Needle beam trolley construction digital management method

Abstract

The invention provides a needle beam trolley construction digital management method, and relates to the technical field of digital management, and the method comprises the steps: employing a laser scanner to scan the wall surface of a to-be-constructed tunnel; acquiring position information of a plurality of working windows of the needle beam trolley; carrying out operation sequence enumeration by taking the maximum number of cooperative work windows as a constraint, and generating a plurality of work window operation sequences; based on the tunnel wall face three-dimensional model, with the requirement for the expected construction quality as the constraint and the requirement for maximizing the construction efficiency as the target, according to the multiple working window operation sequences, casting parameter and vibration parameter optimization is conducted, an optimal construction scheme is output, and digital construction management is conducted on the needle beam trolley. The technical problem of low construction efficiency caused by unreasonable operation sequence and non-uniform resource distribution in the construction process is solved, spatial perception is performed on the to-be-constructed tunnel through three-dimensional modeling, multi-aspect optimization is realized in combination with digital management, and the construction efficiency and precision of the needle beam trolley are improved.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of digital management, in particular to a needle beam trolley construction digital management method. BACKGROUND

[0002] The needle beam trolley is a special equipment for tunnel construction, mainly used for concrete pouring and formwork support in tunnel lining construction, usually composed of needle beam, formwork, walking system, hydraulic system and other parts, and can move and position in the tunnel. However, the wall surface of the tunnel usually has a complex geometric shape, and the construction environment of each tunnel (such as the curvature, inclination, size irregularity of the tunnel, etc.) is different. The traditional construction method usually relies on manual or rough model to plan the operation sequence and resource allocation, which cannot fully consider the specific shape of the tunnel wall surface and the construction conditions, resulting in mismatch between the operation area and the construction equipment, increasing the construction difficulty and reducing the efficiency. In addition, due to the failure to consider the actual construction conditions of different operation windows, unreasonable operation sequence, the equipment is frequently moved or waited between different operation windows, wasting time and resources, and reducing the construction efficiency.

[0003] In summary, the prior art has the technical problem that the unreasonable operation sequence and uneven resource allocation due to the failure to fully consider the specific shape of the tunnel wall surface and the construction conditions further affect the construction efficiency. SUMMARY

[0004] The purpose of the present application is to provide a needle beam trolley construction digital management method to solve the technical problem in the prior art that the unreasonable operation sequence and uneven resource allocation due to the failure to fully consider the specific shape of the tunnel wall surface and the construction conditions further affect the construction efficiency.

[0005] In view of the above problems, the present application provides a needle beam trolley construction digital management method, wherein the needle beam trolley construction digital management method comprises: using a laser scanner to scan the wall surface of the tunnel to be constructed, constructing a three-dimensional model of the tunnel wall surface; obtaining the position information of a plurality of working windows of the needle beam trolley, constructing the working window position distribution; taking the maximum number of collaborative working windows as the constraint, enumerating the operation sequence according to the working window position distribution, generating a plurality of working window operation sequences; based on the three-dimensional model of the tunnel wall surface, taking satisfying the expected construction quality as the constraint, taking maximizing the construction efficiency as the target, according to the plurality of working window operation sequences, respectively optimizing the pouring parameters and the vibrating parameters, outputting the optimal construction scheme, and carrying out digital construction management on the needle beam trolley.

[0006] Optionally, the wall surface of the tunnel to be constructed is scanned using a laser scanner at a plurality of preset scanning positions to obtain a plurality of wall surface point cloud data sets; after point cloud registration and point cloud cleaning are performed on the plurality of wall surface point cloud data sets, grid modeling is performed to generate a three-dimensional model of the tunnel wall surface.

[0007] Optionally, a plurality of work window operation sequences are enumerated according to the work window position distribution, with a preset construction starting point as a reference, a maximum number of collaborative work windows as a simultaneous period construction constraint, and adjacent work windows as a sequential constraint.

[0008] Optionally, a sample data set is retrieved and a concrete quality predictor is trained with the three-dimensional model of the tunnel wall surface as a comparison constraint; a first work window operation sequence is randomly selected from the plurality of work window operation sequences; the concrete quality predictor is used to optimize pouring parameters and vibrating parameters according to the first work window operation sequence, with a desired construction quality as a constraint and a maximum construction efficiency as a target, to output a first optimized construction scheme, and a plurality of optimized construction schemes for the plurality of work window operation sequences are sequentially analyzed and obtained.

[0009] Optionally, a historical needle beam trolley construction record is retrieved and a sample data set is collected with the three-dimensional model of the tunnel wall surface as a comparison constraint and a preset similarity threshold as a condition, wherein the sample data includes a sample work window operation sequence, sample pouring parameters, and sample vibrating parameters; pouring concrete quality parameters under different sample work window operation sequences, sample pouring parameters, and sample vibrating parameters are collected to obtain a sample quality parameter set; a generator and a discriminator of a generative adversarial network are trained and generated using the sample data set and the sample quality parameter set until convergence, to obtain the concrete quality predictor.

[0010] Optionally, a plurality of pouring parameters and a plurality of vibrating parameters are randomly selected within a pouring parameter threshold and a vibrating parameter threshold, and combined to obtain a plurality of construction schemes in combination with the first work window operation sequence; the plurality of construction schemes are evaluated using the concrete quality predictor to output a plurality of quality parameters; the plurality of quality parameters are screened according to the desired construction quality to output a plurality of qualified construction schemes; pouring parameters and vibrating parameters are optimized according to the plurality of qualified construction schemes to output a first optimized construction scheme, with a maximum construction efficiency as a target.

[0011] Optionally, the operation simulation is performed according to the plurality of qualified construction schemes, a plurality of simulated operation durations are output, the qualified construction schemes are regarded as initial solutions, the plurality of qualified construction schemes are arranged in descending order of simulated operation duration to generate an initial solution sequence, the first K solutions of the initial solution sequence are set as optimal solutions, the last J solutions are set as poor solutions, the K optimal solutions are taken as the center, the J poor solutions are equally clustered to obtain K solution sets, wherein J is Q times of K, and Q is an integer greater than 5; in each solution set, the poor solution with the maximum simulated construction duration is set as a poor solution, and K poor solutions are determined; based on the K optimal solutions and the K poor solutions, the poor solutions in the K solution sets are adjusted once according to a preset optimization step length according to the optimization strategy of tending to the optimal solution and avoiding the poor solution, and K updated solution sets are output, wherein if the updated poor solution does not satisfy the pouring parameter threshold or the vibrating parameter threshold, a construction scheme is randomly selected for replacement; the K updated solution sets are identified, if the simulated operation duration of the poor solution in the same solution set is less than the simulated operation duration of the optimal solution, the poor solution is replaced by the optimal solution, and if the simulated operation duration of the poor solution in the same solution set is greater than the simulated operation duration of the poor solution, the poor solution is replaced by the poor solution; iterative optimization is performed until a preset optimization number of times is satisfied, K current solution sets are output, an optimal solution set is determined by evaluation, and the optimal solution of the optimal solution set is set as the first optimized construction scheme, wherein the optimal solution set is a solution set with the smallest sum of simulated operation durations in the K current solution sets.

[0012] Optionally, the simulated operation duration mean of the plurality of poor solutions in each solution set is calculated, and the deviation of the simulated operation duration from the optimal solution and the poor solution is calculated respectively to determine the optimal solution deviation and the poor solution deviation; if the optimal solution deviation is greater than or equal to the poor solution deviation, the optimization strategy is set as the optimization strategy of tending to the optimal solution, the adjustment direction is the optimal solution, and the poor solutions in the K solution sets are adjusted once according to the preset optimization step length; if the optimal solution deviation is less than the poor solution deviation, the optimization strategy is set as the optimization strategy of avoiding the poor solution, the adjustment direction is away from the poor solution, and the poor solutions in the K solution sets are adjusted once according to the preset optimization step length.

