Design and maintenance method, device and equipment for bridge joint and medium

Abstract

The invention provides a bridge joint design and maintenance method and device, equipment and a medium, and relates to the technical field of artificial intelligence, and the method comprises the steps: simulating the stress change of a joint in a future time period through a bridge joint model under different bridge parameters and joint parameters of a bridge; taking multiple groups of different bridge parameters as input data, and taking corresponding joint parameters and stress changes as output data to construct a sample data set; training the long and short-term memory network by using a sample data set to obtain a seam calculation model; inputting the bridge parameters of the to-be-jointed bridge into the joint calculation model to obtain the joint parameters of the to-be-jointed bridge and the stress change of the joint in the future time period; formulating a maintenance strategy of the joint according to the stress change of the joint in the future time period; the stress condition of the joint is monitored in real time, and when the stress of the joint exceeds a limit value, an early warning signal is sent; according to the method, joint parameters and future stress changes can be accurately predicted, so that an accurate joint design and maintenance strategy is realized.

Description

Technical Field

[0001] The present invention relates to the technical field of artificial intelligence, and more particularly, to a method, device, equipment and readable storage medium for the design and maintenance of bridge joints. Background Art

[0002] As a key functional component, bridge joints play an important role in absorbing the deformations of bridges caused by temperature differences, loads, and uneven settlement of the foundation. However, there are many problems in the traditional design of continuous bridge deck joints, mainly manifested in that the joints are vulnerable to temperature changes and vehicle loads, resulting in cracking and fatigue damage, thereby reducing the performance of the bridge. In addition, the traditional joints lack the ability of real-time monitoring, and the maintenance work relies on periodic manual inspections, making it difficult to detect potential risks in a timely manner, resulting in delayed maintenance or over-maintenance, and increasing the maintenance cost. Although the design of ECC concrete joints has made some progress in improving the joint performance, there are still deficiencies in meeting the long-term service requirements under the complex environment of bridges, especially the fatigue damage caused by temperature difference stress. The demand for intelligent, low-maintenance-cost and long-life modern bridges is increasing day by day, and the traditional design and maintenance mode can no longer meet the technical requirements of the new era. Summary of the Invention

[0003] The purpose of the present invention is to provide a method, device, equipment and readable storage medium for the design and maintenance of bridge joints to improve the above problems. To achieve the above purpose, the technical solutions adopted by the present invention are as follows:

[0004] In a first aspect, the present application provides a method for the design and maintenance of bridge joints, including:

[0005] Build a bridge joint model in finite element analysis software, and use the bridge joint model to simulate the force changes of the joint in the future period under different bridge parameters and joint parameters of the bridge;

[0006] Construct a sample data set with multiple groups of different bridge parameters as input data, and their corresponding joint parameters and force changes as output data;

[0007] Build a long short-term memory network, and use the sample data set to train and test the long short-term memory network to obtain a joint calculation model;

[0008] Obtain the bridge parameters of the bridge to be connected, input the bridge parameters of the bridge to be jointed into the joint calculation model, and calculate the joint parameters of the bridge to be connected and the force changes of the joint in the future period;

[0009] Formulate a maintenance strategy for the joint according to the force changes of the joint in the future period;

[0010] After applying the calculated joint parameters to the joint of the bridge to be connected, the stress condition of the joint is monitored in real time. When the stress of the joint exceeds the limit value, a warning signal is sent.

[0011] In a second aspect, the present application also provides a device for designing and maintaining a bridge joint, including:

[0012] Model building module: Build a bridge joint model in finite element analysis software, and use the bridge joint model to simulate the stress change of the joint in the future time period under different bridge parameters and joint parameters of the bridge.

[0013] Dataset construction module: Construct a sample dataset with multiple groups of different bridge parameters as input data, and their corresponding joint parameters and stress changes as output data.

[0014] Training module: Build a long short-term memory network, and use the sample dataset to train and test the long short-term memory network to obtain a joint calculation model.

[0015] Acquisition module: Acquire the bridge parameters of the bridge to be connected, input the bridge parameters of the bridge to be jointed into the joint calculation model, and calculate the joint parameters of the bridge to be connected and the stress change of the joint in the future time period.

[0016] Strategy formulation module: Formulate a maintenance strategy for the joint according to the stress change of the joint in the future time period.

