Identification method of ballastless track subgrade mud failure based on GPR technology

Abstract

The present invention discloses a method for identifying mud-overflowing disease of ballastless track subgrade based on GPR technology, including: carrying out GPR detection and sampling at different mud-overflowing degree positions of ballastless track subgrade, obtaining radar waveform of subgrade surface layer and original soil sample, measuring dry density, relative density and moisture content, and calculating saturated moisture content and moisture content increment accordingly. According to the increment, a subgrade sample with the same dry density as the original sample but different moisture content is prepared, a radar detection test model and a simulation model containing concrete components, subgrade samples and steel plates are constructed, the actual radar waveform is obtained, and the fitting is performed in combination with the moisture content, so as to construct a moisture content radar waveform data set, and a moisture content discrimination network is trained with radar waveform as input and moisture content as output, and then the surface layer of the ballastless track subgrade to be inspected is detected with a ground-coupled radar antenna, and the radar waveform test data set is obtained and input into the network, and the moisture content of the subgrade surface layer and the position of moisture content change are obtained to determine the mud-overflowing disease state of the subgrade.

Description

Technical Field

[0001] The invention relates to the technical field of geotechnical engineering, and in particular to a method for identifying mud slurry damage in a ballastless track subgrade based on a GPR technology. Background Art

[0002] The phenomenon of mud swell is a common subgrade disease in high-speed railway lines, especially in ballastless track systems, which has become a key factor affecting the long-term stability and safety of railways. As a new type of track structure, the structural form, subgrade structure and stress transfer mechanism of ballastless track are significantly different from those of traditional ballasted track. Under the action of train load, the deformation and stability of the subgrade filling material of ballastless track directly affect the safety and stability of the track structure. Mud swell is usually caused by factors such as rainwater infiltration, subgrade erosion and loss of fine particles inside the subgrade during long-term operation, resulting in the formation of local gaps between the base plate of the track structure and the surface layer of the subgrade, which in turn weakens the supporting stiffness of the subgrade, significantly reduces the stability and strength of the track, and may even threaten the safety of train operation in severe cases. Although ballastless track has good integrity and strong stability, due to the lack of adaptive function of ballast, once mud swell occurs, the difficulty of treatment and the cost of repair are often high.

[0003] At present, the research on the mud-overflow disease of ballastless track subgrade mainly focuses on the exploration of the causes, mechanisms and treatment methods of the disease, but there are still great challenges in the early identification and diagnosis of this roadbed disease. Traditional identification methods mainly rely on manual inspections and empirical judgments. However, mud-overflow is usually a highly concealed disease. When the patrol workers discover the disease, a large amount of mud has accumulated inside the subgrade, which has begun to affect the comfort and safety of driving. The workload of manual inspection is large and the recognition error is high. Therefore, the disease identification method based on the measured data of the track inspection vehicle has gradually been applied. Although it has improved the recognition efficiency and accuracy to a certain extent, the identification ability of the subgrade mud-overflow disease is still limited due to the low departure frequency of the track inspection vehicle and its other disease inspection tasks. With the increase in the operating speed of high-speed railways and the increase in passenger demand, the dynamic response of the track caused by the mud-overflow disease has increased, and the impact on train safety has become increasingly severe. Therefore, it is particularly urgent to explore a more efficient and accurate method for identifying the mud-overflow disease of the subgrade.

[0004] Therefore, there is an urgent need to provide a method for identifying ballastless track subgrade slurry damage to improve the accuracy and efficiency of ballastless track subgrade slurry damage identification. Summary of the invention

[0005] In view of the shortcomings of the prior art, the present invention provides a method and device for identifying mud overflow defects in ballastless track subgrade based on bottom penetrating radar.

[0006] In a first aspect, an embodiment of the present invention provides a method for identifying mud slurry damage in a ballastless track subgrade based on GPR technology, the method comprising:

[0007] GPR detection and sampling operations are carried out at the non-slurrying position, critical slurrying position, first-level slurrying position, ..., and N-level slurrying position of the ballastless track subgrade to obtain radar waveforms and undisturbed soil samples of the subgrade surface;

[0008] Obtain the dry density and relative density corresponding to the subgrade surface layer, and the moisture content of each original soil sample; calculate the saturated moisture content and moisture content increment of the subgrade surface layer based on the dry density and relative density;

[0009] According to the increment of moisture content, several bed samples with the same dry density as the original soil sample but different moisture content are configured;

