Multi-source data fusion-based bridge swivel posture intelligent adjustment method and system

Abstract

The invention provides a bridge swivel attitude intelligent adjustment method and system based on multi-source data fusion, and the method comprises the steps: obtaining a multi-source monitoring data set generated in a bridge swivel process, carrying out the time-space alignment and fusion processing of the multi-source monitoring data set, generating fusion monitoring data, and carrying out the adjustment of the swivel attitude of a bridge. And based on the fused monitoring data and a preset target attitude parameter set, identifying attitude deviation characteristics between a bridge swivel attitude and a target attitude, generating an attitude adjustment strategy for a bridge swivel execution mechanism according to the attitude deviation characteristics, and executing the attitude adjustment strategy to adjust the attitude of the bridge swivel execution mechanism. And carrying out real-time posture adjustment operation on the bridge turning process. According to the method, the system reliability can be enhanced while the adjustment efficiency is improved, and the problems of insufficient control precision and response delay caused by data isolation and strategy staticization in a traditional method are solved.

Description

Technical Field

[0001] The present invention relates to the fields of data processing and intelligent control. Specifically, it relates to a method and system for intelligent adjustment of the posture of a bridge rotation based on multi-source data fusion. Background Art

[0002] The adjustment of the posture of a bridge rotation is crucial in bridge construction. The goal is to ensure that the rotating structure precisely matches the preset target trajectory in terms of spatial posture through real-time monitoring and dynamic control. Existing adjustment methods usually rely on simple monitoring data (such as the displacement of key points of the bridge or the hydraulic parameters of the actuator) for posture feedback, and drive the actuator to complete the rotation operation through preset fixed adjustment instructions. However, it is difficult for such methods to accurately quantify the coupled effects of environmental disturbances (such as wind force and temperature changes) and the response lag of the actuator on the rotation posture, resulting in unrecognized dynamic deviations between the actual posture and the target posture. At the same time, the fixed adjustment strategy cannot adapt to the non-linear changes of structural deformation and external disturbances during the rotation process, easily leading to a mismatch between the adjustment instruction and the real-time working conditions, resulting in a decrease in adjustment accuracy, frequent start and stop of the actuator, and even the risk of local overload of the structure, restricting the safety and efficiency of the rotation construction of long-span bridges. Summary of the Invention

[0003] The present invention provides a method and system for intelligent adjustment of the posture of a bridge rotation based on multi-source data fusion.

[0004] In a first aspect, an embodiment of the present invention provides a method for intelligent adjustment of the posture of a bridge rotation based on multi-source data fusion, including: Obtaining a multi-source monitoring data set generated during the rotation of the bridge, where the multi-source monitoring data set includes bridge structure response monitoring data, environmental impact factor monitoring data, and the operating state monitoring data of the rotation actuator; Performing spatio-temporal alignment and fusion processing on the multi-source monitoring data set to generate fused monitoring data; Based on the fused monitoring data and a preset set of target posture parameters, identifying the posture deviation characteristics between the posture of the bridge rotation and the target posture; Generating a posture adjustment strategy for the rotation actuator of the bridge according to the posture deviation characteristics; Executing the posture adjustment strategy to perform real-time posture adjustment operations on the rotation process of the bridge.

[0005] In a second aspect, an embodiment of the present invention provides a system for intelligent adjustment of the posture of a bridge rotation based on multi-source data fusion, including: A memory in which a computer program is stored; A processor for loading the computer program to implement the method for intelligent adjustment of the posture of a bridge rotation based on multi-source data fusion as described above.

[0006] The intelligent adjustment method for the bridge rotation posture based on multi-source data fusion provided by the present invention obtains a multi-source monitoring data set during the bridge rotation process, integrates multi-dimensional information of structural responses, environmental impacts, and the operating states of actuators, performs spatio-temporal alignment and fusion processing on the multi-source data, eliminates the spatio-temporal reference differences during the sensor acquisition process, generates spatio-temporally consistent fusion monitoring data, and provides a reliable data basis for the accurate identification of posture deviations. Based on the dynamic comparison between the fusion monitoring data and the target posture parameters, the posture deviation characteristics are analyzed collaboratively from multiple dimensions including three-dimensional coordinate offset, overall torsion angle, and cross-section deformation degree, comprehensively quantifying the comprehensive deviation degree, breaking through the limitations of traditional single-parameter deviation analysis, and significantly improving the accuracy of deviation identification. Through the posture adjustment strategy generation model, combining structural mechanics constraints and actuator operating rules, a combination of adjustment instructions adapted to the current rotation state is dynamically generated, driving multiple execution units to adjust collaboratively according to the action type, direction, amplitude, and timing, realizing the adaptive optimization of the deviation elimination process, effectively avoiding problems such as local overload or adjustment lag. Execute closed-loop control and real-time feedback of multi-source monitoring data to ensure the continuous optimization and precise execution of the adjustment strategy, maintain high-precision control of the rotation posture under complex environmental disturbances and structural dynamic changes, enhance the system reliability while improving the adjustment efficiency, and solve the problems of insufficient control accuracy and response delay caused by data isolation and static strategies in traditional methods. BRIEF DESCRIPTION OF THE DRAWINGS

[0007] In order to more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the following will briefly introduce the drawings required for use in the description of the embodiments or the prior art. Obviously, the drawings in the following description are only some embodiments of the present invention. For those of ordinary skill in the art, without creative efforts, other drawings can be obtained based on these drawings.

[0008] Figure 1 It is a flowchart of an intelligent adjustment method for the bridge rotation posture based on multi-source data fusion provided by an embodiment of the present invention.

[0009] Figure 2 It is a schematic diagram of the composition of an intelligent adjustment system for the bridge rotation posture based on multi-source data fusion provided by an embodiment of the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0010] The following will clearly and completely describe the technical solutions in the embodiments of the present invention with reference to the drawings in the embodiments of the present invention. Obviously, the described embodiments are only some embodiments of the present invention, rather than all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative efforts belong to the scope of protection of the present invention.

[0011] Please refer to Figure 1 , Figure 1 which is a flowchart of an intelligent adjustment method for the bridge rotation attitude based on multi-source data fusion provided by an embodiment of the present invention. This method can be executed by a computer system, and the method may include the following steps: Step S100: Obtain a multi-source monitoring data set generated during the bridge rotation process. The multi-source monitoring data set includes bridge structure response monitoring data, environmental impact factor monitoring data, and the operating status monitoring data of the rotation execution mechanism.

[0012] The bridge structure response monitoring data is the data reflecting the mechanical response and deformation of the bridge structure during the rotation process. When the bridge rotates, its structure will be affected by various forces and generate corresponding responses, and these response data can reflect the actual working state of the bridge structure. For example, the displacement, strain, stress, etc. data of the key parts of the bridge all belong to the bridge structure response monitoring data. The displacement data can be collected by displacement sensors, and these sensors can be installed at the key nodes or target parts of the bridge to measure the position change of the bridge in real time during the rotation process. The strain data can be obtained using strain gauges. The strain gauges are pasted on the surface of the bridge structure. When the structure deforms, the resistance of the strain gauge will change, and the corresponding strain value can be obtained by measuring the resistance change. The stress data can be calculated based on the strain data combined with the mechanical property parameters of the material.

[0013] The environmental impact factor monitoring data is the data describing the environmental conditions during the bridge rotation process. Environmental factors will have an important impact on the bridge rotation. Different environmental conditions may cause changes in the mechanical properties of the bridge structure and even affect the safety and stability of the rotation. The environmental impact factor monitoring data includes air temperature, wind speed, humidity, etc. The air temperature data can be collected using temperature sensors, and the temperature sensors are installed at different positions around the bridge to obtain accurate environmental temperature information. The wind speed data can be measured by an anemometer, and the anemometer is usually installed at a higher position of the bridge to avoid the interference of surrounding objects on the wind speed measurement. The humidity data can be obtained using humidity sensors, and the humidity sensors can monitor the humidity of the environment in real time.

[0014] The operation status monitoring data of the swing execution mechanism are data regarding the working conditions of the swing execution mechanism of the bridge. The swing execution mechanism is a key device for realizing the swing of the bridge, and its operation status is directly related to the smooth progress of the swing. The operation status monitoring data of the swing execution mechanism cover information such as the rotational speed and torque of the driving motor of the execution mechanism, and the pressure and flow rate of the hydraulic system. The rotational speed of the driving motor can be measured by a rotational speed sensor, which is installed on the shaft of the motor to monitor the rotational speed of the motor in real time. The torque data can be obtained using a torque sensor, which is installed on the output shaft of the motor to measure the torque output by the motor. The pressure data of the hydraulic system can be collected by a pressure sensor, which is installed in the hydraulic pipeline to monitor the pressure change of the hydraulic system in real time. The flow rate data can be measured using a flow sensor, which is installed at the outlet of the hydraulic pump or other key positions to monitor the flow rate of the hydraulic oil.

[0015] In actual operation, in order to obtain an accurate multi-source monitoring data set, multiple monitoring points can be arranged at the bridge swing site, and corresponding sensor devices can be installed. For example, displacement sensors and strain gauges can be set at different spans and heights of the bridge to comprehensively monitor the response of the bridge structure; temperature sensors, anemometers and humidity sensors can be installed at multiple positions around the bridge to obtain accurate data on environmental impact factors; rotational speed sensors, torque sensors, pressure sensors and flow sensors can be installed at key positions of the swing execution mechanism to monitor the operation status of the execution mechanism in real time. At the same time, in order to ensure the reliability and stability of the data, the sensor devices need to be calibrated and maintained regularly to ensure their measurement accuracy.

