A walking control method and device of a supporting retaining wall construction equipment

CN121143313BActive Publication Date: 2026-09-22GUIZHOU INVESTMENT & CONSTR CO LTD OF CHINA CONSTR FOURTH ENG BUREAU
View PDF 2 Cites 0 Cited by

Patent Information

Application Number
CN202511035774.2
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2025-07-25
Publication Date
2026-09-22
Estimated Expiration
2045-07-25

AI Technical Summary

Technical Problem

[0005]本申请提供一种支护挡墙施工设备的行走控制方法和装置,解决了仅依赖人工控制无法实现对设备运行轨迹的精确控制,从而出现灌注点定位偏移的问题

Benefits of technology

1、通过获取施工场地环境数据与支护挡墙类型数据;根据支护挡墙类型数据,在行走方案数据库中,获取施工设备对应的行走模式;通过预处理操作获取行走模式与施工场地环境数据之间的结构响应关联性特征;将结构响应关联性特征与施工场地环境数据输入行走控制模型,并基于行走控制模型输出施工设备对应的行走方案路线;基于行走方案路线,控制施工设备在支护挡墙上进行移动,从而实现了施工设备在结构扰动复杂、路径边界不规则、局部坡度变化显著的支护挡墙环境下的自主运行与精确路径控制,提高了灌注作业定位的准确性、设备移动的运行稳定性与施工操作的整体智能化水平。

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN121143313B_ABST
    Figure CN121143313B_ABST
Patent Text Reader

Abstract

The application provides a walking control method and device of a supporting retaining wall construction equipment, and relates to the field of large model control. The method comprises the following steps: in response to a walking control operation of the construction equipment, obtaining construction site environment data and supporting retaining wall type data; according to the supporting retaining wall type data, obtaining the walking mode corresponding to the construction equipment in the walking scheme database; obtaining the structural response correlation characteristics between the walking mode and the construction site environment data through a preprocessing operation; inputting the structural response correlation characteristics and the construction site environment data into the walking control model, and outputting the walking scheme route corresponding to the construction equipment based on the walking control model; and controlling the construction equipment to move on the supporting retaining wall based on the walking scheme route. The application solves the problem that the accurate control of the equipment running track cannot be realized by relying on manual control only, and the pouring point positioning deviation occurs.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] This application relates to the field of large model control, and in particular to a method and device for controlling the movement of a retaining wall construction equipment. Background Technology

[0002] During the construction of retaining walls, multiple grouting points on the retaining wall structure usually need to be worked on sequentially. Especially in the construction of large-scale continuous wall structures, in order to ensure the uniformity of grouting and the stability of pile quality, construction equipment, such as gantry cranes, need to be continuously moved along the top or side edge of the retaining wall to each predetermined position for cement grouting operations.

[0003] Currently, the movement of equipment on retaining walls is mostly achieved through manual operation, typically relying on direct control of the equipment's walking mechanism by construction personnel or manual operation of remote control devices. This method heavily depends on the operator's experience, judgment, and intuitive correction within their line of sight. However, in actual construction sites, factors such as sudden changes in local elevation differences and irregular boundaries at the top of the retaining wall mean that manual control alone cannot achieve precise control over the equipment's trajectory. Especially when operators lack experience or have limited visibility, the construction equipment is prone to deviating from the ideal trajectory, leading to misalignment of the grouting point. This results in inaccurate cement grouting positions, insufficient or excessive grouting depth, and in severe cases, may even cause structural defects such as concrete backflow in the grouting area, eccentric stress on the pile, or substandard pile quality.

[0004] Therefore, there is an urgent need for a method and device for controlling the movement of retaining wall construction equipment. Summary of the Invention

[0005] This application provides a method and device for controlling the movement of a retaining wall construction equipment, which solves the problem that relying solely on manual control cannot achieve precise control of the equipment's trajectory, thus leading to misalignment of the grouting point.

[0006] The first aspect of this application provides a method for controlling the movement of a retaining wall construction device. The method includes: in response to a movement control operation on the construction device, acquiring construction site environmental data and retaining wall type data; based on the retaining wall type data, acquiring the movement mode corresponding to the construction device from a movement scheme database; acquiring structural response correlation characteristics between the movement mode and the construction site environmental data through preprocessing operations; inputting the structural response correlation characteristics and the construction site environmental data into a movement control model, and outputting a movement scheme route corresponding to the construction device based on the movement control model; and controlling the construction device to move on the retaining wall based on the movement scheme route.

[0007] Optionally, acquiring construction site environmental data and retaining wall type data includes: acquiring the spatial structure and geometric boundaries of the construction area where the retaining wall is located using 3D photogrammetry equipment, and acquiring the material structure corresponding to the retaining wall using ultrasonic testing equipment; constructing a digital twin model of the construction site based on the spatial structure, geometric boundaries, and material structure; acquiring construction site environmental data and retaining wall type data based on the construction site digital twin model. The construction site environmental data includes top track alignment parameter data, local elevation difference distribution data, and slope change rate data; the retaining wall type data includes retaining wall structure type data, segment connection method data, and wall material composition distribution data.

[0008] Optionally, based on the retaining wall type data, the walking mode corresponding to the construction equipment is obtained from the walking scheme database. Specifically, this includes: obtaining the working conditions for the construction equipment to walk on the retaining wall based on the retaining wall type data, including standard stable working conditions, elastic uneven working conditions, and high slope turning working conditions; obtaining the walking mode corresponding to the working conditions from the walking scheme database, and using it as the walking mode corresponding to the construction equipment. The walking scheme database is used to store the correspondence between working conditions and walking modes.

[0009] Optionally, before obtaining the corresponding walking mode of the construction equipment from the walking scheme database based on the retaining wall type data, it is necessary to construct the walking scheme database. Specifically, this includes: obtaining historical simulation walking data of the construction equipment under different working conditions; inputting the historical simulation walking data into the walking mode analysis model, and outputting different walking modes corresponding to different working conditions based on the walking mode analysis model. The walking modes include constant tension synchronous drive mode, variable stiffness floating support mode, and dynamic slope compensation mode; constructing the correspondence between different working conditions and different walking modes, and storing the correspondence in the walking scheme database, with one working condition corresponding to one walking mode.

