A coal dynamic distribution method and system for a thermal power plant

Abstract

This invention relates to the field of thermal power generation technology and discloses a method and system for dynamic coal allocation in thermal power plants. The method includes: acquiring current operating parameters of the thermal power unit; determining unit status parameters based on the current operating parameters; determining coal demand parameters based on the unit status parameters; generating multiple coal allocation strategies based on the coal demand parameters; establishing a unit simulation model; simulating the operation of the coal allocation strategies using the unit simulation model; and outputting operational fluctuation sets corresponding to the multiple coal allocation strategies. The invention also involves constructing a fitness function based on the operational fluctuation sets and optimizing the fitness function using a particle swarm optimization algorithm to obtain the optimal coal allocation strategy. This invention enables dynamic optimization of the coal allocation strategy for thermal power units, improving the stability of thermal power unit operation.

Description

Technical Field

[0001] This application relates to the field of thermal power generation technology, and more specifically, to a method and system for dynamic coal allocation in thermal power plants. Background Technology

[0002] Thermal power plants are one of the world's main methods of power generation. During operation, the energy consumption level of the generating units directly impacts the plant's economic efficiency. Therefore, accurately assessing and allocating the required coal for the generating units is crucial for improving the power plant's energy efficiency and economic benefits.

[0003] However, traditional coal allocation methods for power units generally have certain limitations, making it difficult to achieve efficient and stable coal allocation strategies. There is an urgent need for a scientific and practical dynamic coal allocation method for power units. Summary of the Invention

[0004] This invention provides a dynamic coal allocation method for thermal power plants to solve the problem of difficulty in obtaining efficient and stable coal allocation strategies in existing technologies, including:

[0005] The system acquires the current operating parameters of the thermal power unit, determines the unit status parameters based on these parameters, and then determines the coal demand parameters. Multiple coal allocation strategies are generated based on the coal demand parameters, and a unit simulation model is established. The system then simulates the operation of the coal allocation strategies using the simulation model, outputting the operational fluctuation sets corresponding to each strategy. A fitness function is constructed based on these fluctuation sets, and the fitness function is optimized using a particle swarm optimization algorithm to obtain the optimal coal allocation strategy.

[0006] Further, the unit status parameters are determined based on the current thermal power unit operating parameters, including: obtaining a historical set of unit operating parameters; establishing a sample dataset based on the historical set of unit operating parameters; randomly selecting k cluster centers from the sample dataset; calculating the Euclidean distance from each sample data point in the sample dataset to the initial cluster center; assigning each sample data point to its corresponding cluster based on the Euclidean distance from the initial cluster center; calculating the mean of the sample data within each cluster; recalculating the cluster center based on the mean of the sample data within each cluster; iteratively calculating the cluster center of each cluster until the cluster center no longer changes or the number of iterations reaches the preset maximum number of iterations, thus obtaining the clustering result; calculating the similarity between the current operating parameters and the corresponding cluster centers of each cluster; selecting the cluster center with the highest similarity to the current operating parameters to obtain similar cluster centers; and determining the unit status parameters corresponding to the current operating parameters based on the similar cluster centers.

[0007] Furthermore, determining the unit status parameters corresponding to the current operating parameters based on similar cluster centers includes: obtaining preset standard status parameters, calculating the difference between the cluster center value of the similar cluster centers and the preset standard status parameters, and determining the unit status parameters based on the difference between the cluster center value and the preset standard status parameters.

[0008] Furthermore, the coal demand parameters are determined based on the unit status parameters, including: obtaining the preset standard coal demand parameters of the current thermal power unit, and correcting the preset standard coal demand parameters based on the unit status parameters to obtain the coal demand parameters.

[0009] Furthermore, multiple coal allocation strategies are generated based on coal demand parameters, including: obtaining historical coal demand parameters and corresponding coal allocation strategies of thermal power units; establishing a training dataset based on historical coal demand parameters and corresponding coal allocation strategies; establishing a strategy generation model based on the training dataset and training the strategy generation model to obtain a trained strategy generation model; and inputting the current coal demand parameters into the trained strategy generation model to generate multiple coal allocation strategies.

