Method for determining optimal sliding parameter working condition of steam turbine generator unit based on DOE response surface method

Abstract

The invention is suitable for the technical field of determining the optimal slip parameter working condition of a steam turbine generator unit based on a DOE response curved surface method, and provides a method for determining the optimal slip parameter working condition of the steam turbine generator unit based on the DOE response curved surface method. The method is based on a DOE response curved surface method, and has a good theoretical basis and practical application; according to the method, through statistical methods such as variance analysis and residual analysis, the goodness of fit of the model can be effectively tested, and the accuracy of the optimal sliding parameter working condition is ensured; universality: the method is suitable for different types of steam turbine generator sets and has good universality; according to the method, the operation efficiency of the steam turbine generator set can be effectively improved, so that the fuel consumption and the operation cost are reduced, and good economical efficiency is achieved.

Description

Technical Field

[0001] The invention belongs to the technical field of determining the optimal sliding parameter operating condition of a steam turbine generator set using a response surface method, and in particular relates to a method for determining the optimal sliding parameter operating condition of a steam turbine generator set based on a DOE response surface method. Background Art

[0002] There are mainly the following methods for determining the sliding parameter conditions of traditional steam turbine generator sets: (1) Empirical method: This method determines the sliding parameter conditions based on experience and historical data, but the accuracy of this method is low and it is difficult to adapt to new operating conditions. (2) Experimental method: This method determines the sliding parameter conditions through experiments, but the cost of this method is high, the cycle is long, and it is difficult to conduct large-scale experiments. (3) Mathematical model method: This method determines the sliding parameter conditions by establishing a mathematical model, but the model establishment of this method is relatively complex and it is difficult to consider all influencing factors. The above existing technologies have the following deficiencies:

[0003] (1) Low accuracy: The accuracy of existing technologies is generally low and cannot meet the requirements for efficient operation of modern steam turbine generator sets.

[0004] (2) Poor versatility: The existing technology has poor versatility and is difficult to apply to different types of steam turbine generator sets.

[0005] (3) High cost and long cycle: The existing technology has high cost and long cycle, which can hardly meet the needs of practical applications. Summary of the invention

[0006] The present invention provides a method for determining the optimal sliding parameter operating condition of a steam turbine generator set based on a DOE response surface method, aiming to solve the problems that the prior art is generally not accurate enough to meet the requirements for efficient operation of modern steam turbine generator sets; poor versatility: the prior art is poor in versatility and is difficult to apply to different types of steam turbine generator sets; high cost and long cycle: the prior art is high in cost and long in cycle and is difficult to meet the needs of practical applications.

[0007] The present invention is implemented as follows: a method for determining the optimal sliding parameter operating condition of a steam turbine generator set based on a DOE response surface method, comprising the following steps:

[0008] Step 1: Select the load point for steam turbine operation according to the actual situation. The load point interval should not be greater than 5% of the total load.

[0009] Step 2: For different load points, based on the working principle of the steam turbine, select the steam inlet temperature, steam inlet pressure and steam inlet flow rate as variables, and the power generation coal consumption as the model response value, generate a response surface test design scheme, and record the test data after the test;

[0010] Step 3: According to the test data, a binary multiple regression model is obtained by fitting, and the relationship between the inlet steam temperature and the inlet steam pressure and the power generation coal consumption is analyzed by variance analysis of the binary multiple regression equation, and the variance analysis table and residual analysis chart are obtained to determine whether the test area reaches the optimal area of ​​the corresponding variable;

[0011] Step 4: When the test area reaches the optimal area of ​​the response variable, add axis points to generate a new test plan, test the new test plan again, and record the test data;

[0012] Step 5: Get the second-order response surface model according to the test data of the new test scheme, perform variance analysis on the second-order response surface equation, obtain the variance analysis table and residual analysis chart, and judge whether the second-order response surface equation fits the test data;

[0013] Step 6: Establish DOE contour map and DOE surface map based on the second-order response surface model, and determine the optimal point location area through the graph;

[0014] Step 7: Establish a response optimization diagram to determine the optimal values ​​of the steam inlet temperature, steam inlet pressure and steam inlet flow rate at a certain load point of the steam turbine;

[0015] Step 8. On the "load-pressure-temperature" diagram, connect the steam turbine inlet temperature and steam inlet pressure of the optimal operating conditions of the load point, and finally obtain the optimal sliding parameter operating condition diagram of the steam turbine generator set.

