Steam jet pressure oscillation dominant frequency prediction method, system, equipment and medium

Abstract

The invention discloses a steam jet pressure oscillation dominant frequency prediction method, system and device and a medium. The method comprises the steps of obtaining parameter information of steam jet pressure oscillation to be predicted; inputting the parameter information of the to-be-predicted steam jet pressure oscillation into a trained multi-scale residual attention network to obtain a first dominant frequency f1, a second dominant frequency f2, an amplitude Af1 of the first dominant frequency and an amplitude Af2 of the second dominant frequency of the to-be-predicted steam jet pressure oscillation, the method, the system, the equipment and the medium can quickly and accurately predict the steam jet pressure oscillation dominant frequency.

Description

Technical Field

[0001] The present invention belongs to the fields of energy and power engineering and machine learning, and relates to a method, system, equipment and medium for predicting the main frequency of steam jet pressure oscillation. Background Art

[0002] Steam-immersed jets are widely used in nuclear energy engineering, such as the steam jet condensation process in the safety relief system of nuclear reactors. This process is accompanied by complex phase interface fluctuations and flow field pressure oscillations, which may cause equipment resonance and affect system safety and reliability.

[0003] The phenomenon of steam jet condensation in direct contact with supercooled water is widely used in the application of power systems and equipment such as energy and chemical industries. The steam jet process has efficient heat transfer performance, but it is also often accompanied by condensation pressure oscillation, which may generate noise and vibration, affecting system safety and reliability.

[0004] In the field of nuclear power generation, the passive core emergency cooling system is a key component in the design of advanced nuclear reactors. For example, the core emergency cooling and pressure relief system of the pressurized water reactor and the vacuum vessel pressure suppression system of the thermonuclear experimental reactor both involve the steam submerged jet condensation process. In the field of heating and waste heat recovery in thermal power generation systems, the use of equipment such as adjustable steam ejectors and low-temperature exhaust steam recovery devices can achieve thermoelectric decoupling, improved heating capacity and recovery of low-grade waste heat through the direct contact condensation process of steam and supercooled water. The process of steam jet condensation is accompanied by complex phase interface fluctuations and flow field pressure oscillations, which may cause equipment resonance and affect system safety and reliability. Therefore, accurate prediction of the main frequency of steam jet pressure oscillation is crucial to equipment design and safe operation.

[0005] At present, the main frequency and amplitude of pressure oscillation in the steam jet condensation process are mainly obtained by experimental measurement and numerical simulation calculation. The cost of experimental measurement is high, and it is difficult to obtain internal flow field data. CFD simulation calculation can obtain more comprehensive flow field data and pressure information. In order to achieve accurate simulation, the calculation grid model is large, the time step is small, the calculation cycle of large-scale parametric research is long, and the pressure oscillation characteristics are difficult to obtain in real time.

[0006] Therefore, it is urgent to develop a method that can quickly and accurately predict the main frequency of steam jet pressure oscillation to support the design optimization and safety assessment of related systems. Summary of the invention

[0007] The purpose of the present invention is to overcome the shortcomings of the above-mentioned prior art and provide a method, system, device and medium for predicting the main frequency of steam jet pressure oscillation. The method, system, device and medium can quickly and accurately predict the main frequency of steam jet pressure oscillation.

[0008] To achieve the above object, the present invention discloses a method for predicting the main frequency of steam jet pressure oscillation, comprising:

[0009] Obtaining parameter information of the steam jet pressure oscillation to be predicted;

[0010] The parameter information of the steam jet pressure oscillation to be predicted is input into the trained multi-scale residual attention network to obtain the first main frequency f1, the second main frequency f2, and the amplitude A of the first main frequency of the steam jet pressure oscillation to be predicted. f 1 and the amplitude of the second main frequency A f2 .

