High-speed railway box girder moving and transporting intelligent monitoring and early warning system and method

Abstract

This application provides an intelligent monitoring and early warning system and method for the transportation of box girders in high-speed railways, relating to the field of intelligent monitoring technology. The system includes: a data monitoring component for acquiring transportation monitoring data and external force monitoring data; a defect analysis component for obtaining the distribution of monitoring data on defect responses; and a risk prediction component for performing risk analysis and prediction based on the monitoring changes in the time-series chain of transportation monitoring data, generating corresponding early warning information, and providing visual feedback. This application addresses the technical problem that minor structural defects caused by external forces during the transportation of box girders in high-speed railways are difficult to identify in real time using traditional monitoring methods. It achieves the technical effect of dynamic diagnosis of the health status of box girder structures and advanced prediction of potential risks based on sensor measurement and multi-source data fusion analysis, thereby improving the sensitivity and accuracy of monitoring.

Description

Technical Field

[0001] This application relates to the field of intelligent monitoring technology, and in particular to an intelligent monitoring and early warning system and method for the transportation of box girders for high-speed railways. Background Technology

[0002] As a major national transportation infrastructure, the safety and durability of high-speed railways are directly related to transportation efficiency and socio-economic development. High-speed railway bridge engineering extensively utilizes precast concrete box girder structures. These individual components are heavy and bulky, and the structural stability requirements are extremely high during construction stages such as demolding, transportation, and erection. During transportation, the box girders not only bear their own weight but are also subjected to a variety of complex external forces, including the supporting force of the transport vehicle, acceleration and deceleration inertial forces, braking forces, wind loads, and vibrations and impacts caused by track irregularities.

[0003] Traditional monitoring methods for box girder relocation mostly rely on manual inspections or single-point sensor measurements, making it difficult to achieve dynamic response monitoring of the overall box girder structure. Especially during relocation, because the girder is in a dynamic environment with frequent changes in stress and vibration, hidden problems such as micro-cracks, local structural loosening, and material micro-defects that may exist inside the box girder are difficult to identify in a timely manner. They are often only discovered after cracks have expanded or the structure has become unstable, resulting in increased construction risks and shortened service life.

[0004] In addition, existing monitoring systems mostly focus on collecting macroscopic parameters such as displacement and strain, failing to effectively integrate the correspondence between external forces and beam response during the transfer process, and lacking the ability to conduct collaborative analysis and predictive early warning of monitoring data, resulting in insufficient sensitivity and reliability of monitoring results. Summary of the Invention

[0005] The purpose of this application is to provide an intelligent monitoring and early warning system and method for the transportation of high-speed railway box girders, in order to solve the technical problem that it is difficult to identify minor structural defects caused by external forces during the transportation of high-speed railway box girders in real time through traditional monitoring methods.

[0006] In view of the above problems, this application provides an intelligent monitoring and early warning system and method for the transportation of box girders for high-speed railways.

[0007] Firstly, this application provides an intelligent monitoring and early warning system for the transportation of high-speed railway box girders, comprising: a data monitoring component for acquiring transportation monitoring data of high-speed railway box girders and external force monitoring data of the transportation; a defect analysis component for performing structural defect correlation analysis on the high-speed railway box girders using the external force monitoring data of the transportation, and obtaining the monitoring data distribution of defect responses; and a risk prediction component for performing real-time alignment analysis of the transportation monitoring data based on the monitoring data distribution of defect responses, establishing a time-series chain of transportation monitoring data, performing risk analysis and prediction according to the monitoring changes in the time-series chain of transportation monitoring data, generating corresponding early warning information, and providing visual feedback.

[0008] Secondly, this application also provides an intelligent monitoring and early warning method for the transportation of high-speed railway box girders, including: acquiring transportation monitoring data of high-speed railway box girders and external force monitoring data of transportation; using the external force monitoring data of transportation to perform structural defect correlation analysis on the high-speed railway box girders to obtain the monitoring data distribution of defect response; according to the monitoring data distribution of defect response, performing real-time alignment analysis on the transportation monitoring data to establish a transportation monitoring data time series chain; performing risk analysis and prediction according to the monitoring change amount of the transportation monitoring data time series chain, generating corresponding early warning information, and providing visual feedback.

[0009] The technical solution provided in this application has at least the following technical effects or advantages: based on sensor measurement and multi-source data fusion analysis, it realizes dynamic diagnosis of the health status of box girder structures and advanced prediction of potential risks, thereby improving the technical effect of monitoring sensitivity and accuracy.

[0010] The above description is merely an overview of the technical solution of this application. To enable a clearer understanding of the technical means of this application and to facilitate its implementation according to the description, and to make the above and other objects, features, and advantages of this application more apparent, specific embodiments of this application are described below. It should be understood that the content described in this section is not intended to identify key or important features of the embodiments of this application, nor is it intended to limit the scope of this application. Other features of this application will become readily apparent through the following description. Attached Figure Description

[0011] To more clearly illustrate the technical solutions in this application or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are merely exemplary. For those skilled in the art, other drawings can be obtained based on the provided drawings without creative effort.

[0012] Figure 1 This is a structural schematic diagram of the intelligent monitoring and early warning system for the transportation of high-speed railway box girders, as described in this application.

[0013] Figure 2 This is a flowchart illustrating the intelligent monitoring and early warning method for high-speed railway box girder transportation proposed in this application.

