A method, apparatus, device, and medium for designing and maintaining a bridge joint

Abstract

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

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of artificial intelligence, in particular to a bridge joint design and maintenance method, device, equipment and readable storage medium. BACKGROUND

[0002] As a key functional component, bridge joints bear the important task of absorbing the deformation of the bridge caused by temperature difference, load and uneven settlement of the foundation. However, the traditional continuous joint design of the bridge deck has many problems, mainly manifested in that the joint is easily affected by temperature changes and vehicle loads, leading to cracking and fatigue damage, and thus reducing the performance of the bridge. In addition, the traditional joint lacks real-time monitoring capability, and the maintenance work relies on periodic manual inspection, which is difficult to find potential risks in time, causing maintenance lag or excessive maintenance, and increasing maintenance costs. Although the ECC concrete joint design has made some progress in improving the performance of the joint, it still has deficiencies in dealing with the long-term service requirements of the bridge under complex environments, especially the fatigue damage caused by temperature difference stress. Modern bridges have increasing demands for intelligence, low maintenance cost and long service life, and the traditional design and maintenance mode cannot meet the technical requirements of the new era. SUMMARY

[0003] The purpose of the present application is to provide a bridge joint design and maintenance method, device, equipment and readable storage medium to improve the above problems. In order to achieve the above purpose, the technical solution adopted by the present application is as follows:

[0004] In a first aspect, the present application provides a bridge joint design and maintenance method, comprising:

[0005] Building a bridge joint model in a finite element analysis software, simulating the stress change of the joint in the future period under different bridge parameters and joint parameters of the bridge by using the bridge joint model;

[0006] Constructing a sample data set by taking multiple groups of different bridge parameters as input data, and their corresponding joint parameters and stress changes as output data;

[0007] Building a long short-term memory network, training and testing the long short-term memory network by using the sample data set, and obtaining a joint calculation model;

[0008] Obtaining the bridge parameters of the bridge to be connected, inputting the bridge parameters of the bridge to be connected into the joint calculation model, and calculating the joint parameters of the bridge to be connected and the stress change of the joint in the future period;

[0009] Formulating a maintenance strategy for the joint according to the stress change of the joint in the future period;

[0010] The calculated joint parameters are applied to the joint of the bridge to be connected, and the stress condition of the joint is monitored in real time, and when the stress of the joint exceeds the limit value, a warning signal is sent.

[0011] In a second aspect, the application further provides a bridge joint design and maintenance device, comprising:

[0012] The model building module builds a bridge joint model in a finite element analysis software, and simulates the stress change of the joint in the future period under different bridge parameters and joint parameters by using the bridge joint model.

[0013] The data set construction module constructs a sample data set by taking multiple groups of different bridge parameters as input data, and taking corresponding joint parameters and stress changes as output data.

[0014] The training module builds a long short-term memory network, trains and tests the long short-term memory network by using the sample data set, and obtains a joint calculation model.

[0015] The acquisition module acquires the bridge parameters of the bridge to be connected, inputs the bridge parameters of the bridge to be connected into the joint calculation model, and calculates the joint parameters of the bridge to be connected and the stress change of the joint in the future period.

[0016] The strategy making module makes a maintenance strategy for the joint according to the stress change of the joint in the future period.

[0017] The real-time monitoring module applies the calculated joint parameters to the joint of the bridge to be connected, and monitors the stress condition of the joint in real time, and when the stress of the joint exceeds the limit value, a warning signal is sent.

[0018] In a third aspect, the application further provides a bridge joint design and maintenance device, comprising:

[0019] The memory is used for storing a computer program.

[0020] The processor is used for executing the computer program to realize the steps of the bridge joint design and maintenance method.

[0021] In a fourth aspect, the application further provides a readable storage medium, and the readable storage medium stores a computer program.

[0022] The application has the following beneficial effects:

[0023] The joint calculation model built by the LSTM network of the application can accurately predict joint parameters and future stress changes, so as to realize accurate joint design and maintenance strategy. The application combines future early warning and real-time monitoring, can not only carry out stage maintenance in the whole life cycle of the bridge, optimizes the maintenance cost, prolongs the service life of the joint, but also can monitor the stress change of the bridge in real time, ensures that the joint stress can be responded in time when the joint stress exceeds the limit value, and avoids structural damage. Through intelligent management, the bridge maintenance work becomes more efficient and scientific, reduces the working strength of the maintenance personnel, and improves the driving comfort and traffic efficiency.

