Operation optimization method, device and equipment of thermal power generating unit, medium and product

Abstract

The invention discloses an operation optimization method, device and equipment of a thermal power generating unit, a medium and a product, and relates to the technical field of electric digital data processing.The method comprises the steps that a target digital twinborn model of a flue gas waste heat gradient utilization system of the thermal power generating unit and boundary parameters of the target digital twinborn model are obtained; obtaining a plurality of adjustment parameters in the target digital twinborn model; determining a model key parameter from the plurality of adjustment parameters; optimizing the model key parameters based on the boundary parameters to obtain optimal key parameters corresponding to the model key parameters; the optimal key parameters are applied to target equipment corresponding to the optimal key parameters, so that the flue gas waste heat gradient utilization system of the thermal power generating unit operates based on the optimal key parameters; wherein the target equipment is equipment in a flue gas waste heat gradient utilization system of the thermal power generating unit, and real-time and accurate optimization operation of the equipment of the thermal power generating unit can be achieved.

Description

Technical Field

[0001] This application relates to the technical field of electric digital data processing, and particularly to an operation optimization method, device, equipment, medium and product for thermal power units. Background Art

[0002] In the daily operation and management of thermal power units, improving energy efficiency, reducing emissions, shortening equipment failure downtime and operating costs have become key goals for the industry's development. Improving energy efficiency helps alleviate the energy shortage situation and reduce dependence on limited energy resources; while shortening equipment failure downtime and reducing operating costs are directly related to the economic benefits and market competitiveness of power plants.

[0003] However, the traditional optimization methods currently adopted by thermal power units have many limitations. Traditional methods mostly rely on manual experience and regular maintenance strategies, lacking accurate control over the real-time operating status of equipment. In actual operation, the equipment conditions are complex and changeable, and it is difficult to adapt to this dynamic change only relying on experience, resulting in adjustments often lagging behind actual needs and being unable to achieve real-time and accurate optimization operations for the equipment of thermal power units. Summary of the Invention

[0004] The purpose of this application is to provide an operation optimization method, device, equipment, medium and product for thermal power units, which can achieve real-time and accurate optimization operations for the equipment of thermal power units.

[0005] To achieve the above purpose, this application provides the following solutions: In the first aspect, this application provides an operation optimization method for a thermal power unit, including: Obtaining the target digital twin model of the flue gas waste heat cascade utilization system of the thermal power unit and the boundary parameters of the target digital twin model; Obtaining multiple adjustment parameters in the target digital twin model; Determining the model key parameters from the multiple adjustment parameters; Optimizing the model key parameters based on the boundary parameters to obtain the optimal key parameters corresponding to the model key parameters; Applying the optimal key parameters to the target equipment corresponding to the optimal key parameters, so that the flue gas waste heat cascade utilization system of the thermal power unit operates based on the optimal key parameters; wherein, the target equipment is the equipment in the flue gas waste heat cascade utilization system of the thermal power unit.

[0006] Optionally, the operation optimization method for the thermal power unit further includes: Construct a digital twin model based on the flue gas waste heat cascade utilization system of the thermal power unit; wherein, the digital twin model at least includes a boiler sub-model, a waste heat sub-model, and a steam turbine sub-model; At preset time intervals, collect real-time data from the flue gas waste heat cascade utilization system, and inject the real-time data into the digital twin model, so that the digital twin model performs real-time dynamic simulation based on the real-time data; And, the method for obtaining the target digital twin model of the flue gas waste heat cascade utilization system of the thermal power unit and the boundary parameters of the target digital twin model is specifically as follows: Determine the digital twin model of the flue gas waste heat cascade utilization system of the thermal power unit injected with the latest real-time data as the target digital twin model; Obtain the boundary parameters corresponding to the target digital twin model.

[0007] Optionally, the adjustment parameters include: the opening degree of the first air preheater bypass flue gas baffle, the opening degree of the second air preheater bypass flue gas baffle, the frequency of the circulating water pump, the opening degree of the total valve for feeding water to the high-pressure economizer, the opening degree of the first branch valve for feeding water to the high-pressure economizer, the opening degree of the second branch valve for feeding water to the high-pressure economizer, the opening degree of the condensate to the low-pressure economizer booster pump, the opening degree of the condensate to the low-pressure economizer bypass valve, the opening degree of the condensate to the first low-pressure economizer, and the opening degree of the condensate to the second low-pressure economizer; the method for determining the key model parameters from the multiple adjustment parameters specifically includes: Obtain multiple groups of training adjustment parameter sets; wherein, each group of training adjustment parameter sets contains all the adjustment parameters, and the value of each adjustment parameter is randomly obtained within the corresponding value range of the current adjustment parameter; Obtain the actual coal consumption of each group of training adjustment parameter sets during actual operation; Perform simulation operations on each group of training adjustment parameter sets through the target digital twin model to obtain the simulated coal consumption of each group of training adjustment parameter sets; Use the actual coal consumption and the simulated coal consumption to determine the key model parameters from the multiple adjustment parameters; wherein, the key model parameters are the opening degree of the first air preheater bypass flue gas baffle, the opening degree of the second air preheater bypass flue gas baffle, the frequency of the circulating water pump, and the opening degree of the first branch valve for feeding water to the high-pressure economizer.

[0008] Optionally, the method for using the actual coal consumption and the simulated coal consumption to determine the key model parameters from the multiple adjustment parameters specifically includes: Compare the actual coal consumption and the simulated coal consumption of each training adjustment parameter set to obtain the coal consumption residual value of each training adjustment parameter set; Construct a residual table based on the actual coal consumption, simulated coal consumption, and coal consumption residual values of each training adjustment parameter group; Analyze the residual table to determine the parameter sensitivity of each adjustment parameter; Determine the adjustment parameters with parameter sensitivity greater than the preset threshold as the model key parameters.

[0009] Optionally, optimizing the model key parameters based on the boundary parameters to obtain the optimal key parameters corresponding to the model key parameters specifically includes: Determine the key boundary parameters corresponding to the model key parameters from the boundary parameters; Determine the initial key parameters corresponding to the model key parameters based on the key boundary parameters; wherein, the initial key parameters are less than or equal to the key boundary parameters; Calculate based on the initial key parameters, the preset initial Lagrange multiplier, and the initial penalty factor to obtain the current minimum value of the augmented Lagrangian function; Update the initial key parameters based on the current minimum value to obtain the target key parameters; Update the initial Lagrange multiplier based on the initial Lagrange multiplier, the initial penalty factor, and the key boundary parameters to obtain the target Lagrange multiplier; Update the initial penalty factor based on the preset parameters and the initial penalty factor to obtain the target penalty factor; Repeat the optimization operation based on the target key parameters, the target Lagrange multiplier, and the target penalty factor until the difference between the current minimum value and the previous minimum value corresponding to the current minimum value is less than or equal to the preset difference, or the target key parameters are the same as the key boundary parameters.

[0010] Optionally, the optimization operation specifically includes: Calculate based on the target key parameters, the target Lagrange multiplier, and the target penalty factor to obtain the current minimum value of the augmented Lagrangian function; If the difference between the current minimum value and the previous minimum value corresponding to the current minimum value is greater than the preset difference, update the target key parameters based on the current minimum value to obtain the updated target key parameters; wherein, the target key parameters used in subsequent calculations are the updated target key parameters; Update the target Lagrange multiplier based on the target Lagrange multiplier, the target penalty factor, and the key boundary parameters to obtain the updated target Lagrange multiplier; wherein, the target Lagrange multiplier used in subsequent calculations is the updated target Lagrange multiplier; Update the target penalty factor based on the preset parameters and the target penalty factor to obtain an updated target penalty factor; wherein, the target penalty factor used in subsequent calculations is the updated target penalty factor.