[0010] Optionally, preprocessing operations are used to obtain structural response correlation features between walking patterns and construction site environmental data. Specifically, this includes: constructing a multidimensional environmental state tensor based on construction site environmental data; inputting the multidimensional environmental state tensor into the equipment structural response simulation model corresponding to each walking control model, and outputting a structural response vector through the equipment structural response simulation model; constructing a structural response mapping model that integrates multi-channel convolutional and graph convolutional networks based on the multidimensional environmental state tensor and structural response vector; and extracting features based on the nonlinear propagation relationship between construction environment disturbances and equipment force paths through the structural response mapping model to form structural response correlation features.

[0011] Optionally, before inputting the structural response correlation features and construction site environmental data into the walking control model, and outputting the walking route corresponding to the construction equipment based on the walking control model, it is necessary to construct the walking control model. Specifically, this includes: generating a first module using a position-aware network and topology mapping structure based on the structural response correlation features and construction site environmental data, and generating a second module using a temporal prediction structure and reinforcement learning mechanism; and integrating the first module and the second module through a parameter fusion mechanism and a collaborative feedback mechanism to construct the walking control model.

[0012] Optionally, the structural response correlation characteristics and construction site environmental data are input into the walking control model, and the walking scheme route corresponding to the construction equipment is output based on the walking control model. Specifically, this includes: outputting the spatial trajectory sequence corresponding to the construction equipment based on the first module; outputting the speed control command sequence corresponding to the construction equipment based on the second module; and constructing the walking scheme route corresponding to the construction equipment based on the spatial trajectory sequence and the speed control command sequence.

[0013] A second aspect of this application provides a walking control device for retaining wall construction equipment, the device including an acquisition module and a processing module, wherein... The acquisition module is used to acquire construction site environmental data and retaining wall type data in response to the walking control operation of construction equipment.

[0014] The processing module is used to obtain the corresponding walking mode of the construction equipment from the walking scheme database based on the support retaining wall type data; obtain the structural response correlation characteristics between the walking mode and the construction site environment data through preprocessing operations; input the structural response correlation characteristics and the construction site environment data into the walking control model, and output the corresponding walking scheme route of the construction equipment based on the walking control model; and control the construction equipment to move on the support retaining wall based on the walking scheme route.

[0015] A third aspect of this application provides an electronic device including a processor, a memory, a user interface, and a network interface. The memory is used to store instructions, the user interface and the network interface are used to communicate with other devices, and the processor is used to execute the instructions stored in the memory to cause the electronic device to perform the method as described above.

[0016] A fourth aspect of this application provides a computer-readable storage medium storing a computer program, which is executed by a processor using the method described in any of the foregoing descriptions.

[0017] One or more technical solutions provided in the embodiments of this application have at least the following technical effects or advantages: 1. By acquiring construction site environmental data and retaining wall type data; based on the retaining wall type data, the corresponding walking mode of the construction equipment is obtained from the walking scheme database; the structural response correlation characteristics between the walking mode and the construction site environmental data are obtained through preprocessing operations; the structural response correlation characteristics and construction site environmental data are input into the walking control model, and the walking scheme route corresponding to the construction equipment is output based on the walking control model; based on the walking scheme route, the construction equipment is controlled to move on the retaining wall, thereby realizing the autonomous operation and precise path control of the construction equipment in the retaining wall environment with complex structural disturbances, irregular path boundaries, and significant local slope changes, improving the accuracy of grouting operation positioning, the operational stability of equipment movement, and the overall intelligence level of construction operation.

[0018] 2. Construct a multidimensional environmental state tensor based on construction site environmental data; input the multidimensional environmental state tensor into the equipment structural response simulation model corresponding to each type of walking control model, and output the structural response vector through the equipment structural response simulation model; construct a structural response mapping model that integrates multi-channel convolutional and graph convolutional networks based on the multidimensional environmental state tensor and structural response vector; extract features of the nonlinear propagation relationship between construction environment disturbance and equipment force path through the structural response mapping model to form structural response correlation features, thereby realizing high-dimensional modeling and quantitative expression of the complex coupling mechanism between the structural force state of construction equipment and environmental disturbance response. This enables the walking control model to have a high adaptability to various types of site change conditions at the input end, providing a precise constraint and dynamic feedback basis at the structural physical level for subsequent path reasoning and control strategy generation, thereby effectively improving the movement stability, path tracking accuracy and structural response robustness of equipment on heterogeneous support structures.

[0019] 3. Based on the structural response correlation characteristics and construction site environmental data, a position-aware network and topology mapping structure are used to generate the first module, and a temporal prediction structure and reinforcement learning mechanism are used to generate the second module. The first and second modules are integrated through parameter fusion and collaborative feedback mechanisms to construct a walking control model, thereby realizing the joint modeling of spatial path planning and dynamic control strategies for construction equipment. This enables the model to simultaneously perceive complex site structural characteristics and equipment runtime behavior. In the environment of retaining walls with irregular paths, significant disturbance responses, and high requirements for drive synchronization, the model achieves coordinated output of spatial trajectory and speed commands, improving the structural adaptability of path feasibility assessment and the dynamic stability of control strategy generation. Attached Figure Description

[0020] Figure 1 This is a flowchart illustrating a walking control method for a retaining wall construction equipment provided in an embodiment of this application; Figure 2This is a schematic diagram of a walking control device for a retaining wall construction equipment provided in an embodiment of this application; Figure 3 This is a schematic diagram of the structure of an electronic device provided in an embodiment of this application.

[0021] Explanation of reference numerals in the attached figures: 21. Acquisition module; 22. Processing module; 301. Processor; 302. Communication bus; 303. User interface; 304. Network interface; 305. Memory. Detailed Implementation

[0022] To enable those skilled in the art to better understand the technical solutions in this specification, the technical solutions in the embodiments of this specification will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, and not all embodiments.

