Continuous welded track longitudinal action monitoring method based on digital twinning

Abstract

The invention discloses a method for monitoring the longitudinal action of a seamless track based on digital twinning. The method comprises the following steps: S1, determining the type of a special section of a field seamless track; s2, collecting feature point data by adopting a temperature sensor and a displacement sensor; s3, establishing a finite element simulation model, and calculating the temperature and displacement of a special section and the longitudinal additional force of the steel rail; s4, establishing a mapping model to obtain a mapping relation from the physical database to the virtual database; s5, comparing the mapping data with the data which does not participate in the establishment of the mapping model, and verifying the model; and S6, constructing a digital twin virtual body which is completely equal to the special section of the seamless track, and interacting with the on-site seamless track. Based on the digital twinborn technology, the on-site continuously welded track service state can be judged in real time, various continuously welded track maintenance measures can be simulated, and a maintenance plan can be made more efficiently.

Description

Technical Field

[0001] The present invention relates to the technical field of railway operation and maintenance simulation technology, and in particular to a method for monitoring the longitudinal effects of seamless lines based on digital twins. Background Art

[0002] The permafrost zone of the plateau railway is characterized by high altitude and lack of oxygen, changeable climate, unclear four seasons, large daily temperature difference, long negative temperature period throughout the year, strong solar radiation, common steep slopes, many sections with thick roadbeds, and common thermal melting subsidence of roadbed. These particularities in climate, geological conditions and track structure directly cause the values ​​and change patterns of seamless line status indicators to be different from those in other regions.

[0003] In addition, when the train is running on a long slope, there is a large longitudinal force problem (referred to as braking load) caused by frequent braking, adhesion traction, and the longitudinal component of gravity, which is more complicated than the flat slope section. The rails are subjected to the dynamic load of the train's reciprocating motion, and the seamless line begins to creep to one side. The increase in rail temperature caused by frequent braking of the train will also cause the seamless line to creep to one side.

[0004] In the prior art, the calculation of the additional force of the interaction between beams and rails is generally done by using the large finite element method, which is done by establishing a three-dimensional space coupled solid model. However, bridges and rails in actual environments are very complex engineering structures, and it is very difficult to perform accurate calculations and analyses through simulation. In addition, the on-site deployment of sensors requires monitoring of many points, which is time-consuming and labor-intensive.

[0005] Therefore, in the prior art, under the premise of meeting the engineering application, the tracks, bridges and piers are usually simplified into beam and plate units through some simplification, and the calculation model of the longitudinal force of the rails of the seamless line is established based on the simplified beam and plate units. This calculation model can basically reflect the longitudinal force of the interaction between the beam and the rail, but it can only meet the needs of simple projects and cannot complete the monitoring of the transverse and longitudinal deformation characteristics of the seamless line under complex environments, as well as the stress and deformation characteristics of various parts of special sections such as high piers and long span bridges, bridge-tunnel transition sections and seamless turnouts. Summary of the invention

[0006] In order to solve the problem that the existing technology is unable to monitor the transverse and longitudinal deformation characteristics of seamless lines in complex environments and the stress deformation characteristics of various parts in special sections, a simulated seamless line matching the seamless line in special sections on site is constructed based on digital twin technology to solve the above problems.

[0007] The present application discloses a method for monitoring the longitudinal action of a seamless line based on digital twins, comprising the following steps:

[0008] S1. Establish the special section type of the seamless line on site;

[0009] S2, using temperature sensors and displacement sensors to collect feature point data;

[0010] S3. Establish a finite element simulation model to calculate the temperature, displacement and additional longitudinal force of the rail in special sections;

[0011] S4. Establish a mapping model to obtain a mapping relationship from a physical database to a virtual database;

[0012] S5, comparing the mapped data with the data that did not participate in the establishment of the mapping model to verify the model;

[0013] S6. Through 3D rendering technology, a digital twin virtual body that is exactly the same as the special section of the seamless line is constructed, and interacts with the on-site seamless line.

[0014] Preferably, the special sections of the seamless track in S1 include high-pier long-span bridges, bridge-tunnel transition sections and seamless turnouts.

[0015] Preferably, it is characterized in that the feature point data in S2 includes:

[0016] Displacement and temperature of rails at the ends of high-pier and long-span bridges, displacement and temperature of beam joints;

[0017] Rail displacement and rail temperature at the end of the first span of the simply supported beam at the entrance of the bridge-tunnel transition section, and rail displacement and rail temperature at each section of the temperature transition zone;

[0018] The displacement changes of the tip of the seamless turnout point rail relative to the stock rail, the displacement changes of the tip of the heart rail relative to the wing rail, the displacement in front of the turnout and at the limiter, and the stock rail displacement near the guardrail.

[0019] Preferably, S3 comprises the following steps:

[0020] A seamless track model for high-pier and long-span bridges was established. Based on the principle of beam-rail-bridge interaction, a one-bridge-one-pier lightweight calculation model for seamless track was established to calculate the seamless longitudinal force on high-pier and long-span bridges. The model was solved using the nonlinear finite element method to calculate the mechanical characteristics of the seamless track of high-pier and long-span bridges under different working conditions.

[0021] A seamless track model for the bridge-tunnel transition section was established. Based on the beam-track interaction principle, a lightweight analysis model of the track-substructure in the bridge-tunnel area was established. The model was solved using the nonlinear finite element method to calculate the mechanical characteristics of the seamless track for the bridge-tunnel transition section under different working conditions.

[0022] A seamless turnout model is established. Based on the principle of beam-rail interaction, a lightweight analysis model of the track-substructure in the turnout area is established, and the model is solved using the nonlinear finite element method.

[0023] Preferably, the data in the physical database in S4 are physical data collected by the sensor in S2, and the data in the virtual database are virtual data calculated in S3.

[0024] Preferably, the establishing of the mapping model comprises the following steps:

[0025] Using the physical database as input and the virtual database as output, a neural network model of physical data and virtual data of a special section seamless line under multiple working conditions is constructed and trained. The training data of the neural network model are the physical data sets of N sensor acquisition points in the physical database and the M corresponding virtual data sets in the virtual database calculated by the finite element simulation model. The mapping model is trained based on the physical data sets and the virtual data sets.

[0026] Preferably, the neural network model is a CNN-Bi-GRU-GWO neural network model with adaptive hyperparameters, and the neural network model comprises a four-layer network:

[0027] The first layer of the network is the input layer, which extracts features from one-dimensional time series data through the CNN network;

[0028] The second layer of the network is the Bi-GRU temporal network layer, which takes the feature extraction data of the previous layer of CNN as input and further extracts features on a time scale;

[0029] The third network layer is the neural network hyperparameter optimization layer, which adaptively optimizes the hyperparameters of the CNN network and the Bi-GRU timing network;

[0030] The fourth network layer is the output layer, which is constructed for training and optimization, and the mean square error is used as the objective function of the model. The model is trained by minimizing the mean square error.

[0031] Preferably, S5 comprises the following steps:

[0032] S51. When constructing a mapping model, remove the test points that are common to the physical database and the virtual database, and a portion of the data with a common data type, and propose that the portion does not participate in the construction of the mapping model and is only used for the verification of the mapping model;

[0033] S52, calculating virtual data corresponding to the removed points by using a mapping model for the physical data of the removed points in the physical database;

[0034] S53, comparing the calculated virtual data with the physical data of the point;

[0035] S54, judging the virtual data output by the mapping model, if the error between the virtual data and the physical data corresponding to the point is within a controllable range, the mapping model is verified, if the error is outside the controllable range, the parameters of the mapping model are corrected and optimized.

[0036] Preferably, S6 comprises the following steps:

[0037] By controlling the digital twin virtual body, parameters including fastener resistance, roadbed resistance, ambient temperature, locked rail temperature and train live load can be changed;

[0038] Through the mapping model, the indicators of seamless railway, including rail temperature, creep, and rail longitudinal additional force, are checked and calculated, and a maintenance plan that meets the requirements of the regulations is formulated;

[0039] After maintenance and repair of the seamless line, data feedback collected from the seamless line is interactively verified with the seamless line digital twin virtual body.

[0040] Beneficial effects of the present invention:

[0041] (1) Based on digital twin technology, a digital twin virtual body matching the seamless line in special sections is constructed. This virtual body can be used to judge the service status of the seamless line in real time, making it easier to intuitively grasp the changes in various indicators of the seamless line in special sections and the historical change patterns.

[0042] (2) Through the seamless line digital twin virtual body, various seamless line maintenance measures can be simulated, and the changes in various indicators of the line after maintenance can be calculated, which facilitates the formulation of maintenance plans more efficiently. BRIEF DESCRIPTION OF THE DRAWINGS

[0043] Figure 1 This is a flow chart of a method for monitoring the longitudinal action of a seamless line based on digital twins according to an embodiment of the present invention;

[0044] Figure 2 This is a schematic diagram of monitoring characteristic points of a high-pier long-span bridge according to an embodiment of the present invention;

[0045] Figure 3 Schematic diagram of monitoring characteristic points of temperature and longitudinal displacement at a bridge-tunnel transition section according to an embodiment of the present invention;

[0046] Figure 4 Schematic diagram of monitoring lateral displacement characteristic points at a bridge-tunnel transition section according to an embodiment of the present invention;

[0047] Figure 5 It is a schematic diagram of applying temperature equivalent load to the bridge-tunnel transition section area model according to an embodiment of the present invention;

[0048] Figure 6 A schematic diagram of monitoring characteristic points of a seamless turnout according to an embodiment of the present invention;

[0049] Figure 7 Schematic diagram of sensor collection points of a data collection module according to an embodiment of the present invention.

[0050] The reference numerals are as follows:

[0051] 11-rail; 12-continuous beam; 13-simply supported beam; 14-lower foundation; 15-top plate temperature measuring point; 16-web plate temperature measuring point; 17-beam end displacement measuring point; 18-beam joint; 21-beam end; 22-fastener; 31-basic rail; 32-point rail; 33-switch; 34-stopper; 35-guard rail; 36-wing rail; 37-heart rail. DETAILED DESCRIPTION

[0052] In order to make the objectives, technical solutions and advantages of the present application more clearly understood, the present application is further described in detail below with reference to the accompanying drawings and examples.

[0053] The embodiment of the present application discloses a method for monitoring the longitudinal action of a seamless line based on digital twins, the process is as follows: Figure 1 As shown, the following steps are included:

[0054] S1. Establish the types of special sections of seamless lines on site so as to monitor characteristic points and establish simulation models according to the actual situation on site. Special sections of seamless lines include high-pier long-span bridges, bridge-tunnel transition sections and seamless turnouts.

[0055] S2. Use temperature sensors and displacement sensors to collect feature point data, including:

[0056] The displacement and temperature of the rails at the ends of high-pier and long-span bridges, and the displacement and temperature of beam joints. The displacement and temperature of the rails at the ends of the first span of the simply supported beam at the entrance of the bridge-tunnel transition section, and the displacement and temperature of the rails at each section of the temperature transition zone. The displacement change of the tip of the seamless turnout point rail relative to the base rail, the displacement change of the tip of the heart rail relative to the wing rail, the displacement in front of the turnout and at the stopper, and the base rail displacement near the guardrail.

[0057] In a specific embodiment, temperature and displacement sensors are arranged on the seamless line for all-weather testing to collect temperature and displacement changes of the seamless line in special sections such as high-pier large-span bridges, bridge-tunnel transition sections, and seamless turnouts, as well as environmental parameters such as air temperature and solar radiation in the special sections. The temperature collector used is an infrared thermal imager, and the displacement collector is a high-definition camera using moiré fringe micro-displacement measurement technology, which can realize non-destructive monitoring of the seamless line. The sensor test position is selected as the part with large displacement in the special section of the seamless line.

[0058] like Figure 2As shown, the displacement and temperature of the beam joint 18 composed of the rail 11 at the end of the high-pier long-span bridge, the continuous beam 11 and the simply supported beam 13 are monitored and collected. The temperature of the beam top plate 15, the beam web 16 and the waist of the rail 11 are monitored and collected. Figure 3 As shown, the temperature of 50m, 40m, 30m, 20m, 10m, 8m, 6m, 4m, 2m, 0m and the beam end in the bridge-tunnel transition section is monitored and collected. The longitudinal displacement of the rails at the beam end 21, the tunnel entrance, 25m in the tunnel and 50m in the tunnel in the bridge-tunnel transition section is monitored and collected. Figure 4 As shown, the lateral displacement of the rail 11 within the 6m range of the bridge-tunnel transition section is monitored. Figure 6 As shown, the displacement changes of the tip of the turnout point rail 32 relative to the basic rail 31 and the tip of the heart rail 37 relative to the wing rail 36 are monitored and collected, the basic displacement at the front of the turnout and the stopper 34 is monitored and collected, and the displacement of the basic rail 31 near the guard rail 35 is monitored. A measuring point is arranged about every 10 sleepers in front of the turnout, and 2 measuring points are added near the switch 33, for a total of 3 measuring points. A measuring point is set every 10 sleepers on the turnout heart rail 37, and a total of 2 measuring points are arranged, then a total of 5 temperature force measuring points are arranged, and all measuring points monitor the waist temperature of the rail 11. In this embodiment, only some key feature points of the seamless line need to be monitored and collected, which reduces the on-site point arrangement, saves the on-site monitoring cost, and adopts long-distance non-destructive monitoring to reduce the safety hazards of on-site monitoring.

[0059] S3. Establish a finite element simulation model to calculate the temperature, displacement and additional longitudinal force of the rail in special sections.

[0060] Establish a seamless line model for high-pier and long-span bridges. Based on the principle of interaction between beams, rails and bridges, a one-bridge-one-pier lightweight calculation model for seamless lines is established to calculate the seamless longitudinal forces on high-pier and long-span bridges. The model is solved using the nonlinear finite element method to calculate the mechanical characteristics of the seamless line of high-pier and long-span bridges under different working conditions. The rails are simulated using beam units; the fasteners are simulated using nonlinear spring units; the parameters are taken according to the current specifications or measured results; the beam body and bridge piers are simulated using beam units, the beam body and pier top share a common node, the foundation at the bottom of the pier is simulated using node elastic support, and the rest is simulated using solid units.

[0061] Establish a seamless track model for the bridge-tunnel transition section. Based on the principle of beam-rail interaction, establish a lightweight analysis model of the track-substructure in the bridge-tunnel connection area, solve the model using the nonlinear finite element method, and calculate the mechanical properties of the seamless track of the bridge-tunnel transition section under different working conditions. The rails are simulated using beam units, and the nonlinear constraint parameters of the longitudinal resistance of the fasteners and the longitudinal resistance of the ballast are taken in accordance with the current specifications or measured results; the tunnel entity unit only simulates the tunnel lining, and the simulation length is taken as 20-50m according to the on-site conditions, and the rest is simulated using entity units; such as Figure 5As shown in the figure, the alternating changes of heating and cooling and the temperature gradient are taken into account during the calculation. The temperature load of the bridge-tunnel transition section can be equivalently converted into the distributed force q on the central axis of the rail:

[0062]

[0063] Among them, E is the elastic modulus of the rail, A is the cross-sectional area of ​​the rail, α is the linear expansion coefficient of the rail, ΔT is the temperature difference between the inner and outer rails of the tunnel, that is, T1-T0, L is the length of the rail temperature transition zone, and t is time.

[0064] Establish a seamless turnout model. According to the principle of beam-rail interaction, a lightweight analysis model of the track-substructure in the turnout area is established, and the model is solved using the nonlinear finite element method. The rails are simulated using beam units, and the fasteners in the turnout area are simulated using nonlinear units. The longitudinal and transverse resistance and vertical stiffness of the fasteners are fully considered, and the parameters are taken according to the current specifications or measured results; the longitudinal and transverse resistance of the ballast bed is simulated using nonlinear spring units, and the vertical stiffness of the ballast bed is simulated using vertical springs. The track plate and base plate of the ballastless track are simulated using spatial plate units; the limiter and the spacer iron structure are simulated using nonlinear spring units, and the rest are simulated using solid units.

[0065] S4: Establish a mapping model to obtain a mapping relationship between the physical database and the virtual database. The data in the physical database is the physical data collected by the sensor in S2, and the data in the virtual database is the virtual data calculated by S3.

[0066] Using the physical database as input and the virtual database as output, a neural network model of physical data and virtual data of a special section of seamless railway under multiple working conditions is constructed and trained. The training data of the neural network model is the physical data set of N sensor collection points in the physical database and the M corresponding virtual data sets in the virtual database calculated by the finite element simulation model. The mapping model is trained based on the physical data set and the virtual data set. Figure 7 As shown, in a specific embodiment, N is 4 and M is 7.

[0067] A CNN-Bi-GRU-GWO neural network model based on adaptive hyperparameters is constructed to connect the physical database and the virtual database. The neural network model contains four layers of networks: the first layer of the network is the input layer, which extracts features from the one-dimensional time series data through the CNN network; the second layer of the network is the Bi-GRU time series network layer, which takes the feature extraction data of the previous layer of CNN as input and further extracts features on the time scale; the third layer of the network is the neural network hyperparameter optimization layer, which adaptively optimizes the hyperparameters of the CNN network and the Bi-GRU time series network; the fourth layer of the network is the output layer, which is constructed for training and optimization, and the mean square error is used as the objective function of the model. The model is trained by minimizing the mean square error. The expression of the mean square error function is as follows:

[0068]

[0069] Where n is the total number of data points, P i is the i-th predicted value, A i is the ith actual value.

[0070] S5. Compare the mapped data with the data that did not participate in the establishment of the mapping model to verify the model.

[0071] S51. When constructing a mapping model, remove the test points that are common to the physical database and the virtual database, and remove a portion of the data with a common data type, and exclude the portion from participating in the construction of the mapping model, and only use it for the verification of the mapping model. Figure 7 As shown, in a specific embodiment, 20% of the data does not participate in the construction of the mapping model and is only used for model verification. The physical database test point coordinates actually used to build the mapping model are W1, W2, W3, and W5, and the test point coordinates actually used to build the virtual database of the mapping model are X1, X2, X3, and X5. W4 and X4 are only used for model verification.

[0072] S52, using the physical data of the removed points in the physical database to calculate the virtual data corresponding to the removed points through the mapping model. Figure 7 The temperature and displacement data of the physical data coordinate points W1, W2, W3, and W5 are used to calculate the temperature, displacement, and additional longitudinal force of the rail at the virtual coordinate points X1, X2, X3, and X5 through a mapping model.

[0073] S53, comparing the calculated virtual data with the physical data of the point. Figure 7 The temperature and displacement data of the virtual coordinate point X4 are calculated through the mapping model using the temperature and displacement data of the physical data coordinate points W1, W2, W3, and W5, and compared and verified with the actually measured temperature and displacement data of the physical data coordinate point W4.

[0074] S54, judging the virtual data output by the mapping model, if the error between the virtual data and the physical data corresponding to the point is within a controllable range (not exceeding 5 in this embodiment), the mapping model is verified; if the error is outside the controllable range, the parameters of the mapping model are corrected and optimized.

[0075] S6. Rendering is done on the Unity3D platform to build a digital twin virtual body that is completely equivalent to the special section of the seamless line, and interact with the on-site seamless line through the digital twin virtual body. By controlling the digital twin virtual body, parameters including fastener resistance, ballast resistance, ambient temperature, locked rail temperature, and live load of the train are changed; indicators of the seamless line including rail temperature, creeping amount, and longitudinal additional force of the rail are checked and calculated through the mapping model, and a maintenance plan that meets the requirements of the specification is formulated. After the seamless line is maintained and repaired, the seamless line is collected and fed back with data from the seamless line and the digital twin virtual body of the seamless line is interactively verified.

[0076] The above shows and describes the basic principles, main features and advantages of the present invention. It should be understood by those skilled in the art that the present invention is not limited to the above embodiments. The above embodiments and descriptions are only for explaining the principles of the present invention. Without departing from the spirit and scope of the present invention, the present invention may have various changes and improvements, which fall within the scope of the present invention. The scope of protection of the present invention is defined by the attached claims and their equivalents.

Claims

1. A method for monitoring the longitudinal action of a seamless line based on digital twins, characterized in that: The following steps are involved: S1. Establish the special section type of the seamless line on site; S2, using temperature sensors and displacement sensors to collect feature point data; S3. Establish a finite element simulation model to calculate the temperature, displacement and additional longitudinal force of the rail in special sections; S4. Establish a mapping model to obtain a mapping relationship from a physical database to a virtual database; S5, comparing the mapped data with the data that did not participate in the establishment of the mapping model to verify the model; S6. Through 3D rendering, a digital twin virtual body that is exactly the same as the special section of the seamless line is constructed, and it interacts with the on-site seamless line.

2. The method for monitoring the longitudinal action of a seamless railway based on digital twin according to claim 1 is characterized in that: The special sections of the seamless track in S1 include high-pier long-span bridges, bridge-tunnel transition sections and seamless turnouts.