[0016] Preferably, the method of selecting the load point of the steam turbine operation in step 1 includes: throttling regulation, valve position control, power control and CCS control;

[0017] The throttling regulation controls the main steam to enter the steam turbine through one or several valves that open and close simultaneously;

[0018] The valve position control completes load regulation by adjusting the difference between the target valve position and the output valve position;

[0019] The power control adjusts the valve position and the regulating stage pressure by setting the difference between the target power and the actual power to achieve load control;

[0020] The CCS control, when DEH remote control and CCS input, the load is controlled according to the power control module of the load control center;

[0021] The steam turbine uses throttling or valve position control in the initial operation stage, and uses power control or CCS control during stable operation.

[0022] Preferably, the binary multiple regression model in step 3 is expressed as:

[0023] Y=β0+β1X1+β2X2+β3X12+β4X22+β5X1X2+∈

[0024] Among them, YY is the dependent variable (coal consumption for power generation), X1X1 and X2X2 are independent variables (inlet steam temperature and inlet steam pressure), β0, β1, β2, β3, β4, β5β0, β1, β2, β3, β4, β5 are model parameters, and ∈∈ is the error term.

[0025] Preferably, the variance analysis steps in step three are: significance test of model, significance test of variables, model goodness of fit, residual analysis, multicollinearity diagnosis and model selection.

[0026] Preferably, the significance test of the model is: determining whether the entire regression model is significant by an F test;

[0027] The significance test of the variables is to conduct a t-test on each predictor variable to determine whether their respective effects on the response variable are significant;

[0028] The goodness of fit of the model is evaluated by the coefficient of determination, which is between 0 and 1. The closer the value is to 1, the better the model fits.

[0029] The residual analysis checks the distribution of the residuals to ensure that they are approximately normally distributed and have constant variance;

[0030] The multicollinearity diagnosis, in multiple regression, needs to check whether there is multicollinearity between the predictor variables, that is, high correlation between the variables;

[0031] The model selection uses stepwise regression and best subsets regression variable selection methods to select the model.

[0032] Preferably, the residual analysis diagram steps in step three are: normality of residuals, independence of residuals, homogeneity of variance, outliers and influence points, model fit, and model selection.

[0033] Preferably, the normality of the residuals is checked by a histogram or a normal probability plot of the residuals to see whether the residuals are approximately normally distributed;

[0034] The independence of the residuals, by plotting the residuals against the order of observations to check if there is autocorrelation between the residuals;

[0035] The homogeneity of variance is checked by a scatter plot of the residuals versus the fitted values. If the variance is constant, then the points in the plot should be randomly distributed, with no particular pattern or trend.

[0036] The outliers and influential points, outliers are those values ​​that are significantly different from most other data points, and influential points are those points that have a disproportionate impact on the regression model;

[0037] The model fit can be evaluated by using statistics such as the coefficient of determination, adjusted coefficient of determination, and predicted coefficient of determination to assess the degree of fit of the model to the data. The higher the coefficient of determination, the greater the variability explained by the model.

[0038] The model selection adopts AIC, BIC or stepwise regression method to select the optimal model.

[0039] Preferably, the DOE contour plot in step six includes a two-dimensional view that connects all points with the same response value to form contour lines; the DOE surface plot includes a surface plot that provides a three-dimensional view that shows the relationship between two predictor variables (on the X and Y axes) and the response variable (Z axis, represented by the height of the surface).

[0040] Preferably, step 2 and step 4 also include integrating and storing the experimental data.

[0041] Preferably, the model is also verified and optimized, and the model verification method is: residual analysis, variance analysis, determination coefficient, adjusted determination coefficient, predicted determination coefficient, and the optimization method is: the contour map and surface map, mathematical optimization, software tools, experimental verification, sensitivity analysis and multi-objective optimization, wherein the mathematical optimization includes the use of mathematical methods, such as the steepest ascent method or the steepest descent method, to move step by step along the direction of maximum response to find the optimal solution; the software tools are, for example, one or more of Design-Expert, Minitab, and SAS; the experimental verification is to conduct experiments under the optimal conditions predicted by theory to verify the accuracy and reliability of the model; the sensitivity analysis is to determine which variables are most critical to the process by analyzing the degree of influence of different variables on the response variables; the multi-objective optimization is to use multi-objective optimization technology to balance various objectives when there are multiple response variables.

