Indoor model loading system and method for determining factors affecting the service status of cable-stayed bridges

Abstract

The present invention provides an indoor model loading system and method for determining influencing factors of the service status of a cable-stayed bridge, and relates to the technical field of bridge structure health monitoring. The system and method utilize an indoor bridge model of an electric-controlled loading system for loading, divide the cable-stayed bridge into three blocks, and determine the key factors of each block respectively; make an overall scaled model of the cable-stayed bridge, or make three blocks respectively; design a model test, select appropriate sensors, install the sensors at appropriate positions according to specifications, and obtain relevant monitoring data; determine the influencing factors of the service performance status of the reactive cable-stayed cable service, main beam, and reactive cable tower based on the model test; and apply the determined key factors to actual bridges.

Description

Technical Field

[0001] The present disclosure relates to the technical field of bridge structure health monitoring, and in particular to an indoor model loading system and method for determining influencing factors of the service status of a cable-stayed bridge. Background Art

[0002] The statements in this section merely provide background information related to the present disclosure and do not necessarily constitute prior art.

[0003] As an important part of the infrastructure field, bridges are often affected by multiple factors such as the external environment, vehicle loads, wind loads, earthquakes, etc., and they also have to deal with the problem of gradual decline in internal working performance. These factors together lead to a gradual reduction in the performance of bridge structures. In order to fully grasp the changing trends and performance status of bridge structures, bridge structure health monitoring systems are currently widely used for real-time monitoring.

[0004] However, the inventors found that the current challenge is that there are many types of sensors required for bridge health monitoring, and the number and location of sensors are usually determined based on experience or simple mechanical calculations, which often leads to potential sensor redundancy and improper selection of monitoring locations. These problems further lead to the complexity of data transmission and data analysis, increasing the workload and cost of monitoring. Summary of the invention

[0005] In order to solve the above problems, the present invention proposes an indoor model loading system and method for determining the influencing factors of the service status of a cable-stayed bridge, optimizes the layout and data processing flow of the loading monitoring system, and more accurately captures important changes in the bridge structure by finding key influencing factors while retaining key information while reducing redundant data, thereby further ensuring the reliability and safety of the bridge under high-load operating conditions.

[0006] According to some embodiments, the present disclosure adopts the following technical solutions:

[0007] An indoor model loading system for determining the influencing factors of the service status of a cable-stayed bridge includes a water volume and water circulation electronic control module, a temperature and humidity control module, an electronically controlled jack module, a surround fan module, and an electric wheel load module for simulating vehicle loads; each module is uniformly powered by the electronic control module and is connected to each other via serial communication;

[0008] The water volume and water circulation electric control module controls the electric control water volume and water circulation for flushing the indoor model foundation, the temperature and humidity control module adjusts the ambient temperature and humidity, the electric control jack module controls the bridge displacement and angle change, the surround fan module adjusts the ambient wind speed and direction, and the electric wheel load module adjusts the vehicle load to actively interfere with the state of the cable with different variables, obtain monitoring data of the cable under different states, determine the service performance of the cable according to the monitoring data, and determine the key influencing factors affecting the service state of the cable-stayed bridge.

[0009] Furthermore, the water volume and water circulation electronic control module includes a pipeline body, a switchable water discharge port, a switchable water injection port, a water pipe, a water storage tank, a filter and a flow control mechanism. The filter is used to filter impurities brushed off during foundation flushing. The switchable water discharge port, the switchable water injection port, the water pipe and the water storage tank are used to fill and discharge water from the pipeline to achieve preliminary control of the water volume. The flow control mechanism includes a water absorber and a water ejector, which are used to further control the water flow and flow rate as needed.

[0010] Furthermore, the temperature and humidity control module includes an air conditioner and a humidifier-dehumidifier for adjusting the temperature and humidity of the environment; the electric-controlled jack module includes an electric-controlled jack, the surround fan module includes a 360° exhaust port, and the electric wheel-mounted module includes a trolley body, a traction rope and a traction mechanism with adjustable speed.

