Steam generator feed water flow acquisition method and device, electronic equipment and medium

Abstract

The application discloses a steam generator feed water flow acquisition method and device, electronic equipment and medium. The method acquires a fluid mechanics simulation model of a steam generator feed water ring. The fluid mechanics simulation model is used for simulating fluid movement in the steam generator feed water ring. The fluid mechanics simulation model is used for respectively performing transient numerical calculation on the temperature in the feed water ring under multiple different low feed water flow conditions, and obtaining transient temperature distribution in the feed water ring under each low feed water flow condition. Based on the transient temperature distribution in the feed water ring under each low feed water flow condition, a temperature time series data set is constructed. An initial recurrent neural network model is trained through the temperature time series data set, and a target recurrent neural network model is obtained. The target recurrent neural network model is used for predicting the feed water flow of the steam generator under the low feed water flow condition, and the accuracy of the steam generator feed water flow acquisition under the low feed water flow condition can be improved.

Description

Technical Field

[0001] This application relates to the field of feedwater flow rate acquisition technology for steam generators, and in particular to a method, apparatus, electronic device and medium for acquiring feedwater flow rate of a steam generator. Background Technology

[0002] In pressurized water reactor nuclear power plants, the steam generator is the core equipment connecting the primary and secondary loops. It not only transfers heat from the primary coolant to the secondary water to generate wet saturated steam for power generation, but it is also a key component of the pressure boundary of the reactor's primary coolant loop.

[0003] The feedwater ring assembly of the steam generator is responsible for guiding the main feedwater into the secondary side. After entering the ring pipe through the connecting pipe, the feedwater is sprayed out through the upper nozzle. Under low feedwater flow conditions, the main regulating valve of the steam generator's main feedwater system is closed, and a small feedwater flow needs to be maintained through the bypass regulating valve to stabilize the secondary side water level. The feedwater flow data under low feedwater flow conditions is the core basis for determining whether thermal stratification has occurred in the feedwater ring and assessing the risk of fatigue failure of the feedwater pipeline and connecting pipe welds.

[0004] However, in related technologies, the acquisition of feedwater flow rate of steam generators relies on on-site flow measurement systems. However, due to the large range of this system, the measurement error is significant under low feedwater flow conditions, making it difficult to obtain accurate feedwater flow rate data. Summary of the Invention

[0005] The following is an overview of the subject matter described in detail herein. This overview is not intended to limit the scope of the claims.

[0006] The main objective of this disclosure is to provide a method, apparatus, electronic device, and medium for obtaining the feedwater flow rate of a steam generator, which can improve the accuracy of the feedwater flow rate of the steam generator under low feedwater flow rate conditions.

[0007] The first aspect of this application provides a method for obtaining the feedwater flow rate of a steam generator, including: A fluid dynamics simulation model of the steam generator feedwater ring is obtained, and the fluid dynamics simulation model is used to simulate the fluid motion within the steam generator feedwater ring; Using the fluid dynamics simulation model, transient numerical calculations were performed on the temperature within the feedwater ring under various low feedwater flow conditions to obtain the transient temperature distribution within the feedwater ring under each low feedwater flow condition; the feedwater flow rate under the low feedwater flow condition is less than a first threshold. Based on the transient temperature distribution within the feedwater loop under each low feedwater flow condition, a temperature time-series dataset is constructed; the data in the temperature time-series dataset is used to indicate the relationship between the temperature time-series data within the steam generator feedwater loop and the feedwater flow rate. The initial recurrent neural network model is trained using the temperature time series dataset to obtain the target recurrent neural network model; the target recurrent neural network model is used to predict the feedwater flow of the steam generator under low feedwater flow conditions.

[0008] In some embodiments of this application, the hydrodynamic simulation model of the steam generator feedwater ring is constructed through the following steps: Based on the feedwater ring structure of the steam generator, a three-dimensional geometric model of the feedwater ring is constructed. The three-dimensional geometric model is meshed using an unstructured mesh generation method, and a triangular prism boundary layer mesh is constructed in the water supply ring wall region represented by the three-dimensional geometric model to obtain the mesh model; The fluid dynamics simulation model is constructed based on the three-dimensional geometric model and the mesh model.

[0009] In some embodiments of this application, constructing a three-dimensional geometric model of the feedwater ring based on the feedwater ring structure of the steam generator includes: The water supply pipe in the three-dimensional geometric model is defined as the velocity inlet boundary condition; the velocity inlet boundary condition is used to indicate the inflow velocity of the water supply. The nozzle in the three-dimensional geometric model is defined as the pressure outlet boundary condition; the pressure outlet boundary condition is used to indicate the outflow pressure of the fluid in the water supply ring. The walls in the three-dimensional geometric model are defined as smooth, non-slip wall boundary conditions; these smooth, non-slip wall boundary conditions are used to indicate the interaction between the fluid and the solid wall in the water supply ring. The fluid dynamics simulation model is obtained based on the velocity inlet boundary conditions, the pressure outlet boundary conditions, the smooth, non-slip wall boundary conditions, and the mesh model.

[0010] In some embodiments of this application, the fluid dynamics simulation model is a turbulence model, which integrates an energy equation and a buoyancy effect model. The energy equation is used for heat transfer calculation of the fluid in the feed water ring, and the buoyancy effect model is used to simulate the fluid convection effect caused by temperature difference in the feed water ring. The fluid dynamics simulation model is used to perform transient numerical calculations on the temperature within the feedwater ring under various low feedwater flow conditions, obtaining the transient temperature distribution within the feedwater ring under each low feedwater flow condition, including: The resistance coefficient of the nozzle is determined based on the geometry of the nozzle of the water supply ring. For any low feedwater flow rate condition, the energy equation and buoyancy effect model are coupled and solved based on the physical property parameters of the fluid in the feedwater ring, the temperature boundary conditions, and the resistance coefficient of the nozzle in the feedwater ring to obtain the transient temperature distribution in the feedwater ring under the low feedwater flow rate condition; the physical property parameters are parameters characterizing the thermophysical properties of the fluid, and the temperature boundary conditions are used to characterize the temperature difference in the feedwater ring.

[0011] In some embodiments of this application, the geometry includes the thickness of the nozzle, the hydraulic diameter of the nozzle, and the flow area of ​​the plurality of nozzles; Determining the resistance coefficient of the nozzle based on the geometry of the nozzle of the water supply ring includes: The ratio of the flow area of ​​the multiple nozzles to the area of ​​the circumferential outlet in the fluid simulation mechanical model is determined as the first value; The product of the friction coefficient of the nozzle and the thickness of the nozzle is determined as the second value; The ratio of the second value to the hydraulic diameter of the nozzle is determined as the third value; The resistance coefficient of the water supply ring nozzle is determined based on the first value and the third value.

[0012] In some embodiments of this application, constructing a temperature time-series dataset based on the transient temperature distribution within the feedwater loop under each low feedwater flow condition includes: From the transient temperature distribution within the water supply ring under each low water supply flow condition, extract the simulated temperature time series data corresponding to the preset temperature measurement point of the water supply ring; The temperature time series dataset is constructed based on the simulated temperature time series data corresponding to the preset temperature measurement points.

[0013] In some embodiments of this application, after training the initial recurrent neural network model using the temperature time-series dataset to obtain the target recurrent neural network model, the method further includes: When the flow measurement system of the steam generator detects that the feed water flow rate is lower than the first threshold, the measured temperature time series data of the steam generator at the preset temperature measurement point is obtained. The measured temperature time series data is input into the target recurrent neural network model, and the target recurrent neural network model outputs the predicted value of the feedwater flow rate of the steam generator.

[0014] In some embodiments of this application, after inputting the measured temperature time-series data into the target recurrent neural network model and outputting the predicted feedwater flow rate of the steam generator through the target recurrent neural network model, the method further includes: When the predicted water flow rate reaches the second threshold, the temperature data of the steam generator at a preset temperature measurement point is obtained; the second threshold is less than the first threshold. Thermal stratification is determined based on the temperature data from the preset temperature measurement points, and a determination result is obtained; the determination result is used to indicate whether thermal stratification occurs in the feedwater ring of the steam generator.

[0015] In some embodiments of this application, the number of preset temperature measurement points is multiple; The thermal stratification determination based on the temperature data from the preset temperature measurement points, and the resulting determination, include: If the difference between the temperature data of any two preset temperature measurement points is less than the third threshold, it is determined that no thermal stratification has occurred in the feed water ring of the steam generator. If the difference between the temperature data of any two preset temperature measurement points is greater than or equal to the third threshold, it is determined that thermal stratification has occurred in the feedwater ring of the steam generator.

[0016] To achieve the above objective, a second aspect of the present invention provides a feedwater flow rate acquisition device for a steam generator, the device comprising: The model acquisition module is used to acquire the fluid dynamics simulation model of the steam generator feedwater ring, which is used to simulate the fluid motion within the steam generator feedwater ring. The fluid simulation module is used to perform transient numerical calculations on the temperature in the feedwater ring under various low feedwater flow conditions using the fluid dynamics simulation model, and to obtain the transient temperature distribution in the feedwater ring under each low feedwater flow condition; the feedwater flow rate under the low feedwater flow condition is less than a first threshold. The data construction module is used to construct a temperature time series dataset based on the transient temperature distribution in the feedwater loop under each low feedwater flow condition; the data in the temperature time series dataset is used to indicate the relationship between the temperature time series data in the steam generator feedwater loop and the feedwater flow rate. The model training module is used to train the initial recurrent neural network model using the temperature time series dataset to obtain the target recurrent neural network model; the target recurrent neural network model is used to predict the feedwater flow of the steam generator under low feedwater flow conditions.

[0017] To achieve the above objectives, a third aspect of the present invention provides an electronic device, comprising: at least one control processor and a memory for communicatively connecting to the at least one control processor; the memory stores instructions executable by the at least one control processor, the instructions being executed by the at least one control processor to enable the at least one control processor to perform the above-described method for obtaining feedwater flow rate of a steam generator.

[0018] To achieve the above objectives, a fourth aspect of the present invention provides a computer-readable storage medium storing computer-executable instructions for causing a computer to execute the above-described method for obtaining feedwater flow rate of a steam generator.

[0019] To achieve the above objectives, a fifth aspect of the present invention provides a computer program product in which instructions, when executed by a processor of an electronic device, cause the electronic device to perform the above-described method for obtaining the feedwater flow rate of a steam generator.

[0020] This application provides a method for obtaining feedwater flow rate of a steam generator. The method involves acquiring a fluid dynamics simulation model of the steam generator's feedwater loop. Using this model, transient numerical calculations are performed on the temperature within the feedwater loop under various low feedwater flow rate conditions to obtain the transient temperature distribution under each condition. Based on this transient temperature distribution, a temperature time-series dataset is constructed. The initial recurrent neural network (RNN) model is trained using this dataset to obtain a target RNN model. This target RNN model learns the relationship between temperature time-series data and feedwater flow rate, thereby predicting the feedwater flow rate of the steam generator under low feedwater flow rate conditions. Therefore, by using the target RNN model, easily measurable temperature data can be used to infer the feedwater flow rate, which is difficult to measure directly and accurately under low flow rate conditions, thus improving the prediction accuracy of the steam generator's feedwater flow rate under low flow rate conditions.

[0021] It is understood that the beneficial effects of the second to fifth aspects compared with the related technologies are the same as the beneficial effects of the first aspect compared with the related technologies. Please refer to the relevant description in the first aspect above, which will not be repeated here. Attached Figure Description

[0022] The above and / or additional aspects and advantages of this application will become apparent and readily understood from the description of the embodiments taken in conjunction with the following drawings, in which: Figure 1 This is a schematic flowchart of a method for obtaining the feedwater flow rate of a steam generator according to an embodiment of this application; Figure 2 This is a schematic diagram of a three-dimensional geometric model of a steam generator feedwater ring provided in an embodiment of this application; Figure 3 This is a schematic diagram of the structure of a steam generator feedwater flow acquisition device provided in an embodiment of this application; Figure 4This is a schematic diagram of the hardware structure of the electronic device provided in the embodiments of this application. Detailed Implementation

[0023] The features and exemplary embodiments of various aspects of this application will be described in detail below. To make the objectives, technical solutions, and advantages of this application clearer, the application will be further described in detail below with reference to the accompanying drawings and specific embodiments. It should be understood that the specific embodiments described herein are only intended to explain this application and not to limit it. For those skilled in the art, this application can be implemented without some of these specific details. The following description of the embodiments is merely to provide a better understanding of this application by illustrating examples.

[0024] It should be noted that, in this document, relational terms such as "first" and "second" are used merely to distinguish one entity or operation from another, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Furthermore, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Without further limitations, an element defined by the phrase "comprising..." does not exclude the presence of additional identical elements in the process, method, article, or apparatus that includes said element.

[0025] In all specific embodiments of this application, when processing data related to user identity or characteristics, such as user information, user behavior data, user historical data, and user location information, user permission or consent is obtained first. Furthermore, the collection, use, and processing of this data comply with relevant laws, regulations, and standards. Additionally, when embodiments of this application require access to sensitive personal information, separate permission or consent from the user is obtained through pop-ups or redirects to confirmation pages. Only after obtaining the user's separate permission or consent is the necessary user-related data required for the proper functioning of these embodiments obtained.

[0026] In pressurized water reactor nuclear power plants, the function of the steam generator is to transfer heat from the primary coolant to the secondary coolant, thereby producing wet saturated steam to power the turbine. Simultaneously, the steam generator is also a crucial component of the reactor's primary coolant pressure boundary. The feedwater ring assembly of the Hualong One unit's steam generator (HL-T67) guides the main feedwater into the secondary side of the steam generator. After passing through the feedwater inlet pipe, the feedwater enters the feedwater ring pipe and is ejected through the nozzles at the top.

[0027] Under low-power and hot shutdown conditions, the main regulating valve on the main feedwater line is closed. A small feedwater flow rate is maintained by adjusting the opening of the bypass regulating valve on the main feedwater line to stabilize the secondary water level of the steam generator. Low-flow, low-temperature feedwater slowly enters the horizontal sections of the main feedwater line and feedwater connectors. Due to gravity exceeding inertia, the low-temperature, high-density water flows at the bottom of the high-temperature, low-density water. When the two fluids at different temperatures cannot mix effectively, an uneven temperature distribution occurs across the cross-section of the fluid in the horizontal pipe. This thermal stratification of the fluid in the feedwater pipe causes uneven temperature distribution on the pipe wall, resulting in overall bending stress and localized stress on the pipe cross-section, as well as unexpected displacement and support loads on the piping system. This alternating uneven temperature distribution increases the risk of fatigue failure of the welds in the feedwater line and feedwater connectors.

[0028] The steam generator feedwater flow measurement system has a large measurement range, and the measurement results at low flow rates have significant errors. This makes it impossible to accurately trigger the thermal stratification judgment process based on the on-site flow measurement data, thus making it impossible to determine whether thermal stratification has occurred in the feedwater ring, and consequently, impossible to accurately assess the risk of weld fatigue failure.

[0029] To address the problems of the prior art, this application provides a method, apparatus, electronic device, and medium for obtaining the feedwater flow rate of a steam generator. The method for obtaining the feedwater flow rate of a steam generator provided in this application will be described first.

[0030] Figure 1 A schematic flowchart illustrating a method for obtaining the feedwater flow rate of a steam generator according to an embodiment of this application is shown. Figure 1 As shown in the embodiment of this application, the method for obtaining the feedwater flow rate of a steam generator includes the following steps 101-104, wherein: Step 101: Obtain the fluid dynamics simulation model of the steam generator feedwater ring. The fluid dynamics simulation model is used to simulate the fluid motion within the steam generator feedwater ring.

[0031] In this step, a fluid dynamics simulation model is used to simulate the fluid motion within the feedwater ring of the steam generator. The fluid dynamics simulation model can be built based on the principles of computational fluid dynamics (CFD) to virtually reproduce the physical state within the feedwater ring under different operating conditions in a computer.

[0032] In some implementations, a geometric model of the feedwater ring can be constructed using 3D modeling software based on the actual structural parameters of the steam generator feedwater ring, such as its inner diameter, outer diameter, wall thickness, number of inlets, inlet location, and outlet distribution density. Subsequently, the geometric model is meshed, and the feedwater ring flow channel region is discretized using either structured or unstructured meshes to obtain a mesh model, ensuring computational accuracy. Then, based on fundamental fluid dynamics equations, such as the energy equation and drag equation, combined with fluid properties such as density, specific heat capacity, thermal conductivity, and dynamic viscosity, and setting simulation boundary conditions (e.g., using the feedwater pipe as a velocity inlet boundary condition), a fluid dynamics simulation model is constructed. In some implementations, a turbulence model can be used as the fluid dynamics simulation model, i.e., fundamental fluid dynamics equations are added to the turbulence model.

[0033] The above-mentioned fluid dynamics simulation model is solved using computational fluid dynamics (CFD) simulation software based on the fluid's physical properties and simulation boundary conditions to accurately simulate the fluid flow state within the feedwater ring and output parameters such as velocity, pressure, and temperature at any spatial location within the feedwater ring under different feedwater flow conditions.

[0034] Step 102: Using the fluid dynamics simulation model, transient numerical calculations are performed on the temperature within the feedwater ring under various low feedwater flow conditions to obtain the transient temperature distribution within the feedwater ring under each low feedwater flow condition; the feedwater flow rate under the low feedwater flow condition is less than a first threshold.

[0035] In this step, the first threshold can be set according to the actual situation, and no specific limitation is made here. In some embodiments, the first threshold can be set to five percent of the feedwater flow rate when the steam generator is operating normally.

[0036] Furthermore, by setting various low feedwater flow rates, different feedwater temperatures, and time steps, the fluid dynamics simulation model can be used to perform thermal stratification fluid dynamics calculations of the feedwater loop under different low feedwater flow conditions, so as to obtain the temperature distribution within the feedwater loop under different conditions and at different times.

[0037] The low feedwater flow rate setting can cover the entire low feedwater flow rate range. For example, multiple different flow points can be uniformly selected from the minimum stable feedwater flow rate to the first threshold, and the flow interval can be determined according to the required calculation accuracy. The feedwater temperature can be set according to actual conditions to cover the actual feedwater temperature used. The time step can be determined based on the flow characteristics of the fluid in the feedwater loop to ensure that changes in the fluid flow state within each time step can be accurately captured.

[0038] Furthermore, during the process of performing hydrodynamic calculations of feedwater loop thermal stratification under different low feedwater flow conditions using a hydrodynamic simulation model, temperature data within the feedwater loop can be recorded at set time steps.

[0039] After completing the transient numerical calculations for all low feedwater flow conditions, the transient temperature data of all preset monitoring points in the feedwater loop under each condition are obtained, and then integrated to form the transient temperature distribution corresponding to each condition.

[0040] Step 103: Based on the transient temperature distribution in the feedwater loop under each low feedwater flow condition, construct a temperature time series dataset; the data in the temperature time series dataset is used to indicate the relationship between the temperature time series data in the steam generator feedwater loop and the feedwater flow rate.

[0041] In this step, the time sequence of temperature values ​​corresponding to preset temperature measurement points in the feedwater loop is extracted from the transient temperature distribution of each operating condition. These temperature time-series data are used as input features, and the corresponding feedwater flow rates are used as labels (outputs). These are paired to form a large number of training samples, which are finally aggregated into the temperature time-series dataset.

[0042] The preset temperature measurement points of the water supply ring can be set according to the actual situation, and no specific limitation is made here. In some embodiments, the four symmetrical points at the water supply ring connection nozzle can be used as preset temperature measurement points.

[0043] It should be noted that since the fluid dynamics model is constructed based on the simulation of the feedwater ring structure, the fluid dynamics model has virtual temperature measurement points corresponding to the preset temperature measurement points of the feedwater ring. The temperature time series dataset includes the temperature time series data of the virtual temperature measurement points and their corresponding feedwater flow rates.

[0044] Step 104: Train the initial recurrent neural network model using the temperature time series dataset to obtain the target recurrent neural network model; the target recurrent neural network model is used to predict the feedwater flow rate of the steam generator under low feedwater flow conditions.

[0045] In this step, the initial recurrent neural network model can adopt neural network structures with time-series data processing capabilities, such as Long Short-Term Memory (LSTM) networks and Gated Recurrent Units (GRUs), without any specific limitations.

[0046] Furthermore, the temperature time-series dataset can be divided into a training set and a test set according to a preset ratio, such as 8:2; alternatively, the data from one operating condition in the temperature time-series dataset (i.e., the temperature time-series data of the simulated feedwater loop temperature measurement point under a certain feedwater flow rate, feedwater temperature, and time step) can be used as the test set, while the data from other operating conditions can be used as the training set. The training set is used for iterative updates of the model parameters, and the test set is used to evaluate the final predictive performance of the model.

[0047] Furthermore, the data from the training set is input into the initial recurrent neural network model, and traffic prediction values ​​are obtained through forward propagation. The error between the predicted values ​​and the true labels is calculated using a loss function. The weight parameters of the model are updated using the backpropagation algorithm and optimizer. This process is repeated until the model converges. Finally, the model that meets the preset conditions on the validation set is used as the target recurrent neural network model.

[0048] The loss function, model convergence conditions, and preset conditions can all be set according to the actual situation, and no specific restrictions are imposed here.

[0049] In some implementations, the loss function can be the root mean square error, and the convergence condition and preset condition can be set to the error between the predicted value and the true label being less than 1.0 × 10⁻⁶. -3 .

[0050] In this embodiment, a fluid dynamics simulation model of the steam generator feedwater ring is obtained. Using this model, transient numerical calculations are performed on the temperature within the feedwater ring under various low feedwater flow conditions to obtain the transient temperature distribution under each low feedwater flow condition. Based on this transient temperature distribution, a temperature time-series dataset is constructed. The initial recurrent neural network (RNN) model is trained using this dataset to obtain a target RNN model. This target RNN model learns the relationship between temperature time-series data and feedwater flow, thereby predicting the feedwater flow rate of the steam generator under low feedwater flow conditions. Thus, by using the target RNN model, easily measurable temperature data can be used to infer the feedwater flow rate, which is difficult to measure directly and accurately under low flow conditions, thereby improving the prediction accuracy of the steam generator's feedwater flow rate under low flow conditions.

[0051] In some embodiments, the fluid dynamics simulation model can be constructed through the following steps 201 to 203: Step 201: Construct a three-dimensional geometric model of the feedwater ring based on the feedwater ring structure of the steam generator; Step 202: The three-dimensional geometric model is meshed using an unstructured network partitioning method, and a triangular prism boundary layer mesh is constructed in the water supply ring wall region represented by the three-dimensional geometric model to obtain the mesh model; Step 203: Based on the three-dimensional geometric model and the mesh model, construct the fluid dynamics simulation model.

[0052] Step 203 includes: The water supply pipe in the three-dimensional geometric model is defined as the velocity inlet boundary condition; the velocity inlet boundary condition is used to indicate the inflow velocity of the water supply. The nozzle in the three-dimensional geometric model is defined as the pressure outlet boundary condition; the pressure outlet boundary condition is used to indicate the outflow pressure of the fluid in the water supply ring. The walls in the three-dimensional geometric model are defined as smooth, non-slip wall boundary conditions; these smooth, non-slip wall boundary conditions are used to indicate the interaction between the fluid and the solid wall in the water supply ring. The fluid dynamics simulation model is obtained based on the velocity inlet boundary conditions, the pressure outlet boundary conditions, the smooth, non-slip wall boundary conditions, and the mesh model.

[0053] In this embodiment, based on the actual design drawings and manufacturing parameters of the steam generator feedwater ring, a 1:1 three-dimensional geometric model of the main structure of the steam generator feedwater ring can be created using three-dimensional computer-aided design software. The modeling area can include the feedwater ring pipe, nozzles, feedwater tees, feedwater connecting pipes, and some feedwater pipelines to accurately reflect all the key structural features of the feedwater ring. For example, the three-dimensional geometric model of the feedwater ring is as follows: Figure 2 As shown.

[0054] Furthermore, in the 3D geometric model, the water supply pipe serves as the velocity inlet boundary condition (simulating water inflow), the nozzle as the pressure outlet boundary condition, and other boundaries as smooth, no-slip wall boundary conditions. The velocity inlet boundary condition precisely indicates the inflow velocity of the water supply, the pressure outlet boundary condition indicates the outflow pressure of the fluid in the water supply ring, and the smooth, no-slip wall boundary condition indicates the interaction between the fluid and the solid wall in the water supply ring, i.e., the fluid velocity at the wall is 0, and the wall roughness has no effect, ensuring the simulation of the true contact state between the fluid and the wall, and avoiding flow simulation deviations caused by inaccurate wall condition definitions.

[0055] Furthermore, a three-dimensional mesh is generated for the three-dimensional geometric model of the steam generator feedwater ring. Since there are many nozzle outlets and the calculation is transient, performing overall structured mesh generation would cause a large workload. Therefore, an unstructured mesh generation method is adopted in this embodiment to reduce the time and computational resources required in the subsequent fluid dynamics simulation model establishment process. In addition, in order to accurately analyze the physical process of fluid flow near the wall, a triangular prism boundary layer mesh is generated for the feedwater ring wall region represented by the three-dimensional geometric model.

[0056] Specifically, for the main region of the 3D geometric model, due to the complex internal structure of the feedwater ring, containing numerous curved surfaces and confined spaces, an unstructured mesh is used. This allows for flexible adaptation to the complex geometric shape and avoids the severe mesh distortion problems that structured meshes are prone to when handling such geometries, thus ensuring mesh quality. For all fluid-contacting wall regions of the feedwater ring and the nozzle section in the 3D geometric model, multi-layered triangular prism (or prismatic) boundary layer meshes are generated to better fit the wall surfaces and provide sufficient mesh resolution in the normal direction, thereby accurately capturing near-wall flow details and heat exchange processes. This ensures the subsequent construction of a high-quality temperature time-series dataset.

[0057] In some implementations, the quality of the global mesh is strictly controlled during the meshing process to ensure the computational accuracy of subsequent fluid simulations.

[0058] Specifically, the mesh can be gradually densified, and steady-state calculations can be repeated. When the change in key physical quantities (such as pressure drop and average temperature) is less than the preset tolerance (such as 1%), the current mesh density is considered sufficient and can be used for subsequent transient calculations.

[0059] Furthermore, computational fluid dynamics (CFD) simulation software is used to solve the above-mentioned three-dimensional geometric model, mesh model and boundary conditions. Through numerical iterative calculation, a fluid dynamics simulation model that can accurately simulate the fluid flow state in the feedwater ring is obtained. This fluid dynamics simulation model can output parameters such as flow velocity, pressure and temperature at any spatial location in the feedwater ring under different feedwater flow conditions.

[0060] In this embodiment, by adopting a hybrid mesh strategy that combines unstructured meshes with triangular prism boundary layer meshes, and by precisely setting boundary conditions such as velocity inlet, pressure outlet, and no-slip wall, the fluid dynamics simulation model is able to accurately capture the flow details and near-wall physical phenomena within complex geometry, thereby providing high-fidelity training data for the subsequent initial recurrent neural network model.

[0061] In some embodiments, the fluid dynamics simulation model is a turbulence model, which integrates an energy equation and a buoyancy effect model. The energy equation is used to calculate the heat transfer of the fluid in the feedwater ring, and the buoyancy effect model is used to simulate the fluid convection effect caused by the temperature difference in the feedwater ring.

[0062] Step 102 may include the following steps 301 to 302: Step 301: Determine the resistance coefficient of the nozzle based on the geometry of the nozzle of the water supply ring; Step 302: For any low feedwater flow rate condition, the energy equation and buoyancy effect model are coupled and solved according to the physical property parameters of the fluid in the feedwater ring, the temperature boundary conditions, and the resistance coefficient of the nozzle of the feedwater ring to obtain the transient temperature distribution in the feedwater ring under the low feedwater flow rate condition; the physical property parameters are parameters characterizing the thermophysical properties of the fluid, and the temperature boundary conditions are used to characterize the temperature difference in the feedwater ring.

[0063] The geometry includes the nozzle thickness, the nozzle hydraulic diameter, and the flow area of ​​multiple nozzles. Step 301 may include the following: The ratio of the flow area of ​​the multiple nozzles to the area of ​​the circumferential outlet in the fluid simulation mechanical model is determined as the first value; The product of the friction coefficient of the nozzle and the thickness of the nozzle is determined as the second value; The ratio of the second value to the hydraulic diameter of the nozzle is determined as the third value; The resistance coefficient of the water supply ring nozzle is determined based on the first value and the third value.

[0064] In this embodiment, to adapt to the large velocity and temperature gradient characteristics of the thermal stratification effect in the feedwater loop and to improve the numerical stability of the mainstream region, the SST k-ω turbulence model can be selected using computational fluid dynamics (CFD) simulation software. An energy equation is added for heat transfer calculation of high-temperature fluid and low-temperature feedwater in the feedwater loop, and a buoyancy model is added for distribution calculation of fluids with density differences at different temperatures.

[0065] Furthermore, the resistance coefficient formula for porous structures is used to calculate the resistance coefficient of the feed ring nozzle applied to the feed ring outlet. The resistance coefficient can be calculated using the following formula: ; In the formula, Indicates the drag coefficient. f This represents the coefficient of friction through the outlet orifice; h Indicates the thickness of the nozzle; D Indicates the hydraulic diameter of the nozzle orifice; Indicates the flow area through the multi-hole nozzle; This represents the area of ​​the exit point on the circumference of the model.

[0066] in, Let it be the first value. This is denoted as the second value. This is denoted as the third value.

[0067] In this embodiment, the physical properties may include parameters such as density, specific heat capacity, thermal conductivity, and dynamic viscosity.

[0068] In this embodiment, by integrating the energy equation and buoyancy effect model into the turbulence model, the natural convection phenomenon driven by temperature difference at low flow rates is accurately simulated. Simultaneously, by accurately calculating the nozzle drag coefficient, the outlet boundary conditions are made more physically realistic. These technical solutions collectively ensure the high accuracy of the simulation results, providing high-quality, high-fidelity training data for the subsequent training of the initial recurrent neural network model.

[0069] In some embodiments, step 103 may include the following: From the transient temperature distribution within the water supply ring under each low water supply flow condition, extract the simulated temperature time series data corresponding to the preset temperature measurement point of the water supply ring; The temperature time series dataset is constructed based on the simulated temperature time series data corresponding to the preset temperature measurement points.

[0070] In this embodiment, simulated temperature time-series data corresponding to preset temperature measurement points are extracted from the transient temperature distribution within the feedwater loop under various low feedwater flow conditions. The simulated temperature time-series data is the temperature-time series data of each preset temperature measurement point over the entire calculation period under that condition, and its time dimension is consistent with the time step of the transient numerical calculation to ensure the temporal integrity of the data.

[0071] Using the feedwater flow rate value corresponding to each low feedwater flow rate condition as a label, and the simulated temperature time series characteristics of all preset temperature measurement points under that condition as input data, a temperature time series dataset is constructed. Each data sample in the temperature time series dataset contains a complete set of preset temperature time series characteristics and corresponding feedwater flow rate labels. This dataset is used to clarify the mapping relationship between the temperature time series data of preset temperature measurement points and feedwater flow rate within the steam generator feedwater loop, providing a data foundation for accurately matching the actual monitoring scenario for the subsequent training of the initial recurrent neural network model.

[0072] In this embodiment, by pre-setting temperature measurement points in the simulation to extract data, not only is the data dimensionality greatly reduced and the complexity of processing massive three-dimensional temperature fields avoided, but a direct correspondence between the simulation environment and the actual application scenario is also established, so that the trained model can be seamlessly applied to real sensor data, greatly enhancing its engineering practicality.

[0073] In some embodiments, the accuracy of judging the thermal stratification effect can be improved by using the feedwater flow rate predicted by the embodiments of this application. Specifically, after step 104, the feedwater flow rate acquisition method for the steam generator provided in this embodiment may further include the following steps 401 to 402: Step 401: When the flow measurement system of the steam generator detects that the feed water flow rate is lower than the first threshold, the measured temperature time series data of the steam generator at the preset temperature measurement point is obtained. Step 402: Input the measured temperature time series data into the target recurrent neural network model, and output the predicted value of the feedwater flow rate of the steam generator through the target recurrent neural network model.

[0074] In this embodiment, during the actual operation of the steam generator, the original flow measurement system of the steam generator continuously monitors the feedwater flow rate. When the system detects that the feedwater flow rate is lower than a preset first threshold, the feedwater flow rate acquisition method of the steam generator provided in this application embodiment is activated.

[0075] Furthermore, the measured temperature time series data is collected from physical temperature sensors, such as thermocouples or resistance temperature detectors, that are pre-installed at multiple preset temperature measurement points on the feedwater ring. The physical locations of these temperature measurement points are completely consistent with the virtual temperature measurement point locations in the fluid dynamics simulation model in step S103. The measured temperature time series data is input into the target recurrent neural network model in real time, and the target recurrent neural network model outputs the predicted feedwater flow rate of the steam generator.

[0076] In other implementations, during actual operation, the measured temperature time series data and corresponding calibration flow data (such as the actual flow value obtained through a high-precision calibration device) of preset temperature measurement points can be collected periodically and added to the temperature time series dataset to retrain the target recurrent neural network model, thereby further improving the prediction accuracy and stability of the model in actual application scenarios.

[0077] In this embodiment, the present invention obtains high-fidelity data through CFD simulation and uses a recurrent neural network model to explore the deep correlation between temperature time series and flow rate, fundamentally avoiding the problem of weak physical signals of traditional instruments at low flow rates, and realizing high-precision acquisition under low water supply flow conditions.

[0078] In some embodiments, after step 402, the method for obtaining the feedwater flow rate of the steam generator provided in this embodiment may further include the following steps 501 to 502: Step 501: If the predicted water flow rate reaches the second threshold, acquire the temperature data of the steam generator at a preset temperature measurement point; the second threshold is less than the first threshold. Step 502: Perform thermal stratification determination based on the temperature data of the preset temperature measurement point to obtain the determination result; the determination result is used to indicate whether thermal stratification occurs in the feed water ring of the steam generator.

[0079] The number of preset temperature measurement points is multiple, and step 502 may include the following: If the difference between the temperature data of any two preset temperature measurement points is less than the third threshold, it is determined that no thermal stratification has occurred in the feed water ring of the steam generator. If the difference between the temperature data of any two preset temperature measurement points is greater than or equal to the third threshold, it is determined that thermal stratification has occurred in the feedwater ring of the steam generator.

[0080] In this embodiment, since the thermal stratification phenomenon and the resulting thermal stress risk are more significant and dangerous when the flow rate is extremely low, a second threshold is set. The second threshold is used to trigger the thermal stratification determination process. The second threshold can be set according to the actual situation and is not specifically limited here, but the second threshold must be less than the first threshold.

[0081] In this embodiment, the predicted water flow rate obtained in step 402 is compared with the second threshold to determine whether the predicted value reaches (i.e., is less than or equal to) the second threshold. If the second threshold is not reached, the current flow monitoring status is maintained and no thermal stratification determination is required. If the second threshold is reached, the thermal stratification determination process is initiated.

[0082] After the thermal stratification determination process is initiated, the temperature data of the steam generator at multiple preset temperature measurement points are acquired in real time, and the temperature difference between any two preset temperature measurement points is calculated. If the temperature difference between any two preset temperature measurement points is greater than or equal to the third threshold, it is determined that thermal stratification has occurred in the feedwater ring of the steam generator; if the temperature difference between any two preset temperature measurement points is less than the third threshold, it is determined that thermal stratification has occurred in the feedwater ring of the steam generator.

[0083] The third threshold is the criterion for judging thermal stratification. When the temperature difference inside the steam generator is greater than the third threshold, it is determined that thermal stratification has occurred inside the steam generator. The third threshold can be set according to the actual situation and is not specifically limited here.

[0084] In some embodiments, the third threshold may be set to 30°.

[0085] Since thermal stratification is triggered when the water flow rate reaches the second threshold, in this embodiment, by improving the measurement accuracy of the water flow rate under low operating conditions, the triggering accuracy of thermal stratification is improved, thereby improving the determination accuracy of thermal stratification.

[0086] The following describes the implementation process of the method for obtaining the feedwater flow rate of the steam generator provided in the embodiments of this application: Step 1: Perform a 1:1 three-dimensional geometric model of the main structure of the steam generator feedwater ring. The three-dimensional geometric model of the steam generator feedwater ring is as follows: Figure 2As shown, the modeling area includes a water supply ring pipe, nozzles, water supply tees, water supply connectors, and part of the water supply pipeline; the water supply pipeline serves as the velocity inlet boundary condition of the fluid dynamics simulation model (simulating water inflow), the nozzle serves as the opening pressure outlet boundary condition of the fluid dynamics simulation model (simulating fluid outflow), and other boundaries serve as smooth, non-slip wall boundary conditions in the fluid dynamics simulation model (simulating solid walls).

[0087] Step 2: Perform 3D mesh generation on the geometric model of the steam generator feedwater ring. Due to the large number of nozzle outlets and the transient nature of the calculation, performing overall structured mesh generation would result in a significant workload. Therefore, an unstructured mesh generation method is adopted to reduce the time and subsequent computational resources required during model building. To accurately analyze the physical processes of the flow near the wall (the outer boundary of the fluid, i.e., the boundary of the solid, where the fluid domain is established in the calculation model), a triangular prism boundary layer mesh is generated on the wall (meshing is performed on all fluid domains, and the wall and nozzles are refined). At the same time, the quality of the global mesh is strictly controlled.

