A method for analyzing stress performance of a combined cable-stayed bridge and related equipment

Abstract

The application provides a method for analyzing stress performance of a combined cable-stayed bridge and related equipment, and applies to the technical field of data processing. The application obtains target tower information, a target event set matched with the target tower information, a training sample set and a preset cable-stayed bridge cable force prediction model; the training sample set is pretreated to generate a training sample set with target feature data; the preset cable-stayed bridge cable force prediction model is processed based on the training sample set with target feature data to generate a target cable-stayed bridge cable force prediction model; the target event set matched with the target tower information is processed to generate tower cable force early warning information of a target tower bridge; the target tower information is processed based on the target cable-stayed bridge cable force prediction model to generate attribute information of the target tower; and the attribute information of the target tower and the tower cable force early warning information of the target tower bridge are processed based on the target cable-stayed bridge cable force prediction model to generate target cable force early warning information of the target tower information.

Description

Technical Field

[0001] This invention relates to the field of data processing technology, and in particular to a method and related equipment for analyzing the stress performance of a combined cable-stayed bridge. Background Technology

[0002] The stay cables are key components in cable-stayed bridges that transmit loads, and changes in their internal forces have a significant impact on the overall stress state of the bridge. After several years of service, cable-stayed bridges are subjected to adverse long-term loads and external environmental factors, leading to cable deterioration and abnormal changes in cable forces. The actual cable forces will inevitably deviate from the cable forces under normal operating conditions, which can seriously affect the overall stress state and safe operation of the bridge.

[0003] For cable-stayed bridges, the stiffness and load-bearing capacity of the bridge deck structure are typically low, especially with large spans. This design characteristic necessitates that the main loads of the bridge be borne by multiple stay cables. The robustness of the stay cables, i.e., their ability to maintain performance under adverse conditions, becomes a key factor in ensuring the overall structural safety of the bridge. It is important to note that the stay cables in a cable-stayed bridge do not operate independently; the forces acting on each cable are influenced by and also affect the forces acting on the other cables in the bridge. This interdependence means that if one or more cables fail, it can lead to a redistribution of internal forces throughout the cable-stayed system, potentially triggering a "button-unbuttoning" effect that can cause the failure of the cable-stayed system and even the entire cable-stayed bridge. Therefore, timely assessment of the cable stress state of long-span cable-stayed bridges is crucial for evaluating the overall stress state of the bridge.

[0004] It should be noted that the information disclosed in the background section above is only used to enhance the understanding of the background of this disclosure, and therefore may include information that does not constitute prior art known to those skilled in the art. Summary of the Invention

[0005] The purpose of this application is to provide a method and related equipment and system for analyzing the stress performance of composite cable-stayed bridges, which at least to some extent overcomes the problems existing in the prior art. By conducting long-term stress performance analysis on single-tower or multi-tower cable-stayed bridges with composite decks, automation can be maximized. Furthermore, considering long-term effects and geometric nonlinearity, the simulation of cable-stayed bridge structures can be achieved more realistically and efficiently, assisting in structural design and operation and maintenance.

[0006] Other features and advantages of this application will become apparent from the following detailed description, or may be learned in part by practice of the invention.

[0007] According to one aspect of this application, a method for analyzing the stress performance of a combined cable-stayed bridge is provided, comprising: acquiring target bridge tower information, a target event set matching the target bridge tower information, and a training sample set, wherein the target bridge tower information includes first beam element information for characterizing the main girder steel structure, second beam element information for characterizing the concrete bridge deck, and third beam element information for characterizing the cable-stayed structure, and the training sample set is used to characterize other bridge tower information matching the target bridge tower information; preprocessing the training sample set to generate a training sample set with target feature data, wherein the target feature data is used to characterize risk factors affecting the cable forces of the bridge towers; and acquiring a preset cable force prediction model for the cable-stayed bridge, wherein the preset cable force prediction model is based on the target bridge towers. The process involves: generating a target cable-stayed bridge cable force prediction model based on historical structural information; processing the preset cable-stayed bridge cable force prediction model using the training sample set containing target feature data; processing the target event set matching the target bridge tower information to generate early warning information for the target bridge tower cable force; processing the target bridge tower information using the target cable-stayed bridge cable force prediction model to generate attribute information for the target bridge tower, wherein the attribute information of the target bridge tower includes the initial cable force, target temperature load value, and material shrinkage and creep value of the target bridge tower; and processing the attribute information of the target bridge tower and the early warning information for the target bridge tower cable force based on the target cable-stayed bridge cable force prediction model to generate early warning information for the target cable force of the target bridge tower.

[0008] Another aspect of this application discloses a stress performance analysis device for a combined cable-stayed bridge, characterized in that it comprises: an acquisition module for acquiring target bridge tower information, a target event set matching the target bridge tower information, and a training sample set, wherein the target bridge tower information includes first beam element information for characterizing the main girder steel structure, second beam element information for characterizing the concrete bridge deck, and third beam element information for characterizing the cable-stayed structure, and the training sample set is used to characterize other bridge tower information matching the target bridge tower information; acquiring a preset cable-stayed bridge cable force prediction model, wherein the preset cable-stayed bridge cable force prediction model is generated based on historical structural information of the target bridge tower information; and a processing module for preprocessing the training sample set to generate a training sample set with target feature data, wherein the... The target feature data is used to characterize the risk factors affecting the cable force of the bridge tower; the preset cable force prediction model for cable-stayed bridge is processed based on the training sample set containing the target feature data to generate a target cable force prediction model for cable-stayed bridge; the target event set matching the target bridge tower information is processed to generate early warning information on the cable force of the target bridge tower; the target bridge tower information is processed based on the target cable force prediction model to generate attribute information of the target bridge tower, wherein the attribute information of the target bridge tower includes the initial cable force, the target temperature load value, and the material shrinkage and creep value of the target bridge tower; the target cable force prediction model is used to process the attribute information of the target bridge tower and the early warning information on the cable force of the target bridge tower to generate early warning information on the cable force of the target bridge tower.

[0009] According to another aspect of this application, an electronic device is characterized by comprising: a first processor; and a memory for storing executable instructions of the first processor; wherein the first processor is configured to execute the above-described method for analyzing the stress performance of a combined cable-stayed bridge by executing the executable instructions.

[0010] According to another aspect of this application, a computer-readable storage medium is provided having a computer program stored thereon, which, when executed by a second processor, implements the above-described method for analyzing the stress performance of a combined cable-stayed bridge.

[0011] According to another aspect of this application, a computer program product is provided, comprising a computer program, characterized in that, when the computer program is executed by a third processor, it implements the above-described method for analyzing the stress performance of a combined cable-stayed bridge.

[0012] This application provides a method and related equipment for analyzing the stress performance of a combined cable-stayed bridge. The method involves acquiring relevant information about the target bridge tower, a matched event set, and a training sample set. The target bridge tower information includes beam element information for the main girder steel structure, concrete bridge deck, and cable-stayed structure. The training sample set is then preprocessed through steps such as obtaining a pre-defined mapping table for grouping, feature extraction, dataset partitioning, classifier prediction, and algorithm training to generate a training sample set containing target feature data representing factors influencing the cable force risk of the bridge tower. Then, a pre-defined cable force prediction model for the cable-stayed bridge is used to generate a cable force prediction model for the target cable-stayed bridge based on the processed training sample set. For the target event set, type information, historical cable force value information, cable force influencing factors, and weight information are obtained through processing, thereby generating early warning information for the bridge tower cable force. When generating the target bridge tower attribute information, multiple sets of cable force values ​​are generated by obtaining the beam element bending stiffness values ​​under different bearing weights. Combined with incremental step information, the target temperature load value is obtained. Simultaneously, effective creep strain, stress increment, true elastic strain, and true creep strain are calculated based on material information to determine the material shrinkage and creep value. Finally, based on the model, the target bridge tower attribute information and bridge tower cable force early warning information are processed to calculate the target cable force value and cable force early warning value, thereby generating target cable force early warning information and providing comprehensive analysis and prediction for target bridge tower cable force early warning.

[0013] It should be understood that the above general description and the following detailed description are exemplary and explanatory only, and are not intended to limit this disclosure. Attached Figure Description

[0014] Figure 1 A flowchart illustrating a method for analyzing the stress performance of a composite cable-stayed bridge according to an embodiment of this application is shown.

[0015] Figure 2 A schematic diagram of the structure of a stress performance analysis device for a combined cable-stayed bridge provided in an embodiment of this application is shown;

[0016] Figure 3 This illustration shows a schematic diagram of the structure of an electronic device according to an embodiment of this application;

[0017] Figure 4 A schematic diagram of a storage medium provided in one embodiment of this application is shown. Detailed Implementation

[0018] The preferred embodiments of the present invention will be described below with reference to the accompanying drawings. It should be understood that the preferred embodiments described herein are for illustration and explanation only and are not intended to limit the present invention.

[0019] The following is combined with Figure 1This application describes a method for analyzing the stress performance of a combined cable-stayed bridge according to exemplary embodiments thereof. It should be noted that the following application scenarios are shown only to facilitate understanding of the spirit and principles of this application, and the embodiments of this application are not limited in any way. Rather, the embodiments of this application can be applied to any applicable scenario.

