Method and system for optimizing operation of a circulating fluidized bed boiler for controlling nitrogen oxides

Abstract

The application belongs to the technical field of electric digital data processing, and particularly relates to a circulating fluidized bed boiler nitrogen oxide control optimization operation method and system. The circulating fluidized bed boiler nitrogen oxide control optimization operation method comprises the following steps: obtaining particle formation of a particle swarm based on a particle swarm algorithm; calculating the fitness of each particle according to a target function; obtaining a historical best cost vector and a population minimum cost vector; calculating the position vector and the velocity vector of the particle after iteration; obtaining the operation parameters and the cost of the corresponding circulating fluidized bed boiler and denitration device according to the position vector of the particle after iteration, and setting the operation parameters. The application automatically finds the optimal operation parameters of the circulating fluidized bed boiler and the denitration device through the particle swarm algorithm, fully considers the coupling effect of boiler combustion and tail denitration in the calculation, and can reduce the coal consumption of the circulating fluidized bed boiler and the consumption of the denitration agent under the given load and the demand of nitrogen oxide emission concentration, so as to minimize the operation cost.

Description

Technical Field

[0001] This invention belongs to the field of electronic digital data processing technology, specifically relating to machine learning methods, and more specifically to a method and system for optimizing the control of nitrogen oxide emissions in a circulating fluidized bed boiler. Background Technology

[0002] Circulating fluidized bed boilers can be compatible with low-calorific-value fuels such as coal gangue and biomass, which are difficult to handle stably by traditional boilers, through fluidized bed combustion mechanism. They maintain a low-temperature combustion environment of 800-900℃, combined with efficient sulfur fixation by limestone in the furnace and significant inhibition of NOx formation.

[0003] However, in the current process of NOx control in circulating fluidized bed boilers, the low-temperature / low excess air coefficient combustion strategy adopted to suppress NOx generation weakens fuel burnout, leading to increased residual carbon and a significant decrease in boiler efficiency. Alternatively, simply increasing combustion intensity can improve efficiency, but it significantly increases NOx generation due to the expansion of local high-temperature zones and uneven pulverized coal concentration in the suspended section (especially when burning high-volatile coal types). Fluctuations in the quality of coal entering the furnace (such as density differences when anthracite and lignite are blended) cause instability in the bed material distribution, which exacerbates the segregation phenomenon, resulting not only incomplete combustion of particles but also the destruction of the reducing atmosphere, leading to the failure of pollutant control. Static adjustment of combustion parameters and air-coal ratio is difficult to adapt to real-time operating conditions, and the lag effect caused by the coupling of air volume and coal volume limits the improvement of combustion efficiency. Furthermore, isolated control of the denitrification process (such as the ammonia injection system only responding to the outlet NOx concentration) leads to uneven mixing due to the complex flow state of flue gas, which increases the risk of ammonia escape and cannot coordinate with the front-end optimization of the combustion process.

[0004] Therefore, there is an urgent need to develop a new method and system for optimizing the operation of nitrogen oxide control in circulating fluidized bed boilers, in order to solve the technical problems of incomplete combustion and high pollutant levels caused by the coupling effect of in-furnace combustion efficiency, nitrogen oxide control and tail-end denitrification equipment during the nitrogen oxide control process.

[0005] It should be noted that the information disclosed in this background section is only for understanding the background technology of this application concept, and therefore, the above description is not considered to constitute prior art information. Summary of the Invention

[0006] This disclosure provides at least one method and system for optimizing the control of nitrogen oxides in a circulating fluidized bed boiler.

[0007] In a first aspect, this disclosure provides a method for optimizing the control of nitrogen oxide emissions in a circulating fluidized bed boiler, comprising: Step S1: Based on a particle swarm optimization algorithm, a host computer obtains particles according to the load, bed temperature, primary and secondary air matching, bed pressure, oxygen content, differential pressure of the suspension section, and the denitrification agent injection flow rate of the circulating fluidized bed boiler to form a particle swarm; Step S2: The host computer calculates the fitness of each particle according to an objective function, and the fitness is a cost value; Step S3: The fitness of each particle is traversed, and the fitness of each particle is compared with the historical best cost value, so that the host computer obtains the historical best cost vector; Step S4: The fitness of each particle is traversed, and the fitness of each particle is compared with the minimum cost, so that the host computer obtains the minimum cost vector of the population; Step S5: The host computer calculates the velocity vector... Step S6: When the host computer determines that the number of iterations is met after iteration, it obtains the load, bed temperature, primary and secondary air matching, bed pressure, oxygen content, suspension section differential pressure, and denitrification agent injection flow rate of the corresponding circulating fluidized bed boiler based on the position vector of the iterated particle; and calculates the cost value according to the objective function, then executes step S8; Step S7: When the host computer determines that the number of iterations is not met after iteration, it executes step S2; Step S8: The host computer sets the operating parameters of the circulating fluidized bed boiler and the denitrification device based on the load, bed temperature, primary and secondary air matching, bed pressure, oxygen content, suspension section differential pressure, and denitrification agent injection flow rate of the circulating fluidized bed boiler obtained from the iterated particle.