[0011] In a second aspect, the present application provides an operation optimization device for a thermal power unit, including: A first acquisition unit for acquiring a target digital twin model of a flue gas waste heat cascade utilization system of a thermal power unit and boundary parameters of the target digital twin model; A second acquisition unit for acquiring a plurality of adjustment parameters in the target digital twin model; A determination unit for determining model key parameters from the plurality of adjustment parameters; An optimization unit for optimizing the model key parameters based on the boundary parameters to obtain optimal key parameters corresponding to the model key parameters; An application unit for applying the optimal key parameters to target devices corresponding to the optimal key parameters, so that the flue gas waste heat cascade utilization system of the thermal power unit operates based on the optimal key parameters; wherein, the target devices are devices in the flue gas waste heat cascade utilization system of the thermal power unit.

[0012] In a third aspect, the present application provides a computer device, including: a memory, a processor, and a computer program stored on the memory and executable on the processor, and the processor executes the computer program to implement the steps of the operation optimization method for a thermal power unit described in any one of the above.

[0013] In a fourth aspect, the present application provides a computer-readable storage medium, on which a computer program is stored, and when the computer program is executed by a processor, the steps of the operation optimization method for a thermal power unit described in any one of the above are implemented.

[0014] In a fifth aspect, the present application provides a computer program product, including a computer program, and when the computer program is executed by a processor, the steps of the operation optimization method for a thermal power unit described in any one of the above are implemented.

[0015] In a sixth aspect, the present application provides a chip, the chip includes a processor and a communication interface, the communication interface is coupled to the processor, the processor is used to run a program or an instruction, and when the processor executes the program or the instruction, the steps of the operation optimization method for a thermal power unit described in any one of the above are implemented.

[0016] According to the specific embodiments provided by the present application, the following technical effects are disclosed in the present application: The present application provides an operation optimization method, device, equipment, medium and product for a thermal power unit. By building a target digital twin model of the flue gas waste heat cascade utilization system of the thermal power unit, real-time simulation processing can be performed on the data collected from the flue gas waste heat cascade utilization system of the thermal power unit, so that the target digital twin model can reflect the working condition changes of the equipment in the flue gas waste heat cascade utilization system in real time. Furthermore, the target digital twin model can be used to perform optimization calculations based on the collected data to obtain the optimal key parameters for adjusting the operation of the flue gas waste heat cascade utilization system, thereby enabling real-time and accurate optimization operations on the equipment of the thermal power unit. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] In order to more clearly illustrate the technical solutions in the embodiments of the present application or the prior art, the following will briefly introduce the drawings required to be used in the embodiments. Obviously, the drawings in the following description are only some embodiments of the present application. For those of ordinary skill in the art, without creative efforts, other drawings can also be obtained based on these drawings.

[0018] Figure 1 It is a schematic flowchart of an operation optimization method for a thermal power unit in an embodiment of the present application; Figure 2 It is a schematic diagram of the functional modules of a target digital twin model of a flue gas waste heat cascade utilization system of a thermal power unit provided in an embodiment of the present application; Figure 3 It is a tornado diagram of the adjustment parameters provided in an embodiment of the present application; Figure 4 It is a schematic diagram of the optimization result of an AUGLAG algorithm provided in an embodiment of the present application; Figure 5 It is a schematic diagram of the optimization result of a PSO algorithm provided in an embodiment of the present application; Figure 6 It is a schematic diagram of the optimization result of a COBYLA algorithm provided in an embodiment of the present application; Figure 7 It is a schematic diagram of the optimization result of a GA algorithm provided in an embodiment of the present application; Figure 8 It is a schematic diagram of the functional modules of an operation optimization device for a thermal power unit provided in an embodiment of the present application; Figure 9 It is a schematic diagram of the structure of a computer device provided in an embodiment of the present application. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0019] Next, the technical solutions in the embodiments of the present application will be clearly and completely described in conjunction with the accompanying drawings in the embodiments of the present application. Obviously, the described embodiments are only a part of the embodiments of the present application, rather than all the embodiments. All other embodiments obtained by those of ordinary skill in the art based on the embodiments in the present application without creative efforts shall fall within the protection scope of the present application.

[0020] To make the above objects, features, and advantages of the present application more obvious and understandable, the present application will be further described in detail below with reference to the accompanying drawings and specific embodiments.

[0021] In an exemplary embodiment, as Figure 1 shown, an operation optimization method for a thermal power unit is provided. This method is executed by a computer device, specifically, it can be executed independently by a computer device such as a terminal or a server, or jointly executed by a terminal and a server. In the embodiments of the present application, it includes the following steps 101 to 105. Among them: Step 101, obtain the target digital twin model of the flue gas waste heat cascaded utilization system of the thermal power unit and the boundary parameters of the target digital twin model.

[0022] As an optional implementation manner, before step 101, the following steps may also be executed: Construct a digital twin model based on the flue gas waste heat cascaded utilization system of the thermal power unit; wherein, the digital twin model at least includes a boiler sub-model, a waste heat sub-model, and a steam turbine sub-model; At every preset time interval, collect real-time data from the flue gas waste heat cascaded utilization system and inject the real-time data into the digital twin model, so that the digital twin model performs real-time dynamic simulation based on the real-time data; Moreover, the manner of step 101 to obtain the target digital twin model of the flue gas waste heat cascaded utilization system of the thermal power unit and the boundary parameters of the target digital twin model may specifically be: Determine the digital twin model of the flue gas waste heat cascaded utilization system of the thermal power unit injected with the latest real-time data as the target digital twin model; Obtain the boundary parameters corresponding to the target digital twin model.

[0023] Among them, when implementing this implementation method, a digital twin model including boiler, waste heat, and steam turbine sub-models is constructed based on the flue gas waste heat cascade utilization system of a thermal power unit, providing an accurate virtual mapping for the operation of power plant equipment. By collecting and injecting real-time data at preset time intervals for real-time dynamic simulation, the digital twin model can closely follow the changes in the actual equipment conditions, greatly improving the real-time performance and accuracy of the model. Determining the model injected with the latest real-time data as the target digital twin model and obtaining the corresponding boundary parameters can ensure that subsequent optimization operations are based on the most real equipment state. This not only helps to detect potential equipment problems in a timely manner but also enables the formulation of more effective optimization strategies based on accurate data, thereby significantly improving the energy utilization efficiency of thermal power units, reducing energy consumption and operating costs, while reducing pollutant emissions and enhancing equipment operation stability, strongly promoting the green, efficient, and sustainable development of thermal power units.

[0024] In the embodiments of this application, the digital twin model of the flue gas waste heat cascade utilization system of a thermal power unit can be constructed based on the Sysplorer software and using the Modelica modeling language.

[0025] In addition, the boiler subsystem can also include: equipment models such as a furnace, water wall, superheater, reheater, etc.; The waste heat subsystem can also include: equipment models such as an air preheater, low-temperature economizer, air heater, expansion tank, etc.; The steam turbine subsystem can also include: equipment models such as a steam turbine, condenser, high and low pressure heaters, steam cooler, etc.

[0026] Moreover, the boiler sub-model, waste heat sub-model, and steam turbine sub-model can also include equipment-level models such as a furnace, water wall, steam turbine, economizer, air preheater, superheater reheater, etc.

[0027] In the embodiments of this application, the latest real-time data can be the real-time operation data of the flue gas waste heat cascade utilization system of a thermal power unit; a communication component can be written using Python, and through this communication component, the COM (Component Object Model) interface provided by the power plant industrial data management platform (Plant Information System, PI) can be called to realize the reading and writing of real-time operation data in the PI database.

