A method, system and device for predicting water erosion damage of steam turbine blades

Abstract

The present invention discloses a method, a system and a device for predicting the water erosion damage of steam turbine blades, which relates to the technical field of water erosion damage prediction. The method includes establishing a three-dimensional blade and outer flow field geometric model, meshing the geometric model to obtain a graph structure capable of representing grid cells; performing numerical simulation using the graph structure to obtain a water erosion data training set; constructing a water erosion damage evaluation model for the blade, and the water erosion damage evaluation model includes a flow field prediction network and a moving blade erosion rate prediction network; using the water erosion data training set to input into the water erosion damage evaluation model for training to predict the moving blade erosion rate caused by the impact of secondary water droplets at different radial heights. The present invention uses a sufficient amount of blade water erosion analysis results as sample data to train the prediction network based on the distribution of liquid phase parameters in the flow field and the moving blade erosion rate prediction network, realizes the rapid prediction from design parameters to the moving blade erosion rate of the last stage, and improves the accuracy of the moving blade erosion rate prediction at the same time.

Description

Technical Field

[0001] The present invention relates to the technical field of prediction of water erosion damage, and particularly relates to a method, a system and a device for predicting water erosion damage of steam turbine blades. Background Art

[0002] The last-stage blades of the low-pressure cylinders of conventional condensing steam turbines in power plants and the last-stage blades of nuclear power steam turbines are all operating in wet steam areas. As the steam in the cascade continuously expands and does work, after passing through the Wilson saturation line, steam condensation nucleation occurs and is accompanied by droplet growth, and these small droplets will seriously disrupt the steam flow and reduce the efficiency of the steam turbine stage. Part of the droplets deposit on the blade surface to form a water film, and the larger-sized secondary droplets formed by the tearing of the water film at the trailing edge of the blade by the steam flow will impact the surface of the moving blade at high speed, thereby causing water erosion damage. Therefore, researching a method for evaluating the degree of water erosion damage is of great significance for evaluating the water erosion risk of the blades in the low-pressure cylinder under different working conditions, improving the economic benefits of steam turbine generator sets, and ensuring the safe and stable operation of the units.

[0003] At present, most scholars judge the degree of water erosion damage of steam turbine blades by means of pure numerical simulation methods. For example, in the "Journal of Power Engineering", a method for controlling the impact behavior of secondary water droplets by curved blades is proposed. By defining a material erosion model to simulate the erosion effect of water droplets hitting the blade, and then exploring the influence of stator blade reverse bending on blade water erosion. In the "Research on Water Erosion of the Last-stage Long Blades of the Low-pressure Cylinder of a Steam Turbine", a numerical simulation method is adopted and combined with a particle transport model to analyze the wet steam two-phase flow field of the last three stages of the low-pressure cylinder, and predict the position where the last-stage moving blade is most severely impacted by secondary water droplets.

[0004] However, the calculation process of the pure numerical simulation method in the above-mentioned existing technologies is quite cumbersome, and when studying the water erosion characteristics under variable boundary conditions such as small volume flow rate, each working condition needs to be calculated separately, which greatly increases the time and energy costs of the research work; at the same time, some boundary conditions adopted in the numerical simulation process, such as parameters such as the size and distribution of inlet water droplets, are taken as range values by theory or experience, resulting in a low accuracy of the predicted erosion rate of the moving blade. Summary of the Invention

[0005] Aiming at the deficiencies of the existing technology that the prediction efficiency of the numerical simulation method is slow and the accuracy of the predicted erosion rate of the moving blade is low, the present invention proposes a method, a system and a device for predicting water erosion damage of steam turbine blades. By training a flow field prediction network and a moving blade erosion rate prediction network based on depth graph convolution, rapid prediction from flow field condition control parameters to flow field parameters and then to the erosion rate of the last-stage moving blade is realized, thereby solving the problems existing in the existing technology.

[0006] A method for predicting water erosion damage of steam turbine blades includes the following steps:

[0007] Obtain the geometric parameters and operating condition control parameters of the steam turbine blade sample. Based on the geometric parameters, establish a geometric model including the three-dimensional blade surface and the outer flow domain of the blade, and perform mesh division on the geometric model to obtain a graph structure that can represent the mesh elements.

[0008] Use the graph structure for numerical simulation to obtain the liquid phase parameters at the moving and stationary blade interfaces at different radial heights; the liquid phase parameters at the moving and stationary blade interfaces include the number of primary droplets, droplet diameter, and droplet impact velocity; based on the number of primary droplets, droplet diameter, and droplet impact velocity, obtain the spatial distribution characteristics and motion distribution characteristics of secondary droplets; based on the spatial distribution characteristics and motion distribution characteristics of secondary droplets, obtain the erosion rate of the moving blade caused by secondary water droplet impact at different radial heights.