[0014] Figure labeling: Data monitoring component 11, defect analysis component 12, risk prediction component 13. Detailed Implementation

[0015] This application provides an intelligent monitoring and early warning system and method for the transportation of high-speed railway box girders. It solves the technical problem that it is difficult to identify minor structural defects caused by external forces during the transportation of high-speed railway box girders in real time using traditional monitoring methods. The system achieves the technical effect of dynamic diagnosis of the health status of box girder structures and advanced prediction of potential risks based on sensor measurement and multi-source data fusion analysis, thereby improving the sensitivity and accuracy of monitoring.

[0016] The technical solutions of this application will now be clearly and completely described with reference to the accompanying drawings. Obviously, the described embodiments are only a part of the embodiments of this application, and not all of them. It should be understood that this application is not limited to the exemplary embodiments described herein. All other embodiments obtained by those skilled in the art based on the embodiments of this application without creative effort are within the scope of protection of this application. It should also be noted that, for ease of description, only the parts related to this application are shown in the accompanying drawings, not all of them.

[0017] Example 1, please refer to the appendix. Figure 1 This application provides an intelligent monitoring and early warning system for the transportation of box girders for high-speed railways, specifically including: The data monitoring component is used to acquire monitoring data on the movement of high-speed railway box girders, as well as monitoring data on the external forces involved in the movement.

[0018] Specifically, in the data monitoring component, the system monitors the transportation process of the box girder using deployed sensors such as ultrasonic sensor arrays, strain gauges, deflection sensors, and inclinometers, constructing transportation monitoring data for high-speed railway box girders. This data includes ultrasonic testing data and mechanical monitoring parameter data. Simultaneously, it monitors the external forces borne by the box girder, including wind force, braking force applied by transport vehicles, and acceleration / deceleration forces, constructing external force monitoring data for transportation. This data, along with the transportation monitoring data, provides a foundation for subsequent structural defect analysis and risk prediction.

[0019] Furthermore, the data monitoring component includes: acquiring multi-point ultrasonic sensing data of the box girder in real time during the transportation process by deploying an ultrasonic sensor array at key sections of the box girder, wherein the ultrasonic transmitter is fixed by sleeve bolts pre-embedded in the bottom plate of the box girder, and the ultrasonic receiver is adsorbed to the bottom surface of the top plate of the box girder by a strong magnetic module at the bottom; acquiring beam mechanical monitoring parameters during the transportation process by using strain gauges, deflection sensors, inclinometers, accelerometers, displacement sensors and support pressure sensors installed on the box girder; and integrating the multi-point ultrasonic sensing data and beam mechanical monitoring parameters by time alignment to obtain the transportation monitoring data.

[0020] Specifically, in the data monitoring component, multiple ultrasonic sensor arrays are first deployed at key sections of the box girder, such as the bottom plate, middle section, flanges, and web, to acquire multi-point ultrasonic sensing data of the box girder in real time during transportation. The transducer frequency of each ultrasonic transmitter is set to 390kHz, with a response time of 20ms, ensuring accurate detection of high-frequency deformation or micro-cracks. The ultrasonic transmitters are fixed using sleeve bolts pre-embedded in the bottom plate of the box girder, ensuring a stable position and orientation during transportation and preventing displacement due to vibration or external forces. The ultrasonic signal output is presented in analog form, typically a 4–20mA current signal or a 0–10V voltage signal, for real-time transmission and recording. In addition, the ultrasonic receiver is attached to the bottom surface of the box girder's top plate via a strong magnetic module, ensuring that the receiver will not loosen or fall off during transportation. This strong magnetic module has an attraction force greater than 250N, uses N52-grade neodymium iron boron magnets, and has a surface magnetic flux density higher than 200mT. It can provide sufficient attraction force to cope with high temperatures and external vibrations, and under high-temperature conditions, the magnetic force retention rate exceeds 90%, ensuring that the ultrasonic receiver can always work stably on the top plate of the box girder and accurately receive echo signals. At the same time, in order to supplement and enhance the overall mechanical monitoring of the box girder, various other sensors installed on the box girder, such as strain gauges, deflection sensors, inclinometers, accelerometers, displacement sensors, and support pressure sensors, will monitor important mechanical parameters such as strain, deflection, inclination, acceleration, displacement, and support pressure of the box girder during transportation. These parameters form the beam mechanical monitoring parameters, providing comprehensive structural status information to help identify minor deformations and potential defects of the beam under external forces. Finally, the acquired multi-point ultrasonic sensing data and beam mechanical monitoring parameters are integrated and time-aligned. That is, by comparing timestamps, data from different sensors are merged onto the same timeline, forming a complete transport monitoring dataset. In this way, the system can analyze the dynamic response of the box girder in real time during transport, accurately reflecting the deformation state of each structural unit, and providing a reliable basis for subsequent defect diagnosis and risk warning.

[0021] Furthermore, this application includes: the external force monitoring data for the transfer is various external excitation data acting on the box girder during transportation, including wind force data, braking force and acceleration / deceleration force applied by the transport vehicle, and vibration and impact data caused by uneven track.

[0022] Specifically, in the data monitoring component, since the box girder is not only affected by its own weight but also by various external forces from the external environment and transportation equipment, these external forces have a significant impact on the stability and safety of the box girder. Therefore, these external excitation data are monitored and acquired in real time, such as wind force data, braking force and acceleration / deceleration force applied by the transport vehicle, and vibration and impact data caused by track unevenness. Among them, wind force data is obtained based on the installation of wind speed and wind direction sensors, which can display changes in wind speed and wind direction in real time and help assess the dynamic impact of wind on the box girder. The braking force and acceleration / deceleration force applied by the transport vehicle refer to the inertial force generated on the box girder by the braking, acceleration, or deceleration of the girder transport vehicle. This data can be collected by accelerometers, strain gauges, etc., to help determine whether there is abnormal stress. Vibration and impact data caused by track unevenness can be obtained by vibration sensors, accelerometers, etc., which can monitor the vibration data caused by track unevenness and help assess its impact on the box girder. By collecting these external force excitation data in real time, the system can fully understand the various external influencing factors applied to the box girder during the transportation process, effectively judge the stress status of the box girder during the transportation process, and promptly discover potential structural problems and safety hazards, thereby providing a scientific basis for early warning and risk prediction.

