A comprehensive sensing method for service state of a foundation deformation section ballastless track

Abstract

The application provides a comprehensive perception method for the service state of a foundation deformation section ballastless track. The method comprises the following steps: determining the track lower foundation deformation characteristics and the foundation deformation simulation input parameters, and constructing a ballastless track-lower foundation analysis model which can consider the influence of different foundation deformations; calculating and analyzing the track structure space-time response under the foundation deformation according to the analysis model, and determining the track system high-sensitive response index and the sensitive area; determining the correlation between the track structure space-time response under different foundation deformations based on a neural network model; and realizing the comprehensive perception of the foundation deformation full-section track service state according to the correlation between the track system high-sensitive monitoring point data and the track structure space-time response. The application determines the track system high-sensitive response index and the sensitive area based on the finite element method, determines the correlation between the track structure space-time response under different foundation deformations in combination with the neural network model, and realizes the comprehensive perception of the foundation deformation full-section track service state.

Description

Technical Field

[0001] This invention relates to the field of railway track condition monitoring technology, and in particular to a comprehensive sensing method for the service status of ballastless track in areas with foundation deformation. Background Technology

[0002] Foundation deformation in high-speed railway networks not only affects the service performance of track structures but also threatens the safe operation of trains. Therefore, to ensure the safety and stability of track lines, it is essential to conduct long-term monitoring of the track system in areas with foundation deformation, thereby promptly understanding the service status of the track structure and clarifying its service performance under foundation deformation.

[0003] Currently, in terms of sensing the service status of track structures in areas with foundation deformation, existing monitoring methods typically employ two approaches. On the one hand, to ensure the acquisition of all highly sensitive monitoring indicators and information on sensitive areas, and to comprehensively reflect the service status of the track system, a large number of sensors are usually deployed on-site to sense the service performance of the track system. However, the deployment of a large number of sensors not only causes overlap in the information collected between some measuring points, but also incurs high monitoring costs. On the other hand, track monitoring sites often face the challenge of limited number and location of measuring points, and the selection of sensor locations generally relies solely on experience, making it difficult for the measuring point data results to comprehensively reflect the service status of the track structure.

[0004] Therefore, providing a method for optimizing the monitoring indicators of ballastless track in areas with basic deformation, and obtaining comprehensive and accurate information on the structural service status by optimizing the arrangement of sensors and the spatiotemporal response of the track system, is of great significance for the sustainable development of track system safety monitoring. Summary of the Invention

[0005] The embodiments of the present invention provide a comprehensive sensing method for the service status of ballastless track in a foundation deformation section, so as to achieve comprehensive sensing of the service status of the track in the entire foundation deformation section.

[0006] To achieve the above objectives, the present invention adopts the following technical solution.

[0007] A comprehensive sensing method for the service status of ballastless track in areas with basic deformation includes:

[0008] Based on the foundation deformation monitoring data of high-speed railway ballastless track, the deformation characteristics of the track substructure and the foundation deformation simulation parameters are determined, and input parameter sets for different foundation deformation characteristics are constructed.

[0009] Based on the finite element method, and combined with parametric simulation of track foundation deformation characteristics and track structure design information, a refined analysis model of ballastless track-subfoundation that can consider the influence of different foundation deformations is constructed.

[0010] Input parameter sets with different foundation deformation characteristics are input into the ballastless track-sub-foundation refined analysis model to calculate and analyze the spatiotemporal response of the track structure under foundation deformation, obtain the spatiotemporal response data of the track structure under foundation deformation, and determine the high-sensitivity response index and sensitive area of ​​the track system.

[0011] Based on the spatiotemporal response data of the track structure under the aforementioned basic deformation, a neural network model is used to construct the correlation between the spatiotemporal responses of the track structure under different basic deformation characteristics.

[0012] Based on the high-sensitivity response index of the track system and the optimized layout scheme of monitoring points for the track system in the foundation deformation section of the sensitive area;

[0013] Based on the correlation between the optimized track system monitoring point data and the spatiotemporal response of the track structure, a comprehensive perception result of the service status of the track system across the entire section is achieved by understanding the foundation deformation.

[0014] Preferably, the step of determining the deformation characteristics and simulation parameters of the sub-foundation based on the foundation deformation monitoring data of high-speed railway ballastless track, and constructing an input parameter set for different foundation deformation characteristics, includes:

[0015] Based on the deformation monitoring data of high-speed railway ballastless track foundations, the deformation characteristics of the track sub-foundation are determined. These deformation characteristics include uneven settlement and frost heave deformation caused by the roadbed; uneven settlement and arching deformation caused by tunnels; and flexural deformation, beam end rotation, and pier settlement deformation caused by bridges.