[0016] Step S200: Perform spatio-temporal alignment and fusion processing on the multi-source monitoring data set to generate fused monitoring data.

[0017] Spatio-temporal alignment and fusion processing comprehensively considers the differences in different types of data in the multi-source monitoring data set in terms of time and space, and processes these data uniformly so that they are consistent and comparable in time and space, thereby extracting data that can comprehensively reflect the collaborative change characteristics of the bridge structure state, environmental impact and execution mechanism state. The fused monitoring data is a data set that eliminates the time and space differences and comprehensively reflects the collaborative change characteristics of the bridge structure state, environmental impact and execution mechanism state, and it can provide more comprehensive and accurate information for subsequent bridge swing attitude analysis and adjustment.

[0018] As an implementation manner, in step S200, performing spatio-temporal alignment and fusion processing on the multi-source monitoring data set to generate fused monitoring data may specifically include the following steps S210 to S240: Step S210: Perform data validity verification and processing on the bridge structure response monitoring data, the environmental impact factor monitoring data, and the rotating body actuator operation status monitoring data respectively, eliminate invalid data items, and obtain an effective monitoring data set.

[0019] Data validity verification and processing is to check and verify various types of collected monitoring data to determine whether the data meets the preset validity criteria. Invalid data items may be abnormal values or missing values in the data caused by reasons such as sensor failures and data transmission errors. For example, when a sensor is interfered by the outside world, it may output values beyond the normal range, and these values are invalid data. By performing data validity verification and processing, the quality of the data can be improved, and the impact of invalid data on subsequent analysis and processing can be avoided.

[0020] For the bridge structure response monitoring data, the validity verification may include checking whether the displacement data is within a reasonable change range, whether the strain data conforms to the mechanical properties of the material, etc. If the displacement data exceeds the maximum displacement value allowed by the bridge structure design, or the strain data differs significantly from the theoretical value calculated based on the mechanical properties of the material, then the data is considered invalid. For the environmental impact factor monitoring data, the validity verification may check whether the temperature data is within the reasonable range of the local historical temperature, whether the wind speed data conforms to the actual meteorological conditions, etc. If the temperature data shows abnormal high or low temperatures, or the wind speed data is significantly inconsistent with the actual situation of the surrounding environment, then the data may be invalid. For the rotating body actuator operation status monitoring data, the validity verification may check whether the rotation speed and torque of the drive motor are within the rated operating range of the motor, whether the pressure and flow rate of the hydraulic system meet the design requirements of the system, etc. If the rotation speed of the drive motor exceeds the rated speed, or the pressure of the hydraulic system is too high or too low, then the data is considered invalid.

[0021] In actual operation, statistical analysis methods can be used to perform data validity verification. For example, calculate statistical parameters such as the mean and standard deviation of various types of monitoring data, and determine the normal range of the data according to the statistical parameters. For data outside the normal range, it can be marked as invalid data and eliminated. At the same time, the working status and historical data of the sensor can be combined for comprehensive judgment to improve the accuracy of data validity verification.

[0022] Step S220: Perform timestamp alignment processing on the bridge structure response monitoring data, the environmental impact factor monitoring data, and the rotating body actuator operation status monitoring data in the effective monitoring data set respectively, so that the bridge structure response monitoring data, the environmental impact factor monitoring data, and the rotating body actuator operation status monitoring data have a synchronous correspondence relationship in the time dimension.

[0023] Timestamp alignment processing is to uniformly calibrate different types of monitoring data in terms of time, so that at the same time point, each type of monitoring data has a corresponding valid data value. Since different types of sensors may have different data acquisition frequencies and time bases, the data collected will have time differences. Through timestamp alignment processing, these time differences can be eliminated, providing accurate time-synchronized data for subsequent data analysis and fusion.

[0024] As an implementation manner, in step S220, timestamp alignment processing is respectively performed on the bridge structure response monitoring data, the environmental impact factor monitoring data, and the rotating body actuator operation state monitoring data in the effective monitoring data set, which may specifically include the following steps S221 to S224: Step S221: Obtain a first timestamp sequence corresponding to the bridge structure response monitoring data, a second timestamp sequence corresponding to the environmental impact factor monitoring data, and a third timestamp sequence corresponding to the rotating body actuator operation state monitoring data in the effective monitoring data set.

[0025] A timestamp sequence is a sequence that records the acquisition time of each piece of monitoring data. The first timestamp sequence corresponds to the acquisition time of the bridge structure response monitoring data, the second timestamp sequence corresponds to the acquisition time of the environmental impact factor monitoring data, and the third timestamp sequence corresponds to the acquisition time of the rotating body actuator operation state monitoring data. By obtaining these timestamp sequences, the acquisition time order and time interval of each type of monitoring data can be clarified.

[0026] In actual operation, when the sensor collects data, it will record the acquisition time of each data point at the same time. Arranging these acquisition times in the order of data acquisition gives the corresponding timestamp sequence. For example, when a displacement sensor collects the displacement data of the bridge structure, it will record the time of each acquisition, and arranging these times in sequence forms the first timestamp sequence.

[0027] Step S222: Perform time resampling processing on the first timestamp sequence, the second timestamp sequence, and the third timestamp sequence at a preset reference time interval, respectively generating a first resampled data sequence of the bridge structure response monitoring data, a second resampled data sequence of the environmental impact factor monitoring data, and a third resampled data sequence of the rotating body actuator operation state monitoring data.

[0028] Time resampling processing is to convert data with different time intervals into data with a unified time interval. The preset reference time interval is a fixed time interval determined according to the requirements of data analysis and the characteristics of each type of monitoring data. Through time resampling processing, each type of monitoring data can have the same sampling interval in terms of time, facilitating subsequent time synchronization processing.

[0029] For example, assume that the acquisition time interval of the bridge structure response monitoring data is 10 seconds, the acquisition time interval of the environmental impact factor monitoring data is 20 seconds, and the acquisition time interval of the rotating body actuator operation status monitoring data is 15 seconds. The preset reference time interval is 5 seconds. When performing time resampling processing, for the first timestamp sequence, interpolation or sampling is performed on the original timestamp sequence according to the reference time interval to generate a new timestamp sequence, and the bridge structure response monitoring data is resampled according to the new timestamp sequence to obtain the first resampled data sequence. For the second timestamp sequence and the third timestamp sequence, the same method is used for processing to generate the second resampled data sequence and the third resampled data sequence respectively.

[0030] Linear interpolation algorithm can be used for time resampling. The linear interpolation algorithm calculates the data value at the intermediate time point through linear calculation based on the values and time intervals of two adjacent data points. For example, given two adjacent displacement data points A and B, with their acquisition times being t1 and t2 respectively, and the data values being x1 and x2 respectively. If interpolation calculation is to be performed at a certain time point t between t1 and t2, according to the linear interpolation formula: x = x1 + (x2 - x1) × (t - t1) / (t2 - t1), the displacement data value x corresponding to the time point t can be obtained.

[0031] Step S223: Perform time synchronization processing on the first resampled data sequence, the second resampled data sequence, and the third resampled data sequence to ensure that at the same reference time point, there are corresponding valid data points in the first resampled data sequence, the second resampled data sequence, and the third resampled data sequence.

[0032] Time synchronization processing is to further adjust the resampled data sequences so that there are corresponding valid data for various types of monitoring data at the same reference time point. During the time resampling process, there may be situations where there are no valid data in some data sequences at certain time points, and this problem can be solved through time synchronization processing.

[0033] In actual operation, a data alignment algorithm can be used for time synchronization processing. The data alignment algorithm will compare the data situations of different resampled data sequences at each reference time point. For a sequence lacking data at a certain reference time point, interpolation or extrapolation methods can be used to supplement the data. For example, if at a certain reference time point, the first resampled data sequence has data while the second resampled data sequence has no data, linear interpolation can be performed based on the data of adjacent time points of the second resampled data sequence to obtain the approximate data at this reference time point.

[0034] Step S224: The first resampled data sequence, the second resampled data sequence and the third resampled data sequence that have completed time synchronization processing are respectively used as the bridge structure response monitoring data, the environmental impact factor monitoring data and the rotating actuator operation status monitoring data after timestamp alignment processing.

[0035] After time synchronization processing, various types of monitoring data have been aligned in time. These synchronized data sequences are used as corresponding data after timestamp alignment processing, providing a temporally consistent data basis for subsequent spatial position registration processing and data fusion operations.

[0036] Step S230: Perform spatial position registration processing on the bridge structure response monitoring data, the environmental impact factor monitoring data and the rotating actuator operation status monitoring data in the valid monitoring data set after timestamp alignment processing, so that the bridge structure response monitoring data, the environmental impact factor monitoring data and the rotating actuator operation status monitoring data have a unified spatial reference benchmark in the spatial dimension.

[0037] Spatial registration is the process of spatially calibrating different types of monitoring data so that they share a common reference. Since different types of monitoring data may be collected in different spatial reference frames, spatial discrepancies may exist. Spatial registration eliminates these discrepancies, providing accurate, spatially synchronized data for subsequent data analysis and fusion.

