Method for determining structural parameters of roof insulator, roof insulator for train and train

Abstract

The invention provides a method for determining structural parameters of a roof insulator, which is used for the roof insulator of a train and the train, and can be applied to the field of public transportation. The method for determining the structural parameters of the roof insulator comprises the steps that sampling is carried out in a preset parameter interval according to the number of to-be-sampled sample points determined on the basis of structural information of the roof insulator, multiple sample points are obtained, and the structural information comprises multiple parameter types used for a pit structure of the roof insulator; constructing an agent model according to the plurality of sample points and the resistance value obtained based on the plurality of sample points; and performing iterative optimization processing on the proxy model based on a multi-population genetic algorithm to obtain target structure parameters, the target structure parameters including parameters of the pit structure.

Description

Technical Field

[0001] The present disclosure relates to the field of public transportation, and more specifically, to a method for determining structural parameters of a roof insulator, a roof insulator for a train, and a train. Background Art

[0002] Aerodynamic drag is generated during the operation of the train, and as the speed of the train increases, the aerodynamic drag will also increase. Aerodynamic drag not only restricts the increase in train speed, but also increases the energy consumption of the train.

[0003] In the related art, aerodynamic drag reduction of the train can be achieved by studying the drag reduction of the train body itself, or by studying the flow field characteristics of a large number of external insulating structures such as pantographs and insulators on the top of the train.

[0004] In the process of realizing the concept of the present disclosure, the inventors found that there are at least the following problems in the related art: how to improve the accuracy of determining the structural parameters of the roof insulator to more effectively achieve aerodynamic drag reduction of the train. Summary of the invention

[0005] In view of this, the present disclosure provides a method for determining structural parameters of a roof insulator, a roof insulator for a train, and a train.

[0006] According to one aspect of the present disclosure, a method for determining structural parameters of a roof insulator is provided, comprising: sampling within a preset parameter range according to the number of sample points to be sampled determined based on the structural information of the roof insulator to obtain a plurality of sample points, wherein the structural information includes a plurality of parameter types for a pit structure of the roof insulator; constructing a proxy model according to the plurality of sample points and resistance values ​​obtained based on the plurality of sample points; and iteratively optimizing the proxy model based on a multi-population genetic algorithm to obtain target structural parameters, wherein the target structural parameters include parameters of the pit structure.

[0007] According to an embodiment of the present disclosure, the above-mentioned roof insulator includes a core rod, a plurality of large umbrella skirts and a small umbrella skirt arranged at intervals, the above-mentioned pit structure includes a plurality of pits, and the above-mentioned plurality of pits are arranged on the surface of the above-mentioned core rod, and the above-mentioned parameter type includes the pit diameter of the above-mentioned pits, the pit depth of the above-mentioned pits, and the pit arrangement angles between the above-mentioned pits.

[0008] According to an embodiment of the present disclosure, the above-mentioned preset parameter interval includes a diameter parameter interval, a depth parameter interval and an angle parameter interval.

[0009] According to an embodiment of the present disclosure, the number of sample points to be sampled determined based on the structural information of the roof insulator is sampled within a preset parameter range to obtain multiple sample points, including: determining the second number of the sample points to be sampled based on the first number of the parameter type; based on the second number, performing Latin hypercube sampling in the diameter parameter range, the depth parameter range and the angle parameter range, respectively, to obtain a second number of sample diameter parameters, a second number of sample depth parameters and a second number of sample arrangement angle parameters; and determining the second number of the sample points based on the second number of sample diameter parameters, the second number of sample depth parameters and the second number of sample arrangement angle parameters.

[0010] According to an embodiment of the present disclosure, the plurality of sample points include sample diameter parameters that are different from each other, sample depth parameters that are different from each other, and sample arrangement angle parameters that are different from each other.

[0011] According to an embodiment of the present disclosure, constructing the proxy model based on the above-mentioned multiple sample points and the resistance values ​​obtained based on the above-mentioned multiple sample points includes: using a simulation tool to simulate the finite element model constructed based on the above-mentioned multiple sample points to obtain the above-mentioned resistance values; and constructing the above-mentioned proxy model based on the mapping relationship between the above-mentioned multiple sample diameter parameters, the above-mentioned multiple sample depth parameters, the above-mentioned multiple sample arrangement angle parameters and the above-mentioned resistance values.

[0012] According to an embodiment of the present disclosure, the above-mentioned proxy model is iteratively optimized based on a multi-population genetic algorithm to obtain target structural parameters, including: generating multiple points to be optimized based on the above-mentioned proxy model, wherein the above-mentioned multiple points to be optimized include different diameter parameters to be optimized, different depth parameters to be optimized and different arrangement angle parameters to be optimized; and, using the parameters of each of the above-mentioned multiple parameter types as optimization parameters and minimizing the above-mentioned resistance value as the optimization target, iteratively optimizing the above-mentioned multiple points to be optimized to obtain target points, and determining the diameter parameters to be optimized, depth parameters to be optimized and arrangement angle parameters to be optimized of the above-mentioned target points as the above-mentioned target structural parameters.

[0013] According to an embodiment of the present disclosure, the multi-population genetic algorithm has a preset crossover probability, and the iterative optimization process includes a crossover operation.

[0014] According to an embodiment of the present disclosure, the iterative optimization processing of the above-mentioned multiple points to be optimized using the parameters of each of the above-mentioned multiple parameter types as the optimization parameters and minimizing the above-mentioned resistance value as the optimization target includes: randomly determining two first points to be optimized from the above-mentioned multiple points to be optimized; based on the above-mentioned preset crossover probability, determining whether it is necessary to perform a crossover operation on the parameters of each of the above-mentioned two first points to be optimized, wherein the crossover operation is used to exchange the parameters of the corresponding parameter types of the above-mentioned two first points to be optimized to change the parameters of the above-mentioned two first points to be optimized; and, in the case where it is necessary to perform a crossover operation on the parameters of each of the above-mentioned two first points to be optimized, exchanging the parameters of the corresponding parameter types of the above-mentioned two first points to be optimized to obtain the two first points to be optimized after the parameters are changed.

[0015] According to an embodiment of the present disclosure, the multi-population genetic algorithm has a preset mutation probability, and the iterative optimization process includes a mutation operation.

[0016] According to an embodiment of the present disclosure, the iterative optimization processing of the above-mentioned multiple points to be optimized using the parameters of each of the above-mentioned multiple parameter types as optimization parameters and minimizing the above-mentioned resistance value as optimization target also includes: randomly determining two second points to be optimized from the above-mentioned multiple points to be optimized; based on the above-mentioned preset mutation probability, determining whether it is necessary to perform a mutation operation on the parameters of each of the above-mentioned two second points to be optimized, wherein the above-mentioned mutation operation is used to exchange parameters of different parameter types of the above-mentioned one second point to be optimized to change the parameters of the above-mentioned one second point to be optimized; and, in the case where it is necessary to perform a mutation operation on the parameters of the above-mentioned one second point to be optimized, exchanging the parameters of the above-mentioned different parameter types to obtain the two second points to be optimized after the parameters are changed.

[0017] According to another aspect of the present disclosure, there is provided a roof insulator for a train, the roof insulator comprising: a core rod, a plurality of large sheds and small sheds arranged at intervals; a surface of the core rod is provided with a pit structure, the pit structure comprises a plurality of pits, and target structural parameters of the pits are obtained by using the method as claimed in claims 1 to 7.

