Paying-off device for road and bridge construction and using method

Abstract

The invention relates to the field of road and bridge construction, in particular to a road and bridge construction pay-off device and a using method. The method comprises the following steps: acquiring topographic data, equipment attitude data and environmental parameter data of a construction scene through a laser range finder, an inertial navigation system and an environmental sensor, and carrying out denoising and standardization processing on the data to generate a formatted pay-off data matrix; generating path input data by adopting a dynamic weight fusion algorithm based on the data matrix; a path planning model is generated in combination with construction scene parameters, and an optimized paying-off path and dynamic compensation parameters are obtained through dynamic compensation calculation; the optimized paying-off path and the dynamic compensation parameters are input into a paying-off control module, and a multi-shaft paying-off device is driven to execute high-precision automatic paying-off; the sensor weight and the path planning strategy are dynamically adjusted through real-time paying-off operation results and environment feedback data, and closed-loop optimization is formed. The pay-off precision and the construction efficiency are remarkably improved, meanwhile, the device adapts to complex terrains and dynamic construction environments, manual operation errors are reduced, and the device has high intellectualization and practicability.

Description

Technical Field

[0001] The invention relates to the field of road and bridge construction, and in particular to a road and bridge construction laying-out device and a use method thereof. Background Art

[0002] During the construction of roads and bridges, the wire laying operation is a key step in the early stage of construction, which directly affects the accuracy and quality of subsequent construction. However, traditional wire laying devices mostly rely on manual measurement or single sensor technology. This method has problems such as insufficient wire laying accuracy, low construction efficiency, and large human operation errors in construction scenes with complex terrain and drastic environmental changes. In addition, since the construction environment is often affected by dynamic interference such as wind speed and vibration, the traditional wire laying method lacks the ability to perceive the real-time environment and automatically adjust, resulting in the wire laying effect being difficult to meet complex construction requirements.

[0003] In recent years, with the rapid development of multimodal sensor fusion technology, dynamic path planning algorithms and real-time environmental perception technology, some intelligent solutions have been proposed for the accuracy and adaptability of construction layout. However, in practical applications, the above technologies still have bottlenecks such as insufficient fusion efficiency between sensor data, imperfect real-time compensation strategies and lack of dynamic adaptability in construction path planning.

[0004] Therefore, how to develop a high-precision line-laying device suitable for complex terrain and dynamic construction environments through multimodal sensor data fusion and real-time environmental perception technology, combined with dynamic path planning and real-time compensation strategies, has become a technical problem that needs to be solved urgently in the field of road and bridge construction. Summary of the invention

[0005] The present invention provides a road and bridge construction setting-out device and a use method to solve the problem of how to improve the accuracy and efficiency of road and bridge construction setting-out based on multimodal sensor data fusion, real-time environmental perception and dynamic path planning, while adapting to complex terrain and dynamic construction environments.

[0006] In order to solve the above technical problems, the present invention provides a method for setting out a road and bridge construction, comprising: Obtain terrain data, equipment attitude data and environmental parameter data collected by laser rangefinder, inertial navigation system and environmental sensor, and perform denoising and standardization on the data to generate a formatted laying-out data matrix; Based on the formatted laying-out data matrix, a dynamic weight fusion algorithm is used to fuse the terrain data, the equipment posture data and the environmental parameter data to generate path input data; Generate a path planning model in combination with construction scene parameters, and perform dynamic compensation calculation on the path planning model to generate an optimized laying-out path and dynamic compensation parameters; Input the optimized wire laying path and dynamic compensation parameters into the wire laying control module to drive the multi-axis wire laying device for high-precision automatic wire laying; Based on the real-time wire laying operation results and environmental feedback data, generate feedback adjustment parameters, update the path planning strategy, and transmit them to the wire laying control module in the next cycle.

[0007] Furthermore, the terrain data, equipment attitude data, and environmental parameter data include three-dimensional space coordinates, pitch angle, roll angle, yaw angle, wind speed, and vibration intensity.

[0008] Furthermore, the denoising process performs denoising operations on each column of the data matrix through the wavelet transform method to generate a denoised data matrix.

[0009] Furthermore, the standardization process performs normalization operations on the denoised data matrix through a normalization function to generate a standardized data matrix.

[0010] Furthermore, the generation of the path input data includes: Dynamically calculate the weights of the sensors, perform weighted fusion processing on the sensor data according to the environmental parameters of the real-time construction scenario, and generate a path input vector.

[0011] Furthermore, the generation of the path planning model includes: Extract terrain feature parameters, equipment status parameters, and environmental disturbance parameters from the path input vector, and combine them with the construction scenario parameters to generate a path planning model.

[0012] Furthermore, the dynamic compensation calculation includes: Perform real-time deviation analysis on the path planning model, generate a dynamic compensation factor according to the deviation value, and perform optimization processing on the path planning model to generate an optimized wire laying path and dynamic compensation parameters.

[0013] Furthermore, the control of the multi-axis wire laying device includes: Decompose the optimized wire laying path into multi-dimensional dynamic control vectors, generate device positioning instructions, and drive the multi-axis wire laying device for positioning and attitude adjustment.

[0014] Furthermore, the generation of the real-time feedback data includes: Extract the wire laying position data and wire laying status parameters from the wire laying operation results, compare them with the optimized wire laying path, and generate position deviations and feedback adjustment parameters.

[0015] Furthermore, a road and bridge construction wire laying device includes: A data acquisition and preprocessing module for collecting real-time data of the construction environment through multi-modal sensors and preprocessing it to generate a formatted data matrix for dynamic path planning; A path planning and dynamic compensation module, which is used to analyze the formatted wire laying data matrix and generate an optimized wire laying path and compensation parameters in combination with construction scenario parameters; A wire laying execution and control module, which is used to receive the optimized wire laying path and dynamic compensation parameters and drive a multi-axis wire laying device to perform high-precision wire laying operations; A real-time feedback and closed-loop optimization module, which is used to dynamically adjust the sensor weights and path planning strategies according to the wire laying execution results and environmental feedback data to form an optimized closed loop.

[0016] The key innovation points of the present invention include: (1) Multi-modal data fusion and dynamic weight algorithm: The dynamic weight fusion algorithm is used to fuse and process the laser ranging, device attitude and environmental disturbance parameters to achieve efficient integration and real-time optimization of the data.

[0017] (2) Dynamic path planning and compensation strategy: By extracting terrain features, device states and environmental disturbance parameters, a path planning model is generated in combination with the construction scenario, and the compensation parameters are dynamically adjusted based on real-time deviation analysis, making the path planning more real-time and adaptable.

[0018] (3) Real-time closed-loop optimization mechanism: A real-time feedback mechanism is introduced to fuse and analyze the wire laying operation results and environmental feedback data, and a multi-cycle closed-loop optimization is formed by dynamically updating the sensor weights and path planning strategies to achieve efficient and precise wire laying operations.

[0019] The following are its main beneficial effects: (1) High-precision wire laying: The present invention adopts a multi-modal data fusion technology combining laser ranging, inertial navigation and environmental sensors, and uses the dynamic weight algorithm to perform weighted fusion on terrain, device state and environmental data to generate high-precision path input data, avoiding the problem of insufficient accuracy of traditional single sensors.

[0020] (2) Real-time dynamic adaptability: Through the dynamic compensation calculation of the path planning model, the real-time deviation in complex construction scenarios is corrected, and an optimized wire laying path and dynamic compensation parameters are generated to ensure that the wire laying device can accurately respond to external environmental disturbances such as wind speed and vibration, realizing highly adaptable wire laying operations.

[0021] (3) Closed-loop optimization control: Combining the real-time wire laying execution results and environmental feedback data, dynamically adjusting the sensor weights and path planning strategies to form a closed-loop optimization mechanism, further improving the intelligence and stability of the wire laying process and reducing errors caused by human intervention. Description of the Drawings

[0022] Figure 1It is a schematic flowchart of a method for road and bridge construction setting out provided by an embodiment of this application; Figure 2 It is a structural block diagram of a road and bridge construction setting out device provided by an embodiment of this application. Specific embodiments

[0023] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by those skilled in the technical field to which this application belongs; the terms used in the description of this application in the specification are only for the purpose of describing specific embodiments and are not intended to limit this application; the terms "including" and "having" and any variations thereof in the specification and claims of this application and the above drawings are intended to cover non-exclusive inclusion. The terms "first", "second", etc. in the specification and claims of this application or the above drawings are used to distinguish different objects and not to describe a specific order.

[0024] Referring to "embodiment" herein means that the specific features, structures or characteristics described in connection with the embodiment may be included in at least one embodiment of this application. The phrase appears at various positions in the specification and does not necessarily refer to the same embodiment, nor is it an independent or alternative embodiment mutually exclusive with other embodiments. Those skilled in the art will explicitly and implicitly understand that the embodiments described herein may be combined with other embodiments.

[0025] Embodiment 1: Refer to Figure 1 , which is a schematic flowchart of a method for road and bridge construction setting out provided by an embodiment of the present invention. This process may at least include steps S100 - S400: S100. Obtain real-time terrain data, device attitude data, and environmental parameter data based on a laser rangefinder, an inertial navigation system, and an environmental sensor, and preprocess the multi-modal data to generate a formatted setting out data sequence; S200. Perform dynamic weight fusion processing on the formatted setting out data sequence, and generate an optimized setting out path and dynamic compensation parameters in combination with construction scene parameters; S300. Input the optimized setting out path and dynamic compensation parameters into the setting out control module to drive the multi-axis setting out device to perform real-time adjustment and high-precision automatic setting out; S400. Dynamically adjust the sensor weights and path planning strategies based on the real-time setting out operation results and environmental feedback data, generate updated compensation parameters, and transmit them to the setting out control module of the next cycle.

[0026] Step S100 at least includes steps S110 - S130: S110: Acquisition of multi-modal raw data.

[0027] First, obtain the terrain ranging data in the construction scene through a laser rangefinder, denoted as D1(x, y, z, t), where x, y, z are three-dimensional space coordinates and t is the time variable, representing the real-time ranging result.

[0028] Further, obtain the attitude data of the wire laying device from the inertial navigation system (INS), denoted as A i (ϕ, θ, ψ, t), where ϕ, θ, ψ are the pitch angle, roll angle, and yaw angle, representing the attitude information of the device.

[0029] Further, collect the wind speed and vibration data in real time through environmental sensors, denoted as W(t) and V(t) respectively, where W(t) is the wind speed change value and V(t) is the vibration intensity value.

[0030] Generate a multi-modal raw data matrix: Integrate the above data into the raw data matrix M0, expressed as: M0 = [D1(x, y, z, t) A i (ϕ, θ, ψ, t) W(t) V(t)]; This matrix serves as the input data for subsequent preprocessing steps.

[0031] S120: Multi-modal data preprocessing.

[0032] First, perform denoising processing on each column of data in the matrix M0 using the wavelet transform method to eliminate the noise values introduced by environmental interference. After denoising, generate the data matrix M1, denoted as: M1 = Denoise(M0); where Denoise represents the denoising function.

[0033] Further, perform normalization processing on the denoised matrix M1 to ensure that each data dimension has the same dimension, generating the standardized matrix M2: M2 = Normalize(M1); where Normalize is the normalization function, and the processed data range is unified to [0,1][0,1][0,1].

[0034] Construct a time series: Convert the standardized data matrix M2 into a time series data sequence S p (t), as the input for dynamic path planning: S p (t) = {(M2(t - n), …, M2(t)}, where n is the window length and t is the current time step.

[0035] S130: Multi-modal data formatting.

[0036] Sequence integration: Extract features from the time series S p (t) by dimension and integrate them into the data vector V p required for wire laying optimization: V p = [Mean(D1) Var(Ai )Mean(W)Max(V)] where Mean represents the mean function, Var represents the variance function, and Max represents the maximum function.

[0037] Generate a formatted data matrix: Generate a formatted wire laying data matrix F based on the integration result d , expressed as: The data matrix is used as the input for the next module S200.

[0038] Explanation of the connection between the previous and next steps: S110 and S120: The multi-modal raw data M0 obtained by S110 is passed to S120 for denoising and normalization processing to generate a pre-processed data matrix M2.

[0039] S120 and S130: The standardized matrix M2 generated by S120 is used as the input for S130 for time series construction and formatted integration, and finally a formatted wire laying data matrix F that meets the requirements of dynamic path planning is generated d .

[0040] S130 and S200: The formatted data matrix F obtained in S130 d is directly passed to S200 for dynamic weight fusion and path optimization calculation.

[0041] Step S200 includes at least steps S210 - S230: S210: Based on the wire laying data sequence, use the dynamic weight fusion algorithm to fuse the laser ranging data, device attitude data, and environmental parameter data to generate fused path input data.

[0042] First, obtain the laser ranging data D1, device attitude data A d and environmental parameter data W and V from the formatted wire laying data matrix F i output from S130. Specifically: F d =[D1 A i W V]; where D1 represents terrain ranging data, A i represents the device attitude parameter, and W and V represent the wind speed and vibration parameters respectively.

[0043] Dynamic weight calculation: Based on the real-time construction scenario, dynamically calculate the weight ω of each sensor through the following formula: where ω i is the weight of the i-th type of data, E i is the current environmental interference intensity (such as wind speed or vibration intensity), and β is the adjustment coefficient.

[0044] Perform weighted fusion on the laser ranging, attitude, and environmental parameters to generate a path input vector Ip : where n is the dimension of the input data, and F d (i) is the data value of the i-th class.

[0045] S220: Extract the terrain feature parameters, equipment status parameters, and environmental disturbance parameters from the fused path input data, and analyze them in combination with the construction scene parameters to generate an optimized path planning model.

[0046] First, extract the following feature parameters from the path input vector I p : Terrain feature parameter T geo : Based on the average gradient and maximum height difference of D1, it is calculated as: T geo = Mean(∇D1), Max(ΔD1),, where ∇D1 represents the gradient value and ΔD1 represents the height difference.

[0047] Equipment status parameter T equip : Based on the attitude stability of A i , it is calculated as: T equip = Var(A i ) where Var is the variance function.

[0048] Environmental disturbance parameter T env : Combining the dynamic disturbance intensities of wind speed W and vibration V, it is calculated as: Combined with construction scene analysis: Based on the extracted feature parameters T geo , T equip and T env , combined with the static planning requirements S scene of the construction scene, generate a path planning model P path : where f represents the path planning function.

[0049] S230: Perform dynamic compensation calculation on the path planning model to generate an optimized wire laying path and dynamic compensation parameters adapted to complex terrain and real-time environment.

[0050] Path deviation analysis: Perform real-time deviation calculation on the path planning model P path to obtain a compensation factor C comp : where ΔT represents the deviation between the current value and the planned value.

[0051] Dynamic compensation path generation: Optimize the path planning model based on the compensation factor C comp to generate a dynamic compensation path

[0052] Output optimization result: Generate a wire laying path P opt adapted to complex terrain and real-time environment and dynamic compensation parameter Ccomp Used for wire laying control in S300.

[0053] Explanation of the connection between the previous and subsequent steps: S210 and S220: The fused path input data I generated in S210 p is directly passed to S220 to extract parameters such as terrain features, equipment status, and environmental disturbances for generating a path planning model.

[0054] S220 and S230: The path planning model P in S220 path is used as the input of S230 for deviation analysis and dynamic compensation calculation to generate an optimized path P opt and compensation parameter C comp .

[0055] S230 and S300: The optimized path and compensation parameters output by S230 are passed to S300 to drive the multi-axis wire laying device to perform precise wire laying.

[0056] Step S300 at least includes steps S310 - S330: S310: Input the optimized wire laying path and dynamic compensation parameters into the wire laying control module to drive the precise positioning of the multi-axis wire laying device.

[0057] First, receive the optimized wire laying path P output by S230 opt and dynamic compensation parameter C comp .

[0058] P opt represents the optimized wire laying path, which is the dynamically compensated version of the path planning model P path .

[0059] C comp represents the compensation factor for real-time terrain and environmental disturbances.

[0060] Furthermore, decompose P opt into three-dimensional path parameters P opt (x, y, z), and the dynamic compensation factor C comp is correspondingly assigned to each coordinate dimension to generate a dynamic control vector V control :

[0061] where C comp,x， C comp,y , C comp,z are the projections of the compensation factor in each dimension.

[0062] Device positioning instruction generation: Based on V control generate a precise positioning instruction L device , and pass it to the multi-axis wire laying device: Ldevice = f loc (V control ); where f loc is the device positioning instruction function for driving the multi-axis device for initial positioning.

[0063] S320: Adjust the position and attitude of the wire pay-off device from the positioning data, and perform dynamic adjustment to adapt to real-time environmental changes.

[0064] First, the current position L curr and attitude data A curr (ϕ, θ, ψ) of the wire pay-off device are collected in real time through an inertial navigation system (INS) and built-in sensors of the device.

[0065] L cur represents the coordinates of the device in the current three-dimensional space.

[0066] A curr represents the current attitude angle of the device, including the pitch angle ϕ, roll angle θ, and yaw angle ψ.

[0067] Furthermore, the current positioning data is compared with the target control vector V control to calculate the position deviation ΔL: ΔL = V control − L curr .

[0068] Furthermore, combining the position deviation ΔL and the real-time attitude A curr , adjust the device attitude parameter A adj : A adj = f adj (ΔL, A cur ); where f adj is the attitude adjustment function, and the corrected attitude angle is output.

[0069] S330: According to the device state after dynamic adjustment, perform high-precision wire pay-off operation to generate real-time wire pay-off execution result data.

[0070] Perform wire pay-off operation: Based on the adjusted attitude parameter A adj and the target path control instruction L device , drive the wire pay-off mechanism of the multi-axis device to perform wire pay-off operation.

[0071] Real-time wire pay-off data collection: During the wire pay-off process, the current wire pay-off position L line and wire pay-off state parameter S line are recorded in real time to form wire pay-off result data: R line = [L line S line ; where S line includes wire pay-off state information such as tension and wire length.

[0072] Generate the execution result sequence: Integrate the continuous wire laying results to generate a real-time wire laying execution result sequence where n is the time step.

[0073] Explanation of the connection between the previous and subsequent steps: S310 and S320: The positioning instruction L generated in S310 device is used as the input of S320 to compare the deviation between the current position and the target position, and adjust the attitude of the device.

[0074] S320 and S330: The adjusted attitude parameter A output by S320 adj and the target path instruction are used in S330 to drive the wire laying device to perform the actual wire laying operation.

[0075] S330 and S400 (subsequent module): The wire laying execution result data R generated in S330 exec is transmitted to S400 for real-time feedback and optimization.

[0076] Step S400 at least includes steps S410 - S430: S410: Obtain the wire laying execution result data and real-time environment feedback data, perform difference analysis, and generate feedback adjustment parameters.

[0077] First, obtain the real-time wire laying execution result data R from S330 exec , which includes the wire laying position data L line and the wire laying status parameter S line . At the same time, obtain the real-time environment feedback data F from the environmental sensor env , including the wind speed W(t) and vibration V(t).

[0078] Furthermore, compare the current position L exec in the wire laying execution result R line with the optimized path P opt output by S230, and calculate the position deviation ΔL line : ΔL line = L line - P opt ; Comprehensive difference analysis: Combine the environmental feedback data F env , calculate the dynamic environmental deviation ΔF env : ; Combine the position deviation and the environmental deviation to generate the feedback adjustment parameter A fb : where g is the comprehensive difference analysis function.

[0079] S420: Dynamically update the sensor weights and path planning strategy based on the feedback adjustment parameters to generate optimized compensation parameters.

[0080] First, adjust the parameter A according to the feedback fb , and dynamically update the weights of the sensors: ; where w i is the initial weight, and γ is the adjustment factor.

[0081] Path planning strategy update: Combine the new sensor weights , and adjust the path planning model P path to generate an updated path planning model :

[0082] Where represents the updated path planning function, , are the terrain, equipment, and environmental characteristic parameters respectively.

[0083] Furthermore, perform compensation calculation on the updated path planning model to generate optimized compensation parameters : Where represents the new deviation value.

[0084] S430: Transmit the optimized compensation parameters to the path planning and wire laying control module in the next cycle to form a dynamic optimization closed loop.

[0085] First, integrate the optimized compensation parameters and the updated path planning model into a dynamic control data packet D control : Transmit the dynamic control data packet D control to the path planning input interface of the S200 module for path optimization in the next cycle.

[0086] Furthermore, in the S200 module, based on the path planning and compensation parameters of D control , regenerate the optimized wire laying path and compensation factor to achieve real-time closed-loop optimization.

[0087] Explanation of the connection between the previous and subsequent steps: S410 and S420: The feedback adjustment parameter A generated in S410 fb is directly transmitted to S420 to dynamically adjust the sensor weights and update the path planning strategy.

[0088] S420 and S430: The optimized compensation parameters generated in S420 and the updated path planning model Integrated into data packet D control and transmitted to S430.

[0089] S430 and S200 (next cycle): The data packet D in S430 control is input into the S200 module for path planning in the next cycle, forming a closed loop.

[0090] The key innovations of the present invention include: (1) Multi-modal data fusion and dynamic weight algorithm: The dynamic weight fusion algorithm is used to fuse the laser ranging, device attitude, and environmental disturbance parameters, realizing the efficient integration and real-time optimization of data.

[0091] (2) Dynamic path planning and compensation strategy: By extracting terrain features, device states, and environmental disturbance parameters, a path planning model is generated in combination with the construction scenario, and the compensation parameters are dynamically adjusted based on real-time deviation analysis, making the path planning more real-time and adaptable.

[0092] (3) Real-time closed-loop optimization mechanism: A real-time feedback mechanism is introduced to fuse and analyze the results of the wire laying operation and environmental feedback data. By dynamically updating the sensor weights and path planning strategies, multi-cycle closed-loop optimization is formed to achieve efficient and accurate wire laying operations.

[0093] The following are its main beneficial effects: (1) High-precision wire laying: The present invention adopts a multi-modal data fusion technology combining laser ranging, inertial navigation, and environmental sensors. Through the dynamic weight algorithm, terrain, device state, and environmental data are weighted and fused to generate high-precision path input data, avoiding the problem of insufficient accuracy of traditional single sensors.

[0094] (2) Real-time dynamic adaptability: Through the dynamic compensation calculation of the path planning model, real-time deviations in complex construction scenarios are corrected to generate optimized wire laying paths and dynamic compensation parameters, ensuring that the wire laying device can accurately respond to external environmental disturbances such as wind speed and vibration, and realizing highly adaptable wire laying operations.

[0095] (3) Closed-loop optimization control: Combining the real-time wire laying execution results and environmental feedback data, the sensor weights and path planning strategies are dynamically adjusted to form a closed-loop optimization mechanism, further enhancing the intelligence and stability of the wire laying process and reducing errors caused by human intervention.

[0096] Embodiment 2: Figure 2 Shows a structural block diagram of a road and bridge construction wire laying device according to an embodiment of the present invention. As Figure 2 shown, the structure may include: The data acquisition and preprocessing module 41 is used to obtain real-time data of the construction environment through multi-modal sensors and preprocess it to generate a formatted data sequence for subsequent analysis.

[0097] Through a laser rangefinder, an inertial navigation system, and environmental sensors, terrain data, equipment attitude data, and environmental parameters (wind speed, vibration, etc.) in the construction scene are collected in real time, and a multi-modal raw data matrix is generated.

[0098] Denoising and standardizing the collected raw data to ensure data consistency and accuracy.

[0099] Convert the standardized data into a time series format and integrate it into a formatted data matrix for dynamic path planning.

[0100] The path planning and dynamic compensation module 42 is used to analyze the formatted data and dynamically generate an optimized laying path and compensation parameters in combination with the construction scene parameters.

[0101] Based on the dynamic weight fusion algorithm, perform weighted fusion on multi-modal data to extract terrain feature parameters, equipment status parameters, and environmental disturbance parameters.

[0102] Combine the construction scene requirements to generate an initial path planning model and perform real-time deviation analysis on the model.

[0103] Through dynamic compensation calculation, generate an optimized laying path and compensation parameters suitable for complex terrain and real-time environment.

[0104] The laying execution and control module 43 is used to receive the optimized laying path and dynamic compensation parameters and drive the multi-axis laying device to perform high-precision laying operations.

[0105] Decompose the optimized laying path and compensation parameters into multi-dimensional dynamic control vectors and generate device positioning instructions.

[0106] Through inertial navigation and equipment attitude adjustment, real-time correct the position and attitude of the laying device to ensure the precise alignment of the device with the optimized path.

[0107] Execute high-precision laying operations, record the laying status data in real time, and generate laying execution results for subsequent feedback optimization.

[0108] The real-time feedback and closed-loop optimization module 44 is used to dynamically adjust the sensor weights and path planning strategies according to the laying execution results and environmental feedback data to form an optimization closed-loop.

[0109] Calculate the position deviation and environmental disturbance parameters from the real-time laying execution data and generate feedback adjustment parameters.

[0110] Based on feedback to adjust parameters, dynamically update the sensor weights and re-optimize the path planning strategy to generate new compensation parameters.

[0111] Transfer the optimized compensation parameters and path planning model to the path planning module to achieve real-time dynamic optimization of the closed loop.

[0112] Beneficial effects of the embodiment: 1. High precision and high efficiency: Through multi-modal data fusion and dynamic weight adjustment, high precision in construction setting out and the ability to adapt to complex terrains are achieved, effectively improving the construction efficiency.

[0113] 2. Real-time performance and dynamic adjustment ability: A real-time feedback and closed-loop optimization mechanism is introduced, which can adjust the setting out path and compensation parameters in real time according to environmental changes during the construction process to ensure the accuracy and stability of the construction.

[0114] 3. Intelligence and automation: An intelligent algorithm combining path planning and dynamic control is adopted, reducing manual intervention and the impact of human errors, and providing a more intelligent solution for road and bridge construction.

[0115] Obviously, the embodiments described above are only a part of the embodiments of the present application, rather than all of them. The accompanying drawings show preferred embodiments of the present application, but do not limit the patent scope of the present application. The present application can be implemented in many different forms. On the contrary, the purpose of providing the embodiments is to make the understanding of the disclosed content of the present application more thorough and comprehensive. Although the present application has been described in detail with reference to the foregoing embodiments, for those skilled in the art, they can still modify the technical solutions recorded in the foregoing specific embodiments, or perform equivalent replacements on some of the technical features. Any equivalent structures directly or indirectly using the content of the specification and drawings of the present application in other related technical fields are equally within the scope of the patent protection of the present application.