[0008] In one optional implementation, the load is L; the bed temperature is T; and the primary and secondary air matching is A. k And k takes the values ​​1, 2, or 3; the bed pressure is B. k And k takes positive integer values; oxygen content is OX. k And k takes positive integer values; the differential pressure of the suspension segment is DP. k And k takes the values ​​1 and 2; the denitrification agent injection flow rate is Q. k And k takes positive integer values; particle i is (L,T,A) k B k OX k DP k Q k ).

[0009] In one alternative implementation, the objective function is configured to calculate the total cost of boiler combustion and pollutant control, i.e., the objective function V=f(L,T,A) k B k OX k DP k Q kThe system obtains the fitness of each particle, where fitness is a cost value. In the host computer, a deep learning module based on neural networks and a data prediction module perform deep learning on the historical boiler operating data to obtain a correlation model between boiler operating parameters and costs. The data prediction module then predicts the boiler cost under different operating parameters. In other words, the deep learning module in the host computer periodically performs self-learning analysis on the historical boiler operating data to obtain the relationship between cost V and boiler operating parameters (L, T, A). k B k OX k DP k Q k The correlation model between the two; and the correlation model obtained by calling the deep learning module through the data prediction module in the host computer, and based on the boiler operating parameters (L, T, A) provided by each particle i in the particle swarm algorithm. k B k OX k DP k Q k Predictions are made to obtain the fitness of the particle.

[0010] In an optional implementation, step S3 includes: traversing the fitness of each particle; comparing the fitness of each particle with the historical best cost value; and when the fitness of particle i is less than the historical best cost value, replacing the position vector of particle i with the historical best cost vector P. besti .

[0011] In an optional implementation, step S4 includes: traversing the fitness of each particle; comparing the fitness of each particle with the minimum cost value; and when the fitness of particle i is less than the minimum cost value, replacing the position vector of particle i with the population minimum cost vector G. best .

[0012] In one optional implementation, step S5 includes: the velocity vector iteration formula is V i+1 =wV i +c1r1(P besti -X i )+c2r2(G best -X i The iterative formula for the position vector is X. i+1 =X i +V i+1 Where w represents the weights of the particle swarm optimization algorithm, and V... i Let X be the velocity vector of particle i. i Let V be the position vector of particle i, c1 and c2 be learning factors, r1 and r2 be random probability values, and V be the position vector of particle i. i+1Let X be the velocity vector of particle (i+1). i+1 Let be the position vector of particle (i+1).

[0013] In an optional implementation, step S6 includes: the host computer determining whether particle (i+1) satisfies the iteration count; when the host computer determines that the particle satisfies the iteration count after iteration, the host computer determines the iteration count based on the position vector X. i+1 Obtain the corresponding circulating fluidized bed boiler's load L, bed temperature T, and primary and secondary air matching A. k Bed pressure B k Oxygen content (OX) k , suspending differential pressure DP k The denitrification agent injection flow rate Q of the denitrification unit k The cost value V is calculated based on the objective function; the host computer executes step S8.

[0014] Secondly, this disclosure also provides a circulating fluidized bed system, comprising: a host computer, a circulating fluidized bed boiler, and a denitrification device; wherein, based on a particle swarm optimization algorithm, the host computer acquires particles according to the load, bed temperature, primary and secondary air matching, bed pressure, oxygen content, suspension section differential pressure, and denitrification agent injection flow rate of the circulating fluidized bed boiler to form a particle swarm; the host computer calculates the fitness of each particle according to an objective function, and the fitness is a cost value; the fitness of each particle is traversed, and the fitness of each particle is compared with the historically achieved optimal cost value, so that the host computer obtains the historical optimal cost vector; the fitness of each particle is traversed, and the fitness of each particle is compared with the minimum cost, so that the host computer obtains the minimum population cost vector. Cost vector; the host computer calculates the position vector and velocity vector of the particle after iteration based on the velocity vector iteration formula, the position vector iteration formula, the historical best cost vector, and the population minimum cost vector; when the host computer determines that the particle meets the iteration number, it obtains the load, bed temperature, primary and secondary air matching, bed pressure, oxygen content, suspension section differential pressure, and denitrification agent injection flow rate of the corresponding circulating fluidized bed boiler based on the position vector of the particle after iteration, and calculates the cost value according to the objective function; the host computer sets the operating parameters of the circulating fluidized bed boiler and the denitrification device based on the load, bed temperature, primary and secondary air matching, bed pressure, oxygen content, suspension section differential pressure, and denitrification agent injection flow rate of the circulating fluidized bed boiler obtained by the particle after iteration.

[0015] In one alternative implementation, the host computer is adapted to set the operating parameters of the circulating fluidized bed boiler and the denitrification unit using the circulating fluidized bed boiler nitrogen oxide control optimization operation method described above.

