Collision body construction method for train collision test and train collision test method

Abstract

The application provides a collision body construction method for train collision test and a train collision test method, which can be applied to the technical field of rail transit. The method comprises the following steps: obtaining a plurality of initial structure parameter groups of a preset collision area of an initial collision body; for each initial structure parameter group, determining the predicted displacement of the preset collision area under a plurality of preset impact forces according to the initial structure parameter group to obtain a predicted displacement curve; respectively calculating the difference between the plurality of predicted displacement curves and an expected displacement curve to obtain the deviation degree of each initial structure parameter group; and in response to the existence of a deviation degree lower than a preset threshold in the deviation degrees of the initial structure parameter groups, taking the corresponding initial structure parameter group as a target structure parameter group to obtain a target collision body for train collision test, thereby at least partially solving the technical problem of low structure accuracy of the common collision area of the train collision body and achieving the technical effect of improving the effectiveness of the collision body.

Description

Technical Field

[0001] This invention relates to the field of rail transit technology, specifically to a method for constructing a collision body for train collision testing and a train collision testing method. Background Technology

[0002] The collision tester is the core instrument for train collision safety testing. It generates test data through collision safety testing, providing important support for optimizing train safety design, thereby reducing personal injury and train loss in collision accidents.

[0003] In the process of realizing the concept of this invention, it was found that at least the following problems exist in the related technology: the structure of the common collision area of ​​the train collision body in the related technology mostly relies on empirical judgment or physical test to determine, but the structure determined by the above methods is usually less accurate, which makes the collision body usually have poor test results and low effectiveness when conducting train collision safety tests. Summary of the Invention

[0004] In view of the above problems, the present invention provides a method for constructing a collision body for train collision testing and a method for conducting train collision tests.

[0005] According to one aspect of the present invention, a method for constructing a collision body for train collision testing is provided, comprising: acquiring multiple initial structural parameter sets for a preset collision region of an initial collision body; for each initial structural parameter set, determining the predicted displacement of the preset collision region under multiple preset impact forces based on the initial structural parameter set, and obtaining a predicted displacement curve; calculating the difference between the multiple predicted displacement curves and the desired displacement curve respectively, and obtaining the deviation of each initial structural parameter set, wherein the desired displacement curve is obtained by fitting the desired displacement of the preset collision region under multiple preset impact forces; and, in response to a deviation of less than a preset threshold in the deviation of each of the multiple initial structural parameter sets, using the corresponding initial structural parameter set as a target structural parameter set to obtain a target collision body for train collision testing.

[0006] According to an embodiment of the present invention, the method further includes: in response to the current iteration number t, determining the intermediate structural parameter group with the lowest deviation from a plurality of initial structural parameter groups, where t is an integer greater than or equal to 0; if the deviation of the intermediate structural parameter group is determined to be greater than or equal to a preset threshold, comparing the search state judgment parameter determined by the current iteration number with the preset judgment threshold to determine the search state of the t-th iteration, the search state including a local search state or a global search state; based on the search state of the t-th iteration, determining the evaluation value of each of the plurality of initial structural parameter groups for multiple update directions in the search state from the value mapping, the evaluation value being updated during the historical iteration process, the historical iteration process including multiple iteration processes prior to the iteration number t; for each initial structural parameter group, updating the initial structural parameter group to a candidate structural parameter group based on the evaluation value of the initial structural parameter group for multiple update directions in the search state; using the plurality of candidate structural parameter groups as the plurality of initial structural parameter groups for the (t+1)-th iteration, and repeating the above steps until a preset termination condition is met, the preset termination condition including at least one of the following: obtaining a target structural parameter group with a deviation less than a preset threshold and reaching a preset iteration number.

[0007] According to an embodiment of the present invention, the multiple update directions include a target direction; the target direction is used to increase the matching degree between the initial structural parameter group and the intermediate structural parameter group by updating the initial structural parameter group; wherein, updating the initial structural parameter group into a candidate structural parameter group based on the evaluation values ​​of the initial structural parameter group for the multiple update directions in the search state includes: if the evaluation value of the target direction is determined to be the highest based on the evaluation values ​​of the initial structural parameter group for the multiple update directions in the search state, determining the update method for updating to the target direction based on the method determination parameters; updating the initial structural parameter group based on the update method and the intermediate structural parameter group to obtain the candidate structural parameter group, wherein the update method is a linear update method or a spiral update method.

[0008] According to an embodiment of the present invention, updating the initial structure parameter set based on the update method and the intermediate structure parameter set to obtain a candidate structure parameter set includes: when the update method is a linear update method, calculating the difference between the intermediate structure parameter set and the initial structure parameter set to obtain a first distance parameter set characterizing the distance between the intermediate structure parameter set and the initial structure parameter set; and determining the candidate structure parameter set based on the first distance parameter set, the search state judgment parameter, and the intermediate structure parameter set.

[0009] According to an embodiment of the present invention, an initial structural parameter set is updated based on an update method and an intermediate structural parameter set to obtain a candidate structural parameter set, including: when the update method is a spiral update method, calculating the difference between the intermediate structural parameter set and the initial structural parameter set to obtain a second distance parameter set characterizing the distance between the intermediate structural parameter set and the initial structural parameter set; and obtaining the candidate structural parameter set based on the spiral trajectory control parameters, the second distance parameter set, and the intermediate structural parameter set.

[0010] According to an embodiment of the present invention, the multiple update directions further include random directions; updating the initial structural parameter group to a candidate structural parameter group based on the evaluation values ​​of the initial structural parameter group for the multiple update directions in the search state further includes: determining a random structural parameter group from the multiple initial structural parameter groups if the random direction has the highest evaluation value based on the evaluation values ​​of each initial structural parameter group for the multiple update directions in the search state; updating the initial structural parameter group based on the random structural parameter group to obtain the candidate structural parameter group.

[0011] According to an embodiment of the present invention, the above method further includes: when the number of iterations t=0, determining multiple initial structure parameter groups based on multiple parameter types for determining the preset collision region structure, the preset value range of each of the multiple parameter types, and random parameters, wherein each initial structure parameter group contains the structure parameters indicated by each of the multiple parameter types.

[0012] According to an embodiment of the present invention, the search state judgment parameter is based on the change of the number of iterations; the multiple parameter types are determined according to the properties of the preset material used for the initial collider.

[0013] According to an embodiment of the present invention, the method further includes: for each initial structural parameter group in the t-th iteration, comparing the deviation of the initial structural parameter group with the deviation of the corresponding candidate structural parameter group to obtain a comparison result; updating the reward value of the target update direction in the search state of the t-th iteration included in the reward mapping based on the update rule matching the comparison result to obtain an updated reward value, wherein the target update direction is the update direction used in the process of updating the initial structural parameter group to the corresponding candidate structural parameter group; in the value mapping, determining the target evaluation value of the initial structural parameter group in the search state of the (t+1)-th iteration; and updating the evaluation value of the target update direction of the initial structural parameter in the search state of the t-th iteration in the value mapping based on the evaluation value of the target update direction in the search state of the t-th iteration, the updated reward value, and the target evaluation value to obtain an updated value mapping.

[0014] According to an embodiment of the present invention, based on an update rule that matches the comparison result, the reward value of the target update direction included in the reward mapping in the search state of the t-th iteration is updated to obtain the updated reward value. This includes: when the comparison result indicates that the deviation of the initial structural parameter group is greater than the deviation of the candidate structural parameter group, the reward value of the target update direction included in the reward mapping in the search state of the t-th iteration is positively updated to obtain the updated reward value.

[0015] According to an embodiment of the present invention, based on an update rule that matches the comparison result, the reward value of the target update direction included in the reward mapping in the search state of the t-th iteration is updated to obtain the updated reward value. This includes: when the deviation of the initial structural parameter group represented by the comparison result is less than the deviation of the candidate structural parameter group, the reward value of the target update direction included in the reward mapping in the search state of the t-th iteration is negatively updated to obtain the updated reward value.

