusted according to the furnace area temperature distribution and the oxygen content trend of the flue gas. After the parameter correction, the boiler combustion model calculation result is verified again with the historical operation samples, the prediction error is calculated, and the boiler combustion model weight is updated.

[0048] It should be noted that in the process of online correction and verification 100 in the boiler combustion model, the furnace temperature, steam temperature, oxygen content and flue gas composition signals after the execution of the control instruction are collected, and these real-time detection parameters are compared with the boiler combustion model prediction output. When the deviation between the detected parameters and the model prediction parameters is detected to exceed the preset threshold, the model parameter correction process is automatically triggered.

[0049] In the correction process, the heat release coefficient, air coefficient and fuel reaction rate parameters in the boiler combustion model are dynamically adjusted according to the furnace area temperature distribution and the oxygen content trend of the flue gas, so as to ensure that the boiler combustion model can accurately reflect the actual combustion condition. After the correction is completed, the updated boiler combustion model calculation result is verified again with the historical operation samples, the prediction error is calculated, and the boiler combustion model weight is updated accordingly, so as to realize the self-adaptive optimization and continuous calibration of the boiler combustion model parameters, and make the prediction result consistent with the actual operation state.

[0050] It should be noted that by introducing the online correction and verification mechanism in the boiler combustion model, the dynamic consistency between the combustion model and the actual condition is realized. Unlike the traditional fixed parameter or periodic correction combustion model, the present application can automatically trigger the model parameter correction process when the deviation between the detected parameters such as furnace temperature, steam temperature, oxygen content and flue gas composition and the model prediction value is detected.

[0051] Embodiment 2 is an embodiment of the present application, which provides a smart power plant boiler combustion optimization system, including a boiler combustion modeling module, a simulation optimization calculation module, a real-time combustion regulation module, and an online correction and verification module.

[0052] The boiler combustion modeling module is configured to establish a boiler combustion model based on boiler operating parameters and historical working condition data, and to form a boiler combustion model reflecting the combustion characteristics of the boiler by using air volume, coal volume, oxygen volume and temperature, thereby providing a calculation basis for subsequent optimization.

[0053] The simulation optimization calculation module is configured to interact with the DCS in real time to obtain current operating state parameters of the boiler, to perform simulation optimization calculation according to the boiler combustion model, and to generate optimal air distribution ratio, ammonia injection volume and air-coal ratio, thereby guiding combustion adjustment.

[0054] The real-time combustion adjustment module is configured to adjust the combustion process of the boiler in real time according to the simulation optimization results, to dynamically correct air volume, coal volume and ammonia injection parameters under different load and coal quality conditions, and to realize adaptive coordinated control of oxygen volume and flue gas temperature.

[0055] The online correction verification module is configured to collect operating feedback signals after control execution, to compare measured values with model prediction results, to automatically correct model parameters and to re-verify calculation accuracy when the deviation exceeds a threshold, thereby ensuring the consistency between the boiler combustion model and actual working conditions.

[0056] The embodiment also provides a computer device including a memory and a processor, the memory storing a computer program, and the processor realizing the intelligent power plant boiler combustion optimization system according to the above embodiment when executing the computer program.

[0057] The embodiment also provides a computer readable storage medium storing a computer program, the computer program being executed by a processor to realize the intelligent power plant boiler combustion optimization system according to the above embodiment.

[0058] If the functions are realized in the form of software function units and sold or used as independent products, the functions can be stored in a computer readable storage medium. Based on this understanding, the technical solutions of the present application or parts of the present application that essentially contribute to the prior art or parts of the technical solutions can be embodied in the form of software products. The computer software product is stored in a storage medium and includes a plurality of instructions for causing a computer device (which can be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the methods described in the embodiments of the present application. The aforementioned storage medium includes a U disk, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk, and various media that can store program codes.