[0011] Furthermore, the parameter information of the steam jet pressure oscillation to be predicted includes but is not limited to: Reynolds number Re, Jacobs number Ja, Weber number We, jet penetration dimensionless length L s / D, dimensionless length of jet expansion D s / D and pressure ratio P in / P out .

[0012] Furthermore, before inputting the parameter information of the steam jet pressure oscillation to be predicted into the trained multi-scale residual attention network, the method further includes:

[0013] Perform parameter simulation based on the CFD model and build a sample set based on the simulation results;

[0014] Construct a multi-scale residual attention network;

[0015] The multi-scale residual attention network is trained using the sample set to obtain a trained multi-scale residual attention network.

[0016] Furthermore, the loss function in the process of training the multi-scale residual attention network using the sample set is:

[0017] Loss=MSE+λ1*Physics_constraint+λ2*L2_regularization

[0018] Furthermore, a Bayesian optimization algorithm is used to train the multi-scale residual attention network using the sample set.

[0019] The present invention discloses a steam jet pressure oscillation main frequency prediction system, comprising:

[0020] An acquisition module, used for acquiring parameter information of the steam jet pressure oscillation to be predicted;

[0021] The prediction module is used to input the parameter information of the steam jet pressure oscillation to be predicted into the trained multi-scale residual attention network to obtain the first main frequency f1, the second main frequency f2, the amplitude A of the first main frequency of the steam jet pressure oscillation to be predicted. f 1 and the amplitude of the second main frequency A f2 .

[0022] Furthermore, the parameter information of the steam jet pressure oscillation to be predicted includes but is not limited to: Reynolds number Re, Jacobs number Ja, Weber number We, jet penetration dimensionless length L s / D, dimensionless length of jet expansion D s / D and pressure ratio P in / P out .

[0023] Further, including:

[0024] The simulation module is used to perform parameter simulation based on the CFD model and build a sample set according to the simulation results;

[0025] Building module for constructing multi-scale residual attention networks;

[0026] A training module is used to train the multi-scale residual attention network using the sample set to obtain a trained multi-scale residual attention network.

[0027] The present invention discloses a computer device, comprising a memory, a processor and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, the steps of the method for predicting the main frequency of steam jet pressure oscillation are implemented.

[0028] The present invention discloses a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the steps of the method for predicting the main frequency of steam jet pressure oscillation are realized.

[0029] The present invention has the following beneficial effects:

[0030] The method, system, device and medium for predicting the main frequency of steam jet pressure oscillation of the present invention are as follows: during specific operation, the parameter information of the steam jet pressure oscillation to be predicted is input into the trained multi-scale residual attention network, and the first main frequency f1, the second main frequency f2, the amplitude A of the first main frequency of the steam jet pressure oscillation to be predicted are obtained. f 1 and the amplitude of the second main frequency A f2 , it is simple and convenient to operate, has a fast prediction speed and high accuracy. BRIEF DESCRIPTION OF THE DRAWINGS

[0031] The accompanying drawings constituting a part of the present invention are used to provide a further understanding of the present invention. The exemplary embodiments of the present invention and their descriptions are used to explain the present invention and do not constitute an improper limitation of the present invention. In the accompanying drawings:

[0032] Figure 1 The flow chart of the steam jet CFD calculation model;

[0033] Figure 2 is a flow chart of the present invention;

[0034] Figure 3 This is the architecture diagram of the Multi-Scale Residual Attention Network (MS-RAN);

[0035] Figure 4 This is the result diagram of global sensitivity analysis;

[0036] Figure 5 This is a comparison chart between the predicted value and the actual measured value. DETAILED DESCRIPTION

[0037] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0038] In the description of the present invention, it should be understood that the terms “include” and “comprises” indicate the presence of described features, wholes, steps, operations, elements and / or components, but do not exclude the presence or addition of one or more other features, wholes, steps, operations, elements, components and / or collections thereof.

[0039] It should also be understood that the terms used in the present specification are only for the purpose of describing specific embodiments and are not intended to limit the present invention. As used in the present specification and the appended claims, unless the context clearly indicates otherwise, the singular forms "a", "an" and "the" are intended to include plural forms.