[0023] The terminology used in the following embodiments of this application is for the purpose of describing particular embodiments only and is not intended to be limiting of this application. As used in the specification of this application, the singular expressions “a,” “an,” “the,” “the,” “the,” and “this” are intended to include the plural expressions as well, unless the context clearly indicates otherwise. It should also be understood that the term “and / or” as used in this application refers to and includes any or all possible combinations of one or more of the listed items.

[0024] Hereinafter, the terms "first" and "second" are used for descriptive purposes only and should not be construed as implying or suggesting relative importance or implicitly indicating the number of indicated technical features. Thus, a feature defined as "first" or "second" may explicitly or implicitly include one or more of that feature, and in the description of the embodiments of this application, unless otherwise stated, "multiple" means two or more.

[0025] To enable those skilled in the art to better understand the technical solution of the present invention, the present invention will be further described in detail below with reference to the accompanying drawings.

[0026] Please refer to Figure 1 The flowchart illustrates a walking control method for a retaining wall construction equipment provided in this application embodiment, which mainly includes the following steps: S101 to S105.

[0027] Step S101: In response to the walking control operation of the construction equipment, acquire the construction site environment data and the retaining wall type data.

[0028] Specifically, in the embodiments of this application, the construction equipment is a gantry crane, which performs movement control operations on retaining wall structures of different types and locations, such as port terminals, foundation pit edges, hydraulic retaining walls, urban rail construction areas, or prefabricated structure construction sites. In these situations, the gantry crane needs to transport heavy objects, perform precise positioning, or travel along a linear trajectory along the top of the retaining wall. Because retaining wall structures vary greatly, such as gravity-type, cantilever, anchor-type, or prefabricated segment-type structures, their structural stability, top surface morphology, and support reaction forces all differ significantly. Furthermore, the construction site environment may be accompanied by complex disturbances such as sudden changes in elevation, slope variations, or track discontinuities. Therefore, dynamic control of the gantry crane's travel path, attitude stability, and drive synchronization is required.

[0029] In one possible implementation, step S101 further includes: acquiring the spatial structure and geometric boundaries of the construction area where the retaining wall is located using a 3D photogrammetry device, and acquiring the material structure corresponding to the retaining wall using an ultrasonic testing device; constructing a digital twin model of the construction site based on the spatial structure, geometric boundaries, and material structure; acquiring construction site environmental data and retaining wall type data based on the construction site digital twin model, wherein the construction site environmental data includes top track alignment parameter data, local elevation difference distribution data, and slope change rate data; and the retaining wall type data includes retaining wall structure type data, segment connection method data, and wall material composition distribution data. In this scenario, in response to the gantry crane's travel control request, acquiring the construction site environmental data and retaining wall type data provides key inputs for subsequent path planning and control decisions.

[0030] Specifically, firstly, a three-dimensional photogrammetry device is used to perform a full-area spatial scan of the construction area where the retaining wall is located, acquiring the spatial structural features and geometric boundary information of the wall within the area, including three-dimensional geometric parameters such as wall height, top outline, edge turning points, track layout alignment, and its continuity. Subsequently, ultrasonic testing equipment is used to perform material profile detection on the retaining wall body, identifying the internal compositional layers, segment splicing methods, and local material heterogeneity distribution within the wall, and extracting the integrity index of the structural connection method by combining the time-domain characteristics of reflected waves. After completing the above data acquisition, a digital twin model of the construction site is constructed based on the fused dataset of spatial structure, geometric boundaries, and material structure, enabling it to have a high-fidelity reconstruction capability of the actual state of the retaining wall.

[0031] This digital twin model extracts construction site environmental data and retaining wall type data. The construction site environmental data includes top track alignment parameters such as gauge variation, radius of curvature, and sideslip angle; local elevation distribution data such as unilateral rise points and abrupt changes in height across segments; and slope change rate data such as longitudinal and transverse slope gradients at the top of the wall. The retaining wall type data includes retaining wall structure type data such as classification labels like gravity-type, cantilever-type, and anchor-type; segment connection method data such as mortise and tenon joints, welding, and prestressed anchoring methods; and wall material composition distribution data such as spatial layout information for concrete, rubble, and geogrid-reinforced soil. This data will serve as high-dimensional input features in subsequent walking pattern determination and path control inference.

[0032] Step S102: Based on the retaining wall type data, obtain the corresponding travel mode of the construction equipment from the travel scheme database.

[0033] Specifically, based on the data of the retaining wall type, the appropriate travel mode for the construction equipment is obtained from a pre-built travel scheme database. The purpose of this step is to accurately match the optimal travel control strategy based on the differences in retaining wall structure and equipment operating requirements, so as to improve the operational stability and path adaptability of the gantry crane in different support environments.

[0034] In one possible implementation, step S102 further includes: obtaining the working conditions for the construction equipment to travel on the retaining wall based on the retaining wall type data, including standard stable working conditions, elastic uneven working conditions, and high slope turning working conditions; obtaining the walking mode corresponding to the working conditions in the walking scheme database, and using it as the walking mode corresponding to the construction equipment, the walking scheme database being used to store the correspondence between working conditions and walking modes.

[0035] Specifically, based on the data on retaining wall types, structural and environmental parameters affecting the operating status of construction equipment are extracted. These parameters, combined with pre-defined working condition identification rules, determine the current operating conditions of the construction equipment. Specifically, the retaining wall type data includes the retaining wall structure type (e.g., gravity-type, anchor-type, cantilever type); segmental connection methods (e.g., rigid connection, flexible joint, prestressed anchoring); and the distribution of wall material composition (e.g., monolithic concrete, masonry blocks, steel reinforcement). Combining the above data with environmental elements extracted from the digital twin model, such as wall top slope, track continuity parameters, and foundation bearing capacity level, the current scenario is categorized into one of the following types using working condition identification logic: When the identification result is a standard stable working condition, it indicates that the support retaining wall structure has strong continuity, the top of the wall is flat, the foundation reaction force is uniform, and the environmental disturbance is low. At this time, the construction equipment has good operating stability and is suitable for the constant tension synchronous drive mode to ensure that the tension of the drive mechanism on both sides of the track is consistent, thereby improving the trajectory accuracy and travel coordination.

[0036] When the identification result is an elastic non-uniform working condition, it usually corresponds to an anchored or assembled retaining wall. The structural segments have relative displacement, uneven stiffness, and significant local settlement of the foundation. The height difference at the top of the wall cannot be ignored. A variable stiffness floating support mode is suitable. By adjusting the vertical flexibility of the support part, the uneven reaction force can be buffered to reduce the fatigue and vibration response of the gantry structure.

[0037] When the identification result is a high slope turning condition, it usually corresponds to a continuous slope change, large angle turning or wall curvature at the top of the retaining wall. The equipment's running path may change its posture at any time. In this case, the dynamic slope compensation mode should be selected. By linking the differential drive and adaptively adjusting the wheel group posture, the slope perception and center of gravity are automatically balanced to avoid path deviation or overturning risks.

[0038] After identification, the system retrieves the matching walking mode from the walking plan database using the working condition as the query index, and then uses this walking mode as the target operation control strategy for the current construction equipment. The walking plan database stores the predefined one-to-one mapping relationship between working conditions and walking modes in a structured manner, ensuring that the appropriate path control logic can be quickly switched in various complex construction environments.

[0039] In one possible implementation, step S102 further includes: acquiring historical simulation walking data of construction equipment under different working conditions; inputting the historical simulation walking data into the walking mode analysis model, and outputting different walking modes corresponding to different working conditions based on the walking mode analysis model. The walking modes include constant tension synchronous drive mode, variable stiffness floating support mode, and dynamic slope compensation mode; constructing the correspondence between different working conditions and different walking modes, and storing the correspondence in the walking scheme database, with one working condition corresponding to one walking mode.

[0040] Specifically, historical simulation walking data of construction equipment under different working conditions is obtained. The simulation walking data is generated based on a multiphysics modeling and virtual-real fusion testing platform, covering the operation process of construction equipment under various combinations of retaining wall structures and foundation types. The data content includes the spatial trajectory of the equipment, wheel-rail contact stress, attitude change parameters, drive synchronization deviation, path offset amplitude, structural response stress, and operation stability evaluation indicators.

[0041] The historical simulation walking data mentioned above is used as input and imported into a pre-built walking mode analysis model. The model adopts a deep neural network architecture composed of multilayer perceptrons and attention mechanisms. It can automatically identify the motion law, mechanical response characteristics and instability sensitivity of the equipment under different working conditions based on the feature distribution in the input data, and infer the optimal walking control mode accordingly.

[0042] In the simulation dataset, when the equipment operates with small path deviations, stable attitude changes, and insensitivity to structural response changes in trajectory errors, the model outputs a constant-tension synchronous drive mode as the adaptation mode. This mode maintains constant tension and synchronous traction response in the multi-wheel drive system, enabling the equipment to maintain uniform and stable forward movement on a highly linear continuous track. This avoids local deviations or structural disturbances caused by drive lag or uneven tension, effectively improving energy efficiency and path accuracy under standard stable operating conditions. When the equipment operates with rapid changes in wheel-rail contact force, uneven structural force distribution, and frequent attitude adjustments without severe drift, the model outputs a variable-stiffness floating support mode to enhance adaptability. This mode provides real-time adjustable control of the support structure stiffness, and upon identifying structural variations... When uneven stress occurs at structural nodes or in areas of foundation settlement, the vertical flexibility of local support units is dynamically reduced or increased. This enables the equipment support system to achieve compliance compensation and impact mitigation on heterogeneous structures, thereby reducing the risk of sudden changes in driving load and improving attitude stability. If the equipment attitude deviates significantly and there is dynamic disturbance of the center of gravity at the location of a sudden change in slope in the simulation sample, the model will output a dynamic slope compensation mode to cope with fine-grained walking control under high slopes or curvature paths. This mode combines changes in path curvature and slope gradient response, adopts an active center of gravity balance adjustment mechanism and differential drive collaborative strategy, and dynamically corrects attitude deviation based on forward path prediction. Through speed difference adjustment between drive wheel sets and real-time heading correction, it ensures the trajectory accuracy and structural attitude stability of the equipment during operation on steep slopes or non-linear segments.

[0043] After determining the mode under multiple working conditions, a mapping pair is formed between each working condition label and its corresponding travel mode type, constructing a structured correspondence, which is then written into the travel scheme database. The database, through a working condition feature indexing mechanism, enables automatic matching and travel strategy invocation under the conditions of the retaining wall structure. This allows the control system to quickly switch between adaptive modes based on the identification results in unknown environments, thereby ensuring the safety, stability, and control accuracy of the gantry crane in complex environments.

[0044] Step S103: Obtain the structural response correlation characteristics between the walking pattern and the construction site environmental data through preprocessing operations.

[0045] Specifically, the structural response correlation characteristics between walking patterns and construction site environmental data are obtained through preprocessing operations. The aim is to construct a nonlinear mapping relationship between construction environment disturbances and construction equipment structural responses, thereby providing high-dimensional and strongly coupled input features for the walking control model and improving the responsiveness and stability of path control.

[0046] In one possible implementation, step S103 further includes: constructing a multidimensional environmental state tensor based on construction site environmental data; inputting the multidimensional environmental state tensor into the equipment structural response simulation model corresponding to each type of walking control model, and outputting a structural response vector through the equipment structural response simulation model; constructing a structural response mapping model that integrates multi-channel convolutional and graph convolutional networks based on the multidimensional environmental state tensor and structural response vector; and extracting features based on the nonlinear propagation relationship between construction environment disturbances and equipment force paths through the structural response mapping model to form structural response correlation features.