[0017] Real-time monitoring module: After applying the calculated joint parameters to the joint of the bridge to be connected, the stress condition of the joint is monitored in real time. When the stress of the joint exceeds the limit value, a warning signal is sent.

[0018] In a third aspect, the present application also provides a device for designing and maintaining a bridge joint, including:

[0019] A memory for storing a computer program;

[0020] A processor for implementing the steps of the method for designing and maintaining a bridge joint when executing the computer program.

[0021] In a fourth aspect, the present application also provides a readable storage medium, on which a computer program is stored. When the computer program is executed by a processor, the steps of the above-mentioned method for designing and maintaining a bridge joint are implemented.

[0022] The beneficial effects of the present invention are:

[0023] The seam calculation model established by the LSTM network of the present invention can accurately predict seam parameters and future force changes, thereby realizing precise seam design and maintenance strategies. The present invention combines future early warning and real-time monitoring, which can not only perform phased maintenance throughout the life cycle of the bridge, optimize maintenance costs, and extend the service life of the seams, but also can monitor the stress changes of the bridge in real time, ensuring timely response when the force on the seams exceeds the limit value and avoiding structural damage. Through intelligent management, the bridge maintenance work becomes more efficient and scientific, reducing the work intensity of maintenance personnel while improving driving comfort and traffic efficiency.

[0024] Other features and advantages of the present invention will be described in the subsequent description, and part of them will become obvious from the description, or can be understood by implementing the embodiments of the present invention. The objectives and other advantages of the present invention can be achieved and obtained through the structures specifically pointed out in the written description, claims, and drawings. BRIEF DESCRIPTION OF THE DRAWINGS

[0025] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the following will briefly introduce the drawings required to be used in the embodiments. It should be understood that the following drawings only show some embodiments of the present invention, and therefore should not be regarded as a limitation of the scope. For those of ordinary skill in the art, other related drawings can be obtained based on these drawings without creative efforts.

[0026] Figure 1 It is a schematic flow chart of the design and maintenance method of the bridge seam described in the embodiments of the present invention;

[0027] Figure 2 It is a schematic diagram of the bridge seam model described in the embodiments of the present invention;

[0028] Figure 3 It is a schematic structural diagram of the device for the design and maintenance of the bridge seam described in the embodiments of the present invention;

[0029] Figure 4 It is a schematic structural diagram of the equipment for the design and maintenance of the bridge seam described in the embodiments of the present invention.

[0030] Reference signs in the drawings:

[0031] 01 - First bridge; 02 - Second bridge; 03 - Concrete;

[0032] 800, Equipment for the design and maintenance of the bridge seam; 801, Processor; 802, Memory; 803, Multimedia component; 804, I / O interface; 805, Communication component. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0033] To make the objectives, technical solutions and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are some, but not all, of the embodiments of the present invention. The components of the embodiments of the present invention described and illustrated herein generally may be arranged and designed in a variety of different configurations. Therefore, the following detailed description of the embodiments of the present invention provided in the drawings is not intended to limit the scope of the claimed invention, but is merely representative of selected embodiments of the present invention. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present invention without creative efforts fall within the scope of protection of the present invention.

[0034] It should be noted that like reference numerals and letters denote like items in the following drawings, and thus, once an item is defined in one drawing, it does not require further definition and explanation in subsequent drawings. At the same time, in the description of the present invention, the terms "first", "second", etc. are only used for descriptive distinction and cannot be construed as indicating or implying relative importance.

[0035] Embodiment 1:

[0036] This embodiment provides a method for designing and maintaining a bridge joint.

[0037] See Figure 1 , which shows that this method includes:

[0038] S1. Build a bridge joint model in finite element analysis software, and use the bridge joint model to simulate the stress change of the joint in the future time period under different bridge parameters and joint parameters of the bridge.

[0039] Specifically, step S1 includes:

[0040] S11. Build a bridge joint model in finite element analysis software. The bridge joint model includes two bridges with a joint. The bridge decks of the two bridges are on the same horizontal plane, and the joint between the two bridges is connected by concrete.

[0041] Specifically, as shown in the figure, Figure 2 includes the first bridge 01 and the second bridge 02, and the panels of the first bridge 01 and the second bridge 02 are jointed by concrete 03.

