A method, device, equipment and readable storage medium for train measurement point layout

Abstract

The present invention discloses a method, device, equipment and readable storage medium for layout of train measurement points, which are applied to the field of train testing, and include: obtaining an equivalent simulation model of a train car body in multiple scenarios and multiple physical domains, and extracting simulation information of initial measurement points based on the equivalent simulation model; performing dimensionality reduction processing on the simulation information based on multiple scenarios and multiple physical domains to obtain the dimensionality-reduced simulation information; performing similarity evaluation on the initial measurement points based on the dimensionality-reduced simulation information to obtain a similarity evaluation result; and determining key measurement points and substitute measurement points according to the similarity evaluation result. The present invention uses the equivalent simulation model to obtain the simulation information of each measurement point, and drives the optimal layout of the measurement points of the train car body by using the simulation information. The present invention can comprehensively consider the differences in different physical domains and different test scenarios, minimize the number of measurement points required in train car body testing to the greatest extent, reduce the testing cost of the car body, and can also avoid the loss of important test information and the repeated acquisition of equivalent information.

Description

Technical Field

[0001] The present invention relates to the field of train testing, and in particular to a train measuring point layout method, device, equipment and a readable storage medium. Background Art

[0002] Due to the large size of the high-speed train body structure, the complex connection relationship between components, the numerous test scenarios involved, and the complex external excitation sources of the body, the selection of the measurement point location is critical. The traditional measurement point location selection method generally relies on experience or determines the measurement point location based on the failure condition of the failed component. This method can easily cause the loss of key test information. At the same time, due to the limited number of data channels of the test equipment, adding measurement points means increasing the difficulty of data collection, the test preparation cycle, and the test-related costs. In addition, due to the inaccuracy and comprehensiveness of empirical information, sometimes the information obtained from different measurement points is equivalent information, resulting in repeated acquisition of information and a waste of test resources.

[0003] Therefore, how to provide a train measurement point layout method with low testing cost and comprehensive testing is a technical problem that urgently needs to be solved. Summary of the invention

[0004] In view of this, the purpose of the present invention is to provide a train measuring point layout method, device, equipment and readable storage medium, which solves the problems of high testing cost and incomplete and inaccurate testing in the prior art.

[0005] To solve the above technical problems, the present invention provides a train measuring point layout method, comprising: obtaining an equivalent simulation model of multiple scenes and multiple physical domains of a train body, and extracting simulation information of initial measuring points based on the equivalent simulation model; performing dimensionality reduction processing on the simulation information based on multiple scenes and multiple physical domains to obtain reduced-dimensional simulation information; performing similarity evaluation on the initial measuring points based on the reduced-dimensional simulation information to obtain similarity evaluation results; and determining key measuring points and substitute measuring points according to the similarity evaluation results.

[0006] Optionally, before determining the key measuring points and the substitute measuring points according to the similarity evaluation results, the method further includes: performing a surrounding environment evaluation on the initial measuring point to obtain an environment evaluation result; the surrounding environment evaluation includes at least one of a surrounding layout space evaluation and a surrounding geometric shape evaluation; correspondingly, determining the key measuring points and the substitute measuring points according to the similarity evaluation results includes: determining the key measuring points and the substitute measuring points according to the environment evaluation result and the similarity evaluation result.

[0007] Optionally, the dimensionality reduction processing of the simulation information based on multiple scenarios to obtain the simulation information after dimensionality reduction includes: constructing a data matrix to be reduced in l scenarios of the Ath physical domain according to the number n of information categories provided by the ath physical domain simulation model, and the number of the data matrix to be reduced in dimensionality is n; averaging the elements in each column of the data matrix to be reduced in dimensionality, and constructing a first matrix based on the average value and each element in the data matrix to be reduced in dimensionality; obtaining a covariance matrix based on the first matrix, and the covariance matrix includes eigenvalues ​​and eigenvectors; arranging the eigenvectors in descending order according to the eigenvalues; constructing a second matrix based on the first k eigenvectors after arrangement; the k represents the maximum number of measurement points supported by the train test; and obtaining the data matrix after dimensionality reduction of the ath physical domain in l scenarios based on the data matrix to be reduced in dimensionality and the second matrix.

[0008] Optionally, performing similarity evaluation on the initial measuring points based on the simulation information after dimensionality reduction to obtain a similarity evaluation result includes: taking any measuring point among the initial measuring points as a target measuring point; calculating the Euler distance between the other initial measuring points and the target measuring point according to the simulation information after dimensionality reduction corresponding to the target measuring point and the simulation information after dimensionality reduction corresponding to other initial measuring points; and obtaining the similarity evaluation result according to the Euler distance.

[0009] Optionally, before extracting simulation information of initial measurement points based on the equivalent simulation model, the method further includes: setting the initial measurement points on the surface of the train body according to manual experience and geometric model information of the train body.

[0010] Optionally, obtaining equivalent simulation models of multiple scenarios and multiple physical domains of the train body includes: building equivalent simulation models of each scenario and each physical domain, wherein the equivalent simulation model of each physical domain includes at least one simulation model of the body structure simulation model, the body external flow field simulation model and the body dynamics simulation model.