[0018] According to an embodiment of the present disclosure, the above-mentioned target structure parameters include a pit diameter, a pit depth, and an arrangement angle of the above-mentioned pits between each other; the above-mentioned pit diameter is located in a diameter parameter range, and the above-mentioned diameter parameter range includes 1.8mm~3mm; the above-mentioned pit depth is located in a depth parameter range, and the above-mentioned depth parameter range includes 0.3mm~0.8mm; the above-mentioned pit arrangement angle is located in an angle parameter range, and the above-mentioned angle parameter range includes 4°~18°.

[0019] According to another aspect of the present disclosure, a train is provided, comprising: at least one of the above-mentioned roof insulators for a train. BRIEF DESCRIPTION OF THE DRAWINGS

[0020] The above and other objects, features and advantages of the present disclosure will become more apparent through the following description of the embodiments of the present disclosure with reference to the accompanying drawings, in which:

[0021] Figure 1 The system architecture to which the method for determining the structural parameters of a vehicle roof insulator according to an embodiment of the present disclosure can be applied is schematically shown;

[0022] Figure 2 A flowchart of a method for determining structural parameters of a vehicle roof insulator according to an embodiment of the present disclosure is schematically shown;

[0023] Figure 3 A schematic diagram schematically shows an example of a process of obtaining multiple sample points by sampling within a preset parameter interval according to the number of sample points to be sampled determined based on the structural information of the roof insulator according to an embodiment of the present disclosure;

[0024] Figure 4 An example schematic diagram of a process of iteratively optimizing a proxy model based on a multi-population genetic algorithm to obtain target structural parameters according to an embodiment of the present disclosure is schematically shown;

[0025] Figure 5A A schematic diagram of the original roof insulator velocity field according to an embodiment of the present disclosure is schematically shown;

[0026] Figure 5B A schematic diagram of a pit roof insulator velocity field according to an embodiment of the present disclosure is schematically shown;

[0027] Fig. 6A A schematic diagram schematically shows the original roof insulator pressure according to an embodiment of the present disclosure;

[0028] Figure 6B A schematic diagram schematically illustrates the pressure of a pit roof insulator according to an embodiment of the present disclosure;

[0029] Figure 7 A schematic diagram of the structure of a roof insulator according to an embodiment of the present disclosure is shown; and

[0030] Figure 8 A block diagram of an electronic device suitable for implementing a method for determining structural parameters of a vehicle roof insulator according to an embodiment of the present disclosure is schematically shown. DETAILED DESCRIPTION

[0031] Hereinafter, embodiments of the present disclosure will be described with reference to the accompanying drawings. However, it should be understood that these descriptions are exemplary only and are not intended to limit the scope of the present disclosure. In the following detailed description, for ease of explanation, many specific details are set forth to provide a comprehensive understanding of the embodiments of the present disclosure. However, it is apparent that one or more embodiments may also be implemented without these specific details. In addition, in the following description, descriptions of known structures and technologies are omitted to avoid unnecessary confusion of the concepts of the present disclosure.

[0032] The terms used herein are only for describing specific embodiments and are not intended to limit the present disclosure. The terms "comprise", "include", etc. used herein indicate the existence of the features, steps, operations and / or components, but do not exclude the existence or addition of one or more other features, steps, operations or components.

[0033] All terms (including technical and scientific terms) used herein have the meanings commonly understood by those skilled in the art unless otherwise defined. It should be noted that the terms used herein should be interpreted as having a meaning consistent with the context of this specification and should not be interpreted in an idealized or overly rigid manner.

[0034] When using expressions such as "at least one of A, B, and C, etc.", they should generally be interpreted according to the meaning of the expression commonly understood by those skilled in the art (for example, "a system having at least one of A, B, and C" should include but is not limited to a system having A alone, B alone, C alone, A and B, A and C, B and C, and / or A, B, C, etc.).

[0035] In the technical solution of the present invention, the user information (including but not limited to user personal information, user image information, user device information, such as location information, etc.) and data (including but not limited to data used for analysis, stored data, displayed data, etc.) involved are all information and data authorized by the user or fully authorized by all parties, and the collection, storage, use, processing, transmission, provision, disclosure and application of the relevant data comply with relevant laws, regulations and standards, take necessary confidentiality measures, do not violate public order and good morals, and provide corresponding operation entrances for users to choose to authorize or refuse.

[0036] In the scenario of using personal information for automated decision-making, the methods, devices, and systems provided by the embodiments of the present invention provide users with corresponding operation portals for users to choose to agree or reject the automated decision-making results; if the user chooses to reject, the expert decision-making process will be entered. The expression "automated decision-making" here refers to the activity of automatically analyzing and evaluating an individual's behavioral habits, interests and hobbies, or economic, health, credit status, etc. through computer programs, and making decisions. The expression "expert decision-making" here refers to the activity of making decisions by people who specialize in a certain field, have specialized experience, knowledge and skills, and have reached a certain level of professionalism.

[0037] Aerodynamic resistance is generated during the operation of the train, and as the speed of the train increases, the aerodynamic resistance will also increase. Aerodynamic resistance will not only restrict the increase in train speed, but also increase the energy consumption of the train. Therefore, how to reduce the aerodynamic resistance of the train is an urgent problem to be solved.

[0038] In one example, the drag reduction of the train body itself can be studied, that is, the aerodynamic drag reduction of the train can be achieved by streamlining the train body, reducing the windward area of ​​the train body, or adding a guide device. However, due to the continuous increase in train speed, the efficiency of achieving drag reduction by changing the body structure is gradually decreasing, causing the train drag reduction to reach a bottleneck period.

[0039] In another example, the flow field characteristics of a large number of external insulating structures such as pantographs and insulators on the top of the train can be studied, that is, the resistance on the top of the train can be reduced by optimizing the flow field characteristics of the external insulating structures on the top of the train.

[0040] In the process of realizing the concept of the present disclosure, the inventors found that there are at least the following problems in the related art: how to improve the accuracy of determining the structural parameters of the roof insulator to more effectively achieve aerodynamic drag reduction of the train.

[0041] In order to at least partially solve the technical problems existing in the related art, the present disclosure provides a method for determining the structural parameters of a roof insulator, a roof insulator for a train, and a train, which can be applied to the field of public transportation. The method for determining the structural parameters of a roof insulator comprises: sampling within a preset parameter interval according to the number of sample points to be sampled determined based on the structural information of the roof insulator to obtain a plurality of sample points, wherein the structural information includes a plurality of parameter types for the pit structure of the roof insulator; constructing a proxy model according to the plurality of sample points and the resistance values ​​obtained based on the plurality of sample points; and, based on a multi-population genetic algorithm, iteratively optimizing the proxy model to obtain target structural parameters, wherein the target structural parameters include parameters of the pit structure.

[0042] Figure 1The system architecture of the method for determining the structural parameters of a roof insulator according to an embodiment of the present disclosure is schematically shown. It should be noted that: Figure 1 What is shown is merely an example of a system architecture to which the embodiments of the present disclosure can be applied, in order to help those skilled in the art understand the technical content of the present disclosure, but it does not mean that the embodiments of the present disclosure cannot be used in other devices, systems, environments or scenarios.

[0043] like Figure 1 As shown, the system architecture 100 according to this embodiment may include a first terminal device 101, a second terminal device 102, a third terminal device 103, a network 104 and a server 105. The network 104 is used to provide a medium for a communication link between the first terminal device 101, the second terminal device 102, the third terminal device 103 and the server 105. The network 104 may include various connection types, such as wired, wireless communication links or optical fiber cables, etc.