[0040] It should be further understood that the term "and / or" used in the present specification and the appended claims refers to any combination of one or more of the associated listed items and all possible combinations, and includes these combinations. For example, A and / or B can represent: A exists alone, A and B exist at the same time, and B exists alone. In addition, the character " / " in the present invention generally indicates that the associated objects are in an "or" relationship.

[0041] It should be understood that, although the terms first, second, third, etc. may be used to describe preset ranges, etc. in the embodiments of the present invention, these preset ranges should not be limited to these terms. These terms are only used to distinguish preset ranges from each other. For example, without departing from the scope of the embodiments of the present invention, the first preset range may also be referred to as the second preset range, and similarly, the second preset range may also be referred to as the first preset range.

[0042] The word "if" as used herein may be interpreted as "at the time of" or "when" or "in response to determining" or "in response to detecting", depending on the context. Similarly, the phrases "if it is determined" or "if (stated condition or event) is detected" may be interpreted as "when it is determined" or "in response to determining" or "when detecting (stated condition or event)" or "in response to detecting (stated condition or event)", depending on the context.

[0043] In order to make the purpose, technical solutions and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, rather than all of the embodiments. The components of the embodiments of the present invention described and shown in the drawings here can usually be arranged and designed in various different configurations. Therefore, the following detailed description of the embodiments of the present invention provided in the drawings is not intended to limit the scope of the claimed invention, but merely represents selected embodiments of the present invention. Based on the embodiments in the present invention, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of the present invention.

[0044] Various structural schematic diagrams of the embodiments disclosed in the present invention are shown in the accompanying drawings. These figures are not drawn to scale, and some details are magnified and some details may be omitted for the purpose of clear expression. The shapes of various regions and layers shown in the figures and the relative sizes and positional relationships therebetween are only exemplary, and may deviate in practice due to manufacturing tolerances or technical limitations, and those skilled in the art may additionally design regions / layers with different shapes, sizes, and relative positions according to actual needs.

[0045] Embodiment 1

[0046] refer to Figures 1 to 5 The method for predicting the main frequency of steam jet pressure oscillation of the present invention comprises the following steps:

[0047] 1)CFD model construction and simulation;

[0048] 11) A three-dimensional steam jet model is constructed using three-dimensional modeling software. The geometric dimensions of the three-dimensional steam jet model refer to the typical nuclear reactor safety pressure relief system.

[0049] 12) Meshing, snappyHexMesh, and ICEM tools are used for meshing. Hexahedral structured meshes are used, and meshes are encrypted in the near-wall area. The total number of meshes is in the millions.

[0050] 13) An improved dual-resistance thermal equilibrium phase change model and LES turbulence model were set in the CFD calculation software, and the PIMPLE algorithm was used for pressure-velocity coupling. The model parameters were optimized by comparing with the benchmark experimental data, and a combination of grid search and Bayesian optimization was used to minimize the error between the simulation results and the experimental data.

[0051] 14) Computational simulation settings: inlet steam temperature and pressure, outlet pressure, wall conditions, time step, and total simulation time.

[0052] 15) Implement adaptive mesh refinement and dynamically encrypt the mesh in the jet core area and near the phase interface. The mesh size meets the requirements of LES calculation.

[0053] 2) Data collection and preprocessing Reynolds number (Re), Jacobs number (Ja), Weber number (We), dimensionless length (L / D) and pressure ratio (P in / P out )

[0054] 21) Extract the following data from the CFD simulation results: Input variables are Reynolds number Re, Jacobs number Ja, Weber number We, jet penetration dimensionless length L s / D, dimensionless length of jet expansion D s / D and pressure ratio P in / P out Dimensionless parameters.