[0011] Optionally, an equivalent simulation model of a train body in multiple scenarios and multiple physical domains is obtained, and simulation information of the initial measuring points is extracted based on the equivalent simulation model, including: building a geometric model of the train body, and using processing software to process geometric features in the geometric model to obtain a processed geometric model; meshing the processed geometric model according to the geometric features, dividing the structure into various units, and there is a connection relationship between the various units; based on the various units, the train boundary conditions are defined according to actual operating conditions, and the loads to be applied are determined; based on the train boundary conditions and the loads to be applied, the processed geometric model is solved to obtain simulation information of each initial measuring point under each working condition, and the simulation information includes at least one item of information among structural deformation, stress and vibration.

[0012] The present invention also provides a train measuring point layout device, including: a simulation information acquisition module, used to obtain an equivalent simulation model of multiple scenes and multiple physical domains of a train body, and extract simulation information of initial measuring points; a simulation information processing module, used to perform dimensionality reduction processing on the simulation information based on multiple scenes and multiple physical domains to obtain reduced-dimensional simulation information; a similarity evaluation module, used to perform similarity evaluation on the initial measuring points based on the reduced-dimensional simulation information to obtain similarity evaluation results; and a measuring point layout module, used to determine key measuring points and substitute measuring points according to the similarity evaluation results.

[0013] The present invention also provides a train measuring point layout device, comprising: a memory for storing a computer program; and a processor for implementing the above-mentioned train measuring point layout method when executing the computer program.

[0014] The present invention also provides a computer-readable storage medium, in which computer-executable instructions are stored. When the computer-executable instructions are loaded and executed by a processor, the train measurement point layout method as described above is implemented.

[0015] It can be seen that the present invention obtains equivalent simulation models of multiple scenarios and multiple physical domains of the train body, and extracts simulation information of the initial measuring points based on the equivalent simulation models; performs dimensionality reduction processing on the simulation information based on multiple scenarios and multiple physical domains to obtain simulation information after dimensionality reduction; performs similarity evaluation on the initial measuring points based on the simulation information after dimensionality reduction to obtain similarity evaluation results; and determines key measuring points and substitute measuring points according to the similarity evaluation results. The train measuring point layout method proposed in the present invention obtains simulation information of each measuring point using an equivalent simulation model, and optimizes the arrangement of train body measuring points driven by the simulation information. This method can comprehensively consider the differences in different physical domains and different test scenarios, minimize the number of measuring points required in train body testing, reduce the cost of body testing, and avoid the loss of important test information and repeated acquisition of equivalent information.

[0016] In addition, the present invention also provides a train measuring point layout device, equipment and readable storage medium, which also have the above-mentioned beneficial effects. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on the provided drawings without paying creative work.

[0018] Figure 1 A flow chart of a train measurement point layout method provided by an embodiment of the present invention.

[0019] Figure 2 An example diagram of a vehicle body geometric model provided in an embodiment of the present invention.

[0020] Figure 3 This is an example diagram of the results of vehicle body unit mesh division provided by an embodiment of the present invention.

[0021] Figure 4 An example diagram of a vehicle body boundary condition and load application result provided in an embodiment of the present invention.

[0022] Figure 5 An example diagram of simulation results of vehicle body structure deformation provided in an embodiment of the present invention.

[0023] Figure 6 A position display diagram of an initial measurement point provided in an embodiment of the present invention.

[0024] Figure 7 A flowchart of a train measurement point layout method provided in an embodiment of the present invention.

[0025] Figure 8 A schematic diagram of the structure of a train measuring point layout device provided in an embodiment of the present invention.

[0026] Fig. 9 A schematic diagram of the structure of a train measurement point layout device provided in an embodiment of the present invention. DETAILED DESCRIPTION

[0027] In order to make the purpose, technical solution and advantages of the embodiments of the present invention clearer, the technical solution in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0028] With the rapid development of rail transit equipment, various types of car body structures have been put on the market. In the development process of high-speed train car bodies, testing is the core link. During the testing process, determining the layout of the measuring points is an important step to ensure the accuracy of the test data. How to ensure that the location of the measuring points can obtain the corresponding external stimulus information, that is, how to ensure the reliability of the measurement point layout, how to use the least number of measuring points to obtain the most abundant car body test data, these are all issues that need to be considered.

[0029] Due to the large size of the high-speed train body structure, the complex connection relationship between components, the numerous test scenarios involved, and the complex sources of external excitation of the body, the traditional method of determining the location of the measuring point generally relies on experience or determines the location of the measuring point based on the failure condition of the failed component. This method can easily cause the loss of key test information. At the same time, due to the limited number of data channels of the test equipment, adding measuring points means increasing the difficulty of data collection, the test preparation cycle, and the test-related costs. In addition, due to the inaccurate and incomplete empirical information, sometimes the information obtained from different measuring points is equivalent information, resulting in repeated acquisition of information and waste of test resources. Therefore, when arranging the measuring point location, it is necessary to comprehensively consider multiple issues such as test cost, layout space, and layout difficulty. It is difficult for traditional methods to consider the above factors at the same time.

[0030] In order to solve the above problems, the present invention proposes a train measuring point layout method, which uses multi-source simulation data provided by equivalent simulation models of multiple physical domains and multiple scenarios, and adopts data dimension reduction and data correlation evaluation methods to assist in realizing the optimal layout of measuring point positions. This method can simultaneously consider different physical domain information of different test scenarios, and complete the optimal layout of measuring point positions based on multi-source heterogeneous information obtained from different physical domains, so as to obtain richer vehicle body test information using fewer measuring points, and can effectively avoid the loss of test data caused by relying on traditional experience and the duplication of equivalent test information.

[0031] Please refer to Figure 1 , Figure 1 A flow chart of a train measurement point layout method provided by an embodiment of the present invention. The method may include: S101: acquiring a multi-scenario, multi-physical domain equivalent simulation model of a train body, and extracting simulation information of initial measurement points based on the equivalent simulation model.

[0032] The execution subject of this embodiment is a terminal. This embodiment does not limit the type of terminal, as long as it can complete the operation of the train measurement point layout method.

[0033] The present invention is based on the modeling of the train entity to obtain an equivalent simulation model of multiple physical domains, and obtains simulation information of each initial measurement point based on the equivalent simulation model of multiple physical domains and different test scenarios / operating conditions. This embodiment does not specifically limit the scenario and physical domain. The initial test in this embodiment can be a basic measurement point or a conventional measurement point. Specifically, the position (x i ,y i , z i ) corresponds to the simulation information of different physical domains and different scenarios of the i-th numbered initial measurement point, where the simulation information corresponding to the a-th scenario of the A-th physical domain can be expressed as ,in It represents the number of information categories that the a-th physical domain simulation model can provide. For example, the structural physical field vehicle body simulation model can provide different types of simulation information such as stress value, deformation value, strain value, maximum principal stress, etc. of the corresponding measuring points; similarly, the vehicle body dynamics simulation model can provide different types of information such as the velocity and acceleration of the corresponding measuring points.

[0034] Furthermore, before extracting the simulation information of the initial measuring points based on the equivalent simulation model, the following steps may be included: setting initial measuring points on the surface of the train body according to manual experience and geometric model information of the train body.

[0035] It should be noted that this embodiment is based on the modeling of the train entity, and the geometric model of the car body can be obtained. The initial measurement points are set on the surface of the train body simulation model based on the setting experience of the measurement points and the geometric model information. Specifically, the reference coordinate origin of the car body is taken as the coordinate point (0, 0, 0), and the first The numbered initial measurement points can be expressed as (x i ,y i , z i ), where the coordinates (x i ,y i , z i ) must be on the surface of the vehicle body.

[0036] Furthermore, the above-mentioned acquisition of equivalent simulation models of multiple scenarios and multiple physical domains of the train body may specifically include the following steps: building equivalent simulation models of each scenario and each physical domain; the equivalent simulation model of each physical domain includes at least one simulation model of the body structure simulation model, the body external flow field simulation model and the body dynamics simulation model.

[0037] It should be noted that this embodiment builds a multi-physical domain equivalent simulation model of a train body covering multiple scenarios, including a body structure simulation model, a body external flow field simulation model, a body dynamics simulation model, and other physical domain simulation models.

[0038] Furthermore, the above-mentioned acquisition of multi-scene and multi-physical domain equivalent simulation models of the train body, and extraction of simulation information of the initial measuring points based on the equivalent simulation models, may specifically include the following steps: Step 11: Build a geometric model of the train body, and use processing software to process the geometric features in the geometric model to obtain a processed geometric model; Step 12: Mesh the processed geometric model according to the geometric features, and divide the structure into various units, and there is a connection relationship between the various units; Step 13: Based on each unit, define the train boundary conditions according to the actual operating conditions, and determine the load to be applied; Step 14: Solve the processed geometric model based on the train boundary conditions and the load to be applied to obtain simulation information of each initial measuring point under each working condition, and the simulation information includes at least one information of structural deformation, stress and vibration.

[0039] It should be noted that, in step 11 and step 14, the car body structure simulation model is used as an example to illustrate the above step 11. (1) Geometric model processing and import: A three-dimensional geometric model is built based on the train body. When the construction is completed, the model is saved in an intermediate format for easy identification. With the help of professional processing software such as hypermesh (a computer-aided function application software package) and ANSA (a computer-aided function application software package), the geometric features of the car body are simplified and cleaned. The processed geometric model is as follows: Figure 2 (2) Car body mesh division: Based on each unit, the processed geometric model is meshed according to the geometric features, and the structure is divided into units to ensure the connection relationship between the units, such as Figure 3 (3) Car body boundary conditions and load application: Equivalent simulation models in different physical domains need to adjust information such as boundary conditions and loads according to different application scenarios. For example, boundary conditions should be defined and loads should be applied according to the actual operation of the train. Figure 4 As shown, the vehicle body chassis is constrained ( Figure 4 All degrees of freedom of the structure (the green part in the middle) are calculated, and gravity acceleration load is applied to the overall geometric model to simulate the vertical vibration condition of the vehicle structure. (4) Calculation and solution: With the help of solvers such as ANSYS (a general-purpose explicit and implicit nonlinear finite element analysis software), Abaqus (a set of finite element software for engineering simulation), and Optistruct (a professional structural optimization design software), the structural simulation model under vertical vibration conditions can be solved. Figure 5 As shown in the figure, the simulation information of deformation, stress, vibration and so on of the structure under vertical vibration condition is obtained. Figure 5The color legend in the figure indicates the displacement scale of the deformation cloud map under the corresponding working condition. For example, dark blue indicates that the structural deformation range is 0mm-0.1164mm, and red indicates that the deformation range is 0.9313mm-1.048mm. Through the post-processing function of the finite element simulation software, Figure 6 The corresponding structural deformation values ​​can be read from the marked points 1-8. Similarly, the fluid pressure can be read in the fluid simulation software, and the temperature can be read in the thermodynamic simulation software.

[0040] S102: Perform dimensionality reduction processing on the simulation information based on multiple scenarios and multiple physical domains to obtain dimensionality-reduced simulation information.