[0010] Furthermore, a unit simulation model is established, and the operation of the coal allocation strategy is simulated based on the unit simulation model. The operation fluctuation set corresponding to multiple coal allocation strategies is output, including: establishing a unit simulation model based on the current thermal power unit operating parameters, inputting each coal allocation strategy into the unit simulation model, simulating the operation process of the thermal power unit, and determining the operation fluctuation set of each coal allocation strategy based on the simulation results.

[0011] Furthermore, based on the simulation results, the operational fluctuation set for each coal allocation strategy is determined, including: determining the main steam pressure changes for each coal allocation strategy based on the simulation results; plotting the main steam pressure change curve based on the main steam pressure changes; statistically analyzing the starting point, peak point, valley point, and ending point of the main steam pressure change curve, marking these points as reference points; statistically analyzing the intervals between adjacent reference points on the main steam pressure change curve to obtain fluctuation intervals, determining the total number of fluctuation intervals as the first operational fluctuation value; calculating the absolute difference between the corresponding data of adjacent reference points on the main steam pressure change curve, determining the average of the absolute differences of all data as the second operational fluctuation value; obtaining a preset standard main steam pressure change curve, calculating the correlation coefficient between the main steam pressure change curve and the preset standard main steam pressure change curve, performing a negative correlation mapping on the correlation coefficient to obtain the third operational fluctuation value; and establishing an operational fluctuation set based on the first, second, and third operational fluctuation values.

[0012] Furthermore, constructing a fitness function based on the running fluctuation set includes: constructing a fitness function based on the running fluctuation set, the expression of which is,

[0013] in, The first operating fluctuation value, This is the second operating fluctuation value. This is the third operating fluctuation value. , , These are the preset first weight, preset second weight, and preset third weight, respectively.

[0014] Furthermore, the optimization of the fitness function based on the particle swarm optimization algorithm to obtain the optimal coal allocation strategy includes: Step 1, randomly initializing the velocity and position of each particle in the search space, calculating the fitness function value of each particle, and obtaining the individual optimal value and the global optimal value of the particle; Step 2, updating the velocity and position of each particle according to the individual optimal value and the global optimal value; Step 3, evaluating the fitness function value of the particle, and updating the individual optimal value and the global optimal value of the particle; Step 4, determining whether the particle swarm optimization algorithm meets the convergence condition. If it does, outputting the global optimal value and ending the process, determining the optimal coal allocation strategy based on the global optimal value; otherwise, repeating steps 1 to 3.

[0015] To achieve the above objectives, the present invention also provides a dynamic coal distribution system for thermal power plants, comprising: The demand module is used to obtain the current operating parameters of the thermal power unit, determine the unit status parameters based on the current operating parameters, and determine the coal demand parameters based on the unit status parameters. The simulation module is used to generate multiple coal allocation strategies based on the coal demand parameters, establish a unit simulation model, simulate the operation of the coal allocation strategies based on the unit simulation model, and output the operation fluctuation sets corresponding to multiple coal allocation strategies. The allocation module is used to construct a fitness function based on the operation fluctuation sets, optimize the fitness function based on the particle swarm optimization algorithm, and obtain the optimal coal allocation strategy.

[0016] The beneficial effects of this invention are as follows: By applying the above technical solution, this invention obtains the current operating parameters of the thermal power unit, determines the unit status parameters based on these parameters, and then determines the coal demand parameters based on these parameters. Multiple coal allocation strategies are generated based on the coal demand parameters, a unit simulation model is established, and the coal allocation strategies are simulated using the simulation model, outputting operational fluctuation sets corresponding to each strategy. A fitness function is constructed based on these fluctuation sets, and the fitness function is optimized using a particle swarm optimization algorithm to obtain the optimal coal allocation strategy. This invention enables dynamic optimization of the coal allocation strategy for thermal power units, improving the operational stability of the units. Attached Figure Description

[0017] To more clearly illustrate the technical solutions in the embodiments of this application, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0018] Figure 1 A general flowchart of a dynamic coal allocation method for thermal power plants proposed in an embodiment of the present invention is shown; Figure 2 A schematic diagram of the structure of a dynamic coal distribution system for a thermal power plant, as proposed in an embodiment of the present invention, is shown. Detailed Implementation

[0019] The technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, and not all embodiments. Based on the embodiments of this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.