[0059] The logic and / or steps represented in the flow diagrams or otherwise described herein, for example, can be considered as a sequence of executable instructions, and can be embodied in any computer-readable medium for use by or in connection with an instruction execution system, apparatus, or device, such as a computer-based system, processor-containing system, or other system that can fetch the instructions from the instruction execution system, apparatus, or device and execute the instructions. In the context of this specification, a "computer-readable medium" can be any means that can contain, store, communicate, propagate, or transport the program for use by or in connection with the instruction execution system, apparatus, or device. The computer-readable medium can be, for example but not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, device, or propagation medium.

[0060] More specific examples (a non-exhaustive list) of the computer-readable medium include the following: an electrical connection (electronic) having one or more wires, a portable computer diskette (magnetic), a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or Flash memory), an optical fiber, and a portable compact disc read-only memory (CDROM). Additionally, the computer-readable medium can also be paper or another suitable medium upon which the program is printed, as the program can be electronically captured, for example via an optical scanner, then compiled, interpreted, or otherwise processed, and stored in a computer memory in a form that can be later executed by a computer.

[0061] It should be understood that aspects of the application can be implemented in hardware, software, firmware or combinations thereof. In the above embodiments, various steps or methods can be implemented in software or firmware that is stored in memory and executed by a suitable instruction execution system. For example, if implemented in hardware, as in another embodiment, any of the following technologies, known in the art, or combinations thereof, can be used: a discrete logic circuit having logic gates for implementing logic functions upon data signals, an application specific integrated circuit having appropriate combinational logic gates, a programmable gate array (PGA), a field programmable gate array (FPGA), or the like.

[0062] It should be noted that the above-mentioned embodiments are merely used to illustrate the technical solutions of the present application but not limit the present application, and although the present application is described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical solutions of the present application can be modified or equivalent replaced without departing from the spirit and scope of the present application, and all of them should be covered in the scope of the claims of the present application.

Claims

1. A method for optimizing boiler combustion in a smart power plant, characterized in that, include: A boiler combustion model was established based on boiler operating parameters and historical operating data. By interacting with the DCS, real-time operating parameters of boiler combustion are obtained, and simulation optimization is performed based on the boiler combustion model to generate parameters such as air distribution ratio, ammonia injection amount and air-coal ratio. Real-time combustion adjustments are performed based on simulation optimization results to achieve adaptive regulation of oxygen content and flue gas temperature under different loads and coal quality conditions. The optimization results are fed back to the DCS for control command execution, and are corrected and verified online in the boiler combustion model.

2. The intelligent power plant boiler combustion optimization method as described in claim 1, characterized in that: The establishment of the boiler combustion model includes using a combination of mechanistic modeling and neural network modeling, utilizing boiler operating parameters and historical operating data to construct a multivariate mapping relationship between coal quantity, primary air volume, secondary air volume, oxygen quantity, steam temperature and flue gas temperature, and calibrating the weights and correlation coefficients of combustion parameters through boiler combustion model training.

3. The intelligent power plant boiler combustion optimization method as described in claim 1 or 2, characterized in that: The simulation optimization based on the boiler combustion model includes inputting the real-time operating parameters of the boiler into the boiler combustion model, performing simulation calculations on the combustion conditions, and using a genetic algorithm to optimize and solve the coal quantity, primary air quantity, secondary air quantity and ammonia injection quantity during the simulation process to obtain the air distribution ratio and air-coal ratio parameters under the current load and coal quality conditions.

4. The intelligent power plant boiler combustion optimization method as described in claim 3, characterized in that: The real-time combustion adjustment based on the simulation optimization results includes using the air distribution ratio, ammonia injection rate, and air-coal ratio parameters obtained from the simulation optimization results as combustion adjustment commands. Based on the furnace temperature, oxygen content, and flue gas composition signals, the primary air volume, secondary air volume, fuel input rate, and ammonia injection rate are adjusted synchronously. During the adjustment process, the main steam temperature, superheater outlet temperature, and flue gas oxygen content are collected in real time to dynamically update the model input parameters and correct the combustion state online.

