A sensor layout method and system for rail vehicle status monitoring

Abstract

The present invention relates to the technical field of rail vehicle state monitoring, and specifically discloses a sensor layout method and system for rail vehicle state monitoring, the method comprising: obtaining a finite element model of the rail vehicle load-bearing structure, uniformly extracting multiple structural points; obtaining multiple initial layout schemes based on the multiple structural points through modal analysis; for each initial layout scheme under multiple loads, reconstructing the simulated strains of multiple measuring points and the strains of all structural points; learning a local-global strain relationship model based on an extreme learning machine; taking each initial layout scheme as a particle, taking the root mean square error between the output strain of the local-global strain relationship model and the simulated strain as a constraint, and obtaining the optimal sensor layout based on a particle swarm optimization method. The present invention optimizes the sensor layout by combining a particle swarm optimization algorithm with an extreme learning machine, which helps to reduce the reconstruction error of the strain field of the load-bearing structure.

Description

Technical Field

[0001] The present invention belongs to the technical field of rail vehicle status monitoring, and in particular relates to a sensor layout method and system for rail vehicle status monitoring. Background Art

[0002] The statements in this section merely provide background information related to the present invention and do not necessarily constitute prior art.

[0003] As one of the main public transportation modes, rail vehicles greatly affect people's travel methods and rhythm of life. Failure of rail vehicles during long-term operation usually causes huge economic losses and threatens human personal safety. Therefore, it is very necessary to conduct real-time health monitoring of rail vehicles.

[0004] Reasonable arrangement of sensors to collect real-time status information of rail vehicles is the basis for effective monitoring, and has an important impact on the efficiency and accuracy of structural reconstruction. When considering the layout of sensors, two aspects usually need to be taken into account. The first is the utilization efficiency of sensors, and the second is the reliability of the optical fiber sensor network system. The two are to a certain extent contradictory, so it is necessary to propose a method that can achieve the optimal layout of the optical fiber sensor network while ensuring the reliability of the sensor system under the premise of meeting the established requirements. Traditional sensor optimization layout methods such as effective independence method, origin residue method, QR decomposition method and singular value decomposition method are only applicable to structural models with fewer degrees of freedom, and can obtain more accurate measurement results. For rail vehicles, such as high-speed trains and other large-scale complex structures, due to the greatly increased degrees of freedom, if the traditional sensor optimization layout method is still used, the position accuracy is difficult to guarantee, which is not conducive to the subsequent strain field reconstruction; although the measurement accuracy can be improved by adding sensors, it increases the cost on the one hand, and greatly increases the computational complexity on the other hand, and also causes sensor information redundancy. Therefore, the layout of sensors in key components of rail vehicles still relies mostly on workers' experience. Summary of the invention

[0005] In order to overcome the shortcomings of the above-mentioned prior art, the present invention provides a sensor layout method and system for rail vehicle status monitoring. Aiming at the problem of sensor layout optimization, a method combining a particle swarm optimization algorithm and an extreme learning machine is used to optimize and calibrate the FBG sensor, which helps to reduce the strain field reconstruction error of the load-bearing structure.

[0006] To achieve the above objectives, one or more embodiments of the present invention provide the following technical solutions:

[0007] A sensor layout method for rail vehicle status monitoring comprises the following steps:

[0008] Obtaining a finite element model of the rail vehicle load-bearing structure, and evenly extracting a plurality of structural points;

[0009] Performing modal analysis on the finite element model, and obtaining a plurality of initial layout schemes based on the plurality of structural points according to the modal analysis results;

[0010] For each initial layout scheme under various loads, the simulated strains of multiple measuring points and the strains of all structural points are reconstructed;

[0011] According to the simulated strains of multiple reconstructed measuring points and the strains of all structural points, a local-global strain relationship model is learned based on an extreme learning machine;

[0012] Each initial layout scheme is regarded as a particle, and the root mean square error between the output strain of the local-global strain relationship model and the simulated strain is used as a constraint to obtain the optimal layout of the sensor based on the particle swarm optimization method.

[0013] Furthermore, the methods for obtaining multiple initial layout solutions are:

[0014] Performing modal analysis based on the finite element model to obtain vibration characteristics of the multiple structural points;

[0015] Selecting a plurality of candidate measuring points according to the vibration characteristics;

[0016] Based on different combinations of the plurality of candidate measuring points, a plurality of initial layout solutions are obtained.