[0038] As an embodiment, the step S230 of performing spatial position registration processing on the bridge structure response monitoring data, the environmental impact factor monitoring data, and the rotary actuator operation status monitoring data in the valid monitoring data set after the timestamp alignment processing may specifically include the following steps S231 to S236: Step S231: establishing a unified spatial coordinate system as a registration reference coordinate system.

[0039] A unified spatial coordinate system is a defined reference framework used to describe spatial locations. The registration reference coordinate system is a standard spatial coordinate system determined based on the actual conditions of bridge rotation and the needs of data analysis. The purpose of establishing a registration reference coordinate system is to convert monitoring data from different spatial reference systems into a unified coordinate system for unified comparison and analysis of spatial locations.

[0040] For example, a Cartesian coordinate system can be established with a fixed point on the bridge as the origin and the axis direction of the bridge as the coordinate axis direction as the registration reference coordinate system. In this coordinate system, the positions of various parts of the bridge and the surrounding environment can be accurately represented by coordinate values.

[0041] Step S232: Identify the first spatial reference system corresponding to the bridge structure response monitoring data, the second spatial reference system corresponding to the environmental impact factor monitoring data, and the third spatial reference system corresponding to the running state monitoring data of the swing actuator.

[0042] The first spatial reference system, the second spatial reference system, and the third spatial reference system are the spatial reference systems used when collecting the bridge structure response monitoring data, the environmental impact factor monitoring data, and the running state monitoring data of the swing actuator, respectively. Different types of monitoring data may adopt different spatial reference systems due to different installation positions and measurement methods of the sensors.

[0043] For example, the sensors for the bridge structure response monitoring data may be installed at different parts of the bridge structure, and its spatial reference system may be established based on the local structure where the sensor is located. The sensors for the environmental impact factor monitoring data may be installed at different positions around the bridge, and its spatial reference system may be established based on the local geographical coordinates. The sensors for the running state monitoring data of the swing actuator may be installed on various components of the actuator, and its spatial reference system may be established based on the mechanical structure of the actuator.

[0044] Step S233: Calculate the spatial transformation parameters between the first spatial reference system, the second spatial reference system, and the third spatial reference system and the registration reference coordinate system, respectively.

[0045] The spatial transformation parameters are a set of parameters used to transform the data in different spatial reference systems to the registration reference coordinate system. By calculating the spatial transformation parameters, the coordinate transformation between different spatial reference systems can be achieved.

[0046] As an implementation manner, in step S233, calculating the spatial transformation parameters between the first spatial reference system, the second spatial reference system, and the third spatial reference system and the registration reference coordinate system, respectively, may specifically include the following steps S2331 to S2334: Step S2331: Obtain the set of reference coordinates of a preset number of common control points in the registration reference coordinate system.

[0047] A common control point is a point whose position can be accurately determined in both the registration reference coordinate system and each spatial reference system. The preset number of common control points is the target number of points determined according to the needs of spatial transformation calculation. The reference coordinate set is the coordinate values of these common control points in the registration reference coordinate system.

[0048] For example, select several obvious and easily recognizable points as common control points at the bridge rotation site, such as the vertexes of the bridge piers, preset marking points, etc. By measuring the coordinates of these common control points in the registration reference coordinate system, the reference coordinate set is obtained.

[0049] Step S2332: For the first spatial reference system, obtain the first source coordinate set of the common control points in the first spatial reference system, perform coordinate correspondence matching between the reference coordinate set and the first source coordinate set to generate a first coordinate pair set, calculate the first rotation matrix and the first translation vector from the first spatial reference system to the registration reference coordinate system based on the first coordinate pair set, and combine the first rotation matrix and the first translation vector into the first spatial transformation parameter.

[0050] The first source coordinate set is the coordinate values of the common control points in the first spatial reference system. By measuring the coordinates of the common control points in the first spatial reference system, the first source coordinate set is obtained. Coordinate correspondence matching is to make a one-to-one correspondence between each reference coordinate in the reference coordinate set and the source coordinate of the corresponding common control point in the first source coordinate set. The first coordinate pair set is a coordinate pair set composed of the reference coordinates and source coordinates after corresponding matching.

[0051] The first rotation matrix and the first translation vector are parameters used to describe the rotation and translation relationship from the first spatial reference system to the registration reference coordinate system. Based on the first coordinate pair set, methods such as the least squares method can be used to calculate the first rotation matrix and the first translation vector. The least squares method is a method for solving parameters by minimizing the sum of the squares of the errors. Specifically, according to the coordinate values in the first coordinate pair set, an error equation is established, and by minimizing the sum of the squares of the error equation, the optimal values of the first rotation matrix and the first translation vector are solved. Combining the first rotation matrix and the first translation vector together, the first spatial transformation parameter is obtained.

[0052] Step S2333: For the second spatial reference system, obtain the second source coordinate set of the common control points in the second spatial reference system, perform coordinate correspondence matching between the reference coordinate set and the second source coordinate set to generate a second coordinate pair set, calculate the second rotation matrix and the second translation vector from the second spatial reference system to the registration reference coordinate system based on the second coordinate pair set, and combine the second rotation matrix and the second translation vector into the second spatial transformation parameter.

[0053] The second source coordinate set is the coordinate values of the common control points in the second spatial reference system. Similar to step S2332, the second source coordinate set is obtained by measuring the coordinates of the common control points in the second spatial reference system. The reference coordinate set and the second source coordinate set are subjected to coordinate correspondence matching to generate a second coordinate pair set. Based on the second coordinate pair set, methods such as the least squares method are used to calculate a second rotation matrix and a second translation vector, and they are combined into second spatial transformation parameters.

[0054] Step S2334: For the third spatial reference system, obtain a third source coordinate set of the common control points in the third spatial reference system, perform coordinate correspondence matching on the reference coordinate set and the third source coordinate set to generate a third coordinate pair set, calculate a third rotation matrix and a third translation vector from the third spatial reference system to the registration reference coordinate system based on the third coordinate pair set, and combine the third rotation matrix and the third translation vector into third spatial transformation parameters.

[0055] The third source coordinate set is the coordinate values of the common control points in the third spatial reference system. Similarly, the third source coordinate set is obtained by measuring the coordinates of the common control points in the third spatial reference system. The reference coordinate set and the third source coordinate set are subjected to coordinate correspondence matching to generate a third coordinate pair set. Based on the third coordinate pair set, methods such as the least squares method are used to calculate a third rotation matrix and a third translation vector, and they are combined into third spatial transformation parameters.

[0056] Step S234: Based on the spatial transformation parameters, convert the bridge structure response monitoring data after timestamp alignment processing from the first spatial reference system to the registration reference coordinate system to obtain first registered monitoring data.

[0057] According to the first spatial transformation parameters, the coordinates of each data point in the bridge structure response monitoring data after timestamp alignment processing are converted from the first spatial reference system to the registration reference coordinate system. Specifically, for the coordinates of each data point in the bridge structure response monitoring data, first multiply it by the first rotation matrix and then add the first translation vector to obtain the new coordinates of the data point in the registration reference coordinate system. After converting the coordinates of all data points, first registered monitoring data is obtained.

[0058] Step S235: Based on the spatial transformation parameters, convert the environmental impact factor monitoring data after timestamp alignment processing from the second spatial reference system to the registration reference coordinate system to obtain second registered monitoring data.

[0059] According to a method similar to step S234, based on the second space conversion parameter, the environmental impact factor monitoring data after timestamp alignment processing is converted from the second space reference system to the registration reference coordinate system to obtain the second registered monitoring data.

[0060] Step S236: Based on the space conversion parameter, the running state monitoring data of the slewing actuator after timestamp alignment processing is converted from the third space reference system to the registration reference coordinate system to obtain the third registered monitoring data; the first registered monitoring data, the second registered monitoring data, and the third registered monitoring data together constitute the bridge structure response monitoring data, the environmental impact factor monitoring data, and the running state monitoring data of the slewing actuator after spatial position registration processing.

[0061] Similarly, according to the third space conversion parameter, the running state monitoring data of the slewing actuator after timestamp alignment processing is converted from the third space reference system to the registration reference coordinate system to obtain the third registered monitoring data. The first registered monitoring data, the second registered monitoring data, and the third registered monitoring data are all unified in the registration reference coordinate system in space, and they together constitute various types of monitoring data after spatial position registration processing.

[0062] Step S240: On the basis of completing timestamp alignment processing and spatial position registration processing, the bridge structure response monitoring data, the environmental impact factor monitoring data, and the running state monitoring data of the slewing actuator are input into a preset data fusion model, and the data fusion model performs feature-level fusion operations on the input various types of monitoring data to output the fused monitoring data; the fused monitoring data is a data set that eliminates time and space differences and comprehensively reflects the collaborative change characteristics of the bridge structure state, environmental impact, and actuator state.

[0063] The data fusion model is a model used to fuse different types of monitoring data. The feature-level fusion operation is to extract and fuse the features of the input various types of monitoring data to obtain a fused feature that comprehensively reflects the information of various types of data. By performing feature-level fusion operations through the data fusion model, different types of monitoring data can be organically combined, time and space differences can be eliminated, and a data set that can comprehensively and accurately reflect the collaborative change characteristics of the bridge structure state, environmental impact, and actuator state can be obtained.

[0064] As an implementation manner, the data fusion model is a feature fusion network based on an attention mechanism; based on this, in step S240, by performing feature-level fusion operations on the input various types of monitoring data through the data fusion model to output the fused monitoring data, it may specifically include the following steps S241~S246: Step S241: Input the bridge structure response monitoring data, the environmental impact factor monitoring data, and the operating status monitoring data of the slewing actuator, which have been processed by spatial position registration, into different feature extraction branches of the feature fusion network based on the attention mechanism respectively.