[0020] In one embodiment, this application also proposes a method and related equipment for analyzing the stress performance of a combined cable-stayed bridge. Figure 1 A schematic flowchart illustrating a method for analyzing the stress performance of a combined cable-stayed bridge according to an embodiment of this application is shown. Figure 1 As shown, this method is applied to a server and includes:

[0021] S101, acquire target bridge tower information, target event set matching the target bridge tower information, and training sample set.

[0022] In one implementation, the target bridge tower information includes first beam element information characterizing the main girder steel structure, second beam element information characterizing the concrete bridge deck, and third beam element information characterizing the cable-stayed structure. A training sample set is used to characterize other bridge tower information that matches the target bridge tower information. Specifically, the first beam element information (main girder steel structure): Assuming the main girder steel structure consists of multiple steel beams, the first beam element information may include the cross-sectional dimensions of each steel beam (e.g., height, width, thickness), the material properties of the steel beam (e.g., elastic modulus, yield strength), the connection method between the steel beams (welding, bolting, etc.), and the position coordinates of the steel beam in the bridge tower (e.g., coordinates along the bridge length and vertically). For example, a steel beam has a cross-sectional height of 1.5 meters, a width of 0.5 meters, a thickness of 0.05 meters, an elastic modulus of 200 GPa, a yield strength of 345 MPa, and is welded to adjacent steel beams. Its coordinates in the bridge tower are (10 meters, 5 meters). Second beam unit information (concrete bridge deck): For concrete bridge decks, the second beam unit information can include the concrete strength grade (e.g., C40, C50, etc.), the thickness of the bridge deck, the concrete mix ratio (proportion of cement, aggregate, water, etc.), the reinforcement details within the bridge deck (diameter, spacing, and arrangement of reinforcing bars, etc.), and the connection method between the bridge deck and the main beam steel structure (e.g., connection via shear studs). For example, the concrete bridge deck is 0.3 meters thick, with a strength grade of C50, a mix ratio of cement:aggregate:water = 1:2:0.4, and reinforced with 16mm diameter reinforcing bars spaced 0.2 meters apart, arranged in a double layer and bidirectional manner, connected to the main beam via 22mm diameter shear studs. Third beam unit information (cable-stayed structure): The third beam unit information for cable-stayed structures includes the material of the cable (e.g., high-strength steel wire, steel strand, etc.), the cable diameter, the cable length, the initial tension of the cable, and the anchorage method between the cable and the main beam and bridge tower, etc. For example, the stay cables are made of high-strength steel wire with a diameter of 7mm, with a cable length of 100 meters and an initial tension of 500kN. They are anchored at the main beam and bridge tower using hot-cast anchors.

[0023] The training sample set contains similar information from several other bridge towers that match the target tower's information. For example, there are three other bridge towers. The first tower has a different main beam cross-section than the target tower: a height of 1.2 meters, a width of 0.6 meters, a thickness of 0.04 meters, a material elastic modulus of 180 GPa, a yield strength of 300 MPa, and a bolted connection. Its concrete deck is 0.25 meters thick, with a strength grade of C45, a slightly different mix design, and reinforcement diameters of 14 mm with a spacing of 0.25 meters. The stay cables are made of the same material but have a diameter of 6.5 mm, a length of 95 meters, and an initial tension of 450 kN. The second and third towers also have their own different parameter information. This information from different towers is combined to form the training sample set, used for subsequent model training and analysis to help predict the target tower's cable force and other performance characteristics under different conditions.

[0024] Examples of target event sets matching the target bridge tower information are as follows: Earthquake Event: A magnitude 5.5 earthquake occurred locally, with the epicenter 20 kilometers from the target bridge tower. Parameters such as ground acceleration and duration of vibration during the earthquake constitute the specific information of this earthquake event. For example, the peak horizontal ground acceleration reached 0.2g, the peak vertical ground acceleration was 0.15g, and the duration of vibration was approximately 30 seconds. This earthquake event will have varying degrees of impact on the structure of the target bridge tower, such as causing displacement of the tower foundation and increased vibration of the stay cables, thus affecting cable tension. Strong Wind Event: The area where the target bridge tower is located experienced a 12-hour period of strong winds, with maximum wind speeds reaching 40 m / s (equivalent to a Force 13 gale), primarily from the northwest. Strong winds acting on the bridge tower and main beam will generate significant wind loads, producing lateral forces and torques on the tower structure, causing the stay cables to experience additional tensile or compressive stress changes. For example, strong winds can cause the main beam to undergo a certain lateral displacement, with a maximum displacement of 0.5 meters. This can affect the cable force distribution of the stay cables through structural transmission.

[0025] Overweight vehicle crossing the bridge: An overweight truck exceeding the bridge's design weight limit by 50% (e.g., the bridge's design weight limit is 50 tons, and the truck's actual weight is 75 tons) crosses the bridge containing the target tower. Information such as the vehicle's axle load distribution, speed, and trajectory on the bridge constitutes the characteristics of this event. Overweight vehicles subject the bridge structure to greater loads, particularly significantly affecting the main girder and stay cables. For example, when the vehicle passes, a significant bending deformation occurs in the main girder near one side of the stay cable, causing a 20% instantaneous increase in the cable stress on that side. Traffic congestion event: During a peak period, severe traffic congestion occurs on the bridge containing the target tower, with vehicle density reaching three times the normal traffic density, resulting in slow or even stopped traffic. Prolonged traffic congestion subjectes the bridge structure to continuous dynamic loads, different from the stress conditions under normal traffic flow. In this situation, the impact forces generated by frequent vehicle starts and stops accumulate, exacerbating fatigue damage to the tower and stay cables, affecting the long-term stability of the cable stress. For example, monitoring revealed that during periods of traffic congestion, the frequency of cable tension fluctuations increased, and the amplitude of fluctuations increased by 10% compared to normal conditions.

[0026] Excavation event near the target bridge tower: A large foundation pit excavation project was carried out 50 meters around the target bridge tower, with an excavation depth of 10 meters and an excavation area of ​​100 meters long and 80 meters wide. The excavation process will cause stress release and displacement of the surrounding soil, affecting the bridge tower foundation. For example, the excavation caused a 5-centimeter horizontal displacement of the soil near the bridge tower foundation, which will cause the bridge tower to tilt to a certain extent, thus changing the stress state of the stay cables, resulting in uneven changes in cable force, with some cable forces increasing or decreasing. Foundation construction event of adjacent building: A high-rise building is undergoing foundation piling construction 80 meters away from the target bridge tower, using a hammer-driven piling machine. The vibration and soil displacement effect generated during the piling process will propagate to the bridge tower structure. The frequency of the piling vibration is 15 Hz, the amplitude is 2 mm, and the soil displacement pressure is estimated to be 100 kPa. These factors will cause vibration response of the bridge tower, affecting the cable force stability of the stay cables. For example, monitoring found that during piling, the cable force of some stay cables fluctuated periodically, with the maximum fluctuation amplitude reaching 15 kN.

[0027] S102, preprocess the training sample set to generate a training sample set with target feature data.

[0028] In one implementation, a preset mapping table is obtained, wherein the preset mapping table is used to characterize the historical structural information of the target bridge tower and the corresponding information of the historical event set of the target bridge tower. Assume the target bridge tower is a cable-stayed bridge tower located on a main urban road. The preset mapping table records the correspondence between the historical structural information of the bridge tower and the historical event set over the past ten years. For example, regarding the historical structural information, it records the maintenance and reinforcement of the main beam steel structure of the bridge tower in different years (e.g., the replacement of part of the main beam steel in 2015), the repair records of the concrete bridge deck (e.g., grouting treatment of local cracks in the bridge deck in 2018), and the replacement or adjustment records of the stay cables (e.g., the replacement of two stay cables in 2020), etc. Simultaneously, corresponding historical events that occurred during the same period were recorded in relation to these structural changes. For example, a magnitude 4.5 earthquake occurred nearby in 2015 (although it did not cause serious damage to the bridge towers, it affected the structural condition); the bridge experienced a flood in 2018 (the floodwaters reached a certain height near the bridge tower foundations); and in 2020, due to increased traffic flow, bridge overloading became more frequent. This information constitutes a pre-defined mapping table, used for subsequent analysis of the correlation between different structural states and events.

[0029] The training sample set is grouped based on a pre-defined mapping table to generate a grouped training sample set. This grouped training sample set includes monitoring points to be predicted for different monitoring lengths. The training sample set also includes information on other similar bridge towers. According to the pre-defined mapping table, these bridge towers are grouped according to different monitoring lengths. For example, monitoring lengths are set to 1 year, 3 years, and 5 years. For the 1-year monitoring group, bridge towers with similar structural maintenance records in the past year (e.g., local reinforcement of steel beams) and similar changes in the surrounding environment (e.g., small-scale construction activities nearby) are selected as monitoring points to be predicted. For the 3-year monitoring group, bridge towers that have undergone significant structural adjustments within the past three years (e.g., bridge deck repaving) and experienced certain climate disasters (e.g., multiple rainstorms) are selected. For the 5-year monitoring group, attention is paid to bridge towers that have undergone cable-stayed bridge adjustments within the past five years and whose local traffic flow has changed significantly. This generates a grouped training sample set, with bridge towers in each group having similar monitoring periods and characteristics.