[0041] Step S102 performs dimensionality reduction processing on the obtained simulation information from two levels: multi-scenario and multi-physical domain. This embodiment does not limit the order of dimensionality reduction at the above two levels. It can be understood that, taking measuring point A as the starting point, simulation information of measuring point A in scene A and different physical domains, and simulation information of measuring point A in physical domain A and different scenes can be obtained. When there are too many measuring points, and the scenes and physical domains are richer, the amount of simulation information data obtained is relatively large. Based on the purpose of the present invention, this embodiment reduces the dimensionality of the simulation information of the measuring points based on the scenes and physical domains, so that the number of measuring points corresponding to the simulation information after dimensionality reduction remains unchanged, and only the data dimensions obtained in some scenes and some physical domains are reduced.

[0042] Furthermore, the above-mentioned dimensionality reduction processing of simulation information based on multiple scenarios to obtain simulation information after dimensionality reduction may specifically include the following steps: Step 21: constructing a data matrix to be reduced in l scenarios of the Ath physical domain according to the number of information categories n provided by the ath physical domain simulation model, and the number of data matrices to be reduced is n; Step 22: averaging the elements in each column of the data matrix to be reduced, and constructing a first matrix based on the average value and each element in the data matrix to be reduced; Step 23: obtaining a covariance matrix based on the first matrix, and the covariance matrix includes eigenvalues ​​and eigenvectors; Step 24: arranging the eigenvectors in descending order according to the eigenvalues; Step 25: constructing a second matrix based on the first k eigenvectors after arrangement; k represents the maximum number of measurement points supported by the train test; Step 26: obtaining the data matrix after dimensionality reduction of the ath physical domain under l scenarios based on the data matrix to be reduced and the second matrix.

[0043] Steps 21 to 26 are dimensionality reduction processing based on multiple scenarios, the purpose of which is to remove simulation data of redundant scenarios. Specifically, the following contents may be included: (1) The number of information types that a physical domain simulation model can provide Constructing the Ath physical domain The number of data matrices to be reduced in this scenario is , the matrix to be reduced can be expressed as , the matrices to be reduced are labeled , ,……, ; (2) For each of the above matrices to be reduced in dimension The average value of each column is calculated, and the average value of the column itself is subtracted from the elements of each column to obtain the newly constructed first matrix, which is expressed as ; (3) For the newly obtained first matrix Find the corresponding covariance matrix , and find the eigenvalues ​​and eigenvectors of the covariance matrix; (4) Arrange the eigenvectors in descending order of eigenvalues, extract the first k eigenvectors, and form the second matrix , where k represents the maximum number of test points supported by the train test; (5) Let The dimension reduction of the a-th physical domain simulation data under the l-th scenario is completed, and the resulting dimension-reduced data matrix is ​​labeled as follows: , ,……, If the data matrix after dimensionality reduction is , ,……, Compared with the matrix to be reduced , ,……, You can omit the The simulation data under the scenario, then This scenario can be removed; after dimensionality reduction, the data matrix must have the following inequality: ,in Indicates the number of test scenarios that can be removed. Similarly, the scenario index l is corrected to the number of physical domains , the dimensionality reduction of multi-physical domain information can be completed.

[0044] To better understand the dimensionality reduction process in the previous section, you can refer to the following example: The initial measurement points are arranged according to manual experience as follows: Figure 6 For the multiple measuring points shown, dimensionality reduction based on the test scenario includes: if the stress information measured by measuring points 1-8 under working condition 1 is highly correlated with the stress information of measuring points 1-8 under working condition 2, then only one of working condition 1 and working condition 2 can be retained; dimensionality reduction based on the physical domain includes: if the stress information measured by measuring points 1-8 through the structural simulation model is highly correlated with the pressure information measured by measuring points 1-8 through the fluid simulation model, then one of the structural field information and the flow field information can be retained, and the other physical domain information can be predicted by the remaining physical domain information; since there are a large number of measuring points and physical quantities to be measured in the actual arrangement, the above measuring point information needs to be processed in the form of a matrix / array, and the evaluation of the correlation of the measuring points also needs to be obtained through matrix correlation operations, thereby achieving dimensionality reduction of large-scale test data and facilitating the optimal arrangement of measuring points.

[0045] S103: Perform similarity evaluation on the initial measurement points based on the simulation information after dimensionality reduction to obtain a similarity evaluation result.

[0046] Step S103 can be understood as data dimensionality reduction based on the measuring points to reduce the number of measuring points. The specific process is to use the similarity evaluation algorithm to perform alternative evaluation on the initial measuring points, so as to reduce the number of measuring points while ensuring the comprehensiveness of the test information, so that a comprehensive test can be achieved with the least number of measuring points, while reducing the cost without affecting the reliability and accuracy of the test. Specifically, the measuring point is the location where the test device is installed, such as a sensor device, or other devices used for testing.

[0047] Further, the above-mentioned similarity evaluation of the initial measuring points based on the simulation information after dimensionality reduction to obtain the similarity evaluation result may specifically include the following steps: Step 31: taking any measuring point among the initial measuring points as the target measuring point; Step 32: calculating the Euler distance between the other initial measuring points and the target measuring point according to the simulation information after dimensionality reduction corresponding to the target measuring point and the simulation information after dimensionality reduction corresponding to other initial measuring points; Step 33: obtaining the similarity evaluation result according to the Euler distance.

