Boiler operation optimization method, device and system based on genetic algorithm, electronic equipment and storage medium

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 a storage medium. Firstly, full-dimension operation parameters of a boiler are collected in real time, and dynamic working condition perception is provided for optimization; then, constructing a comprehensive economy evaluation function, and unifying a multi-objective optimization standard; further, multivariable codes are used as chromosomes, the global search capability of a genetic algorithm is used for collaborative optimization, a security constraint penalty mechanism is introduced into fitness evaluation, and all solutions are ensured to meet a safe and environment-friendly rigid boundary; finally, the optimal parameter set obtained through optimization is automatically issued to a control system to be executed, real-time closed-loop optimization which can be adaptively changed along with the working condition is formed, and therefore on the premise that safety and stability are guaranteed, continuous minimization of the total operation cost of the boiler is achieved.

Description

Technical Field

[0001] This invention relates to the field of circulating fluidized bed boiler control technology, and in particular to a boiler operation optimization method, device, system, electronic equipment, and storage medium based on a genetic algorithm. Background Technology

[0002] Circulating fluidized bed (CFB) boilers, as highly efficient and clean combustion equipment, are widely used in the power and industrial heating sectors. To further reduce nitrogen oxide (NOx) emissions, flue gas recirculation (FGR) technology has been introduced into CFB boiler systems. This involves recirculating a portion of the low-temperature flue gas back into the furnace, lowering the combustion zone temperature and oxygen concentration to suppress NOx formation. However, the introduction of FGR increases the number of variables in the boiler system, making the coupling relationships between multiple variables such as coal feeding, air distribution, and recirculation complex, and placing higher demands on operation and control.

[0003] Currently, the optimization of CFB boiler operation with flue gas recirculation mainly relies on operators' experience-based adjustments or single-loop PID control based on fixed rules. These methods have significant limitations: First, operators can typically only make local adjustments based on a few key parameters (such as main steam temperature and oxygen content), making it difficult to systematically and collaboratively optimize all adjustable variables such as coal feed, primary and secondary air ratios, and flue gas recirculation volume, thus failing to achieve globally optimal operation with comprehensive economic goals. Second, manual operation has a lag in response and is heavily influenced by individual experience, leading to fluctuations in boiler operating economy and stability. Furthermore, when boundary conditions such as boiler load and coal quality change, existing experience-based or fixed control strategies are difficult to adapt quickly, requiring a lengthy re-exploration process.

[0004] Some existing advanced optimization methods, such as offline models trained on historical data (e.g., support vector machines), also suffer from insufficient adaptability, making it difficult to respond quickly and dynamically optimize to real-time changing operating conditions, and making it difficult to achieve global minimization of the total boiler operating cost while meeting various safety and environmental constraints. Summary of the Invention

[0005] In view of this, the purpose of the present invention is to provide a boiler operation optimization method, device, system, electronic device, and storage medium based on a genetic algorithm.

[0006] In a first aspect, embodiments of the present invention provide a boiler operation optimization method based on a genetic algorithm, the method comprising: Real-time acquisition of boiler operating parameters, including at least boiler load parameters, combustion parameters, environmental protection parameters, and actuator status parameters; A comprehensive economic evaluation function with the goal of minimizing total operating cost is constructed and used as the fitness function of the genetic algorithm. Encode a set of adjustable boiler operating variables into chromosomes and initialize the population; Based on the fitness function and the safety constraints of boiler operation, a genetic algorithm is used to iteratively optimize the population until the preset termination condition is met, and the optimal chromosome is output. Decode the optimal chromosome to obtain the target economic operation parameter set; Boiler operation is controlled based on the target economic operating parameter set.

[0007] In conjunction with the first aspect, boiler load parameters include main steam flow and feedwater flow; combustion parameters include total coal quantity, total primary air volume, total secondary air volume, furnace negative pressure, and coal quality data; environmental parameters include flue gas temperature, fly ash carbon content, and O2, NOx, and SO2 concentrations in flue gas; and actuator status parameters include flue gas recirculation damper opening, primary air fan current, secondary air fan current, and induced draft fan current.

[0008] In conjunction with the first aspect, the steps for constructing a comprehensive economic evaluation function with the objective of minimizing total operating cost, which serves as the fitness function of the genetic algorithm, include: Based on the real-time collected operating parameters, determine the fuel cost item, plant electricity cost item, and other operating cost items; The fuel cost item, the plant electricity cost item, and other operating cost items are each multiplied by an adjustable weighting coefficient and then summed to form a comprehensive economic evaluation function.

[0009] In conjunction with the first aspect, the steps of encoding a set of adjustable boiler operating variables into chromosomes and initializing the population include: Select the adjustable operating variables of the boiler to form a chromosome. The adjustable operating variables include at least the total coal feed, the ratio of primary and secondary air, the distribution ratio of secondary air volume in each layer, and the opening of the flue gas recirculation damper. Multiple chromosomes are randomly generated within the safe operating range of each adjustable operand to form the initial population.

[0010] In conjunction with the first aspect, based on the fitness function and the safety constraints of boiler operation, the steps of using a genetic algorithm to iteratively optimize the population until a preset termination condition is met and outputting the optimal chromosome include: For each chromosome in the current population, the fitness value of the chromosome is calculated based on a comprehensive economic evaluation function and safety constraints. Chromosomes are selected from the current population based on their fitness values ​​through a selection operation. The selected chromosomes are subjected to crossover and mutation operations in sequence to generate a new offspring population; Use the offspring population as the current population for the next iteration, repeating this process until the preset termination condition is met.

[0011] Combining the first aspect, the steps to decode the optimal chromosome and obtain the target economic operating parameter set include: According to predefined coding rules, the gene values ​​contained in the optimal chromosome are mapped to the specific values ​​of the corresponding adjustable boiler operation variables, thereby obtaining the target economic operation parameter set.

