Tower crane cluster cooperative control method and system for intelligent construction site and medium

Abstract

The invention discloses a tower crane cluster cooperative control method and system for an intelligent construction site and a medium, belongs to the technical field of tower crane control, and aims to solve the problems that existing cluster control among multiple tower cranes mainly depends on manual control, large potential safety hazards are easily generated in complex tower crane operation, and the working efficiency is high. And intelligent cooperative control of work among a plurality of tower cranes is difficult to realize. The method comprises the steps that track error prediction of a tower crane rope is conducted on current dynamic environment characteristics in a current construction area, and wind resistance-swing angle coupling error data are obtained; track intersection and coincidence judgment is conducted on the tower crane rope moving tracks of the tower crane tasks to be executed in the multiple tower cranes in the future time period, and an abnormal tower crane moving track diagram is predicted and determined; performing optimal path generation processing on the abnormal tower crane moