Turbine blade outer surface temperature field prediction method, system, equipment, medium and product

Abstract

The invention discloses a turbine blade outer surface temperature field prediction method, system and device, a medium and a product, and relates to the technical field of thermal protection, the method comprises the following steps: obtaining historical working condition parameters under different working conditions and corresponding turbine blade outer surface temperature fields, and constructing a data set; according to the data set, a turbine blade outer surface temperature field prediction model is constructed based on a BP neural network; performing turbine blade outer surface temperature field prediction on the to-be-predicted working condition parameters by using the trained turbine blade outer surface temperature field prediction model; according to the method, high-precision rapid prediction of the turbine blade outer surface temperature field can be realized, and the distribution trend of the turbine blade outer surface temperature field can be precisely restored.

Description

Technical Field

[0001] The present application relates to the field of thermal protection technology, and in particular to a method, system, equipment, medium and product for predicting the temperature field on the outer surface of a turbine blade. Background Art

[0002] With the rapid development of modern aerospace technology, aircraft requirements for engine thrust and propulsion efficiency continue to increase. Increasing turbine inlet temperature has become a key approach to improving overall engine performance. As a core component of aircraft engines, turbine blades operate in increasingly harsh environments, needing to withstand higher gas temperatures and more severe thermal loads. Therefore, improving the accuracy of turbine blade thermal analysis and providing accurate thermal analysis data for turbine blade thermal protection design is crucial.

[0003] The double-wall cooling structure, a next-generation turbine blade cooling technology, consists of an impingement plate, an impingement cavity, and a film plate. Its operating principle is that after passing through the impingement holes, cold air impacts the target surface, enhancing heat exchange. It then flows out through the film holes, forming a protective air film with the external airflow to protect the turbine blades. This structure combines the advantages of both impingement cooling within the turbine blade and film cooling on the blade surface, significantly improving the cooling and heat exchange efficiency of the turbine blades and has been widely used in the aircraft engine field.

[0004] Currently, the study of turbine blade temperature fields mainly uses two methods: experimental research and numerical simulation. Although experimental research is reliable, it requires expensive experimental equipment and a large amount of resource investment, and is time-consuming and labor-intensive, and is usually not used in the design stage. In contrast, numerical simulation technology can fully reproduce the flow field and temperature field distribution inside the turbine blade, significantly improving production efficiency while reducing costs. However, the full-process design of turbine blades involves multidisciplinary intersections. From initial modeling to meshing to numerical simulation, each link requires a large amount of computing resources. These problems seriously restrict the practical application of subsequent turbine blade optimization design.

[0005] Therefore, based on the above problems, there is an urgent need to provide a new prediction method for the outer surface temperature field of turbine blades, which can achieve high-precision and rapid prediction of the outer surface temperature field of turbine blades, accurately restore the distribution trend of the outer surface temperature field of turbine blades, and shorten the design cycle of turbine blades. Summary of the Invention

[0006] The purpose of this application is to provide a method, system, equipment, medium and product for predicting the temperature field on the outer surface of a turbine blade, which can achieve high-precision and rapid prediction of the temperature field on the outer surface of a turbine blade, accurately restore the distribution trend of the temperature field on the outer surface of a turbine blade, and shorten the design cycle of the turbine blade.

[0007] To achieve the above objectives, this application provides the following solutions:

[0008] In a first aspect, the present application provides a method for predicting the temperature field of the outer surface of a turbine blade, comprising:

[0009] Obtain historical operating parameters under different operating conditions and the corresponding turbine blade outer surface temperature field, and construct a data set;

[0010] According to the data set, a turbine blade outer surface temperature field prediction model is constructed based on a BP neural network; the turbine blade outer surface temperature field prediction model takes operating condition parameters as input and takes the turbine blade outer surface temperature field as output;

[0011] The trained turbine blade outer surface temperature field prediction model is used to predict the turbine blade outer surface temperature field based on the predicted operating parameters.