[0017] Furthermore, modal analysis is performed on the finite element model to obtain modal vibration shape matrices of the multiple structural points and modal vibration shape matrices of multiple measuring points in each initial layout scheme.

[0018] Furthermore, the simulation methods of various loads include:

[0019] The load-bearing structure is divided into regions, and in each initial layout scheme, static loading is performed on one or more regions therein to obtain multiple loads and simulated strains of multiple measuring points in each initial layout scheme under various loads.

[0020] Furthermore, the strains of all structural points are reconstructed including:

[0021] For each initial layout scheme under each load, obtain the simulated strain values ​​of multiple measuring points therein, and solve the modal coordinates according to the simulated strain values ​​of the multiple measuring points and the corresponding modal vibration matrix;

[0022] According to the modal coordinates and the modal vibration shapes of the multiple structural points, strain values ​​of the multiple structural points corresponding to each initial layout scheme under each load are obtained.

[0023] One or more embodiments provide a sensor layout system for rail vehicle status monitoring, comprising:

[0024] A finite element model acquisition module, used to acquire a finite element model of the load-bearing structure of the rail vehicle and evenly extract multiple structural points;

[0025] An initial layout determination module, used to perform modal analysis on the finite element model, and obtain multiple initial layout solutions based on the multiple structural points according to the modal analysis results;

[0026] The global strain reconstruction module is used to reconstruct the simulated strains of multiple measuring points and the strains of all structural points for each initial layout scheme under various loads;

[0027] A local-global relationship learning module is used to learn a local-global strain relationship model based on an extreme learning machine according to the simulated strains of multiple measurement points and the strains of all structural points reconstructed;

[0028] The layout optimization module is used to take each initial layout scheme as a particle, take the root mean square error between the output strain of the local-global strain relationship model and the simulated strain as a constraint, and obtain the optimal layout of the sensor based on the particle swarm optimization method.

[0029] Furthermore, the methods for obtaining multiple initial layout solutions are:

[0030] Performing modal analysis based on the finite element model to obtain vibration characteristics of the multiple structural points;

[0031] Selecting a plurality of candidate measuring points according to the vibration characteristics;

[0032] Based on different combinations of the plurality of candidate measuring points, a plurality of initial layout solutions are obtained.

[0033] Furthermore, modal analysis is performed on the finite element model to obtain modal vibration shape matrices of the multiple structural points and modal vibration shape matrices of multiple measuring points in each initial layout scheme.

[0034] Furthermore, the simulation methods of various loads include:

[0035] The load-bearing structure is divided into regions, and in each initial layout scheme, static loading is performed on one or more regions therein to obtain multiple loads and simulated strains of multiple measuring points in each initial layout scheme under various loads.

[0036] Furthermore, the strains of all structural points are reconstructed including:

[0037] For each initial layout scheme under each load, obtain the simulated strain values ​​of multiple measuring points therein, and solve the modal coordinates according to the simulated strain values ​​of the multiple measuring points and the corresponding modal vibration matrix;

[0038] According to the modal coordinates and the modal vibration shapes of the multiple structural points, strain values ​​of the multiple structural points corresponding to each initial layout scheme under each load are obtained.

[0039] One or more embodiments provide an electronic device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements a sensor layout method for rail vehicle status monitoring when executing the program.

[0040] One or more embodiments provide a computer-readable storage medium having a computer program stored thereon, which implements the sensor layout method for rail vehicle status monitoring when the program is executed by a processor.

[0041] One or more of the above technical solutions have the following beneficial effects:

[0042] By using modal analysis, multiple initial layout schemes are specified from the load-bearing structure of the rail vehicle, ensuring that the subsequent measurement points can be evenly distributed in the load-bearing structure;

[0043] For each initial layout scheme, the strain fields corresponding to each initial layout scheme under different loads and the full-field strain field are obtained and used as training data. Local-global relationship learning is performed based on the extreme learning machine, and the root mean square error of the reconstructed strain and the simulated strain is used as the optimization target. The particle swarm optimization algorithm is used to find the optimal layout scheme, thereby greatly reducing the reconstruction error of the strain field of the load-bearing structure, improving the reliability of the sensor measurement data, and being able to accurately simulate the strain field of the load-bearing structure of the rail vehicle, providing a basis for condition monitoring. BRIEF DESCRIPTION OF THE DRAWINGS

[0044] The accompanying drawings in the specification, which constitute a part of the present invention, are used to provide a further understanding of the present invention. The exemplary embodiments of the present invention and their descriptions are used to explain the present invention and do not constitute improper limitations on the present invention.