[0044] The user can use at least one of the first terminal device 101, the second terminal device 102, and the third terminal device 103 to interact with the server 105 through the network 104 to receive or send messages, etc. The first terminal device 101, the second terminal device 102, and the third terminal device 103 can be various electronic devices with display screens and supporting web browsing, including but not limited to smart phones, tablet computers, laptop portable computers, and desktop computers, etc. Alternatively, the first terminal device 101, the second terminal device 102, and the third terminal device 103 can also be various transportation vehicles that support positioning and navigation functions, including but not limited to trains, smart cars, smart school buses, smart trucks, etc.

[0045] The server 105 may be a server that provides various services, such as a background management server (only as an example) that provides support for websites browsed by users using the first terminal device 101, the second terminal device 102, and the third terminal device 103. The background management server may analyze and process the received data such as user requests, and feed back the processing results (such as web pages, information, or data obtained or generated according to user requests) to the terminal device.

[0046] It should be noted that the method for determining the structural parameters of the roof insulator provided in the embodiment of the present disclosure can generally be executed by the server 105. Accordingly, the device for determining the structural parameters of the roof insulator provided in the embodiment of the present disclosure can generally be set in the server 105. Alternatively, the method for determining the structural parameters of the roof insulator provided in the embodiment of the present disclosure can also be executed by the first terminal device 101, the second terminal device 102, and the third terminal device 103. Accordingly, the device for determining the structural parameters of the roof insulator provided in the embodiment of the present disclosure can also be set in the first terminal device 101, the second terminal device 102, and the third terminal device 103.

[0047] It should be understood that Figure 1 The number of terminal devices, networks and servers in the embodiment is only for illustration. Any number of terminal devices, networks and servers may be provided according to implementation requirements.

[0048] It should be noted that the sequence numbers of the operations in the following method are only used as representations of the operations for the purpose of description, and should not be regarded as representing the execution order of the operations. Unless explicitly stated, the method does not need to be executed completely in the order shown.

[0049] The above describes the system architecture of the method for determining the structural parameters of a roof insulator provided by the present disclosure. Figure 2 For example, the process of determining the structural parameters of the roof insulator of the present disclosure is further described.

[0050] Figure 2 A flow chart of a method for determining structural parameters of a roof insulator according to an embodiment of the present disclosure is schematically shown.

[0051] like Figure 2 As shown, the method 200 for determining the structural parameters of the vehicle roof insulator includes operations S210 to S230.

[0052] In operation S210, sampling is performed within a preset parameter interval according to the number of sample points to be sampled determined based on structural information of the roof insulator to obtain a plurality of sample points, wherein the structural information includes a plurality of parameter types for the pit structure of the roof insulator.

[0053] In operation S220 , a proxy model is constructed according to the plurality of sample points and the resistance values ​​obtained based on the plurality of sample points.

[0054] In operation S230, based on a multi-population genetic algorithm, an iterative optimization process is performed on the proxy model to obtain target structural parameters, wherein the target structural parameters include parameters of the pit structure.

[0055] According to an embodiment of the present disclosure, a roof insulator refers to an insulating device used for an electrified railway or a transmission line, which can be installed on a train roof or a transmission tower to support a conductor and provide an insulating function. In order to determine the structural parameters of the roof insulator, the composition of the resistance to which the roof insulator is subjected can be analyzed. By increasing the air pressure strength on the leeward side of the roof insulator and reducing the pressure difference resistance formed by the front and rear pressure difference, the resistance to which the roof insulator is subjected can be effectively reduced.

[0056] According to the embodiments of the present disclosure, a deflected airflow is generated in the normal flow field of the roof insulator, and the deflected airflow offsets the downwind airflow, thereby reducing the generation of eddy currents on the leeward side of the insulator, weakening the intensity of turbulent motion, thereby reducing energy loss, increasing the leeward side air pressure, and reducing the pressure difference resistance. At the same time, due to the existence of the deflected airflow, a cleaning effect is also produced on the roof insulator, so that the accumulation of dirt on the insulator is reduced. In addition, due to the increase in the leeward side air pressure, the arc blowing ability of the airflow is improved, so that the discharge path is enlarged, and the flashover voltage of the roof insulator is increased.

[0057] According to the embodiments of the present disclosure, when determining the structural parameters of the roof insulator, it can be considered to weaken the turbulence intensity of the roof insulator to reduce the wake vortex; use the deflected airflow to clean the roof insulator; and enhance the arc blowing effect of the airflow to increase the flashover voltage of the roof insulator.

[0058] According to an embodiment of the present disclosure, the structural information of the roof insulator may include multiple parameter types for the pit structure of the roof insulator. Multiple parameter types may be used to define the structural features of the pit structure of the roof insulator. The specific parameter types may be configured according to actual business needs and are not limited here. For example, the parameter types may include the pit diameter of the pit, the pit depth of the pit, and the pit arrangement angle between the pits.

[0059] According to an embodiment of the present disclosure, the number of sample points to be sampled may be determined based on the structural information of the roof insulator. For example, the number of sample points to be sampled may be determined based on the number of parameter types included in the structural information. Alternatively, the number of sample points to be sampled may be determined based on the composition of the parameter types included in the structural information.

[0060] According to an embodiment of the present disclosure, each parameter type may have a corresponding preset parameter interval. The preset parameter interval refers to a predefined range of parameter values ​​of the parameter type. After obtaining the number of sample points to be sampled, sampling can be performed within the preset parameter interval according to the number to obtain multiple sample points. The sampling method may be uniform sampling or sampling according to a preset strategy, etc. The sample point may refer to a specific parameter combination obtained by sampling in the pit structure design space of the roof insulator.

[0061] According to an embodiment of the present disclosure, after obtaining a plurality of sample points, a simulation analysis may be performed on the plurality of sample points to obtain a resistance value of a roof insulator constructed based on the sample points. The specific simulation method may be configured according to actual business needs and is not limited here. After obtaining the resistance value, an agent model may be constructed based on the plurality of sample points and the resistance value. The agent model may be a statistical model, a machine learning model, or any other model that can predict outputs based on input parameters.

[0062] According to an embodiment of the present disclosure, after obtaining the proxy model, the proxy model can be iteratively optimized based on a multi-population genetic algorithm to obtain the target structural parameters. The multi-population genetic algorithm imitates the principles of natural selection and genetics, and improves the search efficiency and avoids falling into the local optimal solution by maintaining multiple populations and allowing information exchange between them. Iterative optimization processing refers to the process of improving the proxy model through repeated iterations to obtain the target structural parameters. In this process, for each round, the performance of the proxy model of the current round can be evaluated, and the proxy model of the next round can be adjusted according to the evaluation results. The target structural parameters refer to the optimal design parameter combination of the roof insulator pit structure obtained by optimizing the multi-population genetic algorithm.

[0063] According to the embodiment of the present disclosure, the number of sample points is determined according to multiple parameter types of the pit structure of the roof insulator, and sampling is performed within a preset parameter range to obtain multiple sample points, and then a proxy model is constructed based on these sample points combined with resistance values, so that the model can predict the performance of the insulator under different structural parameters. On this basis, the proxy model is iteratively optimized by using a multi-population genetic algorithm, and finally the target structural parameters of the optimal pit structure are obtained, which not only improves the design efficiency, but also ensures the optimization of the performance of the insulator, which helps to improve the overall performance and reliability of the roof insulator.

[0064] Reference below Figure 3 and Figure 4 , the method 200 for determining the structural parameters of the roof insulator according to an embodiment of the present invention is further described.

[0065] According to an embodiment of the present disclosure, the roof insulator may include a core rod, a plurality of large sheds and a small shed arranged at intervals. The pit structure may include a plurality of pits, and the plurality of pits are arranged on the surface of the core rod. The parameter type may include a pit diameter of the pit, a pit depth of the pit, and a pit arrangement angle between the pits.