[0012] Optionally, the operating parameters include: mainstream inlet flow, mainstream inlet temperature, flow ratio, cold air inlet temperature, cascade channel outlet pressure, blade rotation speed and Cartesian coordinates of the corresponding turbine blade outer surface.

[0013] Optionally, the step of obtaining the operating parameters under different historical operating conditions and the corresponding turbine blade outer surface temperature fields and constructing a data set further includes:

[0014] Normalize the dataset.

[0015] Optionally, the normalizing the data set specifically includes:

[0016] Using the formula Normalize the dataset;

[0017] Among them, y is the normalized result, x i is the working condition parameter, x min is the minimum value of the working condition parameter, x max is the maximum value of the operating condition parameter.

[0018] Optionally, the normalizing of the data set further includes:

[0019] The Latin hypercube sampling method is used to independently sample the dataset to obtain a training set, a validation set, and a test set.

[0020] Optionally, the method of using the trained turbine blade outer surface temperature field prediction model to predict the turbine blade outer surface temperature field for the operating condition parameter to be predicted further includes:

[0021] The prediction results are compared with the turbine blade outer surface temperature field simulated using the CFD method to evaluate the trained turbine blade outer surface temperature field prediction model.

[0022] In a second aspect, the present application provides a system for predicting the temperature field of the outer surface of a turbine blade, comprising:

[0023] The data set construction module is used to obtain the operating parameters under different historical operating conditions and the corresponding turbine blade outer surface temperature field, and construct the data set;

[0024] a turbine blade outer surface temperature field prediction model construction module, configured to construct a turbine blade outer surface temperature field prediction model based on the data set and a BP neural network; the turbine blade outer surface temperature field prediction model takes operating condition parameters as input and takes the turbine blade outer surface temperature field as output;

[0025] The prediction module is used to predict the temperature field of the outer surface of the turbine blade using the trained turbine blade outer surface temperature field prediction model for the predicted working condition parameters.

[0026] In a third aspect, the present application provides a computer device comprising: a memory, a processor, and a computer program stored on the memory and executable on the processor, wherein the processor executes the computer program to implement the steps of the method for predicting the temperature field of the outer surface of a turbine blade as described in any one of the above.

[0027] In a fourth aspect, the present application provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the steps of the method for predicting the temperature field on the outer surface of a turbine blade as described in any one of the above.

[0028] In a fifth aspect, the present application provides a computer program product, comprising a computer program, which, when executed by a processor, implements the steps of the method for predicting the temperature field on the outer surface of a turbine blade as described above.

[0029] According to the specific embodiments provided in this application, this application has the following technical effects:

[0030] The present application provides a method, system, equipment, medium and product for predicting the outer surface temperature field of a turbine blade. A turbine blade outer surface temperature field prediction model is constructed based on a data set. The turbine blade outer surface temperature field prediction model is trained using a small amount of data to obtain the turbine blade outer surface temperature field under any working conditions within the research range. The present application can quickly predict the turbine blade outer surface temperature field and accurately restore the distribution trend of the turbine blade outer surface temperature field. BRIEF DESCRIPTION OF THE DRAWINGS

[0031] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the embodiments. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0032] Figure 1 This is a flow chart of a method for predicting the temperature field on the outer surface of a turbine blade in one embodiment of the present application;

[0033] Figure 2 This is a schematic diagram of the geometric model of a double-wall turbine blade in one embodiment of the present application;

[0034] Figure 3 This is a schematic diagram of the BP neural network structure in one embodiment of the present application;

[0035] Figure 4 A bar chart comparing the average temperature values ​​predicted by the turbine blade outer surface temperature field prediction model and the CFD simulation in one embodiment of the present application;

[0036] Figure 5 Schematic diagram of predicted temperature error of the prediction results of the turbine blade outer surface temperature field prediction model in one embodiment of the present application. DETAILED DESCRIPTION

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

[0038] This application constructs a prediction model for the outer surface temperature field of turbine blades, mines the intrinsic numerical correlations of existing data based on machine learning, realizes data regression and classification under unknown conditions, and can achieve rapid prediction of the outer surface temperature field of turbine blades under any working conditions within the research scope, shortening the design cycle of turbine blades and saving time for cooling performance evaluation.