[0024] Other features and advantages of the present application will be set forth in the following description, and in part will become apparent from the description, or can be learned by practice of the present application according to the embodiments. The objects and other advantages of the present application can be achieved and obtained by the structure particularly pointed out in the written description, claims, and drawings. BRIEF DESCRIPTION OF DRAWINGS

[0025] In order to more clearly illustrate the technical solutions of the embodiments of the application, the following will briefly introduce the drawings needed to be used in the embodiments. It should be understood that the following drawings only show some embodiments of the application, and therefore should not be regarded as limiting the scope. For those skilled in the art, other related drawings can also be obtained without creative labor on the basis of these drawings.

[0026] Figure 1 The design and maintenance method flow chart of the bridge joint described in the embodiments of the application;

[0027] Figure 2 The bridge joint model schematic diagram described in the embodiments of the application;

[0028] Figure 3 The design and maintenance device structure schematic diagram of the bridge joint described in the embodiments of the application;

[0029] Figure 4 The design and maintenance device structure schematic diagram of the bridge joint described in the embodiments of the application.

[0030] Markings in the figure:

[0031] 01-first bridge; 02-second bridge; 03-concrete;

[0032] 800, bridge joint design and maintenance device; 801, processor; 802, memory; 803, multimedia assembly; 804, I / O interface; 805, communication assembly. DETAILED DESCRIPTION

[0033] In order to make the purposes, technical solutions and advantages of the embodiments of the present application clearer, the technical solutions in the embodiments of the present application will be described clearly and completely below with reference to the drawings in the embodiments of the present application. Obviously, the described embodiments are only some of the embodiments of the present application, rather than all the embodiments. The components of the embodiments of the present application described and shown in the drawings can be arranged and designed in various different configurations. Therefore, the following detailed description of the embodiments of the present application provided in the drawings is not intended to limit the scope of the claimed present application, but only represents selected embodiments of the present application. Based on the embodiments in the present application, all other embodiments obtained by those of ordinary skill in the art without creative efforts belong to the scope of protection of the present application.

[0034] It should be noted that similar reference numerals and letters represent similar items in the following drawings, and therefore, once an item is defined in one drawing, it need not be further defined and explained in subsequent drawings. Meanwhile, in the description of the present application, the terms "first", "second", and the like are only used to distinguish description, and cannot be understood as indicating or implying relative importance.

[0035] Embodiment 1

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

[0037] Referring to Figure 1 , the method includes:

[0038] S1. Building a bridge joint model in a finite element analysis software, and simulating stress changes of the joint in future periods under different bridge parameters and joint parameters by using the bridge joint model;

[0039] Specifically, the step S1 includes:

[0040] S11. Building a bridge joint model in a finite element analysis software, the bridge joint model including two bridges with joints, the bridge decks of the two bridges being located on the same horizontal plane, and the joint between the two bridges being connected by concrete;

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

[0042] S12. Assigning different bridge parameters and joint parameters to the bridge joint model, and calculating stress time series data and strain time series data of the joint in a preset period under different bridge parameters, joint parameters and temperature V by using the finite element analysis software;

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

[0044] The joint parameters include a joint concrete thickness h, a joint length L2, a material strength f c (ECC material compressive strength);

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

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

[0047] A set of bridge parameters, joint parameters, and temperature {L1, B, H, G, h, L2, f c , V} are given to the bridge joint model, and the finite element analysis software simulates the full life cycle of the bridge joint model until the stress or strain value of the bridge joint model reaches the maximum threshold value, at which time the stress time series data and the strain time series data of the joint in the full life cycle are output, wherein if the stress reaches the corresponding maximum threshold value first, the strain stops being generated, and the time period when the stress reaches the maximum threshold value is taken as the full 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) in the full life cycle, where t = 1, 2, …, T, where t represents a time step, which can be divided according to actual needs, and T represents the full life cycle.

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

[0049] S2. A sample data set is constructed by taking a plurality of different bridge parameters as input data, and their corresponding joint parameters and stress changes as output data;

[0050] Specifically, the step S2 includes:

[0051] S21. The stress time series data and the strain time series data of each time step are represented as an output vector;

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

[0053] Specifically, the input data is X = [L1, B, H, G, V], the first output data is The second output data is Y1 = [h, L2, f c ].