[0045] Figure 1 A flow chart of a method for optimizing the layout of sensors for a load-bearing structure of a rail vehicle in one or more embodiments of the present invention;

[0046] Figure 2 FIG. 4 is a structural diagram of an extreme learning machine in one or more embodiments of the present invention. DETAILED DESCRIPTION

[0047] It should be noted that the following detailed descriptions are exemplary and are intended to provide further explanation of the present invention. Unless otherwise specified, all technical and scientific terms used herein have the same meanings as those commonly understood by those skilled in the art to which the present invention belongs.

[0048] It should be noted that the terms used herein are only for describing specific embodiments and are not intended to limit exemplary embodiments according to the present invention. As used herein, unless the context clearly indicates otherwise, the singular form is also intended to include the plural form. In addition, it should be understood that when the terms "comprising" and / or "including" are used in this specification, it indicates the presence of features, steps, operations, devices, components and / or combinations thereof.

[0049] In the absence of conflict, the embodiments of the present invention and the features of the embodiments may be combined with each other.

[0050] Embodiment 1

[0051] Fiber grating sensors (FBG sensors) have the advantages of being able to realize multi-parameter and multi-point monitoring and having high sensitivity, so they have gradually become the most widely used and most mature fiber optic sensors in the engineering field. This embodiment discloses a method for optimizing the layout of sensors for the load-bearing structure of a rail vehicle. Specifically, based on finite element analysis and FBG sensor experiments, the global strain modal matrix of the load-bearing structure, the modal matrix of the corresponding nodes of the FBG sensor, and the strain values ​​of the FBG sensor measurement points are extracted, and the full-field strain of the load-bearing structure is reconstructed using the modal superposition method. The modal superposition method and particle swarm extreme learning machine (PSO-ELM) are used to optimize the layout of the FBG sensors to reduce the strain reconstruction error of the load-bearing structure. The method includes the following steps:

[0052] Step 1: Establish a finite element model of the rail vehicle load-bearing structure and evenly extract multiple structural points.

[0053] In this embodiment, the load-bearing structure is the crossbeam structure of the train, which is the basis for the installation of other parts and provides support for the entire car body.

[0054] A finite element model of the load-bearing structure is established by acquiring the actual parameters of the load-bearing structure. After the finite element model is established, a plurality of structural points are used to approximately replace the entire load-bearing structure and serve as a basis for screening subsequent sensor layout points. In this embodiment, the number of the plurality of structural points is denoted as n.

[0055] Those skilled in the art will appreciate that the above-mentioned finite element modeling can be implemented using currently available finite element analysis software, which is not limited here.

[0056] Step 2: Performing modal analysis based on the finite element model, and obtaining a plurality of initial layout schemes based on the plurality of structural points.

[0057] The step 2 specifically includes:

[0058] Step 2.1: Performing modal analysis based on the finite element model to obtain vibration characteristics of the multiple structural points;

[0059] Step 2.2: selecting a plurality of candidate measuring points according to the vibration characteristics;

[0060] Step 2.3: Based on different combinations of the plurality of candidate measurement points, a plurality of initial layout solutions are obtained.

[0061] According to the selected modal order r, this embodiment first performs vibration simulation on the multiple structural points based on the finite element model, selects strain points as candidate measuring points according to the vibration amplitude, and the number of candidate measuring points is recorded as p. Specifically, according to the fixed support conditions and actual load-bearing conditions of the load-bearing structure in service, the fixed supports at both ends of the beam are used as boundary conditions, and a modal analysis is performed on it, and the modal order is selected according to the modal effective mass accounting for more than 80%.

[0062] Since the principle of sensor layout is to minimize the number of sensors while ensuring the reliability of the sensor system, this embodiment selects m of the p candidate measurement points as the initial layout of the FBG sensors, thus obtaining C p m initial layout solutions. Those skilled in the art will appreciate that if m takes multiple different values, there are more initial layout solutions.

[0063] In addition, based on the above modal analysis, the modal vibration matrix of the multiple structural points is also obtained: And for each initial layout scheme, the modal vibration matrix of multiple measurement points is obtained Among them, n is the number of multiple structural points, m is the number of measurement points, and r is the selected modal order.

[0064] Step 3: The load-bearing structure is subjected to static loading of various loads in sequence. For each initial layout scheme under various loads, the simulated strains of multiple measuring points and the strains of all structural points are reconstructed.