[0012] Secondly, this application provides a boiler operation optimization device based on a genetic algorithm, the device comprising: The data acquisition module is used to collect the boiler's operating parameters in real time. The operating parameters include at least boiler load parameters, combustion parameters, environmental protection parameters, and actuator status parameters. The module is used to construct a comprehensive economic evaluation function with the goal of minimizing the total operating cost, which serves as the fitness function of the genetic algorithm. An initialization module is used to encode a set of adjustable boiler operating variables into chromosomes and initialize the population; The iterative module is used to iteratively optimize the population using a genetic algorithm based on the fitness function and the safety constraints of boiler operation until the preset termination condition is met, and output the optimal chromosome. The decoding module is used to decode the optimal chromosome to obtain the target economic operating parameter set; The control module is used to control the boiler operation based on the target economic operating parameter set.

[0013] Thirdly, this application also provides a boiler operation optimization system based on a genetic algorithm, the system comprising: The data acquisition unit is used to communicate with the boiler's distributed control system and collect the boiler's operating parameters in real time. An optimized computing unit is connected to a data acquisition unit and is equipped with a processor and a memory. The memory stores an executable program, and the processor is configured to execute the program to implement the method described above. The control output unit, connected to the optimization calculation unit, is used to receive the target economic operating parameter set and convert it into control commands to send to the boiler's distributed control system to adjust the boiler operation. The human-machine interface module communicates with the optimization calculation unit and the control output unit to receive operator instructions, set optimization parameters, and display real-time operating status and optimization results.

[0014] Fourthly, this application provides an electronic device, which includes a memory and a processor. The memory stores a computer program, and the processor runs the computer program to cause the electronic device to perform the above-described method.

[0015] Fifthly, this application provides a storage medium storing computer program instructions, which are read and executed by a processor to perform the above-described method.

[0016] The embodiments of this invention bring the following beneficial effects: This application provides a boiler operation optimization method, device, system, electronic device, and storage medium based on a genetic algorithm. The method includes: real-time acquisition of boiler operating parameters, which include at least boiler load parameters, combustion parameters, environmental protection parameters, and actuator status parameters; construction of a comprehensive economic evaluation function with the goal of minimizing total operating cost as the fitness function of the genetic algorithm; encoding a set of adjustable boiler operation variables into chromosomes and initializing the population; iteratively optimizing the population using a genetic algorithm based on the fitness function and the safety constraints of boiler operation until a preset termination condition is met, and outputting the optimal chromosome; decoding the optimal chromosome to obtain a target economic operating parameter set; and controlling boiler operation based on the target economic operating parameter set.

[0017] The method provided in this application first collects all-dimensional operating parameters of the boiler in real time to provide dynamic operating condition perception for optimization; then, it constructs a comprehensive economic evaluation function to unify multi-objective optimization standards; further, it encodes multivariate variables into chromosomes, uses the global search capability of genetic algorithms for collaborative optimization, and introduces a safety constraint penalty mechanism in the fitness evaluation to ensure that all solutions meet the hard boundaries of safety and environmental protection; finally, it automatically sends the optimal parameter set obtained by optimization to the control system for execution, forming a real-time closed-loop optimization that can adaptively follow changes in operating conditions, thereby achieving continuous minimization of the total operating cost of the boiler while ensuring safety and stability.

[0018] Other features and advantages of the invention will be set forth in the description which follows, 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 in accordance with the structures particularly pointed out in the description, claims and 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 1This is a flowchart illustrating the boiler operation optimization method based on genetic algorithms provided in an embodiment of the present invention. Figure 2 This is a schematic diagram of a circulating fluidized bed (CFB) boiler system with flue gas recirculation (FGR) applicable to embodiments of the present invention; Figure 3 This is a schematic diagram of the structure of the boiler operation optimization device based on genetic algorithm provided in an embodiment of the present invention; Figure 4 This is a schematic diagram of the electronic device structure provided in an embodiment of the present invention.

[0022] Figure label: 10 - Acquisition module, 20 - Construction module, 30 - Initialization module, 40 - Iteration module, 50 - Decoding module, 60 - Control module; 130 - Processor, 131 - Memory, 132 - Bus, 133 - Communication interface. Detailed Implementation

[0023] 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.

[0024] To facilitate understanding of this embodiment, the technical terms used in this application will be briefly introduced below.

[0025] Circulating fluidized bed (CFB) boilers are boilers that use a fluidized combustion method, where the fuel is in a suspended and flowing state inside the furnace. They are characterized by high combustion efficiency, low pollutant emissions, and wide fuel adaptability.

[0026] Genetic algorithm (GA) is a global optimization algorithm that simulates natural selection and genetic mechanisms. It iteratively searches for the optimal solution to a problem through operations such as selection, crossover, and mutation. It is suitable for multivariable, nonlinear, and constrained optimization problems.

[0027] Chromosome encoding represents the operational variables to be optimized (such as coal feed rate, air volume ratio, damper opening, etc.) as individuals (chromosomes) in the genetic algorithm, so as to perform genetic operations.

[0028] After introducing the technical terms used in this application, the application scenarios and design concepts of the embodiments of this application will be briefly described below.

[0029] Circulating fluidized bed boilers with flue gas recirculation exhibit strong multivariate coupling, making it difficult to achieve global economic optimization relying solely on human experience. Existing control methods cannot achieve real-time optimization to reduce total operating costs while meeting safety and environmental constraints.

[0030] Based on this, this application provides a boiler operation optimization method, device, system, electronic device, and storage medium based on a genetic algorithm, aiming to solve the defects of existing CFB boiler operation regulation that rely on experience, cannot achieve global optimization, and is difficult to adapt to changes in operating conditions.

[0031] Example 1 This application provides a boiler operation optimization method based on genetic algorithms, combined with... Figure 1 As shown, the method includes: S110 collects boiler operating parameters in real time, including at least boiler load parameters, combustion parameters, environmental protection parameters, and actuator status parameters.

[0032] S120: Construct a comprehensive economic evaluation function with the goal of minimizing total operating cost, which serves as the fitness function of the genetic algorithm.

[0033] S130 encodes a set of adjustable boiler operating variables into chromosomes and initializes the population.

[0034] S140 uses a genetic algorithm to iteratively optimize the population based on the fitness function and the safety constraints of boiler operation until the preset termination condition is met, and outputs the optimal chromosome.