[0066] According to the embodiments of the present disclosure, the core rod refers to the central structural part of the roof insulator, which is usually a long rod-shaped object, serving as the main body and supporting structure of the roof insulator. The large umbrella skirt and the small umbrella skirt refer to the umbrella-shaped structure on the roof insulator, which can be arranged at intervals around the core rod. The specific setting method of the large umbrella skirt and the small umbrella skirt can be configured according to actual business needs and is not limited here. For example, the umbrella skirt can be 31.55mm away from the top of the insulator, the number of large umbrella skirts can be 4, the number of small umbrella skirts can be 3, the radius of the large umbrella skirt can be 105mm, the radius of the small umbrella skirt can be 87mm, the thickness of the large umbrella skirt can be 15.5mm, the thickness of the small umbrella skirt can be 11.7mm, and the interval between the large umbrella skirt and the small umbrella skirt can be 28.3mm.

[0067] According to an embodiment of the present disclosure, a plurality of pits can increase the friction force on the core rod surface. The pit diameter refers to the diameter of the pit, which can affect the structural strength of the pit and the contact area with the outer insulating shed sheath. The pit depth refers to the depth of the pit, which can affect the function of the pit and the combination effect with the outer insulating shed sheath. The pit arrangement angle refers to the arrangement angle of the pit on the core rod surface, which can affect the performance and stability of the roof insulator.

[0068] According to the embodiment of the present disclosure, by using the core rod as the core support of the insulator, combined with the large shed and the small shed arranged at intervals, the design of the insulator provides insulation protection and structural strength. On this basis, the pit structure on the surface of the core rod is designed by adjusting the three key parameters of the pit diameter, the pit depth and the pit arrangement angle. Since the pit diameter affects the contact area, the pit depth affects the structural strength, and the pit arrangement angle affects the overall symmetry and stress distribution, the pit structure can generate deflected airflow at the pit, significantly reduce the size of the vortex on the leeward side, increase the leeward side air pressure of the roof insulator, and reduce the front and rear pressure difference of the roof insulator, thereby achieving the reduction of the pressure difference resistance of the roof insulator. In addition, due to the presence of the pit, a deflected airflow can be generated on the surface of the insulator, and the deflected airflow is used to achieve the cleaning effect of the insulator, reducing the accumulation of dirt on the roof insulator. In addition, the setting of the pit structure can also improve the arc blowing ability of the roof insulator on the leeward side under the high-speed airflow environment, increase the discharge path of the roof insulator, and improve the flashover voltage of the roof insulator under the high-speed airflow environment.

[0069] According to an embodiment of the present disclosure, operation S210 may include the following operations.

[0070] According to the first number of parameter types, a second number of sample points to be sampled is determined. Based on the second number, Latin hypercube sampling is performed in the diameter parameter interval, the depth parameter interval, and the angle parameter interval to obtain a second number of sample diameter parameters, a second number of sample depth parameters, and a second number of sample arrangement angle parameters. According to the second number of sample diameter parameters, the second number of sample depth parameters, and the second number of sample arrangement angle parameters, a second number of sample points is determined.

[0071] According to an embodiment of the present disclosure, the preset parameter interval may include a diameter parameter interval, a depth parameter interval, and an angle parameter interval. The diameter parameter interval may be used to define a sampling range of a pit diameter, the depth parameter interval may be used to define a sampling range of a pit depth, and the angle parameter interval may be used to define a sampling range of a pit arrangement angle. In one example, the diameter parameter interval may be 1.8 mm to 3 mm, the depth parameter interval may be 0.3 mm to 0.8 mm, and the angle parameter interval may be 4° to 18°.

[0072] According to an embodiment of the present disclosure, the second number of sample points to be sampled may be determined according to the first number of parameter types. The second number may be determined as shown in the following formula (1).

[0073] (1);

[0074] Wherein, p represents the second number of sample points to be sampled, and n represents the first number of parameter types. Taking the parameter types including the above-mentioned pit diameter, pit depth and pit arrangement angle as an example, the second number of sample points to be sampled is 10.

[0075] According to an embodiment of the present disclosure, after determining the second number, for each parameter type, a second number of specific parameters of the parameter type can be sampled in a preset parameter interval of the parameter type. For example, for the pit diameter, 10 sample diameter parameters can be sampled in the diameter parameter interval. Alternatively, for the pit depth, 10 sample depth parameters can be sampled in the depth parameter interval. Alternatively, for the pit arrangement angle, 10 sample arrangement angle parameters can be sampled in the angle parameter interval.

[0076] According to the embodiments of the present disclosure, the specific sampling method can be configured according to actual business needs and is not limited here. For example, the Latin hypercube sampling method can be used for sampling. Latin hypercube sampling (LHS) can be used to generate sample points that are approximately uniformly distributed. The Latin hypercube sampling method can make the sample points taken as evenly distributed as possible within the set parameter range to ensure that the sample points of the subsequent proxy model are more uniform and the proxy model is more accurate. After obtaining 10 sample diameter parameters, 10 sample depth parameters, and 10 sample arrangement angle parameters, 10 groups of parameter combinations can be formed, and the 10 groups of parameter combinations are determined as 10 sample points.

[0077] According to the embodiments of the present disclosure, by determining the number of sample points according to the number of parameter types and using the Latin hypercube sampling method, sample points are uniformly collected in each parameter interval, ensuring the uniform distribution of sample points in each parameter interval, and improving the representativeness and coverage of sample points. In addition, since the parameter interval covers three key dimensions of pit diameter, pit depth and pit arrangement angle, by comprehensively considering these parameter types and using these sample points for subsequent model construction and optimization, efficient optimization of the roof insulator pit structure design can be achieved.

[0078] Figure 3 The diagram schematically shows an example process of obtaining a plurality of sample points by sampling within a preset parameter interval according to the number of sample points to be sampled determined based on the structural information of the roof insulator according to an embodiment of the present disclosure.

[0079] like Figure 3 As shown in 300 , the structural information 301 of the roof insulator may include a plurality of parameter types for the pit structure 301_1 of the roof insulator. For example, the parameter type may include a pit diameter 302 , a pit depth 303 , and a pit arrangement angle 304 .

[0080] In one example, for the pit diameter 302, Latin hypercube sampling can be performed in a diameter parameter interval 305 based on the second number to obtain a second number of sample diameter parameters 308. For the pit depth 303, Latin hypercube sampling can be performed in a depth parameter interval 306 based on the second number to obtain a second number of sample depth parameters 309. For the pit arrangement angle 304, Latin hypercube sampling can be performed in an angle parameter interval 307 based on the second number to obtain a second number of sample arrangement angle parameters 310. On this basis, according to the second number of sample diameter parameters 308, the second number of sample depth parameters 309, and the second number of sample arrangement angle parameters 310, a second number of sample points 311 is determined.

[0081] According to an embodiment of the present disclosure, operation S220 may include the following operations.

[0082] The finite element model constructed based on multiple sample points is simulated using simulation tools to obtain the resistance value. The proxy model is constructed based on the mapping relationship between multiple sample diameter parameters, multiple sample depth parameters, multiple sample arrangement angle parameters and the resistance value.

[0083] According to an embodiment of the present disclosure, the plurality of sample points may include different sample diameter parameters, different sample depth parameters, and different sample arrangement angle parameters. After obtaining the plurality of sample points, a finite element model may be constructed based on the plurality of sample points. The finite element model may be used to simulate the performance of the roof insulator under different design parameters, such as stress, strain, etc.

