A Railway Track Damage Detection Method Based on the Salicornia Algorithm and Temperature Inversion Theory

Abstract

This invention provides a railway track damage detection method based on the Salicornia algorithm and temperature inversion theory, comprising: S1, establishing a track inversion model and analyzing the discrete track model using the finite difference method; S2, performing simulation calculations on the track model and obtaining the temperature distribution of the two-dimensional I-shaped flat track using the finite difference method; S3, introducing the Salicornia algorithm and using the internal temperature data of the track obtained through solving the forward problem as input to the inverse problem to invert and identify the internal temperature information of the track; S4, using the inverted internal temperature data to accurately detect the track damage. The beneficial effects of this invention are: the railway track damage detection method based on the Salicornia algorithm and temperature inversion theory, based on temperature inversion theory, achieves non-destructive detection of the internal temperature of the track, thereby accurately assessing track damage.

Description

Technical Field

[0001] This invention belongs to the field of detection technology, and in particular relates to a railway track damage detection method based on the tunic algorithm and temperature inversion theory. Background Technology

[0002] As a major mode of public transportation, the performance and quality of rail transit tracks directly impact personal safety. Track inspection allows for the timely detection of defects and potential hazards, providing strong assurance for safe travel. Testing railway tracks for compressive strength, flexural strength, and impermeability provides a scientific basis for engineering design and construction.

[0003] With increasing societal focus on sustainable development, the rail industry is actively seeking green and environmentally friendly development paths. Railway track inspection, as a crucial link in the industry, plays a vital role in promoting sustainable development. Through inspection, the environmental impact of railway tracks can be assessed, production processes optimized, pollution reduced, and the industry's green development promoted.

[0004] With the continuous advancement of technology, railway track inspection technology is also constantly innovating and developing. The emergence of new inspection technologies has brought higher accuracy and efficiency to railway track inspection, providing strong support for the industry's technological progress. At the same time, technological progress has also driven the innovative development of the railway track inspection industry, providing broader application prospects for railway track inspection.

[0005] The development of the railway track inspection industry is inseparable from the formulation and implementation of industry standards and specifications. By establishing unified inspection standards and specifications, the accuracy and reliability of railway track inspection results can be ensured, providing a strong guarantee for the healthy development of the industry. At the same time, the implementation of industry standards and specifications can also promote the standardization and normalization of the railway track inspection industry.

[0006] Railway track inspection has a positive impact on economic benefits and social development. Through inspection, the quality and safety of projects can be ensured, avoiding economic losses and social impacts caused by quality problems. At the same time, railway track inspection provides technical support and services to the industry, promoting its healthy development and contributing to the sustained and stable growth of the social economy. Furthermore, the accuracy and reliability of railway track inspection can enhance the industry's international competitiveness and propel it onto the world stage.

[0007] In conclusion, railway tracks and railway track inspection are of great significance and value in terms of material foundations, engineering structural safety, quality control requirements, sustainable development promotion, technological progress and innovation, industry standards and norms, as well as economic benefits and social development. Therefore, we should strengthen our attention to and research on railway track inspection, promote the continuous progress and development of railway track inspection technology, and make greater contributions to the healthy development of the industry and the sustainable development of the social economy. However, currently, railway maintenance and upkeep in my country mainly relies on manual inspection. This method depends entirely on the visual observation of inspection workers, which has drawbacks such as high subjectivity, heavy workload, high risk of working at night, and significant weather influence. The accuracy and efficiency of inspection often fall short of ideal results. While high-speed railways use integrated inspection vehicles for automated track inspection, the inspection cycle is relatively long and cannot meet the actual needs of on-site inspection. Summary of the Invention

[0008] In view of this, the present invention aims to propose a railway track damage detection method based on the tunic algorithm and temperature inversion theory, so as to at least solve one of the problems in the background art.

[0009] To achieve the above objectives, the technical solution of the present invention is implemented as follows:

[0010] A railway track damage detection method based on the salver algorithm and temperature inversion theory includes:

[0011] S1. Establish an orbit inversion model and analyze the discrete orbit model using the finite difference method;

[0012] S2. Simulate the track model and use the finite difference method to obtain the temperature distribution of the two-dimensional I-shaped plate of the track.