[0023] The defect analysis component is used to perform structural defect correlation analysis on the high-speed railway box girder using the external force monitoring data of the transport, and to obtain the monitoring data distribution of defect response.

[0024] Specifically, in the defect analysis component, external forces trigger the response of the box girder structure, potentially revealing structural defects. A pre-built theoretical mechanics model is used to analyze the external force monitoring data. This model considers the box girder's geometry, material properties, support conditions, and external excitations, simulating the impact of external forces on each structural unit. Subsequently, based on the force analysis results output by the theoretical mechanics model, the system analyzes the defect response relationships of each structure, obtaining the response characteristics of each defect under different external force conditions. This constitutes the distribution of defect response monitoring data, helping the system identify potential structural problems and providing early warnings to prevent further defect expansion or impact on the box girder's safety.

[0025] Furthermore, the defect analysis component includes: establishing a theoretical mechanical model of the high-speed railway box girder and the external force of transportation; based on the theoretical mechanical model, performing stress analysis on the high-speed railway box girder structure according to the monitoring data of the external force of transportation, using the stress analysis results to analyze the defect response relationship of each structure, and obtaining the monitoring data distribution of the defect response, which is used to characterize the probability of the influence of different structural defect distributions on external force parameters.

[0026] Specifically, in the defect analysis component, a theoretical mechanical model of the high-speed railway box girder and the external forces during transport is first established. This theoretical mechanical model comprehensively considers the box girder's geometry, material properties, support conditions, external forces, and environmental factors. It can accurately simulate the entire stress process of the box girder during transport using finite element analysis, thereby obtaining the stress distribution, deformation, and stress state of different parts under external forces. Subsequently, based on the constructed theoretical mechanical model, stress analysis is performed on the external force monitoring data, simulating the force and strain response of external forces on various parts of the box girder, generating stress analysis results including a theoretical stress matrix. Then, based on these stress analysis results, defect response relationship analysis is performed on different structural units of the box girder, obtaining the defect-sensitive external force parameters and corresponding response probabilities corresponding to the distribution of structural defects. This forms the defect response monitoring data distribution, used to characterize the probability of different structural defect distributions affecting external force parameters, helping to identify potentially high-risk areas and providing a scientific basis for subsequent maintenance and repair work, ensuring the safety and stability of the box girder.

[0027] Furthermore, the defect analysis component includes: taking the external force monitoring data of the transport as input, calculating the theoretical force matrix of the high-speed railway box girder through the theoretical mechanics model; establishing the external force response relationship of each structural defect distribution; using the theoretical force matrix to map and analyze the external force response relationship to obtain the defect-sensitive influence external force parameters and corresponding response probabilities corresponding to each structural defect distribution, and constructing the monitoring data distribution of the defect response.

[0028] Specifically, in the defect analysis component, the external force monitoring data from the transport process is first imported into the theoretical mechanics model as input data. The theoretical mechanics model then solves the equilibrium equations of the structure using finite element analysis. That is, based on the geometry, material, and support conditions of the box girder, a stiffness matrix is ​​used to represent the deformation and stress relationship of each part of the box girder. Then, the input external force data is applied to each degree of freedom of the mechanical model, and the equilibrium equations of the structure are solved using Gaussian elimination or the conjugate gradient method to obtain the stress, strain, displacement, and other force parameters of each node or element. Subsequently, these calculated force parameters are integrated in matrix form to form a theoretical force matrix. This theoretical force matrix contains the stress state of the box girder under various external forces, providing the foundation for subsequent defect response analysis, risk assessment, and early warning systems. Subsequently, based on this theoretical mechanics model, the response changes of different types of defects, such as microcracks, local support loosening, and structural damage, under external forces are simulated. This analysis examines how defects affect the force distribution, deformation, and vibration under external forces. The simulation results are then probabilistically processed to establish the external force response relationships for each structural defect distribution, providing a basis for subsequent defect detection and risk assessment. Next, the obtained theoretical force matrix is ​​synchronized to the corresponding external force response relationships for each structural defect distribution for mapping and analysis. Through iterative simulation of these external force response relationships, the defect-sensitive external force parameters corresponding to each structural defect distribution, such as wind force, acceleration force, and track inequality, are calculated. Simultaneously, the corresponding response probabilities are obtained through probabilistic processing, thereby assessing the potential threat of defects to structural safety under different external forces. Finally, based on the external force parameters and corresponding response probabilities of the defect sensitivity to each structural defect distribution obtained from the analysis, a monitoring data distribution of defect response is constructed. This monitoring data distribution displays the response probability and sensitivity of various structural defects under different external force conditions. For example, it provides the probability distribution of stress, displacement, vibration, and other responses induced by specific defect locations under each external force. This data helps determine which areas of the box girder are most susceptible to damage during transportation, and the safety risks that these defects may cause under external force excitation. In this way, the system can assess the health status of the box girder structure in real time and provide accurate data support for defect early warning, location, and subsequent maintenance.

[0029] Furthermore, the defect analysis component includes: performing coordinate transformation and direction correction on the external force monitoring data based on the actual fixed posture angle of the box girder during transportation to generate posture correction external forces; and mapping the posture correction external forces to each structural unit of the high-speed railway box girder based on the internal structural stiffness distribution and transportation support stiffness of the box girder to correct the theoretical force matrix.

[0030] Specifically, in the defect analysis component, during actual transportation, the box girder does not always maintain an ideal horizontal state; its installation posture may have slight tilt angles or rotational deviations. To ensure that the calculated external force is consistent with the actual force direction of the box girder, data from attitude sensors such as inclinometers, accelerometers, and gyroscopes are collected in real time to calculate the actual fixed attitude angles of the box girder in three-dimensional space, including the actual pitch angle, actual roll angle, and actual yaw angle. Subsequently, a local coordinate system is established based on the calculated actual fixed attitude angles, and the external force monitoring data is transformed from the global coordinate system to the local coordinate system of the box girder through a coordinate transformation matrix. This aligns the direction of the external force with the force direction of the box girder, ensuring that subsequent stress analysis can accurately reflect the effect of external forces on each structural unit of the box girder. After correction, attitude-corrected external force data is generated, which more accurately reflects the distribution of external loads borne by the box girder under its actual posture. Subsequently, since box girders are typically composed of multi-cavity structures, the stiffness of different regions, such as the web, top plate, bottom plate, and support areas, varies. Furthermore, the stiffness distribution of transport support structures, such as support pads, pallets, and hangers, also affects the transmission path of external forces within the beam. Therefore, the system divides the beam into multiple structural units and assigns each unit a corresponding material elastic modulus, moment of inertia, and boundary constraints. Then, based on the ratio of support stiffness to beam stiffness, the attitude correction external forces are weighted and distributed to the corresponding structural unit nodes. Through this mechanical mapping process, the stress changes in different parts under external forces can be accurately reflected, helping to identify areas of high stress concentration or abrupt stress changes. Finally, based on the mapped external force distribution, the theoretical force matrix is ​​corrected. In this process, the difference between the actual external force of each structural unit after mapping and the corresponding external force in the theoretical force matrix is ​​calculated. The calculated difference is multiplied by the correction weight, which is usually between 0.3 and 0.8 and adjusted according to the signal reliability. Then, the product of the theoretical force matrix and the calculated value is added to complete the correction of the theoretical force matrix. This makes the stress analysis of the box girder under complex transportation conditions closer to the real working conditions, thus providing reliable support for intelligent monitoring and safety early warning.

[0031] Furthermore, the defect analysis component includes: simulating typical defect types in the theoretical mechanics model, including microcracks, support loosening, and local structural damage; using transport external force monitoring data as input, calculating the theoretical stress, strain, displacement, and vibration response of each defect element under external force through the theoretical mechanics model; comparing the theoretical response under healthy conditions, quantifying the defect response increment, and obtaining the sensitivity index of each defect element; and through a preset number of simulation iterations, probabilistically processing all obtained sensitivity indices to generate the response probability distribution relationship of each structural defect under transport external force, and establishing the external force response relationship of each structural defect distribution.

[0032] Specifically, in the defect analysis component, typical defect types, including microcracks, support loosening, and local structural damage, are first simulated in the established theoretical mechanical model. Microcracks are simulated by introducing fine cracks into concrete elements or reducing local stiffness; support loosening is represented by adjusting boundary conditions or reducing the constraint stiffness of support nodes; and local structural damage is reflected by modifying the elastic modulus of the material or reducing the load-bearing area of ​​the elements. In this way, the theoretical mechanical model can cover various defect forms that may occur in box girders during actual use and transportation, ensuring the comprehensiveness of the analysis and engineering comparability. Subsequently, the external force monitoring data during transportation is loaded into the theoretical mechanical model as input. Through finite element analysis, the response of different defect locations and types is simulated, and the theoretical dynamic response characteristics of each defect element under external force are calculated, including theoretical stress, strain, displacement, and vibration response, to quantify the degree of influence of external force on the defect location. Subsequently, to quantitatively evaluate the structural response changes caused by defects, the theoretical dynamic response characteristics under the defective state were compared with those under the healthy state. The defect response increment of each element was calculated using the difference method. By dividing each defect response increment by the maximum defect response increment, a sensitivity index for each defective element was quantified. These sensitivity indices characterize the impact of a specific defect on the overall structural response under a specific external force; higher values ​​indicate greater sensitivity to external forces and a higher likelihood of becoming a potential risk point. Then, through a predetermined number of simulation iterations, the above analysis was repeated under different combinations of external forces and defect distributions. The sensitivity indices generated during the simulation were statistically analyzed, and based on the statistical results, all sensitivity indices were probabilistically processed to generate the response probability distribution relationship of each structural defect under transportation external forces. This response probability distribution describes the response probability and trend of different defect types and locations under specific external force conditions. Finally, based on the results of statistical analysis, the external force response relationship of each structural defect distribution is established. This external force response relationship not only reflects the coupling law between defects and external forces, but also provides a quantitative basis for subsequent risk prediction and real-time early warning, enabling the system to identify potential structural anomalies earlier and achieve high-precision safety control of the high-speed railway box girder transportation process.

[0033] Furthermore, this application includes: the theoretical mechanical model is a finite element model, including beam material properties, geometric structure, support constraints, and temperature stress factors.

