Method and system for judging power generation capacity range of heat supply steam extraction on thermal power generating unit, readable medium and electronic equipment
By combining physical mechanisms and transfer learning algorithms, the problem of poor generalization of thermal power set model and neural network in the existing technology is solved, and the accurate judgment of the power generation capacity range of thermal power sets is achieved, providing more reliable power generation Ability assessment.
Patent Information
- Application Number
- CN202411108417.X
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-08-13
- Publication Date
- 2024-11-26
AI Technical Summary
When judging the power generation range of heating and steam extraction to thermal power units, the prior art depends on the thermal power unit model structure and parameters, resulting in excessive fitting accuracy and qualitative relationship errors, and the neural network model does not perform in generalization. It is not possible to accurately obtain the actual power generation capacity range of the thermal power unit.
Using a combination of physical mechanisms and transfer learning algorithms, the minimum main steam flow, minimum main steam flow and minimum exhaust volume of thermal power sets are generated to generate the minimum main steam flow and power generation capacity range under heating and extraction steam, and transfer learning is used The algorithm trains the initial heating and exhaust gas volume and power model to ensure that the model error is less than the preset value, and thus obtains a more accurate power generation capacity range.
It realizes that the power generation capacity range of thermal power units is more accurately obtained without relying on operating data to judge the power generation capacity boundary, avoids qualitative relationship errors, and improves the generalization and accuracy of the model.
Smart Images

Figure CN119026504A_ABST
Abstract
Description
Technical Field
[0001] The invention relates to a method, a system, a readable medium and an electronic device for judging the power generation capacity range of a thermal power unit due to heat extraction steam, and belongs to the technical field of power generation of thermal power units. Background Art
[0002] With the increase in the proportion of new energy sources such as wind and solar, the power system has an increasing demand for the peak-shaving capacity of thermal power units. Heat supply is one of the main factors affecting the peak-shaving capacity of thermal power units. Judging the restrictions of heat supply on the output range of thermal power units is of great significance for understanding the actual peak-shaving capacity of thermal power.
[0003] At present, the method for judging the effect of heating steam extraction on the output of thermal power units is mainly to construct a mechanism model of the thermal power unit, change the amount of heating steam extraction under the boundary conditions of the model, and calculate the upper and lower limits of the power generation capacity of the thermal power unit under different heating steam extraction. This physical method has good logical reasoning and the steps are explainable; but it is more dependent on the model structure and equipment parameters of the thermal power unit, and because the modeling process uses idealized parameters and empirical formulas, it leads to a certain deviation from the actual situation. In addition, conventional neural networks are often used in the training of existing thermal power unit models. Conventional neural network models have poor performance in generalization in thermal power models, and qualitative relationship errors often occur due to excessive pursuit of fitting accuracy. Summary of the invention
[0004] In view of the above problems, the purpose of the present invention is to provide a method, system, readable medium and electronic device for determining the power generation capacity range of a thermal power unit due to heat extraction steam, which is not limited to determining the power generation capacity boundary based on operating data and can more accurately obtain the power generation capacity range of the thermal power unit.
[0005] To achieve the above-mentioned purpose, the present invention proposes the following technical scheme: a method for judging the range of power generation capacity of a thermal power unit due to heating extraction steam, comprising the following steps: obtaining the maximum main steam flow, minimum main steam flow, minimum exhaust volume and heating extraction steam volume of the thermal power unit; inputting the minimum exhaust volume into a heating extraction steam exhaust volume model to generate the minimum main steam flow under heating extraction steam; according to the minimum main steam flow under heating extraction steam, combined with the maximum main steam flow and the minimum main steam flow of the thermal power unit, obtaining the upper and lower boundaries of the main steam under heating extraction steam; inputting the upper and lower boundaries of the main steam under heating extraction steam into the heating extraction steam power model to obtain the power generation capacity range of the thermal power unit under heating extraction steam.