[0013] S3. Introduce the Salicornia algorithm and use the internal temperature data of the orbit obtained by solving the forward problem as the input of the inverse problem to perform inversion identification of the internal temperature information of the orbit.

[0014] S4. Using the internal temperature data obtained from the inversion, the damage to the track can be accurately detected.

[0015] Furthermore, in step S1, it is necessary to collect the thermal properties of the orbit, including thermal conductivity, thermal diffusivity, density, specific heat capacity, and heat transfer coefficient.

[0016] Furthermore, the setting of the internal parameters of the two-dimensional model in step S2 and the introduction of the tunic algorithm in step S3 are both simulated and calculated using Matlab software.

[0017] Furthermore, in step S2, Taylor series expansion is used to solve the first and second derivatives, and partial differential equations are established for the steady-state heat conduction forward problem model. Combined with boundary conditions, it is discretized into an explicit finite difference scheme.

[0018] Furthermore, in step S3, the objective function is constructed as follows:

[0019]

[0020] in, Let B be the calculated temperature value at measurement point k, and let B be the vector of unknown parameters to be identified. The heat conduction forward problem model is obtained by solving the guessed value of B. Let K be the temperature measurement value at point k. When the objective function J(B) reaches its minimum value, the vector B obtained by solving the problem is the unknown parameter vector.

[0021] Furthermore, in step S3, the steps for inversion using the tunic algorithm include:

[0022] Initialize the population: Generate a population of N×D tunicates based on the upper and lower bounds of the search space;

[0023] Calculate fitness: Evaluate the fitness value of each individual and select the individual with the best fitness as the food location;

[0024] Update the positions of the leader and followers: By setting the convergence factor c1 and random factors c2 and c3, dynamically adjust the positions of the leader and followers to make them approach the target area;

[0025] Iterative optimization: The fitness value is continuously updated until the termination condition is met, and the final target parameter estimate is output.

[0026] Furthermore, this solution discloses an electronic device, including a processor and a memory connected in communication with the processor and used to store executable instructions of the processor. The processor is used to execute the above-mentioned railway track damage detection method based on the tunic algorithm and temperature inversion theory.

[0027] Furthermore, this solution discloses a server, including at least one processor and a memory communicatively connected to the processor. The memory stores instructions executable by the at least one processor, which are executed by the processor to cause the at least one processor to perform a railway track damage detection method based on the tunic algorithm and temperature inversion theory.

[0028] Furthermore, this solution discloses a computer-readable storage medium storing a computer program, which, when executed by a processor, implements a railway track damage detection method based on the tunic algorithm and temperature inversion theory.

[0029] Compared with existing technologies, the railway track damage detection method based on the tunic algorithm and temperature inversion theory described in this invention has the following advantages:

[0030] The railway track damage detection method based on the tunic algorithm and temperature inversion theory described in this invention achieves non-destructive detection of the internal temperature of the track, thereby accurately assessing track damage. Attached Figure Description

[0031] The accompanying drawings, which form part of this invention, are used to provide a further understanding of the invention. The illustrative embodiments of the invention and their descriptions are used to explain the invention and do not constitute an undue limitation of the invention. In the drawings:

[0032] Figure 1 This is a flowchart illustrating the implementation process of the track damage detection method based on the tunicate algorithm and temperature inversion theory of the present invention.

[0033] Figure 2 This is a schematic diagram of mesh division in an experimental example of the present invention;

[0034] Figure 3 This is a flowchart illustrating the orbital temperature inversion based on the Salicornia salina algorithm of this invention;

[0035] Figure 4 This is a block diagram of the iterative algorithm for an experimental example of the present invention;

[0036] Figure 5 This is a comparison diagram of the track defect detection methods in practical examples of the present invention;

[0037] Figure 6 This is a three-dimensional temperature change curve for an experimental example of the present invention. Detailed Implementation

[0038] It should be noted that, unless otherwise specified, the embodiments and features described in the present invention can be combined with each other.