[0013] Optionally, the simulated operation duration deviation of the plurality of poor solutions from the optimal solution or the poor solution in each solution set is calculated to obtain a plurality of optimal solution duration deviations and a plurality of poor solution duration deviations, and the optimal solution duration deviation mean and the poor solution duration deviation mean are calculated; if the optimization strategy is the optimization strategy of tending to the optimal solution, the ratio of the optimal solution duration deviation to the optimal solution duration deviation mean is set as an adjustment coefficient to obtain a plurality of adjustment coefficients, the initial optimization step length is adjusted to obtain a plurality of adjusted optimization step lengths as the preset optimization step length; if the optimization strategy is the optimization strategy of avoiding the poor solution, the ratio of the poor solution duration deviation to the poor solution duration deviation mean is set as an adjustment coefficient, the initial optimization step length is adjusted to obtain a plurality of adjusted optimization step lengths as the preset optimization step length.

[0014] Optionally, the scheme with the minimum simulation operation time in the plurality of optimization construction schemes of the plurality of working window operation sequences is set as the optimal construction scheme.

[0015] The technical solutions provided in the present application have at least the following beneficial effects: By using a laser scanner to scan the wall surface of the tunnel to be constructed, a three-dimensional model of the tunnel wall surface is constructed; position information of a plurality of working windows of a needle beam trolley is obtained, and a working window position distribution is constructed; a maximum number of collaborative working windows is taken as a constraint, and operation sequences are enumerated according to the working window position distribution, and a plurality of working window operation sequences are generated; based on the three-dimensional model of the tunnel wall surface, taking satisfying an expected construction quality as a constraint and maximizing construction efficiency as a target, pouring parameters and vibrating parameters are optimized according to the plurality of working window operation sequences, and an optimal construction scheme is output, and the needle beam trolley is subjected to digital construction management. That is, the wall surface of the tunnel to be constructed is spatially perceived by using a laser scanner, a three-dimensional model is generated, the specific shape and structure of the tunnel are truly reflected, the working window position distribution is constructed, the working window position distribution and the maximum number of collaborative working windows are considered, a plurality of working window operation sequences are generated, and pouring parameters and vibrating parameters of each working window operation sequence are optimized in combination with the three-dimensional model of the tunnel wall surface, so that the construction quality is ensured, and the efficiency and precision of the needle beam trolley construction are ensured.

[0016] The above description is only a summary of the technical solutions of the present application. In order to enable the technical means of the present application to be more clearly understood, the present application can be implemented in accordance with the contents of the specification, and in order to enable the above and other purposes, features and advantages of the present application to be more apparent and easy to understand, the following specific embodiments of the present application are described. It should be understood that the contents described in this part are not intended to identify the key or important features of the embodiments of the present application, nor are they used to limit the scope of the present application. Other features of the present application will become apparent from the following description. BRIEF DESCRIPTION OF DRAWINGS

[0017] In order to more clearly illustrate the technical solutions in the present application or the prior art, the following will briefly introduce the drawings needed to be used in the embodiments or the prior art description. Obviously, the drawings in the following description are only exemplary, and other drawings can be obtained by those skilled in the art without creating any inventive labor on the basis of the provided drawings.

[0018] Figure 1 The flowchart of the needle beam trolley construction digital management method of the present application.

[0019] Figure 2 The flowchart of obtaining the first optimization construction scheme in the needle beam trolley construction digital management method of the present application. DETAILED DESCRIPTION

[0020] The application solves the technical problem that the existing technology does not fully consider the specific shape of the tunnel wall surface and the construction conditions, resulting in unreasonable operation sequence and uneven resource allocation, which further affects the construction efficiency. By using a laser scanner to perform spatial perception on the wall surface of the tunnel to be constructed, a three-dimensional model is generated, which truly reflects the specific shape and structure of the tunnel, and the distribution of the working window position is constructed. Considering the working window position distribution and the maximum number of collaborative working windows, a plurality of working window operation sequences are generated. In combination with the three-dimensional model of the tunnel wall surface, the pouring parameters and the vibrating parameters of each working window operation sequence are optimized to ensure the construction quality while improving the efficiency and precision of the needle beam trolley construction.

[0021] Below, the technical solutions in the application will be described clearly and completely with reference to the accompanying drawings. Obviously, the described embodiments are only a part of the embodiments of the application, rather than all the embodiments of the application. It should be understood that the application is not limited by the example embodiments described herein. Based on the embodiments of the application, all other embodiments obtained by those of ordinary skill in the art without creative labor fall within the scope of protection of the application. In addition, it should be noted that, for the convenience of description, only parts related to the application are shown in the drawings, not all.

[0022] Embodiment, please refer to the accompanying Figure 1 The application provides a needle beam trolley construction digital management method, which specifically comprises the following steps: S100: using a laser scanner to scan the wall surface of the tunnel to be constructed, and constructing a three-dimensional model of the tunnel wall surface.

[0023] Further, the S100 of the application comprises: S110: using a laser scanner to scan the wall surface of the tunnel to be constructed at a plurality of preset scanning positions, and obtaining a plurality of wall surface point cloud data sets; S120: after point cloud registration and point cloud cleaning of the plurality of wall surface point cloud data sets, performing grid modeling to generate a three-dimensional model of the tunnel wall surface.

[0024] In particular, the needle beam trolley is a special equipment for tunnel construction, mainly used for concrete pouring and formwork support in tunnel lining construction. It is usually composed of needle beam, formwork, walking system, hydraulic system and other parts, and can move and position in the tunnel to improve construction efficiency and quality. The preset scanning position refers to planning multiple fixed positions of the laser scanner before tunnel construction, and scanning the tunnel wall from these positions to ensure that three-dimensional data of each part of the tunnel is collected. According to the actual structure and shape of the tunnel, multiple preset scanning positions are determined to ensure that scanning from each position can cover each part of the tunnel wall, avoiding dead angles or missed areas. Usually, scanning positions are set at different curvatures and angles of the tunnel to ensure comprehensiveness. For example, for a 500-meter-long tunnel with variable curves, a scanning position is set every 50 meters, and scanning points are set at different heights on both sides of the tunnel.

[0025] At the preset scanning position, the laser scanner starts working to perceive the space of the tunnel to be constructed, records the point cloud data on the tunnel wall point by point through laser beam emission and reception of reflected signals, records the three-dimensional coordinates of the tunnel wall, and calculates the coordinates of each point by measuring the time difference of reflected laser. Each point cloud data contains the three-dimensional coordinates (x, y, z) of each point on the tunnel wall, which can represent the accurate geometry of the tunnel inner wall. Laser scanner is a measuring tool that calculates the position of object surface by emitting and receiving the time difference of reflected laser beam, so as to obtain high-precision three-dimensional spatial point cloud data.

[0026] Point cloud is a collection of multiple points in space obtained by laser scanner, each point representing the coordinates (x, y, z) of a specific position on the surface of the object. In tunnel construction, the wall point cloud dataset refers to the tunnel wall surface information collected by laser scanner from multiple scanning positions, which contains three-dimensional coordinate data of the tunnel wall.

[0027] Point cloud registration is performed on multiple wall point cloud datasets to combine point cloud data from different scanning positions into a unified three-dimensional dataset. Since the coordinate systems of each scanning position are different, registration algorithm is needed to align these data so that they match in the same coordinate system. Point cloud registration is a process of spatial alignment of multiple point cloud datasets from different positions through algorithm. Since the coordinate systems of each scanning position are different, registration can correctly align these datasets in the same coordinate system to ensure data integrity and consistency.