[0009] Use the operating condition control parameters of the blade sample as the input and the liquid phase parameters at the moving and stationary blade cross-sections as the output to train the neural network, and construct a flow field prediction network; use the output of the flow field prediction network as the input, the spatial distribution characteristics and motion distribution characteristics of secondary droplets as the influencing parameters of the moving blade erosion rate, and the moving blade erosion rate as the output to construct a moving blade erosion rate prediction network; establish a water erosion damage assessment model based on the flow field prediction network and the moving blade erosion rate prediction network.

[0010] Input the actual operating condition control parameters of the steam turbine blade to be measured into the water erosion damage assessment model to predict the erosion rate of the moving blade caused by secondary water droplet impact at different radial heights.

[0011] Furthermore, obtaining the erosion rate of the moving blade caused by secondary water droplet impact at different radial heights based on the spatial distribution characteristics and motion distribution characteristics of secondary droplets specifically includes the following steps:

[0012] Taking wet steam as the working medium, perform non-equilibrium condensation flow calculations on blade samples with different structures to obtain the liquid phase mass flow rate in the last-stage stator blade row. G ;

[0013] According to the density of wet steam , the absolute velocity vector of wet steam , the absolute velocity vector of primary droplets generated by wet steam condensation , and the surface tension of primary droplets , use the Weber calculation formula to calculate the diameter of secondary droplets in different blade height regions d ;

[0014] According to the liquid phase mass flow rate in the last-stage stator blade row, the humidity at the relative blade height, the volume of primary droplets, and the density of primary droplets, obtain the number of secondary droplets at different blade heights. M ;

[0015] Calculate the material volume damage caused by a single droplet on the moving blade surface according to the secondary droplet impact velocity, the secondary droplet diameter, and the erosion resistance number of the moving blade material, and then obtain the moving blade erosion rate; wherein, the circumferential velocity of the secondary droplet is the same as the circumferential velocity of the corresponding blade height area, and its radial velocity is the same as the mainstream radial component velocity.

[0016] Furthermore, use the operating condition control parameters of the blade sample as the input and the liquid phase parameters of the stator and rotor blade cross-sections as the output to train the neural network, and construct a flow field prediction network, which specifically includes the following steps:

[0017] Set the initial boundary conditions according to the actual operating conditions of the blade.

[0018] Analyze the liquid phase parameters of the cross-section between the stator and rotor blades. At the same blade height of this cross-section, select m points along the tangential direction, extract the liquid phase parameters at each data point, and then obtain the liquid phase parameters in the channel at the same radial height.

[0019] For a total of k at this cross-section, extract the liquid phase parameter values of the cross-section between the stator and rotor blades at different radial heights to obtain the liquid phase parameter vector space of the cross-section between the stator and rotor blades.

[0020] Establish a flow field prediction network according to the liquid phase parameter vector space of the cross-section between the stator and rotor blades, the operating condition control parameters of the blade sample, and the neural network parameters.

[0021] Furthermore, in the flow field prediction network and the moving blade erosion rate prediction network, three-layer graph convolutional layers are respectively used to extract the intermediate feature information of the flow field, and global pooling is used to aggregate the extracted feature information and then map it to the output space, and the prediction results are output through the fully connected layer.

[0022] Furthermore, it also includes using the mean square error between the predicted flow field of the flow field prediction network and the real flow field, and the mean square error between the moving blade erosion rate predicted by the moving blade erosion rate prediction network and the real moving blade erosion rate as the loss functions respectively to optimize the flow field prediction network and the moving blade erosion rate prediction network.

[0023] The present invention also includes a steam turbine blade water erosion damage prediction system, including:

[0024] An acquisition module, used to acquire the geometric parameters and operating condition control parameters of the steam turbine blade sample, establish a geometric model including the three-dimensional blade surface and the outer flow domain of the blade according to the geometric parameters, and perform mesh division on the geometric model to obtain a graph structure that can represent grid cells.

[0025] A training set construction module, which is used to perform numerical simulation using a graph structure to obtain the liquid-phase parameters of the stator-rotor blade interface at different radial heights; the liquid-phase parameters of the stator-rotor blade interface include the number of primary droplets, droplet diameter, and droplet impact velocity; according to the number of primary droplets, droplet diameter, and droplet impact velocity, obtain the spatial distribution characteristics and motion distribution characteristics of secondary droplets; according to the spatial distribution characteristics and motion distribution characteristics of secondary droplets, obtain the rotor blade erosion rate caused by the impact of secondary water droplets at different radial heights.