[0010] A radar detection test model and a three-dimensional finite element analysis model consisting of concrete components, bed samples, and steel plates arranged from top to bottom were constructed; the radar detection test model was detected using a ground-coupled radar antenna to obtain the actual radar waveform data corresponding to each bed sample; a three-dimensional finite element analysis model was fitted based on the moisture content corresponding to each bed sample; a moisture content-radar waveform data set was constructed based on the fitted three-dimensional finite element analysis model;

[0011] Using radar waveform data as input and water content as output, the water content discrimination network is trained;

[0012] A ground-coupled radar antenna is used to detect the surface of the ballastless track subgrade to be tested, and a radar waveform test data set is obtained; the radar waveform test data set is input into a trained moisture content discrimination network to obtain the moisture content of the current ballastless track subgrade surface and the location of the moisture content change;

[0013] The state of the ballastless track subgrade slurry damage is determined based on the current moisture content of the ballastless track subgrade surface and the location of the moisture content change.

[0014] In a second aspect, an embodiment of the present invention provides a ballastless track subgrade slurry disease identification system based on GPR technology, which is used to implement the above-mentioned ballastless track subgrade slurry disease identification method based on GPR technology, and the system includes:

[0015] The original soil sample acquisition module performs GPR detection and sampling operations at the un-slurrying position, critical slurrying position, first-level slurrying position, ..., and Nth-level slurrying position of the ballastless track subgrade to obtain radar waveforms and original soil samples of the subgrade surface; obtain the dry density and relative density corresponding to the subgrade surface, and the moisture content of each original soil sample; calculate the saturated moisture content and moisture content increment of the subgrade surface based on the dry density and relative density;

[0016] The base bed sample configuration module configures a number of base bed samples with the same dry density as the original soil sample but different moisture content according to the moisture content increment;

[0017] The moisture content-radar waveform data set construction module constructs a radar detection test model and a three-dimensional finite element analysis model arranged from top to bottom by concrete components, bed samples, and steel plates; uses a ground-coupled radar antenna to detect the radar detection test model to obtain the actual radar waveform data corresponding to each bed sample; fits the three-dimensional finite element analysis model based on the moisture content corresponding to each bed sample; and constructs the moisture content-radar waveform data set based on the fitted three-dimensional finite element analysis model;

[0018] The moisture content discrimination network training module takes radar waveform data as input and moisture content as output to train the moisture content discrimination network;

[0019] The ballastless track subgrade slurry overflow disease identification module uses a ground-coupled radar antenna to detect the surface of the ballastless track subgrade to be detected and obtain a radar waveform test data set; the radar waveform test data set is input into the trained moisture content discrimination network to obtain the current moisture content of the ballastless track subgrade surface and the location of the moisture content change; the status of the ballastless track subgrade slurry overflow disease is determined based on the current moisture content of the ballastless track subgrade surface and the location of the moisture content change.

[0020] In a third aspect, an embodiment of the present invention provides an electronic device, comprising a memory and a processor, wherein the memory is coupled to the processor; wherein the memory is used to store program data, and the processor is used to execute the program data to implement the above-mentioned method for identifying slurry damage in ballastless track subgrade based on GPR technology.

[0021] In a fourth aspect, an embodiment of the present invention provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the above-mentioned method for identifying slurry overflow defects in ballastless track subgrade based on GPR technology.

[0022] In a fifth aspect, an embodiment of the present invention provides a computer program product, including a computer program / instruction, which, when executed by a processor, implements the above-mentioned method for identifying slurry overflow defects in ballastless track subgrade based on GPR technology.

[0023] Compared with the prior art, the present invention has the following beneficial effects:

[0024] The present invention provides a method for identifying mud-overflowing diseases of ballastless track subgrade based on GPR technology. GPR detection and sampling are carried out at different mud-overflowing degree positions of ballastless track subgrade, and radar waveforms and original soil samples of the subgrade surface are obtained. The dry density, relative density and moisture content are measured, and the saturated moisture content and moisture content increment are calculated accordingly. According to the increment, a subgrade sample with the same dry density as the original sample but different moisture content is prepared, and a radar detection test model and a simulation model containing concrete components, subgrade samples and steel plates are constructed. The actual radar waveform is obtained and fitted in combination with the moisture content to construct a moisture content-radar waveform data set, and a moisture content discrimination network is trained with the radar waveform as input and the moisture content as output. Then, a ground-coupled radar antenna is used to detect the surface of the ballastless track subgrade to be inspected, and the radar waveform test data set is obtained and input into the network to obtain the moisture content of the subgrade surface and the moisture content change position, which is compared with the moisture content of the original soil sample to determine the mud-overflowing disease state of the subgrade; thereby improving the accuracy and efficiency of mud-overflowing disease identification of ballastless track subgrade. BRIEF DESCRIPTION OF THE DRAWINGS

[0025] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the accompanying drawings required for use in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings in the following description are only some embodiments of the present invention. For ordinary technicians in this field, other accompanying drawings can be obtained based on these accompanying drawings without paying creative labor.