[0016] Thirdly, this disclosure also provides a non-transitory readable storage medium storing a program / instruction that, when executed by a processor, implements the steps of the above-described circulating fluidized bed boiler nitrogen oxide control optimization operation method.

[0017] The beneficial effects of this invention are that it automatically finds the optimal operating parameters of circulating fluidized bed boilers and denitrification devices through particle swarm optimization algorithm. At the same time, it fully considers the coupling effect of boiler combustion and tail-end denitrification in the calculation, which can reduce the coal consumption and denitrification agent consumption of circulating fluidized bed boilers under given load and nitrogen oxide emission concentration requirements, thus minimizing operating costs.

[0018] Other features and advantages of the invention will be set forth in the following description, and will be apparent in part from the description, or may be learned by practicing the invention. The objects and other advantages of the invention are realized and obtained through the structures particularly pointed out in the description and the drawings.

[0019] To make the above-mentioned objects, features and advantages of the present invention more apparent and understandable, preferred embodiments are described below in detail with reference to the accompanying drawings. Attached Figure Description

[0020] To more clearly illustrate the specific embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the specific embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are some embodiments of the present invention. For those skilled in the art, other drawings can be obtained from these drawings without creative effort.

[0021] Figure 1 A flowchart of a method for optimizing the control of nitrogen oxides in a circulating fluidized bed boiler, provided as an embodiment of this disclosure; Figure 2 A flowchart of particle iteration is provided for embodiments of this disclosure; Figure 3 This is a schematic diagram of a circulating fluidized system provided in an embodiment of the present disclosure. Detailed Implementation

[0022] To make the objectives, technical solutions, and advantages of the embodiments of the present invention clearer, the technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0023] The terminology used herein is for the purpose of describing specific exemplary configurations only and is not intended to be limiting. As used herein, the singular articles “a,” “an,” and “the” may also be intended to include plural forms unless otherwise clearly stated herein. The terms “comprising,” “including,” and “having” are inclusive and thus specify the presence of features, steps, operations, elements, and / or components, but do not preclude the presence or addition of one or more other features, steps, operations, elements, components, and / or combinations thereof. The method steps, processes, and operations described herein should not be construed as requiring them to be performed in the specific order discussed or shown, unless specifically identified as such. Additional or alternative steps may be employed.

[0024] As used herein, the phrases “in one embodiment,” “according to one embodiment,” “in some embodiments,” etc., generally refer to the fact that a particular feature, structure, or characteristic following the phrase can be included in at least one embodiment of this disclosure. Therefore, a particular feature, structure, or characteristic can be included in more than one embodiment of this disclosure, such that these phrases do not necessarily refer to the same embodiment. As used herein, the terms “example,” “exemplary,” etc., are used to “serve as an example, instance, or illustration.” Any implementation, aspect, or design described herein as “example” or “exemplary” is not necessarily to be construed as preferred or superior to other implementations, aspects, or designs. Rather, the use of the terms “example,” “exemplary,” etc., is intended to present concepts in a specific manner.

[0025] Particle Swarm Optimization (PSO) is a collaborative stochastic search algorithm developed by simulating the foraging behavior of bird flocks. In PSO, each solution to the optimization problem is represented by a bird in the search space, called a "particle," and the optimal solution corresponds to the "cornfield" the flock is searching for. Each particle has a position vector (its location in the solution space) and a velocity vector (determining its next flight direction and speed). It can calculate its fitness value based on the objective function, which can be understood as its distance from the "cornfield." In each iteration, the particles in the population learn not only from their own experience (historical positions) but also from the "experience" of the best particle in the population, thus determining how to adjust and change their flight direction and speed for the next iteration. Through this iterative process, the entire population gradually converges to the optimal solution.

[0026] Research has revealed that current methods for synergistic optimization of combustion and nitrogen oxide emissions in circulating fluidized bed boilers employ three approaches: a combustion optimization control module based on CO monitoring, a reductant total quantity control module based on airflow and other parameter forecasts, and a zoned injection control module based on a zoned injection quantity distribution table. These methods control airflow to optimize boiler combustion efficiency and zoned ammonia injection to achieve uniform mixing of the reductant and flue gas, thereby improving denitrification efficiency. Another approach involves acquiring historical operating data and historical flue gas data to obtain historical denitrification data. Based on this data, an optimal denitrification prediction model is constructed. The ammonia injection device is then adjusted according to the optimal ammonia injection quantity, and the ammonia slip rate is monitored in real time. The ammonia injection device is then corrected and adjusted based on the ammonia slip rate and real-time flue gas data. This achieves precise ammonia injection regulation, maximizing the denitrification effect.