[0026] A model training module, which is used to take the operating condition control parameters of the blade sample as input and the liquid-phase parameters of the stator-rotor blade cross-section as output to train a neural network, and construct a flow field prediction network; take the output of the flow field prediction network as input, take the spatial distribution characteristics and motion distribution characteristics of secondary droplets as the influencing parameters of the rotor blade erosion rate, and take the rotor blade erosion rate as output to construct a rotor blade erosion rate prediction network; establish a water erosion damage assessment model according to the flow field prediction network and the rotor blade erosion rate prediction network.

[0027] A prediction module, which is used to input the actual operating condition control parameters of the steam turbine blade to be measured into the water erosion damage assessment model to predict the rotor blade erosion rate caused by the impact of secondary water droplets at different radial heights.

[0028] The present invention also includes a computer device for predicting water erosion damage of a steam turbine blade, including: a memory, a processor, and a computer program stored in the memory, and when the processor executes the computer program, the steps of the method for predicting water erosion damage of the last-stage steam turbine blade are implemented.

[0029] The present invention also includes a readable storage medium, the readable storage medium stores a computer program, the computer program includes program instructions, and when the program instructions are executed by a processor, the steps of the method for predicting water erosion damage of the last-stage steam turbine blade are executed.

[0030] The present invention provides a method for predicting water erosion damage of a steam turbine blade, having the following beneficial effects:

[0031] The present invention represents the data in the grid using a graph structure, which maximally preserves the information in the original flow field data and greatly reduces the influence of the grid structure on the flow field prediction. By training a flow field prediction network and a moving blade erosion rate prediction network based on deep graph convolution, the flow field prediction network can predict the liquid phase parameters inside the entire flow field by inputting the operating condition parameters, and has a wide applicable range and high generality for the last-stage blade cascade of steam turbines under different operating conditions. The secondary droplet size and spatial distribution characteristics directly related to water erosion damage are selected as the intermediate quantity for the moving blade erosion rate prediction network to predict, which improves the correlation between the two and makes the prediction of the moving blade erosion rate more reliable. This method has a faster prediction speed compared with the traditional numerical simulation method that calculates through droplet deposition and droplet movement trajectories, and the accuracy of the moving blade erosion rate is more precise. Brief Description of the Drawings

[0032] Figure 1 Schematic diagram of the numerical calculation domain and boundary conditions of the last-stage blade in the embodiment of the present invention;

[0033] Figure 2 Schematic diagram of the channel grid division of the calculation domain in the embodiment of the present invention;

[0034] Figure 3 Schematic diagram of the graph representation method of the grid in the embodiment of the present invention;

[0035] Figure 4 Schematic diagram of the parameter distribution of the cross-section between the moving and static blades in the embodiment of the present invention;

[0036] Figure 5 Schematic diagram of the flow field prediction network in the embodiment of the present invention;

[0037] Figure 6 Schematic diagram of the moving blade erosion rate prediction network in the embodiment of the present invention;

[0038] Figure 7 Flowchart of the steam turbine blade water erosion damage prediction method in the embodiment of the present invention. Detailed Embodiment

[0039] Next, the technical solutions in the embodiments of the present invention will be clearly and completely described in conjunction with the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all the embodiments.

[0040] The present invention proposes a steam turbine blade water erosion damage prediction method, which uses the analysis results of the wet steam condensation flow in the sufficient last-stage blade cascade of the steam turbine as samples to train a flow field prediction network and a moving blade erosion rate prediction network based on deep graph convolution, so as to realize the rapid prediction from the flow field condition control parameters to the flow field parameters and then to the erosion rate of the last-stage moving blade. As Figure 7 shown, this method specifically includes the following steps:

[0041] S1. Establish a geometric model including the three-dimensional blade surface and the outer flow domain of the blade: Using n design parameters, such as blade installation angle, chord length, maximum thickness, etc., to constrain the blade geometric parameters, and adopting the parametric design method to generate a geometric model including the surface of the last-stage blade of the steam turbine and the outer flow domain of the blade. The vector space of the blade geometric structure control parameters is:

[0042] ;

[0043] The aerodynamic outer flow domain of the divided last-stage cascade is as shown in Figure 1 . The left side is the inlet boundary, the right side is the outlet boundary, and the upper and lower sides are periodic symmetric boundaries, which are set to be rotationally periodic symmetric about the rotation axis of the turbomachine.