[0055] The output variables are the Strouhal number (Sr) corresponding to the first main frequency f1 and the second main frequency f2; the dimensionless oscillation amplitude P corresponding to the first main frequency and the second main frequency f / P w (Ratio of the main frequency oscillation amplitude to the average pressure of the water area).

[0056] 22) Perform outlier detection, combine the 3σ criterion and isolation forest algorithm, set thresholds and use unsupervised learning methods to identify and process outliers in multidimensional feature space.

[0057] 23) Use Robust Scaler for feature scaling to improve the model’s robustness to outliers.

[0058] 24) Principal component analysis (PCA) was applied to perform feature dimensionality reduction, and the principal components with an explained variance ratio of more than 98% were retained.

[0059] 3) Build a deep neural network model

[0060] 31) Design the multi-scale residual attention network (MS-RAN) structure:

[0061] The input layer adopts a multi-channel structure, each channel corresponds to a principal component, and the number of nodes is equal to the number of selected principal components.

[0062] Multi-scale convolutional layers are used to extract features in parallel using 1x1, 3x3, and 5x5 convolution kernels to capture point-level, local, and larger-scale features respectively. A residual connection is added between every two convolutional layers, and a pre-activation structure is used, including batch normalization, ReLU activation, and convolution operations, to alleviate the gradient vanishing problem. A self-attention layer based on scaled dot-product attention is added after each residual block to highlight important features and enhance the model's ability to capture key information.

[0063] The output layer consists of 4 nodes, corresponding to the first main frequency f1, the second main frequency f2, and the amplitude A of the first main frequency. f 1. The amplitude of the second main frequency A f2 , and use a linear activation function.

[0064] 32) Design the loss function: The loss function design includes mean square error (MSE) and regularization terms based on physical constraints. The physical constraints include multiple constraints such as energy conservation, momentum conservation, latent heat of phase change, and non-negativity of pressure oscillation frequency.

[0065] That is: Loss=MSE+λ1*Physics_constraint+λ2*L2_regularization

[0066] Among them, Physics_constraint ensures that the prediction results conform to the basic laws of physics.

[0067] c) The Adam optimizer is used, the initial learning rate is set to 0.001, and the cosine annealing learning rate scheduling strategy is used to achieve more refined parameter adjustment in the later stages of training. Batch normalization and Dropout (ratio 0.5, as the empirical optimal value) are implemented to prevent overfitting and enhance the generalization ability of the model.

[0068] 4) Model training and optimization

[0069] 41) The dataset was divided into training set, validation set and test set in a ratio of 7:2:1. The Bayesian optimization algorithm was used to automatically adjust the hyperparameters, including the number of hidden layers, the number of neurons, and the learning rate.

[0070] 42) An early stopping strategy is adopted, and training is stopped when the validation set loss does not decrease for 10 consecutive epochs. Ensemble learning is implemented, and 5 MS-RAN models with different initializations are trained, and the prediction results are integrated using the weighted average method.

[0071] 5) Model evaluation and validation

[0072] 51) Calculate the following performance indicators on the test set:

[0073] Root mean square error (RMSE);

[0074] Coefficient of determination (R 2 );

[0075] Mean absolute percentage error (MAPE);

[0076] Maximum absolute error (MaxAE).

[0077] 52) Draw a scatter plot comparing the predicted values ​​with the actual values ​​to analyze the prediction accuracy of the model.

[0078] 53) The Monte Carlo Dropout method is used to estimate the confidence interval of the prediction results. By keeping the Dropout activation in the inference phase and performing multiple random samplings, the probability distribution of the prediction results is obtained, thereby quantifying the uncertainty of the model.

[0079] 54) SHAP value analysis was used to interpret model predictions and identify the features that have the greatest impact on the prediction results.

[0080] 6) Parameter sensitivity analysis

[0081] 61) The Sobol method is used to calculate the global sensitivity index of each input parameter to the main frequency of pressure oscillation.

[0082] 62) Draw a parameter importance heat map to intuitively display the influence of each parameter.

