Flywheel energy storage rotor topology optimization method and system

Abstract

The present application relates to the technical field of flywheel energy storage system, and particularly relates to a flywheel energy storage rotor topology optimization method and system. Finite element analysis software is used to simulate and analyze the initial shape of the rotor, obtain stress distribution data, set a stress threshold according to the stress distribution data, identify a smaller stress area in the rotor, and mark the optimizable area; in the optimizable area, the SwinTransformer algorithm is optimized based on SDEA to design a hollow parameter, and the rotor structure is optimized; the performance of the optimized rotor structure is verified, and optimization effect data is obtained. A unified coding method is used to represent the hollow parameter, a comprehensive fitness function including structural strength, mass reduction and process realizability is established, and through balanced optimization under multi-objective constraints, the rotor mass is significantly reduced, the stress distribution is significantly improved, and the ultimate speed and energy storage density are significantly improved. The present application effectively solves the problems of large rotor mass, heavy magnetic bearing burden and stress concentration in traditional uniform disc design.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of flywheel energy storage systems, and in particular to a flywheel energy storage rotor topology optimization method and system. BACKGROUND

[0002] At present, the rotor of a flywheel energy storage system usually adopts a uniform disc design. This design scheme is mature in technology and simple in process, but has many limitations, such as: large rotor mass: the uniform design increases the overall mass of the flywheel rotor, which limits the energy storage density of the system, making it difficult to meet some application scenarios with high requirements for energy storage density. Heavy burden on magnetic bearings: the large rotor mass increases the bearing pressure of the magnetic bearings, accordingly requiring higher bearing performance, thereby increasing the complexity of system design and maintenance, increasing the cost and being not conducive to stable operation of the system. Stress concentration: at high speed rotation, the uniform disc design causes stress concentration in a specific area of the rotor, resulting in a large maximum stress of the rotor, increasing the failure risk, and severely limiting the maximum speed of the system, hindering the further improvement of the performance of the flywheel energy storage system. In summary, these factors of the existing uniform disc design jointly restrict the performance improvement of the flywheel energy storage system in terms of high speed, high energy storage density, and manufacturing and maintenance cost, and it is necessary to propose a new rotor design scheme to overcome these limitations. SUMMARY

[0003] In view of the problems existing in the prior art, the present application is proposed.

[0004] Therefore, the problem to be solved by the present application is how to overcome the limitations of the existing uniform disc design, such as: large rotor mass: the uniform design increases the overall mass of the flywheel rotor, which limits the energy storage density of the system, making it difficult to meet some application scenarios with high requirements for energy storage density. Heavy burden on magnetic bearings: the large rotor mass increases the bearing pressure of the magnetic bearings, accordingly requiring higher bearing performance, thereby increasing the complexity of system design and maintenance, increasing the cost and being not conducive to stable operation of the system. Stress concentration: at high speed rotation, the uniform disc design causes stress concentration in a specific area of the rotor, resulting in a large maximum stress of the rotor, increasing the failure risk, and severely limiting the maximum speed of the system, hindering the further improvement of the performance of the flywheel energy storage system. In summary, these factors of the existing uniform disc design jointly restrict the performance improvement of the flywheel energy storage system in terms of high speed, high energy storage density, and manufacturing and maintenance cost, and it is necessary to propose a new rotor design scheme to overcome these limitations.

[0005] To solve the above technical problems, the present application provides the following technical scheme:

[0006] In a first aspect, the embodiments of the present application provide a flywheel energy storage rotor topology optimization method, which comprises simulating and analyzing an initial shape of a rotor by using a finite element analysis software to obtain rotor stress distribution data;

[0007] According to the stress distribution data, a region with small internal stress of the rotor is identified, and a stress threshold is set to mark an optimizable region;

[0008] In the optimizable region, the SwinTransformer algorithm design hole parameters are optimized based on SDEA, and the rotor structure is optimized;

[0009] The performance of the optimized rotor structure is verified, and optimization effect data is obtained.

[0010] As a preferred scheme of the flywheel energy storage rotor topology optimization method, the finite element analysis software is used to simulate and analyze the initial shape of the rotor, including setting the material parameters of the rotor, including density and Poisson's ratio; establishing a geometric model of the rotor and performing mesh division; applying axial and radial displacement constraints; setting the rotating speed working condition; calculating the stress distribution of each region of the rotor under the set working condition.

[0011] As a preferred scheme of the flywheel energy storage rotor topology optimization method, the identification of the region with small internal stress of the rotor includes: setting a stress threshold σ0; extracting the radial stress σr and the tangential stress σt of each node of the rotor; calculating the comprehensive stress σ of the node σ = max(σr, σt); when the comprehensive stress σ of the node σ is less than the stress threshold σ0, the region where the node is located is marked as an optimizable region. r θ i r,i θ,i i

[0012] As a preferred scheme of the flywheel energy storage rotor topology optimization method, the optimization of the SwinTransformer algorithm design hole parameters based on SDEA includes: using a unified coding method to represent the hole parameters; establishing a comprehensive fitness function including structural strength, mass reduction and process realizability; using the SwinTransformer model to predict the hole fitness value; and optimizing and iterating the model parameters through the SDEA algorithm.

[0013] As a preferred scheme of the flywheel energy storage rotor topology optimization method, the unified coding method of the hole parameters includes: a circular hole is represented by a vector [x, y, r, 0], where (x, y) is the center coordinate, r is the radius, and 0 represents a circle; a square hole is represented by a vector [x, y, a, θ, 1], where (x, y) is the center coordinate, a is the side length, θ is the rotation angle, and 1 represents a square.

[0014] ​​​​​​As a preferred scheme of the flywheel energy storage rotor topology optimization method, the comprehensive fitness function comprises a structural strength fitness function f1 for evaluating stress distribution under the cavity configuration, a mass reduction fitness function f2 for evaluating material removal effect, and a process realizability fitness function f3 for evaluating the realizability of the cavity parameters.

[0015] As a preferred scheme of the flywheel energy storage rotor topology optimization method, the optimization iteration process comprises: evaluating the population individuals according to the fitness value; calculating the social influence of individuals on other individuals; performing echolocation update; checking whether the updated position is within a reasonable range; and repeating iteration until the maximum iteration number is reached.

[0016] The optimization effect data comprises mass reduction amount and percentage, stress distribution change and reduction percentage, limit speed improvement value and percentage, and energy storage density improvement value and percentage.

[0017] In a second aspect, the embodiments of the present application provide a flywheel energy storage rotor topology optimization system, which comprises a stress analysis module, a finite element analysis software is used to simulate and analyze the initial shape of the rotor, and stress distribution data of the rotor is obtained;

[0018] A region identification module identifies a region with small internal stress in the rotor according to the stress distribution data, and sets a stress threshold to mark an optimizable region;

[0019] An optimization design module designs cavity parameters in the optimizable region based on the SDEA optimized SwinTransformer algorithm;

[0020] A performance verification module verifies the performance of the optimized rotor structure and obtains optimization effect data.