[0028] Point cloud registration typically uses the Iterative Closest Point (ICP) algorithm, which gradually optimizes the matching between point clouds and eventually merges all point cloud data into a unified three-dimensional dataset. The ICP algorithm is a commonly used point cloud registration method for aligning two or more point cloud datasets. The core idea of the algorithm is to find a best spatial transformation (such as translation and rotation) through repeated iterations to maximize the matching of two point clouds. In each iteration, the ICP algorithm optimizes matching by minimizing the distance between point pairs. Each two point cloud datasets are configured, and the points on the first point cloud are paired with the points on the second point cloud with the smallest distance. The nearest neighbor algorithm is used to select matching point pairs. Each time a pair of corresponding points is selected, the Euclidean distance between them is calculated. Once all matching point pairs are found, the ICP algorithm calculates a transformation matrix containing rotation and translation parameters. The goal is to find a best transformation that aligns the points of the target point cloud with the points of the reference point cloud as much as possible. Apply the calculated transformation to the target point cloud, then calculate new matching point pairs. Then calculate a new transformation matrix to optimize the alignment between point clouds. By repeatedly repeating this process, gradually reduce the distance between point clouds until the matching degree reaches a set threshold, or the number of iterations reaches the preset upper limit. When the matching degree meets the preset standard, or when the number of iterations exceeds the set limit, the ICP algorithm stops, and the registration process ends. At this time, the registration of the two point cloud data is completed. For multiple wall point cloud datasets, repeat this step to eventually merge all point cloud data into a unified three-dimensional dataset.

[0029] Point cloud data may contain noise or abnormal points during acquisition (such as incorrect data caused by poor reflection or equipment failure). Point cloud cleaning is to remove these invalid data and retain valid real data. The cleaning process may use filtering algorithms such as removing abnormal points or low-quality data. In point cloud data, there may be some abnormal points (such as irrelevant data caused by device scanning angle problems), which will be removed. Noise points are usually caused by environmental factors (such as dust in the tunnel, light interference) or equipment reasons (such as errors of laser scanners), and the existence of these points will affect the accuracy of point cloud data. Redundant points can be removed by comparing the distances between adjacent points. If the distance between two points is less than a certain preset threshold (usually determined according to the specific construction needs of the tunnel to be constructed), they can be considered redundant and one of them can be removed. Due to scanning angle or object occlusion, there may be holes in the point cloud data. Hole filling can use various methods such as interpolation based on neighboring points.

[0030] Using mesh modeling techniques, a three-dimensional model of the tunnel wall surface is constructed based on the registered and cleaned point cloud data. Mesh modeling converts point cloud data into a mesh model composed of triangular facets, accurately representing the shape of the tunnel wall surface and providing precise three-dimensional visualization data for subsequent construction. Mesh modeling generally includes two steps: mesh generation and mesh optimization. Mesh generation is to create a three-dimensional mesh model according to point cloud data, and mesh optimization is to improve the geometric accuracy and smoothness of the model by adjusting the topology and node position of the mesh.

[0031] The point cloud data obtained by laser scanning can accurately capture the geometric shape of the tunnel wall surface, and the registered and cleaned data will ensure the high precision of the model. Through three-dimensional modeling, the actual shape of the tunnel is reflected, and accurate construction is carried out according to the model, thereby reducing the risk and loss caused by shape error or equipment incompatibility.

[0032] S200: Obtain the position information of a plurality of working windows of the needle beam trolley, and construct the working window position distribution.

[0033] Specifically, the position of each working window on the needle beam trolley is determined by measuring the position of each working window relative to the frame of the needle beam trolley. That is, according to the structural design drawings of the needle beam trolley, the relative fixed position parameters of each working window on the trolley frame are determined (such as the offset distance, height and front and rear position relative to the center line of the needle beam). The needle beam trolley is a special equipment used in tunnel construction, mainly used for concrete pouring and formwork support in tunnel lining construction, usually composed of needle beam, formwork, walking system, hydraulic system, etc., which can move and position inside the tunnel to assist in completing the tasks of tunnel lining, etc. In tunnel construction, the working window usually refers to the specific position coordinates of each working window on the needle beam trolley in the tunnel, and each working window has a clear position coordinate, which determines the area of the trolley operation.

[0034] Once the range of the working window is determined, the exact location of these working windows within the tunnel is obtained, and the location of each working window is usually represented in three-dimensional coordinates. Using positioning sensors arranged in the tunnel, such as laser positioning instruments, inertial measurement units (IMU), etc., the position coordinates (X, Y, Z) and attitude (pitch angle, yaw angle, roll angle) of the needle beam trolley within the tunnel are obtained in real time. After obtaining the position coordinates of all working windows, these positions are integrated through a three-dimensional visualization tool, and a spatial distribution map of the working windows is generated, showing the positions and distribution relationships of all working windows within the tunnel. The working window position distribution refers to the spatial arrangement of multiple working windows within the tunnel. According to the working window spatial distribution, combined with the tunnel construction progress plan, trolley operation capacity and environmental restrictions, the operation time window, operation sequence, trolley movement path and resource allocation of each working window of the trolley are determined. By obtaining the working window position information of the needle beam trolley and constructing the spatial distribution of the working windows, accurate operation area planning can be provided for tunnel construction.

[0035] S300: Enumerate the operation sequence according to the working window position distribution with the maximum number of collaborative working windows as a constraint, and generate multiple working window operation sequences.

[0036] With the preset construction starting point as the reference, the maximum number of collaborative working windows as the simultaneous period construction constraint, and the adjacent working windows as the sequence constraint, the operation path enumeration is performed according to the working window position distribution, and multiple working window operation sequences are generated.

[0037] Specifically, the maximum number of collaborative working windows is the maximum number of working windows that can be worked simultaneously during the construction process, i.e., the maximum number of working windows that the trolley can collaboratively work between in a time period, for example, assuming that the trolley can handle two working windows simultaneously at most in a certain period, then the maximum number of collaborative working windows in this period is 2, this number is a constraint, which is limited by the operation capacity of the trolley, the spatial requirements of the working windows, the specific construction environment of the tunnel (such as tunnel size, curvature, inclination, etc.), and construction requirements and other factors. Specifically, according to the moving speed, working accuracy, operation area size and other factors of the trolley, the maximum simultaneous operation capacity is evaluated; considering the geometric shape, spatial limitations and operation difficulty of the tunnel, a reasonable maximum number of collaborative working windows is determined.

[0038] The purpose of job sequence enumeration is to find the optimal job sequence based on the distribution of work windows, the constraint of the maximum number of collaborative work windows, and the job sequence constraints between adjacent work windows. Job sequence directly affects the moving path of the trolley and the efficiency of the job, therefore, the correct job sequence can maximize the construction efficiency and reduce the invalid movement of the trolley in the tunnel. According to the position distribution of the work windows in the tunnel, combined with the constraint condition of the maximum number of collaborative work windows, different job sequences are generated. By enumerating all possible job sequences, the optimal sequence is selected. Each sequence should follow the sequence constraints of adjacent work windows to ensure that the trolley can move reasonably to the next work window for work. For example, assuming there are 4 work windows in a tunnel construction project, and the maximum number of collaborative work windows is 2. Through enumeration, the following possible job sequences are obtained: Sequence 1: work window 1 and work window 2 work simultaneously, then work window 3 and work window 4 work simultaneously; Sequence 2: work window 1 and work window 3 work simultaneously, then work window 2 and work window 4 work simultaneously; Sequence 3: work window 1 and work window 4 work simultaneously, then work window 2 and work window 3 work simultaneously.

[0039] Job path enumeration is to plan the specific path of the trolley moving from one work window to another after determining the job sequence. The goal of job path enumeration is to generate multiple feasible paths from the preset construction starting point to the work windows, and ensure that the sequence relationship between the paths meets the preset requirements. Job path generation should at least consider the construction starting point, the relative position of the work windows, the sequence constraints, and the maximum number of collaborative work windows. Path planning algorithms such as the shortest path algorithm in graph theory are used. Path optimization in tunnel construction can be achieved by treating the tunnel as a graph model, where the work windows and construction equipment positions are vertices, and the paths between work windows are edges, with the weights of the edges determined by distance, time, or other construction costs. The tunnel is modeled by treating each work window, starting point, and target point in the tunnel as a vertex in the graph. Each path in the tunnel (such as the passage from one work window to another or the moving route of the trolley) is considered as an edge in the graph. According to the actual distance or estimated travel time between work windows, a weight is assigned to each edge in the graph.