[0047] Specifically, a multidimensional environmental state tensor is first constructed based on the environmental data of the construction site. This tensor is used to express the spatial distribution characteristics and environmental disturbance structure of the construction site. Specifically, it includes the spatial offset matrix of the track alignment data at the top of the retaining wall, the gradient map of local elevation changes, the distribution map of slope change rate, the field intensity map of friction coefficient, the sparse matrix of obstacle distribution, and the time series mapping of temperature and humidity disturbances. After all parameters are uniformly aligned and normalized by tensor, tensor input data with temporal continuity and spatial coherence are formed.

[0048] The multidimensional environmental state tensor is input into a predefined equipment structural response simulation model established for each walking mode (such as constant tension synchronous drive mode, variable stiffness floating support mode, dynamic slope compensation mode, etc.). This model is a multi-parameter coupled structural dynamics model that simulates the structural behavior of construction equipment under specific environmental inputs in the corresponding walking mode, including trajectory stability index, center of gravity displacement response, structural internal stress tensor, wheel-rail contact force change and drive coupling deviation, etc., and outputs the corresponding structural response vector.

[0049] Based on the above input-output data pairs, a structure response mapping model that integrates a multi-channel convolutional neural network (Multi-ChannelCNN) and a graph convolutional network (GCN) is further trained. The former is used to extract the high-frequency regions of local perturbations and the non-homogeneous distribution features of the structure in the multidimensional tensor, while the latter is used to capture the propagation state of the force path of the device structure in the topological network, thereby realizing the topological enhancement mapping from irregular perturbation fields to path responses.

[0050] Finally, based on the structural response mapping model, key features in the process of construction environment disturbances propagating to equipment structural response are extracted, including disturbance-sensitive path nodes, critical points of structural force field changes, response nonlinear enhancement regions, and driving instability prediction factors. These features are integrated into a set of structural response correlation features with high expressive power and control driving value, which serve as the input basis for subsequent walking control models to predict trajectory, adjust attitude, and generate synchronization strategies.

[0051] Step S104: Input the structural response correlation characteristics and construction site environmental data into the walking control model, and output the walking route corresponding to the construction equipment based on the walking control model.

[0052] Specifically, the structural response correlation characteristics and construction site environmental data are input into the walking control model as a high-dimensional joint input vector. Based on the comprehensive learning ability of the spatial structure, disturbance source, force mechanism and dynamic response in the construction path, the walking control model combines the topological characteristics of the equipment structure and dynamic constraints to conduct multi-objective comprehensive evaluation in multiple candidate paths, and dynamically balances trajectory stability, structural response limit, attitude controllability and operation safety boundary.

[0053] Subsequently, the model performs linked reasoning on the input environmental conditions and the sensitive areas of the equipment response, outputting the construction equipment's movement route, including a spatial trajectory sequence and a speed control command sequence. The spatial trajectory sequence is used to define the continuous running path of the equipment within the construction area, while the speed control command sequence is used to control the equipment's speed and acceleration / deceleration behavior in different trajectory segments. Ultimately, a multi-parameter control path with attitude stability, path continuity, and robust response is formed to guide the equipment to achieve precise and reliable movement execution in the retaining wall structure environment.

[0054] In one possible implementation, step S104 further includes: generating a first module based on structural response correlation features and construction site environmental data using a location-aware network and topology mapping structure, and generating a second module using a temporal prediction structure and reinforcement learning mechanism; integrating the first module and the second module through a parameter fusion mechanism and a collaborative feedback mechanism to construct a walking control model; outputting a spatial trajectory sequence corresponding to the construction equipment based on the first module; outputting a speed control command sequence corresponding to the construction equipment based on the second module; and constructing a walking route corresponding to the construction equipment based on the spatial trajectory sequence and the speed control command sequence.

[0055] Specifically, the walking control model involved in step S104 not only needs to simultaneously characterize the high-dimensional dynamic interaction between the construction equipment and the retaining wall, but also needs to have spatiotemporal multi-scale response mapping capabilities. The embodiments in this application now deepen the steps, proposing a complex computational method integrating multi-scale graph embedding modeling, disturbance propagation partial derivative coupling mapping, and dynamic programming of variable structures within a non-convex control domain. First, a joint input tensor is constructed. in, Indicates joint feature input, Indicates the first The construction site environmental disturbance tensor of dimensions, such as slope, track curvature, and friction coefficient distribution; Indicates the first The structural response characteristic vector field in the walking mode, such as the principal stress tensor field, the center of gravity disturbance field, and the contact stiffness distribution tensor; Indicates the number of spatial locations on the path or in the environment grid. This represents the total dimension of the input features. A hybrid coupled state tensor is generated using a fourth-order tensor fusion function. : in, Indicates the first - In terms of position, the first to The fusion response value of the feature pair Indicates the first On the first channel, the first to The feature pair fusion weight parameter is used for feature fusion weight allocation. Indicates the first The perturbation tensor at the th The position of Dimensional value, The first tensor representing the structural response tensor Class in The position of Dimensional value, Indicates the first - Fusion bias term, This represents the activation function.

[0056] First module modeling: using path point sets Construct a high-order multi-scale perturbation graph using the nodes of the graph. The edge weight matrix Indicates in The weighted combined structural response at each perturbation scale, including local thermal stress perturbation weights. Steepness of the turning boundary Path tension derivative response weight Defined as: in, Indicates the first nodes under perturbation and The boundary rights between them Represents nodes in the fused tensor - The value of the position, For the first The structural tension partial derivative caused by perturbation and The partial derivative variables between them. This asymmetric graph structure is processed by a multi-scale graph neural network (MSGNN), outputting a stability range function: in, path point Stability score, The parameter set is Multiscale graph neural networks. Point The set of adjacent nodes, This represents the set of edge weights under multi-scale perturbations, used to describe the perturbation propagation capability. An optimal path is constructed using the minimum stability inverse value. in, This represents the optimal trajectory path obtained. This indicates an instability index; the smaller the better. This represents the weight of the balancing term, used to adjust the influence of the path curvature penalty term. This represents the curvature penalty function for the path, used to avoid sharp turns in the path.