[0030] Feature extraction is performed on the grouped training sample sets to determine the original feature library. For the grouped training sample sets, feature extraction begins. Taking the group with a monitoring length of one year as an example, the extracted features include: the maximum horizontal displacement of the bridge towers within that year (obtained through sensor monitoring), the maximum stress change value of the main beam steel structure (calculated based on strain gauge measurement data), the crack development rate of the concrete bridge deck (based on periodic inspection records), the cable force variation amplitude of the stay cables (data from the cable force monitoring system), the range of ambient temperature variation (data from meteorological stations), and the daily average and peak variations of traffic flow (data from traffic monitoring equipment). These features are then summarized to form the original feature library for this group. Similar methods are used to extract corresponding features for other monitoring lengths. For example, for the group with a monitoring length of three years, features such as structural material performance change indicators (e.g., concrete strength decay rate) can be added; for the group with a monitoring length of five years, long-term cable force fatigue damage factors can be considered.

[0031] The original feature library is divided into several feature datasets to generate training and validation sets. Assume the original feature library contains 100 features (considering all groups). These datasets are divided into training and validation sets according to a certain ratio (e.g., 70% and 30%). For example, 70 features are randomly selected as the training set to train the prediction model; the remaining 30 features are used as the validation set to test the model's accuracy. During the partitioning process, it is crucial to ensure that the data in both the training and validation sets are representative and cover different types of bridge tower structural states and environmental conditions. For instance, the training set should include feature data from bridge towers that have experienced minor natural disasters as well as those subjected to significant traffic load changes; the validation set should follow the same principle and have a similar data distribution to the training set to avoid data bias that could lead to overfitting or underfitting of the model.

[0032] The classifier performs prediction processing on each validation set divided from the original feature library to generate prediction results. A Support Vector Machine (SVM) classifier is used to process the validation sets. The SVM classifier classifies and predicts the bridge tower feature data in the validation set based on the feature patterns learned from the training set. For example, it predicts whether a bridge tower will experience cable tension anomalies (categorized as normal or abnormal) in the future. For each bridge tower feature data in the validation set, the SVM classifier calculates the probability that it belongs to a normal or abnormal cable tension state. For example, for a certain bridge tower, after its feature data is input into the SVM classifier, the probability of belonging to a normal cable tension state is 0.7, and the probability of belonging to an abnormal state is 0.3. These predicted probabilities are used as prediction results for subsequent comparison with actual conditions to evaluate the classifier's performance.

[0033] The model is trained on various training sets defined in the original feature library using a pre-defined algorithm to generate validation set prediction results. A neural network algorithm is used to train the training set. The neural network consists of an input layer (receiving bridge tower feature data), a hidden layer (converting and learning data features), and an output layer (outputting prediction results). For example, the input layer has 10 nodes, corresponding to 10 key bridge tower features (such as main beam stress, cable force changes, etc.); the hidden layer has 3 layers, with 20, 15, and 10 nodes per layer, respectively; the output layer has 2 nodes, representing normal and abnormal cable force states. Through multiple iterations of training, the weights and thresholds of the neural network are adjusted to enable the model to accurately predict cable force states based on the input training set feature data. The trained model is then applied to the validation set to obtain validation set prediction results, i.e., predictions of the cable force state (normal or abnormal) for each bridge tower in the validation set.

[0034] The prediction results and validation set prediction results are processed to generate target feature data, which is used to characterize the risk factors affecting the cable force of bridge towers. The prediction results obtained from the SVM classifier (such as the predicted probability of each bridge tower cable force state) and the validation set prediction results obtained from the neural network (such as the specific cable force normal or abnormal classification) are combined. For example, the consistency ratio between the two is calculated. If the SVM predicts a normal probability of cable force for a bridge tower is 0.8, and the neural network also predicts that the cable force of that bridge tower is normal, then the consistency ratio of that bridge tower is high. This consistency ratio, the average predicted probability, and other information are used as target feature data. This target feature data can characterize the risk factors affecting the cable force of bridge towers. For example, a high consistency ratio indicates that the model's prediction of the cable force state of that bridge tower is relatively reliable and can serve as an important basis for risk assessment; an average predicted probability close to 0.5 indicates that the cable force state of that bridge tower is on the verge of instability and there is a high risk.

[0035] S103, Obtain the preset cable force prediction model for cable-stayed bridges.

[0036] In one implementation, the pre-defined cable-stayed bridge cable force prediction model consists of the following models: a structural mechanics analysis module: based on historical structural information of the target bridge tower, this module includes mechanical analysis models for the bridge tower, main girder steel structure, concrete bridge deck, and cable structure. For example, for the main girder steel structure, a beam element model is used to calculate the internal forces (bending moment, shear force, axial force) and deformations (deflection, rotation) of the steel beam under different loads. The model considers the cross-sectional properties of the steel beam (such as moment of inertia, cross-sectional area), material elastic modulus, and the influence of node connection methods on mechanical performance. For the concrete bridge deck, a plate and shell element model is used to analyze its stress distribution and deformation under factors such as vehicle loads and temperature changes, while also considering the nonlinear characteristics of concrete (such as cracking and creep). The cable-stayed bridge uses a cable element model to simulate its axial force characteristics under tension, considering factors such as cable sag effect and elastic modulus change. By combining these mechanical models of different structures, the mechanical response of the entire cable-stayed bridge structure under various working conditions can be accurately simulated, providing a basis for cable force prediction.

[0037] Data-Driven Prediction Module: This module utilizes a wealth of monitoring data (such as cable force values, temperature changes, traffic flow, and structural deformation at different times) from the historical structural information of the target bridge tower for model training. For example, a neural network algorithm is employed, with input layer nodes corresponding to different monitoring data types (such as cable force, temperature, and traffic flow), and output layer nodes representing the predicted cable force values. The hidden layer learns from historical data to establish a complex nonlinear relationship between the input data and the output cable force. During training, the model continuously adjusts the connection weights between neurons to minimize the error between the predicted cable force and the actual monitored cable force. Simultaneously, time series analysis methods, such as the ARIMA (Autoregressive Moving Average) model, can be used to predict future cable force values ​​based on historical patterns of cable force variation. This module effectively mines information from historical data, improving the accuracy of cable force prediction.

[0038] Environmental Impact Assessment Module: Considering the impact of environmental factors on cable forces, this module models the target bridge tower based on historical environmental data (such as temperature variation range, humidity variation, and historical wind load records). For example, a temperature-cable force relationship model is established to analyze the impact of thermal expansion and contraction of materials caused by temperature changes on cable forces, taking into account the periodic patterns of temperature changes in different seasons and between day and night. For wind loads, a dynamic response model between wind loads and cable forces is established using wind tunnel test data or field-measured wind data, analyzing the impact of different wind speeds and directions on the vibration characteristics of stay cables and changes in cable forces. Humidity changes affect the material properties of the concrete bridge deck and stay cables, thus affecting cable forces. This module also performs a quantitative assessment of this, incorporating environmental factors into the cable force prediction model to make the prediction results more consistent with reality.

[0039] Uncertainty Analysis Module: Due to the complexity of bridge structures, the uncertainty of material properties, and the randomness of external loads, this module analyzes the uncertainties in cable force prediction. For example, considering the uncertainty of the elastic modulus of steel, its range of values ​​is described using a probability distribution (such as a normal distribution), and the impact of this uncertainty on the cable force prediction results is analyzed. For traffic loads, considering the randomness of vehicle type, weight, and speed, Monte Carlo simulation is used to generate a large number of random traffic load cases, calculate the cable force variation range under different conditions, and provide the confidence interval for cable force prediction. Simultaneously, the uncertainties of structural parameters (such as dimensional errors of the main beam and bridge towers, and the dispersion of concrete strength) are also quantitatively analyzed, providing a more comprehensive risk assessment for cable force prediction.

[0040] Historical structural information based on the target bridge tower includes the following: History of structural geometric dimension changes: This records the structural geometric dimensions of the target bridge tower at different times, such as changes in the length, width, and height of the main beam (due to maintenance, reinforcement, or long-term deformation), changes in the tower's verticality, and adjustments to the length of the stay cables. This information is used in the structural mechanics analysis module of the model to accurately update the structural geometric model, making the mechanical calculations more consistent with the actual structural state. For example, if the length of the main beam increases by 0.5 meters during a maintenance, the model will adjust the length parameters of the beam elements accordingly, thereby recalculating the internal forces and deformations under various loads, and consequently affecting the cable force prediction results.

[0041] Material performance evolution history: This includes data on the changes in the material properties of the concrete bridge deck and main steel structure over time, such as the increase and decrease in concrete strength, the accumulation of fatigue damage in the steel, and changes in the material's elastic modulus. In the model's mechanical analysis and prediction module, this data is used to update material parameters and more accurately simulate the mechanical behavior of the structure at different service stages. For example, as concrete strength decreases over time, the model will correspondingly reduce the load-bearing capacity calculation parameters of the concrete bridge deck, leading to a redistribution of internal forces and affecting the stress on the stay cables, thus correcting the cable force predictions.