[0026] Figure 1 A schematic flow chart of a method for identifying mud slurry damage in ballastless track subgrade based on GPR technology provided in an embodiment of the present invention;

[0027] Figure 2 A schematic diagram of the ballastless track subgrade structure and sampling hole distribution provided in an embodiment of the present invention;

[0028] Figure 3 A schematic diagram of a radar detection test model provided by an embodiment of the present invention;

[0029] Figure 4 A schematic diagram of a simulation of a three-dimensional finite element analysis model corresponding to the radar detection test model provided in an embodiment of the present invention;

[0030] Figure 5 A schematic diagram of an on-site detection process of slurry overflow disease in a ballastless track subgrade provided by an embodiment of the present invention;

[0031] Figure 6 A schematic diagram of an electronic device provided by an embodiment of the present invention.

[0032] In the figure: rail and fastener system 1, track plate 2, CA mortar layer 3, base plate 4, sampling holes 5, subgrade surface layer 6, subgrade bottom layer 7, ground penetrating radar 8, concrete component 9, subgrade sample 10, test steel plate 11, ground penetrating radar detection direction 12. DETAILED DESCRIPTION

[0033] Exemplary embodiments will be described in detail herein, examples of which are shown in the accompanying drawings. When the following description refers to the drawings, the same numbers in different drawings represent the same or similar elements unless otherwise indicated. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with the present invention. Instead, they are merely examples of devices and methods consistent with some aspects of the present invention as detailed in the appended claims.

[0034] The terms used in the present invention are only for the purpose of describing specific embodiments and are not intended to limit the present invention. The singular forms "a", "the" and "the" used in the present invention and the appended claims are also intended to include plural forms unless the context clearly indicates other meanings. It should also be understood that the term "and / or" used herein refers to and includes any or all possible combinations of one or more associated listed items.

[0035] It should be understood that although the terms first, second, third, etc. may be used in the present invention to describe various information, these information should not be limited to these terms. These terms are only used to distinguish the same type of information from each other. For example, without departing from the scope of the present invention, the first information may also be referred to as the second information, and similarly, the second information may also be referred to as the first information. Depending on the context, the word "if" as used herein may be interpreted as "at the time of" or "when" or "in response to determining".

[0036] The present invention is described in detail below in conjunction with the accompanying drawings. In the absence of conflict, the features of the following embodiments and implementations can be combined with each other.

[0037] like Figure 2As shown in the figure, the components of the high-speed railway ballastless track from top to bottom are: rail and fastener system 1, track plate 2, CA mortar layer 3, base plate 4, subgrade surface layer 6 and subgrade bottom layer 7. As a new type of track structure, the structural form, subgrade structure and stress transfer mechanism of ballastless track are significantly different from those of traditional ballasted track. Under the action of train load, the deformation and stability of the subgrade filling material (subgrade surface layer 6 and subgrade bottom layer 7) of the ballastless track directly affect the safety and stability of the track structure. During the long-term operation of the ballastless track line, the subgrade slurry disease is induced by factors such as rainwater penetration, subgrade erosion and loss of fine particles inside the subgrade, resulting in the formation of local gaps between the track structure base plate 4 and the subgrade surface layer 6, which in turn weakens the supporting stiffness of the subgrade, significantly reduces the stability and strength of the track, and seriously endangers the operation safety of the train.

[0038] like Figure 1 As shown, an embodiment of the present invention provides a method for identifying mud overflow defects in ballastless track subgrade based on GPR technology, the method comprising:

[0039] Step S1, performing GPR detection and sampling operations at the non-slurry-over position, critical slurry-over position, first-stage slurry-over position, ..., Nth-stage slurry-over position of the ballastless track subgrade to obtain radar waveforms and undisturbed soil samples of the subgrade surface.