[0054] S23. Constructing a sample data set 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 according to a ratio of 8:2;

[0055] Preferably, the sample data set is normalized:

[0056]

[0057] wherein, 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 embodiment, the method further comprises:

[0059] S3. Building a long short-term memory network, training and testing the long short-term memory network using the sample data set, and obtaining a joint calculation model;

[0060] Specifically, the step S3 comprises:

[0061] S31. Constructing a long short-term memory network sequentially from an LSTM hidden layer, a fully connected layer and an output layer;

[0062] Specifically, the LSTM hidden layer comprises two layers of stacked LSTM units:

[0063] The first layer of LSTM units: contains N1 units, sets return_sequences = True, and outputs the hidden state of each time step.

[0064] The second layer of LSTM units: contains N2 units, sets return_sequences = False, and outputs the hidden state of the last time step.

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

[0066] The first layer of fully connected layer and the first output layer: maps the output of the LSTM layer to the dimension of the first output data, i.e. the features of the stress time series data and the strain time series data, and then outputs the first output data, i.e. the time series changes of stress and strain, by the corresponding output layer;

[0067] The second full connection layer and the second output layer: mapping the output of the LSTM layer to the dimension of the second output data, i.e. the features of the seam parameters, and outputting the second output data, i.e. the seam parameters, by the corresponding output layer.

[0068] S32. Input the sample data set into the LSTM hidden layer, and output the hidden state value to the full connection layer after the LSTM hidden layer captures the features of the input data.

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

[0070] The forgetting gate is:

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

[0072] In the formula, x t is an input value, f t represents an output vector of the forgetting gate, and represents a proportion of forgetting the memory of the previous time step, and each element of the proportion has a value in the range of [0, 1]. When f t = 1, it means completely retaining the memory of the previous time step, and when f t = 0, it means completely forgetting the memory of the previous time step; and when f t is between 0 and 1, it means partially forgetting.

[0073] b f is a bias vector of the forgetting gate, which is used to adjust the initial output of the forgetting gate and flexibility in training, and the initial value is a zero vector [0, 0,..., 0], which is automatically updated in training by gradient descent.

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

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

[0076] h t-1 is the hidden state of the previous time step, and the initial hidden state h0 is a zero vector [0, 0,..., 0] at time step t = 0: the hidden state is updated with time step, and is obtained by training.

[0077] Specifically, the input gate is:

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

[0079] where i t determines how much proportion of the current candidate memory will be added to the candidate memory cell W i and b i represent the weight matrix and bias of the input gate;

[0080] where,

[0081] where W c and b c represent the weight matrix and bias of the candidate memory cell;

[0082] The update formula of the candidate memory cell is:

[0083]

[0084] where C t is the memory cell 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(W0· [h t-1 , x t ] + b0);

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

[0088] S33. mapping the hidden state value to the dimension of the output data by the fully connected layer, generating the predicted output data, and outputting by the output layer;

[0089] S34. comparing the predicted output data with the real first output data and second output data in the sample data set, and calculating the loss function;

[0090] Specifically, using mean square error (MSE) as the loss function U1 of the output data:

[0091]

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

[0093] S35. Iteratively updating 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, and the formula is as follows:

[0095]

[0096] In the formula, m t and m t-1 respectively represent the first-order momentum (weighted average of gradients) of t time step and t-1 time step, v t and v t-1 respectively represent the second-order momentum (weighted average of squared gradients) of t time step and t-1 time step, wherein m0=0 and v0=0; m and v are updated by exponential weighting iteration, and the contribution of historical gradients gradually accumulates as the number of iterations increases, and finally the values of m and v tend to be stable and do not depend on the initial values for a long time.

[0097] S36. Repeating the training of the updated long short-term memory network, and obtaining the concrete parameter calculation model when the loss function is less than a preset threshold.

[0098] Based on the above embodiment, the method further comprises:

[0099] S4. Obtaining the bridge parameters of the bridge to be connected, inputting the bridge parameters of the bridge to be connected into the joint calculation model, and calculating the joint parameters of the bridge to be connected and the stress change of the joint in the future period;

[0100] The input data of the joint calculation model further comprises a temperature V, wherein the temperature V is the average temperature of the past 20 years in the location of the bridge to be connected

[0101] Based on the above embodiment, the method further comprises:

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

[0103] Specifically, the step S5 comprises:

[0104] S51. Analyzing the stress change of the joint in the future period, and calculating a comprehensive evaluation index of the joint in the future period;

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

[0106]

[0107] In the formula, M(t) is the comprehensive evaluation index of t time step, s(t) is the stress at the joint, s max The maximum value of the stress of the joint material, ε(t) is the strain at the joint, ε max The maximum value of the stress of the joint material, ω1 is the weight of the stress, and ω2 is the weight of the strain.