[0044] S2. Adaptive mesh generation and graph structure data representation: Perform structured hexahedral mesh generation on the geometric model, refine the mesh near the wall and fillet, generate and refine the boundary layer mesh to ensure the accuracy of local parameters in the aerodynamic analysis. Structured hexahedral meshes or unstructured tetrahedral meshes can be used inside the channel according to the structural needs, and at the same time, mesh independence verification is required to ensure that the calculation is not affected by the number of meshes. Adaptive mesh generation can use structured meshes or unstructured meshes, and use the graph structure to represent the data in the mesh, which greatly reduces the influence of the mesh structure on the flow field prediction. The three-dimensional blade surface and outer flow domain meshes obtained by the division are as shown in Figure 2 . The division uses structured meshes.

[0045] The flow field information obtained by using adaptive meshes is stored in the mesh nodes. To use deep learning for aerodynamic flow field prediction, these flow field data need to be converted into matrix form. Using the graph structure can flexibly represent the topological structure of the mesh elements, and process the boundary conditions and initial conditions as node feature vectors, retaining the information in the original flow field data to the greatest extent. Using X to represent the graph nodes, each graph node X i includes cell center coordinates, Mach number, temperature, etc. n feature dimensions, E represents the edge, and each edge connects two graph nodes . The mathematical expression of the mesh graph structure is:

[0046] ;

[0047] .

[0048] S3. Establishment and integration of training samples for water erosion data; the training samples should include all data from blade geometric parameters and aerodynamic design parameters to the distribution of flow field parameters and then to the matrix of water erosion characteristic variables. The establishment process includes the following specific steps:

[0049] a) First, use the Latin hypercube sampling technique to randomly sample from multiple blade geometric parameter distribution spaces to obtain N sets of last-stage turbine blade profiles that meet the design requirements. Then, establish the outer flow field for aerodynamic calculation using the methods of the first and second steps and complete the grid division.

[0050] b) Secondly, use wet steam as the working medium to calculate the non-equilibrium condensation flow of samples with different structures to obtain the liquid-phase mass flow rate in the last-stage stator blade row. G The droplets formed by the condensation of wet steam in the channel are primary droplets with relatively small diameters, usually less than 1 μm, and have little impact on water erosion. The secondary droplets that cause greater water erosion damage to the last-stage rotor blades are generally generated by the tearing of the water film on the surface of the stator blades. Research has shown that the proportion of secondary water droplets in the last-stage stator blade row is about 10%. Considering that the radial velocity of the secondary droplets is greatly affected by the centrifugal force after entering the rotor blade channel due to their larger diameters, it is necessary to correct the radial distribution of the secondary droplets.

[0051] The average humidity ratio at different relative blade heights is defined as:

[0052] ;

[0053] In the formula, represents the humidity at the relative blade height, represents the average humidity.

[0054] The empirical formula for the radial distribution of secondary droplets at the inlet of the last-stage stator blade considering the centrifugal force is:

[0055] , ;

[0056] , ;

[0057] In the formula, L represents the relative blade height;

[0058] For the secondary water droplets just detached from the trailing edge, the axial initial velocity is very small, taking 3 m / s. The circumferential velocity is the same as the circumferential velocity in the corresponding blade height region, and the radial velocity is taken as the same as the radial component velocity of the mainstream. The diameter d of the secondary water droplets in different blade height regions can be obtained from the Weber calculation formula:

[0059] ;

[0060] In the formula, represents the Weber number, represents the steam density, represents the absolute velocity vector of the steam, represents the absolute velocity vector of the water droplet, represents the surface tension of the water droplet.

[0061] The number of secondary droplets at different blade heights is defined as:

[0062] ;

[0063] where, represents the volume of a single droplet, represents the droplet density.

[0064] The volume damage of the material caused by a single droplet on the moving blade surface is defined as:

[0065] ;

[0066] where, is the droplet impact velocity, d is the droplet diameter, is the erosion resistance number of the material, which is related to the Vickers hardness of the material.

[0067] From the above analysis, it can be seen that the erosion rate of the last-stage moving blade is only related to 3 variables, namely the number of secondary droplets M , the droplet diameter d and the droplet impact velocity V .

[0068] c) Finally, integrate the results of N sample data as the training sets for the flow field prediction network and the moving blade erosion rate prediction network; the cross-section between the moving and stationary blades is a specific flow analysis cross-section in the steam turbine, located in the transition region between the rotating moving blades (rotor blades) and the stationary stationary blades (guide vanes / nozzles).

[0069] S4. Establish a flow field prediction network. The output parameters of the flow field prediction network are selected according to the actual conditions. For the factors affecting the secondary droplet distribution in the last-stage passage of the steam turbine, they should include humidity, droplet diameter, and droplet absolute velocity. To enhance the representation ability and learning ability of the network, different activation functions can be introduced to add non-linear elements to the input of the neural network and enhance the robustness of the training process.