[0016] According to an embodiment of the present invention, the difference between multiple predicted displacement curves and expected displacement curves is calculated to obtain the deviation of each initial structural parameter group, including: determining the first impact force under multiple preset collision region displacements from the expected displacement curves; for each predicted displacement curve, determining the second impact force under multiple preset collision region displacements from the predicted displacement curves; and calculating the difference between the first impact force and the second impact force corresponding to the same preset collision region displacement based on the preset collision region displacement to obtain the deviation.

[0017] Another aspect of the present invention provides a train collision test method, comprising: using a target collision body constructed according to the above-described collision body construction method for train collision testing, testing the target displacement of a preset collision area of ​​the target collision body under multiple target impact forces, so as to perform a safety assessment of the train based on the target displacement and obtain a safety assessment result; wherein the target impact force is obtained by at least one of the following methods: controlling the train's speed or controlling the target collision area of ​​the train.

[0018] Another aspect of the present invention provides a collision body construction device for train collision testing, comprising: an acquisition module for acquiring multiple initial structural parameter sets for a preset collision region of an initial collision body; a first determination module for determining, for each initial structural parameter set, a predicted displacement of the preset collision region under multiple preset impact forces, thereby obtaining a predicted displacement curve; a calculation module for calculating the differences between the multiple predicted displacement curves and the desired displacement curves, thereby obtaining the deviation of each initial structural parameter set, wherein the desired displacement curve is obtained by fitting the desired displacement of the preset collision region under multiple preset impact forces; and a second determination module for, in response to the existence of a deviation below a preset threshold in the deviation of each of the multiple initial structural parameter sets, using the corresponding initial structural parameter set as a target structural parameter set to obtain a target collision body for train collision testing.

[0019] Another aspect of the present invention provides a train collision testing apparatus, comprising: a testing module for testing a target collision body constructed according to the above-described method for constructing a collision body for train collision testing, and testing the target displacement of a preset collision area of ​​the target collision body under multiple target impact forces, so as to perform a safety assessment of the train based on the target displacement and obtain a safety assessment result; wherein the target impact force is obtained by at least one of the following methods: controlling the train's speed or controlling the target collision area of ​​the train.

[0020] Another aspect of the present invention provides an electronic device comprising: one or more processors; and a memory for storing one or more programs, wherein when the one or more programs are executed by the one or more processors, the one or more processors perform the methods described above.

[0021] Another aspect of the present invention provides a computer-readable storage medium having executable instructions stored thereon, which, when executed by a processor, cause the processor to perform the methods described above.

[0022] Another aspect of the present invention provides a computer program product comprising a computer program that, when executed by a processor, implements the above-described method.

[0023] According to an embodiment of the present invention, by determining the predicted displacement curves of multiple initial structural parameter sets and fitting them with the expected displacement curves, since the expected displacement curves are obtained by fitting the expected displacements of the preset collision region under multiple preset impact forces, the degree of conformity between the initial collision body corresponding to each initial structural parameter set and the expected collision condition can be better evaluated. When there is a deviation below a preset threshold among the multiple deviations determined by the fitting, the corresponding target structural parameter set is determined as the structural parameters of the preset collision region. Therefore, this at least partially solves the technical problem of low structural accuracy of the common collision region of train collision bodies, which often results in poor test performance during train collision safety testing, and achieves the technical effect of improving the effectiveness of the target collision body. Attached Figure Description

[0024] The above-mentioned contents, as well as other objects, features and advantages of the present invention, will become clearer from the following description of embodiments of the present invention with reference to the accompanying drawings.

[0025] Figure 1 The diagram illustrates an application scenario of a collision body construction method and apparatus for train collision testing according to an embodiment of the present invention.

[0026] Figure 2 A flowchart of a collision body construction method for train collision testing according to an embodiment of the present invention is shown.

[0027] Figure 3 A schematic diagram of the desired displacement curve according to an embodiment of the present invention is shown.

[0028] Figure 4 A flowchart of a method for constructing a collision body for train collision testing according to another embodiment of the present invention is shown.

[0029] Figure 5 A flowchart of a train collision test method according to an embodiment of the present invention is shown.

[0030] Figure 6 A structural block diagram of a collision body construction device for train collision testing according to an embodiment of the present invention is shown.

[0031] Figure 7 A structural block diagram of a train collision testing apparatus according to an embodiment of the present invention is shown.

[0032] Figure 8 A block diagram of an electronic device suitable for implementing a collision body construction method for train collision testing, according to an embodiment of the present invention, is shown. Detailed Implementation

[0033] Hereinafter, embodiments of the present invention 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 invention. In the following detailed description, numerous specific details are set forth to provide a thorough understanding of the embodiments of the invention for ease of explanation. However, it will be apparent that one or more embodiments may be practiced without these specific details. Furthermore, descriptions of well-known structures and techniques are omitted in the following description to avoid unnecessarily obscuring the concept of the invention.

[0034] The terminology used herein is for the purpose of describing particular embodiments only and is not intended to limit the invention. The terms “comprising,” “including,” etc., as used herein indicate the presence of the stated features, steps, operations, and / or components, but do not exclude the presence or addition of one or more other features, steps, operations, or components.

[0035] All terms used herein (including technical and scientific terms) have the meanings commonly understood by those skilled in the art, unless otherwise defined. It should be noted that the terms used herein are to be interpreted in a manner consistent with the context of this specification, and not in an idealized or overly rigid way.

[0036] When using expressions such as "at least one of A, B and C", they should generally be interpreted in accordance with the meaning that is commonly understood by those skilled in the art (e.g., "a system having at least one of A, B and C" should include, but is not limited to, a system having A alone, a system having B alone, a system having C alone, a system having A and B, a system having A and C, a system having B and C, and / or a system having A, B and C, etc.).

[0037] In the technical solution of this invention, the user information (including but not limited to user personal information, user image information, user device information, such as location information) and data (including but not limited to data used for analysis, stored data, and displayed data) involved are all information and data authorized by the user or fully authorized by all parties. Furthermore, the collection, storage, use, processing, transmission, provision, disclosure, and application of related data all comply with the relevant laws, regulations, and standards of the relevant countries and regions, take necessary confidentiality measures, do not violate public order and good morals, and provide corresponding operation entry points for users to choose to authorize or refuse.

[0038] During the research, it was found that when the collider is a biological model and the predetermined collision area is the abdomen, the abdomen of the biological model in related technologies typically uses a two-layer polyurethane foam structure. The outer foam is softer and is used to simulate the abdominal fat of the organism, while the inner foam is harder and is used to simulate the abdominal muscles. However, the abdominal structure of an organism includes not only fat and muscle layers but also peritoneum and internal organs. The current abdominal structure of the collider differs significantly from the impact characteristics of the biological abdomen.

[0039] To improve the biomimicry of collision objects, many related technologies focus on modifying the number of foam layers and the connection method in the preset collision area. For example, the preset collision area of ​​the collision object adopts a three-layer structure: a front foam layer, a rear foam layer, and a fabric bag for the preset collision area. However, this structure cannot be considered optimal. Alternatively, the biomimicry of the preset collision area can be improved by enhancing the fit between the flesh and components such as the pelvis, without optimizing the number, thickness, or material of the flesh layers, thus limiting the degree of optimization. Another approach is to divide the preset collision area structure into upper and lower parts, with the upper part containing three layers of foam and the lower part containing three layers of foam and a fabric bag. The hardness and combination of the foam are determined through physical calibration. However, optimizing the preset collision area structure using physical experiments is costly and inefficient, and the structural parameters of the preset collision area rely on manual adjustment, making it difficult to obtain a near-optimal combination.

[0040] In view of this, embodiments of the present invention provide a method for constructing a collision body for train collision testing. Based on a computer simulation system and an optimization algorithm for an initial set of structural parameters, the method can automatically optimize the structural parameters of the preset collision area of ​​the collision body without relying on physical experiments. This reduces the development cost of the preset collision area structure of the collision body, shortens the development cycle, and may yield a better combination of structural parameters.

[0041] Figure 1 The illustration shows an application scenario of a collision body construction method, a train collision testing method, an apparatus, a device, a medium, and a program product for train collision testing according to embodiments of the present invention.

[0042] like Figure 1 As shown, application scenario 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 serves as a medium for providing communication links 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 or wireless communication links, or fiber optic cables, etc.

[0043] Users can use the first terminal device 101, the second terminal device 102, and the third terminal device 103 to interact with the server 105 via the network 104 to receive or send messages, etc. Various communication client applications can be installed on the first terminal device 101, the second terminal device 102, and the third terminal device 103, such as shopping applications, web browser applications, search applications, instant messaging tools, email clients, social media platform software, etc. (for example only).

[0044] The first terminal device 101, the second terminal device 102, and the third terminal device 103 can be various electronic devices with displays and supporting web browsing, including but not limited to smartphones, tablets, laptops, and desktop computers. Alternatively, the first terminal device 101, the second terminal device 102, and the third terminal device 103 can also be various vehicles supporting positioning and navigation functions, including but not limited to trains, smart cars, smart school buses, and smart trucks.

[0045] Server 105 can be a server that provides various services, such as a backend management server that supports websites browsed by users using the first terminal device 101, the second terminal device 102, and the third terminal device 103 (this is just an example). The backend management server can analyze and process data such as received 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 devices.

[0046] It should be noted that the collision body construction method for train collision testing provided in this embodiment of the invention can generally be executed by server 105. Correspondingly, the collision body construction device for train collision testing provided in this embodiment of the invention can generally be located in server 105. The collision body construction method for train collision testing provided in this embodiment of the invention can also be executed by a server or server cluster that is different from server 105 and capable of communicating with the first terminal device 101, the second terminal device 102, the third terminal device 103, and / or server 105. Correspondingly, the collision body construction device for train collision testing provided in this embodiment of the invention can also be located in a server or server cluster that is different from server 105 and capable of communicating with the first terminal device 101, the second terminal device 102, the third terminal device 103, and / or server 105.

[0047] It should be understood that Figure 1 The number of first terminal devices, second terminal devices, third terminal devices, networks, and servers shown in the diagram is merely illustrative. Depending on implementation needs, any number of first terminal devices, second terminal devices, third terminal devices, networks, and servers can be included.

[0048] The following will be based on Figure 1 The described scene, through Figures 2-4 The invention provides a detailed description of the collision body construction method for train collision testing according to embodiments of the invention.

[0049] Figure 2 A flowchart of a collision body construction method for train collision testing according to an embodiment of the present invention is shown.

[0050] like Figure 2As shown, the method includes operations S210 to S240.

[0051] In operation S210, multiple initial structural parameter sets for the preset collision region of the initial collider are obtained.

[0052] In operation S220, for each initial structural parameter group, the predicted displacement of the preset collision area under multiple preset impact forces is determined based on the initial structural parameter group, and the predicted displacement curve is obtained.

[0053] In operation S230, the differences between multiple predicted displacement curves and expected displacement curves are calculated to obtain the deviation of each initial structural parameter group. The expected displacement curve is obtained by fitting the expected displacement of the preset collision area under multiple preset impact forces.

[0054] In operation S240, in response to the existence of a deviation below a preset threshold in the deviation of each of the multiple initial structural parameter sets, the corresponding initial structural parameter set is taken as the target structural parameter set to obtain the target collision body for train collision testing.

[0055] The specific type of the initial collider is not limited; it can be a biological model, such as a dummy. The preset collision area is also not limited; it can be any area prone to collision, such as the abdomen or legs of a biological model.

[0056] An initial set of structural parameters can be used to construct a predetermined collision region for the initial collider. This initial set of structural parameters can include multiple structural parameters. These structural parameters can be determined based on the properties of the predetermined material used for the initial collider. For example, if the predetermined material is foam, the structural parameters could be the number of foam layers, thickness, and hardness, etc.

[0057] The predicted or expected displacement can be the amount of compression of the preset collision area when subjected to impact force.

[0058] The desired displacement can be obtained through real experiments, or by simulating the biomechanical characteristics of real organisms through dynamic models to match the force and displacement laws of real organism muscles and bones, or by obtaining the displacement limit required in the preset safety standards.

[0059] The target structural parameter set can be determined iteratively. In each iteration, the initial structural parameter set for the current iteration number can be obtained, and the predicted displacement curve and the deviation of each initial structural parameter set can be calculated. The iteration stops when there is a target structural parameter set whose deviation is lower than a preset threshold among the multiple initial structural parameter sets for the current iteration number.

[0060] In the implementation process, each initial structural parameter set can simulate the initial collision body determined by the initial structural parameter set based on the preset simulation system. The predicted displacement of its preset collision area under multiple preset impact forces is then obtained by fitting multiple predicted displacements.

[0061] The preset simulation system can simulate preset impact forces and initial collision objects. It can also simulate collision scenarios, such as simulating trains and the target collision area of ​​trains.

[0062] In some embodiments, for experimental convenience, a pendulum can be used to output a preset impact force and determine the desired displacement. Thus, during simulation, a simulated pendulum can be obtained based on the pendulum's structural parameters, thereby obtaining the preset impact force.

[0063] The preset simulation system can be composed of a finite element model of the preset collision region of the collider. This model can adjust the abdominal structure according to the input initial structural parameters, and then obtain the predicted displacement curve corresponding to the initial structural parameters in the simulation environment.

[0064] Deviation can be used to quantify the degree of difference between predicted displacement curves and expected displacement curves. In calculating the difference between each predicted displacement curve and the expected displacement curve, the predicted and expected displacement curves can be fitted together to determine the corresponding displacement data of the two curves under the same preset impact force. Then, a preset mathematical model is used to calculate the difference value under at least one preset impact force; this difference value is the deviation of the corresponding initial structural parameter set. The mathematical model can be root mean square error, mean absolute error, etc.

[0065] In determining the target structural parameter set, the deviations of each initial structural parameter set can be compared, and the intermediate structural parameter set with the smallest deviation can be identified. If the deviation of the intermediate structural parameter set is less than a preset threshold, then the intermediate structural parameter set is used as the target structural parameter set.

[0066] There is no limit to the preset threshold; the preset threshold can be determined according to actual needs, such as ±15%.

[0067] According to an embodiment of the present invention, by determining the predicted displacement curves of multiple initial structural parameter sets and fitting them with the expected displacement curves, since the expected displacement curves are obtained by fitting the expected displacements of the preset collision region under multiple preset impact forces, the degree of conformity between the initial collision body corresponding to each initial structural parameter set and the expected collision condition can be better evaluated. Furthermore, when there is a deviation below a preset threshold among the multiple deviations determined by the fitting, the corresponding target structural parameter set is determined as the structural parameters of the preset collision region. Therefore, this at least partially solves the technical problem of low accuracy and low effectiveness of the structure of the constant collision region of the train collision body, and achieves the technical effect of improving the effectiveness of the target collision body.

[0068] According to embodiments of the present invention, the above method may further include the following operations.

[0069] When the number of iterations t=0, multiple initial structure parameter groups are determined based on multiple parameter types used to determine the structure of the preset collision region, the preset value range of each parameter type, and random parameters. Each initial structure parameter group contains the structure parameters indicated by each of the multiple parameter types.

[0070] When the iteration count is 0, i.e., in the initialization phase, multiple initial structure parameter groups can be initialized based on the population size (i.e., the number of initial structure parameter groups to be generated) and the dimension of the initialization problem (i.e., the number of parameter types included in each initial structure parameter group).

[0071] During initialization, the numerical values ​​of the structural parameters indicated by each parameter type in each initial structural parameter group can be obtained through mathematical calculations based on the preset value range of each parameter type and in combination with random parameters. In implementation, it can be based on the upper and lower bounds of the preset value range. For example, the following formula (1) can be used.

[0072] (1)

[0073] in, Indicates the first The q-th element in the initial set of structural parameters is the structural parameter located in the q-th dimension. Indicates the number of initial structure parameter sets. This represents a random parameter, which is a scalar and takes values ​​in the range [0, 1]. , Let represent the upper bound and lower bound of the value of the q-th element, respectively.