[0040] Exemplarily, in this example, when the track plane distortion value is less than 6 mm, the corresponding position is defined as the first-level mud-overturning position; when the track plane distortion value is 6 mm~8 mm, the corresponding position is defined as the second-level mud-overturning position; when the track plane distortion value is greater than 8 mm, the corresponding position is defined as the third-level mud-overturning position.

[0041] Furthermore, during the sampling operation, sampling operations are carried out at the non-slurry position, the critical slurry position, the first slurry position, ..., the Nth slurry position respectively. In this example, N is 4, the sampling depth is 40 cm below the bottom surface of the base plate, the sampling method is hammer sampling, and a separate sampling tube is used. The inner diameter of the sampling tube is not less than 92 mm, and the length of the sampling tube is the sum of the thickness of the base plate and the base bed surface.

[0042] Step S2, obtaining the dry density and relative density corresponding to the subgrade surface layer, and the moisture content of each original soil sample; and calculating the saturated moisture content and moisture content increment of the subgrade surface layer based on the dry density and relative density.

[0043] Furthermore, in this example, the water content w corresponding to the original soil sample at the position where the mud is not turned over is measured. a , the moisture content w corresponding to the original soil sample at the critical mud-overturning position 0 , the moisture content w corresponding to the original soil sample at the first level of mud stirring 1, ..., the moisture content w corresponding to the original soil sample at the Nth level of mud-turning position N , dry density ρ d And relative density G s .

[0044] Furthermore, the moisture content w corresponding to the original soil sample at the un-stirred position is a As the initial moisture content of the subgrade surface, the saturated moisture content w of the subgrade surface in the saturated state is calculated. sr , the expression is as follows:

[0045]

[0046] In the formula, ρ d Indicates the dry density of the surface layer of the base bed, G s Indicates the relative density corresponding to the surface layer of the base bed.

[0047] The expression of moisture content increment is as follows:

[0048]

[0049] Where n represents the saturated moisture content w sr and initial moisture content w a The difference Δw between them is divided equally into the number of parts.

[0050] Step S3, configuring a number of bed samples having the same dry density as the original soil sample but different moisture contents according to the moisture content increment.

[0051] Furthermore, the different moisture contents of the base bed samples are respectively the moisture content w corresponding to the first base bed sample 11 = w a +η w , the moisture content w corresponding to the second bedding sample 22 = w a + 2η w , ..., the moisture content w corresponding to the Nth bedding sample NN = w a +nη w = w sr ; Among them, w a is the initial moisture content of the subgrade surface, w sr is the saturated moisture content, η w is the moisture content increment, n represents the saturated moisture content w sr and initial moisture content w a The difference Δw between them is divided equally into the number of parts.

[0052] Furthermore, the process of configuring a plurality of bed samples having the same dry density as the original soil sample but different moisture contents according to the moisture content increment includes:

[0053] All the original soil samples on the surface of the base bed were air-dried and the moisture content w of the air-dried soil samples was measured. fg ;

[0054] The moisture content is w 11 The first bedding sample: weigh the mass m 11 = ρ d ·V·(1 + w fg ) of air-dried soil sample and add a mass of Δm 1 = ρ d ·V·(w 1 -w fg ) of water, V is the volume of the first base bed sample, and the base bed sample is filled to the same height as the base bed surface; in this example, V = 0.4 m×0.4 m×0.4 m, and the layered compaction method is used to fill the base bed sample into a cube with a side length of 0.4 m.

[0055] By analogy, the moisture content is w 22 The second bedding sample, ..., has a water content of w NN The Nth base bed sample.

[0056] Step S4, constructing a radar detection test model and a three-dimensional finite element analysis model arranged from top to bottom by concrete components, bed samples, and steel plates; using a ground-coupled radar antenna to detect the radar detection test model to obtain actual radar waveform data corresponding to each bed sample; fitting the three-dimensional finite element analysis model in combination with the moisture content corresponding to each bed sample; and constructing a moisture content-radar waveform data set based on the fitted three-dimensional finite element analysis model.

[0057] Furthermore, if Figure 3 As shown in the figure, the height of the concrete component is the same as the height of the base plate in the ballastless track; in this example, the size of the concrete component is set to 0.3 m×0.3 m×0.3 m, and it is placed at the center of the subgrade sample on the subgrade surface. The size of the steel plate is set to 0.6 m×0.6 m×0.05 m, which is used to reflect the electromagnetic signal of the ground penetrating radar.