[0040] When planning the job path, the distance between adjacent work windows and the moving ability of the trolley must be considered to ensure that the path is as short as possible and reduces the empty running time of the trolley. The preset construction starting point, job sequence, and position distribution of the work windows are used to determine the shortest path or optimal path corresponding to each job sequence through path planning algorithms. The shortest path algorithm in graph theory is used to calculate the shortest path for each job sequence. These algorithms can generate the optimal moving path of the trolley based on the positions of the work windows and the distances between adjacent work windows. The work windows are treated as nodes in the graph, and the adjacent work windows are treated as edges. The shortest path algorithm in graph theory is used to optimize the moving path of the trolley.

[0041] In tunnel construction, each work window can be regarded as a node in the graph. The position of the work window, the starting point of the trolley and other work areas can be regarded as a plurality of nodes in the graph. The nodes are connected by edges, and the weight of the edge is the distance between the work windows or the time required for the trolley to move. Adjacent work windows refer to work windows that are close in space or connected to each other. In the construction process, when the trolley moves from one work window to another, the relative positions between them must be considered. Adjacent work windows can be represented by edges, and the weight of these edges is usually the spatial distance between the work windows or the time required for the trolley to travel. Once all the work windows are regarded as nodes in the graph, and adjacent nodes are connected by edges, according to different work sequences, the shortest path from one work window to another is calculated to determine the moving route of the trolley. Specifically, according to the position information of the work window, a graph is established, the work window is the node, and the connection relationship and relative distance between the work windows are the weight of the edge. According to the characteristics of the graph (for example, the weight of all edges is non-negative), a suitable shortest path algorithm is selected, and the Dijkstra algorithm is usually used to calculate the shortest path from one work window to other work windows.

[0042] According to the generated graph model, a suitable shortest path algorithm is selected to optimize the job path, such as Dijkstra algorithm. First, a graph (including nodes and edges) is set, where each edge has a non-negative weight. A distance table is created to record the shortest distance from the source point to each node. The initial distance of the source point is 0, and the initial distance of other nodes is ∞. A set of nodes with determined shortest paths S is created, which is initially empty. A set of nodes with undetermined shortest paths U is created, which initially contains all nodes. From the node set U, select a node u that is not in the set S and has the minimum distance (i.e. the current shortest path node), add the node u to the node set S, and remove the node u from the node set U. For each neighbor node v of the current node u, if the path through node u to node v is shorter than the original distance, update the value of node v in the distance table. Repeat the above steps until the shortest paths of all nodes are determined, or the node set U is empty. Finally, the distance table stores the shortest paths from the source point to all other nodes. For example, assume that the set graph has nodes A, B, and C; the edge weights are as follows: A to B is 4, A to C is 2, B to C is 1, C to A is 2, B to A is 4, and C to B is 1. The shortest paths from node A to all other nodes need to be found. Initialize the distance of node A to 0, and the distances of nodes B and C to ∞. Starting from node A, update the shortest paths of neighbor nodes B and C to get the distance of node A as 0, the distance of node B as 4, and the distance of node C as 2. Select the shortest path node C, and update the shortest paths of neighbor nodes A and B to get the distance of node A as 0 (no update, because 0 is already the shortest path), and the distance of node B as 3 (A to C is 2 + B to C is 1). The updated distances of node A is 0, node B is 3, and node C is 2, which are the final output shortest paths.

[0043] For each job sequence, use the shortest path algorithm to calculate the shortest path of the trolley from one work window to another. Ensure that the trolley follows the order of adjacent work windows during movement and minimizes the movement distance or time, thereby obtaining multiple work window job sequences. Through job order enumeration and job path enumeration, the construction team can generate multiple possible construction schemes, helping to evaluate the advantages and disadvantages of different construction strategies and select the most suitable scheme to maximize construction efficiency and minimize cost.

[0044] S400: Based on the tunnel wall surface three-dimensional model, with the expected construction quality as a constraint and the construction efficiency as a target, the pouring parameters and the vibrating parameters are optimized according to the multiple work window job sequences, and the optimal construction scheme is output for digital construction management of the needle beam trolley.

[0045] Further, the S400 of the present application comprises: S410: retrieve a sample data set with the tunnel wall surface three-dimensional model as a comparison constraint, and train a concrete quality predictor; S420: randomly select a first working window operation sequence from the plurality of working window operation sequences; S430: use the concrete quality predictor to optimize pouring parameters and vibrating parameters according to the first working window operation sequence, with the constraint of meeting the expected construction quality and the goal of maximizing construction efficiency, output a first optimized construction scheme, and sequentially analyze a plurality of optimized construction schemes of the plurality of working window operation sequences.

[0046] S411: retrieve historical needle beam trolley construction records with the tunnel wall surface three-dimensional model as a comparison constraint and with the condition of meeting a preset similarity threshold, collect a sample data set, wherein the sample data includes a sample working window operation sequence, sample pouring parameters, and sample vibrating parameters; S412: collect pouring concrete quality parameters under different sample working window operation sequences, sample pouring parameters, and sample vibrating parameters, and obtain a sample quality parameter set; S413: train a generator and a discriminator of a generative adversarial network using the sample data set and the sample quality parameter set until convergence, and obtain the concrete quality predictor.

[0047] Specifically, the comparison constraint refers to the condition that the current construction tunnel wall surface three-dimensional model needs to meet when retrieving historical construction data. The similarity threshold is a standard value for judging whether the current tunnel wall surface is similar enough to the historical data. By setting the threshold, the most matching historical construction record of the current tunnel can be filtered out. Under the comparison constraint condition, the past needle beam trolley construction records are retrieved, which contain the operation path, operation sequence, and corresponding construction parameters (such as pouring and vibrating parameters) used in the historical construction process. The historical needle beam trolley construction records matching the tunnel wall surface three-dimensional model are extracted from the records to obtain a sample data set, including a sample working window operation sequence, sample pouring parameters, and sample vibrating parameters.

[0048] The sample working window operation sequence records the operation sequence of the trolley between each working window under different construction scenarios; the sample pouring parameters record the related parameters used in the concrete pouring process, such as pouring speed and pouring depth; and the sample vibrating parameters record the parameters used in the vibrating process, such as vibrating frequency and vibrating time.

[0049] At the same time, according to different sample working window operation sequences, sample pouring parameters, and sample vibrating parameters, corresponding pouring concrete quality parameters are collected, i.e., the quality parameters (such as compressive strength, density, uniformity, etc.) of the concrete under different operation sequences and parameter configurations, which reflect the construction quality under various conditions, forming a sample quality parameter set including concrete quality parameters such as compressive strength, density, and durability.

[0050] Using the collected sample dataset and sample quality parameter set, a generative adversarial network (GAN) is trained. During training, the generator generates concrete quality predictions based on the input sample data (such as the operation sequence and parameters), while the discriminator determines whether the generated quality data meets the quality standards of the 3D tunnel wall model. Through adversarial training, the generator and discriminator continuously adjust their parameters, ultimately generating a predictor that can effectively predict concrete quality. The training process continues until the model's loss function converges, indicating that the generator can accurately predict concrete quality parameters. Training is then terminated, resulting in a concrete quality predictor.

[0051] A generative adversarial network (GAN) is a deep learning model consisting of a generator and a discriminator. The generator generates data, while the discriminator determines the authenticity of the data. Through adversarial training, the generator and discriminator gradually improve, ultimately generating high-quality sample data. The generator generates fake data based on input data, while the discriminator determines whether the input data is real data. During training, the two compete and continuously improve, ultimately producing high-quality output.