[0048] It should be noted that, in this embodiment, similarity evaluation and clustering processing are performed on the initial measurement points based on the simulation information after dimensionality reduction. The similarity of the initial measurement points is represented by the weighted Euler distance of the measurement point information vector. For example, the measurement points The data matrix after dimensionality reduction is expressed as , measuring point After dimensionality reduction, the information is represented as , cluster all the initial measurement point information, where the number of categories is . Assume that one of the cores is , the kernel can be understood as any initial measurement point, and the Euler distance between each initial measurement point and the kernel is calculated in turn: ,in Indicates The importance of the simulation information category can be set by the tester according to the actual situation and meet the , .

[0049] S104: Determine key measuring points and substitute measuring points according to the similarity evaluation results.

[0050] Based on the similarity evaluation results, the initial measuring points are divided into key measuring points and substitute measuring points, and the substitute measuring points are measuring points that replace the key measuring points. It can be understood that the substitute measuring point A has a strong similarity with the key measuring point A, and the key measuring point A and the key measuring point B have no similarity, or the similarity is weak. The strong similarity and weak similarity here can be distinguished by a preset similarity threshold. In the later stage, the key measuring points can be used to realize the test of equivalent simulation models of various scenes and physical domains, thereby reducing the number of measuring points. Specifically, the initial measuring points are screened based on similarity, that is, the Euler distances of all the obtained measuring points and the kernel are sorted in ascending order; in the actual test, the key measuring points are used as the main measuring points. In order to ensure the success of the test, replacement measuring points can be selected as supplementary measuring points.

[0051] Furthermore, the above method may also include the following steps: performing a surrounding environment assessment on the initial measuring point to obtain an environmental assessment result; the surrounding environment assessment includes at least one of a surrounding layout space assessment and a surrounding geometric morphology assessment; accordingly, determining key measuring points and substitute measuring points based on the similarity assessment results, including: determining key measuring points and substitute measuring points based on the environmental assessment results and the similarity assessment results.

[0052] Specifically, this embodiment further evaluates other evaluation indicators for the measuring point, such as the surrounding environment evaluation of the measuring point, and obtains the first The preliminary evaluation index of the numbered measuring points can be expressed as ,in Represents the evaluation index number, and the values ​​of each index are normalized to the interval [0,1], where 0 represents the worst index value and 1 represents the best value. Accordingly, the optimal arrangement of the measuring points can be determined based on the evaluation index and replaceability of the measuring points, considering the preliminary evaluation index of the measuring points. If there is a constraint, the first measuring point after screening is the retained measuring point, and the subsequent ones are replaceable measuring points.

[0053] The train measuring point layout method provided by the embodiment of the present invention is applied, by obtaining equivalent simulation models of multiple scenes and multiple physical domains of the train body, and extracting simulation information of the initial measuring point based on the equivalent simulation model; performing dimensionality reduction processing on the simulation information based on multiple scenes and multiple physical domains to obtain simulation information after dimensionality reduction; performing similarity evaluation on the initial measuring point based on the simulation information after dimensionality reduction to obtain similarity evaluation results; and determining key measuring points and substitute measuring points according to the similarity evaluation results. The train measuring point layout method proposed by the present invention obtains simulation information of each measuring point using an equivalent simulation model, and optimizes the arrangement of train body measuring points driven by simulation information. This method can comprehensively consider the differences in different physical domains and different test scenarios, minimize the number of measuring points required in the train body test, reduce the cost of body testing, and avoid the loss of important test information and the repeated acquisition of equivalent information. In addition, the present invention also considers the installation environment of the measuring point in the process of optimizing the arrangement, so as to obtain more abundant body test information using fewer measuring points, which can effectively avoid the loss of test data caused by relying on traditional experience and the duplication of equivalent test information. In addition, with the help of multi-source simulation data provided by the multi-physical domain simulation model, data dimension reduction and data correlation evaluation methods are used to assist in the optimal layout of the vehicle body measurement point positions. This method can simultaneously consider different physical domain information of different test scenarios, and complete the optimal layout of the measurement point positions based on multi-source heterogeneous information obtained from different physical domains.

[0054] In order to make the present invention easier to understand, please refer to Figure 7 , Figure 7 A flow chart of a train measurement point layout method provided in an embodiment of the present invention may specifically include: (1) arranging initial measurement points based on manual experience and vehicle body geometric model information and conducting preliminary evaluation of the measurement points, including evaluation of the space around the measurement points, evaluation of the geometric morphology around the measurement points, and evaluation of other measurement point evaluation indicators. (2) Building a multi-physical domain equivalent simulation model of a train body covering multiple scenarios, including a vehicle body structure simulation model, a vehicle body external flow field simulation model, a vehicle body dynamics simulation model, and other simulation models. (3) Extracting multi-physical domain simulation information of the initial measurement point position, including vehicle body structure simulation information, vehicle body external flow field simulation information, vehicle body dynamics simulation information, and other simulation information. (4) Performing dimensionality reduction processing on the multi-scenario and multi-physical domain simulation information of the initial measurement point, including dimensionality reduction of vehicle body structure information, dimensionality reduction of vehicle body external flow field information, dimensionality reduction of vehicle body dynamics information, and dimensionality reduction of other information. (5) Performing similarity evaluation and clustering processing on the initial measurement points based on the simulation information after dimensionality reduction; screening the initial measurement points based on similarity and evaluating the interchangeability of the measurement points. (6) Determine the optimal arrangement of measuring points based on the evaluation indicators and interchangeability of the measuring points.