[0035] S150 decodes the optimal chromosome to obtain the target economic operation parameter set.

[0036] S160 controls boiler operation based on a target set of economic operating parameters.

[0037] This application first collects real-time, multi-dimensional operating parameters of the boiler to provide dynamic operating condition awareness for optimization. Then, it constructs a comprehensive economic evaluation function that integrates fuel cost, plant power cost, and environmental losses, unifying multi-objective optimization standards. Further, it encodes multiple variables such as coal feeding, air distribution, and recirculation into chromosomes, utilizing the global search capability of a genetic algorithm for collaborative optimization. A safety constraint penalty mechanism is introduced in the fitness evaluation to ensure that all solutions meet the hard boundaries of safety and environmental protection. Finally, the optimal parameter set obtained through optimization is automatically sent to the control system for execution, forming a real-time closed-loop optimization that can adaptively follow changes in operating conditions, thereby continuously minimizing the total operating cost of the boiler while ensuring safety and stability.

[0038] In conjunction with the first aspect, boiler load parameters include main steam flow and feedwater flow; combustion parameters include total coal quantity, total primary air volume, total secondary air volume, furnace negative pressure, and coal quality data; environmental parameters include flue gas temperature, fly ash carbon content, and O2, NOx, and SO2 concentrations in flue gas; and actuator status parameters include flue gas recirculation damper opening, primary air fan current, secondary air fan current, and induced draft fan current.

[0039] Combination Figure 2 The circulating fluidized bed (CFB) boiler system shown is a modification of the traditional CFB boiler. The system mainly consists of the combustion and material circulation main body, the tail flue and flue gas treatment system, and the flue gas recirculation (FGR) modification section added to achieve deep low-NOx combustion.

[0040] The combustion chamber includes the furnace, a cyclone separator for gas-solid separation, and a return system. The tail flue houses various heating surfaces, dust removal, desulfurization, and other environmental protection equipment, with the induced draft fan providing the power for flue gas flow. A particularly crucial modification is the addition of an independent recirculation flue at the tail flue before the induced draft fan. This recirculation flue recirculates a portion of the extracted low-temperature, low-oxygen flue gas back to the lower part of the furnace or the secondary air zone. This recirculation flue is equipped with adjustable recirculation dampers (or fans), allowing for precise control of the recirculated flue gas flow rate by adjusting its opening (or rotation speed). Furthermore, primary and secondary air fans supply the fluidizing air and combustion air required for combustion, respectively. This modified architecture effectively dilutes the oxygen concentration and lowers the temperature in the combustion zone, thereby suppressing NOx formation. Simultaneously, the recirculation damper opening, along with the primary and secondary air volumes, constitutes the core set of operational variables that need to be coordinated and adjusted in subsequent optimization algorithms, providing a direct physical execution interface for achieving global economic optimization under safety and environmental constraints.

[0041] exist Figure 2 The basic workflow of the flue gas recirculation system shown begins with the mixing and fluidized combustion of fuel and primary air in the furnace. The resulting high-temperature flue gas, carrying the bed material, rises and undergoes gas-solid separation via a cyclone separator: solid particles are separated and returned to the furnace to maintain recirculation combustion, while the flue gas enters the tail flue. To reduce nitrogen oxide (NOx) formation, the system incorporates a flue gas recirculation stage: a portion of the low-temperature, low-oxygen tail flue gas is drawn back to the lower part of the furnace or the secondary air area through the recirculation flue. The introduction of recirculated flue gas dilutes the oxygen concentration in the combustion zone and lowers the combustion temperature, effectively suppressing the formation of thermal NOx. The recirculation flow rate is controlled by adjusting the opening of the flue gas recirculation damper in the flue, which is one of the key adjustable operating variables in the subsequent optimization method.

[0042] Furthermore, the primary air fan, secondary air fan, and induced draft fan in the system respectively perform the functions of fluidized combustion, staged air distribution, and maintaining furnace negative pressure. Their operating status (such as current and power) directly affects the boiler's energy consumption and economy. During operation, the entire system generates various collectable parameters in real time, including air volume, coal quantity, and furnace negative pressure reflecting the combustion state; flue gas composition (such as O2, NOx, and SO2 concentrations) reflecting environmental indicators; and damper opening degree and fan current reflecting equipment status. These parameters together constitute the physical data source for subsequent real-time sensing, evaluation, and optimization by the genetic algorithm-based optimization model.

[0043] In this embodiment, the boiler load parameters include main steam flow rate and feedwater flow rate. The combination of these two parameters accurately characterizes the boiler's overall energy output and water balance. Specifically: The main steam flow rate directly reflects the boiler's instantaneous output and is the most critical indicator for measuring the load. Feedwater flow rate: To maintain steam-water balance, the feedwater flow rate must match the main steam flow rate.

[0044] In this embodiment, fuel and combustion air parameters include total coal quantity, total primary air volume, total secondary air volume, furnace negative pressure, and coal quality data. These parameters directly describe the input and internal state of the combustion process. Specifically: Total coal quantity: The sum of fuel input, which is the basis for determining boiler output and combustion status; Total primary air volume: The air volume supplied from the bottom of the furnace to maintain the fluidization of the bed material is a prerequisite for ensuring stable combustion; Total secondary air volume: The combustion air volume supplied from the upper part of the furnace for staged combustion and burnout. Its ratio with the primary air volume is a key variable for optimizing combustion efficiency and reducing NOx. Furnace negative pressure: a key safety parameter reflecting the balance between induced draft and forced draft, which must be maintained within the specified range to prevent flame ejection or air leakage; Data on coal quality entering the furnace includes calorific value, volatile matter, and sulfur content. Changes in fuel characteristics directly affect combustion characteristics, pollutant generation, and optimal operating parameters, and are boundary conditions that optimization algorithms must adapt to.