[0052] The pouring and vibration parameter thresholds are determined based on the actual construction environment, concrete material properties, and construction machinery performance. For each work window sequence, several pouring and vibration parameter thresholds are randomly obtained within these thresholds. Combined with the work window sequence, multiple construction plans are generated. Using a concrete quality predictor, multiple plans are evaluated to select those that meet the expected construction quality. The pouring and vibration parameters are then optimized to determine the optimal construction plan for each work window sequence. This results in multiple optimized construction plans, ultimately outputting the optimal construction plan for digital construction management of the needle beam trolley.

[0053] By optimizing pouring and vibration parameters, we can improve construction efficiency and reduce unnecessary construction time and resource waste while ensuring concrete quality. The Concrete Quality Predictor accurately predicts concrete quality under different operation sequences and parameters based on historical data and actual construction conditions, thus avoiding quality issues caused by improper parameter configuration.

[0054] Further, as attached Figure 2 As shown, this application also includes the following steps: S431: Within the pouring parameter threshold and the vibrating parameter threshold, a number of pouring parameters and a number of vibrating parameters are randomly selected, and a number of construction schemes are obtained by combining the first working window operation sequence; S432: The concrete quality predictor is used to evaluate the number of construction schemes respectively, and a number of quality parameters are output; S433: According to the expected construction quality, the number of quality parameters are screened respectively, and a plurality of qualified construction schemes are output; S434: Taking maximizing construction efficiency as the target, the pouring parameters and the vibrating parameters are optimized according to the plurality of qualified construction schemes, and a first optimized construction scheme is output.

[0055] Specifically, a first operation sequence is randomly selected from a plurality of preset working window operation sequences. In order to ensure the effect of pouring and vibrating operations, the pouring parameter threshold and the vibrating parameter threshold are determined according to the actual construction environment, the concrete material characteristics and the construction machinery performance. The pouring parameter threshold is used to define the range limit of each parameter in the pouring operation, including pouring speed, pressure, etc., which determines the fluidity and stability of the concrete in the pouring process. The vibrating parameter threshold is the range limit of each parameter in the vibrating operation, which usually involves vibrating frequency, vibrating time, etc., and affects the compactness and strength of the concrete. Within the set threshold range, a plurality of pouring parameters and vibrating parameters are randomly selected, and these parameters are combined with the selected working window operation sequence to obtain a plurality of different construction schemes, each of which corresponds to a specific parameter configuration. For example, assuming that the threshold range of pouring rate is 3-5 m³ / h, and the threshold range of vibrating frequency is 1000-1500 times / min, 3 pouring rates (such as 3.5 m³ / h, 4.0 m³ / h, 4.5 m³ / h) and 3 vibrating frequencies (such as 1050 times / min, 1200 times / min, 1350 times / min) are randomly selected and combined into a plurality of construction schemes.

[0056] The concrete quality predictor is used to input the parameter configurations corresponding to the plurality of construction schemes into the concrete quality predictor to evaluate the plurality of construction schemes. The predictor predicts the concrete quality (such as compressive strength, density, etc.) under each construction scheme by inputting the working window operation sequence, pouring parameters, vibrating parameters, etc. For example, through the evaluation of a construction scheme by the predictor, the predicted quality parameters are strength: 35 MPa, uniformity: 0.98 (the closer to 1, the better the quality), and durability: 70 (meets the requirements).

[0057] According to the operation requirements of the tunnel to be constructed, the expected construction quality is determined, including strength, density, uniformity, etc. According to the expected construction quality, a plurality of quality parameters are screened, and a plurality of schemes meeting the expected construction quality are selected as a plurality of qualified construction schemes, that is, each quality parameter of each construction scheme meets the expected construction quality parameter. If one parameter does not meet the requirement, it is proved that the scheme is unqualified and needs to be eliminated. The plurality of qualified construction schemes are further optimized to maximize the construction efficiency, and the pouring and vibrating parameters are adjusted to improve the construction efficiency on the premise of ensuring the quality of the concrete. For example, when the quality parameter of a certain construction scheme is lower than the expected value (such as strength of 28MPa and uniformity of 0.94), these schemes will be excluded. The schemes meeting the standard (such as strength of 35MPa, uniformity of 0.98, and durability of 70) will be retained.

[0058] After the pouring parameters and the vibrating parameters based on the plurality of qualified construction schemes are optimized, a first optimized construction scheme is output, which maximizes the construction efficiency and reduces resource waste and time delay on the basis of meeting the quality standard. For example, assuming that the pouring rate of a certain qualified construction scheme is 4.0m³ / h and the vibrating frequency is 1200 times / min, the parameters are adjusted by the algorithm to obtain a new optimized scheme (for example, pouring rate of 4.2m³ / h and vibrating frequency of 1150 times / min), which improves the construction efficiency on the premise of ensuring the quality of the concrete. By optimizing the pouring and vibrating parameters, the construction efficiency is improved on the basis of ensuring the quality of the concrete, the construction time is reduced, and the prediction result of the concrete quality predictor is used to ensure that each construction scheme meets the quality standard and avoid quality problems caused by improper operation sequence or parameter configuration.

[0059] Further, the present application also includes: The scheme with the minimum simulated operation time in the plurality of optimized construction schemes of the plurality of working window operation sequences is set as the optimal construction scheme.

[0060] Specifically, the plurality of optimized construction schemes are a series of construction schemes obtained by optimizing different work window operation sequences, each scheme is based on different operation sequence, pouring parameter and vibration parameter optimization results, has different parameter settings (pouring, vibration, etc.) and corresponding operation time. Simulate the plurality of optimized construction schemes corresponding to the plurality of work window operation sequences, calculate the time required to complete the construction task, including work window operation time, trolley moving time, interval time between work windows, etc. The work window operation time is the time required for pouring and vibration operation of each work window, which is calculated by the parameters in the optimization process (such as pouring pressure, vibration frequency); the trolley moving time is the time for the trolley to move in the tunnel, which depends on the geometric shape of the tunnel, the driving speed of the trolley, etc.; the interval time between work windows is the switching time between different work windows, including equipment adjustment, material transportation, etc. By weighting calculation of each time factor, the simulation operation time of each construction scheme is obtained.

[0061] The simulation operation time is estimated by considering the operation requirements of each work window, trolley moving time, pouring and vibration time, etc. Among the plurality of optimized construction schemes, by comparing the simulation operation time of each scheme, the scheme with the shortest operation time is selected as the optimal scheme, which means that the construction task can be completed in the shortest time under the premise of ensuring quality, thereby improving construction efficiency and reducing cost. For example, assuming that there are three optimized construction schemes, the simulation operation time of each scheme is: scheme 1: 8 hours, scheme 2: 6.5 hours, scheme 3: 7.2 hours, the simulation operation time of scheme 2 is the shortest, so it is selected as the optimal construction scheme. According to the selected scheme with the minimum simulation operation time, the final construction plan is generated. By selecting the construction scheme with the shortest operation time, the construction efficiency can be significantly improved, the construction time can be reduced, and the project cost can be reduced.