[0055] The present invention includes evaluation steps of indicators such as measuring point similarity, substitutability and surrounding environment evaluation in the process of measuring point layout optimization evaluation, specifically including evaluation of the layout space around the measuring point, evaluation of the geometric morphology around the measuring point, and evaluation of other measuring point evaluation indicators; building a multi-physical domain equivalent simulation model of a train body covering multiple scenes, including a body structure simulation model, a body external flow field simulation model, a body dynamics simulation model, and other simulation models; extracting multi-physical domain simulation information of the initial virtual measuring point position, including body structure simulation information, body external flow field simulation information, body dynamics simulation information, and other simulation information; performing dimensionality reduction processing on the multi-source multi-physical domain simulation information of the initial measuring point, including dimensionality reduction of body structure information, dimensionality reduction of body external flow field information, dimensionality reduction of body dynamics information, and dimensionality reduction of other information; performing similarity evaluation and clustering processing on the initial measuring points based on the information after dimensionality reduction; screening the initial virtual measuring points based on similarity to evaluate the substitutability of the measuring points; and determining the optimal arrangement scheme of the measuring points based on various evaluation indicators and substitutability of the measuring points. The present invention can comprehensively consider the differences in different physical domain test scenarios, minimize the number of measuring points required in vehicle body testing, reduce vehicle body testing costs, avoid the loss of important test information and the repeated acquisition of equivalent information. It avoids the loss of key test information caused by the traditional experience-based measurement point layout method. At the same time, due to the limited number of data channels of the test equipment, the difficulty of data collection caused by the increase in measuring points, the test preparation cycle and test-related costs. In addition, the present invention also solves the problem that the information obtained from different measuring point tests is equivalent information due to inaccurate and incomplete empirical information, resulting in repeated acquisition of information and waste of test resources. It can be seen that the determination of the measuring points of the present invention does not rely on traditional engineering experience, but is based on multi-source heterogeneous high-precision simulation data obtained based on multi-physical domain simulation models.

[0056] The following is an introduction to a train measuring point layout device provided by an embodiment of the present invention. The train measuring point layout device described below and the train measuring point layout method described above can be referred to each other.

[0057] Please refer to Figure 8 , Figure 8 A structural schematic diagram of a train measuring point layout device provided for an embodiment of the present invention may include: a simulation information acquisition module 100, used to obtain an equivalent simulation model of multiple scenes and multiple physical domains of a train body, and extract simulation information of an initial measuring point based on the equivalent simulation model; a simulation information processing module 200, used to perform dimensionality reduction processing on the simulation information based on multiple scenes and multiple physical domains to obtain reduced-dimensional simulation information; a similarity evaluation module 300, used to perform similarity evaluation on the initial measuring point based on the reduced-dimensional simulation information to obtain a similarity evaluation result; and a measuring point layout module 400, used to determine key measuring points and substitute measuring points according to the similarity evaluation result.

[0058] Based on the above embodiment, the train measuring point layout device may further include: an environmental assessment module, which is used to perform a surrounding environment assessment on the initial measuring point to obtain an environmental assessment result; the surrounding environment assessment includes at least one of a surrounding layout space assessment and a surrounding geometric morphology assessment; accordingly, the measuring point layout module 400 is specifically used to determine the key measuring points and the substitute measuring points according to the environmental assessment result and the similarity assessment result.

[0059] Based on any of the above embodiments, the simulation information processing module 200 may include: a data matrix construction unit, which is used to construct a data matrix to be reduced in dimension under l scenarios of the Ath physical domain according to the number n of information categories provided by the ath physical domain simulation model, and the number of the data matrix to be reduced in dimension is n; a first matrix construction unit, which is used to average the elements in each column of the data matrix to be reduced in dimension, and construct a first matrix based on the average value and each element in the data matrix to be reduced in dimension; a covariance matrix acquisition unit, which is used to obtain a covariance matrix based on the first matrix, and the covariance matrix includes eigenvalues ​​and eigenvectors; a sorting unit, which is used to arrange the eigenvectors in descending order according to the eigenvalues; a second matrix construction unit, which is used to construct a second matrix according to the first k eigenvectors after arrangement; the k represents the maximum number of measurement points supported by the train test; a dimensionality reduction unit, which is used to obtain the reduced dimensionality data matrix of the ath physical domain in l scenarios based on the data matrix to be reduced in dimension and the second matrix.

[0060] Based on any of the above embodiments, the simulation information acquisition module 100 may include: a simulation model building module, used to build equivalent simulation models for each scenario and each physical domain; wherein the equivalent simulation model of each physical domain includes at least one simulation model of a vehicle body structure simulation model, a vehicle body external flow field simulation model and a vehicle body dynamics simulation model.

[0061] Based on any of the above embodiments, the similarity evaluation module 300 may include: a target measuring point determination unit, used to take any measuring point among the initial measuring points as a target measuring point; a distance calculation unit, used to calculate the Euler distance between other initial measuring points and the target measuring point according to the dimensionality reduction simulation information corresponding to the target measuring point and the dimensionality reduction simulation information corresponding to other initial measuring points; and an evaluation result unit, used to obtain the similarity evaluation result according to the Euler distance.

[0062] Based on any of the above embodiments, the train measuring point layout device may further include: an initial measuring point setting module, which is used to set the initial measuring points on the surface of the train body according to manual experience and geometric model information of the train body.