[0065] The step 3 specifically includes:

[0066] Step 3.1: Divide the load-bearing structure into regions, and statically load one or more regions in each initial layout scheme to obtain multiple loads and simulated strains of multiple measuring points in each initial layout scheme under various loads.

[0067] Specifically, a static analysis is performed on the structure, a load loading method is designed according to the stress conditions of the load-bearing structure during service, and a numerical simulation static loading is performed on the load-bearing structure. Specifically, the load-bearing structure is divided into regions, for example, 20 regions, and static loading is performed on one or more regions, and static loading of various load combinations is sequentially simulated to obtain multiple loads, the number of loads is recorded as N, and the simulated strains of m measuring points under each load are obtained.

[0068] Step 3.2: For each initial layout scheme under each load, obtain the simulated strain values ​​of multiple measuring points, and reconstruct the strains of all structural points based on the modal superposition method. Specifically, it includes: solving the modal coordinates according to the simulated strain values ​​of the multiple measuring points and the corresponding modal vibration matrix; according to the modal coordinates and the modal vibration shapes of the multiple structural points, obtaining the strain values ​​of the multiple structural points corresponding to each initial layout scheme under each load.

[0069] Based on the modal superposition method, for each load, the strain of m measuring points can be expressed as:

[0070]

[0071] In the formula, q r is the modal coordinate. When the number of sensors is greater than or equal to the selected modal order, q r The least squares solution of is:

[0072]

[0073] In the formula, yes The pseudo-inverse of

[0074] After determining the modal coordinates, the strain values ​​of all structural points can be expressed as:

[0075]

[0076] In this way, the strain values ​​of all structural points of the load-bearing structure are obtained and recorded as the full-field reconstruction strain, thus realizing the construction of the strain field reconstruction model of the load-bearing structure.

[0077] Step 4: Based on the simulated strains of multiple reconstructed measurement points and the strains of all structural points, the local-global strain relationship model is learned based on the extreme learning machine (ELM).

[0078] Based on the modal superposition method, the strain fields under N loads are reconstructed respectively to obtain the full-field reconstructed strain ε corresponding to each initial layout scheme under N loads. n , from which k (k < N) initial layout schemes are selected under loads. The simulated strain ε of the FBG sensor measurement positionm and the full-field reconstruction strain ε n As a training set, it is used for extreme learning machine learning. The principle is as follows Figure 2 shown.

[0079] Extreme Learning Machine (ELM) is a supervised learning algorithm for single hidden layer feedforward neural networks (SLFNs). The model of standard SLFNs is:

[0080]

[0081] In the formula, is the number of hidden layer nodes, g(·) is the activation function, w i is the input weight, b i is the hidden layer node threshold, β i is the hidden layer output weight, x j is the input vector; o j is the output vector.

[0082] Given k learning samples (ε jm ,ε jn ),j=1,2,...,k, where the input is ε jm =[ε 1m ,ε 2m ,...,ε jm ] T ∈R k , the output is ε jn =[ε 1n ,ε 2n ,...,ε jN ] T ∈R k , the learning method of ELM is:

[0083] (1) Determine the number of hidden layer nodes and activation function, and randomly set the input weights and hidden layer node thresholds;

[0084] (2) Calculate the hidden layer output matrix, that is,

[0085]

[0086] (3) Calculate the output layer weights Right now:

[0087]

[0088] In the formula, H + is the Moore-Penrose generalized inverse of H, T = [ε 1 ε 2 ··· ε n ] k×n

[0089] Step 5: Take each initial layout as a particle, take the root mean square error between the output strain of the local-global strain relationship model and the simulated strain as a constraint, and obtain the optimal layout of the sensor based on the particle swarm optimization method (PSO).

[0090] The initial FBG sensor position coordinates (x m ,y m ) as the element of the particle in PSO, there are C p m In this paper, the root mean square error (RMSE) between the expected output strain of the ELM learning samples and the simulated output strain is used as the fitness of PSO, and PSO is used to optimize the layout of FBG sensors, so that ELM can achieve higher accuracy.

[0091] Among them, the root mean square error between the ELM output strain and the simulated strain at the FBG sensor measurement position is used as the constraint:

[0092]

[0093] In the formula, E m is the output strain of the ELM output, ε m is the simulated strain, m is the number of sensors, that is, the corresponding coordinate position.

[0094] Specifically, in steps 4-5, the learning process of PSO-ELM is:

[0095] ① Given a learning sample. The learning sample includes an input vector and an expected output vector. Before training, the learning sample is normalized.