[0034] Specifically, the theoretical mechanics model is established using finite element analysis to accurately describe the mechanical characteristics of the high-speed railway box girder during transportation, including external forces, structural response, and defect sensitivity. Based on actual box girder structural parameters, this model achieves dynamic simulation and quantitative analysis of the overall stress state of the box girder through comprehensive modeling of material, geometry, support, and environmental factors. Regarding the modeling of beam material properties, the model defines parameters such as elastic modulus, Poisson's ratio, density, and damping coefficient based on the characteristics of the high-performance prestressed concrete used in the high-speed railway box girder, while also considering the changes in mechanical properties of different concrete strength grades at different ages. For the internal prestressed steel strands, an elastoplastic material model is used to describe the nonlinear characteristics of the stress-strain relationship during tensioning and loading. In terms of geometric modeling, the model constructs a three-dimensional geometric model based on the actual design drawings of the box girder, including key structures such as the bottom plate, top plate, web, diaphragms, and hoisting holes. The model employs high-density mesh generation technology, locally refining stress concentration areas such as support sections, around lifting holes, and connection nodes to ensure accurate capture of local stress gradient changes and microcrack response characteristics during external force loading. In setting support constraints, the model considers the actual support state of the box girder during transport, including the constraint stiffness characteristics of support pads, pallets, and lifting rods. The system achieves mechanical coupling between the girder and transport equipment by defining boundary conditions, elastic support coefficients, and frictional contact relationships for support nodes. Especially during lifting or braking phases, the model can dynamically update the support reaction force distribution, thus realistically reflecting the force transmission path and support response of the box girder under complex stress environments. To simulate temperature stress factors in the transport environment, the model also considers the impact of ambient temperature changes, solar radiation, internal hydration heat of concrete, and diurnal temperature differences on the thermal stress of the box girder structure. By applying temperature loads and mechanical loads in tandem, the model calculates the additional strain caused by temperature stress and the development trend of internal cracks, thereby improving the model's ability to reproduce real-world conditions. Through the above modeling process, the established finite element model can comprehensively reflect the real stress characteristics of high-speed railway box girders during transportation, providing an accurate theoretical basis and calculation support for external force response analysis, defect sensitivity identification, and risk warning, ensuring that the monitoring results are engineering feasible and predictive reliable.

[0035] The risk prediction component is used to align and parse the migration monitoring data in real time according to the distribution of the monitoring data of the defect response, establish a migration monitoring data time series chain, perform risk analysis and prediction according to the monitoring changes of the migration monitoring data time series chain, generate corresponding early warning information, and provide visual feedback.

[0036] Specifically, in the risk prediction component, to achieve intelligent risk assessment and real-time early warning of the transport status of high-speed railway box girders, the system first aligns and analyzes the real-time collected transport monitoring data based on the previously obtained defect response monitoring data distribution, establishing a continuous transport monitoring data time-series chain. Then, it calculates the real-time changes of various monitoring parameters in the transport monitoring data time-series chain, identifying trends, abrupt changes, and frequency drift to determine the health status of the box girder structure. When the monitored changes exceed the defect monitoring threshold, risk analysis and prediction are immediately executed, comprehensively assessing the abnormal coupling characteristics between external forces and structural responses, confirming potential crack, loosening, or deformation risks, and generating corresponding early warning information. Feedback is then provided through multi-layered visualization methods; for example, the monitor in the driver's cab displays real-time scrolling changes in monitoring data. When the data exceeds a set threshold, the interface numbers flash red as an early warning, pushing the alarm signal to the manager's mobile app via a wireless module, prompting the operator to immediately suspend the girder lifting operation and investigate the cause of the anomaly. Through this real-time analysis and visualization early warning mechanism based on time-series chains, the system can achieve dynamic safety monitoring and rapid response during the transportation of high-speed railway box girders, improving the timeliness and reliability of structural risk identification.

[0037] Furthermore, the risk prediction component includes: real-time alignment of transport monitoring data based on the distribution of defect response monitoring data; time-series splicing of the transport monitoring data using the distribution time of defect response monitoring data as a benchmark to construct a multi-source data time-series chain; real-time analysis of the transport monitoring data time-series chain to calculate monitored changes, including the amplification, abrupt changes, and frequency variations of strain, displacement, vibration, and ultrasonic signals; identification of potential defect characteristics when monitored changes exceed the health baseline or theoretical threshold; and time-series interactive verification based on the monitored changes corresponding to the time-series chain, wherein the amplitude of signal changes at different monitoring points under the same external force excitation is verified. The system compares the signal with the frequency; determines the phase relationship and consistency between the signal and the external force; combines the mutual verification results with the defect response probability matrix to confirm the existence of defects and locate defect areas; combines the monitored changes in defect areas that have undergone interactive verification with the defect response probability distribution to generate a weighted response index, which is used to quantify the sensitivity of minor defects or potential hazards; normalizes the weighted response index of each structural unit and compares it with the defect monitoring threshold. When the preset safety threshold is exceeded, an early warning message is generated, which is displayed in real time on the monitoring screen through a character overlay device and displayed on the driver's cab display in the form of red flashing. At the same time, an alarm notification is sent to the mobile APP of the remote management personnel.