3. The method for monitoring the longitudinal action of a seamless railway based on digital twin according to claim 2 is characterized in that: The feature point data in S2 includes: Displacement and temperature of rails at the ends of high-pier and long-span bridges, displacement and temperature of beam joints; Rail displacement and rail temperature at the end of the first span of the simply supported beam at the entrance of the bridge-tunnel transition section, and rail displacement and rail temperature at each section of the temperature transition zone; The displacement changes of the tip of the seamless turnout point rail relative to the stock rail, the displacement changes of the tip of the heart rail relative to the wing rail, the displacement in front of the turnout and at the limiter, and the stock rail displacement near the guardrail.

4. The method for monitoring the longitudinal action of a seamless railway based on digital twin according to claim 3 is characterized in that: The S3 comprises the following steps: A seamless track model for high-pier and long-span bridges was established. Based on the principle of beam-rail-bridge interaction, a one-bridge-one-pier lightweight calculation model for seamless track was established to calculate the seamless longitudinal force on high-pier and long-span bridges. The model was solved using the nonlinear finite element method to calculate the mechanical characteristics of the seamless track of high-pier and long-span bridges under different working conditions. A seamless track model for the bridge-tunnel transition section was established. Based on the beam-track interaction principle, a lightweight analysis model of the track-substructure in the bridge-tunnel area was established. The model was solved using the nonlinear finite element method to calculate the mechanical characteristics of the seamless track for the bridge-tunnel transition section under different working conditions. A seamless turnout model is established. Based on the principle of beam-rail interaction, a lightweight analysis model of the track-substructure in the turnout area is established, and the model is solved using the nonlinear finite element method.

5. The method for monitoring the longitudinal action of a seamless railway based on digital twin according to claim 4 is characterized in that: The data in the physical database in S4 are the physical data collected by the sensor in S2, and the data in the virtual database are the virtual data calculated by S3.

6. The method for monitoring the longitudinal action of a seamless railway based on digital twin according to claim 5 is characterized in that: The establishment of the mapping model comprises the following steps: Using the physical database as input and the virtual database as output, a neural network model of physical data and virtual data of a special section seamless line under multiple working conditions is constructed and trained. The training data of the neural network model are the physical data sets of N sensor acquisition points in the physical database and the M corresponding virtual data sets in the virtual database calculated by the finite element simulation model. The mapping model is trained based on the physical data sets and the virtual data sets.

7. The method for monitoring the longitudinal action of a seamless railway based on digital twin according to claim 6 is characterized in that: The neural network model is a CNN-Bi-GRU-GWO neural network model with adaptive hyperparameters, and the neural network model includes a four-layer network: The first layer of the network is the input layer, which extracts features from one-dimensional time series data through the CNN network; The second layer of the network is the Bi-GRU temporal network layer, which takes the feature extraction data of the previous layer of CNN as input and further extracts features on a time scale; The third network layer is the neural network hyperparameter optimization layer, which adaptively optimizes the hyperparameters of the CNN network and the Bi-GRU timing network; The fourth network layer is the output layer, which is constructed for training and optimization, and the mean square error is used as the objective function of the model. The model is trained by minimizing the mean square error.

8. The method for monitoring the longitudinal action of a seamless railway based on digital twin according to claim 7 is characterized in that: The S5 comprises the following steps: S51. When constructing a mapping model, remove the test points that are common to the physical database and the virtual database, and a portion of the data with a common data type, and propose that the portion does not participate in the construction of the mapping model and is only used for the verification of the mapping model; S52, calculating virtual data corresponding to the removed points by using a mapping model for the physical data of the removed points in the physical database; S53, comparing the calculated virtual data with the physical data of the point; S54, judging the virtual data output by the mapping model, if the error between the virtual data and the physical data corresponding to the point is within a controllable range, the mapping model is verified, if the error is outside the controllable range, the parameters of the mapping model are corrected and optimized.

9. The method for monitoring the longitudinal action of a seamless railway based on digital twin according to claim 8 is characterized in that: The S6 comprises the following steps: By controlling the digital twin virtual body, parameters including fastener resistance, roadbed resistance, ambient temperature, locked rail temperature and train live load can be changed; Through the mapping model, the indicators of seamless railway, including rail temperature, creep, and rail longitudinal additional force, are checked and calculated, and a maintenance plan that meets the requirements of the regulations is formulated; After maintenance and repair of the seamless line, data feedback collected from the seamless line is interactively verified with the seamless line digital twin virtual body.

Images