[0065] The feature fusion network based on the attention mechanism is a neural network model that uses the attention mechanism for feature fusion. This network contains multiple feature extraction branches, and each feature extraction branch is used to extract the features of the corresponding type of monitoring data. The various types of monitoring data after spatial position registration processing are respectively input into different feature extraction branches to perform independent feature extraction on various types of data.

[0066] For example, the feature fusion network based on the attention mechanism can adopt a convolutional neural network (CNN) as the basic structure of the feature extraction branch. For the bridge structure response monitoring data, it is input into a dedicated CNN feature extraction branch, which extracts the deep features of the bridge structure response monitoring data through operations such as convolutional layers and pooling layers. For the environmental impact factor monitoring data and the operating status monitoring data of the slewing actuator, they are respectively input into two other different CNN feature extraction branches for corresponding feature extraction.

[0067] Step S242: Extract the deep feature expressions of the corresponding type of monitoring data through each feature extraction branch respectively.

[0068] The deep feature expression is an advanced feature that can reflect the essential features of the corresponding type of monitoring data. Each feature extraction branch processes the input monitoring data through a series of neural network layers and gradually extracts the deep features of the data. Taking the CNN feature extraction branch as an example, the convolutional layer performs a convolutional operation on the input data through a convolutional kernel to extract the local features of the data. The pooling layer downsamples the feature map output by the convolutional layer, reduces the size of the feature map, and at the same time retains important feature information. Through the combination of multiple convolutional layers and pooling layers, the deep feature expression of the data is gradually extracted.

[0069] Step S243: Input the deep feature expressions extracted by each feature extraction branch into the attention allocation module.

[0070] The attention allocation module is an important module in the feature fusion network based on the attention mechanism and is used to allocate attention to the deep feature expressions of different types of monitoring data. The deep feature expressions extracted by each feature extraction branch are input into the attention allocation module to perform weighted processing according to the importance of different features.

[0071] Step S244: In the attention allocation module, according to the internal correlation between the state of the current bridge rotation stage and the deep feature representations of the various types of monitoring data, calculate the attention weight coefficients to be allocated to the deep feature representation of the bridge structure response monitoring data, the deep feature representation of the environmental impact factor monitoring data, and the deep feature representation of the running state monitoring data of the rotation execution mechanism respectively.

[0072] The attention weight coefficient is a coefficient used to measure the importance of the deep feature representations of different types of monitoring data in the fusion process. In the attention allocation module, according to the internal correlation between the state of the current bridge rotation stage and the deep feature representations of the various types of monitoring data, the attention mechanism algorithm is used to calculate the attention weight coefficients to be allocated to each deep feature representation. The attention mechanism algorithm can calculate the attention weight coefficients according to factors such as the similarity and correlation between features. For example, the dot product attention mechanism can be adopted. By calculating the dot product between the deep feature representations, the similarity between them is obtained, and then the attention weight coefficients are calculated according to the similarity.

[0073] Step S245: Based on the calculated attention weight coefficients, perform weighted fusion processing on the deep feature representation of the bridge structure response monitoring data, the deep feature representation of the environmental impact factor monitoring data, and the deep feature representation of the running state monitoring data of the rotation execution mechanism.

[0074] Weighted fusion processing is to perform weighted summation on the deep feature representations of various types of monitoring data according to the calculated attention weight coefficients. Through weighted fusion processing, the role of important features can be highlighted, and at the same time, the influence of unimportant features can be weakened, so as to obtain a more comprehensive and accurate feature representation.

[0075] For example, assume that the deep feature representation of the bridge structure response monitoring data is F1, the deep feature representation of the environmental impact factor monitoring data is F2, and the deep feature representation of the running state monitoring data of the rotation execution mechanism is F3, and their corresponding attention weight coefficients are w1, w2, and w3 respectively. Then the weighted fused feature representation F = w1×F1 + w2×F2 + w3×F3.

[0076] Step S246: Perform feature dimensionality reduction and integration operations on the weighted fused feature representation to generate the fused monitoring data; the fused monitoring data is a unified feature vector sequence that synthesizes structural response, environmental impact, and mechanism state information.

[0077] The feature dimension reduction and integration operation further processes the feature representation after weighted fusion, reduces the dimension of the features, and at the same time integrates different features to generate a unified sequence of feature vectors. Feature dimension reduction can adopt methods such as principal component analysis (PCA). Principal component analysis is a method of converting high-dimensional data into low-dimensional data through linear transformation. Specifically, by calculating the covariance matrix of the feature representation after weighted fusion, then solving the eigenvalues and eigenvectors of the covariance matrix, selecting the first few eigenvectors with larger eigenvalues as the principal components, and projecting the original feature representation onto these principal components to obtain the feature representation after dimension reduction.

[0078] Integrate the feature representation after dimension reduction to generate a unified sequence of feature vectors, and this sequence of feature vectors is the fused monitoring data. The fused monitoring data eliminates the time and space differences and comprehensively reflects the co-variation characteristics of the bridge structure state, environmental impact, and actuator state.

[0079] Step S300: Based on the fused monitoring data and a preset set of target attitude parameters, identify the attitude deviation characteristics between the bridge rotation attitude and the target attitude.

[0080] The set of target attitude parameters is the ideal attitude parameters of the bridge rotation preset in advance. The attitude deviation characteristics are the characteristics that describe the difference between the actual attitude of the bridge rotation and the target attitude. By comparing the fused monitoring data and the set of target attitude parameters, the attitude deviation characteristics between the bridge rotation attitude and the target attitude can be identified, providing a basis for subsequent attitude adjustment.

[0081] As an implementation, in step S300, based on the fused monitoring data and a preset set of target attitude parameters, to identify the attitude deviation characteristics between the bridge rotation attitude and the target attitude, it may specifically include the following steps S310 to S360: Step S310: Extract the current attitude feature set representing the current spatial position and attitude of the bridge from the fused monitoring data; the current attitude feature set at least includes the three-dimensional coordinate offset of the key control points of the bridge, the overall torsion angle of the bridge, and the deformation degree of the target section of the bridge.

[0082] The current attitude feature set is a set of features used to describe the current spatial position and attitude of the bridge. The three-dimensional coordinate offset of the key control points of the bridge refers to the difference between the actual three-dimensional coordinates of the key control points of the bridge and the initial three-dimensional coordinates, which reflects the change in the spatial position of the bridge. The overall torsion angle of the bridge refers to the torsion angle of the bridge relative to the initial state, which reflects the torsional deformation of the bridge. The deformation degree of the target section of the bridge refers to the deformation degree of the target section of the bridge during the rotation process, such as the change in cross-sectional area, shape change, etc., which reflects the deformation of the local structure of the bridge.

[0083] The current attitude feature set can be extracted from the fused monitoring data using a feature extraction algorithm. For example, for the three-dimensional coordinate offset of the key control points of the bridge, the difference between its three-dimensional coordinates and the initial three-dimensional coordinates can be calculated based on the three-dimensional coordinate information of the key control points of the bridge in the fused monitoring data. For the overall torsion angle of the bridge, the overall torsion angle of the bridge can be calculated by analyzing the relative displacement relationship of different parts of the bridge in the fused monitoring data and using geometric calculation methods. For the deformation degree of the target cross-section of the bridge, the area change rate, shape change parameters, etc. of the cross-section can be calculated based on the geometric information of the target cross-section in the fused monitoring data to obtain the deformation degree.

[0084] Step S320: Obtain the target attitude feature set corresponding to the current attitude feature set from the preset target attitude parameter set; the target attitude feature set at least includes the target three-dimensional coordinate offset of the key control points of the bridge, the overall target torsion angle of the bridge, and the target deformation degree of the target cross-section of the bridge.

[0085] The target attitude feature set is an ideal attitude feature that is preset and corresponding to the current attitude feature set. The target three-dimensional coordinate offset of the key control points of the bridge is the difference between the three-dimensional coordinates of the key control points of the bridge in the target attitude and the initial three-dimensional coordinates. The overall target torsion angle of the bridge is the overall torsion angle of the bridge in the target attitude. The target deformation degree of the target cross-section of the bridge is the deformation degree of the target cross-section of the bridge in the target attitude.

[0086] Obtaining the target attitude feature set from the preset target attitude parameter set is to extract the corresponding target feature values from the target attitude parameter set according to the feature types of the current attitude feature set. For example, if the current attitude feature set contains the three-dimensional coordinate offset of the key control points of the bridge, then the corresponding target three-dimensional coordinate offset of the key control points of the bridge is found from the target attitude parameter set.

[0087] Step S330: Compare and process the difference between the three-dimensional coordinate offset of the key control points of the bridge in the current attitude feature set and the target three-dimensional coordinate offset of the key control points of the bridge in the target attitude feature set to generate a position deviation feature.

[0088] The difference comparison process is to compare the three-dimensional coordinate offset of the key control points of the bridge in the current attitude feature set with the corresponding target three-dimensional coordinate offset in the target attitude feature set and calculate the difference between them. The position deviation feature is a feature that reflects the deviation of the key control points of the bridge from the target position in the spatial position.