[0011] According to some embodiments, the present disclosure adopts the following technical solutions:

[0012] The method used to determine the factors affecting the service status of cable-stayed bridges includes:

[0013] Construct an indoor cable-stayed bridge scale model and divide the cable-stayed bridge scale model into three blocks;

[0014] Select appropriate sensors and set appropriate monitoring points to obtain monitoring data of the scaled model of the cable-stayed bridge;

[0015] A test method for the scaled model is designed. The state of the scaled model of the cable-stayed bridge is changed by using the above-mentioned loading system. Different vehicle loads and wind loads are applied, different variables are controlled, and the monitoring data of sensors under different states are obtained to determine the influencing factors of the service performance state of the reaction cable, the influencing factors of the service performance state of the main beam, and the influencing factors of the service performance state of the tower.

[0016] Furthermore, a scale model of an indoor cable-stayed bridge is constructed, including:

[0017] Collect the dimensions and physical characteristics of the original cable-stayed bridge to determine the size and proportion of the scaled model;

[0018] Determine the similarity between the scaled model and the original cable-stayed bridge;

[0019] According to the required material properties, choose appropriate materials to make scale models.

[0020] Furthermore, the scaled model of the cable-stayed bridge is divided into three blocks, including the cable, main beam and tower.

[0021] Furthermore, appropriate sensors are selected and appropriate monitoring points are set to obtain monitoring data of the scale model of the cable-stayed bridge, including:

[0022] Determine the sensor monitoring content according to the test purpose and existing needs, determine the functions of various sensors and correspond to the monitoring content, and determine the required sensor models;

[0023] Determine the sensor model and installation location based on relevant specifications and existing conditions, and install the sensor to obtain monitoring data.

[0024] Furthermore, the method for determining the influencing factors of the service performance state of the reaction stay cable includes:

[0025] Actively interfere with the state of the cable through the loading system, including changing the anchoring state, wire breaking state, temperature and humidity of the cable, and applying different vehicle loads and wind loads;

[0026] Obtain monitoring data from all sensors, and use expert scoring method to determine the service performance output index value of the cable based on the cable force, wind speed and direction, vibration, temperature and humidity, wire breakage, and anchorage status data monitored by the sensors;

[0027] Long short-term memory network is used to predict service performance. Different monitoring content data are used as input to obtain different prediction accuracies. The output prediction value is compared with the index value to determine the prediction accuracy. If the prediction accuracy obtained by certain inputs reaches more than 90%, these parameters are determined to be key factors.

[0028] Further, the method for determining the influencing factors of the service performance state of the reaction main beam includes:

[0029] Control variables, change the monitoring contents one by one through the loading system, namely, the state of strain, vibration, cracks in key sections, horizontal and vertical displacements, longitudinal displacements at beam ends, beam end rotation angles, temperature and humidity, support reaction forces, and support displacements;

[0030] Obtain and analyze data to identify monitoring data that vary significantly in each trial;

[0031] Calculate the number of times each monitoring data changes significantly in multiple tests. If changes in most monitoring contents can cause significant changes in certain monitoring contents, then determine these monitoring contents as key factors.

[0032] Furthermore, the method for determining the influencing factors of the service performance status of the reaction tower is:

[0033] Control variables, change the monitoring contents one by one through the loading system, namely the key section strain, vibration, wind speed and direction, deflection, inclination and foundation scour status;

[0034] Obtain and analyze data to identify monitoring data that vary significantly in each trial;

[0035] Calculate the number of times each monitoring data changes significantly in multiple tests. If changes in most monitoring contents can cause significant changes in certain monitoring contents, then determine these monitoring contents as key factors.

[0036] Compared with the prior art, the present invention has the following beneficial effects:

[0037] This paper conducts research on the key factor identification technology of bridge performance status by means of controlling variables and dynamic interactive impact analysis, establishes a relationship model between bridge service status and key factors, and forms a monitorable, analyzable, predictable and controllable key factor database covering the entire life cycle of bridge construction, management, maintenance and operation.

[0038] The present disclosure provides theoretical support for intelligent identification of physical entity performance status, optimizes the layout of inspection and monitoring equipment, and reduces monitoring costs.

[0039] Although the present invention is based on a cable-stayed bridge, it can be extended to other types of bridges, and even the idea can be extended to other transportation infrastructure, such as roadbeds, pavements, tunnels, etc. BRIEF DESCRIPTION OF THE DRAWINGS

[0040] The accompanying drawings constituting a part of the present disclosure are used to provide a further understanding of the present disclosure. The illustrative embodiments of the present disclosure and their descriptions are used to explain the present disclosure and do not constitute an improper limitation on the present disclosure.

[0041] Figure 1 is a schematic diagram of an electric-controlled loading system disclosed in the present invention;

[0042] Figure 2 It is a flow chart of a method for determining key influencing factors of the service status of a cable-stayed bridge disclosed in the present invention;

[0043] Figure 3 It is the scale model making process disclosed in the present invention;

[0044] Figure 4 is an example diagram of sensor layout of the present disclosure;

[0045] Figure 5 is the process of determining and installing the sensor of the present disclosure;

[0046] Figure 6 is the key factor determination process of the inclined cable disclosed in the present invention;

[0047] Figure 7 This is the key factor determination process of the main beam and cable tower disclosed in the present invention. DETAILED DESCRIPTION

[0048] The present disclosure is further described below in conjunction with the accompanying drawings and embodiments.

[0049] It should be noted that the following detailed descriptions are all illustrative and are intended to provide further explanation of the present disclosure. Unless otherwise specified, all technical and scientific terms used herein have the same meanings as those commonly understood by those skilled in the art to which the present disclosure belongs.

[0050] It should be noted that the terms used herein are only for describing specific embodiments and are not intended to limit the exemplary embodiments according to the present disclosure. As used herein, unless the context clearly indicates otherwise, the singular form is also intended to include the plural form. In addition, it should be understood that when the terms "comprising" and / or "including" are used in this specification, it indicates the presence of features, steps, operations, devices, components and / or combinations thereof.

[0051] Example 1

[0052] In one embodiment of the present disclosure, there is provided an indoor model loading system for determining factors affecting the service status of a cable-stayed bridge, including a water volume and water circulation electric control module, a temperature and humidity control module, an electric control jack module, a surround fan module, and an electric wheel load module simulating a vehicle load;

[0053] The water volume and water circulation electric control module controls the electric control water volume and water circulation for flushing the indoor model foundation, the temperature and humidity control module adjusts the ambient temperature and humidity, the electric control jack module controls the bridge displacement and angle change, the surround fan module adjusts the ambient wind speed and direction, and the electric wheel load module adjusts the vehicle load to actively interfere with the state of the cable with different variables, obtain monitoring data of the cable under different states, determine the service performance of the cable according to the monitoring data, and determine the key influencing factors affecting the service state of the cable-stayed bridge.

[0054] As an example, Figure 1 As shown, specifically, it includes an electronically controlled water volume control and water circulation module for foundation flushing, a temperature and humidity control module for adjusting ambient temperature and humidity, an electronically controlled jack module for bridge displacement and rotation angle, a 360° surround fan module for controlling ambient wind speed and direction, and an electric wheel load module for simulating vehicle loads.

[0055] Each module is powered by an electronic control module, and then connected to each other via serial communication. Each module is connected to a computer with appropriate hardware interfaces and software drivers to support communication and control. The switch and mode of each module are controlled by computer software.

[0056] The electric water volume control and water circulation module for foundation flushing includes a pipe body, a switchable water discharge port, a switchable water injection port, a water pipe, a water storage tank, a filter screen and a flow control mechanism. Figure 1 As shown, the water storage bucket can be placed near the water discharge port and the water injection port, so that the water pipe can absorb water into the pipeline body. The water in the pipeline body is ejected through the flow control mechanism to simulate foundation flushing. The filter net is used to filter impurities flushed down during foundation flushing. The switchable water discharge port, switchable water injection port, water pipe, and water storage bucket are used for water injection and discharge of the pipeline to achieve preliminary control of the water volume. The flow control system includes a water absorber and a water ejector, which can further control the flow rate and flow rate of water as needed.

[0057] Specifically, according to the requirements, the module is controlled by computer software, specifically to control the water absorption amount, water absorption rate, water injection amount and water injection rate of the flow control mechanism.

[0058] The temperature and humidity control module for adjusting the ambient temperature and humidity includes an air conditioner and a humidifying and dehumidifying device.

[0059] The electric control jack module for bridge displacement and angle rotation includes two electric control jacks. The jacks can move up and down, left and right, forward and backward. The forward and backward movement controls the longitudinal displacement, and the left and right movement controls the lateral displacement. The two jacks can achieve angle rotation by moving up and down with different amplitudes.

[0060] 360° surround fan module for ambient wind speed and direction control, including 360° exhaust vents.

[0061] The electric wheel-load module for simulating vehicle load includes a trolley body, a traction rope, and a traction mechanism with adjustable speed. According to the requirements, the computer software adjusts the pulling force of the traction mechanism, and then the traction mechanism applies the pulling force to the traction rope, and the traction rope can pull the trolley to move. When the trolley moves to the leftmost end, the traction mechanism on the right is started, and when the trolley moves to the rightmost end, the traction mechanism on the left is started.

[0062] As an embodiment, the loading method of the indoor model loading system for determining the influencing factors of the service status of the cable-stayed bridge is specifically as follows:

[0063] Step 1: Power on all modules of the electronically controlled loading system and the computer;

[0064] Step 2: Control the switches of each module through computer software according to the needs;

[0065] Step 3: Based on the requirements, the specific details of each module are controlled by computer software, such as water absorption rate, water injection rate, wind speed and direction of the fan module, displacement direction and amplitude of the jack, etc.

[0066] Example 2

[0067] In one embodiment of the present disclosure, a method for determining a service status influencing factor of a cable-stayed bridge is provided, comprising:

[0068] Step 1: Construct an indoor cable-stayed bridge scale model and divide the cable-stayed bridge scale model into three blocks;

[0069] Step 2: Select appropriate sensors and set appropriate monitoring points to obtain monitoring data of the scaled model of the cable-stayed bridge;

[0070] Step 3: Design a test method for the scaled model, use the loading system to change the state of the scaled model of the cable-stayed bridge, apply different vehicle loads and wind loads, control different variables, obtain the monitoring data of sensors under different states, and determine the influencing factors of the service performance state of the reaction cable, the influencing factors of the service performance state of the main beam, and the influencing factors of the service performance state of the tower.

[0071] As an embodiment, a method for determining key influencing factors of the service state of a cable-stayed bridge is provided, wherein an indoor bridge model of an electric-controlled loading system is used for loading. Figure 2 The following steps are shown:

[0072] S1: Divide the cable-stayed bridge into three blocks and determine the key factors of each block;

[0073] S2: Make a scaled model of the entire cable-stayed bridge, or make three blocks separately;

[0074] S3: Design model tests, select appropriate sensors, install sensors at appropriate locations according to specifications, and obtain relevant monitoring data;

[0075] S4: Determine the influencing factors of the service performance status of reactive stay cables based on model tests;

[0076] S5: Determine the influencing factors of the service performance status of the reaction main beam based on model tests;

[0077] S6: Determine the influencing factors of the service performance status of the reaction tower based on model tests;

[0078] S7: Apply the identified critical factors to actual bridges.

[0079] Specifically,

[0080] S1: Divide the cable-stayed bridge into three blocks and determine the key factors of each block. The three blocks of the cable-stayed bridge include the cable, main beam and tower.

[0081] S2: Make a scaled model of the entire cable-stayed bridge, or make three blocks separately. Figure 3 As shown, the specific steps are:

[0082] S21: Investigate the size and other physical characteristics of the original bridge, determine the size and proportion of the scaled test model, and determine that the geometric size ratio of each block is 1:10.

[0083] S22: Determine the similarity relationship between the scaled model and the original bridge, including the static characteristics similarity relationship and the dynamic characteristics similarity relationship. The similarity relationship includes the static characteristics similarity relationship and the dynamic characteristics similarity relationship, as described in the following table:

[0084] Table 1 Similarity relationship of static properties

[0085]

[0086] Table 2 Similarity relationship of dynamic characteristics

[0087]

[0088] S23: Based on S22 and the designed material properties, appropriate materials (such as wood, metal, concrete structures of different strengths, etc.) are used to make scale models, including cables, main beams, towers, and supports.

[0089] S3: Design a model test, select appropriate sensors, and install the sensors at appropriate locations according to the specifications. Figure 4 As shown, and obtain relevant monitoring data. The process is as follows Figure 5 As shown, the specific steps are as follows:

[0090] S31: First, the monitoring content should be determined according to the test purpose and existing conditions. Since the test purpose is to determine the key factors that reflect the service status of the cable, the monitoring content should be as comprehensive as possible. The monitoring content of the cable includes cable force, wire breakage, vibration, icing, and fixed status. In addition, it also includes environmental monitoring, wind speed and direction, temperature and humidity, etc.

[0091] S32: Determine the approximate model of the required sensor according to the functions of various sensors and the corresponding monitoring content. Cable force monitoring can use acceleration sensors; wire break detection can use acoustic emission sensors; vibration monitoring can use acceleration sensors; icing monitoring can use ultrasonic testing and video monitoring methods; fixed state can use pressure ring force sensors.

[0092] S33: The sensor model and installation location should be determined in accordance with the current relevant specifications and existing conditions, and the sensor should be installed to obtain monitoring data. The final sensor model should be further determined in the selected sensor type. Cable force and vibration sensors should be installed on all cables as much as possible in the scaled model test; cable icing sensors can be arranged near the top of the tower; fixed state monitoring should be determined according to the cable clamp type, cable clamp inclination angle and bolt arrangement.

[0093] S4: Determine the influencing factors of the service performance of the reaction cable based on the model test. Figure 6 As shown, the specific steps are:

[0094] S41: Actively interfere with the state of the cable through the electronically controlled loading system, change the state of the cable (anchorage state, wire breakage state, temperature and humidity), and apply different vehicle loads and wind loads.

[0095] S42: Acquire the monitoring data of all sensors, and use the expert scoring method to determine the service performance output index value of the inclined cable according to the cable force, wind speed and direction, vibration, temperature and humidity, wire breakage, anchoring status and other data monitored by the sensors.

[0096] An example of a scoring table is shown in Table 3 below. The specific cable status values ​​should be determined based on actual conditions and relevant specifications.

[0097] Table 3 Example of rating table for service performance of stay cables

[0098]

[0099] S43: The Long Short Term Memory (LSTM) algorithm is used to predict service performance. Different monitoring content data are used as input to obtain different prediction accuracies. If the prediction accuracy in the training set reaches more than 95%, the test set is continued, as shown in Table 4 below.

[0100]

[0101] S44: In the test set, if the prediction accuracy obtained by a few inputs reaches more than 90%, these parameters are determined as key factors. Key factors should be determined based on the prediction accuracy and the number of input parameters, so as to achieve higher accuracy with fewer parameters as much as possible.

[0102] S5: Determine the influencing factors of the service performance of the reaction beam based on the model test. Figure 7 As shown, the specific steps are:

[0103] S51: Control variables, change the status of monitoring contents (including strain, vibration, cracks in key sections, horizontal and vertical displacements, longitudinal displacements at beam ends, rotation angles at beam ends, temperature and humidity, support reaction forces, and support displacements) one by one through the electronically controlled loading system. In actual tests, some items can be pre-assumed as key factors, such as strain, vibration, and support reaction forces, based on experience, specifications, and literature. Adjust the horizontal and vertical displacements of the main beam, longitudinal displacements at beam ends, rotation angles at beam ends, temperature and humidity, support displacements, and cracks in key sections in turn.