[0058] Furthermore, a Chirp signal is selected as an excitation signal in a three-dimensional finite element analysis model corresponding to the radar detection test model to simulate a ground-coupled radar antenna; specifically, the method includes:

[0059] The Chirp signal expression is:

[0060]

[0061] Where V(t) is the excitation signal (electromagnetic wave) that changes with time in the time domain; A is the signal amplitude, and f 0is the initial frequency of the electromagnetic wave, B is the rate of change of frequency, and t is the duration of the signal; V(t) describes the change of the signal over time, which is a sine wave with frequency modulation. 0 The recommended range of is 100 MHz ~ 150 MHz; the recommended range of frequency change rate B is 1.0·E+07 Hz / s ~ 1.0·E+08 Hz / s; the recommended range of signal duration t is 20 μs ~ 50 μs, based on which the electromagnetic wave signal is simulated.

[0062] Furthermore, if Figure 4 As shown in the figure, the boundary of the three-dimensional finite element analysis model adopts a general absorbing boundary, which can absorb the energy of the incident wave and reflect it as wall energy; the key material parameters in the three-dimensional finite element analysis model, such as the dielectric constant (ε r ), conductivity (σ r ) and magnetic permeability (μ r ) can be measured in the laboratory by dielectric constant meter, conductivity meter and other equipment. Since the base plate concrete and the subgrade surface subgrade samples are not magnetic, their magnetic permeability μ r = 1.0; It should be pointed out that the other parameters of the above materials are related to the moisture content and can be determined through indoor tests.

[0063] Furthermore, in this example, the water content is calculated by the three-dimensional finite element analysis model as w 11 The first bedding sample has a water content of w 22 The second bedding sample, ..., has a water content of w NN The simulated radar waveform data corresponding to the Nth bedding sample is compared and analyzed with the actual radar waveform data corresponding to each bedding sample, so as to fit the three-dimensional finite element analysis model to ensure the correctness and effectiveness of the three-dimensional finite element analysis model.

[0064] Furthermore, the process of constructing the water content-radar waveform data set based on the fitted three-dimensional finite element analysis model includes: setting the water content value range to 0.6w 0 ≤ w ≤ w sr , the corresponding radar waveform data is obtained based on the moisture content value range through the fitted three-dimensional finite element analysis model, thereby constructing a moisture content-radar waveform data set.

[0065] Step S5, based on the moisture content-radar waveform data set, with the radar waveform data as input and the moisture content as output, a moisture content discrimination network is trained.

[0066] Specifically, in this example, radar waveform data is used as input and moisture content is used as output to train the moisture content discrimination network. The K-fold cross-validation method is used to determine the optimal hyperparameters of the moisture content discrimination network, and the hidden layer weights and biases of the moisture content discrimination network are obtained.

[0067] Step S6, using a ground-coupled radar antenna to detect the subgrade surface layer at the bottom of the base plate on both sides of the ballastless track line to be detected, and obtaining a radar waveform test data set; inputting the radar waveform test data set into the trained moisture content discrimination network to obtain the moisture content of the subgrade surface layer at different positions along the longitudinal direction of the current ballastless track and the position where the moisture content changes ( Figure 5 ).

[0068] Step S7, determining the state of the slurry overflow disease of the ballastless track subgrade according to the current moisture content of the surface layer of the ballastless track subgrade and the position of the moisture content change.

[0069] Furthermore, this example can classify the state of the ballastless track subgrade mud frothing disease according to the determined state of the subgrade mud frothing disease, mark the location of the subgrade mud frothing disease, and propose corresponding prevention and treatment plans for different levels of subgrade mud frothing to avoid further deterioration of the subgrade mud frothing disease.

[0070] On the other hand, the embodiment of the present invention further provides a ballastless track subgrade slurry disease identification system based on GPR technology, which is used to implement the above-mentioned ballastless track subgrade slurry disease identification method based on GPR technology, and the system includes:

[0071] The original soil sample acquisition module performs GPR detection and sampling operations at the un-slurrying position, critical slurrying position, first-level slurrying position, ..., and Nth-level slurrying position of the ballastless track subgrade to obtain radar waveforms and original soil samples of the subgrade surface; obtain the dry density and relative density corresponding to the subgrade surface, and the moisture content of each original soil sample; calculate the saturated moisture content and moisture content increment of the subgrade surface based on the dry density and relative density;