[0027] While the relevant technologies can optimize the control of nitrogen oxides (NOx) in circulating fluidized bed (CFB) boilers, several issues remain unresolved. Firstly, judging boiler combustion efficiency solely based on CO concentration is insufficient and fails to provide a more accurate value; analysis of fly ash and bottom ash carbon content is also necessary. Furthermore, the generation and control of NOx within the furnace depend on numerous operating parameters, necessitating the development of a multi-parameter NOx prediction method (including bed temperature, primary and secondary air matching, bed pressure, and combustion oxygen content). Secondly, the optimization of tail-end denitrification equipment is often overlooked, neglecting in-furnace control. Additionally, existing boilers, especially newly built ones, employ a combination of selective non-catalytic reduction (SNR) and selective catalytic reduction (SCR) denitrification methods, making ammonia injection optimization even more crucial, particularly in scenarios with multiple CFB boilers using parallel cyclone separators. Therefore, a comprehensive approach is required.

[0028] Based on the above research, this disclosure provides a method and system for optimizing the operation of circulating fluidized bed boilers by controlling nitrogen oxides. The method optimizes the operating parameters of the circulating fluidized bed boilers, taking into account the coupled effects of in-furnace combustion efficiency, nitrogen oxide control and tail-end denitrification equipment, while also considering the boiler combustion efficiency and the cost of denitrification agent.

[0029] The shortcomings of the above solutions are the result of the inventor's practical experience and careful research. Therefore, the discovery process of the above problems and the solutions proposed in this disclosure below should be considered as the inventor's contribution to this disclosure.

[0030] It should be noted that similar labels and letters in the following figures indicate similar items. Therefore, once an item is defined in one figure, it does not need to be further defined and explained in subsequent figures.

[0031] The following detailed description of some embodiments of the present invention is provided in conjunction with the accompanying drawings. Unless otherwise specified, the following embodiments and features can be combined with each other.

[0032] like Figures 1 to 3 As shown, at least one embodiment provides a method for optimizing the control of nitrogen oxides in a circulating fluidized bed boiler, comprising: Step S1: Based on the particle swarm optimization algorithm, the host computer obtains particles according to the load, bed temperature, primary and secondary air matching, bed pressure, oxygen content, differential pressure of the suspension section, and the denitrification agent injection flow rate of the circulating fluidized bed boiler to form a particle swarm; Step S2: The host computer calculates the fitness of each particle according to the objective function, and the fitness is a cost value; Step S3: Traverse the fitness of each particle and compare the fitness of each particle with the historical best cost value to obtain the historical best cost vector; Step S4: Traverse the fitness of each particle and compare the fitness of each particle with the minimum cost to obtain the minimum cost vector of the population; Step S5: The host computer iterates the velocity vector... Step S6: When the host computer determines that the number of iterations is met after iteration, it obtains the load, bed temperature, primary and secondary air matching, bed pressure, oxygen content, suspension section differential pressure, and denitrification agent injection flow rate of the corresponding circulating fluidized bed boiler based on the position vector of the iterated particle; and calculates the cost value according to the objective function, then executes step S8; Step S7: When the host computer determines that the number of iterations is not met after iteration, it executes step S2; Step S8: The host computer sets the operating parameters of the circulating fluidized bed boiler and the denitrification device based on the load, bed temperature, primary and secondary air matching, bed pressure, oxygen content, suspension section differential pressure, and denitrification agent injection flow rate of the circulating fluidized bed boiler obtained from the iterated particle.

[0033] Specifically, particle swarm optimization (PSO) can be replaced by genetic algorithms, ant colony optimization (ACO), etc. Taking genetic algorithms as an example, both PSO and genetic algorithms are global optimization algorithms that attempt to simulate the adaptability of an individual population based on natural characteristics. Both start by randomly generating an initial population from the solution space and then search the global solution space, focusing on high-performance parts. However, genetic algorithms have strong global search capabilities but weak local search capabilities, often only obtaining suboptimal solutions rather than optimal solutions.

[0034] In at least one embodiment, the optimal operating parameters of the circulating fluidized bed boiler and the denitrification device are automatically found through the particle swarm optimization algorithm. At the same time, the coupling effect of boiler combustion and tail-end denitrification is fully considered in the calculation. Under the given load and nitrogen oxide emission concentration requirements, the coal consumption and denitrification agent consumption of the circulating fluidized bed boiler can be reduced, so as to minimize the operating cost.

[0035] In at least one embodiment, the load is L; the bed temperature is T; and the primary and secondary air matching is A. k And k takes the values ​​1, 2, or 3; the bed pressure is B. k And k takes positive integer values; oxygen content is OX. k And k takes positive integer values; the differential pressure of the suspension segment is DP. k And k takes the values ​​1 and 2; the denitrification agent injection flow rate is Q. k And k takes positive integer values; particle i is (L,T,A) k B k OX k DP k Q k ).

[0036] Specifically, the concentration of nitrogen oxides is related to bed temperature, primary and secondary air matching, bed pressure, oxygen content, differential pressure in the suspension section, and denitrification agent injection flow rate. By limiting the values ​​of bed temperature, primary and secondary air matching, bed pressure, oxygen content, differential pressure in the suspension section, and denitrification agent injection flow rate, the nitrogen oxide concentration control requirements can be met.