[0006] Furthermore, the heating steam extraction exhaust volume model and the heating steam extraction power model obtain an initial heating steam extraction exhaust volume model and an initial heating steam extraction power model through a typical thermal power mechanism model, and use the main steam flow, heating steam extraction volume, back pressure and exhaust volume as input variables. The initial heating steam extraction exhaust volume model and the initial heating steam extraction power model are trained through a transfer learning algorithm until the error between the calculated values of the thermodynamic parameters of the high-pressure cylinder, the medium-pressure cylinder and the low-pressure cylinder and the actual values of the heat balance diagram is less than a preset value, or the number of iterations is greater than a preset value.
[0007] Furthermore, the typical thermal power mechanism model physically derives and models the thermal power plant through thermodynamic mechanism formulas; conventional thermodynamic variables and power of the thermal power plant are used as output variables, and the conventional thermodynamic variables are consistent with the types of variables in the heat balance diagram.
[0008] Furthermore, the transfer learning algorithm includes a source domain and a target domain, the initial heating steam extraction exhaust volume model or the initial heating steam extraction power model is input into the source domain, and the target domain is a target thermal power plant.
[0009] Furthermore, the source domain is trained by three convolutional layers, the target domain is trained by a fully connected layer, and the three convolutional layers are concatenated with the fully connected layer to obtain a transfer learning algorithm model.
[0010] Furthermore, the fitted value of the transfer learning algorithm model is compared with the true value and characterized by the average absolute error MAE, the root mean square error RMSE and the regression coefficient COEFF.
[0011] Furthermore, the exhaust volume is obtained through the final stage extraction pressure; the relationship between the main steam flow and the exhaust volume is obtained through a fitting formula between the final stage extraction pressure and the exhaust volume, thereby obtaining a heating extraction exhaust volume model.
[0012] Furthermore, the method for obtaining the upper and lower boundaries of the main steam under the heating extraction steam is: in combination with the heating extraction steam exhaust volume model, under different heating extraction steam volumes, the lower boundary of the main steam flow rate is calculated with the minimum main steam flow rate and minimum exhaust volume set by the unit; and the maximum main steam flow rate set by the unit is used as the upper boundary of the main steam flow rate.
[0013] The present invention also discloses a system for judging the power generation capacity range of a thermal power unit affected by heating steam extraction, comprising: a parameter acquisition module, used to acquire the maximum main steam flow, the minimum main steam flow and the minimum exhaust volume of the thermal power unit; a heating steam extraction exhaust volume module, used to input the minimum exhaust volume into a heating steam extraction exhaust volume model to generate the minimum main steam flow under heating steam extraction; a main steam flow range acquisition module, used to obtain the upper and lower boundaries of the main steam flow under heating steam extraction according to the minimum main steam flow under heating steam extraction, combined with the maximum main steam flow and the minimum main steam flow of the thermal power unit; a power generation capacity range acquisition module, used to input the upper and lower boundaries of the main steam under heating steam extraction into the heating steam extraction power model to obtain the power generation capacity range of the thermal power unit under heating steam extraction.
[0014] Furthermore, the heating steam extraction exhaust volume model and the heating steam extraction power model obtain an initial heating steam extraction exhaust volume model and an initial heating steam extraction power model through a typical thermal power mechanism model, and train the initial heating steam extraction exhaust volume model and the initial heating steam extraction power model through a transfer learning algorithm.
[0015] The present invention also provides a computer-readable storage medium having a computer program stored thereon. The computer program is executed by a processor to implement any of the above methods for determining the range of power generation capacity of a thermal power unit due to steam extraction for heating.
[0016] The present invention also provides an electronic device, comprising: one or more processors; a memory; and one or more applications, wherein the one or more applications are stored in the memory and are configured to be executed by the one or more processors, and the one or more programs are used to execute any of the above-mentioned methods for determining the range of power generation capacity of a thermal power unit due to heating extraction steam.