[0042] Historical Load Records: These records detail the various loads borne by the target bridge tower, including traffic loads (changes in flow and weight distribution of different vehicle types over time), wind loads (wind speed and direction records under different seasons and weather conditions), and temperature loads (daily and annual temperature variation curves). This historical load data is crucial input to the environmental impact assessment and data-driven prediction modules within the model. For example, by analyzing years of traffic load data, the model can predict the trend of cable force changes under future traffic flow growth; based on the temperature load history, it can accurately calculate the seasonal fluctuations in cable force caused by temperature changes, improving the accuracy of cable force prediction.

[0043] Structural Maintenance and Reinforcement Records: These records document all past structural maintenance and reinforcement work performed on the target bridge tower, such as the replacement time and post-replacement cable tension adjustments, weld repair status of the main girder steel structure, and crack repair measures for the concrete bridge deck. These records are used for model updates and calibration, ensuring that the model reflects changes in the actual structural condition. For example, in the cable tension prediction model, when there is a cable replacement record, the model will recalculate the overall mechanical properties of the structure based on the replaced cable parameters (such as diameter, elastic modulus, initial tension, etc.), ensuring that subsequent cable tension predictions are based on the latest structural condition and improving the reliability of the prediction results.

[0044] Historical structural health monitoring data includes structural response data collected over a long period using various sensors (such as cable force sensors, strain gauges, and displacement sensors), such as historical cable force values ​​at different locations, strain changes in key parts of the main beam and bridge towers, and overall structural displacement monitoring data. This rich monitoring data forms the foundation for training the data-driven prediction module model. By learning from a large amount of historical monitoring data, the model can discover the intrinsic relationship between cable force and other structural responses, thereby accurately predicting future cable force changes. Simultaneously, historical monitoring data is also used to validate the model's accuracy. By comparing the predicted results with actual monitoring data, the model's parameters and algorithms are continuously optimized, improving the performance of the cable force prediction model.

[0045] S104, Based on the training sample set with target feature data, the preset cable-stayed bridge cable force prediction model is processed to generate the target cable-stayed bridge cable force prediction model.

[0046] In one implementation, it is assumed that the preset cable-stayed bridge cable force prediction model is constructed using a neural network algorithm. The neural network structure includes an input layer, hidden layers, and an output layer. The input layer nodes correspond to target feature data in the training sample set, such as bridge tower foundation settlement, main girder temperature changes, traffic flow levels, ambient humidity, current cable force values, and whether there have been recent earthquakes or strong wind events (represented by 0 / 1). The hidden layer consists of several layers (e.g., 2-3 layers), with the number of nodes in each layer determined according to actual conditions (e.g., 10-20 nodes), used to perform complex nonlinear transformations on the input data. The output layer nodes represent the predicted cable force values.

[0047] First, the training sample set containing target feature data is divided into a training set and a validation set, for example, in a 70%:30% ratio. Then, the training set data is input into a pre-defined neural network model for training. During training, the weights and thresholds of the neural network are adjusted using the backpropagation algorithm based on the difference (error) between the output predicted cable force value and the actual cable force value in the training sample set. For example, mean squared error (MSE) can be used as the loss function; this application does not limit the specific loss function, and the applicant can choose according to actual needs. Through continuous iterative training, the loss function value is gradually reduced until the set convergence condition is met (e.g., the loss function value is less than a certain threshold or the number of iterations reaches the upper limit). After training, the trained model is evaluated using a validation set. Evaluation metrics such as the model's prediction accuracy and root mean square error (RMSE) on the validation set are calculated. For example, prediction accuracy can be obtained by calculating the ratio of the number of correctly predicted cable force values ​​to the total number of samples in the validation set. If the evaluation metrics do not meet the requirements, the model is optimized. Optimization methods may include adjusting the neural network structure (such as increasing or decreasing the number of hidden layers or nodes), adjusting training parameters (such as learning rate or number of iterations), and using regularization techniques to prevent overfitting (such as L1 or L2 regularization).

[0048] For example, in one training iteration, the initial model had an RMSE of 50kN on the validation set. Analysis revealed that this was due to overfitting caused by an excessive number of hidden layer nodes. Therefore, the number of hidden layer nodes was reduced from 20 to 15, and the model was retrained. The new model's RMSE on the validation set decreased to 30kN, and the prediction accuracy improved from 70% to 80%, meeting the performance requirements. This model is now the optimized cable-stayed bridge cable force prediction model, which can be used to predict the cable forces of the target bridge towers.

[0049] When real-time monitoring data of the target bridge tower is obtained (including target feature data of the same type as the training sample set), this data is input into the cable force prediction model of the target cable-stayed bridge, and the model can output the predicted cable force value. For example, if real-time monitoring shows that the current main girder temperature of the target bridge tower has increased by 10°C, traffic flow is at a moderate level, ambient humidity is 60%, the current cable force is 1000kN, and there are no recent earthquakes or strong wind events, this data is processed into the same format as the training sample set and input into the model. The model then calculates and outputs a predicted cable force value of 1020kN for the next time period. By continuously inputting real-time data, the model can continuously predict the trend of cable force changes, providing important reference for the operation and maintenance of the bridge.

[0050] S105, process the target event set that matches the target bridge tower information, and generate bridge tower cable force early warning information for the target bridge tower.

[0051] In one implementation, a set of target events matching the target bridge tower information is processed to generate type information for the target events. This type information characterizes the risk warning level of the target events for the target bridge tower. Assume the set of target events matching the target bridge tower information includes the following events: Earthquake event: A magnitude 5.0 earthquake occurred in the area where the target bridge tower is located, with the epicenter approximately 30 kilometers from the tower. Based on the earthquake's magnitude, epicentral distance, and local geological conditions, this earthquake event is classified as a medium-risk event, corresponding to a risk warning level of 3 (the risk warning level range is set from 1 to 5, where 1 is low risk and 5 is high risk). Strong wind event: During a certain season, the area experienced strong winds lasting for 8 hours, with maximum wind speeds reaching 35 meters per second. Considering the wind speed, duration, and the relative relationship between the wind direction and the bridge tower structure, this strong wind event is assessed as a low-to-medium risk event, with a risk warning level of 2. Overweight vehicle crossing event: A large truck exceeding the bridge's design weight limit by 30% crosses the bridge. Based on the vehicle's overload status, driving speed, and the bridge structure's sensitivity to overload, the incident was classified as a high-risk event, with a risk warning level of 4.

[0052] The type information of the target event is processed to generate historical cable force values ​​for the target bridge tower. Based on the type information of the target event, cable force monitoring data for the target bridge tower during the period before and after the corresponding event is queried to obtain historical cable force values. For example, for the earthquake event mentioned above, cable force monitoring records from 1 hour before the earthquake to 2 hours after the earthquake are viewed. Assuming that the average cable force of the stay cables was 800 kN before the earthquake, the cable force fluctuated instantaneously during the earthquake, reaching a maximum of 950 kN, and gradually stabilized at around 820 kN for a period after the earthquake. For the strong wind event, the cable force values ​​during the strong wind and half an hour before and after are viewed, showing that the cable force fluctuated between 780 kN and 830 kN under the influence of strong winds. In the case of an overweight vehicle crossing the bridge, the cable force briefly increased from 800 kN to 880 kN when the vehicle passed, and then returned to near its initial value after the vehicle passed. This historical cable force value information reflects the immediate and subsequent impact of the target event on the cable force, providing data support for analyzing the patterns of cable force changes.

[0053] Historical cable force information of the target bridge tower is processed to generate cable force influence factors and corresponding weight information. Based on the historical cable force information, the cable force influence factors are analyzed and determined. For earthquake events, influence factors include peak ground acceleration (e.g., 0.15g), earthquake duration (30 seconds), and the natural vibration period of the bridge tower structure (2 seconds). Influence factors for strong wind events include wind speed (35 m / s), the angle between the wind direction and the bridge tower (45 degrees), and wind pulsation characteristics (e.g., turbulence intensity 0.2). Influence factors for overweight vehicle crossing events include the proportion of overweight vehicles (30%), vehicle speed (40 km / h), and vehicle wheelbase (5 meters).

[0054] The weights of each cable force influencing factor were determined through statistical analysis or numerical simulation. For example, a study of the relationship between multiple earthquake events and cable force changes revealed that peak ground acceleration (PGA) has a significant impact on cable force, and its weight was set at 0.4; earthquake duration had a weight of 0.3; and the bridge tower's natural vibration period had a weight of 0.3. For strong wind events, wind speed had a weight of 0.5, the angle between wind direction and the bridge tower had a weight of 0.3, and wind pulsation characteristics had a weight of 0.2. In events involving overweight vehicles crossing the bridge, the overweight ratio of vehicles had a weight of 0.6, the driving speed had a weight of 0.2, and the wheelbase had a weight of 0.2. These weights reflect the relative importance of each influencing factor in cable force changes.