[0045] In this embodiment, environmental parameters include flue gas temperature, fly ash carbon content, and flue gas composition (O2, CO, NOx, SO2, etc.). These parameters directly characterize the boiler's environmental performance and heat loss. Specifically: Flue gas temperature: The main factor affecting boiler flue gas heat loss; the higher the temperature, the lower the thermal efficiency. Carbon content in fly ash reflects the degree of fuel burnout. High carbon content indicates incomplete combustion and significant heat loss due to incomplete mechanical combustion. O2 concentration: reflects the excess air coefficient and directly affects combustion efficiency and exhaust heat loss; NOx concentration: a key environmental indicator. Its generation is closely related to combustion temperature, oxygen concentration and residence time, and it is the main control indicator for flue gas recirculation systems. SO2 concentration: reflects the sulfur content of fuel and desulfurization efficiency, and is related to environmental compliance and equipment corrosion.

[0046] In this embodiment, the actuator status parameters include the flue gas recirculation damper opening, primary air fan current, secondary air fan current, high-pressure fluidizing air fan current, and induced draft fan current. These parameters reflect the real-time operation and energy consumption of each key regulating device and are a direct indication of optimizable operation. Specifically: Flue gas recirculation damper opening: This is a direct variable controlling the flow rate of recirculated flue gas and is a core regulation method for suppressing NOx formation.

[0047] Primary air fan current, secondary air fan current, and induced draft fan current: These directly correspond to the real-time operating power (power consumption) of these main auxiliary machines. They constitute a significant portion of the plant's power consumption cost. The direct data source for this is the current value, and one of the optimization goals is to reduce these current values ​​to save plant power while ensuring combustion.

[0048] In conjunction with the first aspect, step S120 includes: S121, based on the real-time collected operating parameters, determine the fuel cost item, plant electricity cost item, and other operating cost items.

[0049] S122, the fuel cost item, the plant power cost item and other operating cost items are multiplied by an adjustable weighting coefficient and then summed to form a comprehensive economic evaluation function.

[0050] In this embodiment, it is expressed by the following formula:

[0051] in, The combination of operation variables to be optimized; Fuel cost is positively correlated with boiler thermal efficiency, which can be characterized by boiler thermal efficiency calculated using factors such as flue gas temperature and fly ash carbon content. The cost of electricity for plant use is mainly related to the current (power) of the primary air fan, secondary air fan, and induced draft fan; The costs incurred include heat loss from the cooling water and ammonia consumption.

[0052] , , These are the weighting coefficients for various costs, which can be set and adjusted manually according to the power plant's actual economic objectives.

[0053] In conjunction with the first aspect, step S130 includes: S131, select adjustable operating variables of the boiler to form a chromosome. The adjustable operating variables include at least the total coal feed, the ratio of primary and secondary air volume, the distribution ratio of secondary air volume in each layer, and the opening degree of flue gas recirculation damper.

[0054] In genetic algorithms, a chromosome represents a complete set of possible solutions, and each "gene" within a chromosome corresponds to an independently adjustable operating parameter. For example, a typical chromosome... It can be represented as:

[0055] in, Total coal quantity (or, under load command, represented by the total coal quantity correction factor); The ratio of primary wind to secondary wind volume; Assign a secondary air volume allocation ratio to each floor (e.g., upper floor / lower floor air volume ratio). : The opening degree of the flue gas recirculation damper For other adjustable variables.

[0056] This application selects the key operational variables in the boiler system that have the most direct and strongest coupling effect on economic operation and environmental emissions as genes, specifically including: Total coal feed: a fundamental variable that determines the boiler's energy input and directly affects load and combustion stability; The ratio of primary and secondary air volumes reflects the overall supply relationship between fluidizing air and combustion air, and is a core variable affecting combustion efficiency and the flow pattern inside the furnace. Secondary air volume distribution ratio of each layer: This reflects the strategy of staged air supply. By adjusting the ratio of secondary air volume between the upper and lower layers, the temperature and oxygen concentration distribution in the combustion zone can be controlled, thereby synergistically affecting combustion efficiency and NOx generation. Flue gas recirculation damper opening: This is an execution variable that directly controls the recirculated flue gas return flow rate and is a key adjustment method that couples combustion and pollutant control.

[0057] These variables are strongly coupled nonlinearly, making them difficult to coordinate using traditional manual or single-loop control. This application encodes them together into a chromosome, enabling genetic algorithms to perform collaborative search and overall optimization, rather than adjusting them in isolation.

[0058] S132, within the safe operating range of each of the adjustable operands, randomly generate multiple chromosomes to form the initial population.

[0059] In step S132, firstly, the safe operating range corresponds to the physical and technological constraints of each adjustable operational variable encoded as a gene (such as total coal feed, primary and secondary air ratio, secondary air distribution ratio, and flue gas recirculation damper opening). These ranges are determined based on the design limits of the boiler equipment, long-term operational safety regulations, and stringent environmental emission standards. For example, the upper limit of the coal feed is limited by the maximum output of the coal feeder, the fluctuation range of the furnace negative pressure is determined by structural safety and combustion stability, the secondary air ratio must ensure that the flame center does not shift to avoid coking, and the flue gas recirculation damper opening has its mechanical limits of being fully open and fully closed. These ranges ensure that any randomly generated set of parameters is physically feasible and will not cause immediate safety or environmental accidents. Secondly, randomly generating multiple chromosomes refers to using a random algorithm (such as uniformly distributed random numbers) to independently assign values ​​to each gene on each chromosome within the safe interval of each of the aforementioned variables, thereby generating a large number (e.g., hundreds) of individuals with different parameter combinations. The profound significance of this process lies in the initial population diversity it creates. Because the boiler optimization problem has highly nonlinear and multimodal characteristics (i.e., multiple local optima exist), if the initial solutions are concentrated around a certain empirical point, the algorithm is prone to getting trapped in that local optimum and failing to find a globally better solution. Random initialization allows the population to be evenly distributed throughout the vast, multidimensional safe solution space, greatly increasing the probability of the algorithm discovering the globally optimal region in subsequent selection, crossover, and mutation operations.