[0072] The base bed sample configuration module configures a number of base bed samples with the same dry density as the original soil sample but different moisture content according to the moisture content increment;

[0073] The moisture content-radar waveform data set construction module constructs a radar detection test model and a three-dimensional finite element analysis model arranged from top to bottom by concrete components, bed samples, and steel plates; uses a ground-coupled radar antenna to detect the radar detection test model to obtain the actual radar waveform data corresponding to each bed sample; fits the three-dimensional finite element analysis model based on the moisture content corresponding to each bed sample; and constructs the moisture content-radar waveform data set based on the fitted three-dimensional finite element analysis model;

[0074] The moisture content discrimination network training module takes radar waveform data as input and moisture content as output to train the moisture content discrimination network;

[0075] The ballastless track subgrade slurry overflow disease identification module uses a ground-coupled radar antenna to detect the surface of the ballastless track subgrade to be detected and obtain a radar waveform test data set; the radar waveform test data set is input into a trained moisture content discrimination network to obtain the current moisture content of the ballastless track subgrade surface and the location of the moisture content change; the grade of the ballastless track subgrade slurry overflow disease is determined based on the current moisture content of the ballastless track subgrade surface and the location of the moisture content change.

[0076] In summary, the present invention generates a database by combining on-site disease radar detection, indoor calibration tests, numerical analysis and machine learning technology, conducts in-depth analysis of the screened and cleaned data, and establishes a strong correlation between the subgrade slurry disease and the ground penetrating radar signal. It can more accurately identify the development trend of the subgrade slurry, thereby improving the accuracy and efficiency of track maintenance and ensuring the safe and stable operation of the railway.

[0077] According to an embodiment of the present invention, the present invention also provides an electronic device and a readable storage medium.

[0078] Figure 6 A schematic block diagram of an electronic device that can be used to implement an embodiment of the present invention is shown. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device can also represent various forms of mobile devices, such as personal digital processing, cellular phones, smart phones, wearable devices, and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely examples and are not intended to limit the implementation of the present invention described and / or required herein.

[0079] The electronic device includes a computing unit 101, which can perform various appropriate actions and processes according to a computer program stored in a ROM 102 or a computer program loaded from a storage unit 108 into a RAM 103. In the RAM 103, various programs and data required for the operation of the electronic device can also be stored. The computing unit 101, the ROM 102, and the RAM 103 are connected to each other via a bus 104. An I / O interface 105 is also connected to the bus 104.

[0080] A number of components in the electronic device are connected to the I / O interface 105, including: an input unit 106, such as a keyboard, a mouse, etc.; an output unit 107, such as various types of displays, speakers, etc.; a storage unit 108, such as a disk, an optical disk, etc.; and a communication unit 109, such as a network card, a modem, a wireless communication transceiver, etc. The communication unit 109 allows the electronic device to exchange information / data with other devices through a computer network such as the Internet and / or various telecommunication networks.

[0081] The computing unit 101 may be a variety of general and / or special processing components with processing and computing capabilities. Some examples of the computing unit 101 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various dedicated artificial intelligence (AI) computing chips, various computing units running machine learning model algorithms, digital signal processors (DSPs), and any appropriate processors, controllers, microcontrollers, etc. The computing unit 101 performs the various methods and processes described above. For example, in some embodiments, the method in the multidimensional early warning system for pressure injuries may be implemented as a computer software program, which is tangibly contained in a machine-readable medium, such as a storage unit 108. In some embodiments, part or all of the computer program may be loaded and / or installed on an electronic device via ROM 102 and / or a communication unit 109. When the computer program is loaded into RAM 103 and executed by the computing unit 101, one or more steps of the method in the multidimensional early warning system for pressure injuries described above may be executed. Alternatively, in other embodiments, the computing unit 101 may be configured to execute the method in the multidimensional early warning system for pressure injuries in any other appropriate manner (e.g., by means of firmware).

[0082] Various implementations of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), systems on chips (SOCs), load programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various implementations may include: being implemented in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which can be a special purpose or general purpose programmable processor that can receive data and instructions from a storage system, at least one input device, and at least one output device, and transmit data and instructions to the storage system, the at least one input device, and the at least one output device.

[0083] The program code for implementing the method of the present invention can be written in any combination of one or more programming languages. These program codes can be provided to a processor or controller of a general-purpose computer, a special-purpose computer or other programmable data processing device, so that the program code, when executed by the processor or controller, enables the functions / operations specified in the flow chart and / or block diagram to be implemented. The program code can be executed entirely on the machine, partially on the machine, partially on the machine as a stand-alone software package and partially on a remote machine, or entirely on a remote machine or server.