5. The intelligent power plant boiler combustion optimization method as described in any one of claims 1, 2, and 4, characterized in that: The adaptive adjustment of oxygen content and flue gas temperature under different load and coal quality conditions includes: calculating the corresponding theoretical combustion air volume based on the boiler's real-time load signal and the coal quality parameters; dynamically adjusting the total air supply and air distribution ratio according to the deviation between the theoretical air volume and the flue gas oxygen content; monitoring the main steam pressure, furnace negative pressure and flue gas temperature in real time; performing dynamic fitting on the temperature distribution in the combustion zone; and automatically correcting the secondary air volume and fuel delivery rate according to the trend of flue gas oxygen content and flue gas temperature changes when load changes or coal quality fluctuations are detected.

6. The intelligent power plant boiler combustion optimization method as described in claim 5, characterized in that: The step of feeding the optimization results back to the DCS for control command execution includes converting the adaptively adjusted air distribution ratio, air-coal ratio, ammonia injection quantity, and fuel delivery rate into control command parameters, and distributing commands to each damper, pulverized coal feeding device, and ammonia injection valve based on the real-time boiler operation signal. During the command distribution process, execution priority and delay trigger logic are set to control the main steam pressure, furnace temperature, and oxygen quantity signals to remain within a stable range.

7. The intelligent power plant boiler combustion optimization method as described in any one of claims 1, 2, 4, and 6, characterized in that: The online correction and verification in the boiler combustion model includes collecting signals of furnace temperature, steam temperature, oxygen content, and flue gas composition after the control command is executed, and comparing them with the predicted output of the boiler combustion model in real time. When the deviation between the measured parameters and the predicted parameters of the boiler combustion model is detected to exceed a preset threshold, the model parameter correction process is automatically triggered. During the correction process, the heat release coefficient, air coefficient, and fuel reaction rate parameters in the model are dynamically adjusted according to the temperature distribution in the furnace area and the oxygen content trend of the flue gas. After the parameter correction is completed, the calculation results of the boiler combustion model are verified a second time with historical operating samples, the prediction error is calculated, and the weights of the boiler combustion model are updated.

8. A smart power plant boiler combustion optimization system, employing the smart power plant boiler combustion optimization method as described in any one of claims 1 to 7, characterized in that: It includes a boiler combustion modeling module, a simulation optimization calculation module, a real-time combustion adjustment module, and an online correction and verification module; The boiler combustion modeling module is used to establish a boiler combustion model based on boiler operating parameters and historical operating data. It uses air volume, coal volume, oxygen volume and temperature to form a boiler combustion model that can reflect the boiler combustion characteristics, providing a calculation basis for subsequent optimization. The simulation optimization calculation module is used to interact with the DCS in real time, obtain the current operating status parameters of the boiler, perform simulation optimization calculations based on the boiler combustion model, and generate the optimal air distribution ratio, ammonia injection amount and air-coal ratio to guide combustion regulation. The real-time combustion adjustment module is used to adjust the boiler combustion process in real time according to the simulation optimization results, and dynamically correct the air volume, coal volume and ammonia injection parameters under different load and coal quality conditions to achieve adaptive and coordinated control of oxygen content and flue gas temperature. The online correction and verification module is used to collect operational feedback signals after control execution, compare the measured values ​​with the model prediction results, and automatically correct the model parameters and re-verify the calculation accuracy when the deviation exceeds the threshold, so as to ensure the continuous consistency between the boiler combustion model and the actual operating conditions.

9. A computer device comprising a memory and a processor, wherein the memory stores a computer program, characterized in that, When the processor executes the computer program, it implements the steps of the intelligent power plant boiler combustion optimization method according to any one of 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 the processor, it implements the steps of the intelligent power plant boiler combustion optimization method according to any one of claims 1 to 7.

Images