[0060] Finally, these N randomly generated chromosomes are treated as a whole to form an initial population, which is then submitted to a genetic algorithm for iterative evolution. This initial population is essentially an unbiased and systematic initial exploration of the boiler's optimal operating point by the algorithm, eliminating the mindset or operational blind spots that might result from relying solely on the operator's inherent experience. Thus, through step S132, this method can automatically and quickly search for the optimal operating point under any new operating conditions (such as load changes or coal quality fluctuations) starting from a broad and safe basic solution set, thereby dynamically and adaptively finding the optimal operating point under the current conditions. This effectively solves the drawbacks of slow response and the need for re-exploration in existing technologies.

[0061] In conjunction with the first aspect, step S140 includes: S141, for each chromosome in the current population, calculate the fitness value of the chromosome based on the comprehensive economic evaluation function and safety constraints.

[0062] For each chromosome, based on the constructed comprehensive economic evaluation function... The fitness value of a chromosome is calculated. A lower fitness value indicates that the corresponding operating plan is both safe and feasible, with lower total operating costs, thus giving it a greater advantage in the competition of genetic evolution. During the fitness evaluation process, chromosomes that violate safety constraints are penalized. The specific penalty conditions are as follows: Exceeding limits for main steam and reheat steam parameters: If the operating scheme corresponding to the chromosome causes the predicted main steam temperature or main steam pressure, or reheat steam outlet temperature to exceed the allowable operating deviation range of its target setting (e.g., temperature deviation exceeding ±5℃, pressure deviation exceeding ±0.5MPa), it is considered a violation of core process constraints and a penalty will be imposed.

[0063] Furnace negative pressure exceeding the limit: If the predicted furnace negative pressure exceeds the safe operating range (e.g., above -50Pa or below -300Pa), it may endanger the safety of the furnace structure or affect the combustion stability, and a penalty will be imposed.

[0064] Low oxygen content in flue gas: If the predicted oxygen content in the flue gas is below the safe lower limit (e.g., below 2.0%) to ensure complete combustion and prevent a sharp rise in carbon monoxide (CO) and unstable combustion, a penalty is imposed.

[0065] Exceeding pollutant emission standards: If the predicted NOx or SO2 concentration in the flue gas exceeds the prescribed environmental emission limits, penalties will be imposed.

[0066] Critical actuator over-limit: If the flue gas recirculation damper opening command encoded in the chromosome exceeds its mechanical travel range, or if the calculated required primary fan, secondary fan, or induced draft fan current (or power) exceeds its rated operating capacity, a penalty will be imposed.

[0067] Fluidization and combustion stability risks: If significant risks affecting combustion stability, such as poor fluidization, excessively high or low bed temperature, are predicted based on operating variables (such as primary air volume and fuel quantity), penalties will be imposed.

[0068] Specifically, the security constraint penalty mechanism defines a penalty function. To achieve this, in which This represents the combination of operands corresponding to chromosomes. The penalty function... The rules for determining the value are as follows: If chromosome If the corresponding operating scheme satisfies all safety constraints, then ; If chromosome If one or more safety constraints are violated, then ,in It is a preset maximum positive number penalty value.

[0069] When calculating the fitness value of the chromosome, the penalty function is used. With the aforementioned comprehensive economic evaluation function The sums are used to obtain the final fitness value for evaluation by the genetic algorithm. :

[0070] By Set it to an order of magnitude higher than the total cost that the boiler might incur during normal operation (e.g.) This ensures that any infeasible solution that violates safety, environmental, or equipment constraints can be prevented. These will all become extremely poor, thus being naturally eliminated in subsequent selection operations. Mathematically, this mechanism is equivalent to strictly restricting the search space of the genetic algorithm to a feasible region that satisfies all hard constraints.

[0071] S142, based on fitness values, select chromosomes from the current population through a selection operation.

[0072] Step S142, based on the fitness value calculated in S141, selects a dominant individual from the current population as the "parent" for the next generation (offspring). It follows the basic principle that "the smaller the fitness value (the lower the total operating cost and the safer and more feasible), the higher the probability of survival and reproduction." Specifically, it typically employs one of the following two strategies: Roulette wheel selection: This method assigns each chromosome a selection probability inversely proportional to its fitness value. First, the fitness values ​​of all individuals in the population are converted into a probability distribution (similar to a sector on a roulette wheel, with individuals having higher fitness values ​​occupying a larger sector). Then, multiple parent individuals are independently selected by randomly simulating multiple roulette wheel spins. This method ensures that every individual has a chance to be selected, but superior individuals have a significantly higher probability of being selected, thus statistically guaranteeing a continuous improvement in the overall quality of the population.

[0073] Tournament selection: This method is more direct and efficient. It randomly selects a fixed number of individuals (e.g., 2) from the population each time, compares their fitness values, and directly selects the better individual (with a lower fitness value) as the parent. This process is repeated until the required number of parents is selected. This method not only highlights the advantage of elite individuals but is also computationally simple and has good parallelism.

[0074] By selecting operations, the genetic information of chromosomes (i.e., combinations of operational variables) that represent more economical and safer operating schemes is preserved and enters the subsequent reproduction stage. This is the fundamental driving force for the optimization process to converge toward a lower-cost region.

[0075] S143, perform crossover and mutation operations on the selected chromosomes in sequence to generate a new offspring population.

[0076] First, the selected parent chromosomes are randomly paired. For each parent pair, a pre-set crossover probability (usually high, such as 0.8) is used to determine whether crossover occurs. If crossover occurs, one or more gene exchange points are randomly selected, and the gene values ​​of corresponding segments on their chromosomes are exchanged. For example, parent A's gene encoding is [coal feed rate A, ratio A, damper opening A], and parent B's is [coal feed rate B, ratio B, damper opening B]. After crossover, offspring may be produced as [coal feed rate A, ratio B, damper opening A] and [coal feed rate B, ratio A, damper opening B]. The physical significance of this process in boiler optimization lies in its attempt to systematically combine different excellent solutions. For example, combining an excellent coal feeding strategy from one solution with an efficient airflow ratio from another solution may create a completely new operating solution with overall performance surpassing either parent.

[0077] For the offspring chromosomes generated through crossover, any gene on them is randomly altered with a pre-set, low mutation probability (e.g., 0.01). For example, the "flue gas recirculation damper opening" gene value of a certain offspring chromosome can be randomly adjusted to another value within its safe operating range. Mutation operations are crucial for the algorithm to maintain its exploratory capabilities and avoid getting trapped in local optima.