[0028] Among them, the real-time operation data can include the coal quantity, air volume entering the furnace, feed water flow on the steam turbine side, valve opening, pump frequency, etc.

[0029] In the embodiments of the present application, the target digital twin model can perform simulation operations based on the latest injected real-time data, and obtain the simulation operation results. Furthermore, the simulation operation results can be output to a display so that the staff can intuitively view the simulation operation results of the target digital twin model for the actual flue gas waste heat cascade utilization system. The simulation operation results can be information of text type, image type, or statistical chart type. In this regard, the embodiments of the present application do not make any limitations. The simulation operation results may include current coal consumption information, energy utilization rate information, etc. In this regard, the embodiments of the present application do not make any limitations.

[0030] In the embodiments of the present application, the boundary parameters corresponding to the target digital twin model can be the constraint conditions for the operating parameters in the target digital twin model.

[0031] For example, please refer to Table 1: Table 1 Boundary Parameters Corresponding to the Target Digital Twin Model

[0032] Please refer to Figure 2 , Figure 2 , which is a schematic diagram of the functional modules of the target digital twin model of a flue gas waste heat cascade utilization system for a thermal power unit provided in an embodiment of the present application.

[0033] Step 102, obtain multiple adjustment parameters in the target digital twin model.

[0034] In the embodiments of the present application, the adjustment parameters include: the opening degree of the first air preheater bypass flue gas baffle, the opening degree of the second air preheater bypass flue gas baffle, the frequency of the circulating water pump, the opening degree of the total valve for feeding water to the high-pressure economizer, the opening degree of the first sub-valve for feeding water to the high-pressure economizer, the opening degree of the second sub-valve for feeding water to the high-pressure economizer, the opening degree of the condensate to the low-pressure economizer booster pump, the opening degree of the condensate bypass valve to the low-pressure economizer, the opening degree of the valve for condensate to the first low-pressure economizer, and the opening degree of the valve for condensate to the second low-pressure economizer.

[0035] Step 103, determine the model key parameters from the multiple adjustment parameters.

[0036] In the embodiments of the present application, the model key parameters can be determined according to the influence degree of each adjustment parameter on the coal consumption of the target digital twin model. The model key parameters are the adjustment parameters with a greater influence degree on the coal consumption of the target digital twin model.

[0037] As an optional implementation manner, the specific manner for step 103 to determine the model key parameters from the multiple adjustment parameters can be: Obtain multiple groups of training adjustment parameter groups; where each group of training adjustment parameter groups contains all adjustment parameters, and the value of each adjustment parameter is a randomly obtained value within the corresponding value range of the current adjustment parameter; Obtain the actual coal consumption of each group of training adjustment parameter groups during actual operation; Perform simulation operations on each group of training adjustment parameter groups through the target digital twin model to obtain the simulated coal consumption of each group of training adjustment parameter groups; Use the actual coal consumption and the simulated coal consumption to determine the key model parameters from the multiple adjustment parameters; where the key model parameters are the opening degree of the bypass flue gas damper of the first air preheater, the opening degree of the bypass flue gas damper of the second air preheater, the frequency of the circulating water pump, and the opening degree of the first sub-valve for feeding water to the high-pressure economizer.

[0038] Among them, implementing this implementation method provides rich data support for comprehensively and objectively analyzing the impact of adjustment parameters on coal consumption by obtaining multiple groups of training adjustment parameter groups randomly generated within the adjustment parameter value range, and respectively obtaining their actual operation coal consumption and simulated coal consumption obtained through simulation operations using the target digital twin model. Determining key model parameters such as the opening degree of the bypass flue gas damper of the first air preheater, the opening degree of the bypass flue gas damper of the second air preheater, the frequency of the circulating water pump, and the opening degree of the first sub-valve for feeding water to the high-pressure economizer based on the actual coal consumption and the simulated coal consumption can accurately locate the parameters that have a greater impact on coal consumption. This enables the thermal power unit to target these key model parameters for adjustment during subsequent operation optimization, avoiding blind attempts, greatly improving the optimization efficiency, contributing to quickly achieving the goal of reducing coal consumption and improving energy utilization efficiency, while reducing unnecessary resource waste and enhancing the economy and stability of the thermal power unit operation.

[0039] In the embodiments of this application, multiple groups of training adjustment parameter groups can be generated through the Monte Carlo algorithm.

[0040] Furthermore, the impact of parameter changes on the model output can also be analyzed through the Monte Carlo algorithm.

[0041] In Monte Carlo, attention is usually paid to approximating the statistical characteristics (such as expected value, variance, etc.) of a certain target variable through the results obtained from the simulation. The basic evaluation formula is as follows: Monte Carlo simulation is a numerical calculation method based on random sampling, used to estimate the performance, results, or certain characteristics of a complex system or model by simulating a large number of random samples.

[0042] Suppose we have a function Calculate the simulated coal consumption, and its input variable is the training adjustment parameter , and this input variable follows a certain probability distribution Extraction. The goal of the Monte Carlo method is to estimate the expected value of a function, that is:

[0043] where, is the expected value, is the input variable 's probability density function.

[0044] Monte Carlo estimation formula: If it is difficult or impossible to solve this integral directly, the expected value can be approximated by random sampling:

[0045] where: is the number of random samples, is the sample point randomly drawn from the distribution '.

[0046] Variance estimation: Assume that a Monte Carlo simulation is performed on the function to obtain a set of estimated values , the variance formula for Monte Carlo estimation is:

[0047] Specifically, the derivation process of the variance formula for Monte Carlo estimation is as follows: Given independent and identically distributed samples , the Monte Carlo estimator is the sample mean:

[0048] The Monte Carlo estimator is the sample mean, and its variance formula is:

[0049] The single-sample variance can be decomposed into the difference between the second moment and the square of the first moment:

[0050] Replace the theoretical expectation with the sample mean: Second moment estimation:

[0051] First moment square estimation:

[0052] Substitute the two into the variance decomposition formula:

[0053] Therefore,

[0054] In the embodiments of the present application, if the variance of the sample is relatively large, the estimation accuracy is relatively low, and more samples are required to improve the estimation accuracy.

[0055] Error estimation: A key issue in the Monte Carlo method is to determine the error of the estimation. Assume is the estimated value of the expected value, then the error can be calculated by the following formula:

[0056] Since the error of the Monte Carlo estimation is usually inversely proportional to the square root of the sample size , the standard deviation of the error is:

[0057] To achieve a lower error at a given accuracy, the number of simulations needs to be increased .

[0058] Convergence in Monte Carlo simulation: As the sample size increases, the result of the Monte Carlo estimation will get closer and closer to the true expected value. This means that the error has the following convergence characteristics:

[0059] Confidence interval of Monte Carlo simulation: Monte Carlo can also be used to construct the confidence interval of the expected value. Assume that through simulation, samples of are obtained, and the confidence interval of the expected value can be estimated based on the mean and standard deviation of the samples. For example, the 95% confidence interval can be given by the following formula:

[0060] where 1.96 is the critical value of the normal distribution at the 95% confidence level.

[0061] As an alternative implementation, the method for determining the key parameters of the model from the multiple adjustment parameters using the actual coal consumption and the simulated coal consumption may specifically be: Compare the actual coal consumption and the simulated coal consumption of each training adjustment parameter group to obtain the coal consumption residual value of each training adjustment parameter group; Construct a residual table based on the actual coal consumption, the simulated coal consumption, and the coal consumption residual value of each training adjustment parameter group; Analyze the residual table to determine the parameter sensitivity of each adjustment parameter; Determine the adjustment parameters with the parameter sensitivity greater than the preset threshold as the key parameters of the model.