[0096] ② Establish the PSO-ELM neural network topology, including determining the number of neurons in the input layer, hidden layer, and output layer and selecting the activation function.

[0097] ③ Generate a population. Set the number of particles Generate z random number vectors in the range of [-1, 1] as individual particles, each with elements, is the number of hidden layer nodes, and l is the number of neurons in the input layer.

[0098] ④ Initialize PSO’s speed, inertia weight, acceleration factor, and maximum number of iterations.

[0099] ⑤ Calculate the fitness value of each particle. According to equations (4), (5), and (6), the actual output of the learning sample is calculated, and the root mean square error between the expected output and the actual output is further calculated, that is, the fitness of each particle is obtained, and the individual extreme value of each particle and the group extreme value of the population are found.

[0100] ⑥Update the particle's velocity and position according to the two iterative formulas of PSO.

[0101] ⑦ Determine whether the maximum number of iterations or the minimum error has been reached. If so, stop the iteration. The group extreme value at this time is the optimal layout of the FBG sensor optimized by PSO. If not, go to ⑤ and continue iterating.

[0102] By combining the particle swarm optimization algorithm with the extreme learning machine to optimize the calibration of FBG sensors, it is helpful to reduce the strain field reconstruction error of the load-bearing structure, which has broad prospects and high engineering application value for the application of large structures.

[0103] Embodiment 2

[0104] A sensor layout system for rail vehicle status monitoring, characterized by comprising:

[0105] A finite element model acquisition module, used to acquire a finite element model of the load-bearing structure of the rail vehicle and evenly extract multiple structural points;

[0106] An initial layout determination module, used to perform modal analysis on the finite element model, and obtain multiple initial layout solutions based on the multiple structural points according to the modal analysis results;

[0107] The global strain reconstruction module is used to reconstruct the simulated strains of multiple measuring points and the strains of all structural points for each initial layout scheme under various loads;

[0108] A local-global relationship learning module is used to learn a local-global strain relationship model based on an extreme learning machine according to the simulated strains of multiple measurement points and the strains of all structural points reconstructed;

[0109] The layout optimization module is used to take each initial layout scheme as a particle, take the root mean square error between the output strain of the local-global strain relationship model and the simulated strain as a constraint, and obtain the optimal layout of the sensor based on the particle swarm optimization method.

[0110] Embodiment 3

[0111] The purpose of this embodiment is to provide an electronic device.

[0112] An electronic device comprises a memory, a processor and a computer program stored in the memory and executable on the processor, wherein when the processor executes the program, the sensor layout method for rail vehicle status monitoring as described in the first embodiment is implemented.

[0113] Embodiment 4

[0114] The purpose of this embodiment is to provide a computer-readable storage medium.

[0115] A computer-readable storage medium stores a computer program, which, when executed by a processor, implements the sensor layout method for rail vehicle status monitoring as described in the first embodiment.

[0116] The steps involved in the above embodiments 2 to 4 correspond to the method embodiment 1, and the specific implementation methods can refer to the relevant description part of embodiment 1. The term "computer-readable storage medium" should be understood as a single medium or multiple media including one or more instruction sets; it should also be understood to include any medium that can store, encode or carry an instruction set for execution by a processor and enable the processor to execute any method in the present invention.

[0117] Those skilled in the art should understand that the modules or steps of the present invention described above can be implemented by a general-purpose computer device, or alternatively, they can be implemented by a program code executable by a computing device, so that they can be stored in a storage device and executed by the computing device, or they can be made into individual integrated circuit modules, or multiple modules or steps therein can be made into a single integrated circuit module for implementation. The present invention is not limited to any specific combination of hardware and software.

[0118] Although the above describes the specific implementation mode of the present invention in conjunction with the accompanying drawings, it is not intended to limit the scope of protection of the present invention. Those skilled in the art should understand that various modifications or variations that can be made by those skilled in the art on the basis of the technical solution of the present invention without creative work are still within the scope of protection of the present invention.

Claims

1. A sensor layout method for rail vehicle condition monitoring, It is characterized in that The following steps are involved: Obtaining a finite element model of the rail vehicle load-bearing structure, and evenly extracting a plurality of structural points; Performing modal analysis on the finite element model, and obtaining a plurality of initial layout schemes based on the plurality of structural points according to the modal analysis results; For each initial layout scheme under various loads, the simulated strains of multiple measuring points and the strains of all structural points are reconstructed; According to the simulated strains of multiple reconstructed measuring points and the strains of all structural points, a local-global strain relationship model is learned based on an extreme learning machine; Each initial layout scheme is regarded as a particle, and the root mean square error between the output strain of the local-global strain relationship model and the simulated strain is used as a constraint to obtain the optimal layout of the sensor based on the particle swarm optimization method.