[0084] According to an embodiment of the present disclosure, after obtaining a finite element model, a simulation tool can be used to simulate the finite element model to obtain a resistance value. A simulation tool refers to a software tool used to simulate the behavior of a real world or theoretical model. The resistance value refers to the output result obtained during the simulation process, which represents the resistance of the roof insulator under different sample point design parameters.

[0085] According to an embodiment of the present disclosure, a geometric model of a roof insulator can be created based on multiple sample points, and its material properties, such as elastic modulus, Poisson's ratio, etc., can be defined. The geometric model is divided into a finite number of small units to form a finite element mesh. A suitable material model (such as linear elasticity, elastoplasticity, etc.) is selected for the geometric model, and boundary conditions such as fixed supports or free boundaries are applied. According to the simulation purpose, corresponding loads are applied to the model, such as simulating the effects of wind loads, deadweight, etc. on the roof insulator. The finite element solver is run to calculate the response of the roof insulator under given sample point parameters, such as displacement, stress, and strain. In addition, after the simulation is completed, post-processing operations can also be performed, such as viewing stress distribution diagrams, calculating stress concentration in specific areas, or evaluating the deformation of the overall structure.

[0086] According to an embodiment of the present disclosure, after obtaining the resistance value, a proxy model can be constructed based on multiple sample points and the resistance value. The proxy model can approximate the output of the complex model by constructing a corresponding relationship between input parameters (sample diameter parameters, sample depth parameters, sample arrangement angle parameters) and output results (resistance value), that is, determining the optimal pit structure parameters. For example, the proxy model can be a kriging proxy model.

[0087] According to the embodiments of the present disclosure, by using a simulation tool to simulate the finite element model constructed based on these sample points, the performance of the insulator under different design parameters can be simulated, thereby obtaining the resistance value. On this basis, by constructing a proxy model according to the mapping relationship between the sample parameters and the corresponding resistance values, the proxy model can accurately simulate the insulator, thereby quickly predicting the performance of any design parameter combination, which helps to improve the efficiency and accuracy of the insulator optimization design.

[0088] According to an embodiment of the present disclosure, operation S230 may include the following operations.

[0089] Based on the proxy model, multiple points to be optimized are generated, wherein the multiple points to be optimized include different diameter parameters to be optimized, different depth parameters to be optimized, and different arrangement angle parameters to be optimized. The multiple points to be optimized are iteratively optimized with the parameters of each of the multiple parameter types as optimization parameters and the minimized resistance value as the optimization target to obtain the target point, and the diameter parameter to be optimized, the depth parameter to be optimized, and the arrangement angle parameter to be optimized of the target point are determined as the target structural parameters.

[0090] According to an embodiment of the present disclosure, the point to be optimized refers to a parameter combination whose final value has not yet been determined in the design space of the proxy model. The optimization parameter refers to the parameter used to guide the search for the best solution during the optimization process, namely the diameter, depth and arrangement angle parameters of the pits.

[0091] According to an embodiment of the present disclosure, with the optimization goal of reducing the resistance value of the roof insulator under specific conditions as a guide, multiple points to be optimized are iteratively optimized to obtain a target point. The target point refers to the best parameter combination point determined after iterative optimization. After obtaining the target point, the diameter parameter to be optimized, the depth parameter to be optimized, and the arrangement angle parameter to be optimized of the target point can be determined as the target structural parameters.

[0092] According to an embodiment of the present disclosure, the resistance objective function may be composed of a prediction function constructed by a proxy model as shown in the following formula (2). The resistance objective function may refer to a single-objective optimization algorithm with pit diameter, pit arrangement angle, and pit depth as optimization parameters and resistance value as optimization target.

[0093] (2);

[0094] in, Representation Agent Model, Characterization parameter combination, Characterize the resistance value, Characterize the resistance objective function.

[0095] According to the embodiments of the present disclosure, by generating multiple points to be optimized based on the proxy model, taking the different diameter, depth and arrangement angle parameters included in each point to be optimized as optimization parameters, and taking the minimization of resistance value as the optimization target, the multiple points to be optimized are iteratively optimized, and the best solution can be found in the complex design space. On this basis, the parameter combination finally obtained by iterative optimization is determined as the target structural parameter, which represents the optimal design of the roof insulator pit structure, and can minimize the resistance value while ensuring the performance, thereby improving the automation and precision optimization of the roof insulator pit structure design.

[0096] The iterative process of the multi-population genetic algorithm can include the initialization population stage, the fitness evaluation stage, the selection stage, the crossover stage and the mutation stage. In the initialization population stage, the above-mentioned multiple points to be optimized can be used as the beginning of the population, each solution is an individual, and the collection of individuals is called the population. In the fitness evaluation stage, the quality of each individual in the population can be evaluated according to the fitness function. In the selection stage, excellent individuals can be selected as parents according to fitness to generate the next generation. In the crossover stage, new offspring individuals can be generated through crossover operations. In the mutation stage, the chromosomes of offspring individuals can be randomly mutated with a certain probability to increase the diversity of the population.

[0097] In the iterative process, the above-mentioned stages can be repeatedly executed until a predetermined end condition is met, and the solution obtained when the predetermined end condition is met is determined as the target structure parameter. The predetermined end condition can be configured according to actual business needs and is not limited here. For example, the predetermined end condition may include at least one of the following: the fitness meets the fitness threshold, the fitness convergence speed meets the fitness convergence speed threshold, or the iterative process reaches a preset number of iterations.

[0098] According to an embodiment of the present disclosure, a multi-population genetic algorithm has a preset crossover probability, and the iterative optimization process includes a crossover operation. In this case, the parameters of each of the multiple parameter types are used as optimization parameters, and minimizing the resistance value is used as the optimization goal. The iterative optimization process of multiple points to be optimized may include the following operations.

[0099] Two first points to be optimized are randomly determined from a plurality of points to be optimized. Based on a preset crossover probability, it is determined whether it is necessary to perform a crossover operation on the parameters of the two first points to be optimized, wherein the crossover operation is used to exchange parameters of corresponding parameter types of the two first points to be optimized to change the parameters of the two first points to be optimized. If it is necessary to perform a crossover operation on the parameters of the two first points to be optimized, the parameters of corresponding parameter types of the two first points to be optimized are exchanged to obtain the two first points to be optimized after the parameters are changed.

[0100] According to an embodiment of the present disclosure, the preset crossover probability represents the probability of performing a crossover operation on each pair of solutions in each iteration process. The preset crossover probability determines the frequency of the crossover operation in the algorithm, thereby affecting the search capability and convergence speed of the algorithm.

[0101] According to an embodiment of the present disclosure, the number of points to be optimized can be 200, the population size can be 10, and the preset crossover probability can be a random value between 0.7 and 0.9 to ensure the randomness of the crossover probability of each offspring. The first point to be optimized refers to the point to be optimized that participates in the crossover operation. For every two first points to be optimized, it can be determined whether the parameters of the two first points to be optimized need to be crossover-operated based on the preset crossover probability.

[0102] According to the embodiments of the present disclosure, the crossover operation refers to generating new offspring individuals by combining the gene information of the parent individuals, that is, by exchanging the parameters of the corresponding parameter types of the two parent individuals to change the parameters of the two parent individuals. For example, the parameters of the corresponding parameter types of the two first points to be optimized can be exchanged to obtain the two first points to be optimized after the parameters are changed.

[0103] According to the embodiments of the present disclosure, by presetting the crossover probability, a crossover operation can be performed between two randomly selected first points to be optimized, that is, whether to exchange the parameters of the two points is determined according to the set probability, which helps to generate new points to be optimized and increases the diversity of the population. It not only accelerates the optimization process, but also increases the possibility of finding the global optimal solution, making the design of the roof insulator more accurate and efficient.