[0021] In a third aspect, the embodiments of the present application provide a computer device, which comprises a memory and a processor, and the memory stores a computer program, wherein the computer program instructions are executed by the processor to realize the steps of the flywheel energy storage rotor topology optimization method according to the first aspect of the present application.

[0022] In a fourth aspect, the embodiments of the present application provide a computer readable storage medium, which stores a computer program, wherein the computer program instructions are executed by the processor to realize the steps of the flywheel energy storage rotor topology optimization method according to the first aspect of the present application.

[0023] The application has the advantages that the application can reasonably design the cavity under the conditions of meeting the structural strength and process realizability. The total volume of material removal can be calculated by using a related algorithm, and then the rotor mass reduction amount is obtained, so that the effect of reducing the rotor mass is realized, which has a positive significance for improving the efficiency of the whole system, reducing energy consumption and the like.

[0024] In the cavity configuration process, the maximum stress value of the rotor under the current cavity configuration is calculated through structural strength evaluation, and the stress condition is judged based on the structural strength fitness function. The optimized rotor can effectively improve the stress distribution and reduce the stress concentration degree. Compared with the traditional design, the risk of rotor failure caused by stress concentration can be reduced, the rotor can stably operate at a higher speed, and the performance and reliability of the rotor are improved.

[0025] In the design of the cavity, the process realizability evaluation function is used to judge whether each cavity parameter is within the size, shape and position range allowed by the process, so as to ensure the feasibility of the design scheme in the actual manufacturing process, avoid the problem that the design cannot be realized due to process limitations, and improve the practicality and manufacturability of the design.

[0026] The application comprehensively considers various factors such as structural strength requirements, process realizability and mass reduction, and realizes balanced optimization through a comprehensive fitness function. In the design of the cavity, a unified coding method is used to represent the cavity parameters, and an advanced algorithm (socially oriented dolphin echolocation algorithm optimization SwinTransformer) is used for cavity optimization selection and calculation, which improves the flexibility and accuracy of the design. This comprehensive optimization method can ensure that the designed cavity configuration meets various actual requirements while achieving the best performance improvement effect, and the algorithm and parameters can be adjusted according to the actual situation to obtain a better design scheme. BRIEF DESCRIPTION OF DRAWINGS

[0027] In order to more clearly illustrate the technical solutions of the embodiments of the application, the drawings needed in the embodiment description will be briefly introduced. Obviously, the drawings in the following description are only some embodiments of the application, and other drawings can be obtained by those skilled in the art without creative labor.

[0028] Fig. 1 Flowchart of flywheel energy storage rotor topology optimization method;

[0029] Fig. 2 Computer device diagram of flywheel energy storage rotor topology optimization method; DETAILED DESCRIPTION

[0030] In order to make the above objectives, characteristics and advantages of the present application more apparent, concrete embodiments of the present application will be described in detail below with reference to the accompanying drawings.

[0031] In the following description, numerous specific details are set forth in order to provide a thorough understanding of the present application. However, it will be apparent to one skilled in the art that the present application can be practiced without the specific details and other implementations can be employed. Therefore, the present application is not limited to the details disclosed herein and can be practiced with variations that are within the scope and spirit of the present application.

[0032] Secondly, the term "one embodiment" or "an embodiment" as used herein means that a particular implementation can include a particular feature, structure, or characteristic, but every embodiment can not necessarily include the particular feature, structure, or characteristic. Furthermore, the following claims can refer to "one embodiment" or "an embodiment" rather than the "one embodiment" or "an embodiment" of every subsequent claim.

[0033] Embodiment 1

[0034] Reference Figs. 1-2 For the first embodiment of the present application, the embodiment provides a flywheel energy storage rotor topology optimization method, comprising,

[0035] S100: Simulate and analyze the initial shape of the rotor by using finite element analysis software, and obtain rotor stress distribution data;

[0036] In the embodiments of the present application, the specific steps of simulating and analyzing by using ANSYS software include:

[0037] Geometric modeling: Create a three-dimensional model of the rotor using the DesignModeler module in ANSYS Workbench. First, establish the basic shape of the disc according to the given parameters (diameter D, thickness H), and then add features such as central shaft holes. When modeling, attention should be paid to maintaining the symmetry of the geometric structure to avoid unnecessary geometric singular points.

[0038] Material property definition: Define the material properties of high-strength steel in the Engineering Data module. Generally, the following parameters need to be input: density (ρ): 7850 kg / m 3 ; Elastic modulus (E): 210 GPa; Poisson's ratio (ν): 0.3; Yield strength: 800 MPa; Tensile strength: 950 MPa.

[0039] Meshing: Meshing is performed in the Mechanical module, which includes the following steps: selecting hexahedral element type (SOLID186); setting global mesh size as H / 20 (H is the rotor thickness); local mesh refinement in stress concentration areas; mesh quality check to ensure minimum element quality > 0.7; total element number control within 50000-100000.

[0040] In an optional embodiment, the meshing strategy can also employ adaptive meshing technology. The system first performs preliminary analysis using coarse mesh, and then automatically refines the mesh in high stress areas according to stress gradient until the convergence accuracy requirement is met. This method can reduce the consumption of computing resources while ensuring the accuracy of the calculation.

[0041] It should be noted that meshing directly affects the accuracy and efficiency of the calculation. Too dense meshing will result in a sharp increase in computational load, while too sparse meshing may result in inaccurate results. Therefore, mesh independence verification is required, i.e., by gradually refining the mesh, observing whether the result converges, and thus determining the appropriate mesh density.

[0042] Boundary condition setting: axial constraint: axial displacement constraint is applied to the inner surface of the shaft hole; radial constraint: radial displacement constraint is applied to key nodes; load condition: rotational speed ω (usually 10000 rpm) is applied.

[0043] In an optional embodiment, the boundary conditions can also consider the effect of temperature load. Since high-speed rotation generates heat, a temperature field analysis can be added to the model, and the temperature load can be set as follows: ambient temperature: 20℃; working temperature: linear distribution from 20-80℃; heat transfer coefficient: 15W / (m 2 K).

[0044] S101: Simulate the initial shape of the rotor using finite element analysis software, including: setting the material parameters of the rotor, including density and Poisson's ratio; establishing the geometric model of the rotor and performing meshing; applying axial and radial displacement constraints; setting the rotational speed operating condition; calculating the stress distribution of each region of the rotor under the set operating condition.

[0045] Specifically, finite element analysis includes four main steps: material property setting, geometric modeling, meshing, and stress calculation. Material property setting mainly includes density ρ = 7850 kg / m 3The basic parameters include the elastic modulus E = 210 GPa, the Poisson's ratio v = 0.3, etc. The geometric modeling mainly includes the modeling of a disc entity with an outer diameter D = 1 m and a thickness H = 0.2 m. Hexahedral elements are mainly used for meshing, and the grid size is H / 20. The grid in the stress concentration area is densified. The stress calculation includes the calculation of the radial stress σr and the tangential stress σθ distribution under the condition of a set rotating speed ω = 10000 rpm.

