Method and device for correcting adjustable guide vane gap leakage loss model

Abstract

This invention discloses a method, apparatus, computer equipment, and computer-readable storage medium for correcting an adjustable guide vane clearance leakage loss model, relating to the field of variable geometry turbine adjustable guide vane technology. The method includes: constructing a database of multiple clearance flow fields for the blade tip / root clearance and structures containing a rotating shaft based on CFD experimental flow field data of a variable geometry turbine, obtaining independent leakage losses. A machine learning method, primarily using neural networks, is used to fit the corrected AMDCKO model, obtaining blade tip and root clearance loss models, which are then superimposed into a total clearance loss model without a rotating shaft. A rotation shaft correction coefficient KZ is introduced, and its diameter and position are used as variables to model the leakage loss at the tip of the adjustable guide vane containing the rotating shaft. Embedding this model into a one-dimensional performance prediction program can improve the accuracy and reliability of loss calculation, providing a scientific theoretical basis and technical support for the aerodynamic optimization design and parameter matching of variable geometry turbines.

Description

Technical Field

[0001] This invention relates to the field of variable geometry turbine adjustable guide vane technology, and in particular to a method and apparatus for correcting the leakage loss model of adjustable guide vane clearance. Background Technology

[0002] With the ever-increasing demands for high efficiency and adaptability in aero-engines and high-performance gas turbines, variable geometry turbines (VGTs), as one of the key control technologies, have been widely applied in practical engineering. VGTs achieve adaptive control of flow parameters by adjusting the guide vane opening to match different operating conditions, thereby effectively optimizing aerodynamic performance and improving overall system efficiency. Although current research on the flow characteristics and structural design of VGTs is relatively in-depth, research on their internal loss mechanisms and loss models remains relatively weak.

[0003] Turbine loss models are used to quantitatively describe the energy loss patterns in internal flow processes. Currently, conventional clearance loss models, such as the Ainley & Mathieson model and the Kacker & Okapuu model, can only predict clearance leakage losses at the tips of turbine blades and cannot be applied to rotatable, adjustable guide vanes with rotating shafts and root-tip clearances. Therefore, to quickly and accurately predict the one-dimensional performance and clearance leakage losses of variable geometry turbines, it is necessary to construct a clearance leakage loss model specifically for adjustable guide vanes and incorporate it into one-dimensional prediction programs. This would improve the accuracy of loss prediction and provide solid theoretical support for the aerodynamic optimization and structural design of variable geometry turbines.

[0004] Currently, conventional clearance loss models (such as the Ainley & Mathieson model and the Kacker & Okapuu model) are mainly designed for turbines with fixed geometries and can effectively predict clearance leakage losses at the blade tips. However, these models typically assume a relatively stable flow field structure and are not applicable to guide vane structures with rotational adjustment functions, especially in cases where there is clearance between the blade root and tip and a rotation axis, their prediction accuracy and applicability are significantly limited. Summary of the Invention

[0005] The main objective of this invention is to provide a method for correcting the leakage loss model of adjustable guide vane gap.

[0006] Another objective of this invention is to provide a correction device for an adjustable guide vane clearance leakage loss model.

[0007] The third objective of this invention is to provide a computer device.

[0008] A fourth objective of this invention is to provide a non-transitory computer-readable storage medium.

[0009] To achieve the above objectives, a first aspect of the present invention proposes a method for correcting the adjustable guide vane clearance leakage loss model, comprising:

[0010] S1: Based on the CFD experimental flow field data of the variable geometry turbine, a CFD flow field clearance loss database of the adjustable guide vane with tip clearance and no rotating shaft is constructed to obtain the CFD flow field data without rotating shaft at the tip clearance. S2: Based on the obtained CFD flow field data of the blade tip clearance without rotating shaft, the established blade tip clearance loss model formula is fitted using machine learning methods; S3: Based on the CFD experimental flow field data of variable geometry turbine, construct a CFD flow field clearance loss database for adjustable guide vanes in the case of blade root clearance and no rotating shaft, and obtain CFD flow field data without rotating shaft at blade root clearance. S4: Based on the obtained CFD flow field data of the blade root clearance without rotating axis, the established blade root clearance loss model formula is fitted using machine learning methods. S5: Superimpose the obtained tip clearance loss model formula with the obtained root clearance loss model formula to establish the total clearance loss model formula for adjustable guide vanes without rotating shaft leakage. S6: Based on the CFD experimental flow field data of variable geometry turbine, construct a CFD flow field clearance loss database for adjustable guide vanes under the condition of simultaneous blade tip clearance and blade root clearance and rotation axis, and obtain CFD flow field data with clearance and rotation axis. S7: Based on the obtained CFD flow field data with gaps and a rotating shaft, and using the formula of the total gap leakage loss model of the adjustable guide vane without a rotating shaft as a basis, a machine learning method is used for fitting to obtain the gap leakage loss model of the adjustable guide vane with gaps and a rotating shaft, thus completing the modeling of the leakage loss prediction of the adjustable guide vane tip gap.

[0011] Optionally, based on the CFD experimental flow field data of the variable geometry turbine, a CFD flow field clearance loss database of the adjustable guide vane in the presence of tip clearance and without a rotating shaft is constructed to obtain CFD flow field data of the tip clearance without a rotating shaft, including: The leakage loss at the tip clearance of the adjustable guide vane is calculated separately using the following method:

[0012] in, This refers to the clearance leakage loss when there is clearance at the tip of the adjustable guide vane and no shaft. This represents the total loss when the adjustable guide vane has a gap at the tip and no shaft. This represents the total loss under the condition that the adjustable guide vane tip has no clearance and no shaft.

[0013] Optionally, based on the obtained CFD flow field data of the blade tip clearance without rotating shaft, machine learning methods are used to fit the established blade tip clearance loss model formula, including: The formula for the tip clearance loss model parameter is based on the modified AMDCKO clearance loss model. The AMDCKO model uses the total pressure loss coefficient as the main indicator to measure leakage loss and defines the ratio of the total pressure loss caused by clearance leakage to the intake dynamic pressure. The AMDCKO model expresses the loss in the following form:

[0014] in, The average total pressure is the inlet mass flow rate. and The average total pressure and static pressure at the outlet plane mass flow rate. The average total pressure at a fixed blade height on the measuring plane; The formula for tip clearance leakage loss is defined as follows:

[0015] Where c is the chord length, This is the gap value. For leaf height; in the formula, A, n1, n2, ... As the deviation unknowns, the polynomial function forms of A, n1, and n2 include different orders and coefficients to describe... and The nonlinear coupling relationship between them, parameters It is a constant related to the angle of the inlet and outlet airflow.

[0016] Optionally, based on the CFD experimental flow field data of the variable geometry turbine, a CFD flow field clearance loss database of the adjustable guide vane in the presence of blade root clearance and without a rotating shaft is constructed to obtain CFD flow field data of the blade root clearance without a rotating shaft, including: The leakage loss at the root gap of the adjustable guide vane is isolated and calculated as follows:

[0017] in, This refers to the gap leakage loss when there is a gap at the blade root of the adjustable guide vane and no shaft. This represents the total loss under the condition that the adjustable guide vane has a gap at the blade root and no shaft. This represents the total loss under the condition that the adjustable guide vane root has no gap and no shaft.

[0018] Optionally, based on the obtained CFD flow field data of the blade root clearance without rotating axis, machine learning methods are used to fit the established blade root clearance loss model formula, including: The formula for the parameters of the leaf root gap loss model is based on the modified AMDCKO gap loss model, and the expression is:

[0019] in, For the leaf root clearance loss, B, m1, m2, and bias2 are unknowns. Parameters B, m1, and m2 are considered as having relation to... and The polynomial functions B, m1, and m2 have different orders and coefficients to describe and The nonlinear coupling relationship between them can be expressed mathematically as follows:

[0020] in, , , These represent polynomial functions of different orders and coefficients, respectively.

[0021] Optionally, the formula for the adjustable guide vane total clearance leakage loss model without rotating shaft is shown below:

[0022] in, The adjustable guide vane has no leakage loss due to the rotating shaft.

[0023] Optionally, the formula for the gap leakage loss model of the adjustable guide vane with gap and rotation axis is as follows:

[0024] Where KZ is the correction coefficient, expressed as a bivariate polynomial function of the rotation axis diameter X and the rotation axis position Y:

[0025] Where X is the ratio of the diameter of the rotation axis to the axial chord length of the blade: X=D / L Where D is the diameter of the rotation axis, L is the axial chord length of the blade center, and Y is the rotation axis position parameter, expressed as a percentage of the position relative to the axial chord length of the blade center.

[0026] To achieve the above objectives, a second aspect of the present invention provides a correction device for an adjustable guide vane clearance leakage loss model, comprising: A blade tip data module was constructed for CFD experimental flow field data based on variable geometry turbines. A CFD flow field clearance loss database for adjustable guide vanes with blade tip clearance and no rotating shaft was constructed to obtain CFD flow field data with blade tip clearance and no rotating shaft. The blade tip fitting module is used to fit the established blade tip clearance loss model formula based on the obtained blade tip clearance CFD flow field data without rotating axis using machine learning methods. A blade root data module was constructed for CFD experimental flow field data based on variable geometry turbines. A CFD flow field clearance loss database for adjustable guide vanes with blade root clearance and no rotating shaft was constructed to obtain CFD flow field data with blade root clearance and no rotating shaft. The blade root fitting module is used to fit the established blade root clearance loss model formula based on the obtained blade root clearance CFD flow field data without rotating axis using machine learning methods. The superposition module is used to superimpose the obtained tip clearance loss model formula with the obtained root clearance loss model formula to establish the total clearance loss model formula for adjustable guide vanes without rotating shaft leakage. A rotating shaft data module is constructed for CFD experimental flow field data based on variable geometry turbines. A CFD flow field clearance loss database is constructed for adjustable guide vanes with both tip clearance and root clearance and a rotating shaft, so as to obtain CFD flow field data with clearance and a rotating shaft. The total clearance fitting module is used to fit the obtained CFD flow field data with gaps and a rotating shaft, based on the formula of the total clearance leakage loss model of the adjustable guide vane without a rotating shaft, using machine learning methods to obtain the clearance leakage loss model of the adjustable guide vane with gaps and a rotating shaft, and complete the modeling of the leakage loss prediction of the tip clearance of the adjustable guide vane.

[0027] To achieve the above objectives, a third aspect of this application provides a computer device comprising a processor and a memory; wherein the processor runs a program corresponding to the executable program code stored in the memory to implement the correction method for the adjustable guide vane clearance leakage loss model as described in the first aspect embodiment.

[0028] To achieve the above objectives, a fourth aspect of this application provides a non-transitory computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements a method for correcting the adjustable guide vane clearance leakage loss model as described in the first aspect embodiment.

[0029] The embodiments of the present invention have the following beneficial effects: by embedding the model into a one-dimensional performance prediction program, the accuracy and reliability of loss calculation can be effectively improved, thereby providing a more scientific and systematic theoretical basis and technical support for the aerodynamic optimization design and structural parameter matching of variable geometry turbines. Attached Figure Description

[0030] The above and / or additional aspects and advantages of the present invention will become apparent and readily understood from the following description of the embodiments taken in conjunction with the accompanying drawings, wherein: Figure 1 A flowchart illustrating a method for correcting an adjustable guide vane clearance leakage loss model, provided in an embodiment of the present invention; Figure 2 A logic diagram of the method for correcting the leakage loss model of the adjustable guide vane clearance of a variable geometry turbine provided by this invention; Figure 3 This is a comparison chart of the prediction results of the corrected gap loss model in this invention; Figure 4 This is a structural diagram of a correction device for an adjustable guide vane clearance leakage loss model provided in an embodiment of the present invention. Detailed Implementation

[0031] It should be noted that, unless otherwise specified, the embodiments and features described in the present invention can be combined with each other. The present invention will now be described in detail with reference to the accompanying drawings and embodiments.

[0032] To enable those skilled in the art to better understand the present invention, the technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings of the embodiments of the present invention. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort should fall within the scope of protection of the present invention.

[0033] The following describes, with reference to the accompanying drawings, a method and apparatus for correcting the adjustable guide vane clearance leakage loss model according to an embodiment of the present invention.

[0034] Example 1 This embodiment provides a method for correcting an adjustable guide vane clearance leakage loss model. For example... Figure 1-3 As shown, the method includes the following steps: S1: Based on the CFD experimental flow field data of the variable geometry turbine, a CFD flow field clearance loss database of the adjustable guide vane with tip clearance and no rotating shaft is constructed to obtain the CFD flow field data of tip clearance without rotating shaft.

[0035] In order to accurately separate the tip clearance leakage loss of the variable geometry turbine adjustable guide vane under the condition of clearance without shaft, and to provide key technical parameter support for turbine performance optimization and guide vane structure design, this application embodiment constructs a relevant clearance loss database based on the CFD experimental flow field data of the variable geometry turbine, and realizes the separate calculation of the leakage loss through calculation.

[0036] The variable geometry turbine CFD experimental flow field data used in the embodiments of this application were obtained by numerically simulating the working process of the variable geometry turbine using professional fluid dynamics simulation tools. The data covers the flow field parameters of the adjustable guide vanes under different operating conditions and different tip clearance sizes, providing accurate and comprehensive data support for the subsequent database construction.

[0037] In this embodiment, constructing the aforementioned CFD flow field gap loss database requires systematic organization, classification, and filtering of the CFD experimental flow field data to ensure that the data stored in the database accurately reflects the flow field characteristics and gap loss information of the adjustable guide vane under conditions of tip clearance and no rotating shaft. Through the construction of this database, this application provides a data query and retrieval basis for the subsequent accurate calculation of tip clearance leakage loss of the adjustable guide vane, improving the efficiency and accuracy of loss calculation.

[0038] Furthermore, in this embodiment of the application, the leakage loss of the adjustable guide vane tip clearance is calculated separately. The specific calculation method is as follows:

[0039] in, This represents the gap leakage loss in the case of adjustable guide vane tip clearance without shaft in the embodiments of this application. This represents the total loss in the case of adjustable guide vane tip clearance without shaft in the embodiments of this application. This represents the total loss in the case of no gap and no shaft at the tip of the adjustable guide vane in the embodiments of this application.

[0040] In this embodiment of the application, when calculating the leakage loss of the adjustable guide vane tip clearance using the above formula, and The values ​​are all derived from the CFD flow field clearance loss database constructed above, or obtained through targeted CFD experimental simulations of variable geometry turbines, ensuring the accuracy and matching of various parameters during the calculation process. This application, through this separate calculation method, can accurately isolate the losses caused by tip clearance leakage of adjustable guide vanes, eliminating the interference of other loss factors under clearanceless conditions, and providing key technical parameter support for the performance optimization of variable geometry turbines and the structural design of adjustable guide vanes.

[0041] It should be noted that, in the embodiments of this application, when constructing the CFD flow field clearance loss database, different variable parameters such as different tip clearance sizes, different incoming flow conditions, and different turbine speeds can be incorporated according to the needs of actual application scenarios, making the database more applicable; at the same time, in the calculation and In this case, multiple CFD numerical calculation methods can be used for cross-validation to further improve the reliability of the total loss data, thereby ensuring the final gap leakage loss is obtained. The calculation accuracy.

[0042] The clearance leakage loss calculation scheme provided in this application embodiment can be effectively applied to the relevant performance analysis scenarios of variable geometry turbine adjustable guide vanes, laying the foundation for subsequent fitting of the established blade tip clearance loss model formula.

[0043] S2: Based on the obtained CFD flow field data of the blade tip clearance without rotating shaft, the established blade tip clearance loss model formula is fitted using machine learning methods.

[0044] In order to obtain key parameters by fitting a tip clearance loss model based on the AMDCKO model modified by machine learning based on the CFD flow field data of the tip clearance without rotating shaft, and to accurately construct the tip clearance leakage loss calculation formula, so as to achieve accurate assessment of the leakage loss of the adjustable guide vane, the embodiments of this application clarify the model parameter definition, the associated calculation formula and the polynomial function setting.

[0045] This application aims to fit the tip clearance loss model formula to the obtained tip clearance CFD flow field data without rotating shaft using machine learning methods, thereby obtaining model parameters and forming Formula 1. In this application, the AMDCKO model uses the total pressure loss coefficient as the main indicator to measure leakage loss, clarifying the proportional relationship between the total pressure loss caused by clearance leakage and the inlet dynamic pressure. Its expression of the loss is as follows:

[0046] in, The average total pressure is the inlet mass flow rate. and These are the average total pressure and static pressure at the outlet plane mass flow rate, respectively. The average total pressure at a fixed blade height on the measuring plane.

[0047] In this embodiment of the application, the tip clearance leakage loss formula (Formula 1) defined based on the above-mentioned modified AMDCKO model is as follows:

[0048] Where c is the chord length, Here, H is the gap value, A is the leaf height, and n1, n2, and bias1 are unknown deviations that need to be obtained through machine learning. This application can accurately fit these unknown parameters through machine learning methods, ensuring the accuracy of the calculation in Formula 1.

[0049] In this embodiment, the parameter Z in Formula 1 is a constant related to the inlet and outlet airflow angle, calculated by the boundary conditions and the lag angle model. To simplify the calculation, this application assumes that Z is a known constant, and its specific calculation formula includes:

[0050]

[0051]

[0052] Where Z is the loading coefficient, The lift coefficient, The inlet airflow angle at the blade midsection. The outlet airflow angle at the mid-section of the blade. The average airflow angle at the blade midsection is given. In this embodiment, the value of parameter Z can be accurately derived through these related formulas, providing support for the complete construction of Formula 1.

[0053] Furthermore, in the tip clearance loss model of this application embodiment, the parameters A , n 1. n Both are considered to be about and The polynomial function of is roughly expressed in the following mathematical form:

[0054] in, f 1. g 1. h 1 represents polynomial functions of different orders and coefficients. In this embodiment, this setting can effectively reflect the nonlinear coupling relationship between variables, provide a flexible and reliable mathematical framework for fitting the loss model, and help improve the model's prediction accuracy for tip clearance leakage loss.

[0055] This application utilizes the above-mentioned technical solution to fit the parameters of the loss formula based on the modified AMDCKO model using machine learning. It fully leverages the accuracy of CFD flow field data and the nonlinear fitting capability of polynomial functions, enabling the constructed tip clearance loss model to more accurately describe the leakage loss characteristics.

[0056] In the embodiments of this application, the model not only has clear mathematical logic and explicit parameter definitions, but also can adapt to different structural parameters such as blade tip clearance, blade height, and chord length, as well as airflow conditions, laying the foundation for the subsequent construction of a CFD flow field gap loss database for adjustable guide vanes in the presence of blade root clearance and without a rotating shaft.

[0057] S3: Based on the CFD experimental flow field data of variable geometry turbine, construct a CFD flow field clearance loss database for adjustable guide vanes in the presence of blade root clearance and without a rotating shaft, and obtain CFD flow field data without rotating shaft at blade root clearance.

[0058] In order to accurately separate the blade root clearance leakage loss of the variable geometry turbine adjustable guide vane under the condition of blade root clearance without rotating shaft, and to provide key technical parameter support for turbine performance optimization and guide vane structure design, this application embodiment constructs a corresponding clearance loss database based on the CFD experimental flow field data of the variable geometry turbine, and realizes the separate calculation of the leakage loss through calculation.

[0059] This application provides a method for calculating leakage loss in the root clearance of an adjustable guide vane and a corresponding scheme for constructing a CFD flow field clearance loss database. In the embodiments of this application, firstly, based on the CFD experimental flow field data of a variable geometry turbine, a CFD flow field clearance loss database for an adjustable guide vane in the presence of root clearance and without a rotating shaft is specifically constructed.

[0060] In this embodiment, when constructing the aforementioned CFD flow field gap loss database, it is necessary to systematically screen, classify, and organize the collected CFD experimental flow field data to ensure that the data stored in the database can accurately reflect the flow field characteristics and gap loss information of the adjustable guide vane under conditions of blade root gap and no rotating shaft. Through the construction of this database, this application can provide efficient data query and retrieval support for the subsequent accurate calculation of leakage loss from the blade root gap of the adjustable guide vane, significantly improving the efficiency and reliability of loss calculation.

[0061] Furthermore, in this embodiment of the application, the leakage loss between the adjustable guide vane root and the guide vane is separately isolated through a specific calculation method. The specific calculation method is as follows:

[0062] in, This represents the gap leakage loss in the case of adjustable guide vane root with gap and no shaft in the embodiments of this application. This represents the total loss in the case where the adjustable guide vane root has a gap and no shaft, as described in the embodiments of this application. This represents the total loss in the case of no gap and no shaft at the root of the adjustable guide vane in the embodiments of this application.

[0063] It should be noted that, in the embodiments of this application, when constructing the CFD flow field clearance loss database, different variable parameters such as different blade root clearance sizes, different incoming flow conditions, and different turbine speeds can be flexibly incorporated according to the needs of actual application scenarios, further broadening the applicability of the database; at the same time, in obtaining and In numerical calculations, multiple CFD numerical methods can be used for cross-validation to improve the reliability of the total loss data, thereby ensuring the final obtained blade root clearance leakage loss. The calculation accuracy.

[0064] The clearance leakage loss calculation scheme provided in this application embodiment is effectively applicable to the relevant performance analysis scenarios of variable geometry turbine adjustable guide vanes, laying the foundation for subsequent fitting of the blade root clearance loss model formula.

[0065] S4: Based on the obtained CFD flow field data of the blade root clearance without rotating axis, the established blade root clearance loss model formula is fitted using machine learning methods.

[0066] To obtain key parameters by fitting a blade root clearance loss model based on the CFD flow field data without rotating shaft at the blade root clearance using machine learning, and to accurately construct the blade root clearance leakage loss calculation formula (Formula 2), thereby achieving an accurate assessment of the blade root leakage loss of the tunable guide vane.

[0067] This application provides a blade root clearance loss calculation scheme based on the modified AMDCKO clearance loss model. First, relying on the obtained blade root clearance CFD flow field data without rotating shaft, the established blade root clearance loss model formula is fitted using machine learning methods to obtain the blade root clearance loss model parameters, and finally form Formula 2.

[0068] Formula 2 in this application is also modified based on the AMDCKO gap loss model, and its specific expression is as follows:

[0069] in, For the leaf root clearance loss, in the formula B , m 1. m 2. bia s2 are all unknowns that need to be solved using machine learning methods. In this embodiment, the leaf root gap loss model formula is constructed using a typical polynomial format, which can better adapt to the complex relationships between variables and improve the model's fitting accuracy and generalization ability.

[0070] Specifically, in the blade root clearance loss model formula of this application embodiment, the parameters B , m 1. m 2 is explicitly regarded as concerning and The polynomial function of has the following general mathematical expression:

[0071] In the embodiments of this application, f 2. g 2. h2 represents polynomial functions of different orders and coefficients. These functions can accurately reflect the nonlinear coupling relationship between variables, providing a flexible and reliable mathematical framework for fitting the leaf root gap loss model.

[0072] In this embodiment, when fitting model parameters using machine learning methods, the sample information under different operating conditions and structural parameters contained in the blade root clearance CFD flow field data without rotating shaft is fully utilized to ensure that the obtained solution is accurate. B , m 1. m 2. bia s2 can accurately adapt to the actual variation of leaf root gap loss.

[0073] Through the above-mentioned technical design, this application enables Formula 2 to accurately describe the changing characteristics of leakage loss in the adjustable guide vane root gap. This model not only inherits the advantage of the AMDCKO gap loss model with the total pressure loss coefficient as the core indicator, but also further improves the adaptability to nonlinear loss laws through the combination of polynomial functions and machine learning.

[0074] It should be noted that, in the embodiments of this application, the blade root clearance CFD flow field data without rotating axis used to fit the model parameters must undergo strict screening and preprocessing to ensure the accuracy and completeness of the data; at the same time, the polynomial order of f2, g2, and h2 can be adjusted according to the needs of the actual application scenario to achieve the optimal balance between fitting accuracy and computational efficiency.

[0075] This application achieves accurate modeling of blade root clearance leakage loss through this model construction and parameter solving method, laying the foundation for the subsequent establishment of a model formula for leakage loss of total clearance of adjustable guide vanes without rotating shaft.

[0076] S5: Superimpose the fitted blade tip clearance loss model formula with the fitted blade root clearance loss model formula to establish an adjustable guide vane total clearance leakage loss model formula without rotating shaft.

[0077] In order to comprehensively and accurately evaluate the overall clearance leakage loss of the adjustable guide vane under the condition of no rotating shaft, and to provide a complete loss assessment basis for the performance optimization of variable geometry turbine and the design of guide vane structure, this application embodiment superimposes the blade tip clearance loss model formula obtained by SS2 and the blade root clearance loss model formula obtained by SS4 to establish the total clearance leakage loss model formula of the adjustable guide vane without rotating shaft (Formula 3).

[0078] In this embodiment of the application, the specific expression of formula 3 is:

[0079] in, This means that in the embodiments of this application, the total clearance of the adjustable guide vanes has no leakage loss from the rotating shaft. The adjustable guide vane tip clearance leakage loss is calculated using Formula 1. The leakage loss at the root gap of the adjustable guide vane is calculated using Formula 2.

[0080] In this embodiment, a superposition method is used to construct the total clearance leakage loss model because the tip clearance and root clearance of the adjustable guide vane generate independent leakage losses during actual operation. Both types of losses are key factors affecting the overall performance of the adjustable guide vane and even the variable geometry turbine. Directly superimposing these two types of losses comprehensively covers the total clearance leakage loss of the adjustable guide vane, avoiding the impact of overlooking losses at individual clearance locations on the overall evaluation results. This superposition modeling method allows Equation 3 to intuitively and accurately reflect the total clearance leakage loss of the adjustable guide vane under shaftless operating conditions, providing a complete loss assessment basis for subsequent performance analysis and structural optimization of the variable geometry turbine.

[0081] In this embodiment of the application, before performing the superposition calculation of Formula 1 and Formula 2, the calculation dimensions and parameter units of the two types of gap losses are strictly verified to ensure... and The calculation benchmark is consistent, avoiding deviations in the total loss calculation due to parameter mismatch. At the same time, Formula 3 constructed in this application inherits the advantages of Formula 1 and Formula 2, which can adapt to different blade tip and blade root clearance dimensions and accurately respond to changes in airflow characteristics under different operating conditions, thus possessing good adaptability and generalization ability.

[0082] In the embodiments of this application, the model not only has clear calculation logic and is easy to operate, but also ensures the accuracy of the total clearance leakage loss calculation results based on the accurate parameters fitted by the previous CFD flow field data and machine learning. It provides key technical support for the structural design improvement of adjustable guide vanes, clearance size optimization and the improvement of the operating efficiency of variable geometry turbines, and has important engineering application value.

[0083] It should be noted that, in the embodiments of this application, if leakage loss at other gap locations needs to be considered in subsequent practical applications, the calculation sub-items of corresponding gap loss can be further added based on the superposition modeling idea of ​​this application, making the total gap leakage loss model more widely applicable.

[0084] The superposition modeling method provided in this application lays the foundation for the subsequent construction of a CFD flow field gap loss database for adjustable guide vanes under the condition of simultaneous blade tip gap and blade root gap and rotation axis.

[0085] S6: Based on the CFD experimental flow field data of variable geometry turbine, construct a CFD flow field clearance loss database for adjustable guide vanes under the condition of simultaneous blade tip clearance and blade root clearance and rotation axis, and obtain CFD flow field data with clearance and rotation axis.

[0086] In order to accurately capture the gap leakage loss characteristics of adjustable guide vanes under the complex operating conditions of simultaneous tip clearance and root clearance and rotation shaft, and to provide comprehensive and accurate data support for subsequent loss calculation, model construction and parameter fitting under this condition, this application embodiment constructs a corresponding CFD flow field gap loss database based on the CFD experimental flow field data of variable geometry turbine.

[0087] In this embodiment of the application, when constructing the aforementioned CFD flow field clearance loss database, it is first necessary to perform systematic preprocessing operations on the collected variable geometry turbine CFD experimental flow field data, including data cleaning, outlier removal, and data standardization, to ensure the accuracy and completeness of the data. Subsequently, the preprocessed data stream is classified, archived, and stored according to key influencing factors such as blade tip clearance size, blade root clearance size, rotating shaft speed, and incoming flow conditions, so that the database can clearly present the flow field characteristics and clearance loss related information of the adjustable guide vane under different parameter combinations.

[0088] In this embodiment, the construction of the CFD flow field gap loss database fully considers the complex operating conditions of the adjustable guide vane in actual operation. There are dual gaps at the blade tip and root, and the rotating shaft is involved in the operation. The flow field characteristics under this condition are more complex than those under a single gap and no rotating shaft, and the factors affecting gap leakage loss are more diverse. By specifically constructing a database for this condition, this application can fill the gap in the prior art that is insufficient in supporting gap loss data under complex operating conditions.

[0089] In this embodiment, the database not only provides efficient data query and retrieval services for calculating clearance leakage losses of adjustable guide vanes under conditions of simultaneous tip and root clearances and rotating shaft operation, but also provides sufficient sample data for loss model construction and parameter fitting under such complex conditions, thereby improving the accuracy and reliability of loss assessment. Furthermore, this application can continuously expand the data dimensions and sample quantity in the database according to actual engineering needs, such as adding variable parameters like different blade materials and different airflow media, further broadening the database's applicability.

[0090] In summary, the CFD flow field gap loss database constructed in this application embodiment can accurately reflect the flow field characteristics related to gap leakage loss of adjustable guide vanes under complex working conditions, laying the foundation for obtaining a gap leakage loss model of adjustable guide vanes with gaps and a rotating shaft.

[0091] S7: Based on the obtained CFD flow field data with gaps and a rotating shaft, and using the formula of the total gap leakage loss model of the adjustable guide vane without a rotating shaft as a basis, a machine learning method is used for fitting to obtain the gap leakage loss model of the adjustable guide vane with gaps and a rotating shaft, thus completing the modeling of the leakage loss prediction of the adjustable guide vane tip gap.

[0092] In order to accurately assess the end leakage loss of the adjustable guide vane under the condition of simultaneous blade tip and blade root gap and rotating shaft, and to adapt to the actual operation scenario, this application embodiment introduces the rotating shaft correction coefficient KZ based on the corresponding CFD flow field data and Equation 3. KZ is defined as a bivariate polynomial function of the rotating shaft diameter and position. The gap leakage loss model formula (Equation 4) is constructed by fitting through machine learning.

[0093] In this application embodiment, to more accurately capture the influence of the rotating shaft on leakage loss, a rotating shaft correction coefficient is specifically introduced. The total clearance leakage loss under the condition without a rotating shaft is adjusted by this correction factor, so that the model can be adapted to the actual working condition of the rotating shaft.

[0094] The specific expression for Formula 4 is:

[0095] in, This represents the gap leakage loss in the case where the adjustable guide vane has a gap and a rotating shaft in the embodiments of this application. This is the correction factor for the rotation axis.

[0096] In the embodiments of this application, the correction coefficient can be considered as It is a function of the rotation axis diameter-related parameter X and the rotation axis position parameter Y, and its mathematical expression is:

[0097] To facilitate practical engineering applications and simplify the calculation process, the embodiments of this application typically include... K Z It is expressed as a bivariate polynomial in terms of the diameter-related parameter X of the rotation axis and the position parameter Y of the rotation axis. This form can flexibly reflect the nonlinear relationship between the two variables and the correction coefficient, while taking into account both computational efficiency and fitting accuracy.

[0098] In this embodiment, parameter X is the ratio of the diameter of the rotating shaft to the axial chord length of the blade, and its specific calculation formula is as follows: X = D / L Where D is the diameter of the rotating shaft and L is the axial chord length of the blade's center; the rotating shaft position parameter Y is expressed as a percentage of the axial chord length of the blade's center. For example, if the rotating shaft is located at 50% of the axial chord length of the blade's center, then Y = 0.5. This parameter definition method can intuitively and accurately describe the installation position of the rotating shaft on the blade, ensuring the parameter's universality and calculability.

[0099] In this embodiment of the application, during the process of fitting Equation 4 using machine learning methods, CFD flow field data with gaps and a rotation axis are used as samples. By adjusting the order and coefficients of the bivariate polynomial, the fitted result is obtained. It can accurately correct for the leakage loss caused by the rotating shaft, ensuring that the calculations in Formula 4 are accurate. It closely matches the gap leakage loss under actual working conditions.

[0100] Formula 4, constructed in this embodiment, inherits the comprehensive coverage advantage of Formula 3 in terms of blade tip and root gap loss, while also... The coefficients compensate for the influence of the rotation axis, enabling the model to more realistically reflect the actual operating state of the adjustable guide vane.

[0101] In the embodiments of this application, the model not only has clear mathematical logic and explicit parameter definitions, but also can adapt to different operating conditions such as different rotating shaft diameters and different rotating shaft positions. It provides key technical support for the performance optimization of variable geometry turbines and the matching design of adjustable guide vanes and rotating shafts, and has important engineering application value.

[0102] It should be noted that, in the embodiments of this application, fitting The order of the bivariate polynomial used can be adjusted according to actual needs to achieve a balance between fitting accuracy and computational complexity; at the same time, the CFD flow field data used for fitting must cover working condition samples under different combinations of X and Y parameters to ensure... The fitting results have good generalization ability.

[0103] This application achieves accurate modeling of leakage loss in adjustable guide vane clearance under rotating shaft conditions through the above technical solution, further improving the loss assessment system for variable geometry turbines.

[0104] Example 2 This invention also provides a correction device for an adjustable guide vane clearance leakage loss model, such as... Figure 4 As shown, the device includes: A blade tip data module 100 is constructed for CFD experimental flow field data based on variable geometry turbines. A CFD flow field clearance loss database for adjustable guide vanes with blade tip clearance and no rotating shaft is constructed to obtain CFD flow field data with blade tip clearance and no rotating shaft. The blade tip fitting module 200 is used to fit the established blade tip clearance loss model formula based on the obtained blade tip clearance CFD flow field data without rotating shaft using machine learning methods. A blade root data module 300 is constructed for CFD experimental flow field data based on variable geometry turbines. A CFD flow field clearance loss database for adjustable guide vanes with blade root clearance and no rotating shaft is constructed to obtain CFD flow field data with blade root clearance and no rotating shaft. The blade root fitting module 400 is used to fit the established blade root gap loss model formula based on the obtained blade root gap CFD flow field data without rotating axis using machine learning methods. The superposition module 500 is used to superimpose the fitted blade tip clearance loss model formula with the fitted blade root clearance loss model formula to establish an adjustable guide vane total clearance leakage loss model formula without rotating shaft. A rotating shaft data module 600 is constructed for CFD experimental flow field data based on variable geometry turbines. A CFD flow field clearance loss database is constructed for adjustable guide vanes with both tip clearance and root clearance and a rotating shaft, so as to obtain CFD flow field data with clearance and a rotating shaft. The total clearance fitting module 700 is used to fit the obtained CFD flow field data with gaps and a rotating shaft, based on the formula of the total clearance leakage loss model of the adjustable guide vane without rotating shaft, using machine learning methods to obtain the clearance leakage loss model of the adjustable guide vane with gaps and a rotating shaft, and complete the modeling of the leakage loss prediction of the tip clearance of the adjustable guide vane.

[0105] Example 3 To implement the methods of the above embodiments, the present invention also provides a computer device, which includes a memory and a processor; wherein the processor runs a program corresponding to the executable program code by reading executable program code stored in the memory, so as to implement the various steps of the methods described above.

[0106] Example 4 To implement the above embodiments, this application also proposes a non-transitory computer-readable storage medium storing a computer program thereon, which, when executed by a processor, implements the method described in the foregoing embodiments.

[0107] The above description is merely a preferred embodiment of the present invention and is not intended to limit the invention. Various modifications and variations can be made to the present invention by those skilled in the art. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of the present invention should be included within the scope of protection of the present invention.

[0108] In the description of this specification, the references to terms such as "one embodiment," "some embodiments," "example," "specific example," or "some examples," etc., refer to specific features, structures, materials, or characteristics described in connection with that embodiment or example, which are included in at least one embodiment or example of the present invention. In this specification, the illustrative expressions of the above terms do not necessarily refer to the same embodiment or example. Furthermore, the specific features, structures, materials, or characteristics described may be combined in any suitable manner in one or more embodiments or examples. Moreover, without contradiction, those skilled in the art can combine and integrate the different embodiments or examples described in this specification, as well as the features of different embodiments or examples.

[0109] Furthermore, the terms "first" and "second" are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of technical features indicated. Thus, a feature defined as "first" or "second" may explicitly or implicitly include at least one of that feature. In the description of this invention, "a plurality of" means at least two, such as two, three, etc., unless otherwise explicitly specified.

Claims

1. A modeling method for predicting leakage loss at the tip clearance of an adjustable guide vane, characterized in that, include: S1: Based on the CFD experimental flow field data of the variable geometry turbine, a CFD flow field clearance loss database of the adjustable guide vane with tip clearance and no rotating shaft is constructed to obtain the CFD flow field data without rotating shaft at the tip clearance. S2: Based on the obtained CFD flow field data of the blade tip clearance without rotating shaft, the established blade tip clearance loss model formula is fitted using machine learning methods; S3: Based on the CFD experimental flow field data of variable geometry turbine, construct a CFD flow field clearance loss database for adjustable guide vanes in the case of blade root clearance and no rotating shaft, and obtain CFD flow field data without rotating shaft at blade root clearance. S4: Based on the obtained CFD flow field data of the blade root clearance without rotating axis, the established blade root clearance loss model formula is fitted using machine learning methods. S5: Superimpose the fitted blade tip clearance loss model formula with the fitted blade root clearance loss model formula to establish an adjustable guide vane total clearance leakage loss model formula without rotating shaft. S6: Based on the CFD experimental flow field data of variable geometry turbine, construct a CFD flow field clearance loss database for adjustable guide vanes under the condition of simultaneous blade tip clearance and blade root clearance and rotation axis, and obtain CFD flow field data with clearance and rotation axis. S7: Based on the obtained CFD flow field data with gaps and a rotating shaft, and using the formula of the total gap leakage loss model of the adjustable guide vane without a rotating shaft as a basis, a machine learning method is used for fitting to obtain the gap leakage loss model of the adjustable guide vane with gaps and a rotating shaft, thus completing the modeling of the leakage loss prediction of the adjustable guide vane tip gap.

2. The method as described in claim 1, characterized in that, The CFD experimental flow field data based on the variable geometry turbine is used to construct a CFD flow field clearance loss database for adjustable guide vanes under conditions of tip clearance and no rotating shaft, obtaining CFD flow field data without rotating shaft at tip clearance, and also includes: The leakage loss at the tip clearance of the adjustable guide vane is calculated separately using the following method: in, This refers to the clearance leakage loss when there is clearance at the tip of the adjustable guide vane and no shaft. This represents the total loss when the adjustable guide vane has a gap at the tip and no shaft. This represents the total loss under the condition that the adjustable guide vane tip has no clearance and no shaft.

3. The method as described in claim 2, characterized in that, The method of fitting the established tip clearance loss model formula to the obtained tip clearance CFD flow field data without rotating shaft using machine learning methods also includes: The formula for the tip clearance loss model parameter is based on the modified AMDCKO clearance loss model. The AMDCKO model uses the total pressure loss coefficient as the main indicator to measure leakage loss and defines the ratio of the total pressure loss caused by clearance leakage to the intake dynamic pressure. The AMDCKO model expresses the loss in the following form: in, The average total pressure is the inlet mass flow rate. and The average total pressure and static pressure at the outlet plane mass flow rate. The average total pressure at a fixed blade height on the measuring plane; The formula for tip clearance leakage loss is defined as follows: Where c is the chord length, This is the gap value. For leaf height; in the formula A , n 1. n 2. The deviation is an unknown variable. A , n 1. n The polynomial function form of 2 includes different orders and coefficients to describe and The nonlinear coupling relationship between them, parameters It is a constant related to the angle of the inlet and outlet airflow.

4. The method as described in claim 3, characterized in that, The CFD experimental flow field data based on the variable geometry turbine is used to construct a CFD flow field clearance loss database for adjustable guide vanes under conditions of blade root clearance and no rotating shaft, obtaining CFD flow field data without rotating shaft at blade root clearance, and also includes: The leakage loss at the root gap of the adjustable guide vane is isolated and calculated as follows: in, This refers to the gap leakage loss when there is a gap at the blade root of the adjustable guide vane and no shaft. This represents the total loss under the condition that the adjustable guide vane has a gap at the blade root and no shaft. This represents the total loss under the condition that the adjustable guide vane root has no gap and no shaft.

5. The method as described in claim 4, characterized in that, The method of fitting the established blade root clearance loss model formula using machine learning methods based on the obtained blade root clearance CFD flow field data without rotating axis also includes: The formula for the parameters of the leaf root gap loss model is based on the modified AMDCKO gap loss model, and the expression is: in, For leaf root interstitial loss, B , m 1. m 2. bia s2 is an unknown, parameter B , m 1. m 2 is considered to be about and polynomial functions, B , m 1. m The polynomial function form of 2 includes different orders and coefficients to describe and The nonlinear coupling relationship between them can be expressed mathematically as follows: in, , , These represent polynomial functions of different orders and coefficients, respectively.

6. The method as described in claim 5, characterized in that, The formula for the total clearance loss model of the adjustable guide vane without rotating shaft leakage is as follows: in, The adjustable guide vane has no leakage loss due to the rotating shaft.

7. The method as described in claim 6, characterized in that, The formula for the leakage loss model of the adjustable guide vane with gap and rotating shaft is as follows: in, K Z The diameter of the rotating shaft is used as a correction factor. X Position of rotation axis Y The expression for a bivariate polynomial function: in, X The ratio of the diameter of the rotating shaft to the axial chord length of the blade: X = D / L in, D The diameter of the rotating shaft, L The axial chord length at the middle of the blade; Y The rotation axis position parameter is expressed as a percentage of the position relative to the axial chord length at the center of the blade.

8. A modeling device for predicting leakage loss at the tip clearance of an adjustable guide vane, characterized in that, include: A blade tip data module was constructed for CFD experimental flow field data based on variable geometry turbines. A CFD flow field clearance loss database for adjustable guide vanes with blade tip clearance and no rotating shaft was constructed to obtain CFD flow field data with blade tip clearance and no rotating shaft. The blade tip fitting module is used to fit the established blade tip clearance loss model formula based on the obtained blade tip clearance CFD flow field data without rotating axis using machine learning methods. A blade root data module was constructed for CFD experimental flow field data based on variable geometry turbines. A CFD flow field clearance loss database for adjustable guide vanes with blade root clearance and no rotating shaft was constructed to obtain CFD flow field data with blade root clearance and no rotating shaft. The blade root fitting module is used to fit the established blade root clearance loss model formula based on the obtained blade root clearance CFD flow field data without rotating axis using machine learning methods. The superposition module is used to superimpose the fitted blade tip clearance loss model formula with the fitted blade root clearance loss model formula to establish an adjustable guide vane total clearance leakage loss model formula without rotating shaft. A rotating shaft data module is constructed for CFD experimental flow field data based on variable geometry turbines. A CFD flow field clearance loss database is constructed for adjustable guide vanes with both tip clearance and root clearance and a rotating shaft, so as to obtain CFD flow field data with clearance and a rotating shaft. The total clearance fitting module is used to fit the obtained CFD flow field data with gaps and a rotating shaft, based on the formula of the total clearance leakage loss model of the adjustable guide vane without a rotating shaft, using machine learning methods to obtain the clearance leakage loss model of the adjustable guide vane with gaps and a rotating shaft, and complete the modeling of the leakage loss prediction of the tip clearance of the adjustable guide vane.

9. A computer device, characterized in that, Including processor and memory; The processor reads executable program code stored in the memory to run a program corresponding to the executable program code, so as to implement the correction method of the adjustable guide vane clearance leakage loss model as described in any one of claims 1-7.

10. A non-transitory computer-readable storage medium having a computer program stored thereon, characterized in that, When the program is executed by the processor, it implements the correction method for the adjustable guide vane clearance leakage loss model as described in any one of claims 1-7.

Images