[0016] Based on monitoring data and fitting results, the characteristics of the arch deformation of the high-speed railway tunnel are clarified, the simulation parameters of the arch deformation of the tunnel foundation are determined, and the input parameter set of different foundation deformation characteristics is constructed. The input parameter set of the deformation characteristics of the track sub-foundation includes: the spatial deformation morphology characteristics of the sub-foundation; the spatial location of the track structure in the deformation section; the wavelength, amplitude and lateral non-uniformity coefficient of the foundation deformation.

[0017] Preferably, the parametric simulation based on the finite element method, combined with the deformation characteristics of the track foundation and the track structure design information, constructs a refined analysis model of the ballastless track-subfoundation that can consider the influence of different foundation deformations, including:

[0018] The parametric simulation of track structure design information includes the dimensions, elastic modulus, Poisson's ratio, and density of rails, sleepers, track slabs, reinforcing bars, and tunnel inverts. Based on the finite element method, and combined with the parametric simulation of track foundation deformation characteristics and track structure design information, a refined analysis model of ballastless track-subfoundation is constructed that can consider the influence of different foundation deformations. The refined analysis model of ballastless track-subfoundation includes: a nonlinear damage model considering the materials of the track structure, and a cohesive force model simulating the bonding-debonding-contact interaction between interlayer contact interfaces. This cohesive force model defines the damage development process of the interlayer bonding interface and simulates the bonding-debonding-contact process of the interlayer contact interface.

[0019] Preferably, the step of inputting a set of input parameters with different foundation deformation characteristics into the ballastless track-subfoundation refined analysis model to calculate and analyze the spatiotemporal response of the track structure under foundation deformation, obtaining spatiotemporal response data of the track structure under foundation deformation, and determining the high-sensitivity response indicators and sensitive areas of the track system includes:

[0020] The input parameter sets of different foundation deformation characteristics, the tensile stress-strain relationship curves of the track structure material, the compressive stress-strain relationship curves of the track structure material, and the correspondence between damage factor and inelastic strain are input into the refined analysis model of the ballastless track-subfoundation. The spatiotemporal response of the track structure under foundation deformation is calculated and analyzed to obtain the spatiotemporal response data of the track structure under foundation deformation. The spatiotemporal response data of the track structure includes the displacement, stress, strain, structural damage range, structural damage degree, interlayer adhesion force, and interlayer debonding range response data of each structure in the track system.

[0021] The high-sensitivity response indicators and sensitive regions of the track system are determined. The high-sensitivity response indicators and sensitive regions include: high-sensitivity response indicators of large structural deformation, structural damage, material damage and interlayer debonding caused by the deformation of the foundation of the track system. The sensitive regions are the sensitive locations where the response indicators are generated.

[0022] Preferably, the method further includes:

[0023] The traction force-relative displacement relationship before damage occurs at the interlayer contact interface is calculated using the following formula:

[0024]

[0025] in, , , These are the traction forces in the normal direction, the first tangential direction, and the second tangential direction, respectively. , , These are the stiffness coefficients in the normal, first tangential, and second tangential directions, respectively. , , These are the relative displacements in the normal direction, the first tangential direction, and the second tangential direction, respectively.

[0026] The damage assessment criteria for crack initiation at the interlaminar contact interface are calculated using the second nominal stress criterion:

[0027]

[0028] in, Normal tensile strength; , represents the shear strength in the first and second tangential directions; <·> indicates that no damage will occur under pure compressive displacement or pure compressive stress conditions;

[0029] The degree of damage at the interlayer contact interface is quantitatively characterized by introducing a damage factor, which can be calculated using the following formula:

[0030]

[0031] in, This represents the effective relative displacement during the analysis process; The value range is 0-1; when When, it indicates that no damage has occurred at the interlayer interface; when When this occurs, it indicates that the interface is completely damaged and the layers are debonded.

[0032] The traction force-relative displacement relationship after damage to the interlaminar contact interface is calculated using the following formula:

[0033]

[0034]

[0035]

[0036] The criteria for determining the evolution of interlayer contact interface damage to complete debonding are calculated using fracture criteria:

[0037]

[0038] in, , , These represent the interfacial fracture toughness under different fracture modes.