[0046] In an optional embodiment, the finite element analysis process can also consider the influence of the temperature load. By introducing a temperature field distribution of 20-80℃ in the model and setting the heat transfer coefficient 15 W / (m 2 K, the thermal-stress coupling effect of the rotor in the process of high-speed rotation is simulated. In addition, the anisotropic properties of the material can also be considered, and different elastic modulus and strength parameters are set in different directions to more accurately reflect the actual working condition.

[0047] In an optional embodiment, the meshing can also use adaptive meshing technology. First, a preliminary calculation is performed using a relatively coarse mesh, and then the local mesh density is automatically adjusted according to the stress gradient size, and the mesh is densified in the stress concentration area and appropriately thinned in the stress gentle area, which ensures the calculation accuracy and improves the calculation efficiency. The system performs iterative calculation, and when the maximum difference between the results of two adjacent calculations is less than 1%, it is considered that the meshing reaches the convergence standard.

[0048] It should be noted that the finite element analysis is the basis for subsequent optimization design, and its accuracy directly affects the reliability of the optimization result. The degree of simplification of the model should be moderate, which reflects the main stress characteristics and avoids excessive complexity. The mesh quality control is the key to ensure the calculation accuracy, and the independence of the mesh needs to be verified to ensure the reliability of the result. In addition, when setting the boundary conditions, the actual installation and use state needs to be fully considered to ensure that the calculation result has practical engineering significance.

[0049] S200: According to the stress distribution data, a region with small stress in the rotor is identified, and a stress threshold is set to mark the optimizable region;

[0050] According to the stress distribution data, a region with small stress in the rotor is identified, and a stress threshold is set to mark the optimizable region;

[0051] In the embodiments of the present application, the stress region identification process includes the following specific steps: stress data extraction: the node stress data is exported from the ANSYS result file; a stress data matrix is established, which includes the node coordinates and the corresponding radial stress σ r , tangential stress σ θ ; data formatting processing is performed to ensure the continuity and integrity of the data.

[0052] Stress threshold determination: the reference stress threshold σ0 is set to 100 MPa; considering the safety factor K = 1.5; the actual stress threshold calculation:

[0053] σ t resold = σ0 / K

[0054] Specifically, stress data processing includes three steps: stress extraction, data filtering, and region marking. Stress extraction mainly obtains the radial stress σ r and tangential stress σ θ value of each node; data filtering mainly eliminates abnormal data points and calculates the comprehensive stress value of the node; region marking is to mark the region with stress value below the threshold σ0 = 100 MPa as a potential optimization region. The comprehensive stress is determined by taking the maximum value of the radial stress and the tangential stress, that is, σ i = max(σ r,i ,σ θ,i ).

[0055] In an optional embodiment, the determination of the stress threshold can adopt an adaptive method. By calculating the average stress level and stress standard deviation of the entire rotor, the threshold is set to the average stress minus 0.5 times the standard deviation, but at the same time, the minimum threshold is set to 50 MPa to ensure the rationality of the optimization region. This method can better adapt to the stress distribution characteristics under different working conditions.

[0056] In an optional embodiment, the region marking process can also consider the influence of stress gradient. When marking the potential optimization region, not only the absolute value of the stress is considered, but also the degree of stress change. By calculating the stress gradient between adjacent nodes, the region with smaller gradient is preferentially marked as a potential optimization region, which can avoid optimization in the stress mutation region.

[0057] It should be noted that the region identification process needs to fully consider the integrity and local characteristics of the structure. Since the rotor is a whole structure, the local stress distribution will affect each other, so the continuity and integrity of the region should be considered when identifying the low stress region. In addition, considering the needs of actual processing and manufacturing, the identified region cannot be too scattered or too small, and appropriate region merging and shape optimization need to be performed to ensure the realizability of subsequent optimization design.

[0058] S201: identifying a region with smaller stress in the rotor includes: setting a stress threshold σ0; extracting the radial stress σ r and tangential stress σ θ of each node of the rotor; calculating the comprehensive stress σ i = max(σ r,i ,σ θ,i ) of the node; when the comprehensive stress σ iWhen the stress is less than the stress threshold σ0, the area where the node is located is marked as an optimizable area.

[0059] S300: Optimizing the SwinTransformer algorithm design hole parameters in the optimizable area based on SDEA to realize rotor structure optimization.

[0060] S301: The SDEA optimization of the SwinTransformer algorithm design hole parameters includes: using a unified coding method to represent the hole parameters; establishing a comprehensive fitness function including structural strength, mass reduction and process realizability; using the SwinTransformer model to predict the hole fitness value; and optimizing and iterating the model parameters through the SDEA algorithm.

[0061] S302: The unified coding method of the hole parameters includes: a circular hole is represented by a vector [x, y, r, 0], where (x, y) is the center coordinate, r is the radius, and 0 represents a circle; a square hole is represented by a vector [x, y, a, θ, 1], where (x, y) is the center coordinate, a is the side length, θ is the rotation angle, and 1 represents a square.

[0062] S303: The comprehensive fitness function includes: a structural strength fitness function f1 for evaluating the stress distribution under the hole configuration; a mass reduction fitness function f2 for evaluating the material removal effect; a process realizability fitness function f3 for evaluating the realizability of the hole parameters; and a comprehensive fitness function F = f1 x f2 x f3.

[0063] Specifically, the hole parameter design includes three links of parameter coding, prediction model construction and optimization iteration. The parameter coding adopts a unified format, and a circular hole is represented by [x, y, r, 0], where (x, y) is the center coordinate, r is the radius, and 0 represents a circle; a square hole is represented by [x, y, a, θ, 1], where (x, y) is the center coordinate, a is the side length, θ is the rotation angle, and 1 represents a square. The prediction model adopts the SwinTransformer architecture, including an input layer, an encoding layer, an attention layer and an output layer. The optimization iteration adopts the SDEA algorithm, including two stages of social influence update and echolocation update.

[0064] In an optional embodiment, the hole shape can also adopt an ellipse or a polygon. An elliptical hole is represented by [x, y, a, b, θ, 2], where a and b are the lengths of the major and minor axes respectively; a regular polygon is represented by [x, y, r, n, θ, 3], where r is the circumradius and n is the number of sides. By increasing the diversity of hole shapes, more flexible optimization schemes can be obtained, better adapting to different stress distribution characteristics. Each shape is equipped with corresponding constraint conditions to ensure that the generated hole meets the process and strength requirements.