[0042] Compared with the prior art, the embodiments of the present application have the following beneficial effects:

[0043] The optimal steam inlet pressure and temperature of each load point of the steam turbine generator set are analyzed by the DOE response surface method in statistics. The optimal sliding parameter operating condition diagram of the steam turbine generator set is drawn by the optimal steam inlet pressure and temperature of each operating point. In actual production, the steam turbine inlet steam temperature and temperature are controlled according to the optimal sliding parameter operating condition diagram of the steam turbine generator set, so as to achieve efficient operation of the steam turbine generator set. It is scientific: this method is based on the DOE response surface method and has a good theoretical basis and practical application; accuracy: this method can effectively test the goodness of fit of the model through statistical methods such as variance analysis and residual analysis, and ensure the accuracy of the optimal sliding parameter operating condition; versatility: this method is applicable to different types of steam turbine generator sets and has good versatility; economy: this method can effectively improve the operating efficiency of the steam turbine generator set, thereby reducing fuel consumption and operating costs, and has good economy. BRIEF DESCRIPTION OF THE DRAWINGS

[0044] Figure 1 It is a schematic diagram of the flow structure of a method for determining the optimal sliding parameter operating condition of a steam turbine generator set based on the DOE response surface method of the present invention; DETAILED DESCRIPTION

[0045] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as those commonly understood by technicians in the technical field of this application; the terms used in the specification of the application herein are only for the purpose of describing specific embodiments and are not intended to limit this application; the terms "including" and "having" and any variations thereof in the specification and claims of this application and the above-mentioned drawings are intended to cover non-exclusive inclusions. The terms "first", "second", etc. in the specification and claims of this application or the above-mentioned drawings are used to distinguish different objects, not to describe a specific order.

[0046] Reference to "embodiments" herein means that a particular feature, structure, or characteristic described in conjunction with the embodiments may be included in at least one embodiment of the present application. The appearance of the phrase in various locations in the specification does not necessarily refer to the same embodiment, nor is it an independent or alternative embodiment that is mutually exclusive with other embodiments. It is explicitly and implicitly understood by those skilled in the art that the embodiments described herein may be combined with other embodiments.

[0047] The embodiment of the present invention provides a method for determining the optimal sliding parameter operating condition of a steam turbine generator set based on the DOE response surface method, as shown in the figure, comprising the following steps:

[0048] Step 1: Select the load point for steam turbine operation according to the actual situation. The load point interval should not be greater than 5% of the total load.

[0049] Step 2: For different load points, based on the working principle of the steam turbine, select the steam inlet temperature, steam inlet pressure and steam inlet flow rate as variables, and the power generation coal consumption as the model response value, generate a response surface test design scheme, and record the test data after the test;

[0050] Step 3: According to the test data, a binary multiple regression model is obtained by fitting, and the relationship between the inlet steam temperature and the inlet steam pressure and the power generation coal consumption is analyzed by variance analysis of the binary multiple regression equation, and the variance analysis table and residual analysis chart are obtained to determine whether the test area reaches the optimal area of ​​the corresponding variable;

[0051] Step 4: When the test area reaches the optimal area of ​​the response variable, add axis points to generate a new test plan, test the new test plan again, and record the test data;

[0052] Step 5: Get the second-order response surface model according to the test data of the new test scheme, perform variance analysis on the second-order response surface equation, obtain the variance analysis table and residual analysis chart, and judge whether the second-order response surface equation fits the test data;

[0053] Step 6: Establish DOE contour map and DOE surface map based on the second-order response surface model, and determine the optimal point location area through the graph;

[0054] Step 7: Establish a response optimization diagram to determine the optimal values ​​of the steam inlet temperature, steam inlet pressure and steam inlet flow rate at a certain load point of the steam turbine;

[0055] Step 8. On the "load-pressure-temperature" diagram, connect the steam turbine inlet temperature and steam inlet pressure of the optimal operating conditions of the load point, and finally obtain the optimal sliding parameter operating condition diagram of the steam turbine generator set.

[0056] The prior art has the following deficiencies:

[0057] Low accuracy: The accuracy of existing technologies is generally not high, and it is difficult to meet the requirements of efficient operation of modern steam turbine generator sets; Poor versatility: The versatility of existing technologies is poor, and it is difficult to apply to different types of steam turbine generator sets; High cost and long cycle: The cost of existing technologies is high, the cycle is long, and it is difficult to meet the needs of actual applications.