[0088] Step 3: To adapt to the large velocity and temperature gradients in the thermal stratification effect of the feedwater loop and to improve the numerical stability of the mainstream region, the SST turbulence model (simulating fluid motion) is adopted. An energy equation is added for heat transfer calculations of high-temperature fluids and low-temperature feedwater within the feedwater loop; Add the Buoyancy model for calculating the distribution of fluids with density differences at different temperatures; The resistance coefficient of the porous structure nozzle structure is calculated using the formula for the resistance coefficient when applied to the feed ring outlet. The resistance coefficient can be calculated using the following formula: ; In the formula, Indicates the drag coefficient. f This represents the coefficient of friction through the outlet orifice; h Indicates the thickness of the nozzle; D Indicates the hydraulic diameter of the nozzle orifice; Indicates the flow area through the multi-hole nozzle; This represents the area of ​​the exit point on the circumference of the model.

[0089] Step 4: By setting different feedwater flow rates, feedwater temperatures, and time steps, perform hydrodynamic calculations on the feedwater loop under different operating conditions with typical low feedwater flow rates. This will allow us to obtain the temperature distribution within the feedwater loop under different operating conditions and at different times, and establish a criterion for determining thermal stratification, namely, the temperature difference in the calculation domain (the temperature difference throughout the feedwater loop) must be ≥30℃.

[0090] Step 5: Extract time-series data of temperature distribution at four symmetrical points of the water supply loop pipe under different water flow rates, water temperatures, and time intervals.

[0091] Step 6: Select one operating condition data from Step 5 (time series data of feedwater loop pipe distribution under a certain feedwater flow rate and feedwater temperature) as the test set for the recurrent neural network model, and use other operating conditions as the training set (time series data of feedwater loop pipe distribution under other feedwater flow rates and feedwater temperatures) to verify the accuracy of the initial recurrent neural network model's predictions and its generalization performance under other parameters. The recurrent neural network model introduces "gating mechanisms" and "cell states" to preserve and selectively forget information in the long term, making it perform well in tasks such as time series prediction and natural language processing.

[0092] The loss function for the initial recurrent neural network model can be the root mean square error (RMSE). This is used when the error of the traffic prediction data on both the test and training sets reaches 1.0 × 10⁻⁶. -3 The magnitude refers to the time when training is considered complete and the target recurrent neural network model is obtained.

[0093] Step 8: Input the measurement data of the steam generator feedwater pipe temperature sensor into the target recurrent neural network model to obtain the low feedwater flow prediction result; Step 9: When the low feedwater flow prediction result output in Step 8 reaches the feedwater loop thermal stratification trigger flow value, combined with the feedwater loop thermal stratification judgment criteria in Step 4, it can be determined whether thermal stratification effect occurs at this feedwater flow rate. This solves the problem of large flow meter errors at low flow rates, making it impossible to accurately judge feedwater loop thermal stratification and thermal fatigue on site.

[0094] Figure 3 A structural diagram of the feedwater flow rate acquisition device for a steam generator provided in an embodiment of this application is shown. Figure 3 As shown, the feedwater flow rate acquisition device 600 for the steam generator includes: The model acquisition module 601 is used to acquire a fluid dynamics simulation model of the steam generator feedwater ring, which is used to simulate the fluid motion within the steam generator feedwater ring. The fluid simulation module 602 is used to perform transient numerical calculations on the temperature in the feedwater ring under various low feedwater flow conditions using the fluid dynamics simulation model, and to obtain the transient temperature distribution in the feedwater ring under each low feedwater flow condition; the feedwater flow rate under the low feedwater flow condition is less than a first threshold. Data construction module 603 is used to construct a temperature time series dataset based on the transient temperature distribution in the feedwater loop under each low feedwater flow condition; the data in the temperature time series dataset is used to indicate the relationship between the temperature time series data in the steam generator feedwater loop and the feedwater flow rate. The model training module 604 is used to train the initial recurrent neural network model using the temperature time series dataset to obtain the target recurrent neural network model; the target recurrent neural network model is used to predict the feedwater flow of the steam generator under low feedwater flow conditions.

[0095] In some embodiments, the hydrodynamic simulation model of the steam generator feedwater ring is constructed through the following steps: Based on the feedwater ring structure of the steam generator, a three-dimensional geometric model of the feedwater ring is constructed. The three-dimensional geometric model is meshed using an unstructured mesh generation method, and a triangular prism boundary layer mesh is constructed in the water supply ring wall region represented by the three-dimensional geometric model to obtain the mesh model; The fluid dynamics simulation model is constructed based on the three-dimensional geometric model and the mesh model.

[0096] In some implementations, constructing the fluid dynamics simulation model based on the three-dimensional geometric model and the mesh model includes: The water supply pipe in the three-dimensional geometric model is defined as the velocity inlet boundary condition; the velocity inlet boundary condition is used to indicate the inflow velocity of the water supply. The nozzle in the three-dimensional geometric model is defined as the pressure outlet boundary condition; the pressure outlet boundary condition is used to indicate the outflow pressure of the fluid in the water supply ring. The walls in the three-dimensional geometric model are defined as smooth, non-slip wall boundary conditions; these smooth, non-slip wall boundary conditions are used to indicate the interaction between the fluid and the solid wall in the water supply ring. The fluid dynamics simulation model is obtained based on the velocity inlet boundary conditions, the pressure outlet boundary conditions, the smooth, non-slip wall boundary conditions, and the mesh model.

[0097] In some embodiments, the fluid dynamics simulation model is a turbulence model, which integrates an energy equation and a buoyancy effect model. The energy equation is used to calculate the heat transfer of the fluid in the feedwater ring, and the buoyancy effect model is used to simulate the fluid convection effect caused by the temperature difference in the feedwater ring. Fluid simulation module 602 includes: A determination submodule is used to determine the resistance coefficient of the nozzle based on the geometry of the nozzle of the water supply ring; The solution submodule is used to solve the energy equation and buoyancy effect model in a coupled manner for any low feedwater flow condition, based on the physical property parameters of the fluid in the feedwater ring, the temperature boundary conditions, and the resistance coefficient of the nozzle in the feedwater ring, to obtain the transient temperature distribution in the feedwater ring under the low feedwater flow condition; the physical property parameters are parameters characterizing the thermophysical properties of the fluid, and the temperature boundary conditions are used to characterize the temperature difference in the feedwater ring.

[0098] In some embodiments, the geometry includes the thickness of the nozzle, the hydraulic diameter of the nozzle, and the flow area of ​​the plurality of nozzles; The submodules are defined, including: The first determining unit is used to determine the ratio of the flow area of ​​the plurality of nozzles to the area of ​​the circumferential outlet in the fluid simulation mechanics model as a first value. The second determining unit is used to determine the product of the friction coefficient of the nozzle and the thickness of the nozzle as a second value; The third determining unit is used to determine the ratio of the second value to the hydraulic diameter of the nozzle as a third value; The fourth determining unit is used to determine the resistance coefficient of the water supply ring nozzle based on the first value and the third value.

[0099] In some implementations, the data construction module 603 includes: The extraction submodule is used to extract simulated temperature time series data corresponding to preset temperature measurement points in the water supply ring from the transient temperature distribution in the water supply ring under each low water supply flow condition. A submodule is constructed to build the temperature time series dataset based on the simulated temperature time series data corresponding to the preset temperature measurement points.

[0100] In some embodiments, the feedwater flow rate acquisition device 600 for the steam generator further includes: The data acquisition module is used to acquire the measured temperature time series data of the steam generator at a preset temperature measurement point when the flow measurement system of the steam generator measures that the feed water flow is lower than the first threshold. The flow prediction module is used to input the measured temperature time series data into the target recurrent neural network model, and output the predicted value of the feedwater flow of the steam generator through the target recurrent neural network model.