[0062] Further, the step S434 of the application further includes the following steps: According to the plurality of qualified construction schemes, operation simulation is performed, and a plurality of simulation operation durations are output; the qualified construction schemes are regarded as initial solutions, the plurality of qualified construction schemes are arranged in descending order of simulation operation duration to generate an initial solution sequence; the first K solutions of the initial solution sequence are selected as optimal solutions, the last J solutions are selected as poor solutions, and the K optimal solutions are taken as the center to perform equivalent clustering on the J poor solutions to obtain K solution sets, wherein J is Q times of K, and Q is an integer greater than 5; in each solution set, the poor solution with the maximum simulation construction duration is selected as a poor solution, and K poor solutions are determined; based on the K optimal solutions and the K poor solutions, the poor solutions in the K solution sets are adjusted once according to a preset optimization step length according to the optimization strategy, and K updated solution sets are output, wherein if the updated poor solution does not satisfy the pouring parameter threshold or the vibrating parameter threshold, a construction scheme is randomly selected for replacement; the K updated solution sets are identified, if the simulation operation duration of the poor solution in the same solution set is less than the simulation operation duration of the optimal solution, the poor solution is replaced by the optimal solution, and if the simulation operation duration of the poor solution in the same solution set is greater than the simulation operation duration of the poor solution, the poor solution is replaced by the poor solution; iterative optimization is performed until a preset optimization number is satisfied, K current solution sets are output, an optimal solution set is determined, and the optimal solution of the optimal solution set is selected as the first optimized construction scheme, wherein the optimal solution set is the solution set with the smallest simulation operation duration sum in the K current solution sets.

[0063] Specifically, the plurality of qualified construction schemes are simulated, and the plurality of qualified construction schemes are input into the tunnel wall three-dimensional model for construction operation simulation, that is, the specific parameters (such as operation sequence, pouring parameter and vibrating parameter) of each qualified construction scheme are input into the tunnel wall three-dimensional model, the simulation result of each scheme is obtained, and the corresponding simulation operation duration is determined accordingly. That is, after simulation, the simulation operation duration of each qualified construction scheme is output. Construction simulation usually involves simulating the entire construction process, and the time unit can be hours, minutes, etc. The simulation result of each scheme will give the specific completion time of each construction task, so as to obtain the total operation duration. The simulation operation duration is estimated by considering the operation requirements of each work window, the trolley moving time, the pouring and vibrating time, etc. to estimate the total duration of completing the construction. As explained above, the time required to complete the construction task is calculated, including work window operation time, trolley moving time, work window interval time, etc., to obtain a plurality of simulation operation durations.

[0064] Exemplarily, assume there are three qualified construction schemes, A, B and C, involving different pouring and vibrating parameters: Scheme A: pouring speed is 1.5 m³ / h, vibrating time is 12 minutes, transportation time is 10 minutes, and the estimated operation time is 60 minutes; Scheme B: pouring speed is 2.0 m³ / h, vibrating time is 15 minutes, transportation time is 8 minutes, and the estimated operation time is 55 minutes; Scheme C: pouring speed is 1.8 m³ / h, vibrating time is 10 minutes, transportation time is 12 minutes, and the estimated operation time is 58 minutes. Through simulation, the simulated operation time of Scheme A is 62 minutes, the simulated operation time of Scheme B is 54 minutes, and the simulated operation time of Scheme C is 60 minutes.

[0065] According to the plurality of qualified construction schemes, the initial solution sequence is generated in ascending order of simulated operation time, which helps to identify which schemes are most advantageous in construction efficiency. The initial solution sequence is generated by arranging the plurality of qualified construction schemes in ascending order of simulated operation time. The first K solutions of the initial solution sequence are set as superior solutions, and the last J solutions are set as inferior solutions. K+J is the total number of schemes in the initial solution sequence. The K superior solutions are taken as the center to perform equal clustering on the J inferior solutions. The ratio of K and J is set according to Q value, and Q is usually greater than 5, and J is Q times of K. In each solution set, the inferior solution with the longest simulated operation time is selected as the difference solution. For example, assume there are 14 solutions, and Q is 6, then the number of K is 2, and the number of J is 12, that is, the first 2 solutions are superior solutions, and the last 12 solutions are inferior solutions.

[0066] The inferior solutions are clustered to ensure that the solutions in each solution set have similarity in simulated operation time or other criteria. The clustering algorithm (such as K-means clustering) is used to group the inferior solutions to ensure that the solutions in each solution set are similar. In each inferior solution set, the difference in operation time or other parameters between the schemes is small, so they can be adjusted together for optimization. The inferior solutions are clustered into solution sets consistent with the number of superior solutions, resulting in K solution sets.

[0067] In each solution set, the inferior solution with the longest simulated construction time is selected as the difference solution, resulting in K difference solutions. The difference solution is a solution that needs special attention in the optimization process, representing the least ideal scheme, and each solution set has one difference solution. For example, if the inferior solution times of a solution set are [60, 62, 63, 65], then the solution with the maximum time of 65 hours is the difference solution.

[0068] According to the K optimal solutions and K poor solutions, a strategy of approaching the optimal solution and avoiding the poor solution is adopted, that is, moving away from the poor solution and approaching the optimal solution. According to the preset optimization step, all the poor solutions in the K solution sets are adjusted once, and are moved towards the direction of approaching the corresponding optimal solution in each solution set and moving away from the corresponding poor solution in each solution set, to obtain K updated solution sets. If the updated poor solution does not satisfy the preset pouring parameter threshold or the preset vibrating parameter threshold, the poor solution is randomly replaced by another construction scheme. That is, it is determined whether the updated construction parameter falls within the preset pouring parameter threshold or the preset vibrating parameter threshold, and if the updated value exceeds the range, a new construction scheme is randomly selected from the multiple qualified construction schemes (i.e., the initial solution sequence) to replace the poor solution, so as to prevent the illegal parameter from participating in the optimization. For example, assuming that the preset optimization step is 0.5, if the simulation operation time of the current poor solution is 65 hours and the simulation operation time of the optimal solution is 40 hours, the adjusted poor solution time is: 65-(0.5*(65-40))=65+12.5=52.5 hours (trend optimization strategy).

[0069] The K updated solution sets are traversed to determine the optimal solution and the poor solution in each solution set, and the specific parameters (such as the operation sequence, the pouring parameter and the vibrating parameter) of each qualified construction scheme are input into the tunnel wall three-dimensional model to obtain a simulation result and determine the corresponding simulation operation time. If the simulation operation time of a poor solution is less than the simulation operation time of the optimal solution in the solution set, it indicates that the performance of the poor solution is better than that of the original optimal solution after the current round of optimization, and the poor solution is used to replace the optimal solution. If the simulation operation time of a poor solution is greater than the simulation operation time of the poor solution in the solution set, it indicates that the performance of the poor solution is worse after the current round of adjustment, and even worse than the original worst solution, and the poor solution is used to replace the poor solution.

[0070] The above process is repeated for iterative optimization until the preset optimization number is met, the optimization is stopped, and the K current solution sets at this time are output. The preset optimization number refers to the maximum number of iterations allowed in the iterative optimization algorithm, which is usually set before the algorithm starts to execute and is used to control the termination condition of the algorithm. Different algorithms have different convergence speeds. The preset optimization number needs to consider the convergence of the algorithm to ensure that the algorithm can converge to the optimal solution within a limited number of iterations. The determination of the preset optimization number usually needs to be balanced according to the characteristics of the specific problem and the requirements of the actual application. If the preset optimization number is too small, the algorithm may not be able to find the optimal solution; if the preset optimization number is too large, the algorithm may consume too much computing resource and reduce the efficiency. Therefore, a suitable preset optimization number should be able to ensure the performance of the algorithm while improving the utilization of computing resources.

[0071] According to the K current solution sets, an optimal solution set is evaluated. That is, the simulation operation time length sum of the K current solution sets is calculated, the solution set with the minimum simulation operation time length sum is selected as the optimal solution set. An optimal solution is selected from the optimal solution set, that is, a scheme that minimizes the simulation operation time length is selected as the first optimized construction scheme. The first optimized construction scheme is the final best scheme selected through iterative optimization, and is based on the optimal solution in the optimal solution set, representing the best scheme that can be executed in actual construction.