[0089] For example, assume that the three-dimensional coordinate offset of the key control points of the bridge in the current pose feature set is (x1, y1, z1), and the target three-dimensional coordinate offset of the corresponding key control points of the bridge in the target pose feature set is (x2, y2, z2). Then the position deviation feature is (x1 - x2, y1 - y2, z1 - z2).

[0090] Step S340: Compare the overall torsion angle of the bridge in the current pose feature set with the overall target torsion angle of the bridge in the target pose feature set to generate a torsion deviation feature through differential comparison processing.

[0091] Similarly, compare the overall torsion angle of the bridge in the current pose feature set with the overall target torsion angle of the bridge in the target pose feature set, calculate the difference between them, and obtain the torsion deviation feature. The torsion deviation feature reflects the deviation between the overall torsion angle of the bridge and the target torsion angle.

[0092] For example, assume that the overall torsion angle of the bridge in the current pose feature set is θ1, and the overall target torsion angle of the bridge in the target pose feature set is θ2. Then the torsion deviation feature is θ1 - θ2.

[0093] Step S350: Compare the deformation degree of the target cross-section of the bridge in the current pose feature set with the target deformation degree of the target cross-section of the bridge in the target pose feature set to generate a deformation deviation feature through differential comparison processing.

[0094] Compare the deformation degree of the target cross-section of the bridge in the current pose feature set with the target deformation degree of the target cross-section of the bridge in the target pose feature set, calculate the difference between them, and obtain the deformation deviation feature. The deformation deviation feature reflects the deviation between the deformation degree of the target cross-section of the bridge and the target deformation degree.

[0095] For example, assume that the deformation degree of the target cross-section of the bridge in the current pose feature set is d1, and the target deformation degree of the target cross-section of the bridge in the target pose feature set is d2. Then the deformation deviation feature is d1 - d2.

[0096] Step S360: Integrate the position deviation feature, the torsion deviation feature, and the deformation deviation feature to form the pose deviation feature; the pose deviation feature is used to quantitatively describe the comprehensive deviation degree of the bridge rotation pose from the target pose in terms of spatial position, overall torsion, and local deformation.

[0097] The fusion of the position deviation feature, the torsion deviation feature, and the deformation deviation feature can adopt the method of weighted summation. For example, let the position deviation feature be P, the torsion deviation feature be T, and the deformation deviation feature be D, and their corresponding weight coefficients be wP, wT, and wD respectively. Then the attitude deviation feature A = wP×P + wT×T + wD×D.

[0098] By comprehensively considering the deviation conditions of the bridge in terms of spatial position, overall torsion, and local deformation, the attitude deviation feature can accurately quantify and describe the comprehensive deviation degree between the bridge rotation attitude and the target attitude, providing an important basis for subsequent attitude adjustment.

[0099] Step S400: Generate an attitude adjustment strategy for the bridge rotation actuator according to the attitude deviation feature.

[0100] The attitude adjustment strategy is a set of instruction sets for adjusting the bridge rotation attitude. It determines the specific actions of the bridge rotation actuator according to the attitude deviation feature to reduce the deviation between the bridge rotation attitude and the target attitude.

[0101] As an implementation manner, in step S400, generating an attitude adjustment strategy for the bridge rotation actuator according to the attitude deviation feature may specifically include the following steps S410 to S440: Step S410: Input the attitude deviation feature into a preset attitude adjustment strategy generation model, and through the attitude adjustment strategy generation model, analyze the deviation degree and change trend of each of the position deviation feature, the torsion deviation feature, and the deformation deviation feature in the attitude deviation feature.

[0102] The attitude adjustment strategy generation model is a model for generating an attitude adjustment strategy according to the attitude deviation feature. By inputting the attitude deviation feature into the attitude adjustment strategy generation model, the model can analyze and process the attitude deviation feature, and analyze the deviation degree and change trend of each of the position deviation feature, the torsion deviation feature, and the deformation deviation feature.

[0103] The attitude adjustment strategy generation model can adopt a decision-making model combining rules and learning. This model can make decisions through preset rules and learning of historical data. When analyzing the attitude deviation feature, the model can evaluate the position deviation feature, the torsion deviation feature, and the deformation deviation feature according to the preset rules, judge whether their deviation degrees are large or small, and whether their change trends are gradually increasing or gradually decreasing. For example, for the position deviation feature, if its value exceeds the preset threshold, it is considered that the deviation degree is large; if its value continuously increases within a period of time, it is considered that the change trend is gradually increasing.

[0104] Step S420: Based on the attitude adjustment strategy generation model, generate the mechanical constraint rules of the bridge structure and the operation constraint rules of the rotation execution mechanism built into the model, and evaluate the effect prediction of different combinations of adjustment actions on eliminating the position deviation feature, the torsion deviation feature, and the deformation deviation feature.

[0105] The mechanical constraint rules of the bridge structure are the rules regarding the mechanical properties and safety requirements of the bridge structure. The operation constraint rules of the rotation execution mechanism are the rules regarding the operation ability and safety limitations of the rotation execution mechanism. Different combinations of adjustment actions refer to different ways of combining actions for different driving units of the bridge rotation execution mechanism. The effect prediction is to estimate the effects of different combinations of adjustment actions on eliminating the position deviation feature, the torsion deviation feature, and the deformation deviation feature.

[0106] As an implementation, the attitude adjustment strategy generation model is a decision-making model based on the combination of rules and learning; in the attitude adjustment strategy generation model, multiple candidate combinations of adjustment actions are preset. Based on this, in step S420, based on the mechanical constraint rules of the bridge structure and the operation constraint rules of the rotation execution mechanism built into the attitude adjustment strategy generation model, evaluate the effect prediction of different combinations of adjustment actions on eliminating the position deviation feature, the torsion deviation feature, and the deformation deviation feature, which may specifically include the following steps S421 to S424: Step S421: For each candidate combination of adjustment actions, according to the current values of the position deviation feature, the torsion deviation feature, and the deformation deviation feature in the attitude deviation feature, and in combination with the mechanical constraint rules of the bridge structure, predict the distribution of the stress change of the bridge structure and the potential risk areas caused by executing this candidate combination of adjustment actions.

[0107] The distribution of the stress change of the bridge structure refers to the change in the magnitude and distribution of the internal stress of the bridge structure after executing the candidate combination of adjustment actions. The potential risk areas refer to the areas where potential safety hazards may occur in the bridge structure after executing the candidate combination of adjustment actions.

[0108] According to the current values of the position deviation feature, the torsion deviation feature, and the deformation deviation feature in the attitude deviation feature, and in combination with the mechanical constraint rules of the bridge structure, the finite element analysis method can be used to predict the distribution of the stress change of the bridge structure and the potential risk areas. The finite element analysis method is a method that discretizes the bridge structure into multiple finite elements, establishes the mechanical equations of the elements, and then obtains the stress distribution and deformation conditions of the bridge structure by solving these equations. Specifically, according to the current attitude deviation feature and the candidate combination of adjustment actions, determine the force condition of the bridge structure, and then use finite element software to perform a mechanical analysis on the bridge structure to obtain the distribution of the stress change of the bridge structure and the potential risk areas.

[0109] Step S422: Based on the current values of the position deviation feature, torsion deviation feature, and deformation deviation feature in the attitude deviation feature, and in combination with the operating constraint rules of the slewing actuator, predict the required output power, operating speed, and duration of each drive unit when performing the candidate adjustment action combination, and evaluate whether they exceed the safe operating threshold of the actuator.

[0110] The required output power, operating speed, and duration of each drive unit refer to the magnitude of the power to be output, the operating speed, and the operating duration of each drive unit of the slewing actuator when performing the candidate adjustment action combination. The safe operating threshold of the actuator refers to the maximum output power, maximum operating speed, and maximum duration that each drive unit can withstand under the premise of safe operation of the slewing actuator.

[0111] Based on the current values of the position deviation feature, torsion deviation feature, and deformation deviation feature in the attitude deviation feature, and in combination with the operating constraint rules of the slewing actuator, a dynamic analysis method can be used to predict the required output power, operating speed, and duration of each drive unit. The dynamic analysis method is a method of establishing a dynamic model of the slewing actuator, analyzing its motion and force conditions under different working conditions, and thus predicting the operating parameters of each drive unit. Specifically, based on the current attitude deviation feature and the candidate adjustment action combination, determine the motion state and force conditions of the slewing actuator, and then use dynamic software to analyze the slewing actuator to obtain the required output power, operating speed, and duration of each drive unit. Compare these predicted values with the safe operating threshold of the actuator to evaluate whether they exceed the safe operating threshold.

[0112] Step S423: Based on the predicted distribution of bridge structure stress changes, the evaluation results of potential risk areas, and the evaluation results of the output power, operating speed, and duration of each drive unit, calculate the comprehensive effect score of the candidate adjustment action combination for reducing the position deviation feature, the torsion deviation feature, and the deformation deviation feature.

[0113] The comprehensive effect score is a score value used to measure the effect of the candidate adjustment action combination on reducing the attitude deviation feature. Based on the predicted distribution of bridge structure stress changes, the evaluation results of potential risk areas, and the evaluation results of the output power, operating speed, and duration of each drive unit, a comprehensive evaluation index system can be used to calculate the comprehensive effect score.