[0020] This application provides a method for dynamic coal allocation in a thermal power plant, such as... Figure 1 As shown, it includes: S101: Obtain the current operating parameters of the thermal power unit, determine the unit status parameters based on the current operating parameters of the thermal power unit, and determine the coal demand parameters based on the unit status parameters. In some embodiments of this application, determining the unit status parameters based on the current thermal power unit operating parameters includes: acquiring a historical set of unit operating parameters; establishing a sample dataset based on the historical set of unit operating parameters; randomly selecting k cluster centers from the sample dataset; calculating the Euclidean distance from each sample data point in the sample dataset to the initial cluster center; dividing each sample data point into corresponding clusters based on the Euclidean distance from each sample data point in the sample dataset to the initial cluster center; calculating the mean of the sample data within each cluster; recalculating the cluster center based on the mean of the sample data within each cluster; iteratively calculating the cluster center of each cluster until the cluster center no longer changes or the number of iterations reaches a preset maximum number of iterations, obtaining the clustering result; calculating the similarity between the current operating parameters and the corresponding cluster centers of each cluster; selecting the cluster center with the highest similarity to the current operating parameters to obtain similar cluster centers; and determining the unit status parameters corresponding to the current operating parameters based on the similar cluster centers.

[0021] In this embodiment, the operating parameters of the thermal power unit include load, main steam pressure, main steam temperature, feedwater flow rate, and flue gas temperature. By performing k-means clustering on the historical unit operating parameters, five clusters are obtained. Each cluster corresponds to a typical operating mode of a unit. The similarity is determined by the reciprocal of the deviation between the current unit operating parameters and the corresponding cluster centers of each cluster, and the cluster center with the highest similarity is obtained.

[0022] In some embodiments of this application, determining the unit status parameters corresponding to the current operating parameters based on similar cluster centers includes: obtaining preset standard status parameters, calculating the difference between the cluster center value of the similar cluster centers and the preset standard status parameters, and determining the unit status parameters based on the difference between the cluster center value and the preset standard status parameters.

[0023] In this embodiment, the difference between the cluster center value of similar cluster centers and the preset standard state parameter is used as the unit state parameter.

[0024] In some embodiments of this application, determining the coal demand parameters based on the unit status parameters includes: obtaining the preset standard coal demand parameters of the current thermal power unit, and correcting the preset standard coal demand parameters based on the unit status parameters to obtain the coal demand parameters.

[0025] In this embodiment, the unit status parameters are standardized and their range is set to [0, 2]. The standardized unit status parameters are multiplied by the preset standard coal demand parameters to obtain the coal demand parameters.

[0026] S102, generate multiple coal allocation strategies based on coal demand parameters, establish a unit simulation model, simulate the operation of the coal allocation strategies based on the unit simulation model, and output the operation fluctuation set corresponding to multiple coal allocation strategies. In some embodiments of this application, multiple coal allocation strategies are generated based on coal demand parameters, including: obtaining historical coal demand parameters of thermal power units and corresponding coal allocation strategies; establishing a training dataset based on historical coal demand parameters and corresponding coal allocation strategies; establishing a strategy generation model based on the training dataset and training the strategy generation model to obtain a trained strategy generation model; and inputting the current coal demand parameters into the trained strategy generation model to generate multiple coal allocation strategies.

[0027] In this embodiment, historical coal demand parameters of thermal power units and corresponding coal allocation strategies that have been proven effective in practice are obtained to form training sample pairs and establish a training dataset. A strategy generation model is established based on a long short-term memory network model and trained on the training dataset until its loss function converges. The current coal demand parameters are input into the trained strategy generation model, and the strategy generation model uses the mapping rules it has learned to generate multiple coal allocation strategies with differences.