[0072] The multiple work window operation sequences are analyzed in sequence to determine the optimized construction scheme of each work window operation sequence, and multiple optimized construction schemes are obtained. Through the multiple work window operation sequences, the above pouring parameters and vibration parameters are optimized to obtain the optimal construction scheme. The optimized optimal construction scheme is transmitted to the needle beam trolley to realize accurate control of the equipment, including parameter adjustment of pouring and vibration operations, real-time monitoring of construction progress, etc. In the construction process, the execution of each parameter is monitored in real time and fed back to the control center, and the equipment parameters are adjusted according to the real-time data fed back to ensure that the operation process always operates within the optimal scheme. By optimizing the pouring parameters and the vibration parameters, the construction efficiency can be greatly improved under the premise of ensuring the quality of the concrete.

[0073] Further, the application further includes the following steps: The average simulation operation time length of the multiple inferior solutions in each solution set is calculated, and the deviation of the simulation operation time length from the optimal solution and the inferior solution is calculated respectively to determine the optimal solution deviation and the inferior solution deviation. If the optimal solution deviation is greater than or equal to the inferior solution deviation, the optimization strategy is set to the optimal strategy, and the inferior solution is adjusted according to the preset optimization step in the direction of the optimal solution. If the optimal solution deviation is less than the inferior solution deviation, the optimization strategy is set to the inferior strategy, and the inferior solution is adjusted according to the preset optimization step in the direction away from the inferior solution.

[0074] Specifically, the average simulation operation time length of the multiple inferior solutions in each solution set is calculated, and the deviation of the simulation operation time length from the optimal solution is calculated as the optimal solution deviation. The deviation of the simulation operation time length from the inferior solution is calculated as the inferior solution deviation. If the optimal solution deviation is greater than or equal to the inferior solution deviation, it means that the current inferior solution is closer to the inferior solution and farther from the optimal solution, and optimization is needed through the optimal strategy, that is, the inferior solution is adjusted in the direction of the optimal solution. The inferior solution in the K solution sets is adjusted once according to the determined preset optimization step. That is, the new inferior solution parameter is equal to the original inferior solution parameter plus the product of the preset optimization step and the optimal solution deviation. Once adjustment refers to one round of update of the current inferior solution parameter according to the current strategy in one iteration process.

[0075] Conversely, if the optimal solution deviation is less than the poor solution deviation, it indicates that the current poor solution is closer to the optimal solution, the optimization strategy is set to the poor solution avoidance strategy, and the adjustment direction is away from the poor solution. According to the preset optimization step, the poor solution in the K solution set is adjusted once. The optimization strategy is dynamically set according to the deviation of the poor solution from the optimal solution and the poor solution, and the poor solution is effectively adjusted, which helps to improve the efficiency and accuracy of the optimization process and find the optimal solution faster. The preset optimization step corresponding to the optimal strategy and the poor solution avoidance strategy is different, which is determined according to the corresponding strategy and will be described in detail in the subsequent steps, and will not be described here.

[0076] Further, the present application further comprises the following steps: The simulation operation time deviation of each poor solution in each solution set from the optimal solution or the poor solution is calculated respectively to obtain a plurality of optimal solution time deviation and a plurality of poor solution time deviation, and the mean of the optimal solution time deviation and the mean of the poor solution time deviation are calculated. If the optimization strategy is the optimal strategy, the ratio of the optimal solution time deviation to the mean of the optimal solution time deviation is set as the adjustment coefficient, the initial optimization step is adjusted to obtain a plurality of adjusted optimization steps as the preset optimization step. If the optimization strategy is the poor solution avoidance strategy, the ratio of the poor solution time deviation to the mean of the poor solution time deviation is set as the adjustment coefficient, the initial optimization step is adjusted to obtain a plurality of adjusted optimization steps as the preset optimization step.

[0077] Specifically, each solution set includes an optimal solution, a poor solution and a plurality of poor solutions. The simulation operation time deviation of each poor solution in each solution set from the optimal solution (the simulation operation time of the construction scheme is the shortest) is calculated, including the simulation operation time deviation of each poor solution from the optimal solution corresponding to the construction scheme, to obtain a plurality of optimal solution time deviation. The simulation operation time deviation of each poor solution in each solution set from the poor solution (the simulation operation time of the construction scheme is the longest) is calculated to obtain a plurality of poor solution time deviation. The mean of the plurality of optimal solution time deviation is obtained, and the mean of the plurality of poor solution time deviation is obtained.

[0078] The initial optimization step is a parameter set in the iterative optimization algorithm, which determines the adjustment amplitude of the solution in each iteration. Specifically, it is the step size of the algorithm for modifying or adjusting the solution when starting the optimization process. The initial optimization step is usually determined based on experience or by trial, and has an important influence on the efficiency and convergence speed of the optimization process.

[0079] If the optimization strategy is a superior solution strategy, that is, approaching the superior solution, the current inferior solution is gradually adjusted to the superior solution, thereby improving the efficiency of the solution set as a whole. By calculating the ratio of the time deviation of multiple superior solutions to the average time deviation of superior solutions, multiple adjustment coefficients are obtained, which are used to adjust the initial optimization step to obtain multiple adjusted optimization steps as the preset optimization compensation. The larger the deviation, the larger the corresponding adjustment coefficient, and therefore the larger the preset optimization step obtained by multiplying the initial optimization compensation. If the deviation is large, it indicates that the inferior solution is far from the target, and a larger step adjustment is needed, that is, the adjustment amplitude is larger. If the deviation is small, fine adjustment is needed, that is, the adjustment amplitude is smaller.

[0080] If the optimization strategy is an inferior solution strategy, that is, away from the inferior solution, the current inferior solution is gradually adjusted away from the inferior solution, thereby improving the efficiency of the solution set as a whole. Similarly, by calculating the ratio of the time deviation of multiple inferior solutions to the average time deviation of inferior solutions, multiple adjustment coefficients are obtained, which are used to adjust the initial optimization step to obtain multiple adjusted optimization steps as the preset optimization compensation.

[0081] The optimization step is dynamically adjusted according to the deviation of the inferior solution from the superior solution or the inferior solution. The larger the deviation, the larger the adjustment amplitude, which helps to improve the optimization efficiency. At the same time, the smaller the deviation, the smaller the adjustment amplitude, which helps to improve the optimization accuracy, quickly find the optimal solution, and improve the intelligent level of construction management.

[0082] In summary, the needle beam trolley construction digital management method provided by the present application has the following beneficial effects: By using a laser scanner to scan the wall surface of the tunnel to be constructed, a three-dimensional model of the tunnel wall surface is constructed. The position information of a plurality of working windows of the needle beam trolley is obtained, and the working window position distribution is constructed. The maximum number of collaborative working windows is taken as a constraint, the working order enumeration is performed according to the working window position distribution, and a plurality of working window operation sequences are generated. Based on the three-dimensional model of the tunnel wall surface, the expected construction quality is taken as a constraint, the maximum construction efficiency is taken as a target, the pouring parameters and the vibrating parameters are optimized according to the plurality of working window operation sequences, and the optimal construction scheme is output, so as to realize the digital construction management of the needle beam trolley. That is, the laser scanner is used to perform spatial perception on the wall surface of the tunnel to be constructed, a three-dimensional model is generated, the specific shape and structure of the tunnel are truly reflected, the working window position distribution is constructed, the working window position distribution and the maximum number of collaborative working windows are considered, a plurality of working window operation sequences are generated, and the pouring parameters and the vibrating parameters of each working window operation sequence are optimized in combination with the three-dimensional model of the tunnel wall surface, so as to ensure the construction quality while improving the efficiency and precision of the needle beam trolley construction.

[0083] The above description of disclosed embodiments enables one of ordinary skill in the art to make or use the application. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the generic principles defined herein can be applied to other embodiments without departing from the spirit or scope of the application. Therefore, the present application is not intended to be limited to the embodiments shown herein but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.