[0038] Specifically, in the risk prediction component, firstly, based on the distribution of defect response monitoring data, various real-time collected transport monitoring data, such as ultrasonic ranging signals, strain data, displacement changes, acceleration, and vibration signals, are time-aligned and synchronized using interpolation, resampling, and time-series stitching as the benchmark, constructing a continuous and unified multi-source monitoring time-series chain. This chain is then sorted according to data source to form a transport monitoring data time-series chain. This chain fully records the temporal correlation between the dynamic stress, response changes, and external force effects on the box girder during transport. Subsequently, a sliding window algorithm is used to analyze the established transport monitoring data time-series chain in real time, calculating changes and analyzing dynamic trends of key monitoring parameters. The analysis includes indicators such as amplitude changes, abrupt changes, and frequency drift of strain, displacement, vibration, and ultrasonic signals, ensuring that the weak structural response under external force can be amplified, allowing even hidden defects such as minor cracks, loose supports, or localized damage to be sensitively identified. When a monitored change exceeds the health baseline or theoretical threshold, a potential defect identification mechanism is triggered. At this point, the abnormal monitoring data undergoes time-series interactive verification. Specifically, under the same external force excitation, such as vibration or braking impact at a specific frequency, the amplitude and frequency response of signal changes at different monitoring points are compared, and their phase relationship and consistency are analyzed. If multiple monitoring points exhibit consistent vibration frequency changes or synchronous signal abrupt changes under the same excitation, the judgment result is combined with the defect response probability matrix to determine the specific area with the anomaly. This time-series interactive verification mechanism effectively amplifies the coupling effect between external force and structural response, thereby revealing minute defects that are difficult to detect with traditional static monitoring. After confirming the existence of a defect, the time-series verified monitored change in the defect area is fused with the defect response probability distribution matrix to calculate the weighted response index of each monitoring unit. This weighted response index comprehensively considers the monitoring signal amplitude, response consistency, and defect probability weight, and is used to quantify the sensitivity of different structural regions to external force excitation. Subsequently, the weighted response indices of all structural units are normalized to their maximum and minimum values ​​and compared with the set defect monitoring threshold. When the weighted response index of a certain unit exceeds the preset safety threshold, an early warning message is immediately generated. The alarm data is then displayed in real time on the monitoring screen via a character overlay device. Simultaneously, the display in the driver's cab also shows the numerical change and flashes red to alert the driver. At the same time, the system pushes the alarm signal to the remote management personnel's mobile app via a wireless communication module, enabling synchronized mobile alerts and ensuring that operators and management personnel can take immediate intervention measures, such as stopping beam lifting or checking the stability of the lifting equipment. Through this process, the system achieves time-series alignment, real-time analysis, and dynamic interactive verification of multi-source monitoring data. It amplifies the differences in the response of minute structures under external forces, effectively identifying potential hidden defects and ensuring the safety and controllability of the high-speed railway box girder transportation process.

[0039] In summary, the intelligent monitoring and early warning system for high-speed railway box girder transportation provided in this application has the following technical effects: based on sensor measurement and multi-source data fusion analysis, it realizes dynamic diagnosis of the health status of box girder structures and advanced prediction of potential risks, thereby improving the sensitivity and accuracy of monitoring.

[0040] Example 2: Based on the same inventive concept as the intelligent monitoring and early warning system for high-speed railway box girder transportation in the foregoing examples, this application also provides an intelligent monitoring and early warning method for high-speed railway box girder transportation. Please refer to the appendix. Figure 2 The process includes: acquiring monitoring data on the transport of high-speed railway box girders, as well as monitoring data on the external forces involved in the transport; using the external force monitoring data to perform structural defect correlation analysis on the high-speed railway box girders to obtain the monitoring data distribution of defect responses; based on the monitoring data distribution of defect responses, performing real-time alignment analysis on the transport monitoring data to establish a transport monitoring data time series chain; performing risk analysis and prediction according to the monitoring changes in the transport monitoring data time series chain; generating corresponding early warning information; and providing visual feedback.

[0041] Furthermore, the intelligent monitoring and early warning method for the transportation of high-speed railway box girders also includes: deploying an ultrasonic sensor array at key sections of the box girder to acquire multi-point ultrasonic sensing data of the box girder in real time during transportation, wherein the ultrasonic transmitter is fixed by sleeve bolts pre-embedded in the bottom plate of the box girder, and the ultrasonic receiver is adsorbed to the bottom surface of the top plate of the box girder by a strong magnetic module at the bottom; acquiring beam mechanical monitoring parameters during transportation by using strain gauges, deflection sensors, inclinometers, accelerometers, displacement sensors, and support pressure sensors installed on the box girder; and integrating the multi-point ultrasonic sensing data with the beam mechanical monitoring parameters by time alignment to obtain the transportation monitoring data.

[0042] Furthermore, the intelligent monitoring and early warning method for high-speed railway box girder transportation also includes: the external force monitoring data for transportation is various external excitation data acting on the box girder during transportation, including wind force data, braking force and acceleration / deceleration force applied by the transport vehicle, and vibration and impact data caused by uneven track.

[0043] Furthermore, the intelligent monitoring and early warning method for the transportation of high-speed railway box girders also includes: establishing a theoretical mechanical model of the high-speed railway box girder and the external force of transportation; based on the theoretical mechanical model, performing stress analysis on the high-speed railway box girder structure according to the monitoring data of the external force of transportation, using the stress analysis results to analyze the defect response relationship of each structure, and obtaining the monitoring data distribution of the defect response, which is used to characterize the probability of the influence of different structural defect distributions on external force parameters.

[0044] Furthermore, the intelligent monitoring and early warning method for the transportation of high-speed railway box girders also includes: taking the external force monitoring data of the transportation as input, calculating the theoretical force matrix of the high-speed railway box girder through the theoretical mechanical model; establishing the external force response relationship of each structural defect distribution; using the theoretical force matrix to map and analyze the external force response relationship to obtain the defect-sensitive influence external force parameters and corresponding response probabilities corresponding to each structural defect distribution, and constructing the monitoring data distribution of the defect response.

[0045] Furthermore, the intelligent monitoring and early warning method for the transportation of high-speed railway box girders also includes: Based on the actual fixed posture angle of the box girder during transportation, coordinate transformation and direction correction are performed on the external force monitoring data to generate posture correction external forces. Based on the internal structural stiffness distribution of the box girder and the transportation support stiffness, the posture correction external forces are mapped to each structural unit of the high-speed railway box girder to correct the theoretical force matrix.