[0062] Among them, when implementing this implementation method, the residual value is obtained by comparing the actual coal consumption with the simulated coal consumption, a clear residual table is constructed, the sensitivity of each adjustment parameter is accurately analyzed, the parameters with sensitivity greater than the preset threshold are determined as key parameters, which helps the operator to accurately control, avoid blind operation, improve the optimization efficiency, optimize the digital twin model, and enhance the reliability and practicability of the model.

[0063] For example, the residual table can be as shown in Table 2 below: Table 2 Residual Table

[0064] In addition, a scatter plot can also be constructed based on the actual coal consumption, simulated coal consumption, and coal consumption residual values of each training adjustment parameter group. The horizontal axis of this scatter plot can be the measured value, and the vertical axis can be the simulated value. Ideally, the data points should be distributed near the 45° line.

[0065] A residual distribution plot can also be constructed based on the actual coal consumption, simulated coal consumption, and coal consumption residual values of each training adjustment parameter group. The horizontal axis of this residual distribution plot can be the training adjustment parameter value (such as the baffle opening), and the vertical axis can be the residual, which is used to analyze the influence of the training adjustment parameter on the error.

[0066] Optionally, the parameter sensitivity can also include multiple sensitivity indicators, and a tornado diagram of the adjustment parameter can be generated according to the multiple sensitivity indicators. Please refer to Figure 3 , Figure 3 which is the tornado diagram of the adjustment parameter provided by an embodiment of the present application; among them, one adjustment parameter includes seven sensitivity indicators: correlation - linear, correlation - ranking, correlation - Kendall, standardized regression - linear, standardized regression - ranking, partial correlation - linear, and partial correlation - ranking.

[0067] Specifically, correlation - linear is used to show the linear correlation relationship between the adjustment parameter and the output.

[0068] Correlation - ranking is used to show the degree of association between the adjustment parameter and the output and sort them according to the degree of influence.

[0069] Correlation - Kendall refers to using Kendall's rank correlation coefficient to measure the correlation between adjustment parameters and showing the analysis results in the tornado diagram. Kendall's rank correlation coefficient is a statistical indicator used to measure the rank correlation between two adjustment parameters.

[0070] Standardized regression - linear involves the application of standardized regression coefficients in a linear regression model; the use of standardized regression coefficients in a tornado diagram is mainly to compare the relative impact degrees of different independent variables on the dependent variable. Since different independent variables may have different units and magnitudes, directly comparing the original regression coefficients may be misleading. Through standardization, each independent variable is placed under the same dimension, and the magnitude of the absolute value of its standardized regression coefficient directly reflects the impact degree of this independent variable on the dependent variable. The larger the absolute value, the greater the impact of this independent variable on the dependent variable.

[0071] Standardized regression - ranking is used to analyze and display the impact degrees of multiple independent variables on the dependent variable, and these independent variables obtained through standardized regression are sorted in descending order according to the magnitude of their impact degrees on the dependent variable.

[0072] Partial correlation - linear refers to when analyzing the impact of multiple adjustment parameters on a certain result, considering the partial correlation relationship between the adjustment parameters and conducting the analysis based on a linear hypothesis. Under this hypothesis, the linear correlation strength between the adjustment parameters is measured by calculating the partial correlation coefficient. The value range of the partial correlation coefficient is the same as that of the ordinary correlation coefficient, between - 1 and 1. The closer the absolute value of the coefficient is to 1, the stronger the linear relationship between the two adjustment parameters; the closer it is to 0, the weaker the linear relationship.

[0073] Partial correlation - ranking is used to analyze the relationship between multiple independent variables and the dependent variable, and the partial correlation coefficients between each independent variable and the dependent variable are sorted in descending order according to the magnitude of their absolute values.

[0074] Therefore, it can be seen from Figure 3 that the opening degrees of the bypass flue gas dampers of the first air preheater, the opening degrees of the bypass flue gas dampers of the second air preheater, the frequency of the circulating water pump, and the opening degree of the first sub - valve of the feed water to the high - pressure economizer have a greater impact on coal consumption. Furthermore, the opening degrees of the bypass flue gas dampers of the first air preheater, the opening degrees of the bypass flue gas dampers of the second air preheater, the frequency of the circulating water pump, and the opening degree of the first sub - valve of the feed water to the high - pressure economizer can be determined as the key parameters of the model.

[0075] Specifically, corresponding index values can be determined for all seven sensitivity indicators, and the adjustment parameters for which each sensitivity indicator is greater than the preset threshold of that sensitivity indicator can be determined as the key parameters of the model.

[0076] Step 104, optimize the key parameters of the model based on the boundary parameters to obtain the optimal key parameters corresponding to the key parameters of the model.

[0077] In the embodiments of this application, the augmented Lagrangian algorithm (Augmented Lagrangian Algorithm, AUGLAG) can be used to optimize the key parameters of the model.

[0078] As an alternative implementation, the manner in which step 104 optimizes the model key parameters based on the boundary parameters to obtain the optimal key parameters corresponding to the model key parameters may specifically be as follows: Determine the key boundary parameters corresponding to the model key parameters from the boundary parameters; Determine the initial key parameters corresponding to the model key parameters based on the key boundary parameters; wherein, the initial key parameters are less than or equal to the key boundary parameters; Perform calculations based on the initial key parameters, the preset initial Lagrange multiplier, and the initial penalty factor to obtain the current minimum value of the augmented Lagrangian function; Update the initial key parameters based on the current minimum value to obtain the target key parameters; Update the initial Lagrange multiplier based on the initial Lagrange multiplier, the initial penalty factor, and the key boundary parameters to obtain the target Lagrange multiplier; Update the initial penalty factor based on the preset parameters and the initial penalty factor to obtain the target penalty factor; Repeat the optimization operation based on the target key parameters, the target Lagrange multiplier, and the target penalty factor until the difference between the current minimum value and the previous minimum value corresponding to the current minimum value is less than or equal to the preset difference, or the target key parameters are the same as the key boundary parameters.

[0079] Among them, implementing this implementation manner to determine the key boundary parameters from the boundary parameters and obtaining the initial key parameters accordingly provides a reasonable starting point for the optimization process, ensuring that the optimization operation is carried out within the range of equipment safety and operation limits. By calculating the current minimum value of the augmented Lagrangian function based on the initial key parameters, the initial Lagrange multiplier, and the initial penalty factor, and continuously updating the key parameters, the Lagrange multiplier, and the penalty factor, the preset optimization goal can be gradually approximated. In the process of multiple iterative optimizations, until the condition that the difference between the current minimum value and the previous minimum value is less than or equal to the preset difference or the target key parameters are the same as the key boundary parameters is met, this makes the optimization result more accurate and more in line with the actual requirements.

[0080] In the embodiments of the present application, a constrained optimization problem can be constructed based on the key boundary parameters, and the form is:

[0081]

[0082] Wherein, x is the initial key parameter, is the objective function of the simulated coal consumption, is the inequality constraint. Constructed through the key boundary parameters, that is = x - critical boundary parameter. It can be seen that should be less than or equal to 0. m represents the number of model critical parameters included in the initial critical parameters.

[0083] In the embodiments of the present application, the augmented Lagrangian function has the form:

[0084] Where: is the initial penalty factor or the target penalty factor (usually a positive number). is the initial Lagrange multiplier or the target Lagrange multiplier.