[0017] The technical solution of the present invention has at least the following technical effects or advantages: The present invention is committed to exploring the maximum peak-shaving potential of thermal power units under heating conditions, and uses a model that combines physical mechanisms and artificial intelligence methods to solve the output range of the target thermal power units. The proposed method does not need to be limited to operating data to determine the power generation capacity boundary (even if the actual data does not approach the boundary). Because this method only uses actual data to identify the parameters of the model, and obtains the functional relationship between the main steam flow, power, heating extraction steam, and exhaust steam; and when fitting the power generation capacity boundary, it is only necessary to input the main steam flow boundary value and exhaust steam boundary value given by the unit into the functional relationship, so as to extend the impact of heating on the power generation capacity, and more accurately obtain the power generation capacity range of the thermal power unit. BRIEF DESCRIPTION OF THE DRAWINGS
[0018] Figure 1 is a flow chart of a method for determining the range of power generation capacity of a thermal power unit for heat extraction steam in one embodiment of the present invention; Figure 2 is a graph of the original data of the main steam flow rate in one embodiment of the present invention; Figure 3 is a graph of raw data of actual boiler load in one embodiment of the present invention; Figure 4 This is a graph of raw data of heating extraction steam flow rate in one embodiment of the present invention; Figure 5 is a diagram of the original data of exhaust volume in one embodiment of the present invention; Figure 6 is a relationship diagram between exhaust steam pressure and exhaust steam volume in one embodiment of the present invention; Figure 7 is a schematic diagram of an initial heating steam extraction exhaust volume model in one embodiment of the present invention; Figure 8 is a schematic diagram of an initial heating steam extraction power model in one embodiment of the present invention; Fig. 9 is a flow chart of a transfer learning algorithm in one embodiment of the present invention; Fig.10 is a fitting result diagram of a heating steam extraction exhaust volume model in one embodiment of the present invention; Fig.11 is a fitting result diagram of a heating steam extraction power model in one embodiment of the present invention; Fig.12 is a main steam flow range diagram of a target thermal power unit in one embodiment of the present invention; Fig.13 This is a diagram of the power generation capacity range of a thermal power unit under different heating steam extraction amounts in one embodiment of the present invention. DETAILED DESCRIPTION
[0019] In order to enable those skilled in the art to better understand the technical solution of the present invention, the present invention is described in detail through specific embodiments. However, it should be understood that the provision of specific embodiments is only for a better understanding of the present invention, and they should not be understood as limitations of the present invention. In the description of the present invention, it should be understood that the terms used are only for the purpose of description and cannot be understood as indicating or implying relative importance.
[0020] In order to solve the problems existing in the prior art, such as reliance on the model structure and parameters of the thermal power unit, errors in qualitative relationships due to excessive pursuit of fitting accuracy, and poor generalization of the neural network model, the present invention proposes a method, system, readable medium and electronic device for judging the power generation capacity range of the thermal power unit due to heating extraction steam, which uses a mode combining physical mechanism and artificial intelligence method to solve the output range of the target thermal power unit, without being limited to operating data to judge the power generation capacity boundary, and only uses actual data to identify the parameters of the model to obtain the functional relationship between the main steam flow, power, heating extraction steam and exhaust volume; and when fitting the power generation capacity boundary, only the main steam flow boundary value and exhaust volume boundary value given by the unit need to be input into the functional relationship, so that the power generation capacity range of the thermal power unit can be obtained more accurately. The scheme of the present invention is described in detail below through embodiments in conjunction with the accompanying drawings.
[0021] Embodiment 1 This embodiment discloses a method for determining the range of power generation capacity of a thermal power unit due to extraction steam for heating, such as Figure 1 As shown, the direct constraint of the power generation capacity of the thermal power unit is the main steam flow rate, which is limited or affected by the minimum exhaust volume and the heating steam extraction volume. This embodiment uses the main steam flow data, power data, and heating steam extraction data of a power plant to study the influence of heating steam extraction on the upper and lower limits of the unit's power generation capacity.