[0083] 63) Perform local sensitivity analysis and calculate partial derivatives Analyze the local impact of each parameter on the main frequency.

[0084] 7) Visualization and system integration

[0085] 71) Develop a Web 3D visualization module to display the distribution of the main frequency of pressure oscillation under different soda parameters. Encapsulate the trained deep neural network model as a Python library and provide a RESTful API interface.

[0086] 73) Design a Flask-based web interface to implement real-time data input and prediction result display. Implement a multi-level early warning mechanism, set different levels of alarms according to the proximity between the predicted main frequency and the natural frequency of the equipment, including visual and sound prompts, and automatically send notifications to relevant personnel.

[0087] Embodiment 2

[0088] The steam jet pressure oscillation main frequency prediction system of the present invention comprises:

[0089] An acquisition module, used for acquiring parameter information of the steam jet pressure oscillation to be predicted;

[0090] The prediction module is used to input the parameter information of the steam jet pressure oscillation to be predicted into the trained multi-scale residual attention network to obtain the first main frequency f1, the second main frequency f2, the amplitude A of the first main frequency of the steam jet pressure oscillation to be predicted. f 1 and the amplitude of the second main frequency A f2 .

[0091] Furthermore, the parameter information of the steam jet pressure oscillation to be predicted includes but is not limited to: Reynolds number Re, Jacobs number Ja, Weber number We, jet penetration dimensionless length L s / D, dimensionless length of jet expansion D s / D and pressure ratio P in / P out .

[0092] Further, including:

[0093] The simulation module is used to perform parameter simulation based on the CFD model and build a sample set according to the simulation results;

[0094] Building module for constructing multi-scale residual attention networks;

[0095] A training module is used to train the multi-scale residual attention network using the sample set to obtain a trained multi-scale residual attention network.

[0096] The division of modules in the embodiments of the present application is schematic and is only a logical function division. There may be other division methods in actual implementation. In addition, each functional module in each embodiment of the present application may be integrated into a processor, or may exist physically separately, or two or more modules may be integrated into one module. The above-mentioned integrated modules may be implemented in the form of hardware or in the form of software functional modules.

[0097] Embodiment 3

[0098] A computer device includes a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, the steps of the method for predicting the main frequency of steam jet pressure oscillation are implemented. The memory may include a memory, such as a high-speed random access memory, and may also include a non-volatile memory, such as at least one disk memory, etc. The processor, the network interface, and the memory are interconnected through an internal bus, and the internal bus may be an industrial standard architecture bus, a peripheral component interconnection standard bus, an extended industrial standard architecture bus, etc. The bus may be divided into an address bus, a data bus, a control bus, etc. The memory is used to store programs. Specifically, the program may include a program code, and the program code includes computer operation instructions. The memory may include a memory and a non-volatile memory, and provide instructions and data to the processor.

[0099] Embodiment 4

[0100] A computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the steps of the steam jet pressure oscillation main frequency prediction method are implemented. Specifically, the computer-readable storage medium includes, but is not limited to, volatile memory and / or non-volatile memory. The volatile memory may include random access memory (RAM) and / or cache memory, etc. The non-volatile memory may include read-only memory (ROM), hard disk, flash memory, optical disk, magnetic disk, etc.

[0101] Those skilled in the art will appreciate that the embodiments of the present application may be provided as methods, systems, or computer program products. Therefore, the present application may adopt the form of a complete hardware embodiment, a complete software embodiment, or an embodiment in combination with software and hardware. Moreover, the present application may adopt the form of a computer program product implemented in one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) that include computer-usable program code.

[0102] The present application is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems), and computer program products according to the embodiments of the present application. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of the processes and / or boxes 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 generate 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 1A device that provides the functions specified in a block or multiple blocks.

[0103] 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.

[0104] 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.