[0039] Preferably, the step of constructing the correlation between the spatiotemporal responses of the track structure under different foundation deformation characteristics using a neural network model based on the spatiotemporal response data of the track structure under the foundation deformation includes:

[0040] A neural network model is constructed using a Long Short-Term Memory (LSTM) network algorithm. The spatiotemporal response data of the track structure under different foundation deformation characteristics are used as the model dataset. The model dataset is divided into a training set and a test set. The training set data is input into the neural network model, which outputs the spatiotemporal response data of each structure across the entire track segment. The test set is used to validate the output results of the neural network model. A loss function and optimizer are defined, and the neural network model is iteratively trained using a backpropagation algorithm to find the optimal parameters, thus obtaining the optimal neural network model. Based on this optimal neural network model, the correlation between the spatiotemporal responses of the track structure under different foundation deformation characteristics is output. This correlation includes the correlation between track structure displacement and stress under foundation deformation, and the correlation between track structure displacement and track damage.

[0041] Preferably, the monitoring point layout scheme for the track system in the high-sensitivity response index and sensitive area optimization foundation deformation section based on the track system includes:

[0042] Based on the high-sensitivity response indicators and sensitive areas of the track system, the layout of monitoring points for the track system in the foundation deformation section is determined, including determining the type, quantity, and location of sensors. Sensors are deployed and monitored at each response-sensitive location of the track system under the upper arch deformation, and the data measured by the sensors is transmitted in real time through data acquisition equipment.

[0043] Preferably, the step of realizing the comprehensive perception result of the service status of the entire track system across the foundation deformation section based on the correlation between the optimized track system monitoring point data and the spatiotemporal response of the track structure includes:

[0044] The real monitoring data of sensitive areas collected by sensors at the monitoring points of the optimized track system are input into the optimal neural network model. The optimal neural network model solves the response information of the entire track system based on the correlation between the spatiotemporal responses of the track structure, so as to realize the comprehensive perception of the track service status of the entire section of the foundation arch deformation. The comprehensive perception results include track structure damage and cracking, interlayer gaps, and track structure arching and delamination information.

[0045] As can be seen from the technical solutions provided by the embodiments of the present invention above, the embodiments of the present invention provide a method for optimizing the monitoring indicators of ballastless track in sections with foundation deformation based on the finite element method and neural network model. Based on the finite element method, the high-sensitivity response indicators and sensitive areas of the track structure under different foundation deformation conditions are solved, and the layout of monitoring points of the track system in the foundation deformation section is optimized. Based on the neural network model, the correlation between the spatiotemporal responses of the track structure is determined. Based on the correlation between the monitoring data and the spatiotemporal responses of the track structure under different foundation deformations, the response data of the entire track system is solved, realizing a comprehensive perception of the service status of the track system in the entire section with foundation deformation.

[0046] Additional aspects and advantages of the invention will be set forth in part in the description which follows, and will become apparent from the description or may be learned by practice of the invention. Attached Figure Description

[0047] To more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings used in the description of the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0048] Figure 1 A flowchart illustrating the processing of a comprehensive sensing method for the service status of ballastless track in a deformable section, provided as an embodiment of the present invention.

[0049] Figure 2 This invention provides a characteristic curve of upper arch deformation fitted based on monitoring data of upper arch deformation in tunnels.

[0050] Figure 3 This is a structural diagram of a refined analysis model of a two-block ballastless track-tunnel foundation provided in an embodiment of the present invention.

[0051] Figure 4 The diagram shows the relationship between tensile and compressive stress, inelastic strain, and damage factor, and inelastic strain of a two-block ballastless track material, as provided in an embodiment of the present invention.

[0052] Figure 5 This invention provides a bilinear cohesive force model for simulating the adhesion-deadhesion-contact interaction relationship between interlayer contact interfaces.

[0053] Figure 6 This invention provides a distribution map of displacement, structural damage, interlayer debonding response indices and their sensitive locations for a track system under tunnel arch deformation.

[0054] Figure 7This invention provides a neural network structure constructed using the Long Short Term Memory algorithm. Detailed Implementation

[0055] Embodiments of the present invention are described in detail below, examples of which are shown in the accompanying drawings, wherein the same or similar reference numerals denote the same or similar elements or elements having the same or similar functions throughout. The embodiments described below with reference to the accompanying drawings are exemplary and are only used to explain the present invention, and should not be construed as limiting the present invention.

[0056] Those skilled in the art will understand that, unless specifically stated otherwise, the singular forms “a,” “an,” “the,” and “the” used herein may also include the plural forms. It should be further understood that the term “comprising” as used in this specification means the presence of the stated features, integers, steps, operations, elements, and / or components, but does not exclude the presence or addition of one or more other features, integers, steps, operations, elements, components, and / or groups thereof. It should be understood that when we say an element is “connected” or “coupled” to another element, it can be directly connected or coupled to the other element, or there may be intermediate elements. Furthermore, “connected” or “coupled” as used herein can include wireless connections or couplings. The term “and / or” as used herein includes any and all combinations of one or more of the associated listed items.