[0078] S144, use the offspring population as the current population for the next iteration, repeat until the preset termination condition is met.

[0079] Once a new offspring population is generated through crossover and mutation operations, it replaces its parent population and officially becomes the "current population" for the algorithm's next round of evaluation and optimization. This means that the theoretically more promising solutions generated after optimization and recombination in the previous round will serve as the starting point for a new round of exploration. This intergenerational transmission mechanism simulates the process of biological population evolution, enabling the search for the optimal operating point of the boiler to continue in a targeted and continuous manner.

[0080] The termination conditions preset in this application include: A. Reaching the maximum number of iterations: When the number of iterations reaches a preset limit (e.g., 500 iterations), the algorithm will stop regardless of the current result and output the currently found optimal solution. This prevents the algorithm from getting stuck in an infinite loop in extreme cases; B. Population convergence criterion: This is typically manifested as the fitness value (i.e., the lowest total operating cost) of the best individual in the population no longer significantly improving over multiple generations (e.g., 50 generations) (e.g., the improvement is less than a very small threshold). This indicates that the algorithm has fully explored the current solution space and stabilized at an optimal or near-optimal platform, making it unlikely that further iterations will produce significant improvements.

[0081] C. Running time limit: If the total optimization calculation time exceeds the preset value (e.g., 5 minutes), the process will terminate and the current optimal solution will be output to ensure real-time performance.

[0082] Understandably, as long as the termination condition is not met, this generation-evaluation-selection-regeneration cycle will continue to run, driving the population to continuously migrate towards regions with lower total cost within the safe and feasible solution space. More importantly, this cycle can be linked with the boiler's real-time data acquisition (step S110). Once external operating conditions (such as load commands and coal quality) change, causing a decline in the performance of the original optimal solution, this continuous iterative process can dynamically re-optimize based on the latest operating data, automatically adjusting to the optimal set of operating parameters to adapt to the new operating conditions. This fundamentally solves the shortcomings of existing technologies in adapting to changes in operating conditions and their lag.

[0083] In conjunction with the first aspect, step S150 includes: S151, according to the predefined encoding rules, the gene values ​​contained in the optimal chromosome are mapped to the specific values ​​of the corresponding adjustable boiler operation variables, thereby obtaining the target economic operation parameter set.

[0084] Step S151 operates on the optimal chromosome output by the genetic algorithm after the termination condition is met. This chromosome is a gene sequence representing the globally (or near-globally) optimal solution, selected by the algorithm from a massive number of possible solutions through evolution. The decoding process strictly follows the one-to-one encoding rules established in step S130 (encoding and initialization), which is essentially a deterministic inverse mapping function.

[0085] Understandably, during encoding, each "adjustable boiler operating variable" (such as total coal feed, primary and secondary air volume ratio, secondary air volume distribution ratio at each level, and flue gas recirculation damper opening) is converted and normalized into a value within a specific range, serving as a "gene value" on the chromosome. During decoding, the values ​​at each gene position on the optimal chromosome are reverse-engineered back to the specific physical dimensions and engineering values ​​of the corresponding operating variable, according to the exact same rules. For example, if the encoding rules stipulate that the gene value of "flue gas recirculation damper opening" is 0.0 representing fully closed (0%) and 1.0 representing fully open (100%), and the value of this gene on the optimal chromosome is 0.75, then the decoded operating instruction is to set the flue gas recirculation damper opening to 75%.

[0086] Once all the genes have been decoded one by one, these restored values ​​collectively constitute a complete and executable set of target economic operation parameters. This parameter set is a structured set of instructions. Understandably, the target economic operating parameter set obtained through decoding is no longer an abstract mathematical solution, but rather a target setpoint that the boiler distributed control system (DCS) can directly identify, accept, and use to set the control loop. This step ensures seamless integration between the output of the intelligent algorithm and the existing industrial automation infrastructure, enabling the theoretical results of global optimization to be transformed into direct productivity improvements in the actual economic efficiency, safety, and environmental friendliness of the boiler.

[0087] Following step S160, the target economic operating parameters output in step S150 are sent as setpoints to the corresponding control loops in the DCS to achieve closed-loop optimization control. In practical applications, these parameters can also be displayed as suggested values ​​to operators for manual adjustment and optimization of system operation.

[0088] Secondly, embodiments of this application also provide a boiler operation optimization device based on a genetic algorithm, such as... Figure 3 As shown, the device includes: acquisition module 10, construction module 20, initialization module 30, iteration module 40, decoding module 50 and control module 60.

[0089] The acquisition module 10 is used to acquire boiler operating parameters in real time. The operating parameters include at least boiler load parameters, combustion parameters, environmental protection parameters, and actuator status parameters.

[0090] Module 20 is used to construct a comprehensive economic evaluation function with the goal of minimizing total operating cost, which serves as the fitness function of the genetic algorithm.

[0091] Initialization module 30 is used to encode a set of adjustable boiler operating variables into chromosomes and initialize the population.

[0092] The iteration module 40 is used to iteratively optimize the population based on the fitness function and the safety constraints of boiler operation using a genetic algorithm until the preset termination condition is met, and output the optimal chromosome.

[0093] The decoding module 50 is used to decode the optimal chromosome to obtain the target economic operating parameter set.

[0094] The control module 60 is used to control the boiler operation based on the target economic operating parameter set.

[0095] Thirdly, embodiments of this application provide a boiler operation optimization system based on a genetic algorithm, the system comprising: The data acquisition unit is used to communicate with the boiler's distributed control system and collect the boiler's operating parameters in real time.

[0096] In this embodiment, the data acquisition unit serves as the system's perception layer and data entry point. It seamlessly connects to the boiler's existing distributed control system (DCS) via standard industrial communication interfaces (such as OPC and Modbus). Its core function is to acquire all key operating parameters defined in the claims in real-time and at high frequency, including four categories of parameters: boiler load, combustion, environmental protection, and actuator status. This unit ensures that the data foundation upon which the optimization algorithm relies is timely, accurate, and comprehensive, thereby accurately reflecting the boiler's instantaneous operating conditions.