[0070] Set the initial boundary conditions according to the actual operating conditions of the blade. The operating condition parameters are denoted as θ, including the inlet pressure, temperature, outlet pressure, etc., totaling j variables. The vector space representation of the operating condition parameters is:

[0071] ;

[0072] Post-process the calculation results of the non-equilibrium condensation flow in S3, analyze the liquid-phase parameters of a certain cross-section between the stator and rotor blades. At the same blade height of this cross-section, select m points along the tangential direction, extract the liquid-phase parameters at each data point, and the liquid-phase parameters in the channel at the same radial height are expressed as:

[0073] ;

[0074] Extract the liquid-phase parameters at different radial heights at a total of k locations on this cross-section. Therefore, the liquid-phase parameter vector space between the stator and rotor blades is expressed as:

[0075] ;

[0076] In the formula, represents the liquid-phase parameter value of the cross-section between the stator and rotor blades. The superscript represents different radial height positions, and the subscript represents different types of liquid-phase parameters;

[0077] The input variable of the flow field prediction network is the working condition control parameter of the to-be-solved last-stage flow field, and the output is the liquid-phase parameter distribution of the cross-section between the stator and rotor blades. Therefore, the flow field prediction network is expressed as:

[0078] ;

[0079] In the formula, represents the flow field predicted by the flow field prediction network, represents the input parameters of the flow field prediction network, i.e., the working condition parameters, represents the parameters of the flow field prediction network, represents the flow field prediction network.

[0080] The flow field prediction network predicts the flow field parameter distribution through the input working condition control parameters. Through multiple convolutions, it can effectively capture the characteristic information of different scales in the flow field. The random gradient descent algorithm is used to optimize the weight parameters to improve the prediction accuracy. In the flow field prediction network, three graph convolutional layers are set to train the graph structure. Through multiple convolution operations, the intermediate characteristic information of the flow field can be mapped to the physical field characteristic information on the nodes. The parameters of the convolutional layer from the first layer to the third layer are set to 56*56, 56*112, and 112*224 respectively. The specific operations within the network layer also include a 3*3 convolutional kernel, a pooling layer, an activation layer, etc. The ReLU function is used in the activation layer. The propagation method between layers of the graph convolutional neural network is as follows:

[0081] ;

[0082] Among them is the feature expression of the l th layer of the graph structure, is the adjacency matrix of graph nodes, is the degree matrix of, is the node feature of the network, is the weight matrix, is the non - linear activation function ReLU.

[0083] is to integrate the features extracted by the graph convolution layer and finally map them to the output space. After the max - pooling layer, a fully - connected layer needs to be added to map the features obtained by convolution to a higher output dimension. Therefore, three fully - connected layers are added after the max - pooling layer, and the output parameters of the final fully - connected layer are 10 * 1. Considering that too many parameters in the fully - connected layer are likely to cause over - fitting problems, regularization can be introduced, such as adding Dropout between the fully - connected layers to alleviate it. In this model, Dropout is set to 0.2.

[0084] S5. Establish a moving - blade erosion rate prediction network. Select the liquid - phase parameters of the flow field predicted by the flow - field prediction network as the input of the moving - blade erosion rate prediction network. The size and motion characteristics of the secondary droplets are the direct influencing parameters of the moving - blade erosion rate, which have the strongest correlation with the moving - blade erosion rate, improving the credibility of the erosion rate prediction. The moving - blade erosion rate prediction network realizes the prediction from the liquid - phase parameters at the cross - section between the moving and stationary blades to the erosion rate of the moving blade caused by the impact of secondary droplets.

[0085] The input parameters of the moving - blade erosion rate prediction network are the prediction results of the flow - field prediction network, that is , which is expressed by the following formula:

[0086] ;

[0087] The output parameters of the moving - blade erosion rate prediction network are the moving - blade erosion rates caused by the impact of secondary water droplets at different radial heights:

[0088] ;

[0089] In the formula, represents the moving - blade erosion rate.

[0090] The moving - blade erosion rate prediction network is expressed by the following formula:

[0091] ;

[0092] In the formula, represents the numerical value of the moving - blade erosion rate obtained through the moving - blade erosion rate prediction network, represents the parameters of the moving - blade erosion rate prediction network.

[0093] The moving blade erosion rate prediction network receives the output parameters of the flow field prediction network and further performs feature extraction. At the end of the model, a global pooling layer can be added to aggregate the output node features. Finally, the output of the fully connected layer is the predicted moving blade erosion rate. The method for predicting the moving blade erosion rate by predicting the distribution characteristics of the secondary droplet liquid phase parameters in the flow field only needs to predict the size and motion parameters of the secondary droplets, and simply calculates according to the droplet impact material damage formula to obtain the moving blade erosion rate. This method greatly reduces the problem of many parameters to be predicted when directly predicting the moving blade erosion rate, reduces the output variables of the moving blade erosion rate prediction network, reduces the complexity of the network, and improves the training speed of the network.