[0042] S12. Assign different bridge parameters and joint parameters to the bridge joint model, and use the finite element analysis software to calculate the stress time series data and strain time series data of the joint within a preset time period under different bridge parameters, joint parameters and temperature V.

[0043] Specifically, the bridge parameters include the bridge span L1 , bridge width B, bridge deck thickness H, and reinforcement parameter G;

[0044] The joint parameters include joint concrete thickness h, joint length L 2 , material strength f c (Compressive strength of ECC material);

[0045] The stress time series data of the joint within a preset time period can be expressed as s(t), where t = 1, 2, …, T, where T;

[0046] The strain time series data can be expressed as ∈(t);

[0047] Assign a set of bridge parameters, joint parameters, and temperature {L 1 , B, H, G, h, L 2 , f c , V} to the bridge joint model. The finite element analysis software simulates the entire life cycle of the bridge joint model until the stress or strain value of the bridge joint model reaches the maximum threshold. At this time, the stress time series data and strain time series data of the joint within the entire life cycle are output. Among them, if the stress reaches the corresponding maximum threshold first, then the strain stops generating, and the time period when the stress reaches the maximum threshold is used as the entire life cycle of the bridge joint model. The finite element analysis software generates stress time series data s(t) and strain time series data ∈(t) within the entire life cycle, where t = 1, 2, …, T, where t represents the time step, which can be divided according to actual needs, and T represents the entire life cycle.

[0048] Based on the above embodiments, the method further includes:

[0049] S2. Construct a sample data set with multiple groups of different bridge parameters as input data, their corresponding joint parameters, and force changes as output data;

[0050] Specifically, step S2 includes:

[0051] S21. Represent the stress time series data and strain time series data at each time step as an output vector;

[0052] S22. Use a set of bridge parameters and a preset temperature to form a set of input data. The stress time series data and strain time series data of the bridge parameters in all time steps form the first output data, and the joint parameters form the second output data;

[0053] Specifically, the input data is X = [L 1 , B, H, G, V], the first output data is The second output data is Y 1 = [h, L 2 , fc .

[0054] S23. Construct a sample data set from multiple groups of different input data and the corresponding first output data and second output data. Among them, divide the sample data set into a training set and a test set according to a ratio of 8:2;

[0055] Preferably, perform normalization processing on the sample data set:

[0056]

[0057] In the formula, μ X , σ X respectively represent the normalized value, mean value and standard deviation of the input data, respectively represent the normalized value, mean value and standard deviation of the first output data, respectively represent the normalized value, mean value and standard deviation of the second output data.

[0058] Based on the above embodiments, the method further includes:

[0059] S3. Build a long short-term memory network, and use the sample data set to train and test the long short-term memory network to obtain a seam calculation model;

[0060] Specifically, the step S3 includes:

[0061] S31. Build a long short-term memory network successively by an LSTM hidden layer, a fully connected layer and an output layer;

[0062] Specifically, the LSTM hidden layer includes two stacked LSTM units:

[0063] The first layer of LSTM unit: contains N 1 units, set return_sequences = True, and output the hidden state of each time step.

[0064] The second layer of LSTM unit: contains N 2 units, set return_sequences = False, and output the hidden state of the last time step.

[0065] The fully connected layer and the output layer include two layers:

[0066] The first layer of fully connected layer and the first output layer: map the output of the LSTM layer to the dimension of the first output data, that is, the characteristics of the stress time series data and the strain time series data, and then output the first output data through the corresponding output layer, that is, the time series changes of stress and strain;

[0067] The second fully connected layer and the second output layer: Map the output of the LSTM layer to the dimension of the second output data, that is, the features of the seam parameters, and then output the second output data, that is, the seam parameters, through the corresponding output layer.

[0068] S32. Input the sample data set into the LSTM hidden layer. After the LSTM hidden layer captures the features of the input data, it outputs the hidden state value to the fully connected layer;

[0069] Specifically, the LSTM hidden layer includes a forget gate, an input gate, and an output gate;

[0070] Among them, the forget gate is:

[0071] f t = Sigmoid(W f ·[h t-1 , x t +b f );

[0072] In the formula, x t is the input value, and f t represents the output vector of the forget gate, indicating the proportion of forgetting the memory of the previous moment. The value of each element is in the range of [0, 1]. When f t = 1, it means completely retaining the memory of the previous moment. When f t = 0, it means completely forgetting the memory of the previous moment; f t with a value between 0 and 1 indicates partial forgetting.

