A Design Method for a High-Efficiency New Configuration Single-Stage Turbine

Abstract

The present invention relates to a design method for a high-efficiency new configuration single-stage turbine, comprising the following steps: SS1. Define a bionic blade structure; SS2. Generate the wave characteristics of the bionic turbine blade; SS3. Align the original blade profile curve with the wave curve; SS4. Use a global optimization algorithm based on machine learning to optimize the wave curve to determine the specific design parameters of the guide vane and the moving blade, wherein the multi-objective function is set as the total pressure loss coefficient and the total efficiency at the outlet of the turbine cascade under different flow rates and rotational speeds. By using an asymmetric wave concave-convex structure imitating the whiskers of a seal at the blade mid-position to generate counter-rotating vortices to suppress flow separation, and using a more significant wave concave-convex structure at the end wall position than at the blade mid-position to suppress the development of secondary flow, the stage efficiency of the turbine stage is improved and the flow loss is reduced in a wide rotational speed range.

Description

Technical Field

[0001] The invention belongs to the technical field of aeroengine / gas turbine turbines, and relates to a design method for a high-efficiency new configuration single-stage turbine. Background Art

[0002] The turbine component is the main working component of an aeroengine and is usually arranged in the form of turbine stages in an aeroengine, that is, its basic structure is composed of a nozzle guide vane and a working wheel. During the actual working process, due to the changes in working conditions such as the takeoff and cruise of the aircraft, the turbine stage needs to operate at a wide range of flow rates and rotational speeds. The adjustment strategy of the new generation of variable cycle engines further expands the change range of the flow rate and rotational speed of the turbine stage. This will lead to changes in the velocity triangle of the turbine elementary stage, and further lead to problems such as flow separation, increased profile losses, and decreased turbine stage efficiency. Improving the flow rate adaptation range and stage efficiency is the key problem faced in the design of the turbine stage.

[0003] In nature, wavy structures exist on the surfaces similar to whale fins and seal whiskers. Relevant domestic and foreign research has confirmed that the wavy structure of seal whiskers can be approximately parameterized and described using a sine curve. Using a wavy bionic airfoil similar to a seal whisker has the effect of suppressing flow separation and changing the vortex street structure behind the cascade, and is an effective flow control method. However, there are great differences between the flow field environments where the physiological characteristics of animals in nature are located and the flow environment where turbine blades are located. Most of the methods for controlling blade flow by bionic means are only applied to local parts of the blade to specifically optimize specific blade performances. At present, there is still no bionic new configuration wide-adaptability turbine stage design method that can effectively improve the flow rate, loss, and efficiency.

[0004] Currently, the flow control methods for turbines can be divided into mid-span flow control means, such as blade surface roughness control, jet-type vortex exciters, suction surface ball-and-socket structures, etc., and end-wall region flow control means, such as non-axisymmetric walls, boundary layer suction, etc. For example, a high-load low-pressure turbine internal flow separation active regulation device disclosed in CN112594011A. In order to control the laminar separation occurring on the suction surface of the high-load low-pressure turbine blades, a suction surface separation control unit is provided, including a plurality of self-excited jet-type vortex exciters arranged in each turbine blade and a plurality of jet pipes corresponding to and communicating with the self-excited jet-type vortex exciters one by one. The plurality of self-excited jet-type vortex exciters are arranged along the blade span direction. The outlet of each jet pipe is correspondingly communicated with the inlet of a self-excited jet-type vortex exciter, and the inlet of each jet pipe is communicated with the outlet of a pressurization device in the end-wall boundary layer suction unit. The jet outlet of each self-excited jet-type vortex exciter is formed in the development region of the separation bubble 3 on the suction surface of the turbine blade, and the jet angle θ of the jet outlet should be set to be conducive to suppressing the boundary layer separation on the suction surface of the blade. However, methods such as these are only optimized for specific problems of turbine blades, and most of them take turbine blades as the research object, without comprehensive analysis of the turbine stage, and the design process of designing a wide-operating-condition airfoil by integrating these control methods is too complicated; in addition, the bionic airfoils with leading / trailing edge wavy airfoils are mainly used to control external flow noise, and the control effect on the internal flow of turbomachinery is very limited, and mainly for the flow control under the design condition, lacking an optimization design method, and the applicable operating condition range is relatively narrow. Summary of the Invention