[0065] In an optional embodiment, the model training process can also adopt a transfer learning strategy. First, pre-train the model on a general structure optimization dataset, and then fine-tune it using specific data of flywheel rotors. The pre-training phase uses 100,000 general structure samples, and the fine-tuning phase uses 1,000 flywheel rotor samples. This method can significantly improve the convergence speed and optimization effect of the model.

[0066] In an optional embodiment, the social influence parameter a and the echolocation parameter β of the SDEA algorithm can be dynamically adjusted. In the initial stage of optimization, a larger echolocation parameter β is set to enhance the global search ability; as the iteration proceeds, the social influence parameter a is gradually increased to strengthen local optimization. For example, initially set a = 0.3, β = 0.7, adjust every 100 iterations until a = 0.7, β = 0.3.

[0067] It should be noted that the optimization of the cavity parameters is a multi-objective optimization problem that needs to consider multiple objectives such as structural strength, mass reduction, and process realizability. During the optimization process, attention should be paid to maintaining the symmetry of the structure to avoid generating unreasonable cavity distribution. At the same time, since the rotor is a high-speed rotating component, the optimization result must ensure dynamic balance. In addition, the minimum distance between cavities and the minimum edge distance must meet the process requirements, usually not less than 2 times the machining precision.

[0068] S400: Perform performance verification on the optimized rotor structure and obtain optimization effect data.

[0069] S401: The optimization iteration process includes: evaluating the population individuals according to the fitness value; calculating the social influence of individuals on other individuals; performing echolocation update; checking whether the updated position is within a reasonable range; repeating the iteration until the maximum number of iterations is reached;

[0070] The optimization effect data includes: mass reduction and percentage of reduction; stress distribution change and reduction percentage; extreme speed increase value and percentage increase; energy storage density increase value and percentage increase.

[0071] Specifically, performance verification includes four aspects: stress verification, mass calculation, speed analysis, and energy storage evaluation. Stress verification mainly checks the maximum stress and stress distribution uniformity to ensure that the maximum stress does not exceed 70% of the material allowable stress. Mass calculation includes material weight reduction and weight reduction percentage statistics, and requires a total weight reduction of not less than 20%. Speed analysis mainly calculates the critical speed and highest use speed to ensure that the working speed is far from the critical speed of each order. Energy storage evaluation includes the calculation of unit mass energy storage density and the comparison with the prototype.

[0072] In an optional embodiment, performance verification can also include fatigue analysis. The fatigue life of the rotor is evaluated using the stress-life method (S-N curve), and the material S-N curve data is obtained from experimental tests. The cumulative damage value is calculated by the Miner linear cumulative damage theory, and the service life of the rotor under various operating conditions is estimated. The design life is usually required to be no less than 10 years or 10,000 start-stop cycles.

[0073] In an optional embodiment, dynamic characteristic analysis can also be performed. Including modal analysis and transient dynamics analysis, the natural frequency and mode shape of the rotor are calculated, and the vibration response under different rotational speeds is evaluated. Special attention is paid to the risk of resonance within the operating speed range, and the vibration amplitude is required to meet the requirements of ISO 1940 standard, usually requiring dynamic unbalance to be less than G2.5 level.

[0074] In an optional embodiment, performance verification can be extended to extreme operating condition analysis. Including overspeed test (1.2 times rated speed), emergency stop condition and temperature cycle condition, etc. The stress level and deformation of the rotor under these extreme operating conditions are evaluated by finite element simulation, and sufficient safety margin is ensured.

[0075] It should be noted that performance verification is the final inspection of optimized design, which needs to be comprehensively evaluated from multiple dimensions. The verification process should focus on the reliability and integrity of the data, and the key performance indicators should have clear quantitative requirements. The evaluation of optimization effect should be combined with the actual application requirements, both meeting the technical indicators and considering the economy. In addition, the verification results should form a complete technical document, providing a basis for subsequent engineering application and continuous optimization.

[0076] Further, the embodiment also provides a flywheel energy storage rotor topology optimization system, comprising,

[0077] The stress analysis module simulates and analyzes the initial shape of the rotor using finite element analysis software, and obtains stress distribution data of the rotor;

[0078] The region identification module identifies the region with smaller internal stress in the rotor according to the stress distribution data, and sets a stress threshold to mark the optimizable region;

[0079] The optimization design module optimizes the cavity parameters of the SwinTransformer algorithm in the optimizable region based on SDEA;

[0080] The performance verification module verifies the performance of the optimized rotor structure and obtains optimization effect data.

[0081] In summary, by using finite element analysis software for fine meshing and multi-condition simulation analysis, high-precision calculation of the global stress distribution of the rotor is realized. From this, more accurate stress field distribution characteristics are obtained, providing a reliable data basis for subsequent optimization. This method avoids the blindness of stress prediction in traditional experience design, making the cavity arrangement more targeted.

[0082] By setting reasonable stress threshold standards and combining the comprehensive judgment mechanism of radial stress and tangential stress, the automatic identification of the optimization area is realized. This method overcomes the subjectivity and uncertainty of traditional manual experience judgment, improving the accuracy and efficiency of regional identification. Especially through the regional merging algorithm, the continuity and processability of the optimization area are guaranteed.

[0083] By combining deep learning with swarm intelligence optimization, the cavity parameter optimization problem is solved innovatively. This method not only can adaptively learn the optimization strategy under different working conditions, but also can avoid local optimum through social guidance mechanism, realizing better solution than traditional optimization methods. This is an unexpected technical effect.

[0084] By establishing a comprehensive fitness function including structural strength, mass reduction, and process realizability, balanced optimization under multi-objective constraints is realized. This method overcomes the limitations of traditional single-objective optimization, maximizing the mass reduction goal while ensuring structural safety.

[0085] By setting a strict performance verification system, including stress verification, mass calculation, speed analysis, and energy storage evaluation, the reliability of the optimization results is guaranteed. Especially through dynamic characteristic analysis and extreme condition verification, the safety and stability of the optimization results under various working conditions are ensured.

[0086] Example 2

[0087] Reference Fig. 1 - Fig. 2 As the second embodiment of the invention, this embodiment provides a flywheel energy storage rotor topology optimization method. In order to verify the beneficial effects of the invention, economic benefit calculation and simulation experiments are used for scientific demonstration.

[0088] Use professional finite element analysis software ANSYS to calculate the initial shape of the rotor to be used. Select high-strength steel material with a diameter of D meters and a thickness of H meters for simulation analysis. Set the rotational speed of the rotor and other working conditions during simulation, with a rotational speed of ω revolutions per minute. Through software calculation, the stress distribution of each region of the rotor under this working condition is obtained. The stress calculation formula is based on the basic stress calculation formula in elasticity mechanics, and the calculation accurately presents the stress value distribution of each region of the entire rotor.

[0089] In ANSYS software, after a new analysis project is created, first enter the material property setting module. For the selected high-strength steel material, input its density p, Poisson's ratio v and other material parameters. These parameters will serve as the basis data for subsequent stress calculation.