[0073] b f is the bias vector of the forget gate, used to adjust the initial output and flexibility during training. The initial value is the zero vector [0, 0,..., 0], and it is automatically updated during training through gradient descent.

[0074] W f represents the weight matrix of the forget gate, used to adjust the influence of the input data and the hidden state, and needs to be initialized. Random values are taken from the uniform distribution [-0.1, 0.1]. The random values are randomly generated by the code to avoid gradient explosion or gradient disappearance caused by too large initial weights.

[0075] Sigmoid() is the activation function, which maps the input value to the interval [0, 1].

[0076] h t-1 is the hidden state of the previous time step. At time step t = 0, the initial hidden state h 0 takes the all-zero vector [0, 0,..., 0]: The hidden state is updated with the time step and obtained through training.

[0077] Specifically, the input gate is:

[0078] i t = Sigmoid(W i ·[h t-1 , x t + b i );

[0079] In the formula, i t determines what proportion of the current candidate memory will be added to the candidate memory unit W i and b i represent the weight matrix and bias of the input gate;

[0080] Among them,

[0081] In the formula, W c and b c represent the weight matrix and bias of the candidate memory unit;

[0082] The update formula for the candidate memory unit is:

[0083]

[0084] In the formula, C t is the memory unit state at time step t, and f t is the output of the forget gate;

[0085] Specifically, the output gate is:

[0086] o t = Sigmoid(W 0 ·[h t-1 , x t + b 0 );

[0087] Among them, W i and b i represent the weight matrix and bias of the output gate.

[0088] S33. Map the hidden state value to the dimension of the output data by the fully connected layer, and generate the predicted output data which is then output by the output layer;

[0089] S34. Compare the predicted output data with the real first output data and second output data in the sample dataset, and calculate the loss function;

[0090] Specifically, use the mean squared error (MSE) as the loss function U 1 :

[0091]

[0092] In the formula, Represents the predicted value of the i-th sample, Y i Represents the true value of the i-th sample, and N represents the total number of samples.

[0093] S35. Iteratively update the parameters of the long short-term memory network using the loss function;

[0094] Preferably, the Adam optimizer is used, and its adaptive learning rate mechanism can quickly optimize the model parameters. The formula is as follows:

[0095]

[0096] In the formula, m t and m t-1 respectively represent the first-order momentum (weighted mean of gradients) at time step t and time step t-1, v t and v t-1 respectively represent the second-order momentum (weighted mean of gradient squares) at time step t and time step t-1. Among them, m 0 =0, v 0 =0; m and v are updated iteratively by exponential weighting. As the number of iterations increases, the contribution of historical gradients gradually accumulates, and finally the values of m and v will tend to be stable and will not depend on the initial values for a long time.

[0097] S36. Repeat training the updated long short-term memory network. When the loss function is less than the preset threshold, obtain the concrete parameter calculation model.

[0098] Based on the above embodiments, the method further includes:

[0099] S4. Obtain the bridge parameters of the bridge to be connected, input the bridge parameters of the bridge to be jointed into the joint calculation model, and calculate the joint parameters of the bridge to be connected and the force change of the joint in the future period;

[0100] Among them, the input data of the joint calculation model further includes the temperature V, where the temperature V is the average annual temperature in the past 20 years at the location of the bridge to be jointed

[0101] Based on the above embodiments, the method further includes:

[0102] S5. Develop a maintenance strategy for the joint according to the force change of the joint in the future period;

[0103] Specifically, the step S5 includes:

[0104] S51. Analyze the force change of the joint in the future period and calculate the comprehensive evaluation index of the joint in the future period;

[0105] Specifically, the calculation method of the comprehensive evaluation index is:

[0106]

[0107] Wherein, M(t) is the comprehensive evaluation index at the t time step, s(t) is the stress at the joint, s max is the maximum value of the material stress at the joint, ε(t) is the strain at the joint, ε max is the maximum value of the material strain at the joint, ω 1 is the weight of the stress, ω 2 is the weight of the strain.

[0108] S52. Divide the joint into four service stages according to the comprehensive evaluation index, specifically:

[0109]

[0110] S53. Develop corresponding maintenance measures for the four service stages respectively;

[0111] Specifically, the maintenance measure in the prevention stage is: check indicators such as cracks at the joint and repair the cracks.