[0101] In some embodiments, the feedwater flow rate acquisition device 600 for the steam generator further includes: The temperature acquisition module is used to acquire the temperature data of the steam generator at a preset temperature measurement point when the predicted water flow rate reaches a second threshold; the second threshold is less than the first threshold. The stratification determination module is used to determine thermal stratification based on the temperature data of the preset temperature measurement point and obtain the determination result; the determination result is used to indicate whether thermal stratification occurs in the feed water ring of the steam generator.

[0102] In some implementations, the number of preset temperature measurement points is multiple; The layering determination module includes: If the difference between the temperature data of any two preset temperature measurement points is less than the third threshold, it is determined that no thermal stratification has occurred in the feed water ring of the steam generator. If the difference between the temperature data of any two preset temperature measurement points is greater than or equal to the third threshold, it is determined that thermal stratification has occurred in the feedwater ring of the steam generator.

[0103] The steam generator feedwater flow acquisition device 600 provided in this application embodiment can realize the various processes implemented in the aforementioned steam generator feedwater flow acquisition method embodiment and achieve the same technical effect. To avoid repetition, it will not be described again here.

[0104] This application also provides an electronic device, which includes a memory and a processor. The memory stores a computer program, and the processor executes the computer program to implement the above-described method for obtaining the feedwater flow rate of the steam generator.

[0105] like Figure 4 , Figure 4 This is a schematic diagram of the hardware structure of an electronic device provided in an embodiment of this application. The electronic device includes: At least one battery; At least one memory; At least one processor; At least one program; The program is stored in memory, and the processor executes at least one program to implement the above-described method for obtaining the feedwater flow rate of a steam generator according to the present disclosure.

[0106] This electronic device can be any smart terminal, including mobile phones, tablets, personal digital assistants (PDAs), and in-vehicle computers.

[0107] The electronic devices according to embodiments of this application will now be described in detail.

[0108] The processor 1600 can be implemented using a general-purpose central processing unit (CPU), microprocessor, application-specific integrated circuit (ASIC), or one or more integrated circuits, and is used to execute relevant programs to implement the technical solutions provided in the embodiments of this disclosure. The memory 1700 can be implemented as a read-only memory (ROM), static storage device, dynamic storage device, or random access memory (RAM). The memory 1700 can store the operating system and other application programs. When the technical solutions provided in the embodiments of this specification are implemented through software or firmware, the relevant program code is stored in the memory 1700 and is called and executed by the processor 1600 to execute a method for obtaining feedwater flow rate of a steam generator according to an embodiment of this disclosure.

[0109] The input / output interface 1800 is used to implement information input and output. The communication interface 1900 is used to enable communication and interaction between this device and other devices. Communication can be achieved through wired means (such as USB, Ethernet cable, etc.) or wireless means (such as mobile network, WIFI, Bluetooth, etc.). Bus 2000 transmits information between various components of the device (e.g., processor 1600, memory 1700, input / output interface 1800, and communication interface 1900); The processor 1600, memory 1700, input / output interface 1800 and communication interface 1900 are connected to each other within the device via bus 2000.

[0110] This disclosure also provides a storage medium, which is a computer-readable storage medium storing computer-executable instructions for causing a computer to execute the above-described method for obtaining the feedwater flow rate of a steam generator.

[0111] Memory, as a non-transitory computer-readable storage medium, can be used to store non-transitory software programs and non-transitory computer-executable programs. Furthermore, memory may include high-speed random access memory, and may also include non-transitory memory, such as at least one disk storage device, flash memory device, or other non-transitory solid-state storage device. In some embodiments, memory may optionally include memory remotely located relative to the processor, and these remote memories can be connected to the processor via a network. Examples of such networks include, but are not limited to, the Internet, intranets, local area networks, mobile communication networks, and combinations thereof.

[0112] This application also provides a computer program product for implementation, wherein the instructions in the computer program product, when executed by the processor of an electronic device, cause the electronic device to implement any of the steam generator feedwater flow acquisition methods in the above embodiments.

[0113] The embodiments described in this disclosure are for the purpose of more clearly illustrating the technical solutions of this disclosure and do not constitute a limitation on the technical solutions provided by this disclosure. As those skilled in the art will know, with the evolution of technology and the emergence of new application scenarios, the technical solutions provided by this disclosure are also applicable to similar technical problems.

[0114] Those skilled in the art will understand that the technical solutions shown in the figures do not constitute a limitation on the embodiments of this disclosure, and may include more or fewer steps than shown, or combine certain steps, or different steps.

[0115] The device embodiments described above are merely illustrative. The units described as separate components may or may not be physically separate; that is, they may be located in one place or distributed across multiple network units. Some or all of the modules can be selected to achieve the purpose of this embodiment according to actual needs.

[0116] Those skilled in the art will understand that all or some of the steps in the methods disclosed above, as well as the functional modules / units in the systems and devices, can be implemented as software, firmware, hardware, or suitable combinations thereof.

[0117] The terms “first,” “second,” “third,” “fourth,” etc. (if present) in the specification and accompanying drawings of this application are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that the embodiments of this application described herein can be implemented in orders other than those illustrated or described herein. Furthermore, the terms “comprising” and “having,” and any related variations, are intended to cover a non-exclusive inclusion; for example, a process, method, system, product, or apparatus that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or apparatus.

[0118] It should be understood that in this application, "at least one (item)" means one or more, and "more than" means two or more. "And / or" is used to describe the relationship between related objects, indicating that three relationships can exist. For example, "A and / or B" can represent three cases: only A exists, only B exists, and both A and B exist simultaneously, where A and B can be singular or plural. The character " / " generally indicates that the preceding and following related objects are in an "or" relationship. "At least one (item) of the following" or similar expressions refer to any combination of these items, including any combination of single or plural items. For example, at least one (item) of a, b, or c can represent: a, b, c, "a and b", "a and c", "b and c", or "a and b and c", where a, b, and c can be single or multiple.

[0119] In the several embodiments provided in this application, it should be understood that the disclosed apparatus and methods can be implemented in other ways. For example, the apparatus embodiments described above are merely illustrative; for instance, the division of units is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be through some interfaces; the indirect coupling or communication connection between apparatuses or units may be electrical, mechanical, or other forms.

[0120] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0121] Furthermore, the functional units in the various embodiments of this application can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or as a software functional unit.

[0122] If the integrated unit is implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, or all or part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes multiple instructions to cause an electronic device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods of the various embodiments of this application. The aforementioned storage medium includes various media capable of storing programs, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0123] The above is a detailed description of the preferred embodiments of this application. However, the embodiments of this application are not limited to the above-described implementation methods. Those skilled in the art can make various equivalent modifications or substitutions without departing from the spirit of the embodiments of this application. All such equivalent modifications or substitutions are included within the scope defined by the claims of the embodiments of this application.

[0124] The embodiments of this application have been described in detail above with reference to the accompanying drawings. However, this application is not limited to the above embodiments. Within the scope of knowledge possessed by those skilled in the art, various changes can be made without departing from the spirit of this application.