[0039] In order to make the above-mentioned purposes, features and advantages of the present application more obvious and easy to understand, the present application is further described in detail below with reference to the accompanying drawings and specific implementation methods.

[0040] In an exemplary embodiment, Figure 1 As shown, a method for predicting the temperature field of the outer surface of a turbine blade is provided. Figure 2The outer surface temperature of a double-walled turbine blade in a turbine is predicted, wherein the turbine blade is placed in a cascade channel. To protect the blade from erosion by high-temperature combustion gas, film holes are provided on the leading edge, pressure side, suction side, and blade tip of the blade. In this embodiment of the present application, the method includes the following steps S1-S3.

[0041] S1: Obtain the historical operating parameters under different operating conditions and the corresponding turbine blade outer surface temperature field, and construct a data set.

[0042] Obtain the operating parameters under different historical operating conditions and the corresponding turbine blade outer surface temperature field. The operating parameters include 6 thermal parameters and the Cartesian coordinates of the corresponding turbine blade outer surface. The 6 thermal parameters are: mainstream inlet flow rate m in , mainstream inlet temperature T t,in , flow ratio M R , air conditioning inlet temperature T t,c , cascade channel outlet pressure p out and the blade rotation speed N.

[0043] Specifically, the mainstream inlet flow m in 0.5~1.5kg / s, mainstream inlet temperature T t,in 1800~2500K, flow rate is M R 5~15%, the air inlet temperature T t,c is 600~900K, and the cascade channel outlet pressure p out The pressure is 3 to 8 bar, and the blade rotation speed N is 10000 to 30000 rpm, wherein the flow ratio M R It is the ratio of the cooling air inlet flow rate to the mainstream inlet flow rate.

[0044] A data set is constructed based on the operating parameters and the corresponding turbine blade outer surface temperature field.

[0045] S2: Based on the data set and BP neural network, a prediction model for the temperature field on the outer surface of the turbine blade is constructed.

[0046] S2 specifically includes:

[0047] S21: Normalize the data set.

[0048] Since the unit scales of different operating parameters in the data set are different, the operating parameters are normalized and the unit scales of the operating parameters are placed in the range of (0,1). The normalization formula is as follows:

[0049]

[0050] Among them, y is the normalized result, x i is the working condition parameter, xmin is the minimum value of the working condition parameter, x max is the maximum value of the operating condition parameter.

[0051] S22: Use the Latin hypercube sampling method to independently sample the data set to obtain the training set, validation set, and test set.

[0052] The six thermal parameters are combined with the corresponding Cartesian coordinates of the turbine blade outer surface. The Cartesian coordinates include: horizontal coordinate X, vertical coordinate Y, and vertical coordinate Z. The combined parameters are independently sampled three times using the Latin hypercube sampling method, resulting in a training set with 56 samples, a validation set with 16 samples, and a test set with 8 samples. The parameters of the test set are shown in Table 1:

[0053] Table 1 Test set parameters

[0054] Sample No. <![CDATA[m in (kg / s)]]> <![CDATA[T t,in (K)]]> <![CDATA[M R ]]> <![CDATA[T t,c (K)]]> <![CDATA[p out (Well)]]> N (rpm) 1 0.66 2196.16 0.09 711.37 435411 29537 2 0.68 2181.85 0.07 702.08 733915 10220 3 0.68 2385.34 0.04 755.55 649467 27295 4 0.72 2287.18 0.10 805.97 519015 11455 5 1.44 2017.62 0.11 664.73 538987 20897 6 1.12 2286.04 0.11 698.30 426228 23618 7 1.32 2263.89 0.12 796.30 448964 26098 8 0.81 2402.26 0.10 773.18 723325 15264

[0055] There is no overlap between any samples in the training set, validation set, and test set.