[0084] Obviously, many modifications and changes can be made to the application without departing from the spirit and scope of the application. It is understood that the application is not to be limited to the particular embodiments disclosed, but it is intended to cover all modifications which are within the scope of the application as defined by the language of the claims.

Claims

1. A digital management method for needle beam trolley construction, characterized in that: include: Use a laser scanner to scan the wall of the tunnel to be constructed and build a three-dimensional model of the tunnel wall; Obtain the position information of several working windows of the needle beam trolley and construct the working window position distribution; Taking the maximum number of collaborative working windows as a constraint, enumerate the work order according to the work window position distribution to generate multiple work window work sequences; Based on the three-dimensional model of the tunnel wall, with meeting the expected construction quality as a constraint and maximizing construction efficiency as the goal, the pouring parameters and vibration parameters are optimized according to the operation sequences of the multiple working windows, the optimal construction plan is output, and digital construction management of the needle beam trolley is carried out.

2. A digital management method for needle beam trolley construction according to claim 1, characterized in that: Use a laser scanner to scan the wall of the tunnel to be constructed and build a 3D model of the tunnel wall, including: At multiple preset scanning positions, a laser scanner is used to scan the wall of the tunnel to be constructed, obtaining multiple wall point cloud datasets. After performing point cloud registration and point cloud cleaning on the multiple wall point cloud data sets, mesh modeling is performed to generate a three-dimensional model of the tunnel wall.

3. A digital management method for needle beam trolley construction according to claim 1, characterized in that: Taking the preset construction starting point as the benchmark, the maximum number of collaborative work windows as the construction constraint during the same period, and the adjacent work windows as the order constraint, the operation path is enumerated according to the work window position distribution to generate multiple work window operation sequences.

4. A digital management method for needle beam trolley construction according to claim 1, characterized in that: Based on the three-dimensional model of the tunnel wall, with the expected construction quality as a constraint and the goal of maximizing construction efficiency, the pouring parameters and vibration parameters are optimized according to the multiple work window operation sequences, including: Using the three-dimensional model of the tunnel wall as a comparison constraint, retrieving a sample data set and training a concrete quality predictor; Randomly selecting a first working window operation sequence from the plurality of working window operation sequences; The concrete quality predictor is used to optimize the pouring parameters and vibration parameters according to the first working window operation sequence, with meeting the expected construction quality as a constraint and maximizing construction efficiency as a goal. A first optimized construction plan is output, and multiple optimized construction plans of the multiple working window operation sequences are analyzed in sequence to obtain.

5. A digital management method for needle beam trolley construction according to claim 4, characterized in that: Using the three-dimensional model of the tunnel wall as a comparison constraint, retrieving a sample data set and training a concrete quality predictor include: Using the three-dimensional model of the tunnel wall as a comparison constraint and satisfying a preset similarity threshold as a condition, historical needle beam trolley construction records are retrieved to collect a sample data set, wherein the sample data includes a sample working window operation sequence, sample pouring parameters, and sample vibration parameters; Collecting the poured concrete quality parameters under different sample working window operation sequences, sample pouring parameters and sample vibration parameters to obtain a sample quality parameter set; The sample data set and the sample quality parameter set are used to train a generator and a discriminator of a generative adversarial network until convergence, thereby obtaining the concrete quality predictor.

6. A digital management method for needle beam trolley construction according to claim 4, characterized in that: Utilizing the concrete quality predictor, with satisfying expected construction quality as a constraint and maximizing construction efficiency as a goal, optimizing pouring parameters and vibration parameters according to the first working window operation sequence, and outputting a first optimized construction plan, including: Randomly select a number of pouring parameters and a number of vibration parameters within a pouring parameter threshold and a vibration parameter threshold, and combine them with the first working window operation sequence to obtain a number of construction plans; Using the concrete quality predictor, the plurality of construction plans are evaluated respectively, and a plurality of quality parameters are output; Screening the plurality of quality parameters according to the expected construction quality and outputting a plurality of qualified construction plans; With the goal of maximizing construction efficiency, the pouring parameters and vibration parameters are optimized according to the multiple qualified construction plans, and a first optimized construction plan is output.

7. A digital management method for needle beam trolley construction according to claim 6, characterized in that: With the goal of maximizing construction efficiency, optimizing the pouring parameters and vibration parameters based on the multiple qualified construction plans is performed, and a first optimized construction plan is output, including: Performing operation simulation according to the plurality of qualified construction plans and outputting a plurality of simulated operation durations; The qualified construction plans are regarded as initial solutions, and the qualified construction plans are arranged in ascending order according to the simulation operation duration to generate an initial solution sequence; The first K solutions of the initial solution sequence are selected as optimal solutions, and the last J solutions are selected as inferior solutions. The J inferior solutions are clustered equally with the K optimal solutions as the center to obtain K solution sets, where J is Q times K and Q is an integer greater than 5. In each solution set, the inferior solution with the maximum simulated construction time is selected as the difference solution, and K difference solutions are determined; Based on the K optimal solutions and K poor solutions, according to the strategy of seeking the best and avoiding the worst, the poor solutions in the K solution sets are adjusted once according to a preset step length for optimality, and K updated solution sets are output. If the updated poor solution does not meet the casting parameter threshold or the vibration parameter threshold, a construction plan is randomly selected for replacement; Identify the K updated solution sets. If the simulation operation duration of the inferior solution in the same solution set is less than the simulation operation duration of the superior solution, replace the superior solution with the inferior solution. If the simulation operation duration of the inferior solution in the same solution set is greater than the simulation operation duration of the poor solution, replace the poor solution with the inferior solution. Perform iterative optimization until the preset number of optimization attempts is met, output K current solution sets, evaluate and determine the optimal solution set, and select the optimal solution of the optimal solution set as the first optimized construction plan, wherein the optimal solution set is the solution set with the smallest total simulation operation time among the K current solution sets.

8. A digital management method for needle beam trolley construction according to claim 7, characterized in that: Based on the K optimal solutions and K poor solutions, according to the strategy of seeking the best and avoiding the worst, the poor solutions in the K solution set are adjusted once according to the preset optimal step length, including: Calculate the average simulation operation time of multiple inferior solutions in each solution set, and calculate the deviation from the simulation operation time of the optimal solution and the inferior solution respectively, to determine the optimal solution deviation and the inferior solution deviation; If the optimal solution deviation is greater than or equal to the inferior solution deviation, the optimization strategy is set to the optimal strategy, and the inferior solutions in the K solution sets are adjusted once according to the preset optimization step size with the optimal solution as the adjustment direction; If the optimal solution deviation is smaller than the poor solution deviation, the optimization strategy is set to avoid the poor solution strategy, and the poor solutions in the K solution sets are adjusted once according to the preset optimization step size, with the adjustment direction being away from the poor solution.

9. A digital management method for needle beam trolley construction according to claim 8, characterized in that: The method for setting the preset optimization step length includes: Calculate the simulation operation duration deviations of multiple inferior solutions and optimal solutions or poor solutions in each solution set, obtain multiple optimal solution duration deviations and multiple poor solution duration deviations, and calculate the mean of the optimal solution duration deviations and the mean of the poor solution duration deviations; If the optimization strategy is a trending optimization strategy, the ratio of the optimal solution time deviation to the average optimal solution time deviation is set as the adjustment coefficient, and multiple adjustment coefficients are obtained to adjust the initial optimization step length, and multiple adjusted optimization step lengths are obtained as the preset optimization step lengths; If the optimization strategy is an avoidance strategy, the ratio of the difference solution time deviation to the mean of the difference solution time deviation is set as the adjustment coefficient, and the initial optimization step length is adjusted to obtain multiple adjusted optimization step lengths as the preset optimization step lengths.

10. A digital management method for needle beam trolley construction according to claim 4, characterized in that: The scheme with the shortest simulated operation time is selected from the multiple optimized construction schemes of the multiple work window operation sequences and is set as the optimal construction scheme.

Images