[0112] The maintenance measure in the diagnosis stage is: use ultrasonic testing, infrared thermal imaging, etc. to check the internal state of the joint, repair the cracks and reinforce the joint structure.

[0113] The maintenance measure in the repair stage is: repair the damaged part of the joint, reapply the protective coating, replace the material, completely demolish and redesign the joint, and carry out large-scale reconstruction.

[0114] The maintenance measure in the emergency repair stage is: take emergency measures such as rapid reinforcement and local reinforcement of the joint to prevent the accident from expanding.

[0115] Based on the above embodiments, the method further includes:

[0116] S6. After applying the calculated joint parameters to the joint of the bridge to be connected, monitor the stress condition of the joint in real time, and send a warning signal when the stress of the joint exceeds the limit value.

[0117] Specifically, the step S6 includes:

[0118] S61. Obtain the joint temperature monitored by the temperature sensor, and judge whether the joint exceeds the target temperature range. Specifically, the target temperature range is [-5, -40°C]:

[0119] S62. If the joint temperature is lower than the lower limit of the target temperature, start the heating device to heat the joint; if the joint temperature is higher than the upper limit of the target temperature, start the cooling device to cool the joint;

[0120] S63. Obtain the joint stress value monitored by the sensor, and calculate the real-time stress change rate according to the joint stress value:

[0121]

[0122] In the formula, represents the stress change rate, Δσ represents the stress change rate, Δt represents the change period, represents the joint stress value within the change period.

[0123] S64. When the real-time stress change rate exceeds the growth threshold, send a stress index warning signal.

[0124] S65. Obtain the joint strain value monitored by the sensor, compare the joint strain value with the strain limit value, and when the joint strain value exceeds the strain limit value, send a strain index warning signal. Among them, the warning signal can be sent in various ways, such as text messages, emails, push notifications, etc., to notify the maintenance personnel or engineers for further inspection and processing.

[0125] Embodiment 2:

[0126] As Figure 3 shown, this embodiment provides a device for the design and maintenance of bridge joints. The device includes:

[0127] Model building module: Build a bridge joint model in finite element analysis software, and use the bridge joint model to simulate the force change of the joint in the future period under different bridge parameters and joint parameters of the bridge;

[0128] Dataset construction module: Construct a sample dataset with multiple groups of different bridge parameters as input data, and their corresponding joint parameters and force changes as output data;

[0129] Training module: Build a long short-term memory network, and use the sample dataset to train and test the long short-term memory network to obtain a joint calculation model;

[0130] Obtaining module: Obtain the bridge parameters of the bridge to be connected, input the bridge parameters of the bridge to be jointed into the joint calculation model, and calculate the joint parameters of the bridge to be connected and the force change of the joint in the future period;

[0131] Strategy formulation module: Formulate a maintenance strategy for the joint according to the force change of the joint in the future period;

[0132] Real-time monitoring module: After applying the calculated joint parameters to the joint of the bridge to be connected, monitor the force condition of the joint in real time. When the force of the joint exceeds the limit value, send a warning signal.

[0133] Based on the above embodiments, the model building module includes:

[0134] Model building unit: Build a bridge joint model in finite element analysis software. The bridge joint model includes two bridges with a joint. The bridge decks of the two bridges are on the same horizontal plane, and the joint between the two bridges is connected by concrete.

[0135] Parameter assignment unit: Assign different bridge parameters and joint parameters to the bridge joint model, and use the finite element analysis software to calculate the stress time series data and strain time series data of the joint within a preset time period under different bridge parameters, joint parameters, and temperatures.

[0136] Based on the above embodiments, the data set construction module includes:

[0137] Output vector composition unit: Represent the stress time series data and strain time series data at each time step as an output vector.

[0138] Data composition unit: A set of bridge parameters and a preset temperature form a set of input data. The stress time series data and strain time series data of the bridge parameters in all time steps of the input vector form the first output data, and the joint parameters form the second output data.

[0139] Partitioning unit: Construct a sample data set from multiple groups of different input data and the corresponding first output data and second output data. Among them, the sample data set is partitioned into a training set and a test set according to a ratio of 8:2.