[0108] S52. According to the comprehensive evaluation index, the joint is divided into four service stages, specifically:

[0109]

[0110] S53. Corresponding maintenance means is formulated for the four service stages respectively;

[0111] Specifically, the maintenance means of the prevention stage is to check the joint crack and other indicators, and repair the cracks.

[0112] The maintenance means of the diagnosis stage is to check the internal state of the joint by using ultrasonic detection, infrared thermal imaging and the like, repair the cracks and reinforce the joint structure.

[0113] The maintenance means of the repair stage is to repair the damaged part of the joint, reapply the protective coating, replace the material, completely remove and redesign the joint, and perform large-scale reconstruction.

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

[0115] Based on the above embodiment, the method further comprises:

[0116] S6. 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, and when the stress of the joint exceeds the limit value, a warning signal is sent.

[0117] Specifically, the step S6 comprises:

[0118] S61. Obtain the joint temperature monitored by the temperature sensor, and determine whether the joint exceeds the target temperature range, specifically the target temperature range is [-5, -40℃]:

[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] wherein, represents a stress change rate, Δσ represents a stress change rate, Δt represents a change period, represents a joint stress value in a change period.

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

[0124] S65. The joint strain value monitored by the sensor is obtained, and the joint strain value is compared with a strain limit value, and when the joint strain value exceeds the strain limit value, a strain index early warning signal is sent out, wherein the early warning signal can be sent in various ways, such as short message, email, push notification, etc., to notify maintenance personnel or engineers to further check and handle.

[0125] Embodiment 2:

[0126] As Figure 3 shown, the embodiment provides a bridge joint design and maintenance device, which comprises:

[0127] A model building module: a bridge joint model is built in a finite element analysis software, and the bridge joint model is used to simulate the stress change of the joint in a future period under different bridge parameters and joint parameters;

[0128] A data set construction module: a sample data set is constructed by taking multiple groups of different bridge parameters as input data, and taking corresponding joint parameters and stress changes as output data;

[0129] A training module: a long short-term memory network is built, and the long short-term memory network is trained and tested using the sample data set to obtain a joint calculation model;

[0130] An acquisition module: the bridge parameters of a bridge to be connected are obtained, and the bridge parameters of the bridge to be connected are input into the joint calculation model to calculate the joint parameters of the bridge to be connected and the stress change of the joint in a future period;

[0131] A strategy making module: a maintenance strategy of the joint is made according to the stress change of the joint in a future period;

[0132] A real-time monitoring module: after the calculated joint parameters are applied to the joint of the bridge to be connected, the stress 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.

[0133] Based on the above embodiment, the model building module comprises:

[0134] The model building unit builds a bridge joint model in a finite element analysis software, the bridge joint model comprising two bridges with a joint, bridge decks of the two bridges being located on the same horizontal plane, and the joint between the two bridges being connected by concrete;

[0135] The parameter assigning unit assigns different bridge parameters and joint parameters to the bridge joint model, and calculates 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 by using the finite element analysis software.

[0136] Based on the above embodiment, the data set construction module comprises:

[0137] The output vector composition unit represents the stress time series data and the strain time series data of each time step as an output vector;

[0138] The data composition unit comprises a group of input data composed of a group of bridge parameters and a preset temperature, the stress time series data and the strain time series data of the bridge parameters forming first output data in all time steps, and the joint parameters forming second output data;

[0139] The division unit constructs a sample data set from a plurality of different 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 according to a ratio of 8:2.

[0140] Based on the above embodiment, the training module comprises:

[0141] The network construction unit sequentially constructs a long short-term memory network from an LSTM hidden layer, a fully connected layer and an output layer;

[0142] The input unit inputs the sample data set into the LSTM hidden layer, and the LSTM hidden layer outputs a hidden state value to the fully connected layer after capturing the time sequence features of the input data;

[0143] The output unit maps the hidden state value to the dimension of the output data by the fully connected layer, and outputs the predicted output data by the output layer after generating the predicted output data;

[0144] The 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 a loss function;

[0145] The update unit iteratively updates parameters of the long short-term memory network by using the loss function;

[0146] The judgment unit repeatedly trains the updated long short-term memory network, and obtains a concrete parameter calculation model when the loss function is less than a preset threshold.