[0028] In some embodiments of this application, a unit simulation model is established, and the operation of the coal allocation strategy is simulated based on the unit simulation model to output multiple sets of operation fluctuations corresponding to the coal allocation strategies. This includes: establishing a unit simulation model based on the current thermal power unit operating parameters, inputting each coal allocation strategy into the unit simulation model, simulating the operation process of the thermal power unit, and determining the set of operation fluctuations for each coal allocation strategy based on the simulation results.

[0029] In this embodiment, a high-fidelity unit simulation model is established based on the current operating parameters of the thermal power unit. This model can simulate the dynamic process from the issuance of coal allocation instructions to the response of key operating parameters. Each coal allocation strategy is used as input and injected into the unit simulation model to simulate the operation process of the thermal power unit over a period of time. Based on the simulation results, the change curves of key parameters are extracted to determine the operational fluctuation set of each coal allocation strategy.

[0030] In some embodiments of this application, determining the operational fluctuation set of each coal allocation strategy based on simulation results includes: determining the main steam pressure change of each coal allocation strategy based on simulation results; plotting the main steam pressure change curve based on the main steam pressure change; statistically analyzing the starting point, peak point, valley point, and ending point of the main steam pressure change curve, and marking the starting point, peak point, valley point, and ending point of the main steam pressure change curve as reference points; statistically analyzing the intervals between adjacent reference points on the main steam pressure change curve to obtain fluctuation intervals, and determining the total number of fluctuation intervals as the first operational fluctuation value; calculating the absolute difference of the corresponding data of adjacent reference points on the main steam pressure change curve, and determining the average of the absolute differences of all data as the second operational fluctuation value; obtaining a preset standard main steam pressure change curve, calculating the correlation coefficient between the main steam pressure change curve and the preset standard main steam pressure change curve, performing negative correlation mapping on the correlation coefficient to obtain the third operational fluctuation value; and establishing an operational fluctuation set based on the first operational fluctuation value, the second operational fluctuation value, and the third operational fluctuation value.

[0031] In this embodiment, an operational fluctuation set is established by monitoring the fluctuation of the main steam pressure change curve. The frequency of parameter changes is determined by the number of fluctuation intervals of the main steam pressure change curve, resulting in a first operational fluctuation value. The average amplitude of parameter fluctuations is determined by the absolute difference of the corresponding data of each adjacent reference point on the main steam pressure change curve, resulting in a second operational fluctuation value. The deviation between the current fluctuation state and the ideal stable state is determined by the correlation coefficient between the main steam pressure change curve and the preset standard main steam pressure change curve, resulting in a third operational fluctuation value. The three operational fluctuation values ​​are combined into an operational fluctuation set.

[0032] S103. Construct a fitness function based on the running fluctuation set, and optimize the fitness function based on the particle swarm optimization algorithm to obtain the optimal coal allocation strategy.

[0033] In some embodiments of this application, constructing a fitness function based on the running fluctuation set includes: constructing a fitness function based on the running fluctuation set, the expression of which is:

[0034] in, The first operating fluctuation value, This is the second operating fluctuation value. This is the third operating fluctuation value. , , These are the preset first weight, preset second weight, and preset third weight, respectively.

[0035] In this embodiment, the weights are configured according to the power plant's different emphases on fluctuation frequency, amplitude, and overall shape.

[0036] In some embodiments of this application, the optimization of the fitness function based on the particle swarm optimization algorithm to obtain the optimal coal allocation strategy includes: Step 1, randomly initializing the velocity and position of each particle in the search space, calculating the fitness function value of each particle, and obtaining the individual optimal value and the global optimal value of the particle; Step 2, updating the velocity and position of each particle according to the individual optimal value and the global optimal value; Step 3, evaluating the fitness function value of the particle, and updating the individual optimal value and the global optimal value of the particle; Step 4, determining whether the particle swarm optimization algorithm meets the convergence condition. If it does, outputting the global optimal value and ending the process, determining the optimal coal allocation strategy based on the global optimal value; otherwise, repeating steps 1 to 3.