[0046] Furthermore, the intelligent monitoring and early warning method for the transportation of high-speed railway box girders also includes: Typical defect types, including microcracks, support loosening, and local structural damage, are simulated in the theoretical mechanics model. Using transport force monitoring data as input, the theoretical stress, strain, displacement, and vibration response of each defect element under external force are calculated through the theoretical mechanics model. The theoretical response under healthy conditions is compared to quantify the defect response increment, obtaining sensitivity indices for each defect element. Through a preset number of simulation iterations, all obtained sensitivity indices are probabilistically processed to generate the probability distribution relationship of the response of each structural defect under transport force, establishing the external force response relationship of each structural defect distribution.

[0047] Furthermore, the intelligent monitoring and early warning method for the transportation of high-speed railway box girders also includes: The theoretical mechanical model is a finite element model, which includes the beam's material properties, geometric structure, support constraints, and temperature stress factors.

[0048] Furthermore, the intelligent monitoring and early warning method for the transportation of high-speed railway box girders also includes: Based on the distribution of defect response monitoring data, the migration monitoring data is time-aligned. Using the distribution time of the defect response monitoring data as a benchmark, the migration monitoring data is time-series spliced ​​to construct a multi-source data time-series chain. The migration monitoring data time-series chain is then analyzed in real-time to calculate monitored changes, including the amplification, abrupt changes, and frequency variations of strain, displacement, vibration, and ultrasonic signals. When the monitored changes exceed the healthy baseline or theoretical threshold, potential defect characteristics are identified. Time-series interactive verification is performed based on the monitored changes corresponding to the time-series chain, specifically comparing the signal amplitude and frequency changes at different monitoring points under the same external force excitation. The system compares the phase relationship and consistency between the signal and the external force; combines the mutual verification results with the defect response probability matrix to confirm the existence of defects and locate defect areas; combines the monitored changes in defect areas that have undergone interactive verification with the defect response probability distribution to generate a weighted response index, which is used to quantify the sensitivity of minor defects or potential hazards; normalizes the weighted response index of each structural unit and compares it with the defect monitoring threshold. When the preset safety threshold is exceeded, an early warning message is generated, which is displayed in real time on the monitoring screen through a character overlay device and displayed on the driver's cab display in the form of red flashing. At the same time, an alarm notification is sent to the mobile APP of the remote management personnel.

[0049] The various embodiments in this specification are described in a progressive manner, with each embodiment focusing on the differences from other embodiments. The intelligent monitoring and early warning system for high-speed railway box girder transportation in the aforementioned embodiment 1 and the specific examples are also applicable to the intelligent monitoring and early warning method for high-speed railway box girder transportation in this embodiment. Through the foregoing detailed description of the intelligent monitoring and early warning system for high-speed railway box girder transportation, those skilled in the art can clearly understand the intelligent monitoring and early warning method for high-speed railway box girder transportation in this embodiment. Therefore, for the sake of brevity, it will not be described in detail here.

[0050] The above description of the disclosed embodiments enables those skilled in the art to make or use this application. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of this application. Therefore, this application is not to be limited to the embodiments shown herein, but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.

[0051] Obviously, those skilled in the art can make various modifications and variations to this application without departing from the spirit and scope of this application. Therefore, if such modifications and variations fall within the scope of this application and its equivalents, this application also intends to include such modifications and variations.

Claims

1. A high-speed railway box girder intelligent monitoring and early warning system, characterized in that, include: The data monitoring component is used to acquire monitoring data on the movement of high-speed railway box girders, as well as monitoring data on the external forces involved in the movement. The defect analysis component is used to perform structural defect correlation analysis on the high-speed railway box girder using the external force monitoring data of the transport, and to obtain the monitoring data distribution of defect response; The risk prediction component is used to align and parse the migration monitoring data in real time according to the distribution of the monitoring data of the defect response, establish a migration monitoring data time series chain, perform risk analysis and prediction according to the monitoring change amount of the migration monitoring data time series chain, generate corresponding early warning information, and provide visual feedback. The risk prediction component includes: Based on the distribution of monitoring data for defect response, the migration monitoring data is time-aligned, and the migration monitoring data is time-series spliced ​​together with the distribution time of the monitoring data for defect response as a reference to construct a multi-source data time-series chain to obtain the migration monitoring data time-series chain. The time-series chain of the transport monitoring data is analyzed in real time to calculate the monitored changes, including the increase, abrupt change and frequency change of strain, displacement, vibration and ultrasonic signals. When the monitored changes exceed the health baseline or theoretical threshold, potential defect characteristics are identified. Time-series interactive verification is performed based on the monitored changes corresponding to the time-series chain. This involves comparing the amplitude and frequency of signal changes at different monitoring points under the same external force excitation; determining the phase relationship and consistency between the signal and the external force; and combining the mutual verification results with the defect response probability matrix to confirm the existence of the defect and locate the defect area. The monitored changes in defect areas, which have been interactively verified, are combined with the defect response probability distribution to generate a weighted response index, which is used to quantify the sensitivity of minor defects or potential hazards. The weighted response index of each structural unit is normalized and compared with the defect monitoring threshold. When the preset safety threshold is exceeded, an early warning message is generated and displayed in real time on the monitoring screen through a character overlay device. It is also displayed on the driver's cab display in the form of red flashing and sent to the mobile APP of the remote management personnel.