[0114] The comprehensive evaluation index system can include multiple evaluation indexes, such as the degree of change in bridge structure stress, the size of potential risk areas, the rationality of the output power of the driving unit, the stability of the operating speed, etc. Set corresponding weight coefficients for each evaluation index, then calculate the scores of each evaluation index according to the prediction results, and finally perform weighted summation on the scores of each evaluation index according to the weight coefficients to obtain the comprehensive effect score. For example, let the weight coefficient of the degree of change in bridge structure stress be w1, the weight coefficient of the size of potential risk areas be w2, the weight coefficient of the rationality of the output power of the driving unit be w3, and the weight coefficient of the stability of the operating speed be w4. The score of the degree of change in bridge structure stress is S1, the score of the size of potential risk areas is S2, the score of the rationality of the output power of the driving unit is S3, and the score of the stability of the operating speed is S4. Then the comprehensive effect score S = w1×S1 + w2×S2 + w3×S3 + w4×S4.

[0115] Step S424: Based on the historical adjustment effect feedback data learned by the attitude adjustment strategy generation model, correct the comprehensive effect score; the generated promotion optimally collaborates to reduce the adjustment instruction combination of the position deviation feature, the torsion deviation feature, and the deformation deviation feature, and is to select the candidate adjustment action combination with the highest corrected comprehensive effect score.

[0116] The historical adjustment effect feedback data is the adjustment effect data accumulated by the attitude adjustment strategy generation model during past adjustments. By learning the historical adjustment effect feedback data, the model can understand the effects of different adjustment action combinations in actual applications, so as to correct the comprehensive effect score.

[0117] Machine learning algorithms, such as neural network algorithms, can be used to correct the comprehensive effect score. Use the historical adjustment effect feedback data as training data to train a neural network model. Take the predicted comprehensive effect score as the input, and correct it through the trained neural network model to obtain the corrected comprehensive effect score.

[0118] Select the candidate adjustment action combination with the highest corrected comprehensive effect score as the adjustment instruction combination that promotes optimal collaboration to reduce the position deviation feature, the torsion deviation feature, and the deformation deviation feature. This can ensure that the selected adjustment action combination has the best effect in reducing the attitude deviation feature.

[0119] Step S430: According to the effect prediction, on the premise of satisfying the bridge structure mechanical constraint rules and the rotating body actuator operation constraint rules, generate an adjustment instruction combination that promotes optimal collaboration to reduce the position deviation feature, the torsion deviation feature, and the deformation deviation feature.

[0120] According to the results of the effect prediction, on the premise of ensuring compliance with the mechanical constraint rules of the bridge structure and the operation constraint rules of the rotation execution mechanism, select the adjustment action combination with the best effect from multiple candidate adjustment action combinations as the adjustment instruction combination. The adjustment instruction combination specifies the specific actions that each drive unit of the rotation execution mechanism needs to perform to jointly reduce the position deviation feature, torsion deviation feature, and deformation deviation feature.

[0121] Step S440: Package the adjustment instruction combination as the attitude adjustment strategy; the attitude adjustment strategy includes an instruction set for the action type, action direction, action amplitude, and action timing of different drive units in the rotation execution mechanism.

[0122] Package the adjustment instruction combination to form a complete attitude adjustment strategy. The attitude adjustment strategy includes detailed instructions for different drive units in the rotation execution mechanism, including action type (such as rotation, translation, etc.), action direction (such as clockwise, counterclockwise, etc.), action amplitude (such as rotation angle, translation distance, etc.), and action timing (such as the sequence and duration of actions). By packaging the adjustment instruction combination as the attitude adjustment strategy, it is convenient to transfer the instructions to the rotation execution mechanism to achieve the adjustment of the bridge rotation attitude.

[0123] Step S500: Execute the attitude adjustment strategy to perform real-time attitude adjustment operations during the bridge rotation process.

[0124] The real-time attitude adjustment operation is to perform real-time control on the bridge rotation execution mechanism according to the instructions of the attitude adjustment strategy to adjust the rotation attitude of the bridge so that it gradually approaches the target attitude.

[0125] As an implementation method, in step S500, execute the attitude adjustment strategy to perform real-time attitude adjustment operations during the bridge rotation process, which may specifically include the following steps S510 to S550: Step S510: Parse the adjustment instruction set in the attitude adjustment strategy into a control instruction sequence recognizable by the rotation execution mechanism.

[0126] The adjustment instruction set is the instruction set for the rotation execution mechanism included in the attitude adjustment strategy. The control instruction sequence recognizable by the rotation execution mechanism is the instruction sequence that the rotation execution mechanism can understand and execute after converting the format of the adjustment instruction set.

[0127] The parsing and adjustment instruction set can adopt an instruction parsing algorithm. According to the communication protocol and control requirements of the slewing actuator, the instruction information in the adjustment instruction set is format-converted to generate a control instruction sequence recognizable by the slewing actuator. For example, if a certain communication protocol is adopted by the slewing actuator, then the instruction information in the adjustment instruction set needs to be encoded according to the format of this communication protocol to generate a control instruction sequence.

[0128] Step S520: Send the control instruction sequence to multiple drive controllers corresponding to the slewing actuator.

[0129] The multiple drive controllers corresponding to the slewing actuator are devices responsible for controlling each drive unit of the slewing actuator. The control instruction sequence is sent to the drive controller so that the drive controller can control the operation of the drive unit according to the instruction sequence.

[0130] The control instruction sequence can be sent to the drive controller through a communication interface. The communication interface can adopt a wired communication interface (such as a serial port, an Ethernet interface, etc.) or a wireless communication interface (such as Bluetooth, WiFi, etc.). Which communication interface to choose specifically depends on the actual situation and communication requirements of the slewing actuator.

[0131] Step S530: Through the multiple drive controllers, respectively control the corresponding drive units to execute the action type, action direction, action amplitude, and action timing specified by the control instruction sequence.

[0132] The multiple drive controllers respectively control the corresponding drive units to execute corresponding actions according to the received control instruction sequence. The drive unit operates according to the action type, action direction, action amplitude, and action timing in the control instruction sequence, so as to realize the adjustment of the slewing attitude of the bridge.

[0133] For example, if the control instruction sequence specifies that a certain drive unit needs to perform a rotation action, the rotation direction is clockwise, the rotation angle is 30 degrees, and the rotation duration is 10 seconds. Then the drive controller will control the drive unit to perform a rotation action according to this instruction in the specified direction, amplitude, and timing.

[0134] Step S540: During the process of the drive unit executing the action, continuously obtain the multi-source monitoring data set, and loop to execute the steps of performing spatio-temporal alignment and fusion processing on the multi-source monitoring data set to generate fused monitoring data, the step of identifying the attitude deviation characteristics between the slewing attitude of the bridge and the target attitude based on the fused monitoring data and the preset target attitude parameter set, the step of generating an attitude adjustment strategy for the slewing actuator of the bridge according to the attitude deviation characteristics, and the step of executing the attitude adjustment strategy to perform real-time attitude adjustment operations on the slewing process of the bridge.

[0135] During the operation of the driving unit, continuously obtaining the multi-source monitoring data set can provide real-time understanding of the actual situation of the bridge rotation. By repeatedly executing the subsequent steps, the attitude of the bridge rotation can be continuously evaluated and adjusted, forming a closed-loop control process to ensure that the attitude of the bridge rotation gradually approaches the target attitude.

[0136] For example, while the driving unit is operating, continuously collect the monitoring data of the bridge structure response, the monitoring data of environmental impact factors, and the monitoring data of the operating status of the rotation execution mechanism through sensors. Then, perform spatio-temporal alignment and fusion processing on these data to generate fused monitoring data. Based on the fused monitoring data and the preset target attitude parameter set, identify the attitude deviation characteristics. According to the attitude deviation characteristics, generate a new attitude adjustment strategy. Finally, execute the new attitude adjustment strategy to further adjust the attitude of the bridge rotation.

[0137] Step S550: When the identified attitude deviation characteristics meet the preset attitude adjustment completion condition, terminate the execution of the attitude adjustment strategy.

[0138] The attitude adjustment completion condition is a pre-set judgment criterion used to determine whether the attitude of the bridge rotation has been adjusted to be close to the target attitude. When the identified attitude deviation characteristics meet the attitude adjustment completion condition, it indicates that the attitude of the bridge rotation has achieved the expected effect, and at this time, the execution of the attitude adjustment strategy can be terminated.

[0139] As an implementation, in step S550, when the identified attitude deviation characteristics meet the preset attitude adjustment completion condition and terminate the execution of the attitude adjustment strategy, it may specifically include the following steps S551 to S555: Step S551: After each identification of the attitude deviation characteristics, calculate the magnitudes of the position deviation characteristics, the torsion deviation characteristics, and the deformation deviation characteristics in the attitude deviation characteristics.

[0140] The magnitudes of the position deviation characteristics, the torsion deviation characteristics, and the deformation deviation characteristics are values used to measure their sizes. The magnitude can be calculated using the Euclidean distance formula. For example, for the position deviation characteristic P = (Px, Py, Pz), its magnitude |P| = √(Px² + Py² + Pz²). For the torsion deviation characteristic T and the deformation deviation characteristic D, their magnitudes are calculated in a similar way. By calculating the magnitudes, the sizes of the position deviation characteristics, the torsion deviation characteristics, and the deformation deviation characteristics can be quantified, facilitating subsequent judgment and comparison.

[0141] Step S552: Determine whether the magnitude is less than the preset attitude deviation tolerance threshold.

[0142] The preset attitude deviation tolerance threshold is a preset value used to measure the acceptable range of attitude deviation characteristics. If the magnitudes of the position deviation characteristic, the torsion deviation characteristic, and the deformation deviation characteristic are all less than the attitude deviation tolerance threshold, it indicates that the current attitude deviation is within the acceptable range. The setting of the attitude deviation tolerance threshold needs to comprehensively consider factors such as the design requirements of the bridge, the precision requirements of the rotation, and the experience of the actual project. For example, according to the design standard of the bridge, the magnitude tolerance threshold of the position deviation characteristic is specified as 5 mm, the magnitude tolerance threshold of the torsion deviation characteristic is 0.5°, and the magnitude tolerance threshold of the deformation deviation characteristic is 2%. After calculating the magnitudes of the position deviation characteristic, the torsion deviation characteristic, and the deformation deviation characteristic, they are respectively compared with the corresponding tolerance thresholds.

[0143] Step S553: If the magnitude is less than the attitude deviation tolerance threshold, determine whether the change trend of the magnitude tends to be stable and less than the attitude deviation tolerance threshold in a continuous preset number of control processes.

[0144] Even if the magnitude of the current attitude deviation characteristic is less than the attitude deviation tolerance threshold, it cannot be immediately considered that the attitude adjustment has been completed. It is also necessary to determine whether the change trend of the magnitude tends to be stable in a continuous preset number of control processes. The preset number is a fixed number determined according to the actual situation, such as 5 times or 10 times. If in a continuous preset number of control processes, the magnitudes of the position deviation characteristic, the torsion deviation characteristic, and the deformation deviation characteristic all remain below the attitude deviation tolerance threshold and their change amplitudes are very small, it indicates that the attitude deviation has tended to be stable and there are no obvious fluctuations.

[0145] The statistical analysis method can be used to determine whether the change trend of the magnitude tends to be stable. For example, calculate the average value and standard deviation of the magnitude in a continuous preset number of control processes. If the standard deviation is very small, it indicates that the fluctuation of the magnitude is small and the change trend tends to be stable. At the same time, check whether the magnitude in each control process is less than the attitude deviation tolerance threshold. If these two conditions are met, it is considered that the change trend of the magnitude tends to be stable and less than the attitude deviation tolerance threshold.

[0146] Step S554: If the magnitude is less than the attitude deviation tolerance threshold and the change trend of the magnitude tends to be stable and less than the attitude deviation tolerance threshold in a continuous preset number of control processes, confirm that the attitude deviation characteristic meets the attitude adjustment completion condition.

[0147] When the magnitudes of the position deviation feature, the torsion deviation feature, and the deformation deviation feature are all less than the attitude deviation tolerance threshold, and the change trend of the magnitude is stable and less than the attitude deviation tolerance threshold in a continuous preset number of control processes, it indicates that the bridge rotation attitude has achieved the expected effect, and the attitude deviation feature meets the attitude adjustment completion condition. At this time, it can be considered that the bridge rotation attitude has been adjusted to a state close to the target attitude.

[0148] Step S555: In response to confirming that the attitude adjustment completion condition is met, send a stop instruction to the multiple drive controllers, terminate the execution of the current attitude adjustment strategy, and maintain the current state of the rotation execution mechanism until a new rotation control instruction is received.

[0149] Once it is confirmed that the attitude deviation feature meets the attitude adjustment completion condition, it is necessary to terminate the current attitude adjustment strategy in a timely manner. Send a stop instruction to the multiple drive controllers, causing the drive controllers to stop controlling the operation of the drive units, thereby terminating the execution of the attitude adjustment strategy. At the same time, maintain the current state of the rotation execution mechanism to ensure the stability of the bridge rotation attitude. Until a new rotation control instruction is received, further adjust or operate the bridge rotation attitude according to the new instruction.

[0150] During the implementation process of the entire intelligent adjustment method for bridge rotation attitude based on multi-source data fusion, each step is interrelated and interacts synergistically. By obtaining the multi-source monitoring data set, various information during the bridge rotation process can be comprehensively and accurately understood. Through spatio-temporal alignment and fusion processing of the multi-source monitoring data, the time and space differences are eliminated, and the fusion monitoring data that comprehensively reflects the collaborative change characteristics of the bridge structure state, environmental impact, and actuator state is obtained. Based on the fusion monitoring data and the target attitude parameter set, the attitude deviation feature is identified, providing a clear target for attitude adjustment. Generate an attitude adjustment strategy according to the attitude deviation feature and execute this strategy for real-time attitude adjustment operations, forming a closed-loop control process that continuously optimizes and adjusts the bridge rotation attitude. Finally, when the attitude deviation feature meets the attitude adjustment completion condition, terminate the execution of the attitude adjustment strategy to ensure that the bridge rotation attitude achieves the expected effect.

[0151] It can be understood that in the above introductions of the embodiments of the present invention, various algorithms involved, such as the attention mechanism algorithm, the feature extraction algorithm, etc., can be obtained from relevant content in the prior art. To save space, they will not be elaborated in the embodiments of the present invention. In addition, those skilled in the art can make detailed supplements according to the common general knowledge in the art. For example, according to the general knowledge in the art, normalization can be used to eliminate the dimension conflict before feature fusion, interpolation can be used to eliminate the dimension difference, historical data, experience or business scenario requirements can be combined to reasonably set the threshold, the model can be trained based on the general model training method, the number of layers in the model structure can be set based on actual needs, the activation function can be selected, etc. The present invention will no longer give redundant introductions to the overly detailed implementation process here.

[0152] Please refer to Figure 2 , Figure 2 which is a schematic structural diagram of a bridge rotation attitude intelligent adjustment system based on multi-source data fusion provided by an embodiment of the present invention. This system is a computer system for implementing the bridge rotation attitude intelligent adjustment method based on multi-source data fusion. This computer system at least includes a processor 101, a communication interface 102, and a memory 103. Among them, the processor 101, the communication interface 102, and the memory 103 can be connected through a bus or other means. Among them, the processor 101 (or the Central Processing Unit (CPU)) is the computing core and control core of the computer system, which can parse various instructions in the computer system and process various data in the computer system. The communication interface 102 can optionally include a standard wired interface, a wireless interface (such as WI-FI, a mobile communication interface, etc.), and can be controlled by the processor 101 to be used for sending and receiving data; the communication interface 102 can also be used for the transmission and interaction of internal data in the computer system. The memory 103 (Memory) is the memory device in the computer system, used to store programs and data. It can be understood that the memory 103 here can include both the built-in memory of the computer system and, of course, the extended memory supported by the computer system. The memory 103 provides a storage space, and this storage space stores the operating system of the computer system, which can include but is not limited to: Android system, iOS system, Windows Phone system, etc. The present invention does not make any limitations in this regard.

[0153] In one embodiment, the processor 101 executes the bridge rotation attitude intelligent adjustment method based on multi-source data fusion provided above in the embodiments of the present invention by running the computer program in the memory 103.

Claims

1. An intelligent adjustment method for the rotation posture of a bridge based on multi-source data fusion, characterized in that include: Acquire a multi-source monitoring data set generated during the bridge rotation process, wherein the multi-source monitoring data set includes bridge structure response monitoring data, environmental impact factor monitoring data, and rotation actuator operation status monitoring data; Performing spatiotemporal alignment and fusion processing on the multi-source monitoring data set to generate fused monitoring data; Based on the fused monitoring data and a preset target posture parameter set, identifying posture deviation characteristics between the bridge rotation posture and the target posture; generating a posture adjustment strategy for the bridge rotation actuator according to the posture deviation characteristics; The posture adjustment strategy is executed to perform real-time posture adjustment operations on the bridge rotation process.

2. The method according to claim 1, characterized in that, The performing spatiotemporal alignment and fusion processing on the multi-source monitoring data set to generate fused monitoring data includes: Performing data validity verification on the bridge structure response monitoring data, the environmental impact factor monitoring data, and the rotation actuator operation status monitoring data, respectively, eliminating invalid data items, and obtaining a valid monitoring data set; Performing timestamp alignment processing on the bridge structure response monitoring data, the environmental impact factor monitoring data, and the rotation actuator operation status monitoring data in the valid monitoring data set, respectively, so that the bridge structure response monitoring data, the environmental impact factor monitoring data, and the rotation actuator operation status monitoring data have a synchronous corresponding relationship in the time dimension; Performing spatial position registration processing on the bridge structure response monitoring data, the environmental impact factor monitoring data, and the rotation actuator operation status monitoring data in the valid monitoring data set after the timestamp alignment processing, so that the bridge structure response monitoring data, the environmental impact factor monitoring data, and the rotation actuator operation status monitoring data have a unified spatial reference benchmark in the spatial dimension; On the basis of completing the timestamp alignment processing and the spatial position registration processing, the bridge structure response monitoring data, the environmental impact factor monitoring data and the rotating actuator operation status monitoring data are input into a preset data fusion model, and the data fusion model is used to perform feature-level fusion operations on the input types of monitoring data to output the fused monitoring data; the fused monitoring data is a data set that eliminates time and space differences and comprehensively reflects the coordinated change characteristics of the bridge structure status, environmental impact and actuator status.