[0104] To change the transverse and longitudinal displacements of the beam, tools such as jacks can be used to actively create the displacement of the beam; to change the vertical displacement of the beam, static loads or dynamic loads can be applied; for cracks in key sections, active destruction can be used to actively create cracks in key sections of the beam; to change the temperature and humidity, the ambient temperature and humidity of the indoor test can be controlled by equipment such as humidifiers and air conditioners.

[0105] S52: Use the sensor data to determine whether other monitoring contents have been significantly changed due to S51. In this embodiment, the monitoring contents include strain, vibration and support reaction force.

[0106] S53: Calculate the number of times each monitoring data changes significantly in multiple tests. If the changes in most monitoring contents can cause significant changes in certain monitoring contents, then determine these monitoring contents as key factors. In this embodiment, if the changes in the horizontal and vertical displacements of the main beam, the longitudinal displacements of the beam ends, the rotation angles of the beam ends, the temperature and humidity, the displacements of the supports, and the changes in the cracks in the key sections can all cause changes in strain, vibration, and support reaction force, then it means that strain, vibration, and support reaction force can reflect other contents. In theory, the changes in other contents can be inferred from strain, vibration, and support reaction force, and the hypothesis can be verified, and then strain, vibration, and support reaction force can be determined as key factors.

[0107] S6: Determine the influencing factors of the service performance of the reaction tower based on the model test. Figure 7 As shown, the specific steps are:

[0108] S61: Control variables, change the status of monitoring contents (including key section strain, vibration, wind speed and direction, deviation, inclination and foundation scour) one by one through the electronically controlled loading system.

[0109] Similar to S5, in actual experiments, it can be pre-assumed that certain items are key factors, such as strain and vibration of key sections, based on experience, specifications, and literature. Adjust the wind speed and direction, deflection, inclination, and foundation scour in turn. In this embodiment, if the changes in wind speed and direction, deflection, inclination, and foundation scour can all cause changes in strain, vibration, and support reaction force, it means that the strain and vibration of the key section can reflect the other contents. In theory, the changes in the other contents can be inferred from the strain and vibration of the key section, which can verify the hypothesis, and then determine that the strain and vibration of the key section are key factors.

[0110] S62: Use the sensor data to determine whether other monitoring contents have changed due to S61. In this embodiment, the other monitoring contents are the strain and vibration of the key cross section.

[0111] S63: Calculate the number of times each monitoring data changes significantly in multiple tests. If changes in most monitoring contents can cause significant changes in certain monitoring contents, then determine these monitoring contents as key factors.

[0112] S7: Apply the determined key factors to the actual bridge. The specific steps are:

[0113] S71: Determine the sensors corresponding to the key factors in the scaled model test and their layout locations.

[0114] S72: According to the relevant contents determined in S71, corresponding sensors are arranged at corresponding positions of the actual bridge.

[0115] S73: Acquire monitoring data and monitor the actual service status of the bridge in real time.

[0116] The present disclosure is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems), and computer program products according to the embodiments of the present disclosure. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of the processes and / or boxes in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0117] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0118] Although the above describes the specific implementation methods of the present disclosure in conjunction with the accompanying drawings, it is not intended to limit the scope of protection of the present disclosure. Technical personnel in the relevant field should understand that on the basis of the technical solution of the present disclosure, various modifications or variations that can be made by those skilled in the art without creative work are still within the scope of protection of the present disclosure.

