CN-121978940-A - Genetic algorithm-based boiler operation optimization method, device and system, electronic equipment and storage medium

CN121978940ACN 121978940 ACN121978940 ACN 121978940ACN-121978940-A

Abstract

The invention relates to the technical field of circulating fluidized bed boiler control, in particular to a boiler operation optimization method, device and system based on a genetic algorithm, electronic equipment and storage medium, wherein the method comprises the steps of firstly collecting all-dimensional operation parameters of a boiler in real time and providing dynamic working condition perception for optimization; the method comprises the steps of constructing a comprehensive economical evaluation function, unifying multi-objective optimization standards, further, encoding multiple variables into chromosomes, carrying out collaborative optimization by utilizing global searching capability of a genetic algorithm, introducing a safety constraint punishment mechanism in fitness evaluation to ensure that all solutions meet safety and environment-friendly hard boundaries, and finally, automatically issuing an optimal parameter set obtained by optimizing to a control system for execution to form real-time closed-loop optimization capable of adaptively following working condition changes, thereby realizing continuous minimization of total operation cost of a boiler on the premise of ensuring safety and stability.

Inventors

TANG XIUNENG
HE JIANLE
WANG WENYU
GUO DONG
ZHOU XIAOMING
GAO YALEI
FAN WENLEI
Guan Haipo

Assignees

华电电力科学研究院有限公司

Dates

Publication Date: 20260505
Application Date: 20260202

Claims (10)

1. A method for optimizing boiler operation based on a genetic algorithm, the method comprising: Collecting operation parameters of the boiler in real time, wherein the operation parameters at least comprise boiler load parameters, combustion parameters, environment-friendly parameters and executing mechanism state parameters; constructing a comprehensive economical evaluation function aiming at minimizing the total running cost as an adaptability function of a genetic algorithm; Encoding a set of adjustable boiler operating variables into chromosomes and initializing a population; Based on the fitness function and the safety constraint conditions of boiler operation, adopting a genetic algorithm to iteratively optimize the population until a preset termination condition is met, and outputting an optimal chromosome; Decoding the optimal chromosome to obtain a target economic operation parameter set; and controlling the boiler to operate based on the target economic operation parameter set.
2. The method of claim 1, wherein the boiler load parameters include main steam flow and feedwater flow, the combustion parameters include total coal quantity, total primary air quantity, total secondary air quantity, furnace negative pressure and in-furnace coal quality data, the environmental parameters include exhaust gas temperature, fly ash carbon content and O 2 、NOx、SO 2 concentration in the flue gas, and the actuator state parameters include flue gas recirculation baffle opening, primary fan current, secondary fan current and induced fan current.
3. The method of claim 1, wherein the step of constructing a comprehensive economic evaluation function targeting overall operating cost minimization as a fitness function of the genetic algorithm comprises: Determining a fuel cost item, a station service electricity cost item and other operation cost items according to the operation parameters acquired in real time; And multiplying the fuel cost item, the station service electricity cost item and other operation cost items with an adjustable weight coefficient respectively, and then summing to form the comprehensive economical evaluation function.
4. The method of claim 1, wherein the step of encoding a set of adjustable boiler operating variables into chromosomes and initializing the population comprises: Selecting adjustable operation variables of the boiler to form the chromosome, wherein the adjustable operation variables at least comprise total coal feeding amount, total secondary air proportioning, secondary air distribution proportion of each layer and opening of a smoke recycling baffle; and randomly generating a plurality of chromosomes in the safe operation range of each adjustable operation variable to form an initial population.
5. The method according to claim 1, wherein the step of iteratively optimizing the population using a genetic algorithm based on the fitness function, safety constraints of boiler operation, until a preset termination condition is met, and outputting an optimal chromosome, comprises: calculating the fitness value of each chromosome in the current population based on the comprehensive economic evaluation function and the safety constraint condition; Selecting chromosomes from the current population through selection operation according to the fitness value; sequentially executing crossover operation and mutation operation on the selected chromosomes to generate a new offspring population; and taking the offspring population as the current population of the next iteration, and repeating until the preset termination condition is met.
6. The method of claim 1, wherein the step of decoding the optimal chromosome to obtain a set of target economic operating parameters comprises: and according to a predefined coding rule, mapping the gene value contained in the optimal chromosome into a specific value of the corresponding adjustable boiler operation variable, thereby obtaining the target economic operation parameter set.
7. A genetic algorithm-based boiler operation optimization apparatus, the apparatus comprising: the acquisition module is used for acquiring the operation parameters of the boiler in real time, wherein the operation parameters at least comprise a boiler load parameter, a combustion parameter, an environment-friendly parameter and an execution mechanism state parameter; the construction module is used for constructing a comprehensive economic evaluation function aiming at minimizing the total running cost as an adaptability function of the genetic algorithm; the initialization module is used for encoding a group of adjustable boiler operation variables into chromosomes and initializing a population; The iteration module is used for carrying out iterative optimization on the population by adopting a genetic algorithm based on the fitness function and the safety constraint condition of the boiler operation until a preset termination condition is met, and outputting an optimal chromosome; the decoding module is used for decoding the optimal chromosome to obtain a target economic operation parameter set; And the control module is used for controlling the boiler to operate based on the target economic operation parameter set.
8. A genetic algorithm-based boiler operation optimization system, the system comprising: The data acquisition unit is used for being in communication connection with a distributed control system of the boiler and acquiring the operation parameters of the boiler in real time; An optimization computing unit, connected to the data acquisition unit, configured with a processor and a memory, the memory having stored therein an executable program, the processor being configured to execute the program to implement the method of any one of claims 1 to 6; The control output unit is connected with the optimization calculation unit and is used for receiving the target economic operation parameter set, converting the target economic operation parameter set into a control instruction and sending the control instruction to a distributed control system of the boiler so as to adjust the operation of the boiler; The man-machine interaction module is in communication connection with the optimization calculation unit and the control output unit and is used for receiving instructions of operators, setting optimization parameters, displaying real-time running states and optimizing results.
9. An electronic device comprising a memory for storing a computer program and a processor that runs the computer program to cause the electronic device to perform the method of any one of claims 1 to 6.
10. A storage medium having stored therein computer program instructions which, when read and executed by a processor, perform the method of any of claims 1 to 6.