[0058] The optimal steam inlet pressure and temperature of each load point of the steam turbine generator set are analyzed by the DOE response surface method in statistics. The optimal sliding parameter operating condition diagram of the steam turbine generator set is drawn by the optimal steam inlet pressure and temperature of each operating point. In actual production, the steam turbine inlet steam temperature and temperature are controlled according to the optimal sliding parameter operating condition diagram of the steam turbine generator set, so as to achieve efficient operation of the steam turbine generator set. It is scientific: this method is based on the DOE response surface method and has a good theoretical basis and practical application; accuracy: this method can effectively test the goodness of fit of the model through statistical methods such as variance analysis and residual analysis, and ensure the accuracy of the optimal sliding parameter operating condition; versatility: this method is applicable to different types of steam turbine generator sets and has good versatility; economy: this method can effectively improve the operating efficiency of the steam turbine generator set, thereby reducing fuel consumption and operating costs, and has good economy.

[0059] The load point selection methods for steam turbine operation in step 1 include: throttling regulation, valve position control, power control and CCS control;

[0060] Throttling regulation, controlling the main steam entering the turbine through one or several valves that open and close simultaneously;

[0061] Valve position control, which completes load regulation by adjusting the difference between the target valve position and the output valve position;

[0062] Power control, by setting the difference between target power and actual power to adjust valve position and regulating stage pressure to achieve load control;

[0063] CCS control: when DEH remote control and CCS are in operation, the load is controlled according to the power control module of the load control center;

[0064] Throttling or valve position control is used in the initial stage of turbine operation, and power control or CCS control is used during stable operation.

[0065] The binary multiple regression model in step 3 is expressed as:

[0066] Y=β0+β1X1+β2X2+β3X12+β4X22+β5X1X2+∈

[0067] Among them, YY is the dependent variable (coal consumption for power generation), X1 X1 and X2X2 are independent variables (inlet steam temperature and inlet steam pressure), β0, β1, β2, β3, β4, β5β0, β1, β2, β3, β4, β5 are model parameters, and ∈∈ is the error term.

[0068] The variance analysis steps in step three are: significance test of model, significance test of variables, model goodness of fit, residual analysis, multicollinearity diagnosis and model selection.

[0069] The significance test of the model is: use the F test to determine whether the entire regression model is significant;

[0070] Significance test of variables: perform a t-test on each predictor variable to determine whether their respective effects on the response variable are significant;

[0071] Model goodness of fit, the coefficient of determination is used to evaluate the degree of fit of the model to the data. The value of the coefficient of determination is between 0 and 1. The closer the value is to 1, the better the model fits;

[0072] Residual analysis, which examines the distribution of the residuals to ensure that they are approximately normally distributed and have constant variance;

[0073] Multicollinearity diagnosis, in multiple regression, it is necessary to check whether there is multicollinearity between predictor variables, that is, high correlation between variables;

[0074] Model selection, using stepwise regression, best subsets regression variable selection method to select the model.

[0075] The residual analysis graph steps in step three are: normality of residuals, independence of residuals, homogeneity of variance, outliers and influence points, model fit, and model selection.

[0076] Normality of residuals: Check whether the residuals are approximately normally distributed by using residual histograms or normal probability plots;

[0077] Independence of residuals, using plots of residuals versus observation order to check for autocorrelation between residuals;

[0078] Homogeneity of variance is checked by a scatter plot of the residuals versus the fitted values. If the variance is constant, then the points in the plot should be randomly distributed, with no particular pattern or trend.

[0079] Outliers and influential points. Outliers are those values ​​that are significantly different from most other data points, while influential points are those points that have a disproportionate impact on the regression model.

[0080] Model fit can be evaluated through statistics such as the coefficient of determination, adjusted coefficient of determination, and predicted coefficient of determination. The higher the value of the coefficient of determination, the greater the variability explained by the model;

[0081] Model selection, using AIC, BIC or stepwise regression methods to select the optimal model.

[0082] The DOE contour plot in step 6 shows a two-dimensional view, connecting all points with the same response value to form contour lines; the DOE surface plot provides a three-dimensional view showing the relationship between the two predictor variables (on the X and Y axes) and the response variable (the Z axis, represented by the height of the surface).

[0083] Step 2 and step 4 also include integrating and storing the experimental data.