[0022] Since the original data span of thermal power units is relatively large, in order to facilitate research, in this embodiment, the power range is limited to 200MW-315MW, the main steam flow range is limited to 750t / h-1125t / h, and the heating extraction steam range is limited to 148.5t / h-335.4t / h. The above numerical range is limited only for the convenience of explaining the method in this embodiment, and it does not mean that the method can only be used in the above numerical range. There is no direct exhaust volume measurement point in the actual data, so it needs to be characterized by other parameters. According to the Frengel formula: the extraction pressure of the last stage is proportional to the exhaust volume. In this embodiment, the extraction pressure of the 5th section is selected to characterize the exhaust volume. Figure 2 It is the original data graph of the main steam flow rate; Figure 3 It is the original data diagram of actual boiler load; Figure 4 It is the original data diagram of heating extraction steam flow; Figure 5 It is the original data chart of exhaust volume. Figure 6 : is the relationship diagram between the exhaust steam pressure and the exhaust steam volume in this embodiment. It can be seen that there is an obvious linear relationship between the final stage extraction steam pressure and the exhaust steam volume. The final stage extraction steam pressure can be used to characterize the exhaust steam volume of the thermal power unit.
[0023] The method for determining the power generation capacity range of a thermal power unit comprises the following steps: S1 obtains the maximum main steam flow, minimum main steam flow, minimum exhaust volume and heating steam extraction volume of the thermal power unit.
[0024] S2 inputs the minimum exhaust volume into the heating extraction steam exhaust volume model to generate the minimum main steam flow under heating extraction steam.
[0025] S3 obtains the upper and lower boundaries of the main steam under heating extraction steam according to the minimum main steam flow under heating extraction steam, combined with the maximum main steam flow and the minimum main steam flow of the thermal power unit; the method for obtaining the upper and lower boundaries of the main steam under heating extraction steam is: in combination with the heating extraction steam exhaust volume model, under different heating extraction steam volumes, the lower boundary of the main steam flow is calculated with the minimum main steam flow and the minimum exhaust volume set by the unit; the maximum main steam flow set by the unit is used as the upper boundary of the main steam flow.
[0026] S4 inputs the upper and lower boundaries of the main steam under heating extraction steam into the heating extraction steam power model, obtains the power generation capacity range of the thermal power unit under heating extraction steam, and outputs the power generation capacity range under given heating conditions.
[0027] Using a typical thermal power plant mechanism model, the qualitative relationship between the objective functions of the initial heating steam extraction exhaust model and the initial heating steam extraction power model is obtained. The schematic diagram of the initial heating steam extraction exhaust model is shown in the figure. Figure 7 The schematic diagram of the initial heating steam extraction power model is shown in Figure 8 As shown. The qualitative relationships of the initial heating steam extraction exhaust volume model and the initial heating steam extraction power model are both approximately linear relationships, but there is still a slight nonlinearity. In order to ensure the accuracy of the data model, the initial heating steam extraction exhaust volume model and the initial heating steam extraction power model are trained by the transfer learning algorithm to ensure that the model conforms to the correct qualitative relationship. With the main steam flow, heating steam extraction volume, back pressure and exhaust volume as input variables, the initial heating steam extraction exhaust volume model and the initial heating steam extraction power model are trained by the transfer learning algorithm until the error between the calculated values of the thermodynamic parameters of the high-pressure cylinder, the medium-pressure cylinder and the low-pressure cylinder and the actual values of the heat balance diagram is less than the preset value, or the number of iterations is greater than the preset value. The typical thermal power mechanism model physically derives and models the thermal power plant through the thermodynamic mechanism formula. The preset value of the error in this embodiment is 3%. The preset value of the number of iterations is 100 times.
[0028] The training purpose of the transfer learning algorithm is to calculate the given thermal parameters in each mechanism formula, including the feedwater heater terminal difference, the flow coefficient of each group, the pressure loss coefficient, the efficiency, etc. This embodiment is trained with the thermal balance operating data provided by the power plant, and the conventional thermodynamic variables and power of the thermal power plant are used as output variables. The types of conventional thermodynamic variables and variables in the thermal balance diagram are consistent.
[0029] The training method of the heating extraction steam exhaust volume model and the heating extraction steam power model is: First, a first-stage high-pressure heater outlet water temperature (i.e., boiler feed water temperature) is given, and the heat balance formula of the recuperator is used to use an iterative method to determine the amount of steam that needs to be extracted from the unit for each stage of the recuperator and the outlet water temperature of the lower stage recuperator. Then, the water temperature after the condenser can be determined by calculating in sequence through the series calculation method. The steam temperature before the condenser is then obtained through the boiler outlet water temperature and the extraction volume at each stage, and compared with the water temperature after the condenser. According to the heat balance relationship of the condenser, it can be concluded whether the boiler feed water temperature is reasonable. If it is unreasonable, the binary search method is used to continue the calculation until the appropriate boiler feed water temperature is obtained, and finally the thermodynamic parameters of the thermal power plant are determined.