[0037] In at least one embodiment, the objective function is configured to calculate the total cost of boiler combustion and pollutant control, i.e., the objective function V=f(L,T,A) k B k OX k DP k Q k The system obtains the fitness of the particles, where fitness is the cost value. In the host computer, a deep learning module based on neural networks and a data prediction module perform deep learning on the historical boiler operating data to obtain a correlation model between boiler operating parameters and costs. The data prediction module then predicts the boiler cost under different operating parameters. Specifically, the deep learning module in the host computer periodically (preferably every 3 days) performs self-learning analysis on the historical boiler operating data (preferably the historical data from the previous 30 days) to obtain the relationship between cost V and boiler operating parameters (L, T, A). k B k OX k DP k Q k The correlation model between the two; and the correlation model obtained by calling the deep learning module through the data prediction module in the host computer, and based on the boiler operating parameters (L, T, A) provided by each particle i in the particle swarm algorithm. k B k OX k DP k Q k Predictions are made to obtain the fitness of the particle.

[0038] Specifically, the operating parameters of the circulating fluidized bed boiler are controlled and optimized. Under the premise of meeting actual production and environmental protection requirements, the coupled effects of in-furnace combustion efficiency, nitrogen oxide control and tail-end denitrification device are considered, and the total cost of boiler combustion and pollutant control is calculated to optimize it.

[0039] In at least one embodiment, please refer to Figure 2 Step S3 includes: traversing the fitness of each particle; comparing the fitness of each particle with the historical best cost value; when the fitness of particle i is less than the historical best cost value, replacing the position vector of particle i with the historical best cost vector P. besti .

[0040] Specifically, the fitness of each particle is iterated, and each particle's fitness is compared with the historical best cost value. If the fitness of particle i is less than the historical best cost value, then the position vector of particle i is replaced with the historical best cost vector P. besti Otherwise, do not replace the historical best cost vector P. besti .

[0041] In at least one embodiment, please refer to Figure 2 Step S4 includes: traversing the fitness of each particle; comparing the fitness of each particle with the minimum cost value; when the fitness of particle i is less than the minimum cost value, replacing the position vector of particle i with the population minimum cost vector G. best .

[0042] Specifically, the fitness of each particle is iterated, and the fitness of all particles is selected. Each particle's fitness is compared with the minimum cost value. If the fitness of particle i is less than the minimum cost value, then the position vector of particle i is replaced with the vector G of the minimum cost of the population. best Otherwise, do not replace the population minimum cost vector G. best .

[0043] In at least one embodiment, step S5 includes: the velocity vector iteration formula is V i+1 =wV i +c1r1(P besti -X i )+c2r2(G best -X i The iterative formula for the position vector is X. i+1 =X i +V i+1 Where w represents the weights of the particle swarm optimization algorithm, and V... i Let X be the velocity vector of particle i. iLet V be the position vector of particle i, c1 and c2 be learning factors, r1 and r2 be random probability values, and V be the position vector of particle i. i+1 Let X be the velocity vector of particle (i+1). i+1 Let be the position vector of particle (i+1).

[0044] Specifically, V can be calculated using the velocity vector iteration formula and the position vector iteration formula. i+1 and X i+1 This allows us to find the parameters corresponding to particle (i+1).

[0045] In at least one embodiment, step S6 includes: the host computer determining whether the particle (i+1) satisfies the iteration count; when the host computer determines that the particle satisfies the iteration count after iteration, the host computer determines the iteration count based on the position vector X. i+1 Obtain the corresponding circulating fluidized bed boiler's load L, bed temperature T, and primary and secondary air matching A. k Bed pressure B k Oxygen content (OX) k , suspending differential pressure DP k The denitrification agent injection flow rate Q of the denitrification unit k The cost value V is calculated based on the objective function; the host computer executes step S8.

[0046] Based on the same technological concept, such as Figures 1 to 3 As shown, at least one embodiment also provides a circulating fluidized bed system, comprising: a host computer, a circulating fluidized bed boiler, and a denitrification device; wherein, based on a particle swarm optimization algorithm, the host computer acquires particles to form a particle swarm based on the load of the circulating fluidized bed boiler, bed temperature, primary and secondary air matching, bed pressure, oxygen content, suspension section differential pressure, and the denitrification agent injection flow rate of the denitrification device; the host computer calculates the fitness of each particle according to an objective function, and the fitness is a cost value; the fitness of each particle is traversed, and the fitness of each particle is compared with the historically achieved optimal cost value, so that the host computer obtains the historical optimal cost vector; the fitness of each particle is traversed, and the fitness of each particle is compared with the minimum cost, so that the host computer obtains the minimum population cost vector. Cost vector; the host computer calculates the position vector and velocity vector of the particle after iteration based on the velocity vector iteration formula, the position vector iteration formula, the historical best cost vector, and the population minimum cost vector; when the host computer determines that the particle meets the iteration number, it obtains the load, bed temperature, primary and secondary air matching, bed pressure, oxygen content, suspension section differential pressure, and denitrification agent injection flow rate of the corresponding circulating fluidized bed boiler based on the position vector of the particle after iteration, and calculates the cost value according to the objective function; the host computer sets the operating parameters of the circulating fluidized bed boiler and the denitrification device based on the load, bed temperature, primary and secondary air matching, bed pressure, oxygen content, suspension section differential pressure, and denitrification agent injection flow rate of the circulating fluidized bed boiler obtained by the particle after iteration.