[0057] The second module, modeling, defines the device's state vector. Includes speed acceleration Heading angle angular velocity and path offset Construct a variable structure control strategy set: in Indicates the construction equipment in the first Time, Number Local linear approximation control law under the model, Indicates the construction equipment in the first Time, Number Mode bias in the mode, For construction equipment in the first Time, Number Variable structure gain matrix under the mode, Indicates the construction equipment in the first The actual state at any given moment Indicates the construction equipment in the first The reference state at each moment. The perturbation response and mode transition weights are learned using a gated transformer controller (GTC) network. Calculate the global fusion speed control law: in, For the first Time control commands, express The probability of policy selection in the current state is output by the GTC network. This represents the total number of control modes. The following cost function is optimized online using a non-convex constraint optimization method (such as the Alternating Direction Multiplier Method, ADMM): in, Here is the state error weight matrix. Used to control the input regularization matrix and suppress excessive control input. Used to control the input regularization matrix and suppress excessive control input. The penalty coefficient for the jerk term is denoted as . The control input is solved under multiple nonlinear constraints, including path stability boundary conditions, maximum wheel-rail tension, minimum attitude disturbance, and obstacle dynamic boundary conditions. .

[0058] The trajectory sequence output by the first module Speed ​​control sequence output by the second module By integrating a joint state predictor with a segmented feedback adjustment mechanism, a walking route scheme is constructed, which includes a trajectory point sequence, dynamic speed adjustment parameters, attitude correction matrix, and disturbance safety tolerance zone. This scheme guides construction equipment to achieve optimal operating conditions in support retaining wall areas with uneven structures, large thermal disturbances, and irregular path boundaries.

[0059] Step S105: Based on the walking plan route, control the construction equipment to move on the retaining wall.

[0060] Specifically, the spatial trajectory sequence is discretized in time to generate a continuous desired pose target sequence. An error feedback model is constructed by combining real-time sensor data on the equipment's current position, attitude angle, center of gravity changes, and wheel-rail contact state. Based on this error model and the speed control command sequence, control quantities for driving each wheel set or track support unit of the equipment are calculated in real time, including driving speed, direction angle correction, and acceleration / deceleration rhythm. The travel plan route in step S104 ensures that the construction equipment maintains stable operation even under conditions such as structural disturbances, changes in path curvature, or weak local foundation sections. For areas with sudden slope changes, elevation differences, or near boundaries, a combined limit-correction mechanism and attitude stabilization strategy can suppress attitude deviation and prevent lateral deviation at the edges. Furthermore, by identifying sections where path disturbances exceed a threshold in real time and activating safety mode switching logic, including speed reduction, repositioning, attitude correction, or triggering a soft stop, the precise, stable, and continuous movement of the equipment under complex conditions on the retaining wall is ensured.

[0061] Please refer to Figure 2 This illustration shows a schematic diagram of a walking control device for a retaining wall construction equipment according to an embodiment of this application. The device includes an acquisition module 21 and a processing module 22, wherein... The acquisition module 21 is used to acquire construction site environmental data and retaining wall type data in response to the walking control operation of the construction equipment.

[0062] The processing module 22 is used to obtain the walking mode corresponding to the construction equipment from the walking scheme database based on the support retaining wall type data; obtain the structural response correlation characteristics between the walking mode and the construction site environment data through preprocessing operations; input the structural response correlation characteristics and the construction site environment data into the walking control model, and output the walking scheme route corresponding to the construction equipment based on the walking control model; and control the construction equipment to move on the support retaining wall based on the walking scheme route.

[0063] In one possible implementation, the acquisition module 21 is used to acquire construction site environmental data and retaining wall type data, specifically including: acquiring the spatial structure and geometric boundary of the construction area where the retaining wall is located through a three-dimensional photogrammetry device, and acquiring the material structure corresponding to the retaining wall through an ultrasonic testing device; constructing a digital twin model of the construction site based on the spatial structure, geometric boundary, and material structure; acquiring construction site environmental data and retaining wall type data based on the construction site digital twin model, wherein the construction site environmental data includes top track alignment parameter data, local elevation difference distribution data, and slope change rate data; and the retaining wall type data includes retaining wall structure type data, segment connection method data, and wall material composition distribution data.

[0064] In one possible implementation, the processing module 22 is used to obtain the walking mode corresponding to the construction equipment from the walking scheme database based on the retaining wall type data. Specifically, this includes: obtaining the working conditions for the construction equipment to walk on the retaining wall based on the retaining wall type data, including standard stable working conditions, elastic uneven working conditions, and high slope turning working conditions; obtaining the walking mode corresponding to the working conditions from the walking scheme database and using it as the walking mode corresponding to the construction equipment. The walking scheme database is used to store the correspondence between working conditions and walking modes.

[0065] In one possible implementation, the processing module 22 is used to construct a walking scheme database before obtaining the walking mode corresponding to the construction equipment from the walking scheme database based on the retaining wall type data. Specifically, this includes: obtaining historical simulation walking data of the construction equipment under different working conditions; inputting the historical simulation walking data into the walking mode analysis model, and outputting different walking modes corresponding to different working conditions based on the walking mode analysis model. The walking modes include constant tension synchronous drive mode, variable stiffness floating support mode, and dynamic slope compensation mode; constructing the correspondence between different working conditions and different walking modes, and storing the correspondence in the walking scheme database, with one working condition corresponding to one walking mode.

[0066] In one possible implementation, the processing module 22 is used to obtain the structural response correlation features between the walking mode and the construction site environmental data through preprocessing operations. Specifically, this includes: constructing a multidimensional environmental state tensor based on the construction site environmental data; inputting the multidimensional environmental state tensor into the equipment structural response simulation model corresponding to each walking control model, and outputting a structural response vector through the equipment structural response simulation model; constructing a structural response mapping model that integrates multi-channel convolutional and graph convolutional networks based on the multidimensional environmental state tensor and the structural response vector; and extracting features based on the nonlinear propagation relationship between construction environment disturbances and equipment force paths through the structural response mapping model to form structural response correlation features.

[0067] In one possible implementation, the processing module 22 is used to construct a walking control model before inputting structural response correlation features and construction site environmental data into the walking control model and outputting the walking route corresponding to the construction equipment based on the walking control model. Specifically, it includes: generating a first module using a position-aware network and topology mapping structure based on structural response correlation features and construction site environmental data, and generating a second module using a temporal prediction structure and reinforcement learning mechanism; and integrating the first module and the second module through a parameter fusion mechanism and a collaborative feedback mechanism to construct the walking control model.

[0068] In one possible implementation, the processing module 22 is used to input the structural response correlation characteristics and construction site environmental data into the walking control model, and output the walking scheme route corresponding to the construction equipment based on the walking control model. Specifically, it includes: outputting the spatial trajectory sequence corresponding to the construction equipment based on the first module; outputting the speed control command sequence corresponding to the construction equipment based on the second module; and constructing the walking scheme route corresponding to the construction equipment based on the spatial trajectory sequence and the speed control command sequence.

[0069] It should be noted that the above embodiments of the apparatus are only illustrated by the division of the above functional modules. In practical applications, the above functions can be assigned to different functional modules as needed, that is, the internal structure of the device can be divided into different functional modules to complete all or part of the functions described above. In addition, the apparatus and method embodiments provided in the above embodiments belong to the same concept, and the specific implementation process can be found in the method embodiments, which will not be repeated here.

[0070] This application also provides an electronic device. (See reference...) Figure 3 , Figure 3 This is a schematic diagram of the structure of an electronic device provided in an embodiment of this application. The electronic device may include: at least one processor 301, at least one communication bus 302, a user interface 303, at least one network interface 304, and a memory 305.

[0071] The communication bus 302 is used to enable communication between these components.

[0072] The user interface 303 may include a display screen and a camera. Optionally, the user interface 303 may also include a standard wired interface and a wireless interface.

[0073] The network interface 304 may optionally include a standard wired interface or a wireless interface (such as a Wi-Fi interface).

[0074] The processor 301 may include one or more processing cores. The processor 301 connects to various parts of the server using various interfaces and lines, and performs various server functions and processes data by running or executing instructions, programs, code sets, or instruction sets stored in memory 305, and by calling data stored in memory 305. Optionally, the processor 301 may be implemented using at least one hardware form of Digital Signal Processing (DSP), Field-Programmable Gate Array (FPGA), or Programmable Logic Array (PLA). The processor 301 may integrate one or a combination of several of the following: Central Processing Unit (CPU), Graphics Processing Unit (GPU), and modem. The CPU primarily handles the operating system, user interface, and applications; the GPU is responsible for rendering and drawing the content required for display; and the modem handles wireless communication. It is understood that the modem may also not be integrated into the processor 301 and may be implemented as a separate chip.

[0075] The memory 305 may include random access memory (RAM) or read-only memory. Optionally, the memory 305 may include a non-transitory computer-readable storage medium. The memory 305 may be used to store instructions, programs, code, code sets, or instruction sets. The memory 305 may include a program storage area and a data storage area, wherein the program storage area may store instructions for implementing an operating system, instructions for at least one function (such as touch function, sound playback function, image playback function, etc.), instructions for implementing the above-described method embodiments, etc.; the data storage area may store data involved in the above-described method embodiments, etc. Optionally, the memory 305 may also be at least one storage device located remotely from the aforementioned processor 301. (Refer to...) Figure 3 The memory 305, which serves as a computer storage medium, may include an operating system, a network communication module, a user interface module, and a walking control application for the retaining wall construction equipment.

[0076] exist Figure 3In the illustrated electronic device, the user interface 303 is primarily used to provide an input interface for the user and acquire user input data; while the processor 301 can be used to call the walking control application program of the retaining wall construction equipment stored in the memory 305. When executed by one or more processors 301, the electronic device performs one or more of the methods described in the above embodiments. It should be noted that, for the foregoing method embodiments, for the sake of simplicity, they are all described as a series of actions. However, those skilled in the art should understand that this application is not limited to the described order of actions, because according to this application, some steps can be performed in other orders or simultaneously. Secondly, those skilled in the art should also understand that the embodiments described in the specification are all preferred embodiments, and the actions and modules involved are not necessarily essential to this application.

[0077] This application also provides a computer-readable storage medium storing instructions. When executed by one or more processors, these instructions cause an electronic device to perform one or more of the methods described in the above embodiments.

[0078] In the above embodiments, the descriptions of each embodiment have different focuses. For parts not described in detail in a certain embodiment, please refer to the relevant descriptions in other embodiments.

[0079] In the various embodiments provided in this application, it should be understood that the disclosed apparatus can be implemented in other ways. For example, the apparatus embodiments described above are merely illustrative; for instance, the division of units is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be through some service interface; the indirect coupling or communication connection between apparatuses or units may be electrical or other forms.

[0080] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0081] Furthermore, the functional units in the various embodiments of this application can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or as a software functional unit.

[0082] If the integrated unit is implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage device (CMD). Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, or all or part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a memory and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods of the various embodiments of this application. The aforementioned memory includes various media capable of storing program code, such as USB flash drives, portable hard drives, magnetic disks, or optical disks.

[0083] The above description is merely an exemplary embodiment disclosed in this application and should not be construed as limiting the scope of this application. Any equivalent changes and modifications made in accordance with the teachings of this application shall still fall within the scope of this application.

[0084] This application is intended to cover any variations, uses, or adaptations disclosed herein that follow the general principles disclosed herein and include common knowledge or customary technical means in the art that are not described in this application.