[0030] like Fig. 9 As shown in the figure, the transfer learning algorithm includes the source domain and the target domain. The heating steam extraction exhaust volume model and the heating steam extraction power model are derived from the typical thermal power mechanism model, and the mechanism data of the main steam flow, exhaust volume, power and heating steam extraction flow and the general mapping relationship are derived from the mechanism model, and the prior knowledge of the fitting relationship in terms of qualitative laws is obtained. The initial heating steam extraction exhaust volume model and the initial heating steam extraction power model are obtained, and the initial heating steam extraction exhaust volume model or the initial heating steam extraction power model is input in the source domain. The source domain is trained through three layers of convolutional layers. After the source domain training is completed, it will be frozen, and the structure, parameters and weights of the three layers of convolutional layers remain unchanged. At this point, the qualitative relationship between the initial heating steam extraction exhaust volume model and the initial heating steam extraction power model can be basically determined, but the accuracy of the model is not enough to describe the target power plant.
[0031] The target domain is the target thermal power plant. Actual data is collected from the target thermal power plant, and the final fully connected layer is trained with the actual data. At this time, the fully connected layer has a higher fitting accuracy, but poor generalization performance.
[0032] The three convolutional layers of the source domain are concatenated with the fully connected layers of the target domain to obtain a transfer learning algorithm model that satisfies both qualitative relationships and fitting accuracy. The fitting results of the target domain using transfer learning are shown in Figure 2. Fig.10 and Fig.11 shown. Fig.10 This is the fitting result diagram of the heating steam extraction exhaust volume model; Fig.11 This is the fitting result diagram of the heating extraction steam power model. Fig.10 , 11It can be seen that in the fitting of the target thermal power plant relationship, in the relationship cluster of the heating extraction steam exhaust volume model, the heating extraction steam is negatively correlated with the exhaust volume; the main steam flow rate is positively correlated with the exhaust volume; in the relationship cluster of the heating extraction steam power model, the heating extraction steam is negatively correlated with the power; the main steam flow rate is positively correlated with the power. The qualitative relationship of the target thermal power unit model fitted by transfer learning is consistent with the general mechanism model. This shows that transfer learning ensures the correctness of the fitting function structure, which ensures the credibility of the model extension. As can be seen from Table 1, under the fitting of the artificial intelligence method, the fitting accuracy of the two relationship equations is high, which meets the needs of analyzing the precise restrictions of heating extraction on power generation capacity. In summary, transfer learning takes into account both qualitative relationships and model accuracy.
[0033] Considering that transfer learning belongs to machine learning methods, the original data needs to be divided into training sets and test sets. In the training set, the model is trained using known variables and dependent variables; in the test set, the trained model is used to fit the variables, and the fitted value of the transfer learning algorithm model is compared with the true value, which is characterized by the absolute mean error MAE, root mean square error RMSE and regression coefficient COEFF. After testing the test set, the fitting accuracy is shown in Table 1.
[0034] Table 1 Fitting accuracy of heating extraction steam exhaust model and heating extraction steam power model Heating steam extraction exhaust volume model Heating extraction steam power model MAE 0.00131 2.383 RMSE 0.00173 3.095 The calculation formula of the absolute mean error MAE is:
[0035] In the formula, represents the absolute mean error, represents the number of samples, represents the fitted value, Indicates actual value.
[0036] The calculation formula of root mean square error RMSE is:
[0037] In the formula, represents the absolute mean error, represents the number of samples, represents the fitted value, Indicates the actual value. MAE and RMSE can indicate the error level between the fitted value and the true value. The smaller the values of these two parameters, the better the prediction effect. COEFF can indicate the quality of the fitting effect. The closer COEFF is to 1, the higher the accuracy.