[0056] S23: Based on the training set and validation set, a turbine blade outer surface temperature field prediction model is constructed based on the BP neural network.

[0057] S23 specifically includes:

[0058] S231: Establish BP neural network.

[0059] Self-programming on the PyCharm platform, using the PyTorch framework to build a BP neural network, such as Figure 3 As shown in the figure, the BP neural network receives samples in the training set from the input layer, and obtains the output of the hidden layer through the weights and biases corresponding to the input layer and the hidden layer and the first activation function. The output value calculation formula of the hidden layer is as follows:

[0060]

[0061] Among them, H j is the output value of the hidden layer, as the input value of the output layer, f1 is the first activation function, that is, the activation function between the input layer and the hidden layer, n is the number of nodes in the input layer, i is the index of the input layer, ω ij is the weight between the input layer and the hidden layer, X i is the temperature field prediction parameter, b j is the bias between the input layer and the hidden layer, j is the index of the hidden layer, and h is the number of nodes in the hidden layer.

[0062] In this application, the first activation function f1 is a Relu function, and its expression is as follows:

[0063] f1(x)=Relu(x)=max(0,x).

[0064] Among them, max(0,x) is the maximum value.

[0065] The output value of the hidden layer is used as the input value of the output layer, and the output value of the output layer is obtained by calculating the corresponding weights and biases between the hidden layer and the output layer and the second activation function. The output value calculation formula of the output layer is as follows:

[0066]

[0067] Among them, Y k is the output value of the output layer, that is, the k-th prediction result, f2 is the second activation function, that is, the activation function between the hidden layer and the output layer, β jk is the weight between the hidden layer and the output layer, c k is the bias value between the hidden layer and the output layer, k is the index of the output layer, and m is the number of nodes in the output layer.

[0068] In this application, the second activation function f2 is the identification function purelin, which is expressed as follows:

[0069] f2(x)=purelin(x)=x.

[0070] S232: Based on BP neural network, a prediction model for the temperature field on the outer surface of turbine blades is constructed.

[0071] The trial and error method was used to determine that the optimizer of the BP neural network was the SGD optimizer. The learning rate decay strategy was adopted, the initial learning rate was set to 0.1, and the learning rate decay coefficient was set to 0.5. A turbine blade outer surface temperature field prediction model was constructed. The turbine blade outer surface temperature field prediction model took the operating condition parameters as input and the turbine blade outer surface temperature field as output.

[0072] The turbine blade outer surface temperature field prediction model is iteratively calculated using the training set to train the turbine blade outer surface temperature field prediction model. Subsequently, the prediction accuracy and generalization ability of the turbine blade outer surface temperature field prediction model are evaluated and adjusted using the mean absolute percentage error (MAPE) and root mean square error (RMSE) using the validation set. The calculation formulas for the mean absolute percentage error (MAPE) and root mean square error (RMSE) are as follows:

[0073]

[0074] Among them, M is the total number of samples in the test set, Y k is the k-th prediction result, O k is the k-th numerical simulation result, where k is the sample number of the test set.

[0075] S3: Use the trained turbine blade outer surface temperature field prediction model to predict the turbine blade outer surface temperature field based on the predicted operating parameters.

[0076] The prediction results are compared with the turbine blade outer surface temperature field predicted by the CFD method to evaluate the trained turbine blade outer surface temperature field prediction model.