[0085] In the embodiments of the present application, the optimization operation specifically includes: Calculating based on the target critical parameter, the target Lagrange multiplier, and the target penalty factor to obtain the current minimum value of the augmented Lagrangian function; If the difference between the current minimum value and the previous minimum value corresponding to the current minimum value is greater than a preset difference, then update the target critical parameter based on the current minimum value to obtain an updated target critical parameter; wherein, the target critical parameter used in subsequent calculations is the updated target critical parameter; Updating the target Lagrange multiplier based on the target Lagrange multiplier, the target penalty factor, and the critical boundary parameter to obtain an updated target Lagrange multiplier; wherein, the target Lagrange multiplier used in subsequent calculations is the updated target Lagrange multiplier; Updating the target penalty factor based on the preset parameter and the target penalty factor to obtain an updated target penalty factor; wherein, the target penalty factor used in subsequent calculations is the updated target penalty factor.

[0086] Among them, implementing this implementation method, calculations are carried out based on the target critical parameter, the target Lagrange multiplier, and the target penalty factor to continuously explore the current minimum value of the augmented Lagrangian function. In each iteration, by comparing the difference between the current minimum value and the previous minimum value, it is judged whether to continue optimization. If the difference is greater than the preset difference, then update the target critical parameter, the target Lagrange multiplier, and the target penalty factor to ensure that each iteration moves in a more optimal direction. This process of gradual iterative optimization can accurately adjust the model critical parameters to make them more in line with the actual operation requirements.

[0087] In the embodiments of the present application, in each iteration, after solving the minimum value of the augmented Lagrangian function, the form of updating the target critical parameter is:

[0088] The form of updating the Lagrange multiplier is:

[0089] The updated penalty factor form is as follows:

[0090] In the embodiments of the present application, the comparison of parameters before and after optimization and the optimization strategy recommendation can also be displayed on the Web side.

[0091] In addition, the linear approximation method for constrained optimization (Constrained Optimization BY Linear Approximations, COBYLA), the particle swarm optimization algorithm (Particle Swarm Optimization, PSO), and the genetic algorithm (Genetic Algorithm, GA) can also be used to optimize coal consumption.

[0092] The COBYLA algorithm processes constraints through linear approximation and gradually approaches the optimal solution through iterative optimization. In each iteration, the algorithm constructs a linear model based on the current solution to find a better solution and finally approaches the global optimal solution. It is an effective constrained optimization algorithm suitable for various complex problems. By reasonably setting constraints, initial values, and parameters, practical problems can be efficiently solved.

[0093] The PSO algorithm is an optimization technique that simulates the foraging behavior of bird flocks. In PSO, each solution is regarded as a "particle" with a position and a velocity. The particles update their velocities and positions by sharing information to find the optimal solution. PSO is applicable to various complex optimization problems. By reasonably setting parameters, designing fitness functions, and handling constraints, practical problems can be effectively solved.

[0094] The GA algorithm is a global optimization algorithm based on natural selection and genetic mechanisms. The potential solutions to the problem are represented as individuals in the population. The individuals are encoded by genes. The initial population is usually randomly generated, and then the population is iteratively updated to approach the optimal solution. The fitness value of each individual is used to measure its ability to solve the problem, usually calculated by the objective function. Parent individuals are selected according to the fitness values, and crossover and mutation operations are performed to generate new offspring. By continuously iterating these operations, the GA algorithm can effectively solve complex optimization problems.

[0095] The AUGLAG algorithm is an effective method for solving constrained optimization problems. It combines the advantages of the Lagrange multiplier method and the penalty function method. By introducing Lagrange multipliers and penalty parameters, the constrained optimization problem is transformed into a series of unconstrained optimization problems for solution. Its basic idea is to construct an augmented Lagrangian function, which combines the objective function, the linear combination of constraint conditions, and the penalty term, and then iteratively solve the optimal solution of this function to gradually approach the optimal solution of the original problem. Through reasonable parameter settings and convergence conditions, the AUGLAG algorithm is widely applied to the solution of various complex optimization problems.

[0096] Please also refer to Figures 4 to 7 , Figure 4 which is a schematic diagram of the optimization result of the AUGLAG algorithm provided by an embodiment of this application; Figure 5 which is a schematic diagram of the optimization result of the PSO algorithm provided by an embodiment of this application; Figure 6 which is a schematic diagram of the optimization result of the COBYLA algorithm provided by an embodiment of this application; Figure 7 which is a schematic diagram of the optimization result of the GA algorithm provided by an embodiment of this application.

[0097] Specifically, after optimization using the COBYLA algorithm, the coal consumption value is 275.28 g, which is optimized by about 0.5 g. The optimization process has carried out 15 steps and reached the convergence condition. The key adjusted parameters after optimization are: the flue gas side file opening of the air preheater is 75%, the total adjustment valve opening of the feed water to the high-pressure economizer is 94%, the frequency of the condensate water to the low-pressure economizer booster pump is 88%, and the frequency of the warm air heater and the low-temperature economizer circulating water pump is 48.63 Hz.

[0098] After final optimization using the PSO algorithm, the coal consumption value is 275.3 g, and the coal consumption is optimized by about 0.5 g. The number of optimization steps is 10 to reach the convergence condition. After optimization, the adjusted parameters are respectively: the flue gas side file opening of the air preheater is 91%, the total adjustment valve opening of the feed water to the high-pressure economizer is 82.5%, the frequency of the condensate water to the low-pressure economizer booster pump is 55.2%, and the frequency of the warm air heater and the low-temperature economizer circulating water pump is 48.5 Hz.

[0099] After final optimization using the GA algorithm, the coal consumption value is 275.3 g, and the coal consumption is optimized by about 0.5 g. The number of optimization steps is 6 to reach the convergence condition. After optimization, the adjusted parameters are respectively: the flue gas side file opening of the air preheater is 72.4%, the total adjustment valve opening of the feed water to the high-pressure economizer is 82.3%, the frequency of the condensate water to the low-pressure economizer booster pump is 68%, and the frequency of the warm air heater and the low-temperature economizer circulating water pump is 47 Hz.

[0100] After final optimization using the AUGLAG algorithm, the coal consumption value is 275.34 g, and the optimized coal consumption is about 0.46 g. The optimization steps reach 20 steps to meet the convergence condition. After optimizing the adjustment parameters, the flue gas side file opening of the air preheater is 49%, the total adjustment valve opening from feed water to the high-pressure economizer is 76%, the frequency of the condensate water to the booster pump of the low-pressure economizer is 77.5%, and the frequencies of the warm air heater and the low-temperature economizer circulating water pump are 47 Hz.

[0101] By applying four algorithms under certain constraints and taking the minimization of coal consumption as the optimization goal, the results show that the optimized coal consumption is about 0.5 g. The frequency of the condensate water to the booster pump of the low-pressure economizer is relatively high, while the frequency of the circulating water pump is relatively low. During the optimization process, although the number of iteration steps of the PSO algorithm and the GA algorithm is small, their time consumption is the longest; while the AUGLAG algorithm performs best in terms of time consumption, and the number of steps is also moderate. Based on this, the online optimization of the later twin model is more suitable to be implemented using the AUGLAG algorithm.

[0102] Step 105, apply the optimal key parameters to the target equipment corresponding to the optimal key parameters, so that the flue gas waste heat cascade utilization system of the thermal power unit operates based on the optimal key parameters.

[0103] In the embodiment of the present application, the target equipment is the equipment in the flue gas waste heat cascade utilization system of the thermal power unit.

[0104] Optionally, an equipment performance degradation curve can also be constructed according to the latest real-time data collected.

[0105] Obtain various operating parameters during the system operation in real time, such as temperature, pressure, and flow rate, etc.

[0106] Then, clean the collected operating parameters to ensure the accuracy and consistency of the operating parameters.