[0063] Based on any of the above embodiments, the simulation information acquisition module 100 may include: a processing unit, used to build a geometric model of the train body, and use processing software to process the geometric features in the geometric model to obtain a processed geometric model; a division unit, used to mesh the processed geometric model according to the geometric features, and divide the structure into various units, and there is a connection relationship between the various units; a definition unit, used to define the train boundary conditions based on the various units according to actual operating conditions, and determine the loads to be applied; a solution unit, used to solve the processed geometric model based on the train boundary conditions and the loads to be applied, and obtain simulation information of each initial measuring point under each working condition, and the simulation information includes at least one information of structural deformation, stress and vibration.

[0064] It should be noted that the order of the modules and units in the above train measurement point layout device can be changed without affecting the logic.

[0065] The train measuring point layout device provided by the embodiment of the present invention is used to obtain the equivalent simulation model of multiple scenes and multiple physical domains of the train body through the simulation information acquisition module 100, and extract the simulation information of the initial measuring point based on the equivalent simulation model; the simulation information processing module 200 is used to perform dimensionality reduction processing on the simulation information based on multiple scenes and multiple physical domains to obtain the reduced-dimensional simulation information; the similarity evaluation module 300 is used to perform similarity evaluation on the initial measuring point based on the reduced-dimensional simulation information to obtain the similarity evaluation result; the measuring point layout module 400 is used to determine the key measuring points and the substitute measuring points according to the similarity evaluation result. This device uses the equivalent simulation model to obtain the simulation information of each measuring point, and uses the simulation information to drive the optimal layout of the train body measuring points. This method can comprehensively consider the differences in different physical domains and different test scenarios, minimize the number of measuring points required in the train body test, reduce the body test cost, and avoid the loss of important test information and the repeated acquisition of equivalent information.

[0066] The following is an introduction to a train measuring point layout device provided in an embodiment of the present invention. The train measuring point layout device described below and the train measuring point layout method described above can be referred to each other.

[0067] Please refer to Fig. 9 , Fig. 9 A structural diagram of a train measuring point layout device provided for an embodiment of the present invention may include: a memory 10 for storing a computer program; a processor 20 for executing the computer program to implement the above-mentioned train measuring point layout method.

[0068] The memory 10 , the processor 20 , and the communication interface 31 all communicate with each other via the communication bus 32 .

[0069] In an embodiment of the present invention, the memory 10 is used to store one or more programs, and the program may include program code, and the program code includes computer operation instructions. In an embodiment of the present invention, the memory 10 may store a program for realizing the following functions: obtaining an equivalent simulation model of multiple scenes and multiple physical domains of a train body, and extracting simulation information of an initial measuring point based on the equivalent simulation model; performing dimensionality reduction processing on the simulation information based on multiple scenes and multiple physical domains to obtain simulation information after dimensionality reduction; performing similarity evaluation on the initial measuring points based on the simulation information after dimensionality reduction to obtain a similarity evaluation result; and determining key measuring points and substitute measuring points according to the similarity evaluation result.

[0070] In a possible implementation, the memory 10 may include a program storage area and a data storage area, wherein the program storage area may store an operating system and an application required for at least one function, etc.; the data storage area may store data created during use.

[0071] In addition, the memory 10 may include a read-only memory and a random access memory, and provide instructions and data to the processor. A portion of the memory may also include an NVRAM. The memory stores an operating system and operating instructions, executable modules or data structures, or a subset thereof, or an extended set thereof, wherein the operating instructions may include various operating instructions for implementing various operations. The operating system may include various system programs for implementing various basic tasks and processing hardware-based tasks.

[0072] The processor 20 may be a central processing unit (CPU), an application specific integrated circuit, a digital signal processor, a field programmable gate array or other programmable logic device, a microprocessor or any conventional processor, etc. The processor 20 may call a program stored in the memory 10 .

[0073] The communication interface 31 may be an interface of a communication module, and is used to connect to other devices or systems.

[0074] Of course, it should be noted that Fig. 9 The structure shown does not constitute a limitation on the train measuring point layout device in the embodiment of the present invention. In actual applications, the train measuring point layout device may include Fig. 9 More or fewer components than shown, or combinations of certain components.

[0075] The computer-readable storage medium provided in an embodiment of the present invention is introduced below. The computer-readable storage medium described below and the train measurement point layout method described above can be referenced to each other.

[0076] The present invention also provides a computer-readable storage medium, on which a computer program is stored. When the computer program is executed by a processor, the steps of the above-mentioned train measurement point layout method are implemented.

[0077] The computer-readable storage medium may include: a USB flash drive, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk, and other media that can store program codes.

[0078] In this specification, each embodiment is described in a progressive manner, and each embodiment focuses on the differences from other embodiments. The same or similar parts between the embodiments can be referred to each other. For the device disclosed in the embodiment, since it corresponds to the method disclosed in the embodiment, the description is relatively simple, and the relevant parts can be referred to the method part.

[0079] Professionals may further appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, computer software, or a combination of the two. In order to clearly illustrate the interchangeability of hardware and software, the composition and steps of each example have been generally described in the above description according to function. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professionals and technicians may use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of the present invention.

[0080] Finally, it should be noted that, in this article, relationships such as first and second, etc. are used only to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "include", "comprises" or any other variations are intended to cover non-exclusive inclusion, so that a process, method, article or device that includes a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device.