3. The method according to claim 2, wherein The identifying, based on the fused monitoring data and a preset target posture parameter set, a posture deviation feature between the bridge rotation posture and the target posture, includes: Extracting a current posture feature set representing the current spatial position and posture of the bridge from the fused monitoring data; the current posture feature set at least includes a three-dimensional coordinate offset of a key control point of the bridge, an overall torsion angle of the bridge, and a deformation degree of a target cross section of the bridge; Obtain a target pose feature set corresponding to the current pose feature set from the preset target pose parameter set; the target pose feature set at least includes the target three-dimensional coordinate offset of the key control points of the bridge, the target torsional angle of the overall bridge, and the target deformation degree of the target cross-section of the bridge; Perform a difference comparison process on the three-dimensional coordinate offset of the key control points of the bridge in the current pose feature set and the target three-dimensional coordinate offset of the key control points of the bridge in the target pose feature set to generate a position deviation feature; Perform a difference comparison process on the overall torsional angle of the bridge in the current pose feature set and the target overall torsional angle of the bridge in the target pose feature set to generate a torsional deviation feature; Perform a difference comparison process on the deformation degree of the target cross-section of the bridge in the current pose feature set and the target deformation degree of the target cross-section of the bridge in the target pose feature set to generate a deformation deviation feature; Fuse the position deviation feature, the torsional deviation feature, and the deformation deviation feature to form the pose deviation feature; the pose deviation feature is used to quantitatively describe the comprehensive deviation degree between the bridge rotation pose and the target pose in terms of spatial position, overall torsion, and local deformation.

4. The method according to claim 3, wherein Generate a pose adjustment strategy for the bridge rotation actuator according to the pose deviation feature, including: Input the pose deviation feature into a preset pose adjustment strategy generation model, and through the pose adjustment strategy generation model, analyze the deviation degree and change trend of the position deviation feature, the torsional deviation feature, and the deformation deviation feature in the pose deviation feature; Based on the bridge structure mechanics constraint rules and the rotation actuator operation constraint rules built in the pose adjustment strategy generation model, evaluate the effect prediction of different adjustment action combinations on eliminating the position deviation feature, the torsional deviation feature, and the deformation deviation feature; According to the effect prediction, generate an adjustment instruction combination that promotes the optimal collaborative reduction of the position deviation feature, the torsional deviation feature, and the deformation deviation feature on the premise of satisfying the bridge structure mechanics constraint rules and the rotation actuator operation constraint rules; Package the adjustment instruction combination as the pose adjustment strategy; the pose adjustment strategy contains an instruction set for the action type, action direction, action amplitude, and action timing of different drive units in the rotation actuator.

5. The method according to claim 4, characterized in that, Execute the pose adjustment strategy to perform real-time pose adjustment operations on the bridge rotation process, including: Parse the adjustment instruction set in the pose adjustment strategy into a control instruction sequence recognizable by the rotation actuator; Send the control instruction sequence to the corresponding multiple drive controllers of the rotation actuator; Control the corresponding drive units through the multiple drive controllers to execute the action type, action direction, action amplitude, and action timing specified in the control instruction sequence; During the process of the driving unit performing actions, continuously obtain the multi-source monitoring data set, and repeatedly execute the steps of performing spatio-temporal alignment and fusion processing on the multi-source monitoring data set to generate fused monitoring data, the step of identifying the attitude deviation characteristics between the bridge rotation attitude and the target attitude based on the fused monitoring data and the preset target attitude parameter set, the step of generating an attitude adjustment strategy for the bridge rotation actuator according to the attitude deviation characteristics, and the step of executing the attitude adjustment strategy to perform real-time attitude adjustment operations on the bridge rotation process; When the identified attitude deviation characteristics meet the preset attitude adjustment completion condition, terminate the execution of the attitude adjustment strategy.

6. The method according to claim 2, wherein The time stamp alignment processing of the bridge structure response monitoring data, the environmental impact factor monitoring data, and the rotation actuator operation state monitoring data in the effective monitoring data set respectively includes: Obtain the first time stamp sequence corresponding to the bridge structure response monitoring data, the second time stamp sequence corresponding to the environmental impact factor monitoring data, and the third time stamp sequence corresponding to the rotation actuator operation state monitoring data in the effective monitoring data set; Perform time resampling processing on the first time stamp sequence, the second time stamp sequence, and the third time stamp sequence at a preset reference time interval to respectively generate the first resampled data sequence of the bridge structure response monitoring data, the second resampled data sequence of the environmental impact factor monitoring data, and the third resampled data sequence of the rotation actuator operation state monitoring data; Perform time synchronization processing on the first resampled data sequence, the second resampled data sequence, and the third resampled data sequence to ensure that at the same reference time point, there are corresponding valid data points in the first resampled data sequence, the second resampled data sequence, and the third resampled data sequence; Use the first resampled data sequence, the second resampled data sequence, and the third resampled data sequence after time synchronization processing as the bridge structure response monitoring data, the environmental impact factor monitoring data, and the rotation actuator operation state monitoring data after time stamp alignment processing respectively.

7. The method according to claim 2, wherein The spatial position registration processing of the bridge structure response monitoring data, the environmental impact factor monitoring data, and the rotation actuator operation state monitoring data in the effective monitoring data set after time stamp alignment processing includes: Establish a unified spatial coordinate system as the registration reference coordinate system; Identify the first spatial reference system corresponding to the bridge structure response monitoring data, the second spatial reference system corresponding to the environmental impact factor monitoring data, and the third spatial reference system corresponding to the rotation actuator operation state monitoring data; Calculate the spatial transformation parameters between the first spatial reference system, the second spatial reference system, and the third spatial reference system and the registration reference coordinate system respectively; Based on the spatial transformation parameters, transform the bridge structure response monitoring data after timestamp alignment from the first spatial reference system to the registration reference coordinate system to obtain the first registered monitoring data; Based on the spatial transformation parameters, transform the environmental impact factor monitoring data after timestamp alignment from the second spatial reference system to the registration reference coordinate system to obtain the second registered monitoring data; Based on the spatial transformation parameters, transform the running state monitoring data of the swing actuator after timestamp alignment from the third spatial reference system to the registration reference coordinate system to obtain the third registered monitoring data; The first registered monitoring data, the second registered monitoring data, and the third registered monitoring data together constitute the bridge structure response monitoring data, the environmental impact factor monitoring data, and the running state monitoring data of the swing actuator after spatial position registration processing.

8. The method according to claim 2, characterized in that The data fusion model is a feature fusion network based on the attention mechanism; performing feature-level fusion operations on various types of input monitoring data through the data fusion model, and outputting the fused monitoring data, including: Input the bridge structure response monitoring data, the environmental impact factor monitoring data, and the running state monitoring data of the swing actuator after spatial position registration processing into different feature extraction branches of the feature fusion network based on the attention mechanism respectively; Extract the deep feature expressions of the corresponding type of monitoring data through each feature extraction branch respectively; Input the deep feature expressions extracted by each feature extraction branch into the attention allocation module; In the attention allocation module, according to the internal correlation between the state of the current bridge swing stage and the deep feature expressions of various types of monitoring data, calculate the attention weight coefficients that should be assigned to the deep feature expression of the bridge structure response monitoring data, the deep feature expression of the environmental impact factor monitoring data, and the deep feature expression of the running state monitoring data of the swing actuator respectively; Based on the calculated attention weight coefficients, perform weighted fusion processing on the deep feature expression of the bridge structure response monitoring data, the deep feature expression of the environmental impact factor monitoring data, and the deep feature expression of the running state monitoring data of the swing actuator; Perform feature dimensionality reduction and integration operations on the weighted fusion feature expressions to generate the fused monitoring data; the fused monitoring data is a unified feature vector sequence integrating structural response, environmental impact, and mechanism state information.

9. The method according to claim 4, characterized in that The attitude adjustment strategy generation model is a decision-making model based on the combination of rules and learning; in the attitude adjustment strategy generation model, a variety of candidate adjustment action combinations are preset; based on the bridge structure mechanical constraint rules and the swing actuator running constraint rules built into the attitude adjustment strategy generation model, evaluate the effect prediction of different adjustment action combinations on eliminating the position deviation feature, the torsion deviation feature, and the deformation deviation feature, including: For each candidate combination of adjustment actions, according to the current values of the position deviation feature, the torsion deviation feature, and the deformation deviation feature in the pose deviation feature, and in combination with the bridge structure mechanics constraint rules, predict the distribution of bridge structure stress changes and potential risk areas caused after executing the candidate combination of adjustment actions; According to the current values of the position deviation feature, the torsion deviation feature, and the deformation deviation feature in the pose deviation feature, and in combination with the running constraint rules of the swing execution mechanism, predict the required output power, running speed, and duration of each driving unit when executing this candidate combination of adjustment actions, and evaluate whether they exceed the safe operation threshold of the execution mechanism; Combined with the predicted distribution of bridge structure stress changes, the evaluation results of potential risk areas, and the evaluation results of the output power, running speed, and duration of each driving unit, calculate the comprehensive effect score of this candidate combination of adjustment actions for reducing the position deviation feature, the torsion deviation feature, and the deformation deviation feature; Based on the historical adjustment effect feedback data learned by the pose adjustment strategy generation model, correct the comprehensive effect score; Generate an adjustment instruction combination that promotes the optimal collaborative reduction of the position deviation feature, the torsion deviation feature, and the deformation deviation feature, and select the candidate combination of adjustment actions with the highest corrected comprehensive effect score.

10. An intelligent adjustment system for the rotation posture of a bridge based on multi-source data fusion, characterized in that, Including: A memory in which a computer program is stored; A processor for loading the computer program to implement the intelligent adjustment method for the bridge swing pose based on multi-source data fusion according to any one of claims 1-9.

Images