[0055] Based on a preset bridge tower cable force influence feature set, the cable force influence factors of the target bridge tower and their corresponding weights are processed to generate target cable force early warning information for the target bridge tower. It is assumed that the preset bridge tower cable force influence feature set includes the following characteristics: Cable force variation amplitude characteristics: Records the maximum variation value, average variation value, and standard deviation of the cable force of the target bridge tower in different time intervals. For example, in the past week, the maximum variation amplitude of the stay cable force was 50kN (relative to the initial cable force), the average variation amplitude was 20kN, and the standard deviation was 10kN. These data can reflect the short-term fluctuation of the cable force; a large variation amplitude suggests abnormal stress on the structure or strong external disturbance factors. Cable force variation rate characteristics: Calculates the amount of cable force change per unit time, such as the cable force variation rate per hour. If the cable force variation rate suddenly increases within a certain time period, for example, from the normal 1kN per hour to 5kN per hour, this indicates that the structure is undergoing rapid stress adjustment, due to sudden events (such as strong winds, earthquakes, etc.) or the development of structural damage. Environmental Factor Correlation Characteristics: This considers the impact of environmental factors on cable forces, such as the correlation between temperature changes and cable force changes. If the cable force increases by an average of 20 kN for every 10°C increase in temperature, and this correlation shows high consistency in historical data, then temperature change is an important factor influencing cable force, and its corresponding weight will be relatively high. In addition, the relationship between environmental factors such as humidity and wind speed and cable force changes is also included. Structural Condition Characteristics: This involves health indicators of the bridge tower structure itself, such as the degree of corrosion of the main beam steel structure (quantified by corrosion area percentage or remaining wall thickness), the crack development of the concrete bridge deck (crack length, width, number, etc.), and the degree of fatigue damage of the stay cables (monitored by the number of stress cycles and wire breakage rate). These structural condition characteristics interact with cable forces; structural damage leads to abnormal cable force distribution, and changes in cable forces accelerate the development of structural damage.

[0056] Regarding the cable force influencing factors and weights for the target bridge tower, assuming the following main cable force influencing factors and their weights were determined through previous analysis: Cable force variation caused by strong winds (weight 0.3): During a strong wind event, the cable force variation reached 40 kN. Cable force variation caused by temperature changes (weight 0.25): The recent temperature increase of 15℃, according to the temperature-cable force relationship model, is expected to increase the cable force by 30 kN (actual monitoring may have some deviation). Corrosion degree of the main beam steel structure (weight 0.2): After testing, the corrosion area of ​​the main beam steel structure accounts for 5%. According to empirical formulas, this leads to a gradual increase in cable force over the long term, assumed to be equivalent to a current cable force increase of 15 kN (considering the impact of corrosion on structural stiffness and internal force distribution). Cable force fluctuation caused by traffic flow changes (weight 0.15): Due to nearby road construction, traffic flow temporarily increased by 30%, leading to increased cable force fluctuation, with an average fluctuation value of 10 kN. Fatigue damage of stay cables (weight 0.1): Through cable force monitoring and fatigue analysis, it was found that the cumulative fatigue damage of stay cables has an effect on the cable force equivalent to a reduction of 5kN in the current cable force (because fatigue damage leads to a decrease in cable stiffness and redistribution of cable force).

[0057] Based on the above influencing factors and weights, the target cable force warning value is calculated. The calculation formula can be set as follows: Target cable force warning value = (Strong wind cable force variation × weight + Temperature cable force variation × weight + Steel structure corrosion cable force variation × weight + Traffic flow cable force fluctuation × weight + Stay cable fatigue cable force variation × weight) × Correction coefficient. Assume the correction coefficient is 1.2 (to consider other potential factors or uncertainties not fully covered in the above influencing factors). Substituting the data, the target cable force warning value is calculated as follows: Target cable force warning value = (40kN × 0.3 + 30kN × 0.25 + 15kN × 0.2 + 10kN × 0.15 - 5kN × 0.1) × 1.2 = (12kN + 7.5kN + 3kN + 1.5kN - 0.5kN) × 1.2 = 23.5kN × 1.2 = 28.2kN.

[0058] Based on the calculated target cable force warning value, a warning level is set. For example, the warning levels are set as follows: When the target cable force warning value is less than 10kN, it is a green warning, indicating that the cable force is within the normal fluctuation range and the structural safety condition is good. When the target cable force warning value is between 10kN and 20kN, it is a yellow warning, indicating that the cable force has changed to a certain extent and needs to be monitored more closely, but there is no obvious safety risk to the structure at present. When the target cable force warning value is greater than 20kN, it is a red warning, indicating that the cable force has changed significantly and there is a potential structural safety hazard, requiring immediate further inspection and response measures, such as detailed structural testing, traffic flow restriction, and assessment of whether emergency repairs are needed.

[0059] In this example, the target cable force warning value is 28.2 kN, therefore a red warning message is generated to remind relevant personnel to pay attention to the cable force status of the target bridge tower and take timely measures to ensure the safe operation of the bridge. Simultaneously, the warning message can also include detailed analysis results of influencing factors, such as the contribution of strong winds and temperature changes to the cable force, so that technicians can more accurately determine the cause of structural problems and develop targeted solutions.

[0060] S106, Based on the target cable-stayed bridge cable force prediction model, the target bridge tower information is processed to generate the target bridge tower attribute information.

[0061] In one implementation, the flexural stiffness values ​​of the first and second beam elements under different load capacities are obtained. It is assumed that the main steel beam structure (first beam element) and the concrete bridge deck (second beam element) of the target bridge tower jointly bear the bridge deck load. The flexural stiffness values ​​are obtained by conducting loading tests in a laboratory on a scaled-down model with the same materials and dimensions as the actual structure. For example, for the first beam element (steel beam), different load capacities are set, starting from a lighter 100kN and gradually increasing to 500kN in increments of 100kN. Under each load capacity, the deflection of the steel beam is measured using a displacement measurement method, and the stiffness is determined according to the formulas of mechanics of materials. (Where K is the flexural stiffness, P is the applied load, and δ is the resulting deflection) Calculate the flexural stiffness value. For the second beam element (concrete bridge deck), a similar test is conducted. Due to the nonlinear characteristics of concrete, a more complex test method is required, such as graded loading and continuous monitoring of strain changes, using structural analysis software to assist in calculating the flexural stiffness. Assuming a bearing weight of 100 kN, the calculated flexural stiffness of the first beam element is 1 × 10⁻⁶. 6 kN.m 2 The second beam element is 0.5×10 6 kN.m 2 Under a bearing load of 200kN, the bending stiffness of the first beam element becomes 0.9×10⁻⁶. 6 kN.m 2 (As the steel beam enters the elastoplastic stage, its stiffness decreases slightly), the second beam element is 0.48×10 6 kN.m 2 (The development of microcracks inside the concrete leads to a decrease in stiffness), and so on, to obtain the flexural stiffness values ​​under different load-bearing weights.

[0062] The bending stiffness values ​​of the first and second beam elements under different load capacities were processed to generate multiple sets of cable force values. According to structural mechanics principles, the bridge tower, main beam, and stay cables constitute an interacting system. Knowing the bending stiffness values ​​of the first and second beam elements under different load capacities, the cable force values ​​were calculated by establishing the structural equilibrium equations. For example, a finite element analysis software was used to establish an overall model of the bridge tower-main beam-stayed cables, using the bending stiffness values ​​under different load capacities as input parameters to simulate the internal force distribution of the structure under various load conditions, thereby obtaining the corresponding stay cable force values. Assuming a certain load capacity, a set of calculated cable force values ​​was obtained: cable force 300kN for cable 1, 320kN for cable 2, 280kN for cable 3, etc. Multiple sets of different cable force values ​​were obtained under different load capacities. These cable force values ​​reflect the stress state of the stay cables under different load conditions, providing a data basis for subsequently determining reasonable preset cable force values.

[0063] Multiple sets of cable force values ​​are processed using a target cable-stayed bridge cable force prediction model to generate preset cable force values. These values ​​are input into the model, which is based on a large amount of actual bridge monitoring data and theoretical analysis, and may be a neural network model or an empirical formula model. For example, the neural network model processes the input cable force values ​​by learning the complex nonlinear relationships between cable force values ​​and other structural parameters (such as beam element bending stiffness and tower deformation). After internal calculations and optimization algorithms, a preset cable force value that comprehensively considers various factors is output. Assuming the preset cable force value obtained after model processing is 350kN (this is an example; the actual value will be determined based on model calculations), this preset cable force value will serve as a basic parameter for subsequent calculations of target temperature load values, and will also provide a reference for cable force adjustments during bridge construction or operation.