[0057] It will be understood by those skilled in the art that, unless otherwise defined, all terms used herein (including technical and scientific terms) have the same meaning as commonly understood by one of ordinary skill in the art to which this invention pertains. It should also be understood that terms such as those defined in general dictionaries should be understood to have the same meaning as in the context of the prior art, and should not be interpreted in an idealized or overly formal sense unless defined as herein.

[0058] To facilitate understanding of the embodiments of the present invention, the following will provide further explanation and description with reference to the accompanying drawings and several specific embodiments. These embodiments do not constitute a limitation on the embodiments of the present invention.

[0059] The processing flowchart of a comprehensive sensing method for the service status of ballastless track in a foundation deformation section provided by an embodiment of the present invention is as follows: Figure 1 As shown, the processing steps include the following:

[0060] Step S10: Based on the foundation deformation monitoring data of the ballastless track of high-speed railway, clarify the deformation characteristics of the track substructure, determine the foundation deformation simulation parameters, and construct a set of input parameters for different foundation deformation characteristics.

[0061] Step S20: Based on the finite element method, and combined with parametric simulation of track foundation deformation characteristics and track structure design information, construct a refined analysis model of ballastless track-subfoundation that can consider the influence of different foundation deformations.

[0062] Step S30: Based on the refined analysis model of ballastless track-subfoundation, input parameter sets of different foundation deformation characteristics are input into the above refined analysis model of ballastless track-subfoundation. The spatiotemporal response of the track structure under foundation deformation is calculated and analyzed to obtain the spatiotemporal response data of the track structure under foundation deformation. The spatiotemporal response data of the track structure includes response data such as displacement, stress, strain, structural damage range, structural damage degree, interlayer bonding force and interlayer debonding range of each structure of the track system.

[0063] Furthermore, the highly sensitive response indicators and sensitive areas of the track system are identified. These highly sensitive response indicators and sensitive areas include indicators of significant structural deformation, structural damage, material damage, and interlayer debonding that are easily caused by foundation deformation. The spatial location corresponding to these significant response indicators is the sensitive area under that foundation deformation. For example, if the track structure undergoes significant deformation at a certain spatial location within the foundation deformation zone, that spatial location is called the deformation-sensitive area of ​​the track structure under that foundation deformation; the same applies to sensitive indicators and sensitive areas such as track stress and structural damage. Figure 6 This invention provides a distribution map of displacement, structural damage, interlayer debonding response indices and their sensitive locations for a track system under tunnel arch deformation.

[0064] Step S40: Based on the spatiotemporal response data of the track structure under different foundation deformations, use a neural network model to obtain the correlation between the spatiotemporal responses of the track structure under different foundation deformations.

[0065] Based on the spatiotemporal response data of the track structure under different foundation deformation characteristic input parameters obtained from the refined analysis model of ballastless track-subfoundation, the correlation between the spatiotemporal response data of the track structure under different foundation deformation characteristics is constructed using a neural network model.

[0066] The determined correlation is the correlation between different spatiotemporal response data of the track structure under the condition of basic deformation, such as the correlation between the spatial deformation data of each structure of the track in the deformation section and the spatiotemporal response data of each structure of the track under the spatial deformation, such as the stress, strain, degree of structural damage, and range of interlayer debonding.

[0067] The correlation between data 1 and data 2 is established based on a neural network model. Subsequently, based on this correlation, the spatiotemporal response of the track structure in the entire section of the foundation deformation can be directly derived from the track deformation monitoring data at the most unfavorable position (such as the spatiotemporal response of the deformation, stress, damage, and gap development of the track structure in the entire section of the foundation deformation). This allows for the perception of the service status of the track structure in the entire section of the foundation deformation.

[0068] Step S50: Based on the high-sensitivity response indicators and sensitive areas of the track system, optimize the layout of monitoring points of the track system in the foundation deformation section;

[0069] Step S60: Based on the correlation between the optimized track system monitoring point data and the spatiotemporal response of the track structure, a comprehensive perception result of the service status of the track system across the entire foundation deformation section is achieved. This comprehensive perception result mainly includes information on track structure damage and cracking, interlayer separation, track structure camber, and voids.

[0070] Specifically, step S10 includes:

[0071] Based on the deformation monitoring data of the ballastless track foundation of high-speed railway, the deformation characteristics of the track sub-foundation are clarified, the foundation deformation simulation parameters are determined, and the input parameter set for different foundation deformation characteristics is constructed.

[0072] The deformation characteristics of the track subbase include uneven settlement and frost heave deformation caused by the roadbed; uneven settlement and arching deformation caused by the tunnel; and flexural deformation, beam end rotation, and pier settlement deformation caused by the bridge.