[0077] The turbine blade outer surface temperature field prediction method and CFD method of this application are used to predict the test set with 8 groups of samples, such as Figure 4 and Figure 5 As shown in the figure, the average temperature values ​​and predicted temperature errors under 8 groups of sample working conditions are evaluated respectively, among which, Figure 4 and Figure 5 The horizontal axis represents the different working conditions of the test set. Figure 4 The vertical axis is the average temperature value T ave / K, Figure 5 The vertical axis is the predicted temperature error θ, in %. Figure 4 and Figure 5 Significantly, the relative error between the prediction results obtained using the proposed method and the CFD method is within 3%, indicating that the trained turbine blade outer surface temperature field prediction model can fully predict the distribution pattern of the turbine blade outer surface temperature field, with excellent performance, high prediction accuracy, and good generalization ability. This means that the proposed turbine blade outer surface temperature field prediction method maintains high prediction accuracy while achieving faster computational speeds than traditional CFD methods, which are complex to model and computationally expensive.

[0078] Based on the same inventive concept, the present application also provides a turbine blade outer surface temperature field prediction system. The solution provided by this system is similar to the solution described in the aforementioned method. Therefore, the specific limitations of the turbine blade outer surface temperature field prediction system embodiment provided below can be found in the aforementioned limitations of the turbine blade outer surface temperature field prediction method and will not be further elaborated here.

[0079] In an exemplary embodiment, a turbine blade outer surface temperature field prediction system is provided, comprising:

[0080] The data set construction module is used to obtain the operating parameters under different historical operating conditions and the corresponding turbine blade outer surface temperature field, and construct the data set;

[0081] a turbine blade outer surface temperature field prediction model construction module, configured to construct a turbine blade outer surface temperature field prediction model based on the data set and a BP neural network; the turbine blade outer surface temperature field prediction model takes operating condition parameters as input and takes the turbine blade outer surface temperature field as output;

[0082] The prediction module is used to predict the temperature field of the outer surface of the turbine blade using the trained turbine blade outer surface temperature field prediction model for the predicted working condition parameters.

[0083] In an exemplary embodiment, a computer device is provided, which may be a server or a terminal. The computer device includes a processor, a memory, an input / output interface (I / O), and a communication interface. The processor, the memory, and the input / output interface are connected via a system bus, and the communication interface is connected to the system bus via the input / output interface. The processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program, and a database. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The database of the computer device is used to store turbine blade outer surface temperature field prediction data. The input / output interface of the computer device is used to exchange information between the processor and an external device. The communication interface of the computer device is used to communicate with an external terminal via a network connection. When the computer program is executed by the processor, a method for predicting the turbine blade outer surface temperature field is implemented.

[0084] In an exemplary embodiment, a computer device is provided, including a memory and a processor. The memory stores a computer program, and the processor implements the steps in the above method embodiments when executing the computer program.

[0085] In an exemplary embodiment, a computer-readable storage medium is provided, storing a computer program. When the computer program is executed by a processor, the steps in the above-mentioned method embodiments are implemented.

[0086] In an exemplary embodiment, a computer program product is provided, including a computer program. When the computer program is executed by a processor, the steps in the above method embodiments are implemented.

[0087] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, stored data, displayed data, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties, and the collection, use and processing of relevant data must comply with relevant regulations.

[0088] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be completed by instructing the relevant hardware through a computer program. The computer program can be stored in a non-volatile computer readable storage medium, and when the computer program is executed, the processes of the above-mentioned embodiments of the methods can be included. Any reference to memory, databases or other media used in the embodiments provided in the present application can include at least one of non-volatile and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical storage, high-density embedded non-volatile memory, resistive memory (ReRAM), magnetoresistive random access memory (MRAM), ferroelectric memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. As an illustration but not limitation, RAM can be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM), etc.

[0089] The database involved in the embodiments provided in the present application can include at least one of a relational database and a non-relational database. The non-relational database can include a distributed database based on a blockchain, etc., without being limited thereto. The processor involved in the embodiments provided in the present application can be a general-purpose processor, a central processing unit, a graphics processing unit, a digital signal processor, a programmable logic device, a data processing logic device based on quantum computing, etc., without being limited thereto.