[0064] The process involves acquiring a target number of incremental steps, a target cable force value, an iteration acceleration factor, and information on the cable force value and temperature load corresponding to each incremental step. The target number of incremental steps characterizes several sub-steps for obtaining the target temperature load value. Based on the target cable-stayed bridge cable force prediction model, the preset cable force value, the target number of incremental steps, the iteration acceleration factor, and information on the cable force and temperature load corresponding to each incremental step are processed to generate the target temperature load value. A target number of incremental steps is set, for example, 10 incremental steps, to gradually approximate the actual temperature load process. In each incremental step, the cable force value and temperature load corresponding to the current incremental step are measured or calculated. Assuming an initial temperature of 20℃, in the first incremental step, the temperature rises to 21℃, and the cable force value is measured to be 360kN; in the second incremental step, the temperature rises to 22℃, and the cable force value becomes 370kN, and so on. Simultaneously, an iteration acceleration factor is obtained, assumed to be 0.8 (this value is determined based on model convergence characteristics and computational efficiency requirements). The preset cable force value (350kN), the information from these 10 incremental steps (including the cable force value and temperature load for each incremental step), and the iteration acceleration factor are input into the target cable-stayed bridge cable force prediction model. The model, based on its built-in temperature-cable force relationship algorithm (based on the principle of thermal expansion and contraction and structural mechanics analysis), iteratively corrects the influence of temperature load on cable force, ultimately obtaining the target temperature load value. For example, after a series of calculations, such as those using the formula below, the target temperature load value is obtained as 25℃ (i.e., when the temperature reaches 25℃, considering other structural factors, the cable force reaches a stable state near the preset cable force value).

[0065] The material information of the target bridge tower is obtained, including the creep coefficient, strain components, strain changes due to external loads, elastic modulus, and reference elastic modulus. The creep coefficient and strain components are processed to generate effective creep strain. For example, the creep coefficient of concrete is obtained, assuming that the creep coefficient of concrete under specific environmental and loading conditions is known over time, and that the creep coefficient is 0.3 at the current time point. Simultaneously, the strain components are known (obtained through strain gauge measurements), for example, the strain component in a certain direction is 5 × 10⁻⁶. -5 According to the effective creep strain calculation formula (Assume there is only one time phase in this simple example, i.e., m = 0, β0 = 0.3, γ0) (0) =5×10 -5 The effective creep strain Δε' was calculated to be (1-0.3)×5×10. -5 .

[0066] The effective creep strain, strain change information caused by external loads, and elastic modulus are processed to generate stress increments. The strain change information caused by external loads is known (e.g., the strain change at a certain location under vehicle load is 2 × 10⁻⁶, obtained through monitoring or calculation). -4 ), elastic modulus (assuming the elastic modulus of concrete is 3×10), 4 MPa). Calculated according to the stress increment formula. (Here it is assumed) That is, the equivalent elastic modulus is equal to the elastic modulus, and the stress increment Δσ is calculated to be 3 × 10. 4 MPa×(2×10) -4 -3.5×10 -5 = 4.95 MPa.

[0067] The stress increment and reference elastic modulus are processed to generate the true elastic strain and true creep strain. The reference elastic modulus is assumed to be 3.2 × 10⁻⁶. 4 MPa, according to the true elastic strain calculation formula ρ=E(Δε-Δε') / E0, we get ρ=3×10 4 MPa×(2×10) -4 -3.5×10 -5 ) / (3.2×10 4 MPa) = 1.54 × 10 -4 Therefore, the actual creep strain Δε-ρ=2×10 -4 -1.54×10 -4 =4.6×10 -5 .

[0068] The effective creep strain, stress increment, true elastic strain, and true creep strain are processed to generate the material shrinkage and creep value of the target bridge tower. The effective creep strain (3.5 × 10⁻⁶) is then calculated. -5 Stress increment (4.95 MPa), true elastic strain (1.54 × 10⁻⁶ MPa), stress increment (4.95 MPa), true elastic strain (1.54 × 10⁻⁶ MPa). -4 ) and true creep strain (4.6×10 -5 The material shrinkage and creep value of the target bridge tower is calculated by comprehensive processing, such as through weighted summation or other empirical formulas (assuming weights of 0.3, 0.4, 0.2, and 0.1). Material shrinkage and creep value = 0.3 × 3.5 × 10⁻⁶ -5 +0.4×4.95MPa+0.2×1.54×10 -4 +0.1×4.6×10 -5 Ultimately, a numerical value that comprehensively reflects the shrinkage and creep characteristics of the material is obtained, which is used to evaluate the impact of the material on the performance of the bridge tower structure during long-term use.

[0069] In another embodiment, the target cable-stayed bridge cable force prediction model includes a calculation formula for obtaining the target temperature load value, the calculation formula being:

[0070] Where, N p The preset cable force value is N. j-2 For the cable force calculated in the (j-2)th increment step, T j-2 For the temperature load calculated in the (j-2)th increment step, N j-1 For the cable force calculated in the (j-1)th increment step, T j-1 The temperature load is calculated for the (j-1)th increment step, and r2 is the iteration acceleration factor. This will not be discussed further here.

[0071] The target cable-stayed bridge cable force prediction model includes a calculation formula for obtaining the effective creep strain. The calculation formula is as follows:

[0072] Where m represents the number of terms considered when calculating the effective creep strain, β i γ represents the creep coefficient. i (n) This represents the strain component. Assume the creep coefficient of the concrete material of the target bridge tower varies with time as shown below (simplified to three time stages): Time stage (i) is 0-1 years, and its creep coefficient (β... i The creep coefficient (β) is 0.2; for time period (i) of 1-5 years, the creep coefficient (β) is 0.2. i The creep coefficient (β) is 0.3; the creep coefficient for time period (i) is 5-10 years. i The value is 0.4.

[0073] strain component γ i (n) The values ​​were obtained by placing strain gauges at key locations on the bridge tower. It is assumed that in the first year, γ0... (1) =1×10 -4 In the third year (belonging to the 1-5 year stage), γ1 (3) =0.8×10 -4 In the eighth year (belonging to the 5-10 year stage), γ2 (8) =0.6×10 -4 .

[0074] According to the effective creep strain calculation formula For the first year: Δε'1=(1-0.2)×1×10 -4 =0.8×10 -4 ;

[0075] For the third year: Δε'3=(1-0.3)×0.8×10 -4 =0.56×10 -4 ;

[0076] For the eighth year: Δε'8=(1-0.4)×0.6×10 -4 =0.36×10 -4 ;

[0077] Assuming we only consider the contribution of these three time points to the effective creep strain (i.e., m = 2), then the total effective creep strain Δε' = Δε'1 + Δε'3 + Δε'8 = 1.72 × 10⁻⁶ -4 .

[0078] The target cable-stayed bridge cable force prediction model includes a calculation formula for obtaining stress increments. The calculation formula is as follows: in, Let Δε represent the equivalent elastic modulus, Δε represent the total strain change, and Δε' represent the effective creep strain. The strain change Δε caused by external loads (such as vehicle loads, wind loads, etc.) is known to be measured by the structural monitoring system. Assume that at the current calculation moment, Δε = 2.5 × 10⁻⁶. -4 The elastic modulus of the concrete material of the target bridge tower was determined through material testing, assuming E = 3 × 10⁻⁶. 4 MPa. According to the stress increment calculation formula... Here we assume Δσ=3×10 4 MPa×(2.5×10 -4 -1.72×10 -4 = 2.34 MPa.

[0079] The target cable-stayed bridge cable force prediction model includes calculation formulas for obtaining the true elastic strain. The calculation formulas are as follows: in, E represents the equivalent elastic modulus, Δε represents the total strain change, Δε' represents the effective creep strain, and E0 represents the reference elastic modulus.

[0080] The target cable-stayed bridge cable force prediction model includes calculation formulas for obtaining the true creep strain. The calculation formulas are as follows: Where Δε represents the total strain change, and ρ represents the true elastic strain. E represents the equivalent elastic modulus, Δε' represents the effective creep strain, and E0 represents the reference elastic modulus.

[0081] Assume the reference elastic modulus E0 = 3.2 × 10⁻⁶ 4 MPa.

[0082] According to the formula for calculating true elastic strain Therefore: ρ=3×10 4 MPa×(2.5×10 -4 -1.72×10 4MPa) = 0.73 × 10 -4 .

[0083] The actual creep strain Δε-ρ=2.5×10 -4 -0.73×10 -4 =1.77×10 -4 .

[0084] Calculate the material shrinkage and creep values ​​(using a weighted summation method). Set the weights of effective creep strain, stress increment (converted to the equivalent strain value; assuming the stress increment is Δσ, then the equivalent strain increment is Δσ / E), true elastic strain, and true creep strain as w1 = 0.2, w2 = 0.3, w3 = 0.25, and w4 = 0.25, respectively.

[0085] The stress increment converted to the equivalent strain value is: Δσ / E=2.34MPa / (3×10 4 MPa) = 0.78 × 10 -4 .

[0086] Material shrinkage and creep value = w1×Δε' + w2×(Δσ / E) + w3×ρ + w4×(Δε-ρ) = 0.2×10 -4 +0.3×0.78×10 -4 +0.25×0.73×10 -4 +0.25×1.77×10 -4 =1.203×10 -4 .

[0087] The calculated material shrinkage and creep values ​​comprehensively consider the effects of effective creep strain, stress increment, true elastic strain, and true creep strain. They can reflect, to a certain extent, the impact of shrinkage and creep characteristics on the structural performance of the target bridge tower material during long-term use. They can be used for subsequent structural analysis and evaluation, such as predicting structural deformation and cable force changes.

[0088] S107, Based on the target cable-stayed bridge cable force prediction model, process the attribute information of the target bridge tower and the cable force warning information of the target tower bridge to generate target cable force warning information of the target bridge tower information.