[0074] According to embodiments of the present invention, by combining population size and problem dimension, the generation scale and parameter composition of the initial structural parameter set are clearly defined, ensuring that the number of initial parameter sets meets the sample base required for subsequent screening. Furthermore, based on the preset value range of each parameter type, such as upper and lower bound constraints, and combined with random parameters, each structural parameter in each initial parameter set is determined. This avoids structural parameter values ​​deviating from reality, enriches the diversity of the initial parameter sets, and reduces the probability of generating local optima.

[0075] According to an embodiment of the present invention, the difference between multiple predicted displacement curves and expected displacement curves is calculated to obtain the deviation of each initial structural parameter group, which may include the following operations.

[0076] From the expected displacement curve, determine the first impact force under multiple preset collision area displacements; for each predicted displacement curve, determine the second impact force under multiple preset collision area displacements; based on the preset collision area displacement, calculate the difference between the first impact force and the second impact force corresponding to the same preset collision area displacement to obtain the deviation.

[0077] According to an embodiment of the present invention, the predicted displacement curve can be obtained by the following formula (2).

[0078] (2)

[0079] in, This represents the initial structure parameter set. This represents the predicted displacement curve corresponding to the initial set of structural parameters. Indicates the preset impact force. Indicates the predicted displacement; Indicates from arrive The mapping.

[0080] In determining the deviation of each initial structural parameter group, the expected displacement curve and each predicted displacement curve are sampled respectively. That is, the first impact force corresponding to each of the multiple expected displacements of the preset collision region is extracted from the expected displacement curve, and the second impact force corresponding to each of the multiple predicted displacements of the preset collision region is extracted for each predicted displacement curve. Then, based on the displacement of the preset collision region, the difference between the first impact force and the second impact force corresponding to the same displacement is calculated, and the average of the differences obtained under multiple displacements is calculated. The result obtained is the deviation of the initial structural parameter group corresponding to the predicted displacement curve. The specific calculation process can be shown in the following formula (3).

[0081] (3)

[0082] in, Represents the initial structure parameter set The degree of deviation, Indicates the predicted displacement curve. denoted as the desired displacement curve, N represents the number of sampled preset collision region displacements, and i represents the current preset region displacement.

[0083] Figure 3 A schematic diagram of the desired displacement curve according to an embodiment of the present invention is shown.

[0084] like Figure 3 As shown, the desired displacement of multiple preset impact forces at different impact velocities can be determined, with the unit being centimeters (cm). Figure 3 The figure shows the expected displacement curves corresponding to impact velocities of 12 m / s, 6.7 m / s, and 4.3 m / s. The dashed lines in the figure represent the error band determined when each expected displacement curve falls within ±15% of a preset threshold. This error band allows for the rapid determination of the predicted displacement curve that meets the specified conditions.

[0085] If the predicted displacement curve falls into Figure 3 The ±15% error band shown indicates that the collider composed of the initial structural parameter set corresponding to the predicted displacement curve set meets the impact response standard of the preset collision region, i.e., the error is within acceptable limits. .

[0086] According to embodiments of the present invention, the above method may further include the following operations.

[0087] In response to the current iteration number t, the intermediate structural parameter group with the lowest deviation is determined from multiple initial structural parameter groups, where t is an integer greater than or equal to 0. If the deviation of the determined intermediate structural parameter group is greater than or equal to a preset threshold, the search state judgment parameter determined by the current iteration number is compared with the preset judgment threshold to determine the search state of the t-th iteration. The search state includes a local search state or a global search state. Based on the search state of the t-th iteration, the evaluation values ​​of each of the multiple initial structural parameter groups for multiple update directions in the search state are determined from the value mapping. The evaluation values ​​are obtained by updating in the historical iteration process, which includes multiple iteration processes before the iteration number t. For each initial structural parameter group, based on the evaluation values ​​of the initial structural parameter group for multiple update directions in the search state, the initial structural parameter group is updated to a candidate structural parameter group. The multiple candidate structural parameter groups are used as the multiple initial structural parameter groups for the (t+1)-th iteration, and the above steps are repeated until a preset termination condition is met. The preset termination condition includes at least one of the following: obtaining a target structural parameter group with a deviation less than a preset threshold and reaching a preset iteration number.

[0088] By identifying the intermediate structural parameter group with the lowest deviation and comparing its deviation with a preset threshold, it can be determined whether any of the initial structural parameter groups has a deviation below the preset threshold. Therefore, if it is determined that none of the initial structural parameter groups have a deviation below the preset threshold, each initial structural parameter group can be updated to proceed to the next iteration.

[0089] The search state judgment parameter is not limited and can vary with the number of iterations, such as decreasing with the number of iterations. During the update of each initial structure parameter group, the search state judgment parameter can be determined based on the current iteration number, and the search state of the t-th iteration can be obtained by comparing the search state judgment parameter with the preset judgment threshold. The method for determining the search state judgment parameter is not limited and can be as shown in the following formula (4).

[0090] (4)

[0091] in, This indicates the parameters for determining the search status. This represents the parameter vector used to adjust the algorithm's search phase. The value of each dimension decreases linearly from 2 to 0 as the number of iterations increases. This represents a vector of random parameters.

[0092] The preset judgment threshold is not limited and can be set according to the actual situation. For example, it can be 1, thus... The current search state is a local search state. The search state is the global search state. By controlling the search state judgment parameter to change with the number of iterations, the update process can switch between the global search state and the local search state, thereby reducing the chances of not finding the optimal solution or only finding a local optimal solution.

[0093] After determining the search state of the current iteration, the initial structural parameter set can be updated based on this search state, moving towards the update direction corresponding to the highest evaluation value in the value map under the current search state. Specifically, if multiple directions in the value map have the same value, an update direction is randomly selected to update the initial structural parameter set.

[0094] The update direction can include a target direction and a random direction. The target direction can be considered as causing the initial structural parameter set to converge, that is, updating the initial structural parameter set towards the optimal intermediate structural parameter set in the current iteration, so that the initial structural parameter set gets closer and closer to the intermediate structural parameter set. The random direction can be considered as causing the initial structural parameter set to diverge, that is, updating the initial structural parameter set in a random direction, thereby avoiding getting trapped in local optima.

[0095] The value mapping can store the evaluation values ​​of each initial structure parameter set for multiple update directions under different search states in the current iteration.

[0096] For example, the value mapping can be a 2×2 matrix, denoted as Q. Q(1,1) represents the evaluation value of an individual performing a divergent action in the global search state; Q(1,2) represents the evaluation value of an individual performing a convergent action in the global search state; Q(2,1) represents the evaluation value of an individual performing a divergent action in the local search state; and Q(2,2) represents the evaluation value of an individual performing a convergent action in the local search state. Here, the individual represents the initial set of structural parameters. Performing a divergent action means updating in a random direction. Performing a convergent action means updating in the target direction.

[0097] In each iteration, the evaluation values ​​stored in the value mapping are updated based on the change in fitness after each initial structural parameter group is updated to a candidate structural parameter group, so as to evaluate the target update direction selected in the current iteration.

[0098] The historical iteration process can include iterations from iteration number 0 to iteration number t-1. When the iteration number is 0, the evaluation values ​​stored in the value map can all be the target values, such as all being zero.

[0099] After obtaining multiple candidate structural parameter sets, they can be used as multiple initial structural parameter sets for the (t+1)th iteration, thereby repeatedly executing the determination operation S220~S240, as well as the update process when there is no deviation below the preset threshold.

[0100] According to embodiments of the present invention, the local search and global search states are dynamically adapted by the number of iterations. Combined with the continuously updated evaluation values ​​during historical iterations, this provides a basis for the update direction of the initial structural parameter set, reducing the limitation of a single search mode easily getting trapped in local optima. Simultaneously, by setting the preset termination condition as a constraint, it is easy to quickly select the target structural parameter set that meets the deviation requirements, reducing resource waste caused by ineffective iterations.

[0101] According to an embodiment of the present invention, the multiple update directions include a target direction; the target direction is used to increase the matching degree between the initial structural parameter group and the intermediate structural parameter group by updating the initial structural parameter group; based on the evaluation value of the initial structural parameter group for the multiple update directions in the search state, updating the initial structural parameter group to a candidate structural parameter group may include the following operations.