[0094] S6. Co-training and application of the two networks.

[0095] The training process of the neural network requires a large number of data samples. During this process, the deep learning model continuously adjusts the weights and biases of the neural network through optimization algorithms, so that the value of the loss function continuously decreases, and finally reaches the goal that the network output result is close to the real result. At the beginning of training, a larger learning rate can be set to improve the solution efficiency, and then the learning rate is gradually reduced according to the residual convergence situation to refine the parameter adjustment. At the beginning of training, to ensure the residual convergence, the two networks are trained separately to improve the prediction accuracy. The input and output parameters of the depth map convolutional neural network are represented by a regular spatial structure, so that the last-stage cascades of steam turbines with different structures and working conditions can all be represented by a regular data structure to directly participate in the training and prediction of the neural network.

[0096] The loss function of the flow field prediction network is defined as the mean square error between the predicted flow field and the real flow field, and is defined by the following formula:

[0097] ;

[0098] The loss function of the moving blade erosion rate prediction network is defined as the mean square error between the predicted moving blade erosion rate and the real moving blade erosion rate, and is defined by the following formula:

[0099] ;

[0100] After the residuals of the two networks converge, subsequently, the output result of the flow field prediction network is used as the input of the moving blade erosion rate prediction network for co-training. After training, for any last-stage blade of a steam turbine, it is possible to achieve a rapid prediction from the blade working condition parameters to the flow field liquid phase parameters and then to the moving blade erosion rate.

[0101] The present invention predicts the distribution parameters of the flow field in the last-stage cascade through a deep graph convolutional neural network to predict the water erosion rate on the surface of the moving blade. Compared with the traditional numerical simulation method that simultaneously calculates droplet deposition and droplet movement trajectories, this method has a faster prediction speed, more accurate prediction of droplet size and distribution characteristics, and high prediction efficiency. The present invention includes two networks. The flow field prediction network can predict the internal liquid-phase parameters of the entire flow field by inputting operating condition parameters, and has a wide applicable range and high generality for the last-stage cascade of steam turbines under different operating conditions. Selecting the secondary droplet size and spatial distribution characteristics directly related to water erosion damage as the intermediate quantities for prediction improves the correlation between the two, making the prediction of the moving blade erosion rate more reliable.

[0102] Based on the same inventive concept, the present invention also proposes a steam turbine blade water erosion damage prediction system, including:

[0103] An acquisition module, configured to acquire the geometric parameters and operating condition control parameters of a steam turbine blade sample, establish a geometric model including the three-dimensional blade surface and the outer flow domain of the blade according to the geometric parameters, and perform mesh division on the geometric model to obtain a graph structure that can represent grid cells.

[0104] A training set construction module, configured to perform numerical simulation using the graph structure to obtain the liquid-phase parameters at the moving and stationary blade interface at different radial heights; the liquid-phase parameters at the moving and stationary blade interface include the number of primary droplets, droplet diameter, and droplet impact velocity; according to the number of primary droplets, droplet diameter, and droplet impact velocity, obtain the spatial distribution characteristics and motion distribution characteristics of secondary droplets; obtain the moving blade erosion rate caused by the impact of secondary water droplets at different radial heights according to the spatial distribution characteristics and motion distribution characteristics of secondary droplets.

[0105] A model training module, configured to train a neural network with the operating condition control parameters of the blade sample as the input and the liquid-phase parameters at the moving and stationary blade cross-sections as the output to construct a flow field prediction network; use the output of the flow field prediction network as the input, use the spatial distribution characteristics and motion distribution characteristics of secondary droplets as the influencing parameters of the moving blade erosion rate, and use the moving blade erosion rate as the output to construct a moving blade erosion rate prediction network; establish a water erosion damage assessment model according to the flow field prediction network and the moving blade erosion rate prediction network.

[0106] A prediction module, configured to input the actual operating condition control parameters of the steam turbine blade to be measured into the water erosion damage assessment model to predict the moving blade erosion rate caused by the impact of secondary water droplets at different radial heights.

[0107] The present invention also proposes a computer device for predicting steam turbine blade water erosion damage, including: a memory, a processor, and a computer program stored in the memory. When the processor executes the computer program, the steps of the method for predicting water erosion damage of the last-stage steam turbine blade are implemented.