[0038] Based on the function model fitted by the transfer learning method, the upper limit and lower limit of the main steam flow rate under different heating steam extraction rates can be calculated given the minimum main steam flow rate, maximum main steam flow rate, and minimum exhaust volume limited by the unit itself, such as Fig.12 As shown in the figure, it can be seen that the main steam flow rate limit range calculated by this method conforms to the general mechanism model law, proving that the qualitative relationship of this method is correct. At the same time, the actual main steam flow rate is within the main steam flow rate limit range calculated by the method, indicating that this method conforms to the actual situation.
[0039] Through the heating steam extraction power model, the power generation capacity range of the thermal power unit under different heating steam extraction amounts is calculated, such as Fig.13 As shown in the figure, the actual data range is consistent with the main steam and power range calculated by the proposed method, indicating that the method is feasible. It is worth noting that when the heating steam extraction is small, the lower limit of the power generation capacity of the power plant still has a certain margin.
[0040] Embodiment 2 Based on the same inventive concept, the present embodiment discloses a system for judging the power generation capacity range of a thermal power unit for heating extraction steam, including: a parameter acquisition module, used to obtain the maximum main steam flow, minimum main steam flow and minimum exhaust volume of the thermal power unit; a heating extraction steam exhaust volume module, used to input the minimum exhaust volume into a heating extraction steam exhaust volume model to generate the minimum main steam flow under heating extraction steam; a main steam flow range acquisition module, used to obtain the upper and lower boundaries of the main steam flow under heating extraction steam according to the minimum main steam flow under heating extraction steam, combined with the maximum main steam flow and the minimum main steam flow of the thermal power unit; a power generation capacity range acquisition module, used to input the upper and lower boundaries of the main steam under heating extraction steam into the heating extraction steam power model to obtain the power generation capacity range of the thermal power unit under heating extraction steam.
[0041] The heating steam extraction exhaust volume model and the heating steam extraction power model are obtained through the typical thermal power mechanism model, and the initial heating steam extraction exhaust volume model and the initial heating steam extraction power model are trained through the transfer learning algorithm.
[0042] Embodiment 3 Based on the same inventive concept, this embodiment provides a computer-readable storage medium on which a computer program is stored. The computer program is executed by a processor to implement any of the above methods for determining the range of power generation capacity of a thermal power unit due to steam extraction for heating.
[0043] It will be appreciated by those skilled in the art that embodiments of the present invention may be provided as methods, systems, or computer program products. Therefore, the present invention may take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Furthermore, the present invention may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.
[0044] The present invention is described with reference to flowcharts and / or block diagrams of methods, devices (systems), and computer program products according to embodiments of the present invention. It should be understood that each process and / or block in the flowchart and / or block diagram, as well as the combination of processes and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.
[0045] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.
[0046] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.
[0047] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention rather than to limit them. Although the present invention has been described in detail with reference to the above embodiments, ordinary technicians in the relevant field should understand that the specific implementation of the present invention can still be modified or replaced by equivalents, and any modification or equivalent replacement that does not deviate from the spirit and scope of the present invention should be included in the protection scope of the claims of the present invention. The above content is only a specific implementation of the present invention, but the protection scope of the present invention is not limited thereto. Any technician familiar with the technical field can easily think of changes or replacements within the technical scope disclosed by the present invention, which should be included in the protection scope of the present invention. Therefore, the protection scope of the present invention shall be based on the protection scope of the claims.
Claims
1. A method for determining the range of power generation capacity of a thermal power unit due to extraction of heat supply steam, characterized in that: The following steps are involved: Obtain the maximum main steam flow, minimum main steam flow, minimum exhaust volume and heating steam extraction volume of the thermal power unit; The minimum exhaust volume is input into the exhaust volume model of heating steam extraction to generate the minimum main steam flow rate under heating steam extraction; According to the minimum main steam flow rate under the heating extraction steam, combined with the maximum main steam flow rate and the minimum main steam flow rate of the thermal power unit, the upper boundary and the lower boundary of the main steam under the heating extraction steam are obtained; The upper boundary and the lower boundary of the main steam under the heating steam extraction are input into the heating steam extraction power model to obtain the power generation capacity range of the thermal power unit under the heating steam extraction.