Description

Genetic algorithm-based boiler operation optimization method, device and system, electronic equipment and storage medium Technical Field The invention relates to the technical field of circulating fluidized bed boiler control, in particular to a boiler operation optimization method, device and system based on a genetic algorithm, electronic equipment and storage medium. Background A Circulating Fluidized Bed (CFB) boiler is widely used in the fields of electric power and industrial heat supply as a combustion apparatus with high efficiency and cleanliness. To further reduce nitrogen oxide (NOx) emissions, flue Gas Recirculation (FGR) techniques are introduced into CFB boiler systems to reduce the combustion zone temperature and oxygen concentration by recirculating a portion of the low temperature flue gas to the furnace to inhibit NOx production. However, the introduction of flue gas recirculation increases the variables of the boiler system, the coupling relation among multiple variables such as coal feeding, air distribution, recirculation and the like is complex, and higher requirements are put on operation control. At present, CFB boiler operation optimization with flue gas recirculation mainly relies on empirical adjustment by operators or single loop PID control based on fixed rules. The method has the remarkable limitation that firstly, operators can only locally adjust according to a few key parameters (such as main steam temperature and oxygen amount), and the method is difficult to systematically and cooperatively optimize all adjustable variables such as coal feeding, primary and secondary air proportioning, flue gas recirculation amount and the like, and cannot realize global optimal operation aiming at comprehensive economy. Secondly, the response of manual operation is lagged and greatly influenced by personal experience, so that the running economy and stability of the boiler fluctuate. In addition, when boundary conditions such as boiler load, coal quality and the like are changed, the original experience or fixed control strategy is difficult to be quickly and adaptively adjusted, and a longer fumbling process is required. Some existing advanced optimization methods, such as offline models (for example, support vector machines) based on historical data training, also have the problem of insufficient adaptability, are difficult to make quick response and dynamic optimization on working conditions which change in real time, and are difficult to realize global minimization of the total operation cost of the boiler on the premise of meeting various safety and environmental protection constraints. Disclosure of Invention In view of the above, the present invention aims to provide a method, a device, a system, an electronic device and a storage medium for optimizing boiler operation based on a genetic algorithm. In a first aspect, an embodiment of the present invention provides a method for optimizing boiler operation based on a genetic algorithm, the method including: collecting operation parameters of a boiler in real time, wherein the operation parameters at least comprise boiler load parameters, combustion parameters, environment-friendly parameters and executing mechanism state parameters; constructing a comprehensive economical evaluation function aiming at minimizing the total running cost as an adaptability function of a genetic algorithm; Encoding a set of adjustable boiler operating variables into chromosomes and initializing a population; based on the fitness function and the safety constraint conditions of boiler operation, adopting a genetic algorithm to carry out iterative optimization on the population until the preset termination conditions are met, and outputting an optimal chromosome; Decoding the optimal chromosome to obtain a target economic operation parameter set; And controlling the boiler to operate based on the target economic operation parameter set. In combination with the first aspect, the boiler load parameters comprise main steam flow and water supply flow, the combustion parameters comprise total coal quantity, total primary air quantity, total secondary air quantity, hearth negative pressure and coal quality data, the environment-friendly parameters comprise smoke exhaust temperature, fly ash carbon content and O 2、NOx、SO2 concentration in smoke, and the executing mechanism state parameters comprise smoke recirculation baffle opening, primary fan current, secondary fan current and induced draft fan current. With reference to the first aspect, the step of constructing a comprehensive economic evaluation function targeting minimization of total running cost as an fitness function of a genetic algorithm includes: Determining a fuel cost item, a station service electricity cost item and other operation cost items according to the operation parameters acquired in real time; And multiplying the fuel cost item, the station service electricity cost item and other operatio