[0097] The optimized computing unit is connected to the data acquisition unit and is equipped with a processor and a memory. The memory stores an executable program, and the processor is configured to execute the program to implement the method described above.

[0098] In this embodiment, the optimization computing unit is the intelligent core and decision engine of the system. It is typically implemented by an industrial control computer, server, or high-performance embedded controller, and its hardware configuration includes a processor (CPU) and memory. An executable program implementing all the method steps of the first aspect is pre-stored in the storage medium (such as a hard disk or solid-state drive). The processor is configured to load and run this program, specifically executing: receiving data from the data acquisition unit, constructing and updating the economic evaluation model, running a genetic algorithm for iterative optimization (including population initialization, fitness evaluation, selection, crossover, mutation, convergence judgment, etc.), and finally decoding to obtain the target economic operating parameter set. The design of this unit enables complex intelligent algorithms to run reliably and stably in industrial settings.

[0099] The control output unit, connected to the optimization calculation unit, is used to receive the target economic operating parameter set and convert it into control commands to be sent to the boiler's distributed control system to adjust the boiler operation.

[0100] In this embodiment, the control output unit serves as the system execution layer and action interface. It receives the optimal parameter set from the optimization calculation unit and converts this set of mathematical results into standardized control commands (such as setpoints, analog output signals, etc.) that the boiler DCS can recognize and execute. Subsequently, these commands are sent back to the boiler DCS via the communication link, and the DCS drives specific actuators (such as adjusting the coal feeder speed, fan dampers, circulation dampers, etc.) to perform actions, thereby completing the automatic adjustment of boiler operation.

[0101] The human-machine interface unit is connected to the optimization calculation unit and the control output unit. It is used to receive instructions from the operator, set optimization parameters, and display the real-time operating status and optimization results.

[0102] In this embodiment, the human-computer interaction unit serves as both the system monitoring layer and the user interface. It typically consists of devices such as a display screen, keyboard, and mouse, and provides a graphical monitoring interface in software. Its main functions include: Input and settings: Allows operators to input or modify optimization target weights, algorithm parameters, safety constraint thresholds, etc. Monitoring and display: Real-time display of boiler operating status, calculation process of optimization algorithm, historical optimization trajectory and final recommended optimization parameters; Supervision and Intervention: Provides the authority to finalize, manually modify, or suspend the execution of optimization instructions, ensuring that operators always retain supreme control and comply with industrial safety procedures.

[0103] The data stream flows from the data acquisition unit into the optimization calculation unit, where it undergoes intelligent processing to generate optimization results. These results are then applied to the physical boiler via the control output unit, forming an automatic control closed loop of perception-optimization-execution. Simultaneously, the human-machine interface unit provides parameter setting, status monitoring, and safety supervision throughout this closed loop. This system architecture not only transforms the optimization method of this application from theory into a deployable industrial product, but also, through the integration of hardware and software, ultimately achieves real-time, online, adaptive global economic optimization of CFB boilers with flue gas recirculation, fundamentally solving the industry problems of reliance on human experience, slow response, and difficulty in coordination.

[0104] Fourthly, embodiments of this application provide an electronic device, combined with Figure 4 As shown, the electronic device includes a memory 131 and a processor 130. The memory 131 stores a computer program, and the processor 130 runs the computer program to make the electronic device perform the above-described method.

[0105] Furthermore, combined Figure 4 The electronic device shown also includes a bus 132 and a communication interface 133, with the processor 130, the communication interface 133 and the memory 131 connected via the bus 132.

[0106] The memory 131 may include high-speed random access memory (RAM) and may also include non-volatile memory, such as at least one disk storage device. Communication between this system network element and at least one other network element is achieved through at least one communication interface 133 (which can be wired or wireless), such as the Internet, wide area network, local area network, metropolitan area network, etc. The bus 132 may be an ISA bus, PCI bus, or EISA bus, etc. The bus can be divided into address bus, data bus, control bus, etc. For ease of representation, Figure 4 The symbol is represented by a single double-headed arrow, but this does not mean that there is only one bus or one type of bus.

[0107] Processor 130 may be an integrated circuit chip with signal processing capabilities. In implementation, each step of the above method can be completed by the integrated logic circuitry in the hardware of processor 130 or by instructions in software form. Processor 130 may be a general-purpose processor, including a Central Processing Unit (CPU), a Network Processor (NP), etc.; it may also be a Digital Signal Processor (DSP), an Application Specific Integrated Circuit (ASIC), a Field-Programmable Gate Array (FPGA), or other programmable logic devices, discrete gate or transistor logic devices, or discrete hardware components. It can implement or execute the methods, steps, and logic block diagrams disclosed in the embodiments of this invention. The general-purpose processor may be a microprocessor or any conventional processor. The steps of the methods disclosed in the embodiments of this invention can be directly manifested as execution by a hardware decoding processor, or execution by a combination of hardware and software modules in the decoding processor. The software module can reside in a mature storage medium in the art, such as random access memory, flash memory, read-only memory, programmable read-only memory, electrically erasable programmable memory, or registers. This storage medium is located in memory 131, and processor 130 reads the information in memory 131 and, in conjunction with its hardware, completes the steps of the method described in the foregoing embodiments.

[0108] Fifthly, embodiments of this application provide a readable storage medium storing computer program instructions, which are read and executed by a processor to perform the above-described method.

[0109] Those skilled in the art will clearly understand that, for the sake of convenience and brevity, the specific working process of the system and apparatus described above can be referred to the corresponding process in the foregoing method embodiments, and will not be repeated here.

[0110] Furthermore, in the description of the embodiments of the present invention, unless otherwise explicitly specified and limited, the terms "installation," "connection," and "linking" should be interpreted broadly. For example, they can refer to a fixed connection, a detachable connection, or an integral connection; they can refer to a mechanical connection or an electrical connection; they can refer to a direct connection or an indirect connection through an intermediate medium; and they can refer to the internal connection of two components. Those skilled in the art can understand the specific meaning of the above terms in the present invention based on the specific circumstances.