[0005] To overcome the deficiencies of the above-mentioned prior art, the present invention provides a design method for an efficient new configuration single-stage turbine, specifically a design method for a new configuration turbine stage with wide rotational speed adaptability imitating the seal whisker airfoil. By using an asymmetric wavy concave-convex structure imitating seal whiskers at the mid-span position to generate counter-rotating vortices to suppress flow separation, and using a more significant wavy concave-convex structure than at the mid-span position at the end-wall position to suppress the development of secondary flow, so as to improve the stage efficiency and reduce flow losses of the turbine stage in a wide rotational speed range.

[0006] The technical solution adopted by the present invention to solve its technical problems is as follows:

[0007] The present invention provides a design method for an efficient new configuration single-stage turbine, including the following steps:

[0008] SS1. Define the bionic blade structure, the bionic blade structure includes a seal whisker bionic turbine blade, and the pitch and amplitude of the wave characteristics of the bionic turbine blade are larger at the position near the end region than at the mid-span position, and the leading edge curve and the trailing edge curve of the new configuration blade used are independent of each other, and the amplitude and frequency of the two curves do not affect each other;

[0009] SS2. Generate the wavy features of the bionic turbine blade, including the following steps:

[0010] SS21. Define the leading-edge and trailing-edge wavy curves through trigonometric curves, and the expression of the wavy curve is:

[0011]

[0012] where t is the independent variable that can determine the spanwise position of the airfoil section, A(t) is the curve amplitude, is the initial phase of the curve, and p(t) is the curve frequency;

[0013] SS22. Adjust A(t) and p(t) to obtain a larger amplitude and pitch at the blade tip region position;

[0014] SS23. Adjust to obtain a larger axial chord length at the blade tip region position;

[0015] SS3. Align the original airfoil curve with the wavy curve, including the following steps:

[0016] SS31. Align the leading edge of the original airfoil curve with the leading-edge wavy curve, or align the trailing edge of the original airfoil curve with the trailing-edge wavy curve;

[0017] SS32. Adjust the airfoil control points so that the adjusted trailing edge of the airfoil is aligned with the trailing-edge wavy curve, or the adjusted leading edge of the airfoil is aligned with the leading-edge wavy curve, where the adjustment distance from the control point to the mean camber line of the airfoil is linear in the axial direction;

[0018] SS4. Optimize the wavy curve using a machine learning-based global optimization algorithm to determine the specific design parameters of the guide vane and the moving blade, where the multi-objective function is set as the total pressure loss coefficient and the total efficiency at the outlet of the turbine cascade under different flow rates and rotational speeds;

[0019] where the expression of the total pressure loss coefficient is:

[0020]

[0021] where P 01，T , P 01，S , P 02，T correspond to the average values of the total pressure, static pressure at the mid-section of the moving blade inlet, and the total pressure at 1.4 times the axial chord length at the outlet of the cascade;

[0022] The expression of the total efficiency is:

[0023]

[0024] where T 00 , T 02Corresponding to the inlet temperature of the guide vane and the outlet temperature of the moving blade, P 00 , P 02 Corresponding to the inlet pressure of the guide vane and the outlet pressure of the moving blade, and γ is the specific heat ratio of the working fluid.

[0025] Preferably, in step S3, the control points include but are not limited to the leading edge point, the trailing edge point, and the maximum thickness point of the blade.

[0026] Preferably, in step SS4, the global optimization algorithm of machine learning is used to optimize the wavy curve of the turbine blade, including the following steps:

[0027] SS41. Data collection and preprocessing: Collect turbine blade performance data from historical experiments and CFD simulations, including the total pressure loss coefficient and total efficiency under different wavy curve parameters. Through means such as cleaning, normalization, and noise removal, ensure the quality and consistency of the data;

[0028] SS42. Feature selection: On the basis of data preprocessing, determine the key features affecting turbine performance, including the amplitude, frequency, initial phase of the wavy curve, and the geometric parameters of the blade; at the same time, consider the operating conditions features such as flow rate, rotational speed, inlet temperature, and pressure to ensure that the optimization model can comprehensively reflect the performance changes under different operating conditions;