[0037] In this embodiment, within the feasible range of the coal allocation strategy, the position and velocity of each particle in the particle swarm are randomly initialized. The particle position is a coal allocation strategy vector. The fitness function value corresponding to the current position of each particle is calculated. The current position and fitness value of each particle are recorded as its individual historical optimal solution. The particle with the smallest fitness value is found from all particles, and its position is taken as the global historical optimal solution. The particles are iteratively updated based on the particle swarm algorithm until the global historical optimal solution no longer improves or reaches the preset maximum number of iterations. The coal allocation strategy corresponding to the global optimal solution is output as the optimal coal allocation strategy.

[0038] Based on the same technological concept, such as Figure 2 As shown, the present invention also provides a dynamic coal distribution system for thermal power plants, comprising: The demand module is used to obtain the current operating parameters of the thermal power unit, determine the unit status parameters based on the current operating parameters, and determine the coal demand parameters based on the unit status parameters. The simulation module is used to generate multiple coal allocation strategies based on the coal demand parameters, establish a unit simulation model, simulate the operation of the coal allocation strategies based on the unit simulation model, and output the operation fluctuation sets corresponding to multiple coal allocation strategies. The allocation module is used to construct a fitness function based on the operation fluctuation sets, optimize the fitness function based on the particle swarm optimization algorithm, and obtain the optimal coal allocation strategy.

[0039] Through the above description of the embodiments, those skilled in the art can clearly understand that each embodiment can be implemented by means of software plus necessary general-purpose hardware platforms, and of course, it can also be implemented by hardware. Based on this understanding, the above technical solutions, in essence or the part that contributes to the prior art, can be embodied in the form of a software product. This computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, magnetic disk, optical disk, etc., and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute the methods described in the various embodiments or some parts of the embodiments.

[0040] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of this application, and are not intended to limit them. Although this application has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features. Such modifications 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 this application.

Claims

1. A method for dynamic coal allocation in a thermal power plant, characterized in that, include: Obtain the current operating parameters of the thermal power unit, determine the unit status parameters based on the current operating parameters, and determine the coal demand parameters based on the unit status parameters. Multiple coal allocation strategies are generated based on coal demand parameters. A unit simulation model is established. The operation of the coal allocation strategies is simulated based on the unit simulation model, and the operation fluctuation set corresponding to the multiple coal allocation strategies is output. A fitness function is constructed based on the running fluctuation set, and the fitness function is optimized based on the particle swarm optimization algorithm to obtain the optimal coal allocation strategy.

2. The dynamic coal allocation method for thermal power plants according to claim 1, characterized in that, The unit status parameters are determined based on the current operating parameters of the thermal power unit, including: Obtain the historical unit operating parameter set, establish a sample dataset based on the historical unit operating parameter set, and randomly select k cluster centers from the sample dataset; Calculate the Euclidean distance from each sample data in the sample dataset to the initial cluster center, and divide each sample data into the corresponding cluster based on the Euclidean distance from each sample data in the sample dataset to the initial cluster center; Calculate the mean of the sample data within each cluster, and recalculate the cluster centers based on the mean of the sample data within each cluster; The cluster centers of each cluster are calculated iteratively until the cluster centers no longer change or the number of iterations reaches the preset maximum number of iterations, and the clustering results are obtained. Calculate the similarity between the current operating parameters and the corresponding cluster centers of each cluster, select the cluster center with the highest similarity to the current operating parameters to obtain similar cluster centers, and determine the unit status parameters corresponding to the current operating parameters based on the similar cluster centers.

3. The dynamic coal allocation method for thermal power plants according to claim 2, characterized in that, The unit status parameters corresponding to the current operating parameters are determined based on similar cluster centers, including: Obtain preset standard state parameters, calculate the difference between the cluster center value of similar cluster centers and the preset standard state parameters, and determine the unit state parameters based on the difference between the cluster center value and the preset standard state parameters.

4. The dynamic coal allocation method for thermal power plants according to claim 1, characterized in that, The coal demand parameters are determined based on the unit's status parameters, including: Obtain the preset standard coal demand parameters of the current thermal power unit, and correct the preset standard coal demand parameters according to the unit status parameters to obtain the coal demand parameters.