Claims

1. Indoor model loading system for determining the influencing factors of the service status of cable-stayed bridges, It is characterized in that It includes water volume and water circulation electronic control module, temperature and humidity control module, electronic jack module, surround fan module and electric wheel load module simulating vehicle load; each module is powered by the electronic control module and is connected to each other through serial communication; Active interference of different variables on the state of the cable is performed by controlling the electrically controlled water volume and water circulation of the indoor model foundation flushing through the water volume and water circulation electronic control module, adjusting the ambient temperature and humidity through the temperature and humidity control module, controlling the bridge displacement and angle change through the electronic control jack module, adjusting the ambient wind speed and direction through the surround fan module, and adjusting the vehicle load through the electric wheel load module. The active interference includes changing the anchoring state, wire breaking state, temperature and humidity of the cable, and applying different vehicle loads and wind loads; Obtain monitoring data of the cable under different states, specifically: determine the required sensor model according to the function of each sensor and the one-to-one correspondence with the monitoring content: use acceleration sensor for cable force monitoring, acoustic emission sensor for wire break detection, acceleration sensor for vibration monitoring, ultrasonic test method and video monitoring method for icing monitoring, and pressure ring force sensor for fixed state; According to the cable force, wind speed and direction, vibration, temperature and humidity, wire breakage, and anchorage status data obtained from monitoring data, the service performance output index value of the inclined cable is determined by the expert scoring method; Long short-term memory network is used to predict service performance. Different monitoring content data are used as input to obtain different prediction accuracies. The output prediction value is compared with the index value to determine the prediction accuracy. If the prediction accuracy obtained by certain inputs reaches more than 90%, these parameters are determined to be key factors. The loading system is used to change the state of the scaled model of the cable-stayed bridge, apply different vehicle loads and wind loads, control different variables, obtain monitoring data of sensors under different states, and determine the influencing factors of the service performance state of the reaction cable, the influencing factors of the service performance state of the main beam, and the influencing factors of the service performance state of the tower, including: Construct an indoor cable-stayed bridge scale model, which is divided into three blocks, including cable-stayed cables, main beams and cable towers; Construct an indoor cable-stayed bridge scale model, including: Collect the dimensions and physical characteristics of the original cable-stayed bridge to determine the size and proportion of the scaled model; Determine the similarity between the scaled model and the original cable-stayed bridge; According to the required material properties, choose appropriate materials to make scale models; Determine the similarity relationship between the scaled model and the original bridge, including the static characteristics similarity relationship and the dynamic characteristics similarity relationship; the static characteristics similarity relationship includes material characteristics, geometric characteristics and loads, the material characteristics include elastic modulus, strain, stress, Poisson's ratio and mass density, the geometric characteristics include length, linear displacement, angular displacement, area and moment of inertia, and the loads include concentrated loads, linear loads and concentrated bending moments; Similar relations for dynamic characteristics include mass, stiffness, damping, and frequency; Methods for determining the influencing factors of the service performance status of the reaction beam include: Control variables, change the monitoring contents one by one through the loading system, namely, the state of strain, vibration, cracks in key sections, horizontal and vertical displacements, longitudinal displacements at beam ends, beam end rotation angles, temperature and humidity, support reaction forces, and support displacements; Obtain and analyze data to identify monitoring data that vary significantly in each trial; Calculate the number of times each monitoring data changes significantly in multiple tests. If changes in most monitoring contents can cause significant changes in several monitoring contents, then determine these monitoring contents as key factors. The long short-term memory network algorithm is used to predict the service performance. Different monitoring content data are used as input to obtain different prediction accuracies. The number of times each monitoring data changes significantly in multiple tests is calculated. If the changes in most monitoring contents can cause significant changes in certain monitoring contents, these monitoring contents are determined to be key factors; if the changes in the horizontal and vertical displacements of the main beam, the longitudinal displacements of the beam ends, the rotation angles of the beam ends, the temperature and humidity, the displacements of the supports, and the changes in the cracks in the key sections can all cause changes in strain, vibration, and support reaction force, it means that strain, vibration, and support reaction force can reflect several other contents; by inferring the changes in several other contents through strain, vibration, and support reaction force, the hypothesis can be verified, and then strain, vibration, and support reaction force can be determined to be key factors.