[0107] Select one of the three algorithms of COBYLA, PSO, and GA for parameter estimation to ensure that the simulation value is highly consistent with the measured value.

[0108] During the system operation, continuously collect data and update the model parameters to achieve online calibration of the model. Table 3 below shows the calibration parameter variables and corresponding parameter names corresponding to the calibration and performance degradation module.

[0109] Table 3 Parameter Table of Performance Degradation Module

[0110] In addition, the digital twin model will call parameter estimation, add the latest optimization result as a new record to the MySQL database. At the same time, the equipment performance degradation curve will be automatically added to represent the current calibration result, and the equipment performance degradation curve can be output to the Web side for display.

[0111] Implementing the above steps 101 to 105 can achieve real-time and accurate optimization operations on the equipment of thermal power units. In addition, this application can also ensure that subsequent optimization operations are based on the most real equipment status. In addition, this application can also targetedly adjust these key model parameters to avoid blind attempts, greatly improving the optimization efficiency, contributing to quickly achieving the goals of reducing coal consumption and improving energy utilization efficiency, while reducing unnecessary resource waste, and enhancing the economy and stability of the operation of thermal power units. In addition, this application can also help operators accurately control, avoid blind operations, improve the optimization efficiency, optimize the digital twin model, and enhance the reliability and practicability of the model. In addition, this application can also make the optimization results more accurate and more in line with actual requirements. In addition, this application can accurately adjust the key model parameters to make them more suitable for actual operation requirements.

[0112] Based on the same inventive concept, the embodiment of the present application also provides an operation optimization device for a thermal power unit for implementing the operation optimization method of the thermal power unit involved above. The solution provided by this device to solve the problem is similar to the solution described in the above method. Therefore, the specific limitations in one or more embodiments of the operation optimization device for a thermal power unit provided below can refer to the limitations on the operation optimization method of the thermal power unit in the above text, and will not be repeated here.

[0113] In an exemplary embodiment, as Figure 8 shown, there is provided an operation optimization device for a thermal power unit including: A first acquisition unit 801, configured to acquire a target digital twin model of the flue gas waste heat cascade utilization system of the thermal power unit and the boundary parameters of the target digital twin model; A second acquisition unit 802, configured to acquire a plurality of adjustment parameters in the target digital twin model; In the embodiment of the present application, the adjustment parameters include: the opening degree of the first air preheater bypass flue gas damper, the opening degree of the second air preheater bypass flue gas damper, the frequency of the circulating water pump, the opening degree of the total valve for feeding water to the high-pressure economizer, the opening degree of the first branch valve for feeding water to the high-pressure economizer, the opening degree of the second branch valve for feeding water to the high-pressure economizer, the opening degree of the condensate to the low-pressure economizer booster pump, the opening degree of the condensate to the low-pressure economizer bypass valve, the opening degree of the condensate to the first low-pressure economizer valve, and the opening degree of the condensate to the second low-pressure economizer valve.

[0114] A determination unit 803, configured to determine model key parameters from the multiple adjustment parameters; An optimization unit 804, configured to optimize the model key parameters based on the boundary parameters to obtain optimal key parameters corresponding to the model key parameters; An application unit 805, configured to apply the optimal key parameters to a target device corresponding to the optimal key parameters, so that the flue gas waste heat cascaded utilization system of the thermal power unit operates based on the optimal key parameters; wherein, the target device is a device in the flue gas waste heat cascaded utilization system of the thermal power unit.

[0115] As an optional implementation manner, the first acquisition unit 801 is further configured to: Construct a digital twin model based on the flue gas waste heat cascaded utilization system of the thermal power unit; wherein, the digital twin model at least includes a boiler sub-model, a waste heat sub-model, and a steam turbine sub-model; At every preset time interval, collect real-time data from the flue gas waste heat cascaded utilization system and inject the real-time data into the digital twin model, so that the digital twin model performs real-time dynamic simulation based on the real-time data; Moreover, the manner in which the first acquisition unit 801 acquires the target digital twin model of the flue gas waste heat cascaded utilization system of the thermal power unit and the boundary parameters of the target digital twin model is specifically as follows: Determine the digital twin model of the flue gas waste heat cascaded utilization system of the thermal power unit injected with the latest real-time data as the target digital twin model; Acquire the boundary parameters corresponding to the target digital twin model.

[0116] Wherein, implementing this implementation manner, constructing a digital twin model including boiler, waste heat, and steam turbine sub-models based on the flue gas waste heat cascaded utilization system of the thermal power unit provides an accurate virtual mapping for the operation of power plant equipment. By collecting and injecting real-time data at every preset time interval for real-time dynamic simulation, the digital twin model can closely follow the changes in the actual equipment conditions, greatly improving the real-time performance and accuracy of the model. Determining the model injected with the latest real-time data as the target digital twin model and acquiring the corresponding boundary parameters can ensure that subsequent optimization operations are based on the most real equipment state. This not only helps to timely discover potential problems of the equipment, but also can formulate more effective optimization strategies based on accurate data, thereby significantly improving the energy utilization efficiency of the thermal power unit, reducing energy consumption and operation costs, while reducing pollutant emissions and enhancing the operation stability of the equipment, and strongly promoting the thermal power unit to achieve green, efficient, and sustainable development.

[0117] As an optional implementation manner, the manner in which the determination unit 803 determines model key parameters from the multiple adjustment parameters may specifically be: Obtain multiple groups of training adjustment parameter groups; among them, each group of training adjustment parameter groups contains all adjustment parameters, and the value of each adjustment parameter is a randomly obtained value within the corresponding value range of the current adjustment parameter; Obtain the actual coal consumption of each group of training adjustment parameter groups during actual operation; Perform simulation operations on each group of training adjustment parameter groups through the target digital twin model to obtain the simulated coal consumption of each group of training adjustment parameter groups; Use the actual coal consumption and the simulated coal consumption to determine the model key parameters from the multiple adjustment parameters; among them, the model key parameters are the opening degree of the bypass flue gas damper of the first air preheater, the opening degree of the bypass flue gas damper of the second air preheater, the frequency of the circulating water pump, and the opening degree of the first sub-valve for feeding water to the high-pressure economizer.

[0118] Among them, implementing this implementation method provides rich data support for comprehensively and objectively analyzing the impact of adjustment parameters on coal consumption by obtaining multiple groups of training adjustment parameter groups randomly generated within the adjustment parameter value range, and respectively obtaining their actual operation coal consumption and simulated coal consumption obtained through simulation operations using the target digital twin model. Determining model key parameters such as the opening degree of the bypass flue gas damper of the first air preheater, the opening degree of the bypass flue gas damper of the second air preheater, the frequency of the circulating water pump, and the opening degree of the first sub-valve for feeding water to the high-pressure economizer based on the actual coal consumption and the simulated coal consumption can accurately locate the parameters with greater impact on coal consumption. This enables the thermal power unit to target these key parameters for adjustment in the subsequent operation optimization process, avoiding blind attempts, greatly improving the optimization efficiency, contributing to quickly achieving the goal of reducing coal consumption and improving energy utilization efficiency, while reducing unnecessary resource waste, and enhancing the economy and stability of the thermal power unit operation.

[0119] As an optional implementation method, the manner in which the determination unit 803 uses the actual coal consumption and the simulated coal consumption to determine the model key parameters from the multiple adjustment parameters can specifically be: Compare the actual coal consumption and the simulated coal consumption of each training adjustment parameter group to obtain the coal consumption residual value of each training adjustment parameter group; Based on the actual coal consumption, the simulated coal consumption, and the coal consumption residual value of each training adjustment parameter group, construct a residual table; Analyze the residual table to determine the parameter sensitivity of each adjustment parameter; Determine the adjustment parameters with parameter sensitivity greater than the preset threshold as the model key parameters.