[0039] The present invention will now be described in detail with reference to the accompanying drawings and embodiments.

[0040] A method for detecting track damage based on the tunicate algorithm and temperature inversion theory includes the following steps:

[0041] S1. Establish the orbit inversion model and analyze the discrete orbit model using the finite difference method;

[0042] S2. The model was simulated, and the temperature distribution of the two-dimensional I-shaped plate of the track was obtained using the finite difference method.

[0043] S3. The Salicornia algorithm is introduced, which uses the temperature information inside the track obtained by solving the forward problem as the input value in the inverse problem to perform inverse identification of the temperature information inside the track.

[0044] S4. Utilize internal temperature data to accurately detect damage to railway tracks.

[0045] Furthermore, the main thermal properties of the orbit collected in step S1 are: thermal conductivity, thermal diffusivity, density, specific heat capacity, and heat transfer coefficient.

[0046] Furthermore, the setting of internal parameters of the two-dimensional model in step S2, and the introduction of the conjugate gradient method and the tunicate algorithm in S3, are all simulated using Matlab programming software.

[0047] The temperature of the outer wall of the orbit is obtained from the temperature field distribution obtained by the unsteady-state heat conduction forward problem model;

[0048] An objective function is constructed to measure and solve for the temperature of the outer wall of the track. The tunic algorithm is then introduced for inversion and solution to obtain the temperature difference.

[0049] A preset convergence condition is set. When the temperature difference does not meet the convergence condition, the orbital temperature is iterated until the convergence condition is met, and the orbital temperature inversion result is obtained.

[0050] Furthermore, in step S2,

[0051] The process of finite difference is as follows:

[0052] Taylor series can be used to establish representations of first and second derivatives, which can be used not only as error estimates but also to establish more accurate formulas. Suppose we have a continuous function f(x), where x... -1 x0 and x1 are discrete points at equal intervals, and x1 - x0 = x0 - x -1 =Δx, where f(x) represents the function value.

[0053] First, expand the function f(x1) = f(x0 + Δx) using a Taylor series:

[0054]

[0055] In the formula, ο(x) 3 To truncate (x) 3 The following terms are the truncation error terms obtained. Similarly, the function f(x) is used to... -1 Taylor expansion of f(x0-Δx) yields:

[0056]

[0057] Where ο(x) 3 This represents the corresponding truncation error term in the above equation. When the terms following Δx are truncated, the forward and backward difference formulas for the derivative f′(x0) of f(x0) are obtained:

[0058]

[0059] In the formula, f″(x) 0,1 f″(x) is the second derivative of f(x) at some point in the interval (x0, x1). -1,0 ) is in the interval (x) of f(x) -1 The second derivative of x0 is obtained by subtracting formula (2) and formula (3) to obtain the central difference formula:

[0060]

[0061] The formula includes a truncation error term (Δx). 2 (f″′(x -1,0 )+f″′(x 0,1 )) / 3! , where f″′(x -1,0 ) is in the interval (x) of f(x) -1 The third derivative of x, x0), f″′(x 0,1 ) is the third derivative of f(x) in the interval (x0, x1). It is easy to see from the above formula that this central difference formula is more accurate than the forward difference formula and the backward difference formula. However, applying this central difference formula with second-order truncation error does not necessarily make it more accurate than the forward difference formula with first-order truncation error and the backward difference formula with first-order truncation error. This is because in practical applications, the time derivative applied to the unsteady heat transfer equation will always produce an unstable process. This unstable result is invalid, while the application of the forward difference formula can meet the needs of the solution. In order to obtain the corresponding second derivative at x = x0, add formula (2) and formula (3):

[0062]

[0063] The formula includes a truncation error term (Δx). 2 (f (4) (x -1,0 )+f (4) (x 0,1 )) / 4!, where f (4) (x -1,0 ) is in the interval (x) of f(x) -1 The fourth derivative of f(x0) (4) (x 0,1) is the fourth derivative of f(x) on the interval (x0, x1).