[0090] Create a disc-shaped rotor geometric model, and set the size according to the given diameter D meters and thickness H meters. Use stretching, rotation and other operations through the ANSYS Mechanical interface to draw a disc solid model that meets the requirements.

[0091] Mesh the created geometric model. Discretize the continuous geometric solid into a finite number of elements and node sets, select an appropriate meshing method-hexahedral mesh, set the mesh size parameters according to the complexity of the model and the calculation accuracy requirements. Use the default medium mesh density for preliminary division, and then gradually refine the mesh, observe the changes in the calculation results, and when the results tend to be stable, it means that the mesh density has reached the convergence requirement.

[0092] According to the actual rotor installation and working conditions, apply reasonable constraint conditions to the rotor model. The rotor is installed on the two end support structures through the shaft, and the axial and radial displacement constraints are applied at the position corresponding to the center hole of the rotor (contacting the actual installation shaft), limiting its movement in these directions, simulating the actual fixed support state. Through the constraint definition interface of ANSYS software, select the corresponding nodes or surfaces, and then realize it through the fixed constraint Fixed Support.

[0093] Set the rotational speed working condition of the rotor. Set the rotational speed to w revolutions per minute. ANSYS simulates the rotation state of the rotor by applying a rotational angular velocity load. Select the entire rotor model, add a rotational angular velocity load in the load definition interface, and set its value to the radian per second value corresponding to w (radian per second = w x 2p / 60).

[0094] ANSYS calculates each element and node based on the set finite element model, material properties, boundary conditions and load conditions, and iteratively solves the stress distribution of each region of the entire rotor under the set working condition. According to the input p (density), v (Poisson's ratio), w (rotational speed) and r (radius) value corresponding to each node, combined with constants A and C, the software calculates the stress value at each node according to the calculation formulas of radial stress s r and tangential stress s θ .

[0095] Determine constants A and C. The constants A and C in the stress calculation formula for a disk rotating under a plane stress state need to be determined based on specific boundary conditions. Common boundary conditions include the stress conditions at the inner boundary (center hole) and outer boundary (outer diameter edge of the disk). For example, if the radial stress σ at the center hole of the disk (radius r = r0, assuming the center hole radius is r0 meters) is known, r The value of (r0) r is a specific value (such as the stress boundary value at that position obtained based on experience or actual measurement), and the tangential stress σ at the outer diameter edge of the disk (radius r = D / 2) θ The value of (D / 2) is another known boundary value. Substituting these two boundary conditions into the above stress calculation formula, we can obtain a set of two-variable linear equations about A and C:

[0096]

[0097] By solving this set of equations, the specific values ​​of constants A and C can be determined, and accurate parameter values ​​can be used in the entire stress calculation process.

[0098] Analyze radial stress σ r and tangential stress σ θ The cloud map uses different colors to intuitively represent the stress distribution. The darker the color (or according to the software's default color scale, such as from blue to red indicating stress from small to large), the higher the stress value. This allows you to clearly see the areas of stress concentration and the stress value range of each part of the entire rotor, providing a data basis for identifying areas with lower stress in subsequent topology optimization design.

[0099] Based on the stress analysis results, regions within the rotor with low stress are identified. These regions are potential areas for subsequent hole placement and optimization. A stress threshold σ0 (in Pascals) is set. When the calculated stress value σ in a region is lower than σ0, the region is marked as an optimization area.

[0100] The stress threshold σ0 is set based on the rotor material properties of high-strength steel. The initial value is set to σ0 = 100 × 10 6 .

[0101] Check the stress cloud map. Based on the stress distribution represented by the color on the cloud map, first determine the range of the stress value area intuitively, and extract the radial stress σ corresponding to each node of the rotor. r and tangential stress σ θ Numeric value.

[0102] For the extracted stress data of each node, point-by-point comparison and area marking are performed in the following manner.

[0103] Traverse all the stress values of the nodes, considering both the radial stress and the tangential stress, and take the larger value of the two to comprehensively judge the stress level at the node. Let the stress value of a certain node be σ i , the radial stress be σ r,i , and the tangential stress be σ θ,i , then the comprehensive stress σ i of the node can be determined as follows:

[0104] σ i = max(σ r,i , σ θ,i )

[0105] Compare the comprehensive stress value σ i of each node with the set stress threshold σ0. If σ i < σ0, mark the small area where the node is located as a potential optimization area. Continue to perform such judgment and marking operations on all nodes, and finally mark all areas where the nodes meet the condition of stress value being lower than the threshold.

[0106] After point-by-point marking, multiple scattered small areas marked as potential optimization are obtained, and these small areas need to be integrated to determine the final large potential optimization area which is continuous and convenient for subsequent hole design.

[0107] Check the adjacency relationship between each marked small area. If two small areas are adjacent in space and their stress levels are both lower than the threshold, the adjacency can be determined by judging the coordinate continuity and other geometric relationships of the boundary nodes of the areas, such as sharing some boundary nodes. Repeat the operation of merging adjacent areas until no further merging is possible, and finally form several continuous and relatively large stress small areas, which are the potential areas for subsequent hole arrangement for topology optimization design.

[0108] In the identified stress small areas, according to the comprehensive factors such as structural strength requirements and process realizability, reasonably design the shape, size and distribution position of the holes, and use the social-oriented dolphin echo positioning algorithm (SDEA) to optimize the combination of SwinTransformer key parameters to realize the optimization selection and calculation of the holes.

[0109] From the stress analysis and area identification steps, obtain the geometric information, boundary conditions, and material properties (density ρ) of the stress small areas. Determine the structural strength requirement related parameters, including the maximum allowable stress value σ allow and the ultimate stress value σ limit, process realizability parameters, including minimum machining size, machining precision.

[0110] Cavity representation and encoding.

[0111] For the shape, size, and position of the cavity, a unified encoding method is adopted. A circular cavity is represented by the vector [x, y, r, 0], where (x, y) is the center coordinate, r is the radius, and the last bit 0 represents the circular shape. A square cavity is represented by the vector [x, y, a, θ, 1], where (x, y) is the center coordinate, a is the side length, θ is the rotation angle, and the last bit 1 represents the square shape. For a polygonal cavity, the vertex coordinate sequence and an identifier representing the polygon type can be used for encoding. Convert the encoding information of the cavity into a tensor form suitable for SwinTransformer processing. Discretize all possible cavity parameter ranges into fixed-length vectors, and then combine these vectors into batch tensors as inputs to the SwinTransformer.

[0112] Formulate the comprehensive fitness function.

[0113] Structural strength evaluation. Calculate the stress distribution of the rotor under the current cavity configuration. For a given cavity parameter, the maximum stress value σ of the rotor is obtained. The structural strength fitness function f1 is defined as:

[0114] max

[0115]

[0116] Mass reduction evaluation. Calculate the total volume V of material removal under the current cavity configuration 去 . Set the area of a single cavity as S i , there are n cavities, and the rotor thickness is H, then The rotor mass reduction Δm = ρV 去 .