[0102] Based on the evaluation values ​​of multiple update directions in the search state based on the initial structural parameter set, if the target direction has the highest evaluation value, the parameters are determined based on the method, and the update method for updating to the target direction is determined; based on the update method and the intermediate structural parameter set, the initial structural parameter set is updated to obtain the candidate structural parameter set, and the update method is either linear update method or spiral update method.

[0103] When updating in the target direction, the update method can be determined by comparing the method determination parameter with the direction determination threshold. The method determination parameter is not limited in its type; it can be a random number within the target range. It can be a random number within the interval [0, 1]. The threshold for determining its direction is related to the target range.

[0104] When the update method is linear, the difference between the intermediate structure parameter set and the initial structure parameter set is calculated to obtain the first distance parameter set representing the distance between the intermediate structure parameter set and the initial structure parameter set; based on the first distance parameter set, the search state judgment parameter and the intermediate structure parameter set, the candidate structure parameter set is determined.

[0105] When the update method is spiral update, the difference between the intermediate structure parameter set and the initial structure parameter set is calculated to obtain the second distance parameter set representing the distance between the intermediate structure parameter set and the initial structure parameter set; based on the spiral trajectory control parameters, the second distance parameter set, and the intermediate structure parameter set, the candidate structure parameter set is obtained.

[0106] For example, the process of obtaining the candidate structure parameter set can be specifically shown in the following formulas (5) to (8).

[0107] (5)

[0108] (6)

[0109] (7)

[0110] (8)

[0111] in, Let represent the candidate structure parameter set for the t-th iteration, which is also the initial structure parameter set for the (t+1)-th iteration. Let represent the intermediate structure parameter set for the t-th iteration. Let represent the initial set of structure parameters for the t-th iteration. To determine the parameters, Indicates the first distance parameter group, This represents the second distance parameter set; all the above parameter sets or vectors have a dimension of 1. , It is also the number of structural parameters included in each initial structural parameter group. Represents a vector of scaling parameters. This represents the control parameters for the spiral trajectory. This indicates that the parameters are being adjusted. This represents a random parameter vector, where the value of each dimension is a random number in the interval [0, 1].

[0112] According to embodiments of the present invention, by using the target direction with the optimal evaluation value in the current search state, combined with two differentiated update methods—linear or spiral—and incorporating intermediate structural parameter sets to perform directional iteration on the initial structural parameter set to generate candidate structural parameter sets, the directionality of parameter updates is achieved, reducing the resource waste and inefficiency caused by undirected iteration. Furthermore, through different update methods, linear updates can quickly approach the candidate structural parameter set, find a better parameter range, narrow the search boundary, and reduce invalid searches. Spiral updates, on the other hand, use the intermediate structural parameter set as the core, spirally exploring the better parameter region where it is located, thus deeply exploring potential better parameter points in the surrounding area without expanding the search range. This update logic can guide the structural parameters to converge efficiently to the better parameter direction, reducing the number of invalid iteration steps.

[0113] According to an embodiment of the present invention, the multiple update directions further include random directions; based on the evaluation values ​​of the initial structural parameter set for the multiple update directions in the search state, updating the initial structural parameter set to a candidate structural parameter set may further include the following operations.

[0114] Based on the evaluation values ​​of each of the initial structural parameter groups for multiple update directions in the search state, and determining the random direction with the highest evaluation value, a random structural parameter group is selected from the multiple initial structural parameter groups; the initial structural parameter groups are then updated based on the random structural parameter group to obtain a candidate structural parameter group.

[0115] When the evaluation value of the random direction is the highest, a random structural parameter group can be randomly determined from multiple initial structural parameter groups. The candidate structural parameter group can be obtained by using its distance value from the initial structural parameter group, the random structural parameter group and the search state judgment parameter. The specific implementation process can be shown in the following formulas (9) to (10).

[0116] (9)

[0117] (10)

[0118] in, Represents the distance vector. Let represent the set of random structure parameters for the t-th iteration.

[0119] According to an embodiment of the present invention, when the update direction is random, updating the initial structure parameter set based on a randomly determined set of structure parameters can avoid getting trapped in a local optimum.

[0120] In some embodiments, the initial structural parameter set can also be updated using the following formula (11) without considering value mapping.

[0121] (11)

[0122] However, during the research process, it was found that the update method provided by formula (11) depends more on the method of determining the parameters. and search status judgment parameters This means relying on existing, predetermined rules. Such a fixed search strategy struggles to balance local and global search capabilities and may get stuck in a local optimum.

[0123] According to an embodiment of the present invention, the search state judgment parameter is based on the change of the number of iterations; the multiple parameter types are determined according to the properties of the preset material used for the initial collider.

[0124] There are no restrictions on the preset materials; they can be foam, silicone, or sponge, etc.

[0125] In some embodiments, the population size, i.e., the number of initial structural parameter sets, can be set to... The preset number of iterations can be set to 500. When the preset material is foam, the population has 50 initial structural parameter sets, each of which can be set to... ,in This represents the number of layers of abdominal foam. , Representing the The thickness of the abdominal foam; , Representing the The hardness of the abdominal foam layer. The dimension of this optimization problem can be... .

[0126] According to embodiments of the present invention, the above method may further include the following operations.

[0127] For each initial structural parameter group in the t-th iteration, the deviation of the initial structural parameter group is compared with the deviation of the corresponding candidate structural parameter group to obtain the comparison result. Based on the update rule matching the comparison result, the reward value of the target update direction in the search state of the t-th iteration, which is included in the reward mapping, is updated to obtain the updated reward value. The target update direction is the update direction used in the process of updating the initial structural parameter group to the corresponding candidate structural parameter group. In the value mapping, the target evaluation value of the initial structural parameter group in the search state of the (t+1)-th iteration is determined. Based on the evaluation value of the target update direction in the search state of the t-th iteration, the updated reward value, and the target evaluation value, the evaluation value of the target update direction of the initial structural parameter in the search state of the t-th iteration in the value mapping is updated to obtain the updated value mapping.

[0128] The deviation of each initial structural parameter group before and after the update can be compared, and the corresponding update rule can be matched based on the comparison result to update the reward mapping. For example, the deviation of the initial structural parameter group can be compared with the deviation of the corresponding candidate structural parameter group to update the reward value of the target update direction used in the process of updating the initial structural parameter group to the corresponding candidate structural parameter group.

[0129] The update rule is not limited. If the comparison result indicates that the deviation of the initial structural parameter group is greater than that of the candidate structural parameter group, the reward value of the target update direction included in the reward mapping in the search state of the t-th iteration can be positively updated to obtain the updated reward value.

[0130] Furthermore, if the deviation of the initial structural parameter group is less than that of the candidate structural parameter group, the reward value of the target update direction included in the reward mapping in the search state of the t-th iteration can be negatively updated to obtain the updated reward value.

[0131] That is, during the update process, if it is determined that the deviation of the initial structural parameter group is greater than the deviation of the corresponding candidate structural parameter group, then the candidate structural parameter group is determined to be superior to the initial structural parameter group. In this case, the reward value of the target update direction in the search state of the t-th iteration can be positively updated in the reward mapping.

[0132] Conversely, if the deviation of the initial structural parameter set is determined to be less than that of the corresponding candidate structural parameter set, then the initial structural parameter set is considered superior to the candidate structural parameter set. In this case, the reward value of the target update direction in the search state of the t-th iteration can be negatively updated in the reward mapping. If the two are equal, no update is required.

[0133] There are no restrictions on the methods of positive and negative updates; addition can be performed on the original reward value. For example, a positive reward value can be added during a positive update, and a negative reward value can be added during a negative update. Specifically, a positive update can add 1, and a negative update can subtract 1.

[0134] The reward map can store the reward values ​​of each initial structure parameter set for multiple update directions under different search states in the current iteration.