Claims

1. A method for controlling the movement of a retaining wall construction device, characterized in that, The method includes: In response to the movement control operation of the construction equipment, acquire construction site environmental data and retaining wall type data; Based on the support retaining wall type data, the walking mode corresponding to the construction equipment is obtained from the walking scheme database; The structural response correlation characteristics between the walking pattern and the construction site environmental data are obtained through preprocessing operations; the structural response correlation characteristics include disturbance-sensitive path nodes, critical points of structural force field changes, response nonlinear enhancement regions, and driving instability prediction factors. The process of inputting the structural response correlation features and the construction site environmental data into a walking control model, and outputting the walking route corresponding to the construction equipment based on the walking control model, specifically includes: generating a first module using a position-aware network and topology mapping structure based on the structural response correlation features and the construction site environmental data, and generating a second module using a temporal prediction structure and reinforcement learning mechanism; integrating the first module and the second module through a parameter fusion mechanism and a collaborative feedback mechanism to construct the walking control model; obtaining the structural response correlation features between the walking mode and the construction site environmental data through preprocessing operations specifically includes: constructing a multidimensional environmental state tensor based on the construction site environmental data; inputting the multidimensional environmental state tensor into the equipment structural response simulation model corresponding to each of the walking control models, and outputting a structural response vector through the equipment structural response simulation model; constructing a structural response mapping model that integrates multi-channel convolutional and graph convolutional networks based on the multidimensional environmental state tensor and the structural response vector; and extracting features based on the nonlinear propagation relationship between construction environment disturbances and equipment force paths through the structural response mapping model to form the structural response correlation features. Based on the described walking route, the construction equipment is controlled to move on the retaining wall.

2. The method according to claim 1, characterized in that, The acquisition of construction site environmental data and retaining wall type data specifically includes: The spatial structure and geometric boundary of the construction area where the retaining wall is located are obtained by three-dimensional photogrammetry equipment, and the material structure of the retaining wall is obtained by ultrasonic testing equipment. Based on the spatial structure, geometric boundaries, and material structure, a digital twin model of the construction site is constructed. Based on the digital twin model of the construction site, the environmental data of the construction site and the data of the retaining wall type are obtained. The environmental data of the construction site includes top track alignment parameter data, local elevation difference distribution data and slope change rate data; the data of the retaining wall type includes retaining wall structure type data, segment connection method data and wall material composition distribution data.

3. The method according to claim 1, characterized in that, The step of obtaining the walking mode corresponding to the construction equipment from the walking scheme database based on the retaining wall type data specifically includes: Based on the data on the type of retaining wall, the working conditions under which the construction equipment moves on the retaining wall are obtained. The working conditions include standard stable working conditions, elastic uneven working conditions, and high slope turning working conditions. In the walking scheme database, the walking mode corresponding to the working condition is obtained and used as the walking mode corresponding to the construction equipment. The walking scheme database is used to store the correspondence between the working condition and the walking mode.

4. The method according to claim 3, characterized in that, Before obtaining the corresponding travel mode of the construction equipment from the travel plan database based on the retaining wall type data, it is necessary to construct the travel plan database, which specifically includes: Obtain historical simulation walking data of the construction equipment under different working conditions; The historical simulation walking data is input into the walking mode analysis model, and different walking modes corresponding to different working conditions are output based on the walking mode analysis model. The walking modes include constant tension synchronous drive mode, variable stiffness floating support mode and dynamic slope compensation mode. A correspondence is established between different operating conditions and different walking modes, and the correspondence is stored in the walking scheme database, with one operating condition corresponding to one walking mode.

5. The method according to claim 1, characterized in that, The step of inputting the structural response correlation characteristics and the construction site environmental data into the walking control model, and outputting the walking route corresponding to the construction equipment based on the walking control model, specifically includes: The first module outputs the spatial trajectory sequence corresponding to the construction equipment; Based on the speed control command sequence corresponding to the construction equipment output by the second module; Based on the spatial trajectory sequence and the speed control command sequence, the walking route corresponding to the construction equipment is constructed.

6. A walking control device for a retaining wall construction equipment, characterized in that, The device includes an acquisition module and a processing module, wherein, The acquisition module is used to acquire construction site environmental data and retaining wall type data in response to the walking control operation of the construction equipment. The processing module is used to obtain the walking mode corresponding to the construction equipment from the walking scheme database based on the support retaining wall type data; obtain the structural response correlation features between the walking mode and the construction site environment data through preprocessing operations; the structural response correlation features include disturbance-sensitive path nodes, critical points of structural force field changes, response nonlinear enhancement zones, and driving instability prediction factors; input the structural response correlation features and the construction site environment data into the walking control model, and output the walking scheme route corresponding to the construction equipment based on the walking control model, specifically including: generating a first module using a position-aware network and topology mapping structure based on the structural response correlation features and the construction site environment data, and generating a second module using a temporal prediction structure and reinforcement learning mechanism; and fusing the first module and the second module through parameter fusion. The walking control model is constructed by integrating the combined mechanism and the collaborative feedback mechanism. The step of obtaining the structural response correlation features between the walking mode and the construction site environmental data through preprocessing operations specifically includes: constructing a multi-dimensional environmental state tensor based on the construction site environmental data; inputting the multi-dimensional environmental state tensor into the equipment structural response simulation model corresponding to each walking control model, and outputting a structural response vector through the equipment structural response simulation model; constructing a structural response mapping model that integrates multi-channel convolutional and graph convolutional networks based on the multi-dimensional environmental state tensor and the structural response vector; extracting features from the nonlinear propagation relationship between construction environment disturbances and equipment force paths through the structural response mapping model to form the structural response correlation features; and controlling the construction equipment to move on the retaining wall based on the walking scheme route.

7. An electronic device, characterized in that, The device includes a processor, a communication bus, a user interface, a network interface, and a memory. The memory is used to store instructions. The user interface and the network interface are used to communicate with other devices. The processor is used to execute the instructions stored in the memory to cause the electronic device to perform the method as described in any one of claims 1 to 5.

8. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores instructions that, when executed, perform the method as described in any one of claims 1 to 5.

Citation Information

Patent Citations

  • Retaining wall building equipment and retaining wall construction method

    CN118007651A

  • Filling production line control method and system based on virtual reality technology

    CN120143617A