[0047] In at least one embodiment, the host computer is adapted to set the operating parameters of the circulating fluidized bed boiler and the denitrification device using the circulating fluidized bed boiler nitrogen oxide control optimization operation method as described above.

[0048] Based on the same technical concept, at least one embodiment also provides a non-transitory readable storage medium storing a program / instruction that, when executed by a processor, implements the steps of the above-described circulating fluidized bed boiler nitrogen oxide control optimization operation method.

[0049] In summary, this invention uses particle swarm optimization to automatically find the optimal operating parameters for circulating fluidized bed boilers and denitrification devices. Simultaneously, the calculation fully considers the coupling effect of boiler combustion and tail-end denitrification, enabling the reduction of coal consumption and denitrification agent consumption in circulating fluidized bed boilers under given load and nitrogen oxide emission concentration requirements, thus minimizing operating costs.

[0050] The disclosures and other solutions, examples, embodiments, modules, and functional operations described in this document can be implemented in digital electronic circuits, or computer software, firmware, or hardware, including the structures disclosed in this document and their structural equivalents, or combinations thereof. The disclosures and other embodiments can be implemented as one or more computer program products, i.e., one or more modules of computer program instructions encoded on a tangible and non-volatile computer-readable medium for execution by a data processing apparatus or for controlling the operation of the data processing apparatus. The computer-readable medium can be a machine-readable storage device, a machine-readable storage substrate, a storage device, a material composition that influences machine-readable propagated signals, or one or more of these. The terms "data processing unit" or "data processing apparatus" include all means, devices, and machines for processing data, including, for example, programmable processors, computers, or multiprocessors or computer groups. In addition to hardware, the apparatus may also include code that creates an execution environment for a computer program, such as code constituting processor firmware, a protocol stack, a database management system, an operating system, or combinations thereof. The propagated signals are artificially generated signals, such as machine-generated electrical, optical, or electromagnetic signals, which are generated to encode information for transmission to a suitable receiver device.

[0051] Computer programs (also known as programs, software, software applications, scripts, or code) can be written in any programming language (including compiled or interpreted languages) and can be deployed in any form, including as standalone programs or as modules, components, subroutines, or other units suitable for use in a computing environment. A computer program does not necessarily correspond to a file in a file system. A program can be stored in a portion of a file that holds other programs or data (e.g., one or more scripts stored in a markup language document), in a single file dedicated to that program, or in multiple coordinating files (e.g., a file storing one or more modules, subroutines, or portions of code). Computer programs can be deployed and executed on one or more computers located at a single site or distributed across multiple sites interconnected by a communication network.

[0052] The processing and logic flows described in this document can be executed by one or more programmable processors that execute one or more computer programs to perform functions by manipulating input data and generating outputs. The processing and logic flows can also be executed by special-purpose logic circuitry, and the devices can be implemented as special-purpose logic circuitry, such as FPGAs (Field-Programmable Gate Arrays) or ASICs (Application-Specific Integrated Circuits).

[0053] For example, processors suitable for executing computer programs include general-purpose and special-purpose microprocessors, as well as any one or more of any type of digital computer. Typically, the processor receives instructions and data from read-only memory or random access memory, or both. The basic components of a computer are a processor that executes instructions and one or more storage devices that store the instructions and data. Typically, a computer will also include one or more mass storage devices for storing data, such as magnetic disks, magneto-optical disks, or optical disks, or operatively coupled to receive data from or transfer data to mass storage devices, or both. However, a computer does not necessarily have such devices. Computer-readable media suitable for storing computer program instructions and data include all forms of non-volatile memory, media, and memory devices, including, for example, semiconductor memory devices such as erasable programmable read-only memory (EPROM), electrically erasable programmable read-only memory (EEPROM), and flash memory devices; magnetic disks, such as internal hard disks or removable disks; magneto-optical disks; and optical disc read-only memory (CD ROM) and digital versatile optical disc read-only memory (DVD-ROM). The processor and memory may be supplemented by dedicated logic circuitry or incorporated into dedicated logic circuitry.

[0054] While this application contains numerous details, it should not be construed as limiting the scope of any invention or claim, but rather as a description of features of specific embodiments of a particular invention. Certain features described in the context of individual embodiments may also be implemented in combination in a single embodiment. Conversely, various functions described in the context of a single embodiment may also be implemented individually in multiple embodiments, or in any suitable sub-combination. Furthermore, although the foregoing features may be described as functioning in certain combinations, or even initially claimed to be so, in some cases one or more features from a combination of claims may be removed from the combination, and a combination of claims may refer to a sub-combination or a variation of a sub-combination.