[0135] For example, the reward mapping can be a 2×2 matrix, denoted as R. R(1,1) represents the reward value obtained by an individual performing a divergent action in the global search state; R(1,2) represents the reward value obtained by an individual performing a convergent action in the global search state; R(2,1) represents the reward value obtained by an individual performing a divergent action in the local search state; and R(2,2) represents the reward value obtained by an individual performing a convergent action in the local search state. Here, the individual is the initial set of structure parameters. Performing a divergent action updates the parameters in a random direction. Performing a convergent action updates the parameters in the target direction.

[0136] The reward map can also be updated based on a historical iteration process, which can include iterations from iteration number 0 to iteration number t-1. When the iteration number is 0, the evaluation values ​​stored in the reward map can all be the target values, such as all being zero.

[0137] According to embodiments of the present invention, by comparing the deviations of each initial structural parameter set before and after the update, the merits of the target update direction in the current search state can be determined. If the updated candidate structural parameter set is superior to the initial structural parameter set, the reward value of the target update direction in the corresponding search state is positively updated. This increases the execution probability of the target update direction in the subsequent search state, making it easier to search along the better path and obtain the final target structural parameters. Conversely, a negative update of the reward value reduces its execution probability, facilitating the exploration of other better paths to obtain the target structural parameters more quickly.

[0138] During the process of updating the value mapping, the search state of the (t+1)th iteration can be determined, and the highest evaluation value among the multiple update directions under this search state can be determined, thereby obtaining the target evaluation value.

[0139] Then, by using the target evaluation value, the evaluation value of the target update direction in the current search state, and the updated reward value, the evaluation value of the target update direction in the current search state is updated, thereby obtaining the updated reward mapping.

[0140] In the implementation process, the value mapping of each initial structural parameter group can be achieved through the following formula (12).

[0141] (12)

[0142] in, This represents the update evaluation value of the target update direction in the search state of the t-th iteration. This represents the search state in the t-th iteration. Indicates the target update direction for the t-th iteration. This represents the evaluation value of the target update direction in the search state of the t-th iteration. This indicates the updated reward value. Indicates the number of iterations. At that time, state The maximum evaluation value in value mapping, i.e., the target evaluation value. Indicates the learning rate. This represents the discount rate, and both values ​​are within the range [0, 1].

[0143] According to embodiments of the present invention, by comparing the deviation between the initial structural parameter set and the candidate structural parameter set in each iteration, a positive reward is given to the better target update direction, and the value mapping is dynamically updated in combination with multi-dimensional evaluation values. This can more accurately select the better parameter update direction that is more suitable for the collision conditions, strengthen the effective search path, reduce the waste of ineffective iterations, improve the screening efficiency and accuracy of the target structural parameter set, and thus enhance the effectiveness and reliability of the final target collider for the collision test.

[0144] According to embodiments of the present invention, by optimizing based on deviation and combining reward and evaluation values, the overall optimization performance can be effectively improved. During the optimization process, there is no need to know the specific information of the environment beforehand; instead, experience and rewards are accumulated through interaction with the environment, leading to the selection of the optimal decision. This ensures that each action in the optimization process moves towards maximizing the reward rather than following a fixed search strategy, thus exhibiting strong adaptability. Furthermore, it can adaptively balance local convergence and global search, effectively improving convergence accuracy and speed. When dealing with complex optimization problems, it is more effective in breaking through local optimum stagnation and getting closer to the global optimum.

[0145] Figure 4 A flowchart of a method for constructing a collision body for train collision testing according to another embodiment of the present invention is shown.

[0146] like Figure 4 As shown, the method includes operations S401 to S409.

[0147] In operation S401, in response to being in the t-th iteration, a set of multiple initial structural parameters for the preset collision region of the initial collider is obtained.

[0148] In operation S402, for each initial structural parameter group, the predicted displacement of the preset collision area under multiple preset impact forces is determined based on the initial structural parameter group, and the predicted displacement curve is obtained.

[0149] In operation S403, the difference between multiple predicted displacement curves and expected displacement curves is calculated to obtain the deviation of each initial structural parameter group.

[0150] In operation S404, the intermediate structural parameter set with the lowest deviation is determined from multiple initial structural parameter sets.

[0151] In operation S405, determine whether the fitness of the intermediate structure parameter group is lower than a preset threshold. If it is higher than or equal to the preset threshold, execute operation S406. If it is lower than the preset threshold, execute operation S409.

[0152] In operation S406, for each initial structural parameter set, based on the evaluation values ​​of the initial structural parameter set determined by the value mapping for multiple update directions in the search state of the current iteration number t, the initial structural parameter set is updated to a candidate structural parameter set.

[0153] In operation S407, the value mapping and reward mapping are updated based on the deviation of each initial structural parameter group and the deviation of the candidate structural parameter groups corresponding to each initial structural parameter group.

[0154] In operation S408, multiple candidate structural parameter sets are used as multiple initial structural parameter sets for the (t+1)th iteration.

[0155] In operation S409, the intermediate structure parameter set is used as the target structure parameter set.

[0156] Figure 5 A flowchart of a train collision test method according to an embodiment of the present invention is shown.

[0157] like Figure 5 As shown, the method includes operation S510.

[0158] In operation S510, using the target collision body constructed according to the above-described collision body construction method for train collision testing, the target displacement of the preset collision area of ​​the target collision body is tested under multiple target impact forces, so as to conduct a safety assessment of the train based on the target displacement; wherein, the target impact force is obtained by at least one of the following methods: controlling the train's speed or controlling the train's target collision area.

[0159] A target collider can be constructed based on the target structure parameter set, and a collision test can be performed on it.

[0160] During testing, the target impact force gradient can be constructed through a multi-dimensional combination of methods. For example, it can be achieved by controlling the train's speed, referencing collision speed standards for different line types, adjusting the train's acceleration curve, braking strategy, and initial kinetic energy, and combining this with the type of collision object to form different impact intensities; the higher the speed, the greater the impact force generated at the moment of collision. On the other hand, the target collision area of ​​the train can be controlled. This area can include various facilities inside the train, such as tables, fixed tables, and passenger handrails, as well as key structural elements of the train body, such as the front of the train, side wall pillars, and window frames.

[0161] By changing the location of the collision contact point, such as by changing the collision contact area, the path and intensity of the collision force transmission can be altered, thereby simulating a real collision scenario.

[0162] During the test of each target impact force, real-time displacement data of the preset collision area of ​​the target collider can be recorded, including compression and displacement change rate. After the test is completed, the data under all target impact forces are summarized and compared with the displacement threshold and structural strength limit in the train safety design standard to evaluate the train's structural crashworthiness, the danger to personnel, and the anti-falling performance of key facilities, forming an assessment report covering the overall safety level and optimization suggestions for weak points.

[0163] Based on the above-described method for constructing a collision body for train collision testing, this invention also provides a device for constructing a collision body for train collision testing. The following will be combined with... Figure 6 The device is described in detail.

[0164] Figure 6 A structural block diagram of a collision body construction device for train collision testing according to an embodiment of the present invention is shown.

[0165] like Figure 6 As shown, the collision body construction device 600 for train collision testing in this embodiment includes an acquisition module 610, a first determination module 620, a calculation module 630, and a second determination module 640.

[0166] The acquisition module 610 is used to acquire multiple initial structural parameter sets for the preset collision region of the initial collider; in one embodiment, the acquisition module 610 can be used to perform the operation S210 described above, which will not be repeated here.

[0167] The first determining module 620 is used to determine the predicted displacement of the preset collision area under multiple preset impact forces for each initial structural parameter group, and obtain the predicted displacement curve. In one embodiment, the first determining module 620 can be used to perform the operation S220 described above, which will not be repeated here.

[0168] The calculation module 630 is used to calculate the difference between multiple predicted displacement curves and expected displacement curves respectively, and to obtain the deviation of each initial structural parameter group. The expected displacement curve is obtained by fitting the expected displacement of the preset collision area under multiple preset impact forces. In one embodiment, the calculation module 630 can be used to perform the operation S230 described above, which will not be repeated here.

[0169] The second determining module 640 is configured to, in response to the existence of a deviation below a preset threshold in the deviation of each of the multiple initial structural parameter sets, use the corresponding initial structural parameter set as the target structural parameter set to obtain the target collision body for train collision testing. In one embodiment, the second determining module 640 may be used to perform the operation S240 described above, which will not be repeated here.