[0120] Among them, when implementing this implementation method, the residual value is obtained by comparing the actual and simulated coal consumption, a clear residual table is constructed, the sensitivity of each adjustment parameter is accurately analyzed, the parameters with sensitivity greater than the preset threshold are determined as key parameters, which helps the operator to accurately control, avoid blind operation, improve the optimization efficiency, optimize the digital twin model, and enhance the reliability and practicability of the model.

[0121] As an alternative implementation method, the optimization unit 804 optimizes the key parameters of the model based on the boundary parameters. The specific method for obtaining the optimal key parameters corresponding to the key parameters of the model can be as follows: Determine the key boundary parameters corresponding to the key parameters of the model from the boundary parameters; Determine the initial key parameters corresponding to the key parameters of the model based on the key boundary parameters; among them, the initial key parameters are less than or equal to the key boundary parameters; Calculate based on the initial key parameters, the preset initial Lagrange multiplier and the initial penalty factor to obtain the current minimum value of the augmented Lagrangian function; Update the initial key parameters based on the current minimum value to obtain the target key parameters; Update the initial Lagrange multiplier based on the initial Lagrange multiplier, the initial penalty factor and the key boundary parameters to obtain the target Lagrange multiplier; Update the initial penalty factor based on the preset parameters and the initial penalty factor to obtain the target penalty factor; Repeat the optimization operation based on the target key parameters, the target Lagrange multiplier and the target penalty factor until the difference between the current minimum value and the previous minimum value corresponding to the current minimum value is less than or equal to the preset difference, or the target key parameters are the same as the key boundary parameters.

[0122] Among them, when implementing this implementation method, determining the key boundary parameters from the boundary parameters and obtaining the initial key parameters accordingly provides a reasonable starting point for the optimization process, ensuring that the optimization operation is carried out within the range of equipment safety and operation limits. By calculating the current minimum value of the augmented Lagrangian function based on the initial key parameters, the initial Lagrange multiplier and the initial penalty factor, and continuously updating the key parameters, the Lagrange multiplier and the penalty factor, the preset optimization goal can be gradually approached. In the process of multiple iterative optimizations, until the condition that the difference between the current minimum value and the previous minimum value is less than or equal to the preset difference or the target key parameters are the same as the key boundary parameters is met, this makes the optimization result more accurate and more in line with the actual requirements.

[0123] In the embodiments of the present application, the optimization operation can be specifically: Calculate based on the target key parameters, the target Lagrange multiplier and the target penalty factor to obtain the current minimum value of the augmented Lagrangian function; If the difference between the current minimum value and the previous minimum value corresponding to the current minimum value is greater than a preset difference, then update the target key parameter based on the current minimum value to obtain an updated target key parameter; wherein, the target key parameter used in subsequent calculations is the updated target key parameter; Update the target Lagrange multiplier based on the target Lagrange multiplier, the target penalty factor, and the key boundary parameter to obtain an updated target Lagrange multiplier; wherein, the target Lagrange multiplier used in subsequent calculations is the updated target Lagrange multiplier; Update the target penalty factor based on the preset parameter and the target penalty factor to obtain an updated target penalty factor; wherein, the target penalty factor used in subsequent calculations is the updated target penalty factor.

[0124] Among them, implementing this implementation method, calculations are carried out based on the target key parameter, the target Lagrange multiplier, and the target penalty factor, continuously exploring the current minimum value of the augmented Lagrange function. In each iteration, by comparing the difference between the current minimum value and the previous minimum value, it is judged whether to continue optimization. If the difference is greater than the preset difference, then update the target key parameter, the target Lagrange multiplier, and the target penalty factor to ensure that each iteration moves in a more optimal direction. This process of gradually iterative optimization can accurately adjust the key parameters of the model to make it more suitable for the actual operation requirements.

[0125] Implementing the above implementation method can achieve real-time and accurate optimization operations on the equipment of thermal power units. In addition, this application can also ensure that subsequent optimization operations are based on the most real equipment state. In addition, this application can also specifically adjust these model key parameters, avoiding blind attempts, greatly improving the optimization efficiency, contributing to quickly achieving the goals of reducing coal consumption and improving energy utilization efficiency, while reducing unnecessary resource waste, enhancing the economy and stability of the operation of thermal power units. In addition, this application can also help operators accurately control, avoid blind operations, improve the optimization efficiency, optimize the digital twin model, and enhance the reliability and practicality of the model. In addition, this application can also make the optimization results more accurate and more in line with actual requirements. In addition, this application can accurately adjust the model key parameters to make it more suitable for the actual operation requirements.

[0126] In an exemplary embodiment, a computer device is provided. The computer device can be a server or a terminal, and its internal structure diagram can be as Figure 9As shown in the figure. The computer device includes a processor, a memory, an input / output interface (Input / Output, abbreviated as I / O), and a communication interface. Among them, the processor, the memory, and the input / output interface are connected through a system bus, and the communication interface is connected to the system bus through the input / output interface. Among them, the processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program, and a database. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The database of the computer device is used to store the operation optimization data of the thermal power unit. The input / output interface of the computer device is used to exchange information between the processor and external devices. The communication interface of the computer device is used to communicate with an external terminal through a network connection. When the computer program is executed by the processor, it implements an operation optimization method for a thermal power unit.

[0127] Those skilled in the art can understand that Figure 9 the structure shown in the figure is only a block diagram of some structures related to the solution of this application, and does not constitute a limitation on the computer device to which the solution of this application is applied. The specific computer device may include more or fewer components than those shown in the figure, or combine certain components, or have different component arrangements.

[0128] In an exemplary embodiment, a computer device is further provided, including a memory and a processor. A computer program is stored in the memory. When the processor executes the computer program, the steps in the above method embodiments are implemented.

[0129] In an exemplary embodiment, a computer-readable storage medium is provided, storing a computer program. When the computer program is executed by the processor, the steps in the above method embodiments are implemented.

[0130] In an exemplary embodiment, a computer program product is provided, including a computer program. When the computer program is executed by the processor, the steps in the above method embodiments are implemented.

[0131] In an exemplary embodiment, a chip is provided. The chip includes a processor and a communication interface. The communication interface is coupled to the processor. The processor is used to run programs or instructions to implement the steps in the above method embodiments, and can achieve the same technical effects. To avoid repetition, it will not be elaborated here.

[0132] It should be understood that the chip mentioned in the embodiments of this application may also be referred to as a system-level chip, a system chip, a chip system, or a system-on-chip, etc.

[0133] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data for analysis, stored data, displayed data, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties, and the collection, use, and processing of relevant data need to comply with relevant regulations.

[0134] Those of ordinary skill in the art can understand that all or part of the processes in the methods of the above embodiments can be completed by instructing relevant hardware through a computer program. This computer program can be stored in a non-volatile computer-readable storage medium. When this computer program is executed, it can include the processes of the embodiments of the above various methods. Among them, any reference to a memory, database, or other medium used in the various embodiments provided in this application can include at least one of non-volatile and volatile memories. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetoresistive random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. By way of illustration and not limitation, RAM can be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM), etc.

[0135] The databases involved in the various embodiments provided in this application can include at least one of relational databases and non-relational databases. Non-relational databases can include distributed databases based on blockchain, etc., without limitation. The processors involved in the various embodiments provided in this application can be general-purpose processors, central processors, graphics processors, digital signal processors, programmable logic devices, data processing logics based on quantum computing, etc., without limitation.