[0064] The equations for the steady-state heat conduction forward problem model are shown below:

[0065]

[0066] C1:T=f(x),y=L y (8)

[0067] C2:

[0068] C3:

[0069] C4:

[0070] In the formula, C1 is the temperature distribution boundary, C3 and C4 are the adiabatic boundaries, and C2 is the heat flux boundary q, which is fixed at 150 (w / m²). 2 ), where λ is the thermal conductivity of 50 W / (m·K).

[0071] Partial differential equations can be written as the following formulas:

[0072]

[0073] Where T i,j For the temperature at the discrete point (i,j), removing the error term yields:

[0074]

[0075] Let Δx = Δy, then it can be rewritten as

[0076]

[0077] This formula is the formula for solving the internal nodes, and it is an explicit form of finite difference.

[0078] In step (S3),

[0079] The process of constructing the objective function is as follows:

[0080]

[0081] In the above formula Let B be the calculated temperature value at measurement point k, and let B be the vector of unknown parameters to be identified. The heat conduction forward problem model is obtained by solving the guessed value of B. Let be the temperature measurement value at measuring point k. When the objective function J(B) reaches its minimum value, the resulting vector B is the vector of unknown parameters.

[0082] The inversion process of the tunic algorithm, the random walk process is as follows:

[0083] X D×N =rand(D,N).(ub(D,N)-lb(D,N))+lb(D,N) (16)

[0084] Leaders in the population use It means that followers use Let i = 2, 3, 4, ..., N; d = 1, 2, 3, ..., D

[0085] During the movement and foraging of the salver chain, the leader's position update is represented as follows:

[0086]

[0087] In the formula, and F d ...

[0088] The leader's position is updated only based on the location of the food. c1 is the convergence factor in the optimization algorithm, balancing global exploration and local exploitation. is the most important control parameter in the tunic. The expression for c1 is:

[0089]

[0090] In the formula: l is the current iteration number; L is the maximum iteration number. The convergence factor is a decreasing function of 2-0. The control parameters c2 and c3 are random numbers in the range [0,1], used to enhance convergence. The randomness enhances the global search and individual diversity of the chain group.

[0091] During the movement and foraging of the salver chain, the followers move forward in a chain-like manner through mutual influence between individuals in front and behind. Their displacements conform to Newton's laws of motion, and the displacements of the followers are:

[0092]

[0093] Considering that t is iterative in the optimization algorithm, let's assume t = 1 and v0 = 0 during the iteration. This can be expressed as:

[0094]

[0095] In the formula: i≥2; and These are the positions of two consecutive tunicates in the d-th dimension. Therefore, the position of the follower is represented as:

[0096]

[0097] In the formula: and These represent the positions of the followers after the update and the positions of the followers before the update in the d-th dimension, respectively.

[0098] Algorithm flow:

[0099] 1) Initialize the population. Based on the upper and lower bounds of each dimension of the search space, initialize a population of N×D tunicates.

[0100] 2) Calculate the initial fitness. Calculate the fitness values ​​of N tunicates.

[0101] 3) Select food. Since we do not know the location of the target (i.e., food) during actual positioning, the salps are sorted according to their fitness values, and the position of the salps with the best fitness at the top of the list is set as the current food location.

[0102] 4) Select leaders and followers. After selecting the food location, there are N-1 salps remaining in the group. According to the order of the salps group, the salps in the first half are regarded as leaders, and the rest are regarded as followers.

[0103] 5) Position Update. First update the leader's position, then update the followers' positions.

[0104] 6) Calculate fitness. Calculate the fitness of the updated population. Compare the updated fitness value of each salps with the fitness value of the current food. If the updated salps have a better fitness value than the food, then the location of the salps with the better fitness value is used as the new food location.

[0105] 7) Repeat steps 4)-6) until a certain number of iterations are reached or the fitness value reaches the termination threshold. Once the termination condition is met, output the current food position as the estimated position of the target.

