Railway bridge parameter dynamic identification and evaluation method, device, equipment and storage medium

Abstract

The present invention relates to the field of railway bridge structure and sensor monitoring technology, and in particular to a method, device, equipment and storage medium for dynamic identification and evaluation of railway bridge parameters, including obtaining the long-gauge strain response of a high-speed train passing through a railway simply supported beam bridge by using a long-gauge strain sensor, and solving the selected sample data to obtain a long-gauge strain time-history curve, and then solving the area enclosed by the long-gauge strain time-history curves of all long-gauge sensors, with the peak value and spacing as parameters to be identified, and by establishing a coupled vibration model, numerical simulation is performed with a sufficient amount of different railway operating parameters to obtain a sample library and use it to train a neural network, and the railway operating parameters can be obtained by substituting the parameters to be identified. The present invention can realize the rapid identification of train operating parameters on the upper part of the railway bridge without affecting the operating traffic, greatly improving the monitoring efficiency.

Description

Technical Field

[0001] The present invention relates to the field of railway bridge structure and sensor monitoring technology, and in particular to a railway bridge parameter dynamic identification and evaluation method, device, equipment and storage medium. Background Art

[0002] High-speed railway bridges play an important role in the transportation system. While providing people with safe, comfortable and convenient travel conditions, due to the continuous load of high-speed trains and the damage of the external environment, as well as the continuous degradation of the bridge's own material properties, the bridge structure will be damaged to varying degrees, resulting in its actual service life being far less than the designed service life. Therefore, it is particularly urgent to carry out health monitoring research on existing high-speed railway bridges. Maintaining the health of bridges is crucial to the safe operation of high-speed trains.

[0003] Based on this, most of the existing technologies implement health monitoring of bridges by testing bridge vibration, displacement, and strain. This method is usually used for large-span bridges. Due to the high installation and maintenance costs of the health monitoring system, there is less research on small and medium-span bridges, and railway bridges are mainly small and medium-span. Compared with highway bridges, the loads borne by railway bridges are mainly characterized by fixed load positions, wheelbases and vehicle speeds that remain at the same level for a long time, and large axle weights. Based on these characteristics, timely knowing the actual load acting on the structure can provide a more intuitive and real understanding of the working status of the bridge. It is also possible to make timely analysis and evaluation of the bearing capacity of the bridge and the flatness of the track based on the characteristics of the load through experience or design specifications. In addition, for complex multi-parameter problems, since it is impossible to establish an ideal mathematical model, but the parameters measured by the sensor clearly contain information on the railway operation parameters, combined with the powerful ability of the BP neural network to solve nonlinear mapping problems, it is possible to identify the railway operation parameters from the obtained parameters. From the use of sensors, it can be found that since traditional strain sensors are "point" measurements, the measurement range is too local and cannot obtain the strain of the complete structure, especially for long-span structures such as bridges. It is obviously unrealistic to cover them with strain gauges. Therefore, a dynamic identification and evaluation method, device, equipment and storage medium for railway bridge parameters are urgently needed to solve the above problems. Summary of the invention

[0004] The present invention aims to at least improve one of the technical problems existing in the prior art. To this end, the present invention proposes a method, device, equipment and storage medium for dynamic identification and evaluation of railway bridge parameters.

[0005] A method for dynamic identification and evaluation of railway bridge parameters according to an embodiment of the first aspect of the present invention is characterized by comprising:

[0006] Step S1, building a railway bridge parameter dynamic identification and evaluation scenario, and arranging a number of long-gauge strain sensors on the bridge to be monitored;

[0007] Step S2, collecting the long gauge length strain response of a train load passing through the bridge to be monitored to obtain long gauge length strain response data;

[0008] Step S3, solving the measured long gauge length strain response data, extracting the quasi-static long gauge length strain signal, obtaining the long gauge length strain time history curve, and further obtaining the long gauge length strain influence line of the railway bridge to be identified;

[0009] Step S4, solving the long gauge length strain time history area, peak value and spacing of the long gauge length sensor based on the long gauge length strain time history curve, thereby forming input layer data of the railway bridge operation parameters to be identified;

[0010] Step S5, establishing a train-track-bridge coupled vibration model, performing numerical simulation with a sufficient number of trains with different operating parameters, extracting the long gauge length strain time history curve of the bridge sensor position under each train load and obtaining the enclosed long gauge length strain time history area, vehicle speed, axle weight and wheel-rail contact force curve;

[0011] Step S6, using the simulated long gauge strain time history area, peak value and spacing as the input layer, and the vehicle speed, axle load, and wheel-rail contact force curve as the output layer to establish a neural network model and perform training to obtain a trained neural network model;

[0012] Step S7, the long gauge strain time history area, peak value and spacing of the railway bridge to be identified are substituted into the trained neural network model as the input layer to identify the vehicle speed, axle load and wheel-rail contact force curve;

[0013] Step S8, analyzing the long gauge strain influence line of the railway bridge to be identified, substituting it into the trained neural network model to identify the railway operation parameters, and completing the dynamic identification and evaluation process of the railway bridge parameters.

[0014] According to the method for dynamic identification and evaluation of railway bridge parameters of an embodiment of the present invention, a long-gauge strain sensor is used to obtain the long-gauge strain response of a high-speed train passing through a railway simply supported beam bridge, and the selected sample data is solved to obtain a long-gauge strain time-history curve, and then the area enclosed by the long-gauge strain time-history curves of all long-gauge sensors is solved, and the peak value and spacing are used as parameters to be identified. By establishing a train-track-bridge coupled vibration model, numerical simulation is performed with a sufficient amount of different railway operating parameters, a rich sample library is obtained and used to train a neural network, and then the parameters to be identified are substituted to obtain the railway operating parameters. The present invention can realize the rapid identification of train operating parameters on the upper part of the railway bridge without affecting the operating traffic, greatly improving the monitoring efficiency and providing a guarantee for the operational safety of the bridge.

[0015] In a possible implementation manner of the first aspect, the long gauge length sensor is a long gauge length fiber Bragg grating sensor, or

[0016] Compared with traditional point strain gauges, the long-gauge resistance strain sensor can complete the full-span layout of the bridge and realize the monitoring of the bridge strain influence line.

[0017] In a possible implementation of the first aspect, in step S6, a neural network model is established and trained with the long gauge length strain time history area, peak value and spacing as the input layer, and the train speed, axle weight and wheel-rail contact force curve as the output layer, specifically including:

[0018] The strain time history area of ​​each gauge sensor at the bottom of the bridge of the lth train is recorded as , the peak value is recorded as , the peak spacing is , the vehicle speed is , axle weight is The wheel-rail contact force curve is ,in , is the number of trains;

[0019] A training model is established through a single hidden layer neural network. The range of the number of hidden layer neurons is determined by an empirical formula. Then a BP network with a variable number of hidden layer neurons is designed. The training errors of various network structures are compared to obtain the most appropriate number of neurons. The empirical formula is as follows:

[0020] ,

[0021] in, is the number of neurons in the hidden layer, is the number of neurons in the input layer, is the number of neurons in the output layer, for The constant between

[0022] The number of neurons in the input layer and output layer of the neural network is directly determined by the input parameters and output parameters of the network. The input parameters of the input layer are , is the input data, and the output parameters of the output layer are , For output data.

[0023] In a possible implementation of the first aspect, in step S6, the input layer parameters are all or part of the data obtained by the long gauge length sensor analysis, and the output layer is all or part of the data of the railway operation parameters. All parameters can be trained at one time, or the network model of a single parameter can be trained separately in multiple times.

[0024] In a possible implementation manner of the first aspect, in step S6, when constructing a neural network for training a model, the neural network used includes a multi-layer feedforward network, and the transfer function used selects a logarithmic function or a tangent function between the input layer and the hidden layer, and selects a linear function between the hidden layer and the output layer, wherein:

[0025] The logarithmic function is: ;

[0026] The tangent function is: ;

[0027] The linear function is: .

[0028] In a possible implementation of the first aspect, in step S4, the long gauge length strain time history area is solved by directly integrating the area enclosed by the curve and the horizontal axis; the peak size is calculated based on the characteristics of the long gauge length strain time history curve, and the average value of multiple peaks is taken; the peak spacing is calculated by taking the maximum value of each adjacent peak as the reference point.

[0029] In a possible implementation manner of the first aspect, the railway bridge includes a concrete bridge or a steel bridge.

[0030] According to the railway bridge parameter dynamic identification and evaluation device of the second aspect of the present invention, the parameter dynamic identification and evaluation device comprises:

[0031] A collection module is used to collect the long-gauge strain response of a train load passing through the bridge to be monitored, and obtain the long-gauge strain response data;

[0032] The calculation module solves the measured long gauge strain response data, extracts the quasi-static long gauge strain signal, obtains the long gauge strain time history curve, and further obtains the long gauge strain influence line of the railway bridge to be identified; based on the long gauge strain time history curve, the long gauge strain time history area, peak value and spacing of the long gauge sensor are solved to form the input layer data of the operating parameters of the railway bridge to be identified;

[0033] Construct a module, establish a train-track-bridge coupled vibration model, perform numerical simulations with a sufficient number of trains with different operating parameters, extract the long gauge length strain time history curves at the bridge sensor position under each train load, and obtain the enclosed long gauge length strain time history area, vehicle speed, axle weight, and wheel-rail contact force curves;

[0034] The training module uses the simulated long gauge strain time history area, peak value and spacing as the input layer, and the vehicle speed, axle load and wheel-rail contact force curve as the output layer to establish a neural network model and train it to obtain a trained neural network model;

[0035] The identification module uses the long gauge strain time history area, peak value and spacing of the railway bridge to be identified as the input layer and substitutes it into the trained neural network model to identify the vehicle speed, axle weight and wheel-rail contact force curve;

[0036] The analysis output module analyzes the long gauge strain influence lines of the railway bridge to be identified, substitutes them into the trained neural network model to identify the railway operation parameters, and outputs the railway bridge operation parameters.

[0037] According to the railway bridge parameter dynamic identification and evaluation device of the third aspect embodiment of the present invention, the railway bridge parameter dynamic identification and evaluation device includes: a memory, a processor, and a railway bridge parameter dynamic identification and evaluation program stored in the memory and executable on the processor, wherein the railway bridge parameter dynamic identification and evaluation program implements the steps of the railway bridge parameter dynamic identification and evaluation method as described above when executed by the processor.

[0038] The storage medium according to the fourth aspect of the present invention, wherein the storage medium stores a railway bridge parameter dynamic identification and evaluation program,

[0039] When the railway bridge parameter dynamic identification and evaluation program is executed by the processor, the steps of the railway bridge parameter dynamic identification and evaluation method as described above are implemented.

[0040] Additional aspects and advantages of the present invention will be given in part in the following description and in part will be obvious from the following description, or will be learned through practice of the present invention. BRIEF DESCRIPTION OF THE DRAWINGS

[0041] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings required for use in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0042] Figure 1 is a flow chart of a method for dynamic identification and evaluation of railway bridge parameters according to an embodiment of the present invention;

[0043] Figure 2 is a schematic diagram of the arrangement position of the long gauge length sensor of the simply supported beam under the train load in the method for dynamic identification and evaluation of railway bridge parameters according to an embodiment of the present invention;

[0044] Figure 3 is a schematic diagram of a train-track-bridge finite element model in a method for dynamic identification and evaluation of railway bridge parameters according to an embodiment of the present invention;

[0045] Figure 4 yes Figure 3 A partial enlarged schematic diagram of the train-track-bridge finite element;

[0046] Figure 5 It is a schematic diagram of the coupling between rails, fasteners and track plate nodes;

[0047] Figure 6 is a train wheelbase diagram in a method for dynamic identification and evaluation of railway bridge parameters according to an embodiment of the present invention;

[0048] Figure 7 is a macro strain time history curve diagram of a long gauge length sensor in the method for dynamic identification and evaluation of railway bridge parameters according to an embodiment of the present invention;

[0049] Figure 8 is a wheel-rail contact force curve of a certain wheelset of a train obtained in the method for dynamic identification and evaluation of railway bridge parameters according to an embodiment of the present invention;

[0050] Fig. 9 is a comparison diagram of the wheel-rail contact force curve identified in the railway bridge parameter dynamic identification and evaluation method according to an embodiment of the present invention and the actual wheel-rail force curve;

[0051] Fig.10 It is the relative error between the wheel-rail contact force curve identified in the method for dynamic identification and evaluation of railway bridge parameters according to an embodiment of the present invention and the actual wheel-rail force curve. DETAILED DESCRIPTION

[0052] The embodiments of the present invention are described in detail below. The embodiments described with reference to the accompanying drawings are exemplary. It should be understood that the specific embodiments described herein are only used to explain the present application and are not used to limit the present application.

[0053] It should be noted that when an element is referred to as being "fixed to" another element, it may be directly on the other element or there may be an intermediate element. When an element is considered to be "connected to" another element, it may be directly connected to the other element or there may be an intermediate element at the same time.

[0054] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as those commonly understood by those skilled in the art to which the present invention belongs. The terms used herein in the specification of the present invention are only for the purpose of describing specific embodiments and are not intended to limit the present invention. The term "and / or" used herein includes any and all combinations of one or more of the related listed items.

[0055] The terms "first", "second", "third", etc. in the specification and claims of the present application and the drawings are used to distinguish different objects rather than to describe a specific order. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions. For example, a series of steps or units are included, or optionally, steps or units not listed are included, or optionally, other steps or units inherent to these processes, methods, products or devices are included.

[0056] Only the part relevant to the present application is shown in the accompanying drawings, but not all of the content. Before discussing the exemplary embodiments in more detail, it should be mentioned that some exemplary embodiments are described as processing or methods depicted as flow charts. Although the flow chart describes each operation (or step) as a sequential process, many of the operations therein can be implemented in parallel, concurrently or simultaneously. In addition, the order of each operation can be rearranged. When its operation is completed, the process can be terminated, but it can also have additional steps not included in the accompanying drawings. The process can correspond to a method, function, procedure, subroutine, subprogram, etc.

[0057] The terms "component", "module", "system", "unit", etc. used in this specification are used to represent computer-related entities, hardware, firmware, a combination of hardware and software, software, or software in execution. For example, a unit can be, but is not limited to, a process running on a processor, a processor, an object, an executable file, an execution thread, a program, and / or distributed between two or more computers. In addition, these units can be executed from various computer-readable media having various data structures stored thereon. Units can communicate through local and / or remote processes, for example, based on signals having one or more data packets (e.g., data from a second unit interacting with another unit in a local system, a distributed system, and / or a network. For example, the Internet interacts with other systems via signals).

[0058] Example 1

[0059] See also Figure 1 As shown, this embodiment provides a method for dynamic identification and evaluation of railway bridge parameters, which is characterized by comprising:

[0060] Step S1, building a railway bridge parameter dynamic identification and evaluation scenario, and arranging a number of long-gauge strain sensors on the bridge to be monitored;

[0061] Step S2, collecting the long gauge length strain response of a train load passing through the bridge to be monitored to obtain long gauge length strain response data;

[0062] Step S3, solving the measured long gauge length strain response data, extracting the quasi-static long gauge length strain signal, obtaining the long gauge length strain time history curve, and further obtaining the long gauge length strain influence line of the railway bridge to be identified;

[0063] Step S4, solving the long gauge length strain time history area, peak value and spacing of all long gauge length sensors based on the long gauge length strain time history curve, thereby forming input layer data of the railway bridge operation parameters to be identified;

[0064] Step S5, establishing a train-track-bridge coupled vibration model, performing numerical simulation with sufficient trains with different operating parameters, extracting the long gauge length strain time history curve of the bridge sensor position under each train load, and obtaining the enclosed long gauge length strain time history area, vehicle speed, axle weight, wheel-rail contact force curve and other train operating parameters, solving the problem that the train load parameters cannot be obtained to form a complete sample in actual situations;

[0065] Step S6, using the simulated long gauge strain time history area, peak value and spacing as the input layer, and the vehicle speed, axle load, and wheel-rail contact force curve as the output layer to establish a neural network model and perform training to obtain a trained neural network model;

[0066] Step S7, the long gauge strain time history area, peak value and spacing of the railway bridge to be identified are substituted into the trained neural network model as the input layer to identify the vehicle speed, axle load and wheel-rail contact force curve;

[0067] Step S8, analyzing the long gauge strain influence line of the railway bridge to be identified, substituting it into the trained neural network model to identify the railway operation parameters, and completing the dynamic identification and evaluation process of the railway bridge parameters.

[0068] According to the method for dynamic identification and evaluation of railway bridge parameters of an embodiment of the present invention, a long-gauge strain sensor is used to obtain the long-gauge strain response of a high-speed train passing through a railway simply supported beam bridge, and the selected sample data is solved to obtain a long-gauge strain time-history curve, and then the area enclosed by the long-gauge strain time-history curves of all long-gauge sensors is solved, and the peak value and spacing are used as parameters to be identified. By establishing a train-track-bridge coupled vibration model, numerical simulation is performed with a sufficient amount of different railway operating parameters, a rich sample library is obtained and used to train a neural network, and then the parameters to be identified are substituted to obtain the railway operating parameters. The present invention can realize the rapid identification of train operating parameters on the upper part of the railway bridge without affecting the operating traffic, greatly improving the monitoring efficiency and providing a guarantee for the operational safety of the bridge.

[0069] Optionally, the railway bridge includes a concrete bridge or a steel bridge, a prestressed bridge and a non-prestressed bridge.

[0070] It should be noted that the long gauge length sensor is a long gauge length fiber Bragg grating sensor, or

[0071] Compared with traditional point strain gauges, the long-gauge resistance strain sensor can complete the full-span layout of the bridge and realize the monitoring of the bridge strain influence line.

[0072] It should be noted that in step S2, the long gauge strain response of the train load after passing through the measured bridge needs to be collected; the train load can be any train load, including high-speed trains, ordinary railway passenger cars, railway freight cars, etc., and no skylight time operation is required.

[0073] It should be noted that in step S6, the long gauge strain time history area, peak value and spacing are used as the input layer, and the train speed, axle load and wheel-rail contact force curve are used as the output layer to establish a neural network model and perform training, which specifically includes:

[0074] The strain time history area of ​​each gauge sensor at the bottom of the bridge of the lth train is recorded as , the peak value is recorded as , the peak spacing is , the vehicle speed is , axle weight is The wheel-rail contact force curve is ,in , is the number of trains;

[0075] A training model is established through a single hidden layer BP neural network. The approximate range of the number of hidden layer neurons is determined through an empirical formula. Then a BP network with a variable number of hidden layer neurons is designed through program code. The training errors of various network structures are compared to obtain the most appropriate number of neurons. The empirical formula is as follows:

[0076] ,

[0077] in, is the number of neurons in the hidden layer, is the number of neurons in the input layer, is the number of neurons in the output layer, for The constant between

[0078] The number of neurons in the input layer and output layer of the neural network is directly determined by the input parameters and output parameters of the network. The input parameters of the input layer are , is the input data, and the output parameters of the output layer are , For output data.

[0079] It should be noted that in step S6, the input layer parameters are all or part of the data obtained by the long gauge length sensor analysis, and the output layer is all or part of the data of the railway operation parameters. All parameters can be trained at one time, or the network model of a single parameter can be trained separately in multiple times.

[0080] It should be noted that in step S6, when constructing a neural network for training a model, the neural network used is not limited to the BP neural network, and includes other code toolboxes for deep learning. The transfer function used selects a logarithmic function or a tangent function between the input layer and the hidden layer, and selects a linear function between the hidden layer and the output layer, where:

[0081] The logarithmic function is: ;

[0082] The tangent function is: ;

[0083] The linear function is: .

[0084] It should be noted that the railway bridge includes a concrete bridge or a steel bridge.

[0085] This embodiment is mainly based on the characteristics that long gauge strain time history curves contain obvious train operation parameter information, combined with the powerful ability of BP neural network to solve nonlinear mapping problems. On this basis, a railway operation parameter identification method based on long gauge sensor is developed, which is explained below with reference to specific examples.

[0086] like Figure 2 The figure shows a simply supported high-speed railway bridge, a double-track bridge with a total beam length of L , the stiffness of the whole beam is EI , assuming that the middle of the bottom of the beam is filled with n The gauge length is le Long gauge length sensor. The strain time history area of ​​each gauge length sensor at the bottom of the bridge of the first train is recorded as , the peak value is recorded as , the peak spacing is , the vehicle speed is , axle weight is The wheel-rail contact force curve is ,in , is the number of trains.

[0087] The long gauge length strain time history area is calculated by direct integration of the area enclosed by the curve and the horizontal axis; the peak value is calculated by taking the average value of multiple peaks according to the characteristics of the long gauge length strain time history curve; the peak spacing is calculated by taking the maximum value of each adjacent peak as the reference point.

[0088] The principle of BP neural network is the fastest gradient descent method, that is, through a large number of sample training, the connection weights of the hidden layer in the network are continuously adjusted to continuously make the actual value close to the expected value to minimize the overall error. The entire algorithm consists of two basic propagation processes: forward propagation and back propagation. In forward propagation, the input signal first enters the network structure from the input layer, is processed step by step by the hidden layer and transmitted to the output layer, and the error between the expected value and the output value is compared. If the error requirement is not met, the error signal is returned along the original connection channel in the back propagation, and the error signal is minimized by modifying the weights of neurons in each layer.

[0089] The sample set in the database is used to train the BP neural network, and the test set is used to test the trained network structure and obtain the error of this network. Then, the network structure with the smallest error is selected as the final network structure, and finally the verification set is used to verify the accuracy of the network structure.

[0090] The refined train-track-bridge coupled vibration model in the present invention is the basis for calculating the sample data set. The bridge vibration response obtained by simulating a high-speed train crossing a bridge and measuring it on site can be used as sample data.

[0091] like Figure 3 and Figure 4 As shown, Figure 4A is the rail, B is the track slab, C is the cement asphalt mortar layer (CA mortar layer), D is the concrete base plate, E is the main beam, and F is the node coupling diagram of the rail and the track slab. The present invention establishes a 32-meter span track-bridge model, on which a CRTSⅡ slab ballastless track is laid, and the rail is a 60kg / m hot-rolled rail conventionally used in high-speed railways. The BEAM188 beam unit based on Timoshenko beam theory is used to simulate the rails and main beams. The commonly used fasteners for CRTSⅡ slab ballastless track on high-speed railways are WJ-8 type, with a fastener spacing of 0.6 meters, and are simulated using COMBIN14 linear elastic spring-damper units. The track slab, CA mortar layer, concrete base plate, bridge beam, etc. are simulated using BEAM188 units, and the model is established by assigning the unit combined cross-section, such as Figure 5 As shown. This model simulates the connection between the rail and the track plate as a narrow rigid strip bridge model. The global coordinate system is xyz, and the local coordinate system of the corresponding rail unit is defined as uvw. Since the rail unit has the x-axis rotational freedom around the yoz axis perpendicular to the beam plane and the z-axis rotational freedom around the xoy axis perpendicular to the beam plane, and the fastener spring-damper COMBIN14 unit has no rotational freedom, it cannot form a rotational constraint on the rail beam unit, and therefore does not conform to the actual connection relationship between the rail, fastener, and track plate, as shown in Figure 5 To this end, the constraint equation between the rail beam unit node and the fastener spring-damper is established to constrain the redundant degrees of freedom of the rail beam unit.

[0092] Angular displacement of rail beam unit node i around the X direction It has no effect on the x-direction displacement at the nodes of the j-1, j, and j+1 fastener spring units. The angular displacement of the beam unit node i around the x-direction The y-direction displacement at the node of the j-1th fastener spring unit is affected by:

[0093]

[0094] in: is the z-coordinate of node i, is the z-coordinate of node i-1, is the angular displacement of node i around the X direction, h is the distance between the rail beam unit node and the fastener spring unit node, l is the fastener distance.

[0095] Similarly, the angular displacement of rail beam unit i around the X direction is The z-direction displacement at the node of the j+1th fastener spring unit is affected by:

[0096]

[0097] in: is the z-coordinate of node i, is the z-coordinate of node i+1, is the angular displacement of node i around the X direction, h is the distance between the rail beam unit node and the fastener spring unit node, l is the fastener distance.

[0098] Similarly, the influence of the rotational angular displacement rotz of the rail beam unit i around the Z direction on the x- and y-direction displacements at the nodes of the j-1, j, and j+1 fastener spring units is approximately 0. The rotational angular displacement rotz of the beam unit i around the Z direction has no influence on the z-direction displacement at the nodes of the j-1, j, and j+1 fastener spring units. In this way, the y-direction displacement constraint equation is:

[0099]

[0100] in: is the vertical displacement of the fastener spring unit node, is the vertical displacement of the rail beam unit node, is the rotational angular displacement of the i-1 node of the rail beam unit around the X direction, is the rotational angular displacement of the i+1 node of the rail beam unit around the X direction, l is the fastener distance.

[0101] The x and z displacements of the fastener spring unit nodes are determined by the displacements on the bottom surface of the beam unit to which they are connected. The displacement constraint equation is approximately as follows:

[0102]

[0103]

[0104] in: is the lateral displacement of the fastener spring unit node, is the lateral displacement of the rail beam unit node, is the longitudinal displacement of the fastener spring unit node, is the longitudinal displacement of the rail beam unit node.

[0105] The train model is based on the CRH3 EMU. Figure 6As shown, in the modeling of the present invention, it is simplified to a 10-DOF vehicle model, and the train body, bogie and wheel are simulated by MASS21 units. Taking into account the degrees of freedom of each component, the body and bogie mass units are set to have rotational inertia, and the wheel mass unit has no rotational inertia. The vertical connection between the components is simulated by COMBIN14 linear elastic spring-damper unit, and the longitudinal connection is simulated by BEAM4 unit.

[0106] After the model is established, the solution phase begins. The mass unit parameters of the train, the time step during solution, and the train movement distance are set according to the axle weight and speed of the train to be simulated. After the solution, the post-processing phase begins. The wheel-rail contact force, axle weight, speed, and macro-strain time history curves under train load are extracted to establish a data set. The extracted macro-strain time history curves are shown in Figure 1. Figure 7 The wheel-rail contact force curve is shown in Figure 8 shown.

[0107] The comparison between the identified value and the true value after the input layer parameterization is input into the BP network is as follows: Fig. 9 As shown. Fig.10 It can be seen that the relative error of the trained neural network structure in identifying the wheel-rail force curve is less than 5%, and the effect is significant.

[0108] Example 2

[0109] This embodiment provides a railway bridge parameter dynamic identification and evaluation device, wherein the parameter dynamic identification and evaluation device includes:

[0110] A collection module is used to collect the long-gauge strain response of a train load passing through the bridge to be monitored, and obtain the long-gauge strain response data;

[0111] The calculation module solves the measured long-gauge strain response data, extracts the quasi-static long-gauge strain signal, obtains the long-gauge strain time-history curve, and further obtains the long-gauge strain influence line of the railway bridge to be identified; based on the long-gauge strain time-history curve, the long-gauge strain time-history area, peak value and spacing of all long-gauge sensors are solved to form the input layer data of the operating parameters of the railway bridge to be identified;

[0112] Construct a module, establish a train-track-bridge coupled vibration model, perform numerical simulations with a sufficient number of trains with different operating parameters, extract the long gauge length strain time history curves at the bridge sensor position under each train load, and obtain the enclosed long gauge length strain time history area, vehicle speed, axle weight, wheel-rail contact force curve and other train operating parameters;

[0113] The training module uses the simulated long gauge strain time history area, peak value and spacing as the input layer, and the vehicle speed, axle load and wheel-rail contact force curve as the output layer to establish a neural network model and train it to obtain a trained neural network model;

[0114] The identification module uses the long gauge strain time history area, peak value and spacing of the railway bridge to be identified as the input layer and substitutes it into the trained neural network model to identify the vehicle speed, axle weight and wheel-rail contact force curve;

[0115] The analysis output module analyzes the long gauge strain influence lines of the railway bridge to be identified, substitutes them into the trained neural network model to identify the railway operation parameters, and outputs the railway bridge operation parameters.

[0116] Example 3

[0117] The present embodiment provides a device for dynamically identifying and evaluating railway bridge parameters, wherein the device for dynamically identifying and evaluating railway bridge parameters comprises: a memory, a processor, and a program for dynamically identifying and evaluating railway bridge parameters stored in the memory and executable on the processor, wherein the program for dynamically identifying and evaluating railway bridge parameters implements the steps of the method for dynamically identifying and evaluating railway bridge parameters as described above when the program for dynamically identifying and evaluating railway bridge parameters is executed by the processor.

[0118] Example 4

[0119] This embodiment provides a storage medium, wherein the storage medium stores a railway bridge parameter dynamic identification and evaluation program.

[0120] When the railway bridge parameter dynamic identification and evaluation program is executed by the processor, the steps of the railway bridge parameter dynamic identification and evaluation method as described above are implemented.

[0121] In the description of the present invention, it is to be understood that the terms “center”, “longitudinal”, “lateral”, “length”, “width”, “thickness”, “up”, “down”, “front”, “back”, “left”, “right”, “vertical”, “horizontal”, “top”, “bottom”, “inside”, “outside”, “clockwise”, “counterclockwise”, “axial”, “radial”, “circumferential”, etc., indicating orientations or positional relationships based on the orientations or positional relationships shown in the accompanying drawings, are only for the convenience of describing the present invention and simplifying the description, and do not indicate or imply that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation, and therefore should not be understood as a limitation to the invention.

[0122] In the description of this specification, the description with reference to the terms "one embodiment", "some embodiments", "illustrative embodiments", "examples", "specific examples", or "some examples" means that the specific features, structures, materials, or characteristics described in conjunction with the embodiment or example are included in at least one embodiment or example of the present invention. In this specification, the schematic representation of the above terms does not necessarily refer to the same embodiment or example.

[0123] Obviously, the described embodiments are only a part of the embodiments of the present application, rather than all the embodiments. Mentioning "embodiment" in this article means that the specific features, structures or characteristics described in conjunction with the embodiment may be included in at least one embodiment of the present embodiment application. The appearance of this phrase in various positions in the specification is not necessarily the same embodiment, nor is it an independent or alternative embodiment that is mutually exclusive with other embodiments. It can be explicitly and implicitly understood by those skilled in the art that the embodiments described herein can be combined with other embodiments. Based on the embodiments in this application, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of this application.

[0124] Although the embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that various changes, modifications, substitutions and variations may be made to the embodiments without departing from the principles and spirit of the present invention, and that the scope of the present invention is defined by the claims and their equivalents.

Claims

1. A method for dynamic identification and evaluation of railway bridge parameters, characterized in that: include: Step S1, building a railway bridge parameter dynamic identification and evaluation scenario, and arranging a number of long-gauge strain sensors on the bridge to be monitored; Step S2, collecting the long gauge length strain response of a train load passing through the bridge to be monitored to obtain long gauge length strain response data; Step S3, solving the measured long gauge length strain response data, extracting the quasi-static long gauge length strain signal, obtaining the long gauge length strain time history curve, and further obtaining the long gauge length strain influence line of the railway bridge to be identified; Step S4, solving the long gauge length strain time history area, peak value and spacing of the long gauge length sensor based on the long gauge length strain time history curve, thereby forming input layer data of the railway bridge operation parameters to be identified; Step S5, establishing a train-track-bridge coupled vibration model, performing numerical simulation with a sufficient number of trains with different operating parameters, extracting the long gauge length strain time history curve of the bridge sensor position under each train load and obtaining the enclosed long gauge length strain time history area, vehicle speed, axle weight and wheel-rail contact force curve; Step S6, using the simulated long gauge strain time history area, peak value and spacing as the input layer, and the vehicle speed, axle load, and wheel-rail contact force curve as the output layer to establish a neural network model and perform training to obtain a trained neural network model; Among them, the strain time history area of ​​each gauge sensor at the bottom of the bridge of the lth train is recorded as , the peak value is recorded as , the peak spacing is , the vehicle speed is , axle weight is The wheel-rail contact force curve is ,in , is the number of trains; Step S7, substituting the long gauge strain time history area, peak value and spacing of the railway bridge to be identified as the input layer into the trained neural network model to identify the vehicle speed, axle weight and wheel-rail contact force curve; Step S8, analyzing the long gauge strain influence line of the railway bridge to be identified, substituting it into the trained neural network model to identify the railway operation parameters, and completing the dynamic identification and evaluation process of the railway bridge parameters.