[0104] According to an embodiment of the present disclosure, a multi-population genetic algorithm has a preset mutation probability, and the iterative optimization process includes a mutation operation. In this case, the parameters of each of the multiple parameter types are used as optimization parameters, and minimizing the resistance value is used as the optimization goal. The iterative optimization process of the multiple points to be optimized can also include the following operations.

[0105] Two second points to be optimized are randomly determined from a plurality of points to be optimized. Based on a preset mutation probability, it is determined whether it is necessary to perform a mutation operation on the parameters of each of the two second points to be optimized, wherein the mutation operation is used to exchange parameters of different parameter types of a second point to be optimized to change the parameters of a second point to be optimized. When it is necessary to perform a mutation operation on the parameters of a second point to be optimized, the parameters of different parameter types are exchanged to obtain two second points to be optimized after the parameters are changed.

[0106] According to an embodiment of the present disclosure, the preset mutation probability refers to the probability of individual parameters mutating during each iteration. The preset mutation probability determines the frequency of mutation operations in the algorithm, thereby affecting the algorithm's search capability and convergence speed.

[0107] According to an embodiment of the present disclosure, the number of points to be optimized can be 200, the population size can be 10, and the preset mutation probability can be a random value between 0.001 and 0.05 to ensure the randomness of the mutation probability of each offspring. The second point to be optimized refers to the point to be optimized that participates in the mutation operation. For every two second points to be optimized, it can be determined whether the parameters of the two second points to be optimized need to be mutated based on the preset mutation probability.

[0108] According to the embodiments of the present disclosure, the mutation operation refers to forming a new individual by randomly changing the gene values ​​at certain loci in the individual chromosome encoding string. For example, parameters of different parameter types can be exchanged to obtain two second points to be optimized after the parameters are changed.

[0109] According to an embodiment of the present disclosure, the target structural parameters may be a pit diameter of 2 mm, a pit arrangement angle of 12°, and a pit depth of 0.5 mm.

[0110] According to the embodiments of the present disclosure, by presetting the mutation probability, a mutation operation can be performed between two randomly selected second points to be optimized, that is, whether to mutate the parameters of the two points is determined according to the set probability, which helps to generate new points to be optimized and increases the diversity of the population. It not only improves the flexibility of the optimization process, but also increases the possibility of finding the global optimal solution, making the design of the roof insulator more accurate and efficient.

[0111] Figure 4 The diagram schematically shows an example of a process of iteratively optimizing a proxy model based on a multi-population genetic algorithm to obtain target structural parameters according to an embodiment of the present disclosure.

[0112] like Figure 4 As shown, in 400, multiple points to be optimized 402 can be generated based on the proxy model 401. For example, the multiple points to be optimized 402 can include a point to be optimized 402_1, a point to be optimized 402_2, ..., a point to be optimized 402_M, where M is a positive integer. For the above multiple points to be optimized 402, the multiple points to be optimized 402 can be iteratively optimized with the parameters of the multiple parameter types as optimization parameters and the minimized resistance value as the optimization target to obtain a target point 407, and the diameter parameter to be optimized, the depth parameter to be optimized, and the arrangement angle parameter to be optimized of the target point 407 are determined as the target structure parameter 408.

[0113] In one example, for the crossover link, the first point to be optimized 403 can be randomly determined from the multiple points to be optimized 402. After obtaining the first point to be optimized 403, operation S410 can be performed. In operation S410, it can be determined whether it is necessary to perform a crossover operation on the parameters of the two first points to be optimized 403 according to the preset crossover probability? If so, the parameters of the corresponding parameter types of the two first points to be optimized 403 can be exchanged to obtain the two first points to be optimized 404 after the parameters are changed. If not, the above operation of determining the first point to be optimized 403 can be repeated.

[0114] In another example, for the mutation link, a second point to be optimized 405 can be randomly determined from the multiple points to be optimized 402. After obtaining the second point to be optimized 405, operation S420 can be performed. In operation S420, it can be determined whether it is necessary to perform a mutation operation on the parameters of the two second points to be optimized according to the preset mutation probability? If so, the parameters of different parameter types can be exchanged to obtain two second points to be optimized 406 after the parameters are changed. If not, the above operation of determining the second point to be optimized 405 can be repeated.

[0115] By executing the above-mentioned cross-link and variation links, taking the parameters of each of the multiple parameter types as optimization parameters and minimizing the resistance value as the optimization goal, multiple points to be optimized are iteratively optimized to obtain the target point 407, and the diameter parameter to be optimized, the depth parameter to be optimized and the arrangement angle parameter to be optimized of the target point 407 are determined as the target structure parameters 408.

[0116] According to the embodiments of the present disclosure, after obtaining the target structural parameters, the target structural parameters can be applied to the finite element model to perform fluid dynamics simulation verification to obtain simulation results. Figure 5A , Figure 5B , Fig. 6A and Figure 6B , a comparison is made between the simulation results of the original roof insulator in the related art and the pit roof insulator obtained by the method 200 for determining the structural parameters of the roof insulator according to the embodiment of the present invention.

[0117] Figure 5A A schematic diagram of an original roof insulator velocity field according to an embodiment of the present disclosure is schematically shown. Figure 5B A schematic diagram of a pit roof insulator velocity field according to an embodiment of the present disclosure is schematically shown. Fig. 6A A schematic diagram schematically illustrates the original roof insulator pressure according to an embodiment of the present disclosure. Figure 6B A schematic diagram of pit roof insulator pressure according to an embodiment of the present disclosure is schematically shown.

[0118] like Figure 5AAs shown in Figure 5, 500A is the velocity field of the original roof insulator at 100m / s; Figure 5B As shown in Figure 5, 500B is the velocity field of the pit roof insulator at 100 m / s. Fig. 6A As shown in the figure, 600A is the pressure of the original roof insulator; Figure 6B As shown, 600B is the pressure of the pit roof insulator.

[0119] In summary Figure 5A to Figure 6B As shown, the resistance distribution comparison between the original roof insulator and the pit roof insulator can be obtained as shown in Table 1 below.

[0120] Table 1

[0121]

[0122] The above are merely exemplary embodiments, but are not limited thereto, and may also include other methods for determining structural parameters of roof insulators known in the art, as long as the overall performance and reliability of the roof insulators can be improved.

[0123] The above describes the method for determining the structural parameters of the roof insulator provided by the present disclosure. Figure 7 For example, the roof insulator designed based on the structural parameter determination method of the roof insulator disclosed in the present invention is further described.

[0124] Figure 7 A schematic structural diagram of a roof insulator according to an embodiment of the present disclosure is shown schematically.

[0125] like Figure 7 As shown, the roof insulator 700 may include: a core rod 701, a plurality of large sheds 702 and small sheds 703 arranged at intervals.

[0126] The actual fixing height of the core rod 701 may be 400 mm. In the simulation process, for the convenience of simulation calculation, the hardware and base structure of the roof insulator 700 may be omitted, the actual simulation structure height is 330 mm, and the cross-sectional radius of the core rod 701 is 32 mm.

[0127] The surface of the core rod 701 may be provided with a pit structure. The pit structure includes a plurality of pits, for example, pit 704 and pit 705. The target structural parameters of the pits are obtained using the structural parameter determination method 200 of the roof insulator. The target structural parameters may include pit diameter, pit depth, and pit arrangement angle. The pit arrangement angle refers to the angle between the pits, for example, the pit arrangement angle may refer to the angle between the first column of pits 706 and the second column of pits 707. For the description of the pit diameter, pit depth, and pit arrangement angle, please refer to the relevant content above, which will not be repeated here.