[0170] According to embodiments of the present invention, any plurality of modules among the acquisition module 610, the first determining module 620, the calculation module 630, and the second determining module 640 can be combined into one module, or any one of these modules can be split into multiple modules. Alternatively, at least part of the functionality of one or more of these modules can be combined with at least part of the functionality of other modules and implemented in one module. According to embodiments of the present invention, at least one of the acquisition module 610, the first determining module 620, the calculation module 630, and the second determining module 640 can be at least partially implemented as hardware circuitry, such as a field-programmable gate array (FPGA), a programmable logic array (PLA), a system-on-a-chip, a system-on-a-substrate, a system-on-package, an application-specific integrated circuit (ASIC), or any other reasonable means of integrating or packaging circuitry, or implemented in software, hardware, or firmware, or in any appropriate combination of any of these three implementation methods. Alternatively, at least one of the acquisition module 610, the first determining module 620, the calculation module 630, and the second determining module 640 can be at least partially implemented as a computer program module, which, when run, can perform corresponding functions.

[0171] Based on the above-described method for train collision testing, the present invention also provides a train collision testing apparatus. The following will be combined with... Figure 7 The device is described in detail.

[0172] Figure 7 A structural block diagram of a train collision testing apparatus according to an embodiment of the present invention is shown.

[0173] like Figure 7 As shown, the train collision test apparatus 700 of this embodiment includes a test module 710.

[0174] The test module 710 is used to test the target displacement of a preset collision area of ​​the target collision body constructed according to the above-described collision body construction method for train collision testing under multiple target impact forces, so as to conduct a safety assessment of the train based on the target displacement and obtain a safety assessment result; wherein, the target impact force is obtained by at least one of the following methods: controlling the train's speed or controlling the train's target collision area; in one embodiment, the test module 710 can be used to perform the operation S510 described above, which will not be repeated here.

[0175] Figure 8 A block diagram of an electronic device suitable for implementing a collision body construction method for train collision testing, according to an embodiment of the present invention, is shown.

[0176] like Figure 8 As shown, an electronic device 800 according to an embodiment of the present invention includes a processor 801, which can perform various appropriate actions and processes according to a program stored in a read-only memory ROM 802 or a program loaded from a storage portion 808 into a random access memory RAM 803. The processor 801 may include, for example, a general-purpose microprocessor (e.g., a CPU), an instruction set processor and / or an associated chipset and / or a special-purpose microprocessor (e.g., an application-specific integrated circuit (ASIC)), etc. The processor 801 may also include 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 an embodiment of the present invention.

[0177] RAM 803 stores various programs and data required for the operation of electronic device 800. Processor 801, ROM 802, and RAM 803 are interconnected via bus 804. Processor 801 executes various operations of the method flow according to embodiments of the present invention by executing programs in ROM 802 and / or RAM 803. It should be noted that the programs may also be stored in one or more memories other than ROM 802 and RAM 803. Processor 801 may also execute various operations of the method flow according to embodiments of the present invention by executing programs stored in said one or more memories.

[0178] According to an embodiment of the present invention, the electronic device 800 may further include an input / output (I / O) interface 805, which is also connected to a bus 804. The electronic device 800 may also include one or more of the following components connected to the I / O interface 805: an input section 806 including a keyboard, mouse, etc.; an output section 807 including a cathode ray tube (CRT), liquid crystal display (LCD), etc., and a speaker, etc.; a storage section 808 including a hard disk, etc.; and a communication section 809 including a network interface card such as a LAN card, modem, etc. The communication section 809 performs communication processing via a network such as the Internet. A drive 810 is also connected to the I / O interface 805 as needed. A removable medium 811, such as a disk, optical disk, magneto-optical disk, semiconductor memory, etc., is installed on the drive 810 as needed so that computer programs read from it can be installed into the storage section 808 as needed.

[0179] The present invention also provides a computer-readable storage medium, which may be included in the device / apparatus / system described in the above embodiments; or it may exist independently and not assembled into the device / apparatus / system. The computer-readable storage medium carries one or more programs, which, when executed, implement the method according to the embodiments of the present invention.

[0180] According to embodiments of the present invention, a computer-readable storage medium may be a non-volatile computer-readable storage medium, such as including, but not limited to: portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination thereof. In the present invention, a computer-readable storage medium may be any tangible medium containing or storing a program that can be used by or in conjunction with an instruction execution system, apparatus, or device. For example, according to embodiments of the present invention, a computer-readable storage medium may include ROM 802 and / or RAM 803 and / or one or more memories other than ROM 802 and RAM 803 described above.

[0181] Embodiments of the present invention also include a computer program product comprising a computer program containing program code for performing the methods shown in the flowchart. When the computer program product is run on a computer system, the program code enables the computer system to implement the collision body construction method and the train collision testing method provided in the embodiments of the present invention.

[0182] When the computer program is executed by the processor 801, it performs the functions defined in the system / apparatus of this invention. According to embodiments of the invention, the systems, apparatuses, modules, units, etc., described above can be implemented by computer program modules.

[0183] In one embodiment, the computer program may rely on a tangible storage medium such as an optical storage device or a magnetic storage device. In another embodiment, the computer program may also be transmitted and distributed in the form of signals over a network medium, and may be downloaded and installed via the communication section 809, and / or installed from a removable medium 811. The program code contained in the computer program can be transmitted using any suitable network medium, including but not limited to: wireless, wired, etc., or any suitable combination thereof.

[0184] In such an embodiment, the computer program can be downloaded and installed from a network via communication section 809, and / or installed from removable medium 811. When the computer program is executed by processor 801, it performs the functions defined in the system of this embodiment of the invention. According to embodiments of the invention, the systems, devices, apparatuses, modules, units, etc., described above can be implemented by computer program modules.

[0185] According to embodiments of the present invention, program code for executing the computer programs provided in the embodiments of the present invention can be written in any combination of one or more programming languages. Specifically, these computational programs can be implemented using high-level procedural and / or object-oriented programming languages, and / or assembly / machine languages. Programming languages ​​include, but are not limited to, languages ​​such as Java, C++, Python, "C", or similar programming languages. The program code can be executed entirely on the user's computing device, partially on the user's device, partially on a remote computing device, or entirely on a remote computing device or server. In cases involving remote computing devices, the remote computing device can be connected to the user's computing device via any type of network, including a local area network (LAN) or a wide area network (WAN), or it can be connected to an external computing device (e.g., via the Internet using an Internet service provider).

[0186] The flowcharts and block diagrams in the accompanying drawings illustrate the architecture, functionality, and operation of possible implementations of systems, methods, and computer program products according to various embodiments of the present invention. In this regard, each block in a flowchart or block diagram may represent a module, segment, or portion of code containing one or more executable instructions for implementing a specified logical function. It should also be noted that in some alternative implementations, the functions indicated in the blocks may occur in a different order than those indicated in the drawings. For example, two consecutively indicated blocks may actually be executed substantially in parallel, and they may sometimes be executed in reverse order, depending on the functions involved. It should also be noted that each block in a block diagram or flowchart, and combinations of blocks in a block diagram or flowchart, may be implemented using a dedicated hardware-based system that performs the specified function or operation, or using a combination of dedicated hardware and computer instructions.

[0187] Those skilled in the art will understand that the features described in the various embodiments of the present invention can be combined or combined in various ways, even if such combinations or combinations are not explicitly described in the present invention. In particular, the features described in the various embodiments of the present invention can be combined and / or combined in various ways without departing from the spirit and teachings of the present invention. All such combinations and / or combinations fall within the scope of the present invention.

[0188] The embodiments of the present invention have been described above. However, these embodiments are merely illustrative and not intended to limit the scope of the invention. Although various embodiments have been described above, this does not mean that the measures in the various embodiments cannot be used advantageously in combination. Various substitutions and modifications can be made by those skilled in the art without departing from the scope of the invention, and all such substitutions and modifications should fall within the scope of the invention.