5. The dynamic coal allocation method for thermal power plants according to claim 1, characterized in that, Multiple coal allocation strategies are generated based on coal demand parameters, including: Obtain historical coal demand parameters and corresponding coal allocation strategies for thermal power units, and establish a training dataset based on the historical coal demand parameters and corresponding coal allocation strategies; A policy generation model is built based on the training dataset and trained to obtain a well-trained policy generation model. Input the current coal demand parameters into the trained strategy generation model to generate multiple coal allocation strategies.

6. The dynamic coal allocation method for thermal power plants according to claim 1, characterized in that, Establish a unit simulation model, simulate the operation of the coal allocation strategy based on the unit simulation model, and output the operation fluctuation sets corresponding to multiple coal allocation strategies, including: A unit simulation model is established based on the current operating parameters of the thermal power unit. Each coal allocation strategy is input into the unit simulation model to simulate the operation process of the thermal power unit. The operation fluctuation set of each coal allocation strategy is determined based on the simulation results.

7. The dynamic coal allocation method for thermal power plants according to claim 1, characterized in that, Based on the simulation results, the operational fluctuation set of each coal allocation strategy is determined, including: Based on the simulation results, determine the main steam pressure changes for each coal distribution strategy, and plot the main steam pressure change curves based on the main steam pressure changes. The starting point, peak point, valley point, and end point of the main steam pressure variation curve are statistically analyzed, and these points are marked as reference points. The intervals between adjacent reference points on the main steam pressure variation curve are statistically analyzed to obtain the fluctuation intervals. The total number of fluctuation intervals is determined as the first operating fluctuation value. Calculate the absolute difference between the data corresponding to each adjacent reference point on the main steam pressure variation curve, and determine the average of the absolute differences of all data as the second operating fluctuation value; Obtain the preset standard main steam pressure variation curve, calculate the correlation coefficient between the main steam pressure variation curve and the preset standard main steam pressure variation curve, perform negative correlation mapping on the correlation coefficient, and obtain the third operating fluctuation value. Establish an operational fluctuation set based on the first operational fluctuation value, the second operational fluctuation value, and the third operational fluctuation value.

8. The dynamic coal allocation method for thermal power plants according to claim 1, characterized in that, Construct a fitness function based on the set of fluctuations, including: The fitness function is constructed based on the running fluctuation set, and its expression is as follows: in, The first operating fluctuation value, This is the second operating fluctuation value. This is the third operating fluctuation value. , , These are the preset first weight, preset second weight, and preset third weight, respectively.

9. The dynamic coal allocation method for thermal power plants according to claim 1, characterized in that, The optimization of the fitness function based on the particle swarm optimization algorithm to obtain the optimal coal allocation strategy includes: Step 1: Randomly initialize the velocity and position of each particle in the search space, calculate the fitness function value of each particle, and obtain the individual optimal value and the global optimal value of the particle. Step 2: Update the velocity and position of each particle based on its individual optimal value and global optimal value; Step 3: Evaluate the fitness function value of the particle and update the individual optimal value and global optimal value of the particle; Step 4: Determine whether the particle swarm optimization algorithm meets the convergence condition. If it does, output the global optimum and end the process. Determine the optimal coal allocation strategy based on the global optimum. Otherwise, repeat steps 1 to 3.

10. A dynamic coal distribution system for a thermal power plant, characterized in that, include: The demand module is used to obtain the current operating parameters of the thermal power unit, determine the unit status parameters based on the current operating parameters, and determine the coal demand parameters based on the unit status parameters. The simulation module is used to generate multiple coal allocation strategies based on coal demand parameters, establish a unit simulation model, simulate the operation of the coal allocation strategies based on the unit simulation model, and output the operation fluctuation set corresponding to multiple coal allocation strategies. The allocation module is used to construct a fitness function based on the running fluctuation set, and optimize the fitness function based on the particle swarm optimization algorithm to obtain the optimal coal allocation strategy.

Images