[0128] The shed can be 31.55mm away from the top of the insulator, the number of large sheds can be 4, the number of small sheds can be 3, the radius of the large shed can be 105mm, the radius of the small shed can be 87mm, the thickness of the large shed can be 15.5mm, the thickness of the small shed can be 11.7mm, and the interval between the large shed and the small shed can be 28.3mm.

[0129] According to an embodiment of the present disclosure, a roof insulator including a core rod, a plurality of large sheds and small sheds arranged at intervals, and a pit structure on the surface of the core rod is designed. Since the pit structure includes a plurality of pits, target structural parameters of the pits are determined using structural parameters of the roof insulator. By adding the pit structure to the core rod, when a high-speed airflow flows through, the non-smooth surface structure can reduce the aerodynamic resistance of the roof insulator by reducing the front and rear pressure difference of the roof insulator. Moreover, the pit structure can generate small vortices when the high-speed airflow flows through, which clean the surface of the insulator core rod, thereby reducing the amount of dirt accumulated on the roof insulator. Therefore, the roof insulator can maintain electrical insulation performance while improving mechanical stability and durability by optimizing the parameters of the pit structure, thereby achieving a comprehensive improvement in the performance of the roof insulator and ensuring its reliability and safety in a high-voltage electrical environment.

[0130] According to an embodiment of the present disclosure, the target structural parameters may include a pit diameter, a pit depth, and a pit arrangement angle between pits.

[0131] According to an embodiment of the present disclosure, the pit diameter is located in the diameter parameter interval, and the diameter parameter interval can be used to limit the sampling range of the pit diameter. For example, the diameter parameter interval includes 1.8mm~3mm. The pit depth is located in the depth parameter interval, and the depth parameter interval can be used to limit the sampling range of the pit depth. For example, the depth parameter interval includes 0.3mm~0.8mm. The pit arrangement angle is located in the angle parameter interval, and the angle parameter interval can be used to limit the sampling range of the pit arrangement angle. For example, the angle parameter interval includes 4°~18°.

[0132] According to the embodiments of the present disclosure, the setting of the diameter parameter range ensures that the pit can provide sufficient mechanical engagement without excessively increasing material consumption or affecting the insulation performance. The setting of the depth parameter range balances the structural strength and manufacturing cost while ensuring the functionality of the pit. The setting of the angle parameter range helps to optimize the aerodynamic performance of the roof insulator, reduce the impact of wind load, and ensure the stability of the structure. Therefore, through these precise parameter controls, the resistance of the roof insulator in a high-speed airflow environment can be effectively reduced, and the amount of dirt accumulation can be reduced; at the same time, compared with the traditional structural insulator, the creepage distance is increased and the flashover voltage is increased in an environment without airflow due to the presence of the pit structure. When there is airflow, the arc blowing ability is enhanced, which further improves the insulation performance, so that the design of the roof insulator optimizes the mechanical stability and durability while ensuring the electrical insulation performance, and improves the reliability and safety of the product.

[0133] According to an embodiment of the present disclosure, there is also provided a train including at least one roof insulator for a train.

[0134] Figure 8 A block diagram of an electronic device suitable for implementing a method for determining structural parameters of a vehicle roof insulator according to an embodiment of the present disclosure is schematically shown. Figure 8 The electronic device shown is only an example and should not bring any limitation to the functions and scope of use of the embodiments of the present disclosure.

[0135] like Figure 8 As shown, the computer electronic device 800 according to the embodiment of the present disclosure includes a processor 801, which can perform various appropriate actions and processes according to the program stored in the read-only memory (ROM) 802 or the program loaded from the storage part 809 to the random access memory (RAM) 803. The processor 801 may include, for example, a general-purpose microprocessor (such as a CPU), an instruction set processor and / or a related chipset and / or a special-purpose microprocessor (for example, an application-specific integrated circuit (ASIC)), etc. The processor 801 may also include an onboard memory for caching purposes. The processor 801 may include a single processing unit or multiple processing units for performing different actions of the method flow according to the embodiment of the present disclosure.

[0136] In RAM 803, various programs and data required for the operation of electronic device 800 are stored. Processor 801, ROM 802 and RAM 803 are connected to each other via bus 804. Processor 801 performs various operations of the method flow according to the embodiment of the present disclosure by executing the program in ROM 802 and / or RAM 803. It should be noted that the program can also be stored in one or more memories other than ROM 802 and RAM 803. Processor 801 can also perform various operations of the method flow according to the embodiment of the present disclosure by executing the program stored in the one or more memories.

[0137] According to an embodiment of the present disclosure, the electronic device 800 may further include an input / output (I / O) interface 805, which is also connected to the bus 804. The electronic device 800 may further include one or more of the following components connected to the input / output (I / O) interface 805: an input portion 806 including a keyboard, a mouse, etc.; an output portion 807 including a cathode ray tube (CRT), a liquid crystal display (LCD), etc., and a speaker, etc.; a storage portion 808 including a hard disk, etc.; and a communication portion 809 including a network interface card such as a LAN card, a modem, etc. The communication portion 809 performs communication processing via a network such as the Internet. A drive 810 is also connected to the input / output (I / O) interface 805 as needed. A removable medium 811, such as a magnetic disk, an optical disk, a magneto-optical disk, a semiconductor memory, etc., is installed on the drive 810 as needed, so that the computer program read therefrom is installed into the storage portion 808 as needed.

[0138] According to an embodiment of the present disclosure, the method flow according to an embodiment of the present disclosure can be implemented as a computer software program. For example, an embodiment of the present disclosure includes a computer program product, which includes a computer program carried on a computer-readable storage medium, and the computer program contains a program code for executing the method shown in the flowchart. In such an embodiment, the computer program can be downloaded and installed from the network through the communication part 809, and / or installed from the removable medium 811. When the computer program is executed by the processor 801, the above-mentioned functions defined in the system of the embodiment of the present disclosure are executed. According to an embodiment of the present disclosure, the system, equipment, device, module, unit, etc. described above can be implemented by a computer program module.

[0139] The present disclosure also provides a computer-readable storage medium, which may be included in the device / apparatus / system described in the above embodiment; or may exist independently without being assembled into the device / apparatus / system. The above computer-readable storage medium carries one or more programs, and when the above one or more programs are executed, the method for determining the structural parameters of the roof insulator according to the embodiment of the present disclosure is implemented.

[0140] According to an embodiment of the present disclosure, the computer-readable storage medium may be a non-volatile computer-readable storage medium. For example, it may include, but is not limited to: a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination thereof. In the present disclosure, a computer-readable storage medium may be any tangible medium containing or storing a program that may be used by or in combination with an instruction execution system, apparatus, or device.

[0141] For example, according to an embodiment of the present disclosure, the computer-readable storage medium may include the ROM 802 and / or the RAM 803 described above and / or one or more memories other than the ROM 802 and the RAM 803 .

[0142] An embodiment of the present disclosure also includes a computer program product, which includes a computer program, and the computer program contains a program code for executing the method provided by the embodiment of the present disclosure. When the computer program product runs on an electronic device, the program code is used to enable the electronic device to implement the method for determining the structural parameters of the roof insulator provided by the embodiment of the present disclosure.

[0143] When the computer program is executed by the processor 801, the above functions defined in the system / device of the embodiment of the present disclosure are executed. According to the embodiment of the present disclosure, the system, device, module, unit, etc. described above can be implemented by a computer program module.