Claims

1. A method for constructing a collision body for train collision testing, characterized in that, include: Obtain multiple initial structural parameter sets for the preset collision region of the initial collider; For each set of initial structural parameters, the predicted displacement of the preset collision region under multiple preset impact forces is determined based on the set of initial structural parameters, and the predicted displacement curve is obtained. The differences between multiple predicted displacement curves and expected displacement curves are calculated respectively to obtain the deviation of each set of initial structural parameters. The expected displacement curve is obtained by fitting the expected displacement of the preset collision area under multiple preset impact forces. In response to the existence of a deviation below a preset threshold in the deviation of each of the multiple initial structural parameter sets, the corresponding initial structural parameter set is taken as the target structural parameter set to obtain the target collision body for train collision testing.

2. The method according to claim 1, characterized in that, The method further includes: In response to the current iteration number t, the intermediate structural parameter set with the lowest deviation is determined from the multiple initial structural parameter sets, where t is an integer greater than or equal to 0; If the deviation of the intermediate structure parameter group is determined to be greater than or equal to the preset threshold, the search state judgment parameter determined by the current iteration number is compared with the preset judgment threshold to determine the search state of the t-th iteration. The search state includes a local search state or a global search state. Based on the search state of the t-th iteration, the evaluation values ​​of each of the initial structural parameter groups for multiple update directions in the search state are determined from the value mapping. The evaluation values ​​are obtained by updating during the historical iteration process, which includes multiple iteration processes before the iteration number t. For each initial structural parameter group, based on the evaluation values ​​of the initial structural parameter group for multiple update directions in the search state, the initial structural parameter group is updated to a candidate structural parameter group; Multiple candidate structural parameter sets are used as multiple initial structural parameter sets for the (t+1)th iteration, and the above steps are repeated until a preset termination condition is met. The preset termination condition includes at least one of the following: obtaining a target structural parameter set with a deviation less than a preset threshold and reaching a preset number of iterations.

3. The method according to claim 2, characterized in that, The plurality of update directions include a target direction; the target direction is used to increase the matching degree between the initial structural parameter set and the intermediate structural parameter set by updating the initial structural parameter set; The step of updating the initial structural parameter set to a candidate structural parameter set based on the evaluation values ​​of the initial structural parameter set for multiple update directions in the search state includes: If, based on the evaluation values ​​of multiple update directions under the search state using the initial structural parameter set, the target direction has the highest evaluation value, then the update method for updating towards the target direction is determined based on the method determination parameters. Based on the update method and the intermediate structural parameter group, the initial structural parameter group is updated to obtain the candidate structural parameter group. The update method is either a linear update method or a spiral update method.

4. The method according to claim 3, characterized in that, The step of updating the initial structural parameter set based on the update method and the intermediate structural parameter set to obtain the candidate structural parameter set includes: when the update method is a linear update method. The difference between the intermediate structural parameter set and the initial structural parameter set is calculated to obtain a first distance parameter set that characterizes the distance between the intermediate structural parameter set and the initial structural parameter set; The candidate structure parameter group is determined based on the first distance parameter group, the search state judgment parameter, and the intermediate structure parameter group.

5. The method according to claim 3, characterized in that, The step of updating the initial structural parameter set based on the update method and the intermediate structural parameter set to obtain the candidate structural parameter set includes: when the update method is a spiral update method. The difference between the intermediate structural parameter set and the initial structural parameter set is calculated to obtain a second distance parameter set that characterizes the distance between the intermediate structural parameter set and the initial structural parameter set; The candidate structure parameter set is obtained based on the spiral trajectory control parameters, the second distance parameter set, and the intermediate structure parameter set.

6. The method according to claim 2, characterized in that, The multiple update directions also include random directions; updating the initial structure parameter set to a candidate structure parameter set based on the evaluation values ​​of the initial structure parameter set for the multiple update directions in the search state further includes: If the evaluation value of the random direction is the highest based on the evaluation values ​​of the multiple update directions of each of the initial structural parameter sets in the search state, then the random structural parameter set is determined from the multiple initial structural parameter sets. The initial structure parameter set is updated based on the random structure parameter set to obtain the candidate structure parameter set.

7. The method according to any one of claims 2 to 6, characterized in that, The method further includes: When the iteration number t=0, based on multiple parameter types used to determine the preset collision region structure, the preset value range of each of the multiple parameter types, and random parameters, multiple initial structure parameter groups are determined, and each initial structure parameter group contains the structure parameters indicated by each of the multiple parameter types.

8. The method according to claim 7, characterized in that, The search state judgment parameters are based on the number of iterations; the types of the parameters are determined according to the properties of the preset material used for the initial collider.

9. The method according to claim 2, characterized in that, The method further includes: For each initial structure parameter group in the t-th iteration, the deviation of the initial structure parameter group is compared with the deviation of the corresponding candidate structure parameter group to obtain the comparison result; Based on the update rule matching the comparison result, the reward value of the target update direction in the search state of the reward mapping in the t-th iteration is updated to obtain the updated reward value. The target update direction is the update direction used in the process of updating the initial structure parameter group to the corresponding candidate structure parameter group. In the value mapping, the target evaluation value of the initial structural parameter set in the search state of the (t+1)th iteration is determined; Based on the evaluation value of the target update direction in the search state of the t-th iteration, the updated reward value, and the target evaluation value, the initial structure parameters in the value mapping are updated based on the evaluation value of the target update direction in the search state of the t-th iteration, resulting in the updated value mapping.

10. The method according to claim 9, characterized in that, The update rule based on the comparison result updates the reward value of the target update direction in the search state of the t-th iteration, including the reward mapping, to obtain the updated reward value, including: If the comparison result indicates that the deviation of the initial structural parameter set is greater than the deviation of the candidate structural parameter set, the reward value of the target update direction included in the reward mapping in the search state of the t-th iteration is positively updated to obtain the updated reward value.

11. The method according to claim 9, characterized in that, The update rule based on the comparison result, which updates the reward value of the target update direction in the search state of the t-th iteration, includes: If the comparison result indicates that the deviation of the initial structural parameter group is less than the deviation of the candidate structural parameter group, the reward value of the target update direction included in the reward mapping in the search state of the t-th iteration is negatively updated to obtain the updated reward value.

12. The method according to claim 1, characterized in that, The step of calculating the differences between multiple predicted displacement curves and expected displacement curves to obtain the deviation of each initial structural parameter group includes: From the desired displacement curve, determine the first impact force under multiple preset collision region displacements; For each of the predicted displacement curves, a second impact force under multiple preset collision region displacements is determined from the predicted displacement curves; Based on the displacement of the preset collision area, the difference between the first impact force and the second impact force corresponding to the same preset collision area displacement is calculated to obtain the deviation.

13. A train collision test method, characterized in that, include: A target collision body is constructed using the collision body construction method for train collision testing according to any one of claims 1 to 12. The target displacement of the preset collision area of ​​the target collision body is tested under multiple target impact forces, so as to conduct a safety assessment of the train based on the target displacement and obtain a safety assessment result. The target impact force is obtained by at least one of the following methods: controlling the train's speed or controlling the target collision area of ​​the train.

14. A collision body construction device for train collision testing, characterized in that, The device includes: The acquisition module is used to acquire multiple initial structural parameter sets for the preset collision region of the initial collider; The first determining module is used to determine the predicted displacement of the preset collision area under multiple preset impact forces for each set of initial structural parameters, and obtain the predicted displacement curve. The calculation module is used to calculate the differences between multiple predicted displacement curves and expected displacement curves respectively, and to obtain the deviation of each initial structural parameter group. The expected displacement curve is obtained by fitting the expected displacement of the preset collision area under multiple preset impact forces. The second determining module is used to determine the target structural parameter group in response to the existence of a deviation of less than a preset threshold in the deviation of each of the multiple initial structural parameter groups, so as to obtain the target collision body for train collision testing.

15. An electronic device comprising: One or more processors; Memory, used to store one or more computer programs. The characteristic feature is that the one or more processors execute the one or more computer programs to implement the steps of the method according to any one of claims 1 to 13.

Images