[0090] The technical features of the above embodiments can be combined arbitrarily. In order to make the description concise, all possible combinations of the technical features in the above embodiments are not described, but as long as the combinations of the technical features do not exist, they should be considered as the scope of the present application.

[0091] The principles and implementation modes of the present application are described by applying specific examples herein. The above description of the embodiments is only used to help understand the method and its core idea of the present application; meanwhile, for those skilled in the art, according to the idea of the present application, the specific implementation mode and application range can be changed. In conclusion, the content of the present application should not be understood as a limitation.

Claims

1. A method for predicting the temperature field of the outer surface of a turbine blade, characterized in that: The method for predicting the temperature field on the outer surface of the turbine blade includes: Obtain historical operating parameters under different operating conditions and the corresponding turbine blade outer surface temperature field, and construct a data set; According to the data set, a turbine blade outer surface temperature field prediction model is constructed based on a BP neural network; the turbine blade outer surface temperature field prediction model takes operating condition parameters as input and takes the turbine blade outer surface temperature field as output; The trained turbine blade outer surface temperature field prediction model is used to predict the turbine blade outer surface temperature field based on the predicted operating parameters.

2. The method for predicting the temperature field of the outer surface of a turbine blade according to claim 1, characterized in that: The operating parameters include: mainstream inlet flow, mainstream inlet temperature, flow ratio, cold air inlet temperature, cascade channel outlet pressure, blade rotation speed, and Cartesian coordinates of the corresponding turbine blade outer surface.

3. The method for predicting the temperature field of the outer surface of a turbine blade according to claim 1, characterized in that: The method of obtaining the operating parameters under different historical operating conditions and the corresponding turbine blade outer surface temperature field and constructing a data set further includes: Normalize the dataset.

4. The method for predicting the temperature field of the outer surface of a turbine blade according to claim 3, characterized in that: The normalization of the data set specifically includes: Using the formula Normalize the dataset; Among them, y is the normalized result, x i is the working condition parameter, x min is the minimum value of the working condition parameter, x max is the maximum value of the operating condition parameter.

5. The method for predicting the temperature field of the outer surface of a turbine blade according to claim 3, characterized in that: The normalization of the data set further includes: The Latin hypercube sampling method is used to independently sample the dataset to obtain a training set, a validation set, and a test set.

6. The method for predicting the temperature field of the outer surface of a turbine blade according to claim 1, characterized in that: The method further comprises: using the trained turbine blade outer surface temperature field prediction model to predict the turbine blade outer surface temperature field for the operating condition parameters to be predicted; and then: The prediction results are compared with the turbine blade outer surface temperature field simulated using the CFD method to evaluate the trained turbine blade outer surface temperature field prediction model.

7. A system for predicting the temperature field of the outer surface of a turbine blade, characterized in that: The prediction system for the turbine blade outer surface temperature field includes: The data set construction module is used to obtain the operating parameters under different historical operating conditions and the corresponding turbine blade outer surface temperature field, and construct the data set; a turbine blade outer surface temperature field prediction model construction module, configured to construct a turbine blade outer surface temperature field prediction model based on the data set and a BP neural network; the turbine blade outer surface temperature field prediction model takes operating condition parameters as input and takes the turbine blade outer surface temperature field as output; The prediction module is used to predict the temperature field of the outer surface of the turbine blade using the trained turbine blade outer surface temperature field prediction model for the predicted working condition parameters.

8. A computer device comprising: A memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the method for predicting the temperature field on the outer surface of a turbine blade according to any one of claims 1 to 6.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the method for predicting the temperature field on the outer surface of a turbine blade according to any one of claims 1 to 6 is implemented.

10. A computer program product comprising a computer program, characterized in that When the computer program is executed by a processor, the method for predicting the temperature field on the outer surface of a turbine blade according to any one of claims 1 to 6 is implemented.

Images