[0081] The above is a detailed introduction to a train measuring point layout method, device, equipment and computer-readable storage medium provided by the present invention. Specific examples are used in this article to illustrate the principles and implementation methods of the present invention. The description of the above embodiments is only used to help understand the method of the present invention and its core idea; at the same time, for a general technician in this field, according to the idea of ​​the present invention, there will be changes in the specific implementation method and application scope. In summary, the content of this specification should not be understood as a limitation on the present invention.

Claims

1. A train measurement point layout method, characterized in that: include: Obtaining a multi-scenario, multi-physical domain equivalent simulation model of a train body, and extracting simulation information of an initial measurement point based on the equivalent simulation model; Performing dimensionality reduction processing on the simulation information based on multiple scenarios and multiple physical domains to obtain dimensionality-reduced simulation information; Performing similarity evaluation on the initial measurement points based on the simulation information after dimensionality reduction to obtain a similarity evaluation result; Determining key measuring points and substitute measuring points according to the similarity evaluation results; Before determining the key measuring points and the substitute measuring points according to the similarity evaluation results, the method further includes: Performing a surrounding environment assessment on the initial measurement point to obtain an environmental assessment result; the surrounding environment assessment includes at least one of a surrounding layout space assessment and a surrounding geometric shape assessment; Accordingly, the key measuring points and the substitute measuring points are determined according to the similarity evaluation results, including: The key measuring points and the substitute measuring points are determined according to the environmental assessment result and the similarity assessment result.

2. The train measurement point layout method according to claim 1, characterized in that: The simulation information is subjected to dimensionality reduction processing based on multiple scenarios to obtain dimensionality-reduced simulation information, including: According to the number n of information categories provided by the a-th physical domain simulation model, construct a data matrix to be reduced in dimension under the l-th scenario of the A-th physical domain; the number of the data matrix to be reduced in dimension is the same as the number of the information categories; Calculate the average value of each column element in the data matrix to be reduced in dimension, and construct a first matrix based on the average value and each element in the data matrix to be reduced in dimension; Obtaining a covariance matrix based on the first matrix, wherein the covariance matrix includes eigenvalues ​​and eigenvectors; Arrange the eigenvectors in descending order according to the eigenvalues; Constructing a second matrix according to the first k eigenvectors after arrangement; wherein k represents the maximum number of measurement points supported by the train test; Based on the data matrix to be reduced in dimensionality and the second matrix, a reduced-dimensionality data matrix of the a-th physical domain in l scenarios is obtained.

3. The train measurement point layout method according to claim 1, characterized in that: Based on the dimensionality-reduced simulation information, similarity evaluation is performed on the initial measurement points to obtain similarity evaluation results, including: Taking any measuring point among the initial measuring points as a target measuring point; Calculate the Euler distance between the other initial measuring points and the target measuring point according to the dimensionality-reduced simulation information corresponding to the target measuring point and the dimensionality-reduced simulation information corresponding to the other initial measuring points; The similarity evaluation result is obtained according to the Euler distance.

4. The train measurement point layout method according to claim 1, characterized in that: Before extracting simulation information of the initial measurement point based on the equivalent simulation model, the method further includes: The initial measuring points are set on the surface of the train body according to manual experience and geometric model information of the train body.

5. The train measurement point layout method according to claim 1, characterized in that: Obtain a multi-scenario, multi-domain equivalent simulation model of the train body, including: Build equivalent simulation models for each scenario and each physical domain; wherein the equivalent simulation model for each physical domain includes at least one simulation model of a vehicle body structure simulation model, a vehicle body external flow field simulation model, and a vehicle body dynamics simulation model.

6. The train measurement point layout method according to claim 1, characterized in that: Obtaining a multi-scenario, multi-physical domain equivalent simulation model of a train body, and extracting simulation information of an initial measurement point based on the equivalent simulation model, including: Building a geometric model of the train body, and processing geometric features in the geometric model using processing software to obtain a processed geometric model; Meshing the processed geometric model according to the geometric features to divide the structure into various units, wherein there is a connection relationship between the various units; Based on the various units, train boundary conditions are defined according to actual operating conditions, and loads to be applied are determined; The processed geometric model is solved based on the train boundary conditions and the load to be applied to obtain simulation information of each initial measurement point under each working condition, wherein the simulation information includes at least one of structural deformation, stress and vibration.

7. A train measuring point layout device, characterized in that: include: A simulation information acquisition module is used to obtain an equivalent simulation model of a train body in multiple scenarios and multiple physical domains, and to extract simulation information of an initial measurement point based on the equivalent simulation model; A simulation information processing module, used for performing dimension reduction processing on the simulation information based on multiple scenarios and multiple physical domains to obtain reduced-dimensional simulation information; A similarity evaluation module, used for performing similarity evaluation on the initial measurement points based on the simulation information after dimensionality reduction to obtain a similarity evaluation result; A measuring point layout module, used for determining key measuring points and substitute measuring points according to the similarity evaluation result; Also includes: The environmental assessment module is used to perform a surrounding environment assessment on the initial measuring point to obtain an environmental assessment result; the surrounding environment assessment includes at least one of a surrounding layout space assessment and a surrounding geometric morphology assessment; correspondingly, the measuring point layout module is specifically used to determine the key measuring point and the substitute measuring point according to the environmental assessment result and the similarity assessment result.

8. A train measuring point layout device, characterized in that: include: Memory for storing computer programs; A processor, configured to implement the train measurement point layout method as described in any one of claims 1 to 6 when executing the computer program.

9. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores computer-executable instructions, and when the computer-executable instructions are loaded and executed by the processor, the train measurement point layout method according to any one of claims 1 to 6 is implemented.

Images