[0144] In one embodiment, the computer program may rely on tangible storage media such as optical storage devices, magnetic storage devices, etc. In another embodiment, the computer program may also be transmitted and distributed in the form of signals on a network medium, and downloaded and installed through the communication part 809, and / or installed from a removable medium 811. The program code contained in the computer program may be transmitted using any appropriate network medium, including but not limited to: wireless, wired, etc., or any suitable combination of the above.

[0145] According to an embodiment of the present disclosure, the program code for executing the computer program provided by the embodiment of the present disclosure can be written in any combination of one or more programming languages. Specifically, these computing programs can be implemented using high-level process and / or object-oriented programming languages, and / or assembly / machine languages. Programming languages ​​include, but are not limited to, Java, C++, python, "C" language or similar programming languages. The program code can be executed entirely on the user computing device, partially on the user device, partially on the remote computing device, or entirely on the remote computing device or server. In the case of a remote computing device, the remote computing device can be connected to the user computing device through any type of network, including a local area network (LAN) or a wide area network (WAN), or can be connected to an external computing device (for example, using an Internet service provider to connect through the Internet).

[0146] The flowcharts and block diagrams in the accompanying drawings illustrate the possible architecture, functions and operations of the systems, methods and computer program products according to various embodiments of the present disclosure. In this regard, each box in the flowchart or block diagram may represent a module, a program segment, or a part of a code, and the above-mentioned module, program segment, or a part of the code contains one or more executable instructions for implementing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the box may also occur in an order different from that marked in the accompanying drawings. For example, two boxes represented in succession can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each box in the block diagram or flowchart, and the combination of boxes in the block diagram or flowchart, can be implemented with a dedicated hardware-based system that performs the specified function or operation, or can be implemented with a combination of dedicated hardware and computer instructions. It can be understood by those skilled in the art that the features recorded in the various embodiments and / or claims of the present disclosure can be combined and / or combined in a variety of ways, even if such a combination or combination is not explicitly recorded in the present disclosure. In particular, without departing from the spirit and teaching of the present disclosure, the features described in the various embodiments and / or claims of the present disclosure may be combined and / or combined in a variety of ways. All of these combinations and / or combinations fall within the scope of the present disclosure.

[0147] The embodiments of the present disclosure are described above. However, these embodiments are only for illustrative purposes and are not intended to limit the scope of the present disclosure. Although the embodiments are described above separately, this does not mean that the measures in the various embodiments cannot be used in combination to advantage. The scope of the present disclosure is defined by the attached claims and their equivalents. Without departing from the scope of the present disclosure, those skilled in the art may make a variety of substitutions and modifications, which should all fall within the scope of the present disclosure.

Claims

1. A method for determining structural parameters of a roof insulator, comprising: Sampling within a preset parameter interval to obtain a plurality of sample points according to the number of sample points to be sampled determined based on the structural information of the roof insulator, wherein the structural information includes a plurality of parameter types for the pit structure of the roof insulator; constructing a proxy model according to the plurality of sample points and the resistance values ​​obtained based on the plurality of sample points; and Based on a multi-population genetic algorithm, the proxy model is iteratively optimized to obtain target structural parameters, wherein the target structural parameters include parameters of the pit structure.

2. The method according to claim 1, wherein: The roof insulator includes a core rod, a plurality of large sheds and a small shed that are spaced apart from each other, the pit structure includes a plurality of pits that are arranged on the surface of the core rod, and the parameter types include pit diameters of the pits, pit depths of the pits, and pit arrangement angles between the pits.

3. The method according to claim 2, wherein: The preset parameter intervals include a diameter parameter interval, a depth parameter interval and an angle parameter interval; The number of sample points to be sampled determined based on the structural information of the roof insulator is sampled within a preset parameter interval to obtain a plurality of sample points, including: Determining a second number of sample points to be sampled according to the first number of parameter types; Based on the second number, Latin hypercube sampling is performed in the diameter parameter interval, the depth parameter interval, and the angle parameter interval to obtain a second number of sample diameter parameters, a second number of sample depth parameters, and a second number of sample arrangement angle parameters; and A second number of the sample points is determined according to the second number of sample diameter parameters, the second number of sample depth parameters and the second number of sample arrangement angle parameters.

4. The method according to claim 3, wherein: The plurality of sample points include sample diameter parameters that are different from each other, sample depth parameters that are different from each other, and sample arrangement angle parameters that are different from each other; The constructing of the proxy model according to the plurality of sample points and the resistance values ​​obtained based on the plurality of sample points comprises: Using a simulation tool, simulating a finite element model constructed based on the multiple sample points to obtain the resistance value; as well as The proxy model is constructed according to the mapping relationship between the multiple sample diameter parameters, the multiple sample depth parameters, the multiple sample arrangement angle parameters and the resistance value.

5. The method according to any one of claims 1 to 4, wherein: The agent model is iteratively optimized based on a multi-population genetic algorithm to obtain target structural parameters including: Based on the proxy model, generating a plurality of points to be optimized, wherein the plurality of points to be optimized include different diameter parameters to be optimized, different depth parameters to be optimized, and different arrangement angle parameters to be optimized; and Taking the parameters of each of the multiple parameter types as optimization parameters and minimizing the resistance value as the optimization goal, the multiple points to be optimized are iteratively optimized to obtain target points, and the diameter parameters to be optimized, the depth parameters to be optimized and the arrangement angle parameters to be optimized of the target points are determined as the target structural parameters.

6. The method according to claim 5, wherein: The multi-population genetic algorithm has a preset crossover probability, and the iterative optimization process includes a crossover operation; The iterative optimization process of the multiple points to be optimized using the parameters of the multiple parameter types as optimization parameters and minimizing the resistance value as the optimization target comprises: Randomly determine two first points to be optimized from the multiple points to be optimized; Based on the preset crossover probability, determining whether it is necessary to perform a crossover operation on the parameters of each of the two first points to be optimized, wherein the crossover operation is used to exchange parameters of corresponding parameter types of the two first points to be optimized to change the parameters of the two first points to be optimized; and When it is necessary to perform a cross operation on the parameters of the two first points to be optimized, the parameters of the corresponding parameter types of the two first points to be optimized are exchanged to obtain the two first points to be optimized after the parameters are changed.

7. The method according to claim 5, wherein: The multi-population genetic algorithm has a preset mutation probability, and the iterative optimization process includes a mutation operation; The iterative optimization process of the multiple points to be optimized using the parameters of the multiple parameter types as optimization parameters and minimizing the resistance value as the optimization target also includes: Randomly determine two second points to be optimized from the multiple points to be optimized; Based on the preset mutation probability, determining whether it is necessary to perform a mutation operation on the parameters of each of the two second points to be optimized, wherein the mutation operation is used to exchange parameters of different parameter types of the one second point to be optimized to change the parameters of the one second point to be optimized; and When a mutation operation needs to be performed on the parameters of the second point to be optimized, the parameters of the different parameter types are exchanged to obtain two second points to be optimized after the parameters are changed.

8. A roof insulator for a train, wherein: The roof insulator comprises: a core rod, a plurality of large sheds and small sheds arranged at intervals; The surface of the core rod is provided with a pit structure, the pit structure includes a plurality of pits, and the target structural parameters of the pits are obtained by using the method as described in claims 1 to 7.

9. The roof insulator according to claim 8, wherein: The target structural parameters include pit diameter, pit depth, and pit arrangement angles between the pits; The pit diameter is within a diameter parameter range, which includes 1.8 mm to 3 mm; the pit depth is within a depth parameter range, which includes 0.3 mm to 0.8 mm; the pit arrangement angle is within an angle parameter range, which includes 4° to 18°.

10. A train comprising: At least one roof insulator as claimed in claim 8 or 9.

Images