Claims

1. A method for obtaining the feedwater flow rate of a steam generator, characterized in that, include: A fluid dynamics simulation model of the steam generator feedwater ring is obtained, and the fluid dynamics simulation model is used to simulate the fluid motion within the steam generator feedwater ring; Using the fluid dynamics simulation model, transient numerical calculations were performed on the temperature within the feedwater ring under various low feedwater flow conditions to obtain the transient temperature distribution within the feedwater ring under each low feedwater flow condition; the feedwater flow rate under the low feedwater flow condition is less than a first threshold. Based on the transient temperature distribution within the feedwater loop under each low feedwater flow condition, a temperature time series dataset is constructed. The data in the temperature time series dataset is used to indicate the relationship between the temperature time series data and the feedwater flow rate in the steam generator feedwater loop. The initial recurrent neural network model is trained using the temperature time series dataset to obtain the target recurrent neural network model; the target recurrent neural network model is used to predict the feedwater flow of the steam generator under low feedwater flow conditions.

2. The method for obtaining the feedwater flow rate of the steam generator according to claim 1, characterized in that, The hydrodynamic simulation model of the steam generator feedwater ring is constructed through the following steps: Based on the feedwater ring structure of the steam generator, a three-dimensional geometric model of the feedwater ring is constructed. The three-dimensional geometric model is meshed using an unstructured mesh generation method, and a triangular prism boundary layer mesh is constructed in the water supply ring wall region represented by the three-dimensional geometric model to obtain the mesh model; The fluid dynamics simulation model is constructed based on the three-dimensional geometric model and the mesh model.

3. The method for obtaining the feedwater flow rate of a steam generator according to claim 2, characterized in that, The construction of the fluid dynamics simulation model based on the three-dimensional geometric model and the mesh model includes: The water supply pipe in the three-dimensional geometric model is defined as the velocity inlet boundary condition; the velocity inlet boundary condition is used to indicate the inflow velocity of the water supply. The nozzle in the three-dimensional geometric model is defined as the pressure outlet boundary condition; the pressure outlet boundary condition is used to indicate the outflow pressure of the fluid in the water supply ring. The walls in the three-dimensional geometric model are defined as smooth, non-slip wall boundary conditions; these smooth, non-slip wall boundary conditions are used to indicate the interaction between the fluid and the solid wall in the water supply ring. The fluid dynamics simulation model is obtained based on the velocity inlet boundary conditions, the pressure outlet boundary conditions, the smooth, non-slip wall boundary conditions, and the mesh model.

4. The method for obtaining the feedwater flow rate of the steam generator according to claim 1, characterized in that, The fluid dynamics simulation model is a turbulence model, which integrates an energy equation and a buoyancy effect model. The energy equation is used to calculate the heat transfer of the fluid in the feed water ring, and the buoyancy effect model is used to simulate the fluid convection effect caused by the temperature difference in the feed water ring. The fluid dynamics simulation model is used to perform transient numerical calculations on the temperature within the feedwater ring under various low feedwater flow conditions, obtaining the transient temperature distribution within the feedwater ring under each low feedwater flow condition, including: The resistance coefficient of the nozzle is determined based on the geometry of the nozzle of the water supply ring. For any low feedwater flow rate condition, the energy equation and buoyancy effect model are coupled and solved based on the physical property parameters of the fluid in the feedwater ring, the temperature boundary conditions, and the resistance coefficient of the nozzle in the feedwater ring to obtain the transient temperature distribution in the feedwater ring under the low feedwater flow rate condition; the physical property parameters are parameters characterizing the thermophysical properties of the fluid, and the temperature boundary conditions are used to characterize the temperature difference in the feedwater ring.

5. The method for obtaining the feedwater flow rate of the steam generator according to claim 4, characterized in that, The geometry includes the thickness of the nozzle, the hydraulic diameter of the nozzle, and the flow area of ​​the plurality of nozzles; Determining the resistance coefficient of the nozzle based on the geometry of the nozzle of the water supply ring includes: The ratio of the flow area of ​​the multiple nozzles to the area of ​​the circumferential outlet in the fluid simulation mechanical model is determined as the first value; The product of the friction coefficient of the nozzle and the thickness of the nozzle is determined as the second value; The ratio of the second value to the hydraulic diameter of the nozzle is determined as the third value; The resistance coefficient of the water supply ring nozzle is determined based on the first value and the third value.

6. The method for obtaining the feedwater flow rate of a steam generator according to claim 1, characterized in that, The temperature time-series dataset is constructed based on the transient temperature distribution within the feedwater loop under each low feedwater flow condition, including: From the transient temperature distribution within the water supply ring under each low water supply flow condition, extract the simulated temperature time series data corresponding to the preset temperature measurement point of the water supply ring; The temperature time series dataset is constructed based on the simulated temperature time series data corresponding to the preset temperature measurement points.

7. The method for obtaining the feedwater flow rate of a steam generator according to claim 1, characterized in that, After training the initial recurrent neural network model using the temperature time-series dataset to obtain the target recurrent neural network model, the method further includes: When the flow measurement system of the steam generator detects that the feed water flow rate is lower than the first threshold, the measured temperature time series data of the steam generator at the preset temperature measurement point is obtained. The measured temperature time series data is input into the target recurrent neural network model, and the target recurrent neural network model outputs the predicted value of the feedwater flow rate of the steam generator.

8. The method for obtaining the feedwater flow rate of a steam generator according to claim 7, characterized in that, After inputting the measured temperature time-series data into the target recurrent neural network model and outputting the predicted feedwater flow rate of the steam generator through the target recurrent neural network model, the method further includes: If the predicted water flow rate reaches the second threshold, the temperature data of the steam generator at a preset temperature measurement point is obtained; the second threshold is less than the first threshold. Thermal stratification is determined based on the temperature data from the preset temperature measurement points, and a determination result is obtained; the determination result is used to indicate whether thermal stratification occurs in the feedwater ring of the steam generator.

9. The method for obtaining the feedwater flow rate of a steam generator according to claim 8, characterized in that, The number of preset temperature measurement points is multiple; The thermal stratification determination based on the temperature data from the preset temperature measurement points, and the resulting determination, include: If the difference between the temperature data of any two preset temperature measurement points is less than the third threshold, it is determined that no thermal stratification has occurred in the feed water ring of the steam generator. If the difference between the temperature data of any two preset temperature measurement points is greater than or equal to the third threshold, it is determined that thermal stratification has occurred in the feedwater ring of the steam generator.

10. A device for obtaining the feedwater flow rate of a steam generator, characterized in that, The device includes: The model acquisition module is used to acquire the fluid dynamics simulation model of the steam generator feedwater ring, which is used to simulate the fluid motion within the steam generator feedwater ring. The fluid simulation module is used to perform transient numerical calculations on the temperature in the feedwater ring under various low feedwater flow conditions using the fluid dynamics simulation model, and to obtain the transient temperature distribution in the feedwater ring under each low feedwater flow condition; the feedwater flow rate under the low feedwater flow condition is less than a first threshold. The data construction module is used to construct a temperature time series dataset based on the transient temperature distribution in the feedwater loop under each low feedwater flow condition; the data in the temperature time series dataset is used to indicate the relationship between the temperature time series data in the steam generator feedwater loop and the feedwater flow rate. The model training module is used to train the initial recurrent neural network model using the temperature time series dataset to obtain the target recurrent neural network model; the target recurrent neural network model is used to predict the feedwater flow of the steam generator under low feedwater flow conditions.

11. An electronic device, characterized in that, It includes at least one control processor and a memory for communicatively connecting to the at least one control processor; the memory stores instructions executable by the at least one control processor, which, when executed by the at least one control processor, enable the at least one control processor to perform the feedwater flow acquisition method for the steam generator according to any one of claims 1 to 9.

12. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer-executable instructions for causing a computer to perform the method for obtaining the feedwater flow rate of the steam generator according to any one of claims 1 to 9.

13. A computer program product, characterized in that, When the instructions in the computer program product are executed by the processor of the electronic device, the electronic device causes the electronic device to perform the method for obtaining the feedwater flow rate of the steam generator as described in any one of claims 1 to 9.

Images