[0084] It also includes model verification and optimization. The model verification methods are: residual analysis, variance analysis, determination coefficient, adjusted determination coefficient, predicted determination coefficient. The optimization methods are: contour plots and surface plots, mathematical optimization, software tools, experimental verification, sensitivity analysis and multi-objective optimization. Mathematical optimization includes the use of mathematical methods, such as the steepest ascent method or the steepest descent method, to move step by step along the direction of maximum response to find the optimal solution; software tools, such as Design-Expert, Minitab, SAS or one or more; experimental verification, conducting experiments under the optimal conditions predicted by theory to verify the accuracy and reliability of the model; sensitivity analysis, determining which variables are most critical to the process by analyzing the degree of influence of different variables on the response variables; multi-objective optimization, when there are multiple response variables, use multi-objective optimization technology to balance each goal.

[0085] The electrical components appearing in the text are all electrically connected to the controller and the power supply. The control method of the present invention is controlled by the controller. The control circuit of the controller can be implemented by simple programming by technicians in this field. The provision of power supply is also common knowledge in this field. The present invention is mainly used to protect mechanical devices, so the present invention will no longer explain the control method and circuit connection in detail.

[0086] It should be noted that, for the above-mentioned embodiments, for the sake of simplicity, they are all described as a series of action combinations, but those skilled in the art should know that the present invention is not limited by the described order of actions, because according to the present invention, some steps may be performed in other orders or simultaneously. Secondly, those skilled in the art should also know that the embodiments described in the specification are all preferred embodiments, and the actions and modules involved are not necessarily required by the present invention.

[0087] In the several embodiments provided in the present application, it should be understood that the disclosed devices can be implemented in other ways. For example, the device embodiments described above are merely schematic, such as the division of the above-mentioned units. There may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or communication connection shown or discussed can be through some interfaces, and the indirect coupling or communication connection between devices or units can be in the form of telecommunication or other forms.

[0088] The units described above as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0089] The above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit the scope of protection of the invention. Obviously, the described embodiments are only some embodiments of the present invention, rather than all embodiments. Based on these embodiments, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of the present invention. Although the present invention has been described in detail with reference to the above embodiments, ordinary technicians in this field can still combine, add, delete or make other adjustments to the features in the various embodiments of the present invention according to the circumstances without conflict, without making creative work, so as to obtain different other technical solutions that do not deviate from the concept of the present invention in essence, and these technical solutions also belong to the scope of protection of the present invention.

Claims

1. A method for determining the optimal sliding parameter operating condition of a steam turbine generator set based on DOE response surface method, characterized in that: The following steps are involved: Step 1: Select the load point for steam turbine operation according to the actual situation. The load point interval should not be greater than 5% of the total load. Step 2: For different load points, based on the working principle of the steam turbine, select the steam inlet temperature, steam inlet pressure and steam inlet flow rate as variables, and the power generation coal consumption as the model response value, generate a response surface test design scheme, and record the test data after the test; Step 3: According to the test data, a binary multiple regression model is obtained by fitting, and the relationship between the inlet steam temperature and the inlet steam pressure and the power generation coal consumption is analyzed by variance analysis of the binary multiple regression equation, and the variance analysis table and residual analysis chart are obtained to determine whether the test area reaches the optimal area of ​​the corresponding variable; Step 4: When the test area reaches the optimal area of ​​the response variable, add axis points to generate a new test plan, test the new test plan again, and record the test data; Step 5: Get the second-order response surface model according to the test data of the new test scheme, perform variance analysis on the second-order response surface equation, obtain the variance analysis table and residual analysis chart, and judge whether the second-order response surface equation fits the test data; Step 6: Establish DOE contour map and DOE surface map based on the second-order response surface model, and determine the optimal point location area through the graph; Step 7: Establish a response optimization diagram to determine the optimal values ​​of the steam inlet temperature, steam inlet pressure and steam inlet flow rate at a certain load point of the steam turbine; Step 8. On the "load-pressure-temperature" diagram, connect the steam turbine inlet temperature and steam inlet pressure of the optimal operating conditions of the load point, and finally obtain the optimal sliding parameter operating condition diagram of the steam turbine generator set.

2. A method for determining the optimal sliding parameter operating condition of a steam turbine generator set based on DOE response surface method according to claim 1, characterized in that: The load point selection method of the steam turbine operation in step 1 includes: throttling regulation, valve position control, power control and CCS control; The throttling regulation controls the main steam to enter the steam turbine through one or several valves that open and close simultaneously; The valve position control completes load regulation by adjusting the difference between the target valve position and the output valve position; The power control adjusts the valve position and the regulating stage pressure by setting the difference between the target power and the actual power to achieve load control; The CCS control, when DEH remote control and CCS input, the load is controlled according to the power control module of the load control center; The steam turbine uses throttling or valve position control in the initial operation stage, and uses power control or CCS control during stable operation.