[0055] Similarly, although operations are described in a specific order in the accompanying drawings, this should not be construed as requiring the specific order or sequence shown to perform such operations, or all the described operations, in order to obtain the desired results. Furthermore, the separation of various system components in the embodiments of this application should not be construed as requiring such separation in all embodiments.

[0056] Only some implementations and examples are described. Other implementations, enhancements and variations can be made based on the content described and illustrated in this application.

[0057] When no intermediate component exists other than a line, trace, or other medium between the first and second components, the first component is directly coupled to the second component. When an intermediate component other than a line, trace, or other medium exists between the first and second components, the first component is indirectly coupled to the second component. The term "coupling" and its variations include direct coupling and indirect coupling. Unless otherwise stated, the term "about" is used to mean a range including upper and lower 10% of the value.

[0058] While several embodiments are provided in this disclosure, it should be understood that the disclosed systems and methods may be embodied in many other specific forms without departing from the spirit or scope of this disclosure. The present examples are intended to be illustrative rather than restrictive and are not limited to the details given. For example, various elements or components may be combined or integrated into another system, or certain features may be omitted or not implemented.

[0059] In the several embodiments provided herein, it should be understood that the disclosed apparatus and methods can also be implemented in other ways. The apparatus embodiments described above are merely illustrative; for example, the flowcharts and block diagrams in the accompanying drawings illustrate the architecture, functionality, and operation of possible implementations of apparatus, methods, and computer program products according to various embodiments of this application. In this regard, each block in a flowchart or block diagram may represent a module, segment, or portion of code containing one or more executable instructions for implementing a specified logical function. It should also be noted that in some alternative implementations, the functions marked in the blocks may occur in a different order than those marked in the drawings. For example, two consecutive blocks may actually be executed substantially in parallel, and they may sometimes be executed in reverse order, depending on the functions involved. It should also be noted that each block in a block diagram and / or flowchart, and combinations of blocks in block diagrams and / or flowcharts, can be implemented using a dedicated hardware-based system that performs the specified function or action, or using a combination of dedicated hardware and computer instructions.

[0060] Furthermore, without departing from the scope of this disclosure, the discrete or individual technologies, systems, subsystems, and methods described and illustrated in the various embodiments may be combined or integrated with other systems, modules, technologies, or methods. Other items shown or discussed as coupled may be directly connected or indirectly coupled or communicated via some interface, device, or intermediate component in an electrical, mechanical, or other manner. Those skilled in the art can identify other examples of changes, substitutions, and modifications without departing from the spirit and scope of this disclosure.

Claims

1. A method for optimizing the control of nitrogen oxide emissions in a circulating fluidized bed boiler, characterized in that, include: Step S1: Based on the particle swarm optimization algorithm, the host computer obtains particles according to the load, bed temperature, primary and secondary air matching, bed pressure, oxygen content, differential pressure of the suspension section and the denitrification agent injection flow rate of the circulating fluidized bed boiler, so as to form a particle swarm. Step S2: The host computer calculates the fitness of each particle according to the objective function, and the fitness is the cost value; Step S3: Iterate through the fitness of each particle and compare the fitness of each particle with the historical best cost value so that the host computer can obtain the historical best cost vector. Step S4: Iterate through the fitness of each particle and compare the fitness of each particle with the minimum cost so that the host computer can obtain the minimum cost vector of the population. Step S5: The host computer calculates the position vector and velocity vector of the particle after iteration based on the velocity vector iteration formula, the position vector iteration formula, the historical best cost vector, and the population minimum cost vector; Step S6: When the host computer determines that the number of iterations is satisfied after iteration, it obtains the load, bed temperature, primary and secondary air matching, bed pressure, oxygen content, suspension section differential pressure and denitrification agent injection flow rate of the corresponding circulating fluidized bed boiler according to the position vector of the particle after iteration, and calculates the cost value according to the objective function, and then executes step S8. Step S7: If the host computer determines that the number of iterations is not met after the iteration, it executes step S2; Step S8: The host computer sets the operating parameters of the circulating fluidized bed boiler and the denitrification device based on the load, bed temperature, primary and secondary air matching, bed pressure, oxygen content, differential pressure of the suspension section, and denitrification agent injection flow rate of the circulating fluidized bed boiler obtained by the particles after iteration.

2. The method for optimizing the control of nitrogen oxide emissions in a circulating fluidized bed boiler as described in claim 1, characterized in that, The load is L; The bed temperature is T; The primary and secondary winds are matched as A. k And k takes the values ​​1, 2, or 3; Bed pressure is B k And k takes positive integer values; Oxygen content is OX k And k takes positive integer values; The differential pressure of the suspension section is DP k And k takes the values ​​1 or 2; The denitrification agent injection flow rate is Q k And k takes positive integer values; Particle i is (L,T,A) k B k OX k DP k Q k ).