[0105] Those skilled in the art will readily appreciate other embodiments of the present invention after considering the specification and disclosure of the invention. This application is intended to cover any variations, uses or adaptations of the present invention that follow the general principles of the present invention and include common knowledge or customary techniques in the art that are not disclosed by the present invention. The specification and examples are to be considered exemplary only, and the true scope and spirit of the present invention are indicated by the following claims.

[0106] It should be understood that the present invention is not limited to the exact construction that has been described above and shown in the drawings and that various modifications and changes may be made without departing from the scope thereof. The scope of the present invention is limited only by the appended claims.

[0107] The above description is only a preferred embodiment of the present invention and does not limit the present invention in any way. Any simple modification, change and equivalent structural change made to the above embodiment based on the technical essence of the present invention still falls within the protection scope of the technical solution of the present invention.

Claims

1. A method for predicting the main frequency of steam jet pressure oscillation, characterized in that: include: Obtaining parameter information of the steam jet pressure oscillation to be predicted; The parameter information of the steam jet pressure oscillation to be predicted is input into the trained multi-scale residual attention network to obtain the first main frequency f1, the second main frequency f2, and the amplitude A of the first main frequency of the steam jet pressure oscillation to be predicted. f1 and the amplitude of the second main frequency A f2 .

2. The method for predicting the main frequency of steam jet pressure oscillation according to claim 1, characterized in that: The parameter information of the steam jet pressure oscillation to be predicted includes but is not limited to: Reynolds number Re, Jacobs number Ja, Weber number We, jet penetration dimensionless length L s / D, dimensionless length of jet expansion D s / D and pressure ratio P in / P out .

3. The method for predicting the main frequency of steam jet pressure oscillation according to claim 1, characterized in that: Before inputting the parameter information of the steam jet pressure oscillation to be predicted into the trained multi-scale residual attention network, the method further includes: Perform parameter simulation based on the CFD model and build a sample set based on the simulation results; Construct a multi-scale residual attention network; The multi-scale residual attention network is trained using the sample set to obtain a trained multi-scale residual attention network.

4. The method for predicting the main frequency of steam jet pressure oscillation according to claim 3, characterized in that: The loss function in the process of training the multi-scale residual attention network using the sample set is: Loss=MSE+λ1*Physics_constraint+λ2*L2_regularization.

5. The method for predicting the main frequency of steam jet pressure oscillation according to claim 3, characterized in that: The multi-scale residual attention network is trained using the sample set using a Bayesian optimization algorithm.

6. A steam jet pressure oscillation main frequency prediction system, characterized in that: include: An acquisition module, used for acquiring parameter information of the steam jet pressure oscillation to be predicted; The prediction module is used to input the parameter information of the steam jet pressure oscillation to be predicted into the trained multi-scale residual attention network to obtain the first main frequency f1, the second main frequency f2, the amplitude A of the first main frequency of the steam jet pressure oscillation to be predicted. f1 and the amplitude of the second main frequency A f2 .

7. The steam jet pressure oscillation main frequency prediction system according to claim 6, characterized in that: The parameter information of the steam jet pressure oscillation to be predicted includes but is not limited to: Reynolds number Re, Jacobs number Ja, Weber number We, jet penetration dimensionless length L s / D, dimensionless length of jet expansion D s / D and pressure ratio P in / P out .

8. The steam jet pressure oscillation main frequency prediction system according to claim 6, characterized in that: include: The simulation module is used to perform parameter simulation based on the CFD model and build a sample set according to the simulation results; Building module for constructing multi-scale residual attention networks; A training module is used to train the multi-scale residual attention network using the sample set to obtain a trained multi-scale residual attention network.

9. A computer device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the computer program, the steps of the method for predicting the main frequency of steam jet pressure oscillation are implemented as described in any one of claims 1-5.

10. A computer-readable storage medium storing a computer program, characterized in that: When the computer program is executed by a processor, the steps of the method for predicting the main frequency of steam jet pressure oscillation are implemented as described in any one of claims 1 to 5.

Images