[0108] The present invention also provides a readable storage medium storing a computer program, the computer program including program instructions which, when executed by a processor, are used to perform the steps of the method for predicting water erosion damage of the last-stage blades of a steam turbine.

[0109] The above are only the preferred specific embodiments of the present invention, but the protection scope of the present invention is not limited thereto. Any person skilled in the art within the technical scope disclosed by the present invention, according to the technical solution and inventive concept of the present invention, making equivalent substitutions or changes should be covered by the protection scope of the present invention.

Claims

1. A method for predicting the water erosion damage of steam turbine blades, characterized in that, Including the following steps: Obtain the geometric parameters and operating condition control parameters of the steam turbine blade sample, establish a geometric model including the three-dimensional blade surface and the outer flow domain of the blade according to the geometric parameters, and perform mesh division on the geometric model to obtain a graph structure that can represent the mesh cells; Numerical simulation is carried out using a graph structure to obtain the liquid-phase parameters of the stator-rotor blade interface at different radial heights; the liquid-phase parameters of the stator-rotor blade interface include the number of primary droplets, droplet diameter, and droplet impact velocity; based on the number of primary droplets, droplet diameter, and droplet impact velocity, the spatial distribution characteristics and motion distribution characteristics of secondary droplets are obtained; based on the spatial distribution characteristics and motion distribution characteristics of secondary droplets, the erosion rate of the moving blade caused by the impact of secondary water droplets at different radial heights is obtained; the obtaining of the erosion rate of the moving blade caused by the impact of secondary water droplets at different radial heights based on the spatial distribution characteristics and motion distribution characteristics of secondary droplets specifically includes the following steps: taking wet steam as the working medium, performing non-equilibrium condensation flow calculations on blade samples with different structures to obtain the liquid-phase mass flow rate in the last-stage stator blade row G ; according to the density of the wet steam , the absolute velocity vector of the wet steam , the absolute velocity vector of the primary droplets generated by the condensation of the wet steam , and the surface tension of the primary droplets , the diameter of the secondary droplets in different blade height regions is calculated using the Weber calculation formula d ; according to the liquid-phase mass flow rate in the last-stage stator blade row, the humidity at the relative blade height, the volume and density of the primary droplets, the number of secondary droplets at different blade heights is obtained M ; according to the impact velocity of the secondary droplets, the diameter of the secondary droplets, and the erosion resistance number of the moving blade material, the volume damage of the material caused by a single droplet on the surface of the moving blade is calculated, and then the erosion rate of the moving blade is obtained; among them, the circumferential velocity of the secondary droplets is the same as the circumferential velocity of the corresponding blade height region, and its radial velocity is the same as the mainstream radial component velocity; Taking the operating condition control parameters of the blade sample as the input and the liquid phase parameters of the stator and rotor blade cross-sections as the output, the neural network is trained to construct a flow field prediction network; taking the output of the flow field prediction network as the input, the spatial distribution characteristics and motion distribution characteristics of the secondary droplets are used as the influencing parameters of the rotor blade erosion rate, and the rotor blade erosion rate is used as the output to construct a rotor blade erosion rate prediction network; a water erosion damage assessment model is established based on the flow field prediction network and the rotor blade erosion rate prediction network; the step of taking the operating condition control parameters of the blade sample as the input and the liquid phase parameters of the stator and rotor blade cross-sections as the output to train the neural network to construct a flow field prediction network specifically includes the following steps: setting the initial boundary conditions according to the actual operating conditions of the blade; analyzing the liquid phase parameters of the cross-section between the stator and rotor blades, and selecting m points along the tangential direction at the same blade height of this cross-section to extract the liquid phase parameters at each data point, so as to obtain the liquid phase parameters in the channel at the same radial height; extracting the liquid phase parameter values of the cross-section between the stator and rotor blades at different radial heights at a total of k locations of this cross-section to obtain the liquid phase parameter vector space of the cross-section between the stator and rotor blades; establishing a flow field prediction network according to the liquid phase parameter vector space of the cross-section between the stator and rotor blades, the operating condition control parameters of the blade sample, and the neural network parameters; Input the actual operating condition control parameters of the steam turbine blade to be measured into the water erosion damage assessment model, and predict the moving blade erosion rate caused by the secondary water droplet impact at different radial heights.

2. The method for predicting water erosion damage of steam turbine blades according to claim 1, characterized in that In the flow field prediction network and the moving blade erosion rate prediction network, three-layer graph convolutional layers are respectively used to extract the intermediate feature information of the flow field, and the global pooling is used to aggregate the extracted feature information and then map it to the output space, and the prediction result is output through the fully connected layer.