3. The method for determining the optimal sliding parameter condition of a steam turbine generator set based on DOE response surface method according to claim 1, characterized in that: The binary multiple regression model in step 3 is expressed as: Y=β0+β1X1+β2X2+β3X12+β4X22+β5X1X2+∈ Among them, YY is the dependent variable (coal consumption for power generation), X1X1 and X2X2 are independent variables (inlet steam temperature and inlet steam pressure), β0, β1, β2, β3, β4, β5β0, β1, β2, β3, β4, β5 are model parameters, and ∈∈ is the error term.

4. A method for determining the optimal sliding parameter operating condition of a steam turbine generator set based on DOE response surface method as claimed in claim 3, characterized in that: The variance analysis steps in step three are: significance test of model, significance test of variables, goodness of model fit, residual analysis, multicollinearity diagnosis and model selection.

5. The method for determining the optimal sliding parameter condition of a steam turbine generator set based on DOE response surface method according to claim 4, characterized in that: The significance test of the model is: determine whether the entire regression model is significant through F test; The significance test of the variables is to conduct a t-test on each predictor variable to determine whether their respective effects on the response variable are significant; The goodness of fit of the model is evaluated by the coefficient of determination, which is between 0 and 1. The closer the value is to 1, the better the model fits. The residual analysis checks the distribution of the residuals to ensure that they are approximately normally distributed and have constant variance; The multicollinearity diagnosis, in multiple regression, needs to check whether there is multicollinearity between the predictor variables, that is, high correlation between the variables; The model selection uses stepwise regression and best subsets regression variable selection methods to select the model.

6. The method for determining the optimal sliding parameter operating condition of a steam turbine generator set based on DOE response surface method according to claim 1, characterized in that: The residual analysis diagram steps in step three are: normality of residuals, independence of residuals, homogeneity of variance, outliers and influence points, model fit, and model selection.

7. A method for determining the optimal sliding parameter operating condition of a steam turbine generator set based on DOE response surface method as claimed in claim 6, characterized in that: Normality of the residuals, by checking whether the residuals are approximately normally distributed through a histogram or a normal probability plot of the residuals; The independence of the residuals, by plotting the residuals against the order of observations to check if there is autocorrelation between the residuals; The homogeneity of variance is checked by a scatter plot of the residuals versus the fitted values. If the variance is constant, then the points in the plot should be randomly distributed, with no particular pattern or trend. The outliers and influential points, outliers are those values ​​that are significantly different from most other data points, and influential points are those points that have a disproportionate impact on the regression model; The model fit can be evaluated by using statistics such as the coefficient of determination, adjusted coefficient of determination, and predicted coefficient of determination to assess the degree of fit of the model to the data. The higher the coefficient of determination, the greater the variability explained by the model. The model selection adopts AIC, BIC or stepwise regression method to select the optimal model.

8. The method for determining the optimal sliding parameter operating condition of a steam turbine generator set based on DOE response surface method according to claim 1, characterized in that: The DOE contour plot in step six includes a two-dimensional view that connects all points with the same response value to form contour lines; the DOE surface plot includes a surface plot that provides a three-dimensional view that shows the relationship between two predictor variables (on the X and Y axes) and the response variable (Z axis, represented by the height of the surface).

9. The method for determining the optimal sliding parameter operating condition of a steam turbine generator set based on DOE response surface method according to claim 1, characterized in that: The step 2 and the step 4 also include integrating and storing the experimental data.

10. The method for determining the optimal sliding parameter operating condition of a steam turbine generator set based on DOE response surface method according to claim 1, characterized in that: It also includes verification and optimization of the model. The model verification method is: residual analysis, variance analysis, determination coefficient, adjusted determination coefficient, predicted determination coefficient. The optimization method is: contour map and surface map, mathematical optimization, software tools, experimental verification, sensitivity analysis and multi-objective optimization. The mathematical optimization includes the use of mathematical methods, such as the steepest ascent method or the steepest descent method, to move step by step along the direction of maximum response to find the optimal solution; the software tools are, for example, Design-Expert, Minitab, SAS or one or more; the experimental verification is to conduct experiments under the optimal conditions predicted by theory to verify the accuracy and reliability of the model; the sensitivity analysis is to determine which variables are most critical to the process by analyzing the degree of influence of different variables on the response variables; the multi-objective optimization is to use multi-objective optimization technology to balance various objectives when there are multiple response variables.

Images