Claims

1. A method for laying out lines in road and bridge construction, characterized in that: The following steps are involved: Obtain terrain data, equipment attitude data and environmental parameter data collected by laser rangefinder, inertial navigation system and environmental sensor, and perform denoising and standardization on the data to generate a formatted laying-out data matrix; Based on the formatted laying-out data matrix, a dynamic weight fusion algorithm is used to fuse the terrain data, the equipment posture data and the environmental parameter data to generate path input data; Generate a path planning model in combination with construction scene parameters, and perform dynamic compensation calculation on the path planning model to generate an optimized laying-out path and dynamic compensation parameters; The optimized wire-paying path and dynamic compensation parameters are input into a wire-paying control module to drive a multi-axis wire-paying device to automatically pay out wires with high precision; Based on the real-time wire-laying operation results and environmental feedback data, feedback adjustment parameters are generated and the path planning strategy is updated and passed to the wire-laying control module of the next cycle.

2. The method for setting out the lines for road and bridge construction according to claim 1, characterized in that: The terrain data, equipment attitude data and environmental parameter data include three-dimensional space coordinates, pitch angle, roll angle, yaw angle, wind speed and vibration intensity.

3. The method for setting out the lines in road and bridge construction according to claim 1, characterized in that: The denoising process performs a denoising operation on each column of data in the data matrix by using a wavelet transform method to generate a denoised data matrix.

4. The method for setting out the lines in road and bridge construction according to claim 3, characterized in that: The standardization process performs a normalization operation on the denoised data matrix through a normalization function to generate a standardized data matrix.

5. The method for setting out the lines in road and bridge construction according to claim 1, characterized in that: The generation of the path input data includes: The sensor weights are dynamically calculated, and the sensor data is weighted and fused according to the environmental parameters of the real-time construction scene to generate a path input vector.

6. The method for setting out the lines in road and bridge construction according to claim 5, characterized in that: The generation of the path planning model includes: The terrain feature parameters, equipment status parameters and environmental disturbance parameters are extracted from the path input vector, combined with the construction scene parameters, to generate a path planning model.

7. The method for setting out the lines in road and bridge construction according to claim 6, characterized in that: The dynamic compensation calculation includes: The path planning model is analyzed for deviation in real time, a dynamic compensation factor is generated according to the deviation value, and the path planning model is optimized to generate an optimized laying-out path and dynamic compensation parameters.

8. The method for setting out the lines in road and bridge construction according to claim 1, characterized in that: The control of the multi-axis pay-off device includes: The optimized pay-off path is decomposed into multi-dimensional dynamic control vectors to generate device positioning instructions, and drive the multi-axis pay-off device to perform positioning and posture adjustment.

9. The method for setting out the lines in road and bridge construction according to claim 8, characterized in that: The generation of the real-time feedback data includes: The wire-laying position data and wire-laying state parameters are extracted from the wire-laying operation results, compared with the optimized wire-laying path, and the position deviation and feedback adjustment parameters are generated.

10. A laying-out device for road and bridge construction, characterized in that: include: The data acquisition and preprocessing module is used to collect real-time data of the construction environment through multimodal sensors and preprocess it to generate a formatted data matrix for dynamic path planning; A path planning and dynamic compensation module is used to analyze the formatted setting-out data matrix and generate an optimized setting-out path and compensation parameters in combination with construction scene parameters; A wire-paying execution and control module, configured to receive the optimized wire-paying path and dynamic compensation parameters, and drive a multi-axis wire-paying device to perform a high-precision wire-paying operation; The real-time feedback and closed-loop optimization module is used to dynamically adjust the sensor weights and path planning strategies according to the execution results of the line release and environmental feedback data to form an optimization closed loop.

Images