[0073] The set of input parameters for the deformation characteristics of the track subbase includes: spatial deformation morphology characteristics of the subbase; spatial location of the track structure in the deformation section; wavelength, amplitude, and lateral non-uniformity coefficient of the base deformation.

[0074] In this embodiment, based on the longitudinal arch deformation monitoring data of the high-speed railway ballastless track tunnel foundation, the tunnel arch deformation monitoring data are fitted, such as... Figure 2 As shown; based on monitoring data and fitting results, the deformation characteristics of the upper arch of the high-speed railway tunnel are clarified, and the simulation parameters of the upper arch deformation of the tunnel foundation are determined. The fitting curve of the upper arch at the bottom of the tunnel and the characteristic parameters of the upper arch deformation are shown in the following formula:

[0075]

[0076] In the formula, This represents the amplitude of the arch deformation at the bottom of the tunnel. The wavelength of the tunnel arch deformation; These are the coordinates of the location of the tunnel arch area.

[0077] Specifically, step S20 includes:

[0078] This invention is based on the finite element method and combines parametric simulation of track foundation deformation characteristics and track structure design information to construct a refined analysis model of ballastless track-subfoundation that can consider the influence of different foundation deformations.

[0079] The structure of a refined analysis model for a dual-block ballastless track-tunnel foundation provided in this embodiment of the invention is as follows: Figure 3 As shown in Table 1, the parametric simulation of the track structure design information is presented.

[0080] Table 1. Parameters of Twin-Block Ballastless Track and Tunnel

[0081]

[0082] The aforementioned refined analysis model for the ballastless track-subfoundation includes: a nonlinear damage model considering the various materials of the track structure, and a cohesive force model simulating the bonding-debonding-contact interaction between interlayer contact interfaces. The nonlinear damage model enables the established refined analysis model for the ballastless track-subfoundation to more realistically simulate the damage process of the track structure under foundation deformation, thereby outputting accurate track damage response data. The cohesive force model simulates the damage evolution process of the interlayer interfaces in the refined analysis model for the ballastless track-subfoundation under foundation deformation, thus outputting accurate interlayer damage response data for the track structure.

[0083] The following relationships represent the damage properties of the material and need to be input into the finite element software when constructing the refined analysis model of the ballastless track-subbase.

[0084] The various relationship curves below are used to define the evolution mechanism of nonlinear damage and interlayer bonding state of various materials in the track structure. After constructing the refined analysis model of ballastless track-subfoundation, the following relationship curves need to be input into the refined analysis model of ballastless track-subfoundation so that the refined analysis model of ballastless track-subfoundation can output some damage response of track structure under foundation deformation conditions. Inputting the following relationship curves is to make the simulation calculation results of the model closer to the actual track damage under foundation deformation.

[0085] The input parameters for the nonlinear damage model of each material in the above track structure include: the correspondence between tensile and compressive stress and inelastic strain, and the relationship between damage factor and inelastic strain.

[0086] The tensile stress-inelastic strain and tensile stress-strain relationship curves together define the tensile failure property of the material, and are input into the refined analysis model of ballastless track-sub-foundation, so that the above analysis model can accurately output the tensile failure response data of the track structure under foundation deformation; the compressive stress-inelastic strain and compressive stress-strain relationship of the material are similarly used to define the compressive failure of the material.

[0087] The tensile and compressive stress-inelastic strain and damage factor-inelastic strain correspondence diagrams of a two-block ballastless track material provided in this embodiment of the invention are shown below. Figure 4 As shown.

[0088] Furthermore, the tensile stress-strain relationship curve of the track structure material is calculated using the following formula:

[0089]

[0090]

[0091]

[0092] This curve defines the tensile damage constitutive model of the track structure material.

[0093] The compressive stress-strain relationship curve of the track structure material is calculated using the following formula:

[0094]

[0095]

[0096]

[0097] This curve defines the constitutive model of the compressive damage of the track structure material.

[0098] The relationship between the damage factor and the inelastic strain is calculated using the following formula:

[0099]

[0100] in, , These are the parameter values ​​for the descending segment of the tensile and compressive stress-strain curves, respectively. , These are the representative values ​​of uniaxial tensile and compressive strength, respectively. , Peak tensile and compressive strain; , These are the uniaxial tensile and compressive damage factors, respectively. This corresponds to inelastic strain.