[0147] Based on the above embodiments, the policy making module comprises:

[0148] The first calculation unit: analyzing the stress change of the joint in the future period, and calculating the comprehensive evaluation index of the joint in the future period;

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

[0150] The making unit: making corresponding maintenance means for the four service stages respectively.

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

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

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

[0154] The second calculation unit: acquiring the joint stress value monitored by the sensor, and calculating 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, a stress index warning signal is sent out;

[0156] The second warning unit: acquiring the joint strain value monitored by the sensor, comparing the joint strain value with the strain limit value, and when the joint strain value exceeds the strain limit value, a strain index warning signal is sent out.

[0157] It should be noted that, as for the device in the above embodiments, the specific manner in which each module performs the operation has been described in detail in the embodiments related to the method, and will not be described in detail here.

[0158] Embodiment 3:

[0159] Corresponding to the above method embodiments, the present embodiment also provides a bridge joint design and maintenance device. The bridge joint design and maintenance device described below can be mutually corresponding to the bridge joint design and maintenance method described above.

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

[0161] The processor 801 is configured to control overall operation of the bridge joint design and maintenance device 800 to accomplish all or part of the above-mentioned bridge joint design and maintenance method. The memory 802 is configured to store various types of data to support operation of the bridge joint design and maintenance device 800, which can include, for example, instructions for any application or method operating on the bridge joint design and maintenance device 800, and application-related data, such as contact data, sent and received messages, pictures, audio, video, and the like. The memory 802 can be implemented by any type of volatile or non-volatile storage devices 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 storage, flash memory, magnetic disk or optical disk. The multimedia component 803 can include a screen and an audio component. The screen can be, for example, a touch screen, and the audio component is configured to output and / or input audio signals. For example, the audio component can include a microphone configured to receive external audio signals. The received audio signals can be further stored in the memory 802 or transmitted through the communication component 805. The audio component further includes at least one speaker configured to output audio signals. The I / O interface 804 provides an interface between the processor 801 and other interface modules, which can be a keyboard, a mouse, a button, and the like. The buttons can be virtual buttons or physical buttons. The communication component 805 is configured to enable wired or wireless communication between the bridge joint design and maintenance device 800 and other devices. The wireless communication, such as Wi-Fi, Bluetooth, near field communication (NFC), 2G, 3G or 4G, or one or more of them or a combination of one or more of them, so the corresponding communication component 805 can include a Wi-Fi module, a Bluetooth module, an NFC module.

[0162] In an example 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, micro-controllers, microprocessors or other electronic elements for executing the above-mentioned bridge joint design and maintenance method.

[0163] In another example embodiment, a computer-readable storage medium including program instructions that, when executed by a processor, implement the steps of the above-mentioned bridge joint design and maintenance method is also provided. For example, the computer-readable storage medium can be the above-mentioned memory 802 including program instructions that 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 embodiments, a readable storage medium is also provided in this embodiment, and the readable storage medium described below can be referred to in correspondence with the above-mentioned bridge joint design and maintenance method.

[0166] A readable storage medium, on which a computer program is stored, the computer program being executed by a processor to implement the steps of the above-mentioned bridge joint design and maintenance method of the method embodiments.

[0167] The readable storage medium can specifically be a U disk, a mobile hard disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), a magnetic disk or an optical disk, and various readable storage media that can store program codes.

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

[0169] The above merely illustrates the specific embodiments of the present application, but the protection scope of the present application is not limited thereto, any person skilled in the art can easily think of the changes or replacements within the technical range disclosed by the present application, which should be covered in the protection scope of the present application. Therefore, the protection scope of the present application should be subject to the protection scope of the claims.