[0084] In the context of the present invention, a readable storage medium may be a tangible medium that may contain or store a program for use by or in conjunction with an instruction execution system, device, or apparatus. A readable storage medium may be a machine-readable signal medium or a machine-readable storage medium. A readable storage medium may include, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, device, or device, or any suitable combination of the foregoing. More specific examples of readable storage media may include an electrical connection based on one or more lines, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

[0085] To provide interaction with a user, the systems and techniques described herein can be implemented on a computer having: a display device for displaying information to the user; and a keyboard and a pointing device (e.g., a mouse or trackball) through which the user can provide input to the computer. Other types of devices can also be used to provide interaction with the user; for example, the feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including acoustic input, voice input, or tactile input).

[0086] The systems and techniques described herein may be implemented in a computing system that includes back-end components (e.g., as a data server), or a computing system that includes middleware components (e.g., an application server), or a computing system that includes front-end components (e.g., a user computer with a graphical user interface or a web browser through which a user can interact with implementations of the systems and techniques described herein), or a computing system that includes any combination of such back-end components, middleware components, or front-end components. The components of the system may be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include: a local area network (LAN), a wide area network (WAN), and the Internet.

[0087] A computer system may include a client and a server. The client and the server are generally remote from each other and usually interact through a communication network. The relationship of client and server is generated by computer programs running on respective computers and having a client-server relationship with each other. The server may be a cloud server, a server of a distributed system, or a server combined with a blockchain.

[0088] The above embodiments are only used to illustrate the design ideas and features of the present invention, and their purpose is to enable those skilled in the art to understand the content of the present invention and implement it accordingly. The protection scope of the present invention is not limited to the above embodiments. Therefore, any equivalent changes or modifications made based on the principles and design ideas disclosed by the present invention are within the protection scope of the present invention.

Claims

1. A method for identifying mud slurry damage in ballastless track subgrade based on GPR technology, characterized in that: The method comprises: GPR detection and sampling operations are carried out at the non-slurrying position, critical slurrying position, first-level slurrying position, ..., and N-level slurrying position of the ballastless track subgrade to obtain radar waveforms and undisturbed soil samples of the subgrade surface; Obtain the dry density and relative density corresponding to the subgrade surface layer, and the moisture content of each original soil sample; calculate the saturated moisture content and moisture content increment of the subgrade surface layer based on the dry density and relative density; According to the increment of moisture content, several bed samples with the same dry density as the original soil sample but different moisture content are configured; A radar detection test model and a three-dimensional finite element analysis model consisting of concrete components, bed samples, and steel plates arranged from top to bottom were constructed; the radar detection test model was detected using a ground-coupled radar antenna to obtain the actual radar waveform data corresponding to each bed sample; a three-dimensional finite element analysis model was fitted based on the moisture content corresponding to each bed sample; a moisture content-radar waveform data set was constructed based on the fitted three-dimensional finite element analysis model; Using radar waveform data as input and water content as output, the water content discrimination network is trained; A ground-coupled radar antenna is used to detect the surface of the ballastless track subgrade to be tested, and a radar waveform test data set is obtained; the radar waveform test data set is input into a trained moisture content discrimination network to obtain the moisture content of the current ballastless track subgrade surface and the location of the moisture content change; The state of the ballastless track subgrade slurry damage is determined based on the current moisture content of the ballastless track subgrade surface and the location of the moisture content change.

2. The method for identifying mud slurry damage in ballastless track subgrade based on GPR technology according to claim 1 is characterized in that: The process of calculating the saturated moisture content and moisture content increment of the subgrade surface layer based on the dry density and relative density includes: The moisture content w corresponding to the original soil sample at the un-slurryed position a As the initial moisture content of the subgrade surface, the saturated moisture content w of the subgrade surface in the saturated state is calculated. sr , the expression is as follows: ； In the formula, ρ d Indicates the dry density of the surface layer of the base bed, G s Indicates the relative density corresponding to the surface layer of the base bed; The expression of moisture content increment is as follows: ； Where n represents the saturated moisture content w sr and the initial moisture content w of the subgrade surface a The difference Δw between them is divided equally into the number of parts.