2. The indoor model loading system for determining the influencing factors of the service status of a cable-stayed bridge according to claim 1, It is characterized in that The water volume and water circulation electronic control module includes a pipeline body, a switchable water discharge port, a switchable water injection port, a water pipe, a water storage tank, a filter and a flow control mechanism. The filter is used to filter impurities brushed off during foundation flushing. The switchable water discharge port, the switchable water injection port, the water pipe and the water storage tank are used to fill and discharge water from the pipeline to achieve preliminary control of the water volume. The flow control mechanism includes a water absorber and a water ejector, which are used to further control the water flow and flow rate as needed.

3. The indoor model loading system for determining the influencing factors of the service status of a cable-stayed bridge according to claim 1, It is characterized in that The temperature and humidity control module includes an air conditioner and a humidifier-dehumidifier for adjusting the temperature and humidity of the environment; the electric control jack module includes an electric control jack, the surround fan module includes a 360° exhaust port, and the electric wheel-mounted module includes a trolley body, a traction rope and a traction mechanism with adjustable speed.

4. Methods for determining factors affecting the service status of cable-stayed bridges, It is characterized in that include: Construct an indoor cable-stayed bridge scale model and divide the cable-stayed bridge scale model into three blocks; Select appropriate sensors and set appropriate monitoring points to obtain monitoring data of the scaled model of the cable-stayed bridge; Design a test method for the scale model, use the loading system as described in any one of claims 1 to 3 to change the state of the scale model of the cable-stayed bridge, apply different vehicle loads and wind loads, control different variables, obtain monitoring data of sensors under different states, and determine the influencing factors of the service performance state of the reaction cable, the influencing factors of the service performance state of the main beam, and the influencing factors of the service performance state of the cable tower; The scaled model of the cable-stayed bridge is divided into three blocks, including the cable, main beam and tower; Construct a scale model of an indoor cable-stayed bridge, including: Collect the dimensions and physical characteristics of the original cable-stayed bridge to determine the size and proportion of the scaled model; Determine the similarity between the scaled model and the original cable-stayed bridge; According to the required material properties, choose appropriate materials to make scale models.

5. The method for determining the influencing factor of the service state of a cable-stayed bridge according to claim 4, It is characterized in that Select appropriate sensors and set appropriate monitoring points to obtain monitoring data of the scale model of the cable-stayed bridge, including: Determine the sensor monitoring content according to the test purpose and existing needs, determine the functions of various sensors and correspond to the monitoring content, and determine the required sensor models; Determine the sensor model and installation location based on relevant specifications and existing conditions, and install the sensor to obtain monitoring data.

6. The method for determining the influencing factor of the service state of a cable-stayed bridge according to claim 4, It is characterized in that Methods for determining the influencing factors of the service performance status of the reaction beam include: Control variables, change the monitoring contents one by one through the loading system, namely, the state of strain, vibration, cracks in key sections, horizontal and vertical displacements, longitudinal displacements at beam ends, beam end rotation angles, temperature and humidity, support reaction forces, and support displacements; Obtain and analyze data to identify monitoring data that vary significantly in each trial; Calculate the number of times each monitoring data changes significantly in multiple tests. If changes in most monitoring contents can cause significant changes in certain monitoring contents, then determine these monitoring contents as key factors.

7. The method for determining the influencing factor of the service state of a cable-stayed bridge according to claim 4, It is characterized in that The method for determining the influencing factors of the service performance status of the reaction tower is: Control variables, change the monitoring contents one by one through the loading system, namely the key section strain, vibration, wind speed and direction, deflection, inclination and foundation scour status; Obtain and analyze data to identify monitoring data that vary significantly in each trial; Calculate the number of times each monitoring data changes significantly in multiple tests. If changes in most monitoring contents can cause significant changes in certain monitoring contents, then determine these monitoring contents as key factors.

Images