[0106] In the specific implementation process, it includes:

[0107] like Figures 1 to 6 As shown in the figure, this experimental example provides a method for detecting track damage based on the tunicate algorithm and temperature inversion theory. The process is as follows:

[0108] First, a microwave humidity sensor was used to detect the humidity of the track, while an infrared thermometer was used to accurately measure its temperature. To calculate the thermal conductivity, an adiabatic temperature rise meter was used to observe the surface temperature rise of the railway track at specific temperatures. Additionally, a laser scintillation method was used to directly determine the thermal diffusivity of the material. To obtain the density of the railway track, a direct weighing method was used to measure the volume and weight of the sample.

[0109] To address the positive heat transfer problem, a two-dimensional unsteady-state heat transfer model along the horizontal direction of the railway track was constructed based on Fourier's law of thermal conductivity and the principle of energy conservation. To make this model more closely resemble actual conditions, the following simplifications were made:

[0110] (1) The railway track is considered as a composite material, and a two-dimensional numerical model is established for it. In this model, we obtain the temperature correlation between the thermal parameters of mortar and aggregate by fitting the experimental data from existing literature. We assume that the railway track is homogeneous in all aspects and that its thermal parameters do not change with time. At the same time, there is no internal heat source inside the track, we ignore the contact thermal resistance, and assume that the temperature at the interface is continuously distributed.

[0111] (2) The inner side of the railway track is in close contact with the metal wall, which maintains a constant temperature Tf, constituting a third type of boundary condition, with a convective heat transfer coefficient of h1. The outer side of the railway track is directly exposed to the ambient temperature Ta, also belonging to the third type of boundary condition, with a convective heat transfer coefficient of h2.

[0112] To solve the unsteady-state heat conduction problem, we set the parameter values ​​for the model and used the finite difference method for numerical calculation to obtain the temperature distribution on the outer wall of the railway track.

[0113] In the solution process, we first set an initial value (Tf)0 for the temperature inside the railway track, and then substituted this value into the system of equations for the heat conduction problem. Through programming calculations, the temperature distribution at each point within the heat conduction problem region can be obtained.

[0114] Next, the temperature of the outer wall of the railway track obtained by solving the unsteady-state heat conduction forward problem will be compared with the actual temperature data measured by the temperature probe. These data will be substituted into the objective function used to solve the inverse problem to determine whether the solution meets the convergence criterion. If it does, then we can output the inverse result of the internal temperature.

[0115] The essence of the inverse problem of heat conduction lies in constructing an objective function that aims to minimize the difference between known and unknown parameters. By employing appropriate optimization algorithms, we can solve for the inverse values ​​of these unknown parameters, thereby gaining a more accurate understanding of the temperature distribution inside the railway track.

[0116] When the value of the objective function J is lower than a pre-set, sufficiently small number μ, it means that the internal temperature distribution obtained through the inverse problem of heat conduction is very close to the true solution. To verify this, we substitute the calculated value of the temperature of the outer wall of the railway track at a given initial internal temperature (Tf)0 into the objective function of the inverse problem and evaluate the value of the objective function.

[0117] If the objective function value is too large and does not meet our convergence condition, then we need to iteratively update Tf. In each iteration, we use the tunic algorithm to determine a new Tf value, and then substitute this new value into the forward problem to obtain a new temperature distribution. Next, we recalculate the objective function value. This iterative process continues until the objective function value meets the convergence condition. In this way, we can gradually approximate the true internal temperature distribution.

[0118] Table 1. Inversion results of different algorithms for inversion temperature.

[0119]

[0120] Table 1 presents the trap identification results of the two algorithms. As shown in the table, the *Symplocos salina* algorithm outperforms the Archimedes algorithm in terms of convergence criterion, convergence speed, and robustness. The algorithm exhibits relatively small errors and strong robustness. This advantage indicates that the *Symplocos salina* inversion algorithm has broad application prospects in the field of thermal nondestructive testing.

[0121] Temperature field effects are a major factor causing damage and even separation at the interlayer interfaces of the track. Periodic temperature action causes repeated warping deformation of the structural layers, leading to voids between layers and resulting in unfavorable conditions such as localized support issues and high-temperature arching in longitudinally connected plate structures. It also generates significant tensile stress on the top or bottom surface of the track, causing concrete cracking and adversely affecting the durability and service safety of ballastless tracks. Therefore, obtaining the temperature field distribution allows us to detect track damage.