3. The method for optimizing the control of nitrogen oxide emissions in a circulating fluidized bed boiler as described in claim 2, characterized in that, The objective function is configured to calculate the total cost of boiler combustion and pollutant control, i.e., the objective function V=f(L,T,A) k B k OX k DP k Q k ), to obtain the fitness of the particle, and the fitness is the cost value; The host computer uses a neural network-based deep learning module and a data prediction module to perform deep learning on the historical boiler operating data to obtain a correlation model between boiler operating parameters and costs. The data prediction module then predicts the boiler costs under different operating parameters. The host computer uses a deep learning module based on neural networks to periodically perform self-learning analysis on historical boiler operating data to obtain the cost V and boiler operating parameters (L, T, A). k B k OX k DP k Q k The relationship model between ) and ; The data prediction module in the host computer calls the association model trained by the deep learning module, and uses the boiler operating parameters (L, T, A) provided by each particle i in the particle swarm optimization algorithm. k B k OX k DP k Q k To predict the fitness of a particle, we can use a predictive tool.

4. The method for optimizing the control of nitrogen oxide emissions in a circulating fluidized bed boiler as described in claim 3, characterized in that, Step S3 includes: Iterate through the fitness of each particle; Compare the fitness of each particle with the historical cost-effectiveness. When the fitness of particle i is less than the historical best cost, the position vector of particle i is replaced with the historical best cost vector P. besti .

5. The method for optimizing the control of nitrogen oxide emissions in a circulating fluidized bed boiler as described in claim 4, characterized in that, Step S4 includes: Iterate through the fitness of each particle; Compare the fitness of each particle with the minimum cost value; When the fitness of particle i is less than the minimum cost value, the position vector of particle i is replaced with the population minimum cost vector G. best .

6. The method for optimizing the control of nitrogen oxide emissions in a circulating fluidized bed boiler as described in claim 5, characterized in that, Step S5 includes: The velocity vector iteration formula is V i+1 =wV i +c1r1(P besti -X i )+c2r2(G best -X i ); The iterative formula for the position vector is X i+1 =X i +V i+1 ; Where w is the weight of the particle swarm optimization algorithm, and V i Let X be the velocity vector of particle i. i Let V be the position vector of particle i, c1 and c2 be learning factors, r1 and r2 be random probability values, and V be the position vector of particle i. i+1 Let X be the velocity vector of particle (i+1). i+1 Let be the position vector of particle (i+1).

7. The method for optimizing the control of nitrogen oxide emissions in a circulating fluidized bed boiler as described in claim 6, characterized in that, Step S6 includes: The host computer determines whether particle (i+1) satisfies the required number of iterations; When the host computer determines that the particle has met the required number of iterations after iteration, the host computer uses the position vector X... i+1 Obtain the corresponding circulating fluidized bed boiler's load L, bed temperature T, and primary and secondary air matching A. k Bed pressure B k Oxygen content (OX) k , suspending differential pressure DP k The denitrification agent injection flow rate Q of the denitrification unit k And calculate the cost value V according to the objective function; The host computer executes step S8.

8. A circulating fluidized bed system, characterized in that, include: Supervisory control and data acquisition (SCADA) system, circulating fluidized bed boiler, denitrification unit; in Based on the particle swarm optimization algorithm, the host computer obtains particles according to the load, bed temperature, primary and secondary air matching, bed pressure, oxygen content, differential pressure of the suspension section, and denitrification agent injection flow rate of the circulating fluidized bed boiler to form a particle swarm. The host computer calculates the fitness of each particle based on the objective function, and the fitness is a cost value; Iterate through the fitness of each particle and compare the fitness of each particle with the historical best cost value so that the host computer can obtain the historical best cost vector. Iterate through the fitness of each particle and compare the fitness of each particle with the minimum cost so that the host computer can obtain the minimum cost vector of the population. The host computer calculates the position and velocity vectors of the particles after iteration based on the velocity vector iteration formula, the position vector iteration formula, the historical best cost vector, and the population minimum cost vector. When the host computer determines that the particle meets the iteration number after iteration, it obtains the load, bed temperature, primary and secondary air matching, bed pressure, oxygen content, suspension section differential pressure and denitrification agent injection flow rate of the corresponding circulating fluidized bed boiler based on the position vector of the particle after iteration, and calculates the cost value based on the objective function. The host computer sets the operating parameters of the circulating fluidized bed boiler and the denitrification device based on the load, bed temperature, primary and secondary air matching, bed pressure, oxygen content, differential pressure of the suspension section, and denitrification agent injection flow rate of the denitrification device obtained by the particles after iteration.

9. The circulating fluidized bed system as described in claim 8, characterized in that, The host computer is suitable for setting the operating parameters of the circulating fluidized bed boiler and the denitrification device using the nitrogen oxide control optimization operation method for circulating fluidized bed boilers as described in any one of claims 1-7.

10. A non-transitory readable storage medium having a program / instruction stored thereon, characterized in that, When executed by the processor, the program / instruction implements the steps of the circulating fluidized bed boiler nitrogen oxide control optimization operation method according to any one of claims 1 to 7.

Images