2. The method for dynamic identification and evaluation of railway bridge parameters according to claim 1 is characterized in that: The long gauge length sensor is a long gauge length fiber grating sensor or a long gauge length resistance strain sensor.

3. The method for dynamic identification and evaluation of railway bridge parameters according to claim 1 is characterized in that: In step S6, the long gauge strain time history area, peak value and spacing are used as the input layer, and the train speed, axle load and wheel-rail contact force curve are used as the output layer to establish a neural network model and perform training, which specifically includes: A training model is established through a single hidden layer neural network. The range of the number of hidden layer neurons is determined by an empirical formula. Then a BP network with a variable number of hidden layer neurons is designed. The training errors of various network structures are compared to obtain the most appropriate number of neurons. The empirical formula is as follows: ， in, is the number of neurons in the hidden layer, is the number of neurons in the input layer, is the number of neurons in the output layer, for The constant between The number of neurons in the input layer and output layer of the neural network is directly determined by the input parameters and output parameters of the network. The input parameters of the input layer are , is the input data, and the output parameters of the output layer are , For output data.

4. The method for dynamic identification and evaluation of railway bridge parameters according to claim 1 is characterized in that: In step S6, the input layer parameters are all or part of the data obtained by the long gauge length sensor analysis, and the output layer is all or part of the data of the railway operation parameters. The network model of all parameters is trained at one time or a single parameter is trained separately for multiple times.

5. The method for dynamic identification and evaluation of railway bridge parameters according to claim 1 is characterized in that: In step S6, when constructing a neural network for training a model, the neural network used includes a multi-layer feedforward network, and the transfer function used selects a logarithmic function or a tangent function between the input layer and the hidden layer, and selects a linear function between the hidden layer and the output layer.

6. The method for dynamic identification and evaluation of railway bridge parameters according to claim 1 is characterized in that: In step S4, the long gauge length strain time history area is solved by directly integrating the area enclosed by the curve and the horizontal axis; the peak value is calculated by taking the average value of multiple peaks according to the characteristics of the long gauge length strain time history curve; the peak spacing is calculated by taking the maximum value of each adjacent peak as the reference point.

7. The method for dynamic identification and evaluation of railway bridge parameters according to claim 1 is characterized in that: The railway bridge includes a concrete bridge or a steel bridge.

8. A railway bridge parameter dynamic identification and evaluation device, characterized in that: The parameter dynamic identification and evaluation device comprises: A collection module is used to collect the long-gauge strain response of a train load passing through the bridge to be monitored, and obtain the long-gauge strain response data; The calculation module solves the measured long gauge strain response data, extracts the quasi-static long gauge strain signal, obtains the long gauge strain time history curve, and further obtains the long gauge strain influence line of the railway bridge to be identified; based on the long gauge strain time history curve, the long gauge strain time history area, peak value and spacing of the long gauge sensor are solved to form the input layer data of the operating parameters of the railway bridge to be identified; Construct a module, establish a train-track-bridge coupled vibration model, perform numerical simulations with a sufficient number of trains with different operating parameters, extract the long gauge length strain time history curves at the bridge sensor position under each train load, and obtain the enclosed long gauge length strain time history area, vehicle speed, axle weight, and wheel-rail contact force curves; The training module uses the simulated long gauge strain time history area, peak value and spacing as the input layer, and the vehicle speed, axle load and wheel-rail contact force curve as the output layer to establish a neural network model and train it to obtain a trained neural network model; The identification module uses the long gauge strain time history area, peak value and spacing of the railway bridge to be identified as the input layer and substitutes it into the trained neural network model to identify the vehicle speed, axle weight and wheel-rail contact force curve; The analysis output module analyzes the long gauge strain influence line of the railway bridge to be identified, substitutes it into the trained neural network model to identify the railway operation parameters, and outputs the railway bridge operation parameters.

9. A railway bridge parameter dynamic identification and evaluation device, characterized in that: The railway bridge parameter dynamic identification and evaluation device includes: a memory, a processor, and a railway bridge parameter dynamic identification and evaluation program stored in the memory and executable on the processor. When the railway bridge parameter dynamic identification and evaluation program is executed by the processor, the steps of the railway bridge parameter dynamic identification and evaluation method as described in any one of claims 1 to 7 are implemented.

10. A storage medium, characterized in that: The storage medium stores a railway bridge parameter dynamic identification and evaluation program. When the railway bridge parameter dynamic identification and evaluation program is executed by a processor, the steps of the railway bridge parameter dynamic identification and evaluation method as described in any one of claims 1 to 7 are implemented.

Images