[0140] Based on the above embodiments, the training module includes:

[0141] Network construction unit: Sequentially construct a long short-term memory network by an LSTM hidden layer, a fully connected layer, and an output layer.

[0142] Input unit: Input the sample data set into the LSTM hidden layer. After the LSTM hidden layer captures the time series features of the input data, it outputs the hidden state value to the fully connected layer.

[0143] Output unit: The fully connected layer maps the hidden state value to the dimension of the output data, generates the predicted output data, and outputs it by the output layer.

[0144] Comparison unit: Compare the predicted output data with the real first output data and second output data in the sample data set, and calculate the loss function.

[0145] Update unit: Use the loss function to iteratively update the parameters of the long short-term memory network.

[0146] Judgment unit: Repeatedly train the updated long short-term memory network, and when the loss function is less than the preset threshold, obtain the concrete parameter calculation model.

[0147] Based on the above embodiments, the strategy formulation module includes:

[0148] The first calculation unit: Analyze the force change of the joint in the future time period, and calculate the comprehensive evaluation index of the joint in the future time period;

[0149] The division unit: Divide the joint into four service stages according to the comprehensive evaluation index;

[0150] The formulation unit: Formulate corresponding maintenance measures for the four service stages respectively.

[0151] Based on the above embodiments, the real-time monitoring module includes:

[0152] The acquisition unit: Acquire the joint temperature monitored by the temperature sensor, and judge whether the joint exceeds the target temperature range:

[0153] The temperature control unit: If the joint temperature is lower than the lower limit of the target temperature, start the heating device to heat the joint; if the joint temperature is higher than the upper limit of the target temperature, start the cooling device to cool the joint;

[0154] The second calculation unit: Acquire the joint stress value monitored by the sensor, and calculate the real-time stress change rate according to the joint stress value;

[0155] The first warning unit: When the real-time stress change rate exceeds the growth threshold, send out a stress index warning signal;

[0156] The second warning unit: Acquire the joint strain value monitored by the sensor, compare the joint strain value with the strain limit value, and when the joint strain value exceeds the strain limit value, send out a strain index warning signal.

[0157] It should be noted that regarding the devices in the above embodiments, the specific manners in which each module performs operations have been described in detail in the embodiments related to the method, and will not be elaborated herein.

[0158] Embodiment 3:

[0159] Corresponding to the above method embodiment, in this embodiment, a design and maintenance device for bridge joints is also provided. A design and maintenance device for bridge joints described below can be mutually corresponding and referred to with a design and maintenance method for bridge joints described above.

[0160] Figure 4 It is a block diagram of a design and maintenance device 800 for bridge joints shown according to an exemplary embodiment. AsFigure 4 As shown, the design and maintenance device 800 for bridge joints may include: a processor 801 and a memory 802. The design and maintenance device 800 for bridge joints may also include one or more of a multimedia component 803, an I / O interface 804, and a communication component 805.

[0161] Among them, the processor 801 is used to control the overall operation of the design and maintenance device 800 for bridge joints to complete all or part of the steps in the above-mentioned design and maintenance method for bridge joints. The memory 802 is used to store various types of data to support the operation of the design and maintenance device 800 for bridge joints. These data may include, for example, instructions for any application or method operating on the design and maintenance device 800 for bridge joints, as well as application-related data, such as contact data, received and sent messages, pictures, audio, video, etc. The memory 802 can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as Static Random Access Memory (SRAM), Electrically Erasable Programmable Read-Only Memory (EEPROM), Erasable Programmable Read-Only Memory (EPROM), Programmable Read-Only Memory (PROM), Read-Only Memory (ROM), magnetic memory, flash memory, a magnetic disk, or an optical disc. The multimedia component 803 may include a screen and an audio component. The screen may be, for example, a touch screen, and the audio component is used to output and / or input audio signals. For example, the audio component may include a microphone for receiving external audio signals. The received audio signals may be further stored in the memory 802 or sent through the communication component 805. The audio component also includes at least one speaker for outputting audio signals. The I / O interface 804 provides an interface between the processor 801 and other interface modules, and the above-mentioned other interface modules may be a keyboard, a mouse, buttons, etc. These buttons may be virtual buttons or physical buttons. The communication component 805 is used for wired or wireless communication between the design and maintenance device 800 for bridge joints and other devices. Wireless communication, such as Wi-Fi, Bluetooth, Near Field Communication (NFC), 2G, 3G, or 4G, or a combination of one or more of them. Accordingly, the communication component 805 may include: a Wi-Fi module, a Bluetooth module, and an NFC module.