3. The method for identifying mud slurry damage in ballastless track subgrade based on GPR technology according to claim 1 is characterized in that: The moisture content of the base bed sample is: The moisture content w corresponding to the first bedding sample 11 = w a + η w , the moisture content w corresponding to the second bedding sample 22 = w a + 2η w , ..., the moisture content w corresponding to the Nth bedding sample NN = w a +nη w = w sr ; Among them, w a is the initial moisture content of the subgrade surface, w sr is the saturated moisture content, η w is the moisture content increment, n represents the saturated moisture content w sr and the initial moisture content w of the subgrade surface a The difference Δw between them is divided equally into the number of parts.

4. The method for identifying mud slurry damage in ballastless track subgrade based on GPR technology according to claim 1 or 3, characterized in that: The process of configuring a number of bed samples with the same dry density as the original soil sample but different moisture content according to the moisture content increment includes: All the original soil samples on the surface of the base bed were air-dried and the moisture content w of the air-dried soil samples was measured. fg ; The moisture content is w 11 The first bedding sample: weigh the mass m 11 = ρ d ·V·(1 + w fg ) of air-dried soil sample and add a mass of Δm1 = ρ d ·V·(w1 - w fg ) of water to form a base bed sample with the same height as the base bed surface; where V is the volume of the first base bed sample, ρ d represents the dry density of the surface layer of the subgrade, and w1 represents the moisture content of the original soil sample at the first level of mud-turning position; By analogy, the moisture content is w 22 The second bedding sample, ..., has a water content of w NN The Nth base bed sample.

5. The method for identifying mud slurry damage in ballastless track subgrade based on GPR technology according to claim 1 is characterized in that: The height of the concrete element is the same as the height of the base plate in the ballastless track.

6. The method for identifying mud slurry damage in ballastless track subgrade based on GPR technology according to claim 1 is characterized in that: Chirp signal is selected as the excitation signal in the three-dimensional finite element analysis model corresponding to the radar detection test model to simulate the ground-coupled radar antenna.

7. A ballastless track subgrade slurry disease identification system based on GPR technology, characterized in that: The system is used to implement the method for identifying mud-overflowing defects of ballastless track subgrade based on GPR technology as described in any one of claims 1 to 6, the system comprising: The original soil sample acquisition module performs GPR detection and sampling operations at the un-slurrying position, critical slurrying position, first-level slurrying position, ..., and Nth-level slurrying position of the ballastless track subgrade to obtain radar waveforms and original soil samples of the subgrade surface; obtain the dry density and relative density corresponding to the subgrade surface, and the moisture content of each original soil sample; calculate the saturated moisture content and moisture content increment of the subgrade surface based on the dry density and relative density; The base bed sample configuration module configures a number of base bed samples with the same dry density as the original soil sample but different moisture content according to the moisture content increment; The moisture content-radar waveform data set construction module constructs a radar detection test model and a three-dimensional finite element analysis model arranged from top to bottom by concrete components, bed samples, and steel plates; uses a ground-coupled radar antenna to detect the radar detection test model to obtain the actual radar waveform data corresponding to each bed sample; fits the three-dimensional finite element analysis model based on the moisture content corresponding to each bed sample; and constructs the moisture content-radar waveform data set based on the fitted three-dimensional finite element analysis model; The moisture content discrimination network training module takes radar waveform data as input and moisture content as output to train the moisture content discrimination network; The ballastless track subgrade slurry overflow disease identification module uses a ground-coupled radar antenna to detect the surface of the ballastless track subgrade to be detected and obtain a radar waveform test data set; the radar waveform test data set is input into the trained moisture content discrimination network to obtain the current moisture content of the ballastless track subgrade surface and the location of the moisture content change; the status of the ballastless track subgrade slurry overflow disease is determined based on the current moisture content of the ballastless track subgrade surface and the location of the moisture content change.

8. An electronic device comprising a memory and a processor, characterized in that: The memory is coupled to the processor; wherein the memory is used to store program data, and the processor is used to execute the program data to implement the method for identifying slurry overflow defects in ballastless track subgrade based on GPR technology as described in any one of claims 1 to 6.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the program is executed by a processor, the method for identifying mud slurry damage in ballastless track subgrade based on GPR technology as described in any one of claims 1 to 6 is implemented.

10. A computer program product comprising a computer program / instructions, characterized in that When the computer program / instruction is executed by a processor, the method for identifying mud slurry damage in ballastless track subgrade based on GPR technology as described in any one of claims 1 to 6 is implemented.

Images