[0089] In one implementation, a target cable force value for the target cable-stayed bridge is generated by processing a preset cable force value, a target temperature load value, and a target bridge tower material shrinkage and creep value based on a target cable-stayed bridge cable force prediction model. Assume the target cable force prediction model uses the following formula to calculate the target cable force value: N t =N p +k1T j +k2Δε scAmong them, the target cable force value Nt, the preset cable force value Np, the target temperature load value Tj, and the material shrinkage and creep value Δε sc k1 represents the influence coefficient of the target temperature load value on the target cable force value, and k2 represents the influence coefficient of the material shrinkage and creep value of the target bridge tower on the target cable force value.

[0090] For example, the preset cable force value Np = 500kN, the target temperature load value Tj = 10℃ (here it is assumed that the temperature load value is in degrees Celsius and has a linear relationship with the cable force change), and the target bridge tower material shrinkage and creep value Δε sc =5×10 -5 (Assuming the shrinkage and creep values ​​are expressed in strain form and have been calculated using the methods described above). Through model analysis and calibration, K1 = 20 kN / ℃ (representing a 20 kN change in cable force for every 1℃ change in temperature) and K2 = 10000 kN (representing the change in cable force per unit shrinkage and creep strain). Substituting these values ​​into the formula yields: N t =500kN+20kN / ℃×10℃+10000kN×5×10 -5 Therefore, the target cable force value of the target bridge tower is 700.5 kN.

[0091] Based on the cable force prediction model for the target cable-stayed bridge, the early warning information of the cable force of the target tower bridge is processed to generate the early warning value of the cable force of the target tower. Assume that the formula for calculating the early warning value of the cable force based on the early warning information of the tower cable force in the cable force prediction model for the target cable-stayed bridge is as follows: Where R represents the risk warning level of the target event (the value range is assumed to be 1-5, with a higher number indicating a higher risk), and N... h For the historical cable force information of the target bridge tower (e.g., the average cable force over a past period), F i Let w be the quantified value of the influence of the i-th cable force influencing factor (such as environmental factors, traffic flow, etc.) on the cable force. i The weight information corresponding to the cable force influence factor is given by a, b, and c, which are coefficients determined by the model based on experience and data analysis.

[0092] For example, the risk warning level of the target event is R=3, and the historical cable force information of the target bridge tower is N. h =400kN, there are two cable force influencing factors: environmental temperature change factor F1 = 5 (assuming a large temperature change has a significant impact on cable force), with a weight w1 = 0.4; traffic flow change factor F2 = 8 (assuming a sudden and significant increase in traffic flow), with a weight w2 = 0.6. Through model calibration, a = 50kN, b = 0.8, c = 10kN were determined. Substituting these values ​​into the formula, we get: W = 50kN × 3 + 0.8 × 400kN +

[0093] 10kN × (5 × 0.4 + 8 × 0.6) = 538kN. Therefore, the cable tension warning value for the target bridge tower is 538kN.

[0094] Based on the target bridge tower's cable force warning value, the target cable force value of the target bridge tower is processed to generate target cable force warning information for the target bridge tower. Assume the warning rule is set as follows: when the target cable force value N... t A red alert is issued when the cable force exceeds 1.2 times the warning value W, indicating excessive cable force and a significant safety risk to the structure, requiring immediate action such as traffic restrictions and structural inspections. When the target cable force value N... t A yellow alert is issued when the cable tension is between 1.0 and 1.2 times the warning value, indicating that the cable tension is too high and requires enhanced monitoring and attention to changes in the structural condition. When the target cable tension value N... t When the cable tension is less than 1.0 times the warning value, a green warning is issued, indicating that the cable tension is within the normal range and the structural safety condition is good.

[0095] In the example above, the target cable force value N t =700.5kN, cable force warning value W = 538kN, W × 1.2 = 645.6kN. Because 700.5kN > 645.6kN, a red warning message is issued, indicating that the cable force of the target bridge tower is too high. Relevant personnel need to conduct a comprehensive inspection and assessment of the bridge structure in a timely manner and take corresponding measures to ensure the safe operation of the bridge.

[0096] This application obtains target bridge tower information, a matching event set, and a training sample set from the server. The target bridge tower information includes beam element information for the main girder steel structure, concrete bridge deck, and cable-stayed structure. The training sample set is then preprocessed, generating a training sample set containing target feature data representing factors influencing bridge tower cable force risk through steps such as obtaining a pre-defined mapping table for grouping, feature extraction, dataset partitioning, classifier prediction, and algorithm training. Then, a pre-defined cable-stayed bridge cable force prediction model is generated based on the processed training sample set to predict the target cable force. For the target event set, type information, historical cable force value information, cable force influencing factors, and weight information are obtained, thereby generating bridge tower cable force early warning information. When generating target bridge tower attribute information, multiple sets of cable force values ​​are generated by obtaining beam element bending stiffness values ​​under different bearing weights. Combined with incremental step information, the target temperature load value is obtained. Simultaneously, effective creep strain, stress increment, true elastic strain, and true creep strain are calculated based on material information to determine the material shrinkage and creep value. Finally, based on the model, the target bridge tower attribute information and bridge tower cable force early warning information are processed to calculate the target cable force value and cable force early warning value, thereby generating target cable force early warning information and providing comprehensive analysis and prediction for target bridge tower cable force early warning.

[0097] In one implementation, such as Figure 2As shown, this application also provides a stress performance analysis device for a combined cable-stayed bridge, comprising:

[0098] The acquisition module 201 is used to acquire target bridge tower information, a target event set matching the target bridge tower information, and a training sample set. The target bridge tower information includes first beam element information representing the main girder steel structure, second beam element information representing the concrete bridge deck, and third beam element information representing the cable-stayed structure. The training sample set is used to represent other bridge tower information matching the target bridge tower information. The module also acquires a preset cable-stayed bridge cable force prediction model, which is generated based on historical structural information of the target bridge tower information.

[0099] The processing module 202 is used to preprocess the training sample set to generate a training sample set with target feature data, wherein the target feature data is used to characterize the risk factors affecting the cable force of the bridge tower; process the preset cable force prediction model of the cable-stayed bridge based on the training sample set with target feature data to generate a target cable force prediction model of the cable-stayed bridge; process the target event set that matches the target bridge tower information to generate early warning information of the cable force of the target bridge tower; process the target bridge tower information based on the target cable force prediction model of the cable-stayed bridge to generate attribute information of the target bridge tower, wherein the attribute information of the target bridge tower includes the initial cable force of the target bridge tower, the target temperature load value, and the material shrinkage and creep value of the target bridge tower; and process the attribute information of the target bridge tower and the early warning information of the cable force of the target bridge tower based on the target cable force prediction model of the cable-stayed bridge to generate early warning information of the target cable force of the target bridge tower.

[0100] This application provides an electronic device, such as... Figure 3 As shown, the electronic device 3 includes a first processor 300, a memory 301, a bus 302, and a communication interface 303. The first processor 300, the communication interface 303, and the memory 301 are connected through the bus 302. The memory 301 stores a computer program that can run on the first processor 300. When the first processor 300 runs the computer program, it executes the stress performance analysis method for the combined cable-stayed bridge provided in any of the foregoing embodiments of this application.

[0101] Bus 302 can be an ISA bus, PCI bus, or EISA bus, etc. The bus can be divided into an address bus, a data bus, a control bus, etc. The memory 301 is used to store programs. After receiving an execution instruction, the first processor 300 executes the program. The stress performance analysis method for the combined cable-stayed bridge disclosed in any of the foregoing embodiments of this application can be applied to the first processor 300, or implemented by the first processor 300.

[0102] The first processor 300 is an integrated circuit chip with signal processing capabilities. In implementation, each step of the above method can be completed through integrated logic circuits in the hardware of the first processor 300 or through software instructions. The first processor 300 can be a general-purpose processor, including a central processing unit (CPU), a network processor (NP), etc.; it can also be a digital signal processor (DSP), an application-specific integrated circuit (ASIC), an off-the-shelf programmable gate array (FPGA), or other programmable logic devices, discrete gate or transistor logic devices, or discrete hardware components. The software module can reside in random access memory, flash memory, read-only memory, programmable read-only memory, electrically erasable programmable memory, registers, or other mature storage media in the art. This storage medium is located in memory 301. The first processor 300 reads information from memory 301 and, in conjunction with its hardware, completes the steps of the above method.

[0103] This application provides a computer-readable storage medium, such as... Figure 4 As shown, the computer-readable storage medium 401 stores a computer program, which is read and run by the second processor 402 to implement the stress performance analysis method for the combined cable-stayed bridge as described above.

[0104] The computer program products provided in the above embodiments of this application and the method for analyzing the stress performance of combined cable-stayed bridges provided in the embodiments of this application are based on the same inventive concept and have the same beneficial effects as the methods used, run or implemented by their stored applications.