[0162] In an exemplary embodiment, the bridge joint design and maintenance device 800 can be implemented by one or more application specific integrated circuits (ASICs), digital signal processors (DSPs), digital signal processing devices (DSPDs), programmable logic devices (PLDs), field programmable gate arrays (FPGAs), controllers, microcontrollers, microprocessors or other electronic components, and is used to execute the above-mentioned bridge joint design and maintenance method.

[0163] In another exemplary embodiment, a computer-readable storage medium including program instructions is also provided. When the program instructions are executed by a processor, the steps of the above-mentioned bridge joint design and maintenance method are implemented. For example, the computer-readable storage medium can be the above-mentioned memory 802 including program instructions, and the above-mentioned program instructions can be executed by the processor 801 of the bridge joint design and maintenance device 800 to complete the above-mentioned bridge joint design and maintenance method.

[0164] Embodiment 4:

[0165] Corresponding to the above method embodiment, a readable storage medium is also provided in this embodiment. A readable storage medium described below can be mutually corresponding and referred to with a bridge joint design and maintenance method described above.

[0166] A readable storage medium stores a computer program. When the computer program is executed by a processor, the steps of the bridge joint design and maintenance method in the above method embodiment are implemented.

[0167] Specifically, the readable storage medium can be various readable storage media such as a USB flash drive, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disc, etc., which can store program codes.

[0168] The above are only the preferred embodiments of the present invention and are not used to limit the present invention. For those skilled in the art, the present invention can have various changes and modifications. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention shall be included in the protection scope of the present invention.

[0169] As described above, it is only the specific implementation manner of the present invention, but the protection scope of the present invention is not limited thereto. Any person skilled in the art within the technical scope disclosed by the present invention can easily think of changes or substitutions, which should all be covered within the protection scope of the present invention. Therefore, the protection scope of the present invention shall be subject to the protection scope of the claims.

Claims

1. A method for designing and maintaining bridge joints, characterized in that: include: A bridge joint model is built in finite element analysis software, and the bridge joint model is used to simulate the stress changes of the joints in the future period under different bridge parameters and joint parameters; A sample data set is constructed by taking multiple sets of different bridge parameters as input data and their corresponding joint parameters and force changes as output data; Building a long short-term memory network, and using the sample data set to train and test the long short-term memory network to obtain a seam calculation model; Obtaining bridge parameters of the bridges to be connected, inputting the bridge parameters of the bridges to be jointed into the joint calculation model, and calculating the joint parameters of the bridges to be connected and the stress changes of the joints in the future period; Formulate joint maintenance strategies based on joint stress changes in future periods; After applying the calculated joint parameters to the joints of the bridges to be connected, the stress conditions of the joints are monitored in real time. When the stress on the joints exceeds the limit value, an early warning signal is sent.

2. The method for designing and maintaining bridge joints according to claim 1, characterized in that: A bridge joint model is built in the finite element analysis software, and the bridge joint model is used to simulate the stress changes of the joints in the future period under different bridge parameters and joint parameters, including: A bridge joint model is constructed in finite element analysis software, wherein the bridge joint model includes two bridges with joints, the bridge decks of the two bridges are located on the same horizontal plane, and the joint between the two bridges is connected by concrete; Different bridge parameters and joint parameters are assigned to the bridge joint model, and the finite element analysis software is used to calculate the stress time series data and strain time series data of the joint within a preset time period under different bridge parameters, joint parameters and temperatures.

3. The method for designing and maintaining bridge joints according to claim 2, characterized in that: A sample data set is constructed by taking multiple sets of different bridge parameters as input data and their corresponding joint parameters and force changes as output data, including: Obtaining the time step included in the stress time series data, constructing the temperature corresponding to a set of bridge parameters into time series data with the same time step as the stress time series data, and obtaining temperature time series data, wherein the time step included in the stress time series data is the same as the time step included in the strain time series data; The stress time series data, strain time series data and temperature time series data of each time step are expressed as an input vector; The input vectors of a set of stress time series data, strain time series data and temperature time series data of a set of bridge parameters at all time steps constitute a set of input data, and the bridge parameters constitute a set of output data; A sample data set is constructed from multiple sets of different input data and output data.