[0101] Furthermore, the traction force-relative displacement relationship before the interlayer contact interface damage occurs is calculated using the following formula:

[0102]

[0103] in, , , These are the traction forces in the normal direction, the first tangential direction, and the second tangential direction, respectively. , , These are the stiffness coefficients in the normal, first tangential, and second tangential directions, respectively. , , These are the relative displacements in the normal direction, the first tangential direction, and the second tangential direction, respectively.

[0104] The damage assessment criteria for crack initiation at the interlaminar contact interface are calculated using the second nominal stress criterion:

[0105]

[0106] in, Normal tensile strength; , represents the shear strength in the first and second tangential directions; <·> indicates that no damage will occur under pure compressive displacement or pure compressive stress conditions.

[0107] The degree of damage at the interlayer contact interface is quantitatively characterized by introducing a damage factor, which can be calculated using the following formula:

[0108]

[0109] in, This represents the effective relative displacement during the analysis process; The value range is 0-1; when When, it indicates that no damage has occurred at the interlayer interface; when When this occurs, it indicates that the interface is completely damaged and the layers are debonded.

[0110] The traction force-relative displacement relationship following damage to the interlayer contact interface is calculated using the following formula:

[0111]

[0112]

[0113]

[0114] The criteria for determining whether the interlayer contact interface damage has evolved to complete debonding are calculated using fracture criteria:

[0115]

[0116] in, , , These represent the interfacial fracture toughness under different fracture modes.

[0117] The cohesive force model used in this embodiment of the invention to simulate the adhesion-deadhesion-contact interaction relationship between interlayer contact interfaces is a bilinear cohesive force model. The structure of one such cohesive force model provided in this embodiment of the invention is as follows: Figure 5 As shown in Table 2, the parameters of the contact interface cohesion model are selected.

[0118] Table 2 Parameters of Cohesive Model at Contact Interface

[0119]

[0120] Specifically, step S40 includes: determining the correlation between the spatiotemporal responses of the track structure under different foundation deformations, including: constructing a neural network model using the LSTM (Long Short-Term Memory) algorithm, wherein the algorithm structure of Long Short-Term Memory is as follows: Figure 7 As shown.

[0121] The spatiotemporal response data of the track structure under different foundation deformation characteristics obtained in step S3 based on the refined analysis model of ballastless track-subfoundation are used as the model dataset. The model dataset is divided into a training set and a test set. The training set data is input into the aforementioned neural network model, and the neural network model outputs the spatiotemporal response data of each structure of the track structure under the full range of foundation deformation. The input variable of this neural network is the limited displacement response data of the track structure under foundation deformation, and the output variable is the spatiotemporal response data of the track structure stress, strain, structural damage degree, and interlayer debonding under the full range of foundation deformation.

[0122] The output of the neural network model is validated using a test set. A loss function and optimizer are defined. The neural network model is trained iteratively using the backpropagation algorithm to find the optimal parameters of the neural network model, improve the model performance, and solve the correlation between the spatiotemporal response of the track structure under different arch deformations.

[0123] Specifically, step S50 includes: optimizing the layout of monitoring points in the track system of the foundation deformation section, including: determining the sensor type, quantity, and sensor placement location; and transmitting the data measured by the sensors in real time through data acquisition equipment.

[0124] In this embodiment, sensors are deployed to monitor the sensitive locations of the track system under the deformation of the upper arch, and key detection is carried out on locations prone to track structure cracking and interlayer debonding; the test data is monitored, recorded and transmitted in real time through data acquisition equipment.

[0125] Specifically, step S60 includes: the comprehensive perception of the service status of the track system in the entire section of the foundation deformation includes: based on the limited data information obtained from sensor detection and monitoring, and according to the correlation between the spatiotemporal responses of the track structure under different foundation deformations, solving the response information of the entire track system in the foundation deformation section.

[0126] In this embodiment, based on the limited monitoring data transmitted by the data acquisition device, and combined with the correlation relationship of the spatiotemporal response of the track structure under different arch deformations obtained by the constructed LongShort Term Memory neural network model, the response information of the entire track system is solved, so as to achieve comprehensive perception of the track service status of the entire arch deformation section with limited monitoring data.

[0127] In summary, the optimization method and system for monitoring and detecting ballastless track in foundation deformation sections proposed in this invention address the problems of limited number and location of monitoring points in foundation deformation sections, which makes it difficult to comprehensively reflect the service status of the track structure, as well as the problems of overlapping measurement information and high testing costs caused by deploying a large number of sensors. This invention, based on the finite element method, solves for the high-sensitivity response indicators and sensitive areas of the track structure under different foundation deformation conditions, and optimizes the layout of monitoring points in the track system of foundation deformation sections. Based on a neural network model, the correlation between the spatiotemporal responses of the track structure is determined. Based on the limited monitoring data and the correlation between the spatiotemporal responses of the track structure under different foundation deformations, the response data of the entire track system in the foundation deformation section is solved, avoiding problems such as an excessive number or difficulty in determining the location of monitoring points in the track system of foundation deformation sections. It enables comprehensive perception of the service status of the entire track section in foundation deformation through optimized limited track monitoring data indicators.