Claims

1. A method for analyzing the stress performance of a composite cable-stayed bridge, characterized in that, include: Acquire target bridge tower information, a set of target events matching the target bridge tower information, and a training sample set. The target bridge tower information includes first beam element information for characterizing the main girder steel structure, second beam element information for characterizing the concrete bridge deck, and third beam element information for characterizing the cable-stayed structure. The training sample set is used to characterize other bridge tower information that matches the target bridge tower information. The training sample set is preprocessed to generate a training sample set with target feature data. This includes obtaining a preset mapping table, wherein the preset mapping table is used to characterize the historical structural information of the target bridge tower information and the corresponding information of the historical event set of the target bridge tower information; grouping the training sample set based on the preset mapping table to generate a grouped training sample set, wherein the grouped training sample set includes monitoring points to be predicted with different monitoring lengths; extracting features from the grouped training sample set to determine the original feature library; dividing the original feature library into various feature datasets to generate training sets and validation sets; performing prediction processing on each validation set divided by the original feature library based on a classifier to generate prediction results; training each training set divided by the original feature library based on a preset algorithm to generate validation set prediction results; and processing the prediction results and the validation set prediction results to generate target feature data, wherein the target feature data is used to characterize the risk factors affecting the cable force of the bridge tower. Obtain a preset cable-stayed bridge cable force prediction model, wherein the preset cable force prediction model is generated based on historical structural information of the target bridge tower; The preset cable-stayed bridge cable force prediction model is processed based on the training sample set containing the target feature data to generate the target cable-stayed bridge cable force prediction model. Process the target event set that matches the target bridge tower information to generate early warning information on the cable tension of the target bridge tower; Based on the target cable-stayed bridge cable force prediction model, the target bridge tower information is processed to generate the target bridge tower attribute information, wherein the target bridge tower attribute information includes the initial cable force of the target bridge tower, the target temperature load value, and the material shrinkage and creep value of the target bridge tower. Based on the target cable-stayed bridge cable force prediction model, the attribute information of the target bridge tower and the early warning information of the target tower cable force are processed to generate target cable force early warning information of the target bridge tower information.

2. The method as described in claim 1, characterized in that, The target event set matching the target bridge tower information is processed to generate early warning information on the bridge tower cable tension of the target bridge tower, including: The target event set that matches the target bridge tower information is processed to generate target event type information, wherein the target event type information is used to characterize the risk warning level of the target event to the target bridge tower; The type information of the target event is processed to generate historical cable force value information of the target bridge tower; The historical cable force value information of the target bridge tower is processed to generate the cable force influence factor of the target bridge tower and the weight information corresponding to the cable force influence factor of the target bridge tower; Based on a preset bridge tower cable force influence feature set, the cable force influence factor of the target bridge tower and the weight information corresponding to the cable force influence factor of the target bridge tower are processed to generate target cable force early warning information for the target bridge tower.

3. The method as described in claim 2, characterized in that, Based on the target cable-stayed bridge cable force prediction model, the target bridge tower information is processed to generate the target bridge tower attribute information, including: Obtain the bending stiffness values ​​of the first beam element and the second beam element under different bearing weights; The bending stiffness values ​​of the first beam element and the second beam element under different bearing weights are processed to generate multiple sets of cable force values; Based on the target cable-stayed bridge cable force prediction model, multiple sets of cable force values ​​are processed to generate preset cable force values; The incremental step information of the target number, the target cable force value, the iteration acceleration factor, and each incremental step information includes the cable force value corresponding to the current incremental step information and the temperature load corresponding to the incremental step information, wherein the incremental step information of the target number is used to characterize several sub-step information for obtaining the target temperature load value; Based on the target cable-stayed bridge cable force prediction model, the preset cable force value, the incremental step information of the target number, the iteration acceleration factor, and each incremental step information including the cable force value and the temperature load corresponding to the incremental step information are processed to generate the target temperature load value. Obtain the material information of the target bridge tower, wherein the material information of the target bridge tower includes creep coefficient, strain components, strain change information caused by external load, elastic modulus and reference elastic modulus; The creep coefficient and the strain components are processed to generate an effective creep strain; The effective creep strain, the strain change information caused by external load, and the elastic modulus are processed to generate stress increments; The stress increment and the reference elastic modulus are processed to generate the true elastic strain and the true creep strain. The effective creep strain, the stress increment, the true elastic strain, and the true creep strain are processed to generate the material shrinkage and creep value of the target bridge tower.

4. The method as described in claim 3, characterized in that, Based on the target cable-stayed bridge cable force prediction model, the target bridge tower information is processed to generate the target bridge tower attribute information, which also includes: The target cable-stayed bridge cable force prediction model includes a calculation formula for obtaining the target temperature load value. The calculation formula is as follows: ； in, For the preset cable tension value, The cable force calculated for the (j-2)th increment step. The temperature load calculated for the (j-2)th increment step, The cable force calculated for the (j-1)th increment step. The temperature load calculated for the (j-1)th increment step, This is the iteration acceleration factor; The target cable-stayed bridge cable force prediction model includes a calculation formula for obtaining the effective creep strain, and the calculation formula is as follows: ； Where m represents the number of terms considered when calculating the effective creep strain. Represents the creep coefficient. Represents strain components; The target cable-stayed bridge cable force prediction model includes a calculation formula for obtaining stress increments, which is as follows: ； in, Represents the equivalent elastic modulus. This represents the total change in strain. Represents effective creep strain; The target cable-stayed bridge cable force prediction model includes a calculation formula for obtaining the true elastic strain, and the calculation formula is as follows: ； in, Represents the equivalent elastic modulus. This represents the total change in strain. Represents effective creep strain. Represents the reference elastic modulus; The target cable-stayed bridge cable force prediction model includes a calculation formula for obtaining the true creep strain, and the calculation formula is as follows: ； in, This represents the total change in strain. Represents true elastic strain. Represents the equivalent elastic modulus. Represents effective creep strain. This represents the reference elastic modulus.

5. The method as described in claim 4, characterized in that, Based on the target cable-stayed bridge cable force prediction model, the attribute information of the target bridge tower and the cable force early warning information of the target bridge tower are processed to generate target cable force early warning information for the target bridge tower, including: Based on the target cable-stayed bridge cable force prediction model, the preset cable force value, the target temperature load value, and the material shrinkage and creep value of the target bridge tower are processed to generate the target cable force value of the target bridge tower. Based on the target cable-stayed bridge cable force prediction model, the cable force early warning information of the target tower bridge is processed to generate the cable force early warning value of the target tower. Based on the cable force warning value of the target bridge tower, the target cable force value of the target bridge tower is processed to generate the target cable force warning information of the target bridge tower.

6. The method as described in claim 5, characterized in that, Based on the target cable-stayed bridge cable force prediction model, the attribute information of the target bridge tower and the cable force early warning information of the target tower bridge are processed to generate target cable force early warning information of the target bridge tower information, which also includes: The target cable-stayed bridge cable force prediction model also includes a calculation formula for obtaining the target cable force value of the target bridge tower. The calculation formula is as follows: ； Among them, the target cable force value Nt, the preset cable force value Np, the target temperature load value Tj, and the material shrinkage and creep value are... , This represents the influence coefficient of the target temperature load value on the target cable force value. The coefficient representing the influence of the material shrinkage and creep value of the target bridge tower on the target cable force value; The target cable-stayed bridge cable force prediction model also includes a calculation formula for obtaining the cable force warning value of the target bridge tower, and the calculation formula is as follows: ； in, The risk warning level for the target event. For the historical cable force information of the target bridge tower, Let i be the cable force influence factor. The weight information corresponding to the cable force influence factor is given by coefficients a, b, and c.

7. A stress performance analysis device for a combined cable-stayed bridge, characterized in that, For implementing the method of claim 1, the apparatus includes: The acquisition module is used to acquire target bridge tower information, a set of target events matching the target bridge tower information, and a training sample set. The target bridge tower information includes first beam element information representing the main girder steel structure, second beam element information representing the concrete bridge deck, and third beam element information representing the cable-stayed structure. The training sample set is used to represent other bridge tower information matching the target bridge tower information. The module also acquires a preset cable-stayed bridge cable force prediction model, which is generated based on historical structural information of the target bridge tower information. The processing module is used to preprocess the training sample set to generate a training sample set with target feature data, wherein the target feature data is used to characterize the risk factors affecting the cable force of the bridge tower; process the preset cable force prediction model of the cable-stayed bridge based on the training sample set with target feature data to generate a target cable force prediction model of the cable-stayed bridge; process the target event set that matches the target bridge tower information to generate early warning information of the cable force of the target bridge tower; process the target bridge tower information based on the target cable force prediction model of the cable-stayed bridge to generate attribute information of the target bridge tower, wherein the attribute information of the target bridge tower includes the initial cable force of the target bridge tower, the target temperature load value, and the material shrinkage and creep value of the target bridge tower; and process the attribute information of the target bridge tower and the early warning information of the cable force of the target bridge tower based on the target cable force prediction model of the cable-stayed bridge to generate early warning information of the target cable force of the target bridge tower.

8. An electronic device, characterized in that, include: First processor; and memory for storing executable instructions of the first processor; The first processor is configured to execute the stress performance analysis method of any one of claims 1 to 6 by executing the executable instructions.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by the second processor, it implements the stress performance analysis method for the combined cable-stayed bridge as described in any one of claims 1 to 6.

Images