2. The sensor layout method for rail vehicle status monitoring according to claim 1, It is characterized in that The methods for obtaining multiple initial layout solutions are as follows: Performing modal analysis based on the finite element model to obtain vibration characteristics of the multiple structural points; Selecting a plurality of candidate measuring points according to the vibration characteristics; Based on different combinations of the plurality of candidate measuring points, a plurality of initial layout solutions are obtained.

3. The sensor layout method for rail vehicle status monitoring according to claim 1, It is characterized in that The finite element model is subjected to modal analysis to obtain modal vibration shape matrices of the plurality of structural points and modal vibration shape matrices of the plurality of measuring points in each initial layout scheme.

4. The sensor layout method for rail vehicle status monitoring according to any one of claims 1 to 3, It is characterized in that The simulation methods for various loads include: The load-bearing structure is divided into regions, and in each initial layout scheme, static loading is performed on one or more regions therein to obtain multiple loads and simulated strains of multiple measuring points in each initial layout scheme under various loads.

5. The sensor layout method for rail vehicle status monitoring according to any one of claims 1 to 3, It is characterized in that Reconstruction of the strains at all structural points includes: For each initial layout scheme under each load, obtain the simulated strain values ​​of multiple measuring points therein, and solve the modal coordinates according to the simulated strain values ​​of the multiple measuring points and the corresponding modal vibration matrix; According to the modal coordinates and the modal vibration shapes of the multiple structural points, strain values ​​of the multiple structural points corresponding to each initial layout scheme under each load are obtained.

6. A sensor layout system for rail vehicle condition monitoring, It is characterized in that include: A finite element model acquisition module, used to acquire a finite element model of the load-bearing structure of the rail vehicle and evenly extract multiple structural points; An initial layout determination module, used to perform modal analysis on the finite element model, and obtain multiple initial layout solutions based on the multiple structural points according to the modal analysis results; The global strain reconstruction module is used to reconstruct the simulated strains of multiple measuring points and the strains of all structural points for each initial layout scheme under various loads; A local-global relationship learning module is used to learn a local-global strain relationship model based on an extreme learning machine according to the simulated strains of multiple measurement points and the strains of all structural points reconstructed; The layout optimization module is used to take each initial layout scheme as a particle, take the root mean square error between the output strain of the local-global strain relationship model and the simulated strain as a constraint, and obtain the optimal layout of the sensor based on the particle swarm optimization method.

7. The sensor layout system for rail vehicle status monitoring according to claim 6, It is characterized in that The methods for obtaining multiple initial layout solutions are as follows: Performing modal analysis based on the finite element model to obtain vibration characteristics of the multiple structural points; Selecting a plurality of candidate measuring points according to the vibration characteristics; Based on different combinations of the plurality of candidate measuring points, a plurality of initial layout solutions are obtained.

8. The sensor layout system for rail vehicle status monitoring according to claim 6, It is characterized in that The finite element model is subjected to modal analysis to obtain modal vibration shape matrices of the plurality of structural points and modal vibration shape matrices of the plurality of measuring points in each initial layout scheme.

9. A sensor layout system for rail vehicle condition monitoring according to any one of claims 6 to 8, It is characterized in that The simulation methods for various loads include: The load-bearing structure is divided into regions, and in each initial layout scheme, static loading is performed on one or more regions therein to obtain multiple loads and simulated strains of multiple measuring points in each initial layout scheme under various loads.

10. A sensor layout system for rail vehicle status monitoring according to any one of claims 6 to 8, It is characterized in that Reconstruction of the strains at all structural points includes: For each initial layout scheme under each load, the simulated strain values ​​of multiple measuring points are obtained, and the modal coordinates are solved according to the simulated strain values ​​of the multiple measuring points and the corresponding modal vibration matrix; According to the modal coordinates and the modal vibration shapes of the multiple structural points, strain values ​​of the multiple structural points corresponding to each initial layout scheme under each load are obtained.

11. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, It is characterized in that When the processor executes the program, the sensor layout method for rail vehicle status monitoring as described in any one of claims 1 to 5 is implemented.

12. A computer-readable storage medium having a computer program stored thereon, It is characterized in that When the program is executed by a processor, a sensor layout method for rail vehicle status monitoring as described in any one of claims 1 to 5 is implemented.

Images