2. The intelligent monitoring and early warning system for high-speed railway box girder transportation according to claim 1, characterized in that, The data monitoring components include: By deploying an ultrasonic sensor array at key sections of the box girder, multi-point ultrasonic sensing data of the box girder during the transportation process can be acquired in real time. The ultrasonic transmitter is fixed by sleeve bolts embedded in the bottom plate of the box girder, and the ultrasonic receiver is adsorbed to the bottom surface of the top plate of the box girder by a strong magnetic module at the bottom. By using strain gauges, deflection sensors, inclinometers, accelerometers, displacement sensors, and support pressure sensors installed on the box girder, mechanical monitoring parameters of the girder during the transportation process are obtained. The multi-point ultrasonic sensing data and the beam mechanical monitoring parameters are time-aligned and integrated to obtain the transport monitoring data.

3. The intelligent monitoring and early warning system for high-speed railway box girder transportation according to claim 1, characterized in that, The external force monitoring data for the transport includes various external excitation data acting on the box girder during transportation, including wind force data, braking force and acceleration / deceleration force applied by the transport vehicle, and vibration and impact data caused by uneven track.

4. The intelligent monitoring and early warning system for high-speed railway box girder transportation according to claim 1, characterized in that, The defect analysis component includes: Establish a theoretical mechanical model of the box girder of high-speed railway and the external force of its transport; Based on the theoretical mechanics model, the stress analysis of the high-speed railway box girder structure is performed according to the external force monitoring data of the transport. The stress analysis results are used to analyze the defect response relationship of each structure and obtain the monitoring data distribution of the defect response, which is used to characterize the probability of the influence of different structural defect distributions on external force parameters.

5. The intelligent monitoring and early warning system for high-speed railway box girder transportation according to claim 4, characterized in that, The defect analysis component includes: Using the external force monitoring data of the transport as input, the theoretical force matrix of the high-speed railway box girder is calculated through the theoretical mechanical model; Establish the external force response relationship for each structural defect distribution; By using the theoretical force matrix to map and analyze the external force response relationship, the external force parameters sensitive to each structural defect distribution and the corresponding response probability are obtained, and the monitoring data distribution of the defect response is constructed.

6. The intelligent monitoring and early warning system for high-speed railway box girder transportation according to claim 5, characterized in that, The defect analysis component includes: Based on the actual fixed posture angle of the box girder during the transportation process, coordinate transformation and direction correction are performed on the external force monitoring data to generate posture correction external force; Based on the internal structural stiffness distribution of the box girder and the stiffness of the transport support, the attitude correction external force is mapped to each structural unit of the high-speed railway box girder to correct the theoretical force matrix.

7. The intelligent monitoring and early warning system for high-speed railway box girder transportation according to claim 5, characterized in that, The defect analysis component includes: Typical defect types are simulated in the theoretical mechanical model, including microcracks, support loosening, and local structural damage; Using the external force monitoring data as input, the theoretical stress, strain, displacement and vibration response of each defect element under the action of external force are calculated through the theoretical mechanical model. By comparing the theoretical response under healthy conditions, the defect response increment is quantified to obtain the sensitivity index of each defect unit. By simulating and iterating a predetermined number of times, all the obtained sensitivity indicators are processed probabilistically to generate the response probability distribution relationship of each structural defect under the action of external force during transportation, and to establish the external force response relationship of each structural defect distribution.

8. The intelligent monitoring and early warning system for high-speed railway box girder transportation according to claim 7, characterized in that, The theoretical mechanical model is a finite element model, which includes the beam's material properties, geometric structure, support constraints, and temperature stress factors.

9. A method for intelligent monitoring and early warning of high-speed railway box girder transportation, characterized in that, Executed by the intelligent monitoring and early warning system for high-speed railway box girder transport as described in any one of claims 1 to 8, including: Acquire monitoring data on the movement of high-speed railway box girders, as well as monitoring data on the external forces involved in the movement; The external force monitoring data of the transport was used to perform structural defect correlation analysis on the high-speed railway box girder to obtain the monitoring data distribution of defect response; Based on the distribution of the monitoring data of the defect response, the migration monitoring data is aligned and analyzed in real time to establish a migration monitoring data time series chain. Risk analysis and prediction are performed according to the monitoring changes in the migration monitoring data time series chain to generate corresponding early warning information and provide visual feedback. The intelligent monitoring and early warning method for high-speed railway box girder transportation also includes: Based on the distribution of monitoring data for defect response, the migration monitoring data is time-aligned, and the migration monitoring data is time-series spliced ​​together with the distribution time of the monitoring data for defect response as a reference to construct a multi-source data time-series chain to obtain the migration monitoring data time-series chain. The time-series chain of the transport monitoring data is analyzed in real time to calculate the monitored changes, including the increase, abrupt change and frequency change of strain, displacement, vibration and ultrasonic signals. When the monitored changes exceed the health baseline or theoretical threshold, potential defect characteristics are identified, and time-series interactive verification is performed based on the monitored changes corresponding to the time-series chain. In this process, the amplitude and frequency of signal changes at different monitoring points under the same external force excitation are compared. Determine the phase relationship and consistency between the signal and the external force; combine the mutual verification results with the defect response probability matrix to confirm the existence of the defect and locate the defect area; The monitored changes in defect areas, which have been interactively verified, are combined with the defect response probability distribution to generate a weighted response index, which is used to quantify the sensitivity of minor defects or potential hazards. The weighted response index of each structural unit is normalized and compared with the defect monitoring threshold. When the preset safety threshold is exceeded, an early warning message is generated and displayed in real time on the monitoring screen through a character overlay device. It is also displayed on the driver's cab display in the form of red flashing and sent to the mobile APP of the remote management personnel.

Images