[0029] SS43. Model selection and training: Select the multi-objective genetic algorithm (MOGA) as the optimization algorithm, and use the preprocessed data to train the multi-objective genetic algorithm (MOGA) to establish a machine learning model that can predict the turbine performance under different wavy curve parameters;

[0030] SS44. Define the optimization objectives: Define two optimization objectives in the multi-objective genetic algorithm (MOGA): minimize the total pressure loss coefficient and maximize the total efficiency; at the same time, set the corresponding constraint conditions to ensure the physical feasibility and manufacturing constraints of the wavy curve;

[0031] SS45. Optimization algorithm configuration: Configure the parameters of the multi-objective genetic algorithm (MOGA), including population size, crossover rate, mutation rate, and number of iterations, etc., and design a comprehensive fitness function to evaluate the performance of individuals in each iteration;

[0032] SS46. Optimization iteration: In the predefined search space, the multi-objective genetic algorithm (MOGA) continuously searches for the optimal wavy curve parameters through iteration; after each iteration, update the optimal solution according to the fitness evaluation, and gradually approach the global optimum;

[0033] SS47. Result analysis and verification: After the optimization is completed, the optimal wave curve parameters provided by the multi-objective genetic algorithm (MOGA) are analyzed in detail and verified using independent data sets or CFD simulations to ensure the reliability and effectiveness of the optimization results;

[0034] SS48. Design iteration and adjustment: According to the optimization results, adjust the wave curve design and perform multiple rounds of design iterations until the expected performance indicators are achieved.

[0035] Preferably, it further includes a blade cooling design step to improve the performance and durability of the blade in a high temperature environment; specifically, it includes adopting an internal cooling channel design to use airflow to circulate inside the blade to reduce the blade surface temperature; and optimizing the distribution of the cooling airflow to achieve efficient heat exchange and minimize the impact on the aerodynamic performance of the blade.

[0036] The advantages of the present invention compared with the prior art are as follows:

[0037] (1) The present invention can effectively break up the wake vortex structure and reduce flow separation by using the wave characteristics of bionic blades at the trailing edge of the guide vane and the leading edge of the moving blade of the turbine stage, thereby improving flow stability. This design is particularly helpful in maintaining the suitability of the moving blade inlet angle of attack when the flow rate and speed change, reducing flow losses, and thus improving the overall efficiency of the turbine stage.

[0038] (2) The wave characteristics of the bionic blades generate counter-rotating vortex structures on the suction surface of the moving blades, which significantly accelerates the momentum exchange between the boundary layer and the mainstream. This enhanced momentum exchange helps to improve the overall performance of the turbine stage, especially under high load or variable operating conditions, and can maintain a high energy conversion efficiency.

[0039] (3) The present invention reduces the number of key parameters that need to be considered in the design and simplifies the design process by clearly defining the leading edge and trailing edge curves. Compared with the traditional flow control method, this simplification not only reduces the design complexity, but also makes the solution of the optimal design parameters more efficient and accurate through the application of intelligent algorithms.

[0040] (4) By using a global optimization algorithm based on machine learning, the present invention realizes the intelligent and automated design of turbine stages, greatly improving R&D efficiency. This intelligent design method not only shortens the design cycle, but also ensures optimal performance under different operating conditions through multi-objective optimization. BRIEF DESCRIPTION OF THE DRAWINGS

[0041] Figure 1 The present invention is a flow chart of a method for designing a high-efficiency new-configuration single-stage turbine.

[0042] Figure 2Schematic diagram of the turbine region of a high-efficiency new configuration single-stage turbine design method of the present invention.

[0043] Figure 3 Schematic diagram of the turbine control points of a high-efficiency new configuration single-stage turbine design method of the present invention.

[0044] Figure 4 Schematic diagram of a turbine of a high-efficiency new configuration single-stage turbine design method of the present invention.

[0045] Figure 5 Schematic diagram of a turbine of a high-efficiency new configuration single-stage turbine design method of the present invention. Detailed implementation manners

[0046] To make the purpose, technical solutions and advantages of the implementation of the present invention clearer, the technical solutions in the embodiments of the present invention will be described in more detail below with reference to the accompanying drawings in the embodiments of the present invention. In the drawings, the same or similar reference numerals denote the same or similar elements or elements having the same or similar functions throughout. The described embodiments are some, but not all, of the embodiments of the present invention. The embodiments described below by referring to the drawings are exemplary and are intended to explain the present invention and should not be construed as limiting the present invention. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present invention without making creative efforts fall within the scope of protection of the present invention. The structure and technical solutions of the present invention will be further specifically described below with reference to the drawings, and an embodiment of the present invention is given.

[0047] A high-efficiency new configuration single-stage turbine design method of the present invention uses a biomimetic blade structure to improve the flow loss and efficiency of the turbine stage in a wide flow rate and rotational speed range. Among them, the guide vane or moving blade of the turbine stage uses a biomimetic turbine blade with seal whiskers, and the pitch and amplitude of the wave characteristics of the biomimetic turbine blade are larger at the pitch and amplitude near the end region than those at the middle of the blade, and the leading edge curve and trailing edge curve of the new configuration blade used are independent of each other, and the amplitude and frequency of the two curves do not affect each other; the airfoil of the biomimetic turbine blade is adjusted in the spanwise direction according to the axial chord length determined by the leading edge / trailing edge curve, and is determined by adjusting the airfoil control points.

[0048] For the described biomimetic turbine stage, the generation process of the wave characteristics of the blade is as follows:

[0049] First, the leading edge and trailing edge wave curves are defined by trigonometric function curves, and the expression of the wave curve is:

[0050]

[0051] where t is an independent variable that can determine the spanwise position of the airfoil section, A(t) is the curve amplitude, is the initial phase of the curve, and p(t) is the curve frequency. In the spanwise direction, by adjusting A(t) and p(t), the leading and trailing edge wave curves can have a larger amplitude and pitch at the proximal region. By adjusting the airfoil can have a larger axial chord length at the proximal region;

[0052] After the leading edge and trailing edge curves are fixed, align the leading edge of the original airfoil curve with the leading edge curve (or align the trailing edge of the original airfoil curve with the trailing edge curve);

[0053] By adjusting the airfoil control points, align the trailing edge of the adjusted airfoil with the trailing edge curve (or align the leading edge of the adjusted airfoil with the leading edge curve). During the adjustment process, the adjustment distance from the control point to the mean camber line of the airfoil is linear in the axial direction.

[0054] For the bionic turbine stage described, its specific design parameters are optimized by a global optimization algorithm based on machine learning for the wave curve

[0055]

[0056] to determine the specific design parameters of the guide vane and rotor blade. The multi-objective function is set as the total pressure loss coefficient and total efficiency at the outlet of the turbine cascade under different flow rates and rotational speeds.

[0057] The expression of the total pressure loss coefficient is:

[0058]

[0059] where P 01，T , P 01，S , P 02，T correspond to the total pressure, static pressure at the mid-section of the rotor blade inlet, and the average value of the total pressure at 1.4 times the axial chord length at the outlet of the cascade, respectively.

[0060] The total pressure loss coefficient Y total is a key performance evaluation index in the design of turbine blades. It is based on the concept of total pressure in fluid mechanics and quantifies the loss of fluid energy by comparing the total pressure differences at the inlet and outlet of the turbine blade. The design principle of this coefficient is based on the energy dissipation caused by factors such as viscosity and flow separation when the fluid flows through the turbine blade. The denominator P 01,T - P 01,SAs a benchmark, it reflects the dynamic energy level of the fluid at the inlet. By minimizing the total pressure loss coefficient, optimizing the blade design, reducing energy losses, and improving the overall efficiency of the turbine. The measurement point is selected at 1.4 times the axial chord length because at this position, the fluid flow has fully developed and can better reflect the influence of the blade on the flow. In the local area near the blade outlet, the flow may be affected by factors such as blade surface roughness and blade edge shape, resulting in inconsistent local flow characteristics with the overall flow characteristics. By taking the average value at 1.4 times the axial chord length, the influence of these local effects on the evaluation results can be reduced. The average total pressure at this position can represent the overall state of the flow at the blade outlet. It comprehensively takes into account the work done by the blade on the fluid and the influence of flow phenomena such as flow separation and secondary flow, providing a comprehensive index for evaluating blade performance. In addition, the evaluation of this coefficient helps to understand the influence of flow characteristics on blade performance under different operating conditions, thereby guiding the improvement of blade shape and structure. During the design process, machine learning optimization algorithms are used to intelligently find the optimal design parameters, improve the R & D efficiency, shorten the design cycle, reduce the maintenance cost of the turbine, and extend its service life.

[0061] The expression for the overall efficiency is:

[0062]

[0063] Where T 00 , T 02 correspond to the temperatures at the inlet of the guide vane and the outlet of the moving blade, and P 00 , P 02 correspond to the pressures at the inlet of the guide vane and the outlet of the moving blade, and γ is the specific heat ratio of the working fluid. This expression involves several key thermodynamic parameters, including temperature, pressure, and the specific heat ratio γ, which together determine the efficiency of the turbine in converting thermal energy into mechanical energy.

[0064] In the working principle of the turbine, high-temperature and high-pressure gas enters the turbine through the guide vane, then expands and does work, pushing the moving blade to rotate, thereby converting thermal energy into mechanical energy. During this process, the temperature and pressure of the gas will change. The temperature T 00 and pressure P 00 at the inlet of the guide vane represent the initial state of the gas entering the turbine, while the temperature T 02 and pressure P 02 at the outlet of the moving blade reflect the state of the gas after passing through the turbine. In the calculation formula of the overall efficiency, the numerator T 00 -T 02 represents the decrease in the temperature of the gas after passing through the turbine, which reflects the heat released by the gas, that is, the energy obtained by the turbine from the gas. The T 00 in the denominator represents the total thermal energy of the gas in the initial state, and It takes into account the entropy increase caused by the pressure drop and the energy loss of the irreversible process. Here, γ is the specific heat ratio of the working fluid, a parameter characterizing the thermodynamic properties of the gas, which can have different values at different temperatures and pressures. The term in the denominator of this expression is an embodiment of the second law of thermodynamics, that is, in a closed system, the spontaneous process will lead to an increase in entropy. In a turbine, due to the expansion and flow of the gas, entropy increase will inevitably occur, which will cause a part of the energy to be dissipated in the form of heat rather than being converted into mechanical energy. Therefore, this term reflects the energy loss caused by irreversible factors in the actual operation of the turbine. Through this expression of the overall efficiency, the design and operation efficiency of the turbine are quantitatively evaluated, so as to optimize the design of the blades. The optimization goal is to maximize η total , that is, under the given inlet temperature and pressure, extract as much energy as possible from the gas while reducing the energy loss caused by the irreversible process.

[0065] Specifically, the global optimization algorithm of machine learning is used to optimize the wave curve of the turbine blade to improve the efficiency of the turbine stage in a wide speed range and reduce the flow loss, including the following steps:

[0066] SS41. Data collection and preprocessing: Collect turbine blade performance data from historical experiments, CFD simulations and public research, including the total pressure loss coefficient and the overall efficiency under different wave curve parameters. By means of cleaning, normalization and noise removal, the quality and consistency of the data are ensured, laying a solid foundation for the subsequent training of the machine learning model.

[0067] SS42. Feature selection: On the basis of data preprocessing, determine the key features affecting the turbine performance, including the amplitude, frequency, initial phase of the wave curve and the geometric parameters of the blade. At the same time, consider the operating conditions such as flow rate, rotational speed, inlet temperature and pressure to ensure that the optimization model can comprehensively reflect the performance changes under different operating conditions.

[0068] SS43. Model selection and training: Select the multi-objective genetic algorithm (MOGA) as the optimization algorithm, and use the preprocessed data to train MOGA to establish a machine learning model that can predict the turbine performance under different wave curve parameters.

[0069] SS44. Define the optimization goal: Define two optimization goals in the multi-objective genetic algorithm (MOGA): minimize the total pressure loss coefficient and maximize the overall efficiency. At the same time, set the corresponding constraint conditions to ensure the physical feasibility and manufacturing constraints of the wave curve.

[0070] SS45.Optimization Algorithm Configuration: Configure the parameters of the Multi-Objective Genetic Algorithm (MOGA), including population size, crossover rate, mutation rate, and number of iterations, to ensure that the algorithm can effectively search for the optimal solution in a complex search space. Design a comprehensive fitness function to evaluate the performance of individuals in each iteration.

[0071] SS46. Optimization iteration: In the predefined search space, the multi-objective genetic algorithm (MOGA) continuously searches for the optimal wave curve parameters through iteration. After each iteration, the optimal solution is updated according to the fitness evaluation, gradually approaching the global optimum.

[0072] SS47. Result analysis and verification: After the optimization is completed, the optimal wave curve parameters provided by the multi-objective genetic algorithm (MOGA) are analyzed in detail and verified using independent data sets or CFD simulations to ensure the reliability and effectiveness of the optimization results.

[0073] SS48. Design iteration and adjustment: According to the optimization results, adjust the wave curve design and perform multiple rounds of design iterations until the expected performance indicators are achieved. This process improves design efficiency and obtains the best blade shape that meets the design requirements through continuous iterative optimization.

[0074] The optimized blade design shows lower flow losses and higher efficiency over a wide speed range, meeting the design requirements of a high-efficiency new-configuration single-stage turbine, significantly improving design efficiency and reducing R&D costs.

[0075] It also further includes a blade cooling design step to improve the performance and durability of the blade in a high temperature environment; specifically, it includes adopting an internal cooling channel design to use airflow to circulate inside the blade to reduce the blade surface temperature; and optimizing the distribution of the cooling airflow to achieve efficient heat exchange and minimize the impact on the aerodynamic performance of the blade.

[0076] The advantages of the present invention compared with the prior art are as follows:

[0077] (1) The present invention can effectively break up the wake vortex structure and reduce flow separation by using the wave characteristics of bionic blades at the trailing edge of the guide vane and the leading edge of the moving blade of the turbine stage, thereby improving flow stability. This design is particularly helpful in maintaining the suitability of the moving blade inlet angle of attack when the flow rate and speed change, reducing flow losses, and thus improving the overall efficiency of the turbine stage.

[0078] (2) The wave characteristics of the bionic blades generate counter-rotating vortex structures on the suction surface of the moving blades, which significantly accelerates the momentum exchange between the boundary layer and the mainstream. This enhanced momentum exchange helps to improve the overall performance of the turbine stage, especially under high load or variable operating conditions, and can maintain a high energy conversion efficiency.

[0079] (3) By clearly defining the leading edge and trailing edge curves, the present invention reduces the number of key parameters to be considered in the design, simplifying the design process. Compared with traditional flow control methods, this simplification not only reduces the design complexity, but also, through the application of intelligent algorithms, makes the solution of the optimal design parameters more efficient and accurate.

[0080] (4) By using a global optimization algorithm based on machine learning, the present invention realizes the intelligentization and automation of turbine stage design, greatly improving the R & D efficiency. This intelligent design method not only shortens the design cycle, but also, through multi-objective optimization, ensures optimal performance under different working conditions.

[0081] Through the above embodiments, the object of the present invention is completely and effectively achieved. Those skilled in the art can understand that the present invention includes but is not limited to the content described in the drawings and the above specific embodiments. Although the present invention has been described with respect to the currently considered most practical and preferred embodiments, it should be understood that the present invention is not limited to the disclosed embodiments, and any modification that does not deviate from the functional and structural principles of the present invention will be included in the scope of the claims.

Claims

1. A method for designing a high-efficiency new-configuration single-stage turbine, characterized in that: The following steps are involved: SS1. Define the bionic blade structure. The pitch and amplitude of the wave characteristics of the bionic turbine blade near the end area are larger than those in the middle of the blade. The leading edge curve and the trailing edge curve of the new configuration blade used are independent of each other, and the amplitude and frequency of the two curves will not affect each other. SS2. Generate the wave characteristics of the bionic turbine blade, including the following steps: SS21. The leading edge and trailing edge wave curves are defined by trigonometric function curves. The expression of the wave curve is: Where t is the independent variable that can determine the spanwise position of the blade section, A(t) is the curve amplitude, is the initial phase of the curve, p(t) is the frequency of the curve; SS22. Adjust A(t) and p(t) to obtain a larger amplitude and pitch at the blade tip; SS23. Adjustment To obtain a larger axial chord length at the blade tip; SS3. Align the original blade curve with the wave curve, including the following steps: SS31. Align the leading edge of the original blade profile curve with the leading edge wave curve, or align the trailing edge of the original blade profile curve with the trailing edge wave curve; SS32. Adjust the blade control point so that the adjusted blade trailing edge is aligned with the trailing edge wave curve, or the adjusted blade leading edge is aligned with the leading edge wave curve, wherein the adjustment distance from the control point to the blade mid-arc is linear in the axial direction; SS4. Use a global optimization algorithm based on machine learning to optimize the wave curve to determine the specific design parameters of the guide vanes and moving blades, where the multi-objective function is set as the total pressure loss coefficient and total efficiency at the turbine cascade outlet under different flow rates and speeds; The expression of the total pressure loss coefficient is: Where P 01，T , P 01，S , P 02，T The total pressure and static pressure at the middle section of the corresponding moving blade inlet and the average total pressure at 1.4 times the axial chord length of the blade cascade outlet; The expression of overall efficiency is: Where T 00 ,T 02 Corresponding to the guide vane inlet and moving blade outlet temperature, P 00 ,P 02 Corresponding to the guide vane inlet and moving blade outlet pressure, γ is the specific heat ratio of the working fluid.

2. A high-efficiency new-configuration single-stage turbine design method according to claim 1, characterized in that: In step SS4, the wave curve of the turbine blade is optimized using a global optimization algorithm based on machine learning, including the following steps: SS41. Data collection and preprocessing: Collect turbine blade performance data from historical experiments and CFD simulations, including total pressure loss coefficient and total efficiency under different wave curve parameters, and ensure data quality and consistency through cleaning, normalization and noise removal; SS42. Feature selection: Based on data preprocessing, key features that affect turbine performance are determined, including the amplitude, frequency, initial phase of the wave curve and the geometric parameters of the blades; at the same time, flow, speed, inlet temperature and pressure operating conditions are considered to ensure that the optimization model can fully reflect the performance changes under different operating conditions; SS43. Model selection and training: Select the multi-objective genetic algorithm (MOGA) as the optimization algorithm and use the preprocessed data to train the multi-objective genetic algorithm (MOGA) to establish a machine learning model that can predict the turbine performance under different wave curve parameters; SS44. Define optimization objectives: Define two optimization objectives in the multi-objective genetic algorithm (MOGA): minimize the total pressure loss coefficient and maximize the total efficiency; at the same time, set corresponding constraints to ensure the physical feasibility and manufacturing constraints of the wave curve; SS45.Optimization Algorithm Configuration: Configure the parameters of the Multi-Objective Genetic Algorithm (MOGA), including population size, crossover rate, mutation rate, and number of iterations, and design a comprehensive fitness function to evaluate the performance of individuals in each iteration; SS46. Optimization iteration: In the predefined search space, the multi-objective genetic algorithm (MOGA) continuously searches for the optimal wave curve parameters through iterations; after each iteration, the optimal solution is updated according to the fitness evaluation, gradually approaching the global optimum; SS47. Result analysis and verification: After the optimization is completed, the optimal wave curve parameters provided by MOGA are analyzed in detail and verified using independent data sets or CFD simulations to ensure the reliability and effectiveness of the optimization results; SS48. Design iteration and adjustment: According to the optimization results, adjust the wave curve design and perform multiple rounds of design iterations until the expected performance indicators are achieved.

3. A high-efficiency new-configuration single-stage turbine design method according to claim 2, characterized in that: In step S3, the control points include but are not limited to the leading edge point, the trailing edge point and the maximum thickness point of the blade.

4. A high-efficiency new-configuration single-stage turbine design method according to claim 3, characterized in that: In step S1, the bionic blade structure includes a seal whisker bionic turbine blade.

5. A high-efficiency new-configuration single-stage turbine design method according to claim 4, characterized in that: It also further includes a blade cooling design step to improve the performance and durability of the blade in a high temperature environment; specifically, it includes adopting an internal cooling channel design to use airflow to circulate inside the blade to reduce the blade surface temperature; and optimizing the distribution of the cooling airflow to achieve efficient heat exchange and minimize the impact on the aerodynamic performance of the blade.

Images