Claims

1. A method of designing and maintaining a bridge joint, characterized by, The method comprises the following steps: a bridge joint model is built in a finite element analysis software, and the bridge joint model is used to simulate stress changes of the joint in a future period under different bridge parameters and joint parameters, including: a bridge joint model is built in a finite element analysis software, the bridge joint model comprising two bridges with a joint, the bridge decks of the two bridges being located on the same horizontal plane, and the joint between the two bridges being 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 stress time series data and strain time series data of the joint in a preset period under different bridge parameters, joint parameters and temperatures; a sample data set is constructed by taking a plurality of different bridge parameters as input data and their corresponding joint parameters and stress changes as output data, including: a time step contained in the stress time series data is obtained, and a temperature corresponding to a group of bridge parameters is constructed as time series data with the same time step as the stress time series data to obtain temperature time series data, wherein the time step contained in the stress time series data and the time step contained in the strain time series data are the same; the stress time series data, the strain time series data and the temperature time series data of each time step are represented as an input vector; the input vectors of the stress time series data, the strain time series data and the temperature time series data of a group of bridge parameters at all time steps constitute a group of input data, and the bridge parameters constitute a group of output data; a plurality of different input data and output data are constructed as a sample data set; a long short-term memory network is built, and the long short-term memory network is trained and tested by using the sample data set to obtain a joint calculation model; bridge parameters of a bridge to be connected are obtained, and the bridge parameters of the bridge to be connected are input into the joint calculation model to calculate joint parameters of the bridge to be connected and stress changes of the joint in a future period; a maintenance strategy for the joint is formulated according to the stress changes of the joint in the future period; after the calculated joint parameters are applied to the joint of the bridge to be connected, the stress of the joint is monitored in real time, and a warning signal is sent when the stress of the joint exceeds a limit value.

2. The method of designing and maintaining a bridge joint according to claim 1, wherein, The method comprises the following steps: a long short-term memory network is built, and the long short-term memory network is trained and tested by using the sample data set to obtain a joint calculation model, including: a long short-term memory network is built in sequence by an LSTM hidden layer, a fully connected layer and an output layer; the sample data set is input into the LSTM hidden layer, and the LSTM hidden layer outputs a hidden state value to the fully connected layer after capturing the time sequence characteristics of the input data; the hidden state value is mapped to the dimension of the output data by the fully connected layer, and the predicted output data is output by the output layer after being generated; the predicted output data is compared with the real first output data and the real second output data in the sample data set to calculate a loss function; the parameters of the long short-term memory network are iteratively updated by using the loss function; 3. A bridge joint design and maintenance apparatus, characterized by, the updated long short-term memory network is repeatedly trained, and the concrete parameter calculation model is obtained when the loss function is less than a preset threshold. The method for designing and maintaining the bridge joint according to any one of claims 1 to 2 comprises: The model building module: building a bridge joint model in a finite element analysis software, and simulating stress changes of the joint in future periods under different bridge parameters and joint parameters by using the bridge joint model; The data set construction module: constructing a sample data set by taking multiple groups of different bridge parameters as input data, and corresponding joint parameters and stress changes as output data; The training module: building a long short-term memory network, training and testing the long short-term memory network by using the sample data set, and obtaining a joint calculation model; The acquisition module: acquiring bridge parameters of a bridge to be connected, inputting the bridge parameters of the bridge to be connected into the joint calculation model, and calculating joint parameters of the bridge to be connected and stress changes of the joint in future periods; The strategy making module: making a maintenance strategy for the joint according to the stress changes of the joint in future periods; The real-time monitoring module: after applying the calculated joint parameters to the joint of the bridge to be connected, monitoring stress conditions of the joint in real time, and sending a warning signal when the stress of the joint exceeds a limit value.

4. The apparatus for design and maintenance of bridge joints according to claim 3, characterized in that, The training module includes: The network building unit: sequentially building a long short-term memory network by using an LSTM hidden layer, a full connection layer, and an output layer; The input unit: inputting the sample data set into the LSTM hidden layer, outputting hidden state values to the full connection layer after the LSTM hidden layer captures time sequence features of the input data, and outputting predicted output data after the full connection layer maps the hidden state values to dimensions of the output data; The output unit: outputting the predicted output data by the output layer after generating the predicted output data; The comparison unit: comparing the predicted output data with real first output data and second output data in the sample data set, and calculating a loss function; The update unit: iteratively updating parameters of the long short-term memory network by using the loss function; The judgment unit: repeatedly training the updated long short-term memory network, and obtaining the concrete parameter calculation model when the loss function is less than a preset threshold.

5. A bridge joint design and maintenance apparatus, characterized by, It includes: A memory for storing a computer program; A processor for implementing steps of the bridge joint design and maintenance method according to any one of claims 1 to 2 when the computer program is executed.

6. A readable storage medium characterized by: The computer program is stored on the readable storage medium, and the computer program is executed by the processor to implement steps of the bridge joint design and maintenance method according to any one of claims 1 to 2. The computer program is stored on the readable storage medium, and the computer program is executed by the processor to implement steps of the bridge joint design and maintenance method according to any one of claims 1 to 2.

Images