[0136] The technical features of the above embodiments can be combined arbitrarily. For the sake of brevity of description, not all possible combinations of the various technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, it should be considered as the scope recorded in this specification.

[0137] In this text, specific examples are used to elaborate on the principles and implementation manners of the present application. The description of the above embodiments is only used to help understand the method of the present application and its core idea; at the same time, for those of ordinary skill in the art, according to the idea of the present application, there will be changes in the specific implementation manners and application scopes. In summary, the content of this specification should not be construed as a limitation to the present application.

Claims

1. An operation optimization method for a thermal power unit, characterized in that, The operation optimization method for the thermal power unit includes: Obtaining the target digital twin model of the flue gas waste heat cascade utilization system of the thermal power unit and the boundary parameters of the target digital twin model; Obtaining multiple adjustment parameters in the target digital twin model; Determining the model key parameters from the multiple adjustment parameters; Optimizing the model key parameters based on the boundary parameters to obtain the optimal key parameters corresponding to the model key parameters; Applying the optimal key parameters to the target equipment corresponding to the optimal key parameters, so that the flue gas waste heat cascade utilization system of the thermal power unit operates based on the optimal key parameters; wherein, the target equipment is the equipment in the flue gas waste heat cascade utilization system of the thermal power unit.

2. The operation optimization method of the thermal power unit according to claim 1, wherein The operation optimization method for the thermal power unit further includes: Constructing a digital twin model based on the flue gas waste heat cascade utilization system of the thermal power unit; wherein, the digital twin model at least includes a boiler sub-model, a waste heat sub-model, and a steam turbine sub-model; At every preset time interval, collecting real-time data from the flue gas waste heat cascade utilization system and injecting the real-time data into the digital twin model, so that the digital twin model performs real-time dynamic simulation based on the real-time data; And, the specific manner of obtaining the target digital twin model of the flue gas waste heat cascade utilization system of the thermal power unit and the boundary parameters of the target digital twin model is: Determining the digital twin model of the flue gas waste heat cascade utilization system of the thermal power unit injected with the latest real-time data as the target digital twin model; Obtaining the boundary parameters corresponding to the target digital twin model.

3. The operation optimization method of the thermal power unit according to claim 1, wherein, The adjustment parameters include: the opening degree of the first air preheater bypass flue gas damper, the opening degree of the second air preheater bypass flue gas damper, the circulating water pump frequency, the opening degree of the total valve for feeding water to the high-pressure economizer, the opening degree of the first branch valve for feeding water to the high-pressure economizer, the opening degree of the second branch valve for feeding water to the high-pressure economizer, the opening degree of the condensate to the low-pressure economizer booster pump, the opening degree of the condensate to the low-pressure economizer bypass valve, the opening degree of the condensate to the first low-pressure economizer, and the opening degree of the condensate to the second low-pressure economizer; the specific process of determining the model key parameters from the multiple adjustment parameters includes: Obtaining multiple groups of training adjustment parameter groups; wherein, each group of training adjustment parameter groups contains all the adjustment parameters, and the value of each adjustment parameter is a randomly obtained value within the corresponding value range of the current adjustment parameter; Obtaining the actual coal consumption of each group of training adjustment parameter groups during actual operation; Performing simulation operations on each group of training adjustment parameter groups through the target digital twin model to obtain the simulated coal consumption of each group of training adjustment parameter groups; Using the actual coal consumption and the simulated coal consumption to determine the model key parameters from the multiple adjustment parameters; wherein, the model key parameters are the opening degree of the first air preheater bypass flue gas damper, the opening degree of the second air preheater bypass flue gas damper, the circulating water pump frequency, and the opening degree of the first branch valve for feeding water to the high-pressure economizer.

4. The operation optimization method of the thermal power unit according to claim 3, characterized in that The specific process of using the actual coal consumption and the simulated coal consumption to determine the model key parameters from the multiple adjustment parameters includes: Compare the actual coal consumption of each training adjustment parameter group with the simulated coal consumption to obtain the coal consumption residual value of each training adjustment parameter group; Based on the actual coal consumption, simulated coal consumption, and coal consumption residual value of each training adjustment parameter group, construct a residual table; Analyze the residual table to determine the parameter sensitivity of each adjustment parameter; Determine the model key parameters as the adjustment parameters whose parameter sensitivity is greater than the preset threshold.

5. The operation optimization method of the thermal power unit according to claim 1, characterized in that Optimizing the model key parameters based on the boundary parameters to obtain the optimal key parameters corresponding to the model key parameters, specifically including: Determine the key boundary parameters corresponding to the model key parameters from the boundary parameters; Determine the initial key parameters corresponding to the model key parameters based on the key boundary parameters; wherein, the initial key parameters are less than or equal to the key boundary parameters; Calculate based on the initial key parameters, the preset initial Lagrange multiplier, and the initial penalty factor to obtain the current minimum value of the augmented Lagrangian function; Update the initial key parameters based on the current minimum value to obtain the target key parameters; Update the initial Lagrange multiplier based on the initial Lagrange multiplier, the initial penalty factor, and the key boundary parameters to obtain the target Lagrange multiplier; Update the initial penalty factor based on the preset parameters and the initial penalty factor to obtain the target penalty factor; Repeat the optimization operation based on the target key parameters, the target Lagrange multiplier, and the target penalty factor until the difference between the current minimum value and the previous minimum value corresponding to the current minimum value is less than or equal to the preset difference, or the target key parameters are the same as the key boundary parameters.

6. The operation optimization method of the thermal power unit according to claim 5, characterized in that The optimization operation specifically includes: Calculate based on the target key parameters, the target Lagrange multiplier, and the target penalty factor to obtain the current minimum value of the augmented Lagrangian function; If the difference between the current minimum value and the previous minimum value corresponding to the current minimum value is greater than the preset difference, update the target key parameters based on the current minimum value to obtain the updated target key parameters; wherein, the target key parameters used in subsequent calculations are the updated target key parameters; Update the target Lagrange multiplier based on the target Lagrange multiplier, the target penalty factor, and the key boundary parameters to obtain the updated target Lagrange multiplier; wherein, the target Lagrange multiplier used in subsequent calculations is the updated target Lagrange multiplier; Update the target penalty factor based on the preset parameters and the target penalty factor to obtain the updated target penalty factor; wherein, the target penalty factor used in subsequent calculations is the updated target penalty factor.

7. An operation optimization device for a thermal power unit, characterized in that The operation optimization device of the thermal power unit includes: A first acquisition unit for acquiring the target digital twin model of the flue gas waste heat cascade utilization system of the thermal power unit and the boundary parameters of the target digital twin model; A second acquisition unit for acquiring a plurality of adjustment parameters in the target digital twin model; A determination unit, configured to determine model key parameters from the multiple adjustment parameters; An optimization unit, configured to optimize the model key parameters based on the boundary parameters to obtain optimal key parameters corresponding to the model key parameters; An application unit, configured to apply the optimal key parameters to a target device corresponding to the optimal key parameters, so that the flue gas waste heat cascade utilization system of the thermal power unit operates based on the optimal key parameters; wherein, the target device is a device in the flue gas waste heat cascade utilization system of the thermal power unit.

8. A computer device, comprising: A memory, a processor, and a computer program stored on the memory and executable on the processor, wherein the processor executes the computer program to implement the steps of the thermal power unit operation optimization method according to any one of claims 1-6.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by the processor, it implements the steps of the thermal power unit operation optimization method according to any one of claims 1-6.

10. A computer program product, comprising a computer program, characterized in that, When the computer program is executed by the processor, it implements the steps of the thermal power unit operation optimization method according to any one of claims 1-6.

Images