2. The method for determining the range of power generation capacity of thermal power units due to extraction of heat supply steam as claimed in claim 1, characterized in that: The heating steam extraction exhaust volume model and the heating steam extraction power model obtain the initial heating steam extraction exhaust volume model and the initial heating steam extraction power model through a typical thermal power mechanism model, and use the main steam flow, heating steam extraction volume, back pressure and exhaust volume as input variables. The initial heating steam extraction exhaust volume model and the initial heating steam extraction power model are trained through a transfer learning algorithm until the error between the calculated values of the thermodynamic parameters of the high-pressure cylinder, the medium-pressure cylinder and the low-pressure cylinder and the actual values of the heat balance diagram is less than a preset value, or the number of iterations is greater than a preset value.
3. The method for determining the range of power generation capacity of thermal power units due to extraction of heat supply steam as claimed in claim 2, characterized in that: The typical thermal power mechanism model physically derives and models the thermal power plant through thermodynamic mechanism formulas; conventional thermodynamic variables and power of the thermal power plant are used as output variables, and the conventional thermodynamic variables are consistent with the types of variables in the heat balance diagram.
4. The method for determining the range of power generation capacity of thermal power units due to extraction of heat supply steam as claimed in claim 2, characterized in that: The transfer learning algorithm includes a source domain and a target domain. The initial heating steam extraction exhaust volume model or the initial heating steam extraction power model is input into the source domain, and the target domain is a target thermal power plant.
5. The method for determining the range of power generation capacity of thermal power units due to extraction of heat supply steam as claimed in claim 4, characterized in that: The source domain is trained by three convolutional layers, the target domain is trained by a fully connected layer, and the three convolutional layers are concatenated with the fully connected layer to obtain a transfer learning algorithm model.
6. The method for determining the range of power generation capacity of thermal power units due to extraction steam for heating as claimed in claim 5, characterized in that: The fitted value of the transfer learning algorithm model is compared with the true value and characterized by the average absolute error MAE, the root mean square error RMSE and the regression coefficient COEFF.
7. The method for determining the range of power generation capacity of a thermal power unit due to extraction steam for heating according to any one of claims 1 to 6, characterized in that: The exhaust volume is obtained through the final stage extraction pressure; the relationship between the main steam flow and the exhaust volume is obtained through the fitting formula of the final stage extraction pressure and the exhaust volume, thereby obtaining a heating extraction exhaust volume model.
8. The method for determining the range of power generation capacity of thermal power units due to extraction steam for heating as claimed in claim 7, characterized in that: The method for obtaining the upper and lower boundaries of the main steam under heating extraction steam is: Combined with the heating steam extraction exhaust volume model, under different heating steam extraction volumes, the lower boundary of the main steam flow rate is calculated based on the minimum main steam flow rate and the minimum exhaust volume set by the unit; the maximum main steam flow rate set by the unit is used as the upper boundary of the main steam flow rate.
9. A system for determining the range of power generation capacity of thermal power units due to extraction of heat supply steam, characterized in that: include: A parameter acquisition module is used to obtain the maximum main steam flow rate, the minimum main steam flow rate and the minimum exhaust volume of the thermal power unit; A heating steam extraction exhaust volume module is used to input the minimum exhaust volume into a heating steam extraction exhaust volume model to generate a minimum main steam flow rate under heating steam extraction; A main steam flow range acquisition module is used to obtain the upper and lower boundaries of the main steam flow under the heating extraction steam according to the minimum main steam flow under the heating extraction steam and the maximum and minimum main steam flow of the thermal power unit; The power generation capacity range acquisition module is used to input the upper boundary and lower boundary of the main steam under the heating extraction steam into the heating extraction steam power model to obtain the power generation capacity range of the thermal power unit under the heating extraction steam.
10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program, and the computer program is executed by a processor to implement the method for determining the range of power generation capacity of a thermal power unit due to steam extraction for heating as described in any one of claims 1 to 8.