3. A method for predicting water erosion damage of steam turbine blades according to claim 1, characterized in that, It also includes using the mean square error between the predicted flow field of the flow field prediction network and the real flow field, and the mean square error between the moving blade erosion rate predicted by the moving blade erosion rate prediction network and the real moving blade erosion rate as the loss functions respectively to optimize the flow field prediction network and the moving blade erosion rate prediction network.

4. A steam turbine blade water erosion damage prediction system, characterized in that, Including: An acquisition module, which is used to obtain the geometric parameters and operating condition control parameters of the steam turbine blade sample, establish a geometric model including the three-dimensional blade surface and the outer flow domain of the blade according to the geometric parameters, and perform mesh division on the geometric model to obtain a graph structure that can represent the mesh cells; The training set construction module is used to perform numerical simulation using a graph structure to obtain the liquid phase parameters of the stator-rotor blade interface at different radial heights; the liquid phase parameters of the stator-rotor blade interface include the number of primary droplets, droplet diameter, and droplet impact velocity; based on the number of primary droplets, droplet diameter, and droplet impact velocity, the spatial distribution characteristics and motion distribution characteristics of secondary droplets are obtained; based on the spatial distribution characteristics and motion distribution characteristics of secondary droplets, the erosion rate of the moving blade caused by the impact of secondary water droplets at different radial heights is obtained; the obtaining of the erosion rate of the moving blade caused by the impact of secondary water droplets at different radial heights based on the spatial distribution characteristics and motion distribution characteristics of secondary droplets specifically includes the following steps: using wet steam as the working medium, performing non-equilibrium condensation flow calculations on blade samples with different structures to obtain the liquid phase mass flow rate in the last-stage stator blade row G ; according to the density of the wet steam , the absolute velocity vector of the wet steam , the absolute velocity vector of the primary droplets generated by the condensation of the wet steam , and the surface tension of the primary droplets , use the Weber calculation formula to calculate the diameter of secondary droplets in different blade height regions d ; according to the liquid phase mass flow rate in the last-stage stator blade row, the humidity at the relative blade height, the volume of the primary droplets, and the density of the primary droplets, obtain the number of secondary droplets at different blade heights M ; according to the impact velocity of the secondary droplets, the diameter of the secondary droplets, and the erosion resistance number of the moving blade material, calculate the volume damage of the material caused by a single droplet on the surface of the moving blade, and then obtain the erosion rate of the moving blade; wherein, the circumferential velocity of the secondary droplets is the same as the circumferential velocity of the corresponding blade height region, and its radial velocity is the same as the mainstream radial component velocity; A model training module, which is used to train a neural network with the operating condition control parameters of blade samples as inputs and the liquid phase parameters of the stator and rotor blade cross-sections as outputs, so as to construct a flow field prediction network; taking the output of the flow field prediction network as an input, using the spatial distribution characteristics and motion distribution characteristics of secondary droplets as influence parameters of the moving blade erosion rate, and using the moving blade erosion rate as an output, to construct a moving blade erosion rate prediction network; establishing a water erosion damage assessment model according to the flow field prediction network and the moving blade erosion rate prediction network; the step of training the neural network with the operating condition control parameters of blade samples as inputs and the liquid phase parameters of the stator and rotor blade cross-sections as outputs to construct a flow field prediction network specifically includes the following steps: setting initial boundary conditions according to the actual operating conditions of the blades; analyzing the liquid phase parameters of the cross-section between the stator and rotor blades, at the same blade height of this cross-section, m points are selected along the tangential direction, and the liquid phase parameters at each data point are extracted, so as to obtain the liquid phase parameters in the channel at the same radial height; for a total of k the liquid phase parameter values of the cross-sections between the stator and rotor blades at different radial heights at are extracted to obtain the liquid phase parameter vector space of the cross-section between the stator and rotor blades; a flow field prediction network is established according to the liquid phase parameter vector space of the cross-section between the stator and rotor blades, the operating condition control parameters of blade samples, and the neural network parameters; A prediction module, which is used to input the actual operating condition control parameters of the steam turbine blade to be measured into the water erosion damage assessment model, and predict the moving blade erosion rate caused by the secondary water droplet impact at different radial heights.

5. A computer device for predicting water erosion damage of steam turbine blades, characterized in that, Including: A memory, a processor, and a computer program stored in the memory. When the processor executes the computer program, it implements the steps of the steam turbine blade water erosion damage prediction method according to any one of claims 1-3.

6. A readable storage medium, characterized in that, The readable storage medium stores a computer program, and the computer program includes program instructions. When the program instructions are executed by the processor, they are used to execute the steps of the steam turbine blade water erosion damage prediction method according to any one of claims 1-3.

Images