[0111] If the aforementioned functions are implemented as software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this invention, or the part that contributes to the prior art, or a portion of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of this invention. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0112] In the description of this invention, it should be noted that the terms "center," "upper," "lower," "left," "right," "vertical," "horizontal," "inner," and "outer," etc., indicate the orientation or positional relationship based on the orientation or positional relationship shown in the accompanying drawings. They are used only for the convenience of describing the invention and for simplifying the description, and do not indicate or imply that the device or element referred to must have a specific orientation, or be constructed and operated in a specific orientation. Therefore, they should not be construed as limitations on the invention. Furthermore, the terms "first," "second," and "third" are used for descriptive purposes only and should not be construed as indicating or implying relative importance.

[0113] Finally, it should be noted that the above embodiments are merely specific implementations of the present invention, used to illustrate the technical solutions of the present invention, and not to limit it. The scope of protection of the present invention is not limited thereto. Although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that any person skilled in the art can still modify or easily conceive of changes to the technical solutions described in the foregoing embodiments within the technical scope disclosed in the present invention, or make equivalent substitutions for some of the technical features; and these modifications, changes, or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of the present invention, and should all be covered within the scope of protection of the present invention. Therefore, the scope of protection of the present invention should be determined by the scope of the claims.

Claims

1. A boiler operation optimization method based on genetic algorithm, characterized in that, The method includes: The boiler's operating parameters are collected in real time, including at least boiler load parameters, combustion parameters, environmental protection parameters, and actuator status parameters. A comprehensive economic evaluation function with the goal of minimizing total operating cost is constructed and used as the fitness function of the genetic algorithm. Encode a set of adjustable boiler operating variables into chromosomes and initialize the population; Based on the fitness function and the safety constraints of boiler operation, a genetic algorithm is used to iteratively optimize the population until the preset termination condition is met, and the optimal chromosome is output. Decode the optimal chromosome to obtain the target economic operation parameter set; The boiler operation is controlled based on the target set of economic operating parameters.

2. The method according to claim 1, characterized in that, The boiler load parameters include main steam flow and feedwater flow; the combustion parameters include total coal quantity, total primary air volume, total secondary air volume, furnace negative pressure, and coal quality data; the environmental protection parameters include flue gas temperature, fly ash carbon content, and O2, NOx, and SO2 concentrations in the flue gas; and the actuator status parameters include flue gas recirculation damper opening, primary air fan current, secondary air fan current, and induced draft fan current.

3. The method according to claim 1, characterized in that, The steps for constructing a comprehensive economic evaluation function with the objective of minimizing total operating cost, which serves as the fitness function of the genetic algorithm, include: Based on the real-time collected operating parameters, determine the fuel cost item, plant electricity cost item, and other operating cost items; The comprehensive economic evaluation function is formed by multiplying the fuel cost item, the plant electricity cost item, and other operating cost items by an adjustable weighting coefficient and then summing the results.

4. The method according to claim 1, characterized in that, The steps of encoding a set of adjustable boiler operating variables into chromosomes and initializing the population include: The adjustable operating variables of the boiler are selected to form the chromosome. The adjustable operating variables include at least the total coal feed, the ratio of primary and secondary air volume, the distribution ratio of secondary air volume in each layer, and the opening of the flue gas recirculation damper. Multiple chromosomes are randomly generated within the safe operating range of each of the adjustable operands to form an initial population.

5. The method according to claim 1, characterized in that, Based on the fitness function and the safety constraints of boiler operation, the step of using a genetic algorithm to iteratively optimize the population until a preset termination condition is met and outputting the optimal chromosome includes: For each chromosome in the current population, calculate the fitness value of the chromosome based on the comprehensive economic evaluation function and the security constraints; Based on the fitness value, chromosomes are selected from the current population through a selection operation; The selected chromosomes are subjected to crossover and mutation operations in sequence to generate a new offspring population; The offspring population is used as the current population for the next iteration, and this process is repeated until the preset termination condition is met.

6. The method according to claim 1, characterized in that, The steps of decoding the optimal chromosome to obtain the target economic operation parameter set include: According to predefined encoding rules, the gene values ​​contained in the optimal chromosome are mapped to the specific values ​​of the corresponding adjustable boiler operation variables, thereby obtaining the target economic operation parameter set.

7. A boiler operation optimization device based on a genetic algorithm, characterized in that, The device includes: The data acquisition module is used to acquire the operating parameters of the boiler in real time. The operating parameters include at least boiler load parameters, combustion parameters, environmental protection parameters, and actuator status parameters. The module is used to construct a comprehensive economic evaluation function with the goal of minimizing the total operating cost, which serves as the fitness function of the genetic algorithm. An initialization module is used to encode a set of adjustable boiler operating variables into chromosomes and initialize the population; The iterative module is used to iteratively optimize the population using a genetic algorithm based on the fitness function and the safety constraints of boiler operation until a preset termination condition is met, and then output the optimal chromosome. The decoding module is used to decode the optimal chromosome to obtain the target economic operating parameter set; The control module is used to control the operation of the boiler based on the target economic operating parameter set.

8. A boiler operation optimization system based on a genetic algorithm, characterized in that, The system includes: The data acquisition unit is used to communicate with the boiler's distributed control system and collect the boiler's operating parameters in real time. An optimized computing unit is connected to the data acquisition unit and is equipped with a processor and a memory. The memory stores an executable program, and the processor is configured to execute the program to implement the method as described in any one of claims 1 to 6. A control output unit, connected to the optimization calculation unit, is used to receive the target economic operating parameter set, convert it into control commands, and send them to the distributed control system of the boiler to adjust the boiler operation. The human-computer interaction module is communicatively connected to the optimization calculation unit and the control output unit, and is used to receive instructions from the operator, set optimization parameters, and display real-time operating status and optimization results.

9. An electronic device, characterized in that, The electronic device includes a memory and a processor, the memory storing a computer program and the processor running the computer program to cause the electronic device to perform the method of any one of claims 1 to 6.

10. A storage medium, characterized in that, The storage medium stores computer program instructions, which, when read and executed by a processor, perform the method described in any one of claims 1 to 6.

Images