[0128] Those skilled in the art will understand that the accompanying drawings are merely schematic diagrams of one embodiment, and the modules or processes shown in the drawings are not necessarily essential for implementing the present invention.

[0129] As can be seen from the above description of the embodiments, those skilled in the art can clearly understand that the present invention can be implemented by means of software plus necessary general-purpose hardware platforms. Based on this understanding, the technical solution of the present invention, or the part that contributes to the prior art, can be embodied in the form of a software product. This computer software product can be stored in a storage medium, such as ROM / RAM, magnetic disk, optical disk, etc., and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute the methods described in various embodiments or some parts of the embodiments of the present invention.

[0130] The various embodiments in this specification are described in a progressive manner. Similar or identical parts between embodiments can be referred to mutually. Each embodiment focuses on describing the differences from other embodiments. In particular, for apparatus or system embodiments, since they are basically similar to method embodiments, the description is relatively simple; relevant parts can be referred to the descriptions in the method embodiments. The apparatus and system embodiments described above are merely illustrative. The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the modules can be selected to achieve the purpose of this embodiment according to actual needs. Those skilled in the art can understand and implement this without creative effort.

[0131] The above description is merely a preferred embodiment of the present invention, but the scope of protection of the present invention is not limited thereto. Any variations or substitutions that can be easily conceived by those skilled in the art within the technical scope disclosed in the present invention should be included within the scope of protection of the present invention. Therefore, the scope of protection of the present invention should be determined by the scope of the claims.

Claims

1. A method for comprehensively sensing the service state of a foundation deformation section ballastless track, characterized in that, The application relates to a method for comprehensively sensing the service state of a high-speed railway ballastless track system. The method comprises the following steps: determining the track lower foundation deformation characteristics and the foundation deformation simulation parameters according to the foundation deformation monitoring data of the high-speed railway ballastless track, and constructing the input parameter set of different foundation deformation characteristics; Based on the finite element method, the parameterized simulation of the track foundation deformation characteristics and the track structure design information is combined to construct a fine analysis model of the ballastless track-lower foundation which can consider the influence of different foundation deformations; The input parameter set of different foundation deformation characteristics is input into the fine analysis model of the ballastless track-lower foundation, the time-space response of the track structure under the foundation deformation is calculated and analyzed, the time-space response data of the track structure under the foundation deformation is obtained, the high-sensitive response index and the sensitive area of the track system are determined; The neural network model is used to construct the correlation between the time-space responses of the track structure under different foundation deformation characteristics according to the time-space response data of the track structure under the foundation deformation; The monitoring point arrangement scheme of the track system in the foundation deformation section is optimized based on the high-sensitive response index and the sensitive area of the track system; According to the correlation between the optimized monitoring point data of the track system and the time-space response of the track structure, the comprehensive sensing result of the service state of the track system in the whole foundation deformation section is realized.

2. The method of claim 1, wherein, The method comprises the following steps: determining the track lower foundation deformation characteristics and the foundation deformation simulation parameters according to the foundation deformation monitoring data of the high-speed railway ballastless track, and constructing the input parameter set of different foundation deformation characteristics; The track lower foundation deformation characteristics include the uneven settlement of the subgrade, the frost heaving deformation, the uneven settlement of the tunnel, the hogging deformation, the deflection deformation of the bridge, the beam end rotation angle and the pier settlement deformation, The tunnel foundation hogging deformation simulation parameters are determined based on the monitoring data and the fitting result, the input parameter set of different foundation deformation characteristics is constructed, and the input parameter set of the track lower foundation deformation characteristics comprises the spatial deformation shape characteristics of the lower foundation, the spatial position of the track structure in the deformation section, the wavelength, the amplitude and the lateral uneven coefficient of the foundation deformation.

3. The method of claim 2, wherein, The method comprises the following steps: setting the parameterized simulation of the track structure design information including the corresponding size, the elastic modulus, the Poisson's ratio and the density of the rail, the sleeper, the track bed plate, the steel bar and the tunnel inverted arch, combining the parameterized simulation of the track foundation deformation characteristics and the track structure design information based on the finite element method, and constructing the fine analysis model of the ballastless track-lower foundation which can consider the influence of different foundation deformations, The fine analysis model of the ballastless track-lower foundation comprises the nonlinear damage model of each material of the track structure and the cohesion model for simulating the bonding-unbonding-contact interaction relationship between the interlayer contact interfaces, the cohesion model defines the damage development process of the interlayer bonding interface and simulates the bonding-unbonding-contact process of the interlayer contact interface.