[0122] Those skilled in the art will recognize that the units and method steps of the various examples described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, computer software, or a combination of both. To clearly illustrate the interchangeability of hardware and software, the components and steps of the various examples have been generally described in terms of functionality in the foregoing description. Whether these functions are implemented in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementations should not be considered beyond the scope of this invention.

[0123] In the several embodiments provided in this application, it should be understood that the disclosed methods and systems can be implemented in other ways. For example, the division of units described above is merely a logical functional division, and in actual implementation, there may be other division methods. For instance, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. The aforementioned units may or may not be physically separated. 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 units can be selected to achieve the purpose of the embodiments of the present invention according to actual needs.

[0124] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, and not to limit them. Although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some or all of the technical features therein. Such modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the scope of the technical solutions of the embodiments of the present invention, and they should all be covered within the scope of the claims and specification of the present invention.

[0125] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of the present invention should be included within the protection scope of the present invention.

Claims

1. A railway track damage detection method based on the tunic algorithm and temperature inversion theory, characterized in that, include: S1. Establish an orbit inversion model and analyze the discrete orbit model using the finite difference method; S2. Simulate the track model and use the finite difference method to obtain the temperature distribution of the two-dimensional I-shaped plate of the track. S3. Introduce the Salicornia algorithm and use the internal temperature data of the orbit obtained by solving the forward problem as the input of the inverse problem to perform inversion identification of the internal temperature information of the orbit. S4. Using the internal temperature data obtained from the inversion, the damage to the track can be accurately detected; In step S3, the objective function is constructed as follows: in, For measuring points The calculated temperature value at that location, Calculate the temperature value for the unknown parameter vector to be identified. according to The guessed values ​​are obtained by solving the heat conduction forward problem model. For measuring points The temperature measurement value at that location makes the above objective function... When the minimum value is reached, the vector obtained by solving the problem is... A vector of unknown parameters; In step S3, the steps for inversion using the tunic algorithm include: Initialize the population: Generate a population of N × D tunicates based on the upper and lower bounds of the search space; Calculate fitness: Evaluate the fitness value of each individual and select the individual with the best fitness as the food location; Update the positions of the leader and followers: By setting the convergence factor c1 and random factors c2 and c3, dynamically adjust the positions of the leader and followers to make them approach the target area; Iterative optimization: The fitness value is continuously updated until the termination condition is met, and the final target parameter estimate is output.

2. The railway track damage detection method based on the tunicate algorithm and temperature inversion theory according to claim 1, characterized in that, In step S1, it is necessary to collect the thermal properties of the orbit, including thermal conductivity, thermal diffusivity, density, specific heat capacity, and heat transfer coefficient.

3. The railway track damage detection method based on the tunicate algorithm and temperature inversion theory according to claim 1, characterized in that: In step S2, the internal parameters of the two-dimensional model are set, and in step S3, the tunicate algorithm is introduced. Both of these processes are simulated and calculated using Matlab software.

4. The railway track damage detection method based on the tunicate algorithm and temperature inversion theory according to claim 1, characterized in that, In step S2, Taylor series expansion is used to solve the first and second derivatives, and partial differential equations are established for the steady-state heat conduction forward problem model. Combined with boundary conditions, it is discretized into an explicit finite difference scheme.

5. An electronic device, comprising a processor and a memory communicatively connected to the processor and used for storing processor-executable instructions, characterized in that: The processor is used to execute the railway track damage detection method based on the tunic algorithm and temperature inversion theory as described in any one of claims 1-4.

6. A server, characterized in that: It includes at least one processor and a memory communicatively connected to the processor, the memory storing instructions executable by the at least one processor, the instructions being executed by the processor to cause the at least one processor to perform the railway track damage detection method based on the tunic algorithm and temperature inversion theory as described in any one of claims 1-4.

7. A computer-readable storage medium storing a computer program, characterized in that: When the computer program is executed by the processor, it implements the railway track damage detection method based on the tunic algorithm and temperature inversion theory as described in any one of claims 1-4.

Images