4. The method for designing and maintaining bridge joints according to claim 1, characterized in that: Building a long short-term memory network, using the sample data set to train and test the long short-term memory network, and obtaining a seam calculation model, including: The long short-term memory network is constructed by the LSTM hidden layer, the fully connected layer and the output layer in sequence; The sample data set is input into the LSTM hidden layer. The LSTM hidden layer captures the temporal characteristics of the input data and outputs the hidden state value to the fully connected layer. The hidden state value is mapped to the dimension of the output data by the fully connected layer, and the predicted output data is generated and output by the output layer; Compare the predicted output data with the actual first output data and the second output data in the sample data set, and calculate a loss function; Iteratively updating the parameters of the long short-term memory network using the loss function; The updated long short-term memory network is repeatedly trained, and when the loss function is less than a preset threshold, a concrete parameter calculation model is obtained.

5. A bridge joint design and maintenance device, characterized in that: include: Model building module: building a bridge joint model in the finite element analysis software, and using the bridge joint model to simulate the stress changes of the joints in the future under different bridge parameters and joint parameters; Dataset construction module: constructs a sample dataset by taking multiple sets of different bridge parameters as input data and their corresponding joint parameters and force changes as output data; Training module: building a long short-term memory network, using the sample data set to train and test the long short-term memory network, and obtaining a seam calculation model; Acquisition module: acquiring bridge parameters of the bridges to be connected, inputting the bridge parameters of the bridges to be connected into the joint calculation model, and calculating the joint parameters of the bridges to be connected and the stress changes of the joints in the future period; Strategy formulation module: formulate joint maintenance strategies based on the stress changes of the joints in the future period; Real-time monitoring module: After applying the calculated joint parameters to the joints of the bridges to be connected, the stress conditions of the joints are monitored in real time. When the stress of the joints exceeds the limit value, an early warning signal is sent.

6. The bridge joint design and maintenance device according to claim 5, characterized in that: The model building module includes: Model building unit: building a bridge joint model in finite element analysis software, wherein the bridge joint model includes two bridges with joints, the decks of the two bridges are located on the same horizontal plane, and the joint between the two bridges is connected by concrete; Parameter assignment unit: assign different bridge parameters and joint parameters to the bridge joint model, and use the finite element analysis software to calculate the stress time series data and strain time series data of the joint within a preset time period under different bridge parameters, joint parameters and temperatures.

7. The bridge joint design and maintenance device according to claim 6, characterized in that: The data set construction module includes: Output vector composition unit: The stress time series data and strain time series data of each time step are represented as an output vector; Data forming unit: a group of input data is formed by a group of bridge parameters and a preset temperature, the stress time series data and the strain time series data of the bridge parameters constitute the first output data at all time step input vectors, and the joint parameters constitute the second output data; Division unit: A sample data set is constructed from a plurality of different sets of input data and corresponding first output data and second output data, wherein the sample data set is divided into a training set and a test set in a ratio of 8:

2.

8. The bridge joint design and maintenance device according to claim 5, characterized in that: The training module includes: Network construction unit: construct a long short-term memory network by sequentially using LSTM hidden layer, fully connected layer and output layer; Input unit: The sample data set is input into the LSTM hidden layer. The LSTM hidden layer captures the temporal characteristics of the input data and outputs the hidden state value to the fully connected layer. Output unit: The hidden state value is mapped to the dimension of the output data by the fully connected layer, and the predicted output data is generated and output by the output layer; Comparison unit: compares the predicted output data with the real first output data and the real second output data in the sample data set, and calculates the loss function; Update unit: iteratively update the parameters of the long short-term memory network using the loss function; Judgment unit: Repeat the training of the updated long short-term memory network, and when the loss function is less than the preset threshold, the concrete parameter calculation model is obtained.

9. A bridge joint design and maintenance device, characterized in that: include: Memory for storing computer programs; A processor, configured to implement the steps of the bridge joint design and maintenance method as claimed in any one of claims 1 to 4 when executing the computer program.

10. A readable storage medium, characterized in that: The readable storage medium stores a computer program, and when the computer program is executed by a processor, the steps of the bridge joint design and maintenance method according to any one of claims 1 to 4 are implemented.

Images