4. The method of claim 3, wherein, The input parameter set of different foundation deformation characteristics is input into the ballastless track-underlying foundation refined analysis model, the time-space response of the track structure under foundation deformation is calculated and analyzed, the time-space response data of the track structure under foundation deformation is obtained, and the high-sensitive response index and sensitive area of the track system are determined, including: The input parameter set of different foundation deformation characteristics, the tensile stress-strain relationship curve of the track structure material, the compressive stress-strain relationship curve of the track structure material and the corresponding relationship between the damage factor and the inelastic strain are input into the ballastless track-underlying foundation refined analysis model, the time-space response of the track structure under foundation deformation is calculated and analyzed, the time-space response data of the track structure under foundation deformation is obtained, and the time-space response data of the track structure under foundation deformation includes the displacement, stress, strain, structure damage range, structure damage degree, interlayer bonding force and interlayer debonding range response data of the track system. The high-sensitive response index and sensitive area of the track system are determined, including the high-sensitive response index of structural large deformation, structural damage, material damage and interlayer debonding of the track system caused by foundation deformation, and the sensitive area is the sensitive position corresponding to the response index.

5. The method of claim 4, wherein, The method further includes: The traction force-relative displacement relationship before the damage of the interlayer contact interface is calculated by the following formula: where t n , t s , t t are the normal, first tangential and second tangential tractions, respectively; k n , k s , k t are the normal, first tangential and second tangential stiffness coefficients, respectively; δ n , δ s , δ t are the normal, first tangential and second tangential relative displacements, respectively. The damage judgment condition of the interlayer contact interface crack initiation is calculated by using the secondary nominal stress criterion: wherein is the normal tensile strength; is the shear strength in the first and second tangential directions; and <·> indicates that no damage occurs under a pure compressive displacement or pure compressive stress state; The damage degree of the interlayer contact interface is quantitatively characterized by introducing a damage factor, and the damage factor can be calculated by the following formula: wherein, D is the effective relative displacement during the analysis; the value range of D is 0-1; when D=0, it indicates that the interlayer interface has not been damaged; when D=1, it indicates that the interface is completely damaged and the interlayer debonding occurs. The traction force-relative displacement relationship after the damage of the interlayer contact interface is calculated by the following formula: t s = (1 - D)k s δ s t t = (1 - D)k t δ t The debonding judgment condition of the interlayer contact interface damage evolution is calculated by using the fracture criterion: wherein, Gc, Gc are the interfacial fracture toughnesses for different fracture modes, respectively.

6. The method according to claim 4 or 5, characterized in that, The neural network model is constructed by using the long short-term memory network algorithm, the track structure time-space response data under different foundation deformation characteristics are used as the model data set, the model data set is divided into a training set and a test set, the training set data is input into the neural network model, the neural network model outputs the time-space response data of each structure of the track structure in the whole section, the output results of the neural network model are verified by using the test set, the loss function and the optimizer are defined, the neural network model is iteratively trained by using the back propagation algorithm, the best parameters of the neural network model are solved, the optimal neural network model is obtained, and the correlation between the track structure time-space responses under different foundation deformation characteristics is output based on the optimal neural network model, and the correlation between the track structure time-space responses includes the correlation between the track structure displacement and stress under foundation deformation, and the correlation between the track structure displacement and track damage. The high-sensitive response index and sensitive area of the track system are used to optimize the monitoring point arrangement scheme of the foundation deformation section track system, including:

7. The method of claim 5, wherein, ​ The monitoring point arrangement of the track system of the basic deformation section based on the high sensitivity response index and the sensitive area determination comprises determining the sensor type, the number and the sensor layout position, and the sensor layout monitoring is performed on each response sensitive position of the track system under the upwarping deformation. The sensor measured data information is transmitted in real time through the data acquisition equipment.

8. The method of claim 7, wherein, The comprehensive perception result of the service state of the track system of the basic deformation section is realized according to the correlation between the monitoring point data of the optimized track system and the track structure space-time response, and the comprehensive perception result comprises: The real monitoring data of the sensitive area collected by the uploaded sensor of the optimized track system is input into the optimal neural network model. The optimal neural network model solves the track system response information according to the correlation between the track structure space-time response, and realizes the comprehensive perception of the service state of the track of the basic upwarping deformation section. The comprehensive perception result comprises the track structure damage cracking, the interlayer separation, the track structure upwarping and the void disease information.

Images