[0117] The mass reduction fitness function f2 is defined as:

[0118]

[0119] where Δm target is the desired mass reduction target value.

[0120] Process realizability evaluation. Check whether the current cavity configuration meets the process realizability conditions. For each cavity parameter, determine whether it is within the process-allowed size, shape, and position range. The process realizability fitness function f3 is defined as:

[0121]

[0122] Comprehensive fitness function. The comprehensive fitness function F is:

[0123] F = f1 x f2 x f3

[0124] SwinTransformer realizes prediction. The cavity parameter encoding vectors of all individuals are combined into a total data set D, which has a size of M (i.e. contains M different cavity configuration encoding samples). The data set D is divided into a training set D train , a validation set D val and a test set D test according to an 80% training, 10% validation and 10% test ratio. Let the number of training set samples be M train , the number of validation set samples be M val , and the number of test set samples be M test , satisfying M train + M val + M test = M.

[0125] Each sample (i.e. the cavity parameter encoding vector of an individual) is normalized to a distribution with a mean of 0 and a standard deviation of 1. For each element x ij in the input encoding vector (representing the jth feature value of the ith sample), the mean μ j and the standard deviation σ j are calculated:

[0126]

[0127] Then each element is normalized:

[0128]

[0129] The SwinTransformer architecture is constructed.

[0130] The input two-dimensional encoding vector is divided into non-overlapping small blocks (patches). Let the size of each small block be P x P. After patching, the dimension of the input feature map changes from [batch size , num features ] to [batch size , num patces , C], where num patces is the number of small blocks after division, and the calculation formula is C is the embedding dimension of each small block after linear mapping.

[0131] where batch size is the batch size, which here can be the number of samples selected for each training, and num patces is the number of features after cavity parameter encoding

[0132] Block merge operation is performed to change the resolution and channel number of the feature map to gradually extract higher-level features. Each block merge will merge 2x2 small blocks adjacent to one large block, and the channel number is doubled. The feature map dimension of the current layer [batc size ,num patces ,C] becomes After block merge, the new feature map dimension becomes

[0133] Set the window size to WxW, divide the feature map into multiple windows, and apply the multi-head attention mechanism in each window. For the multi-head attention mechanism, there are H heads, and the calculation process of each head is as follows:

[0134] (1) First, linear transformation is performed on the input feature vector to obtain Query vector Q, Key vector K and Value vector V. Let the input feature dimension be [batc size ,num patces ,C], and obtain through three different linear transformation matrices:

[0135] W Q ∈R C×C / H 、W K ∈R C×C / H 、W V ∈R C×C / H :

[0136] Q=XW Q ,K=XW K ,V=XW V

[0137] Where X is the input feature, and the dimensions of the output Q, K, V are:

[0138] [batc size ,num patces ,C / H].

[0139] (2) Calculate the dot product between Query and Key to obtain attention score A, and perform scaling and normalization processing.

[0140]

[0141] Then normalize the attention score through the Softmax function:

[0142] A softmax =Softmax(A)

[0143] (3) Multiply the normalized attention score with the Value vector to obtain the attention output of each head.

[0144] O = A softmax V

[0145] Finally, the attention outputs of all heads are concatenated and a linear transformation is applied to obtain the final window attention output, which still has the dimension of [batc size ,num patces ,C].

[0146] (4) A feed-forward network is added after each attention layer, which contains two fully connected layers with an activation function ReLU in between, to further transform the features in a nonlinear way. Let the output dimension of the first fully connected layer of the feed-forward network be 4C (the expansion factor can be adjusted according to the actual situation), then the calculation of the feed-forward network is:

[0147] FFN(X) = ReLU(XW1 + b1)W2 + b2

[0148] where W1 e R C×4C ,b1 is the weight and bias of the first fully connected layer, W2 e R 4C×C ,b2 is the weight and bias of the second fully connected layer, and the output dimension is the same as the input feature dimension, which is [batc size ,num patces ,C].

[0149] Select the loss function. According to the nature of the prediction target, select the mean squared error loss function (Mean Squared Error, MSE) or cross entropy loss function (Cross Entropy Loss), etc. If the fitness value is a continuous numerical value, the mean squared error loss function is usually selected, and its calculation formula is as follows:

[0150]

[0151] where F is the fitness value of the i-th sample predicted by the model, F i is the actual fitness value of the sample.

[0152] If the fitness value is processed into a classification form, the cross entropy loss function is selected, and its calculation formula is:

[0153]

[0154] where y i is the true class label (0 or 1) of the sample, is the probability that the sample belongs to class 1 predicted by the model.

[0155] Set the number of rounds (Epochs) of training, which represents the number of times the entire training set will be used to train the model.

[0156] The optimizer (such as Adam) is used to update the parameters of the model according to the calculated loss value by backpropagation. The key parameters of SwinTransformer are updated by the backpropagation algorithm to minimize the loss function. The Adam optimizer is used, and its update formula is as follows:

[0157]

[0158] where m t and v t are the first and second moment estimates of the gradient, β1 and β2 are related hyperparameters, g t is the current gradient, α is the learning rate, ∈ is a small constant to prevent the denominator from being zero, and θ t is the model parameter.

[0159] The sample data is selected in batches from the training set, and the batch size is set to batc size The batch data is input into the SwinTransformer model for forward propagation calculation to obtain the predicted fitness value of the model for the batch of samples. According to the selected loss function, the loss value L MSE or L CE between the predicted value and the actual value is calculated.

[0160] After training, the test set data is prepared, and its data format is consistent with the training set and validation set. The test set data is input into the trained SwinTransformer model in batches, and the fitness value prediction result of each test set sample is obtained by forward propagation calculation of the model.

[0161] The social-oriented dolphin echolocation algorithm (SDEA) is used to optimize the SwinTransformer model.

[0162] According to the fitness value predicted by SwinTransformer, each individual in the population is evaluated. The higher the fitness value, the better the individual's cavity configuration.

[0163] For each individual i, its social influence from other individuals is calculated. The update calculation formula in dimension j is as follows:

[0164]

[0165] This formula indicates that individual i adjusts its position in dimension j according to the difference between the fitness of other individuals and itself, as well as the position difference, and moves towards the direction of better individuals.

[0166] Update individual position, formula as follows:

[0167]

[0168] For each individual i in dimension j on the echolocation update:

[0169]

[0170] Where r ij Is a random number in the range [-1, 1]. This update simulates the behavior of dolphins exploring the surrounding environment through echolocation, adding randomness to the search process.

[0171] Update individual position, formula as follows:

[0172]

[0173] Check if the updated individual position is out of the reasonable value range of the cavity parameters, including whether the cavity shape code is within the legal category range, whether the size parameter is within the size range that can be achieved by the process, whether the position parameter is within the area with less stress, etc. If it is out of range, adjust the individual position to the boundary value and update the individual position matrix X in the population.

[0174] Repeat 3.4 and 3.5 until the maximum number of iterations I max is reached. After completing the iterations, select the individual with the highest fitness value F in the population as the optimal solution. The cavity parameter code corresponding to the optimal solution is the result of the cavity optimization selection.

[0175] Decode the cavity parameter code vector of the optimal solution to obtain the actual shape, size and position parameters of the cavity. Output the detailed parameter information of the cavity, including the shape, size (such as the radius of a circle, the side length of a square, etc.) and position (coordinates) of each cavity. At the same time, calculate and output the final material removal volume V 去 , the rotor mass reduction Δm and the stress distribution of the optimized rotor, etc. to evaluate the optimization effect and verify whether the design requirements are met.

[0176] For the rotor with a cavity structure after topological optimization design, perform stress analysis, modal analysis, etc. again using finite element analysis software to test its maximum stress, overall mass and limit speed performance indicators under the same working conditions (such as the same rotational speed ω of 60 rpm, etc.). At the same time, compare the traditional uniform disc design rotor (same material and initial size), verify the optimization effect of the present invention, confirm that the optimized rotor has lower maximum stress, significantly reduced overall mass, allows higher rotational speed and higher energy storage density, and effectively reduces the load or unloading pressure of the magnetic bearing.

[0177] Mass reduction analysis

[0178] For the initial design (assuming a uniform disc rotor), the disc mass is calculated according to the formula:

[0179]

[0180] where p is the material density (kg / m3), D is the disc diameter (m), H is the disc thickness (m), V initial is the initial disc volume.

[0181] According to the optimized cavity configuration, the total volume of material removed V 去 is calculated, and the area of a single cavity is S i (m2). If there are n cavities arranged, then

[0182] Rotor mass after optimization

[0183] Calculate the mass reduction Am = m initial - m optimized .

[0184] Calculate the mass reduction percentage:

[0185]

[0186] By comparing the mass before and after optimization and the mass reduction percentage, analyze the effect of the optimization algorithm in reducing mass. If the mass reduction percentage does not meet the expected target, repeat step 3 for correction.

[0187] Stress distribution change analysis

[0188] Use ANSYS to calculate the stress distribution of the initial design rotor at the working speed. Analyze the characteristics of the initial design stress distribution, determine the maximum stress value and the location and size of the stress concentration area. Similarly, use the method to calculate the stress distribution of the optimized rotor (with cavities) at the same working speed, and obtain the distribution of radial stress σ r,optimized and tangential stress σ θ,optimized .

[0189] Determine the maximum stress value of the optimized stress distribution.

[0190] Calculate the stress reduction value:

[0191]

[0192] Calculate the stress reduction percentage:

[0193]

[0194] By comparing the stress reduction value and the stress reduction percentage, the improvement effect of the optimization algorithm on the stress distribution can be evaluated. If the stress in the critical area (such as near the rotor surface or center) and the maximum stress reduction percentage do not meet the expected target, repeat step 3 to make corrections.

[0195] Critical speed analysis

[0196] The initial design can calculate its critical speed n initial (rpm) through the critical speed calculation formula. The optimized rotor, also uses the corresponding method to calculate its critical speed n optimized .

[0197] Calculate the speed increase value Δn = n optimized -n initial And the speed increase percentage:

[0198]

[0199] Speed increase percentage

[0200] Energy storage density analysis

[0201] The energy storage density calculation formula is Where I is the moment of inertia, ω is the speed, and m is the rotor mass.

[0202] The initial design calculates its energy storage density E initial , the moment of inertia I initial can be calculated according to the formula for the moment of inertia of a disc . The optimized rotor, calculate its energy storage density E optimized , where the moment of inertia I optimized needs to be recalculated according to the optimized rotor geometry.

[0203] Calculate the energy storage density increase value ΔE = E optimized -E initial And the energy storage density increase percentage:

[0204]

[0205] By comparing the changes in energy storage density, the influence of the optimization algorithm on the performance of the energy storage system can be evaluated. If the energy storage density improvement does not meet the expected target, repeat the step of "in the identified area with less stress, according to the structural strength requirements, process realizability and other comprehensive factors, reasonably design the shape, size and distribution position of the cavity and other parameters, and use the social-oriented dolphin echo positioning algorithm (SDEA) to optimize the combination of SwinTransformer key parameters to realize the optimization selection and calculation of the cavity" to make corrections. The initial design of the flywheel energy storage system rotor is a uniform disc made of high-strength steel with a density of kg / m3, a Poisson's ratio (V=0.3), a diameter (D=1) m, and a thickness (H=0.2) m.

[0206] Stress analysis: Using ANSYS software, set the rotor speed to rpm, perform simulation analysis, and obtain the stress distribution. After calculation, it is found that the stress value in the annular area with a radius (r) of 0.2-0.4 meters from the center of the disc is continuously below the set stress threshold of Pa, which is marked as an optimizable area.

[0207] Topology optimization design: In the optimizable area, design a circular cavity with a diameter (d=0.1) m, and a total of 10 cavities are uniformly arranged. According to the above material removal amount and mass reduction amount calculation formula, the area of a single cavity is m2, the total volume of material removal is m3, and the mass reduction of the rotor is kg.

[0208] Performance verification: The optimized rotor is simulated again, and it is found that the maximum stress is reduced to 60% of the original, the overall mass is reduced by about 20%, and the energy storage density is improved by about 30% through the energy storage density calculation formula. The limit speed is increased from 12000 rpm to 15000 rpm, and the bearing pressure of the magnetic bearing is also significantly reduced, verifying the effectiveness and advantages of the topology optimization design of the present application.

[0209] Through the above detailed performance index comparison and analysis, the effectiveness of the optimization algorithm can be fully verified, and whether the optimized cavity configuration meets the design requirements and expected targets in terms of mass reduction, stress distribution improvement, limit speed increase, and energy storage density improvement can be evaluated. At the same time, the optimization algorithm can be further improved and adjusted based on the analysis results to obtain a better design scheme.

[0210] Example 3

[0211] The embodiment also provides a computer device suitable for the flywheel energy storage rotor topology optimization method, including a memory and a processor; the memory is used to store computer executable instructions, and the processor is used to execute the computer executable instructions to realize the forced oscillation detection and positioning method for power distribution networks as proposed in the above embodiment.

[0212] The embodiment also provides a storage medium, which stores a computer program, and the computer program is executed by a processor to implement the method for forced oscillation detection and positioning of a power distribution network.

[0213] The computer device can be a terminal, and the computer device includes a processor, a memory, a communication interface, a display screen and an input device connected through a system bus. The processor of the computer device is configured to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for running the operating system and the computer program in the non-volatile storage medium. The communication interface of the computer device is configured to perform wired or wireless communication with an external terminal. The wireless communication can be achieved through WIFI, an operator network, NFC (near field communication) or other technologies. The display screen of the computer device can be a liquid crystal display screen or an electronic ink display screen. The input device of the computer device can be a touch layer overlaid on the display screen, or a key, trackball or touchpad arranged on the shell of the computer device, or an external keyboard, touchpad or mouse, etc.

[0214] If the functions are implemented in the form of software function units and sold or used as independent products, the functions can be stored in a computer readable storage medium. Based on this understanding, the technical solutions of the present application or the parts of the technical solutions that essentially contribute to the prior art can be embodied in the form of a software product. The computer software product is stored in a storage medium and includes a plurality of instructions for causing a computer device (which can be a personal computer, a server or a network device, etc.) to execute all or part of the steps of the method of each embodiment of the present application. The aforementioned storage medium includes a U disk, a mobile hard disk, a read-only memory (ROM, Read-Only Memory), a random access memory (RAM, Random Access Memory), a magnetic disk or an optical disk and various program code storage media.

[0215] The logic and / or steps represented in the flow diagrams or otherwise described herein, for example, can be considered as a sequence of executable instructions, and can be embodied in any computer-readable medium for use by or in connection with an instruction execution system, apparatus, or device, such as a computer-based system, processor-containing system, or other system that can fetch the instructions from the instruction execution system, apparatus, or device and execute the instructions. In the context of this specification, a "computer-readable medium" can be any means that can contain, store, communicate, propagate, or transport the program for use by or in connection with the instruction execution system, apparatus, or device. The computer-readable medium can be, for example but not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, device, or propagation medium.

[0216] More specific examples (a non-exhaustive list) of the computer-readable medium include the following: an electrical connection (electronic) having one or more wires, a portable computer diskette (magnetic), a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or Flash memory), an optical fiber, and a portable compact disc read-only memory (CDROM). Additionally, the computer-readable medium can also be paper or another suitable medium upon which the program is printed, as the program can be electronically captured, for example via an optical scanner, then compiled, interpreted, or otherwise processed, and stored in a computer memory in a form that can be later executed by a computer. In some embodiments, the computer-readable medium can be non-transitory.

[0217] It should be understood that aspects of the application can be implemented in hardware, software, firmware or combinations thereof. In the embodiments described above, various steps or methods can be implemented, for example, by software or firmware stored in memory and executed by a suitable instruction execution system. For example, if implemented in hardware, and in another embodiment, any of the following techniques, which are well known in the art of making integrated circuits, can be used to implement the various techniques and technologies described herein: a discrete logic circuit(s) having logic gates for implementing logic functions upon data signals, an application specific integrated circuit having appropriate combinational logic gates, a programmable gate array(s) (PGA), a field programmable gate array (FPGA), and / or the like.

[0218] It should be noted that the above-mentioned embodiments are merely used to illustrate the technical solutions of the present application, rather than limit the present application, and although the present application has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical solutions of the present application can be modified or equivalent replaced, without departing from the spirit and scope of the technical solutions of the present application, and all of them should be covered in the scope of the claims of the present application.

Claims

1. A flywheel energy storage rotor topology optimization method, characterized by: The flywheel energy storage rotor topology optimization method comprises the following steps: including, The rotor initial shape is simulated and analyzed by using a finite element analysis software to obtain rotor stress distribution data; The identification of the region with low stress in the rotor includes: setting a stress threshold σ0; extracting the radial stress σ of each node of the rotor r,i and tangential stress σ θ,i ; Calculate the node comprehensive stress σ i = max(σ r,i , σ θ,i ); when the node comprehensive stress σ i When it is less than the stress threshold σ0, the area where the node is located is marked as an optimizable area; According to the stress distribution data, a region with small internal stress of the rotor is identified, and a stress threshold is set to mark the optimization region; In the optimization region, the SDEA optimization SwinTransformer algorithm is used to design the hollow parameters to realize the optimization of the rotor structure; The SDEA optimization SwinTransformer algorithm for designing the hollow parameters comprises: adopting a unified coding method to represent the hollow parameters; establishing a comprehensive fitness function including structural strength, mass reduction and process realizability; using a SwinTransformer model to predict the hollow fitness value; and optimizing and iterating the model parameters by using a SDEA algorithm; The comprehensive fitness function comprises: a structural strength fitness function f1 for evaluating the stress distribution under the hollow configuration; a mass reduction fitness function f2 for evaluating the material removal effect; and a process realizability fitness function f3 for evaluating the realizability of the hollow parameters; and a comprehensive fitness function F = f1 × f2 × f3.

2. A flywheel energy storage rotor topology optimization method as claimed in claim 1, characterized in that: The performance of the optimized rotor structure is verified to obtain optimization effect data.

3. A flywheel energy storage rotor topology optimization method as claimed in claim 2, characterized in that: The simulation and analysis of the rotor initial shape by using the finite element analysis software comprises: setting the rotor material parameters including density and Poisson's ratio; establishing a rotor geometric model and performing mesh division; applying axial and radial displacement constraints; setting the rotating speed working condition; and calculating the stress distribution of each region of the rotor under the set working condition.

4. A flywheel energy storage rotor topology optimization method as claimed in claim 3, characterized in that: The unified coding method of the hollow parameters comprises: a circular hollow is represented by a vector [x, y, r, 0], wherein (x, y) is the center coordinate, r is the radius, and 0 represents a circle; and a square hollow is represented by a vector [x, y, a, θ, 1], wherein (x, y) is the center coordinate, a is the side length, θ is the rotation angle, and 1 represents a square. The optimization iteration process comprises: evaluating the population individuals according to the fitness value; calculating the social influence of the individuals on each other; performing echo positioning update; checking whether the updated position is within a reasonable range; and repeating the iteration until the maximum iteration number is reached.

5. A flywheel energy storage rotor topology optimization system based on the flywheel energy storage rotor topology optimization method of any one of claims 1-4, characterized in that: The optimization effect data comprises: mass reduction amount and reduction percentage; stress distribution change and reduction percentage; limit speed improvement value and improvement percentage; and energy storage density improvement value and improvement percentage. The stress analysis module uses a finite element analysis software to simulate and analyze the initial shape of the rotor to obtain rotor stress distribution data; The region identification module identifies a region with small internal stress of the rotor according to the stress distribution data, and sets a stress threshold to mark the optimization region; The optimization design module uses the SDEA optimization SwinTransformer algorithm to design the hollow parameters in the optimization region; 6.A computer device, comprising a memory and a processor, wherein the memory stores a computer program, and the computer device is characterized in that: The performance verification module verifies the performance of the optimized rotor structure to obtain optimization effect data. The processor executes the computer program to realize the steps of the flywheel energy storage rotor topology optimization method according to any one of claims 1-4.

7. A computer readable storage medium having stored thereon a computer program, characterized in that: The computer program, when executed by a processor, implements the steps of the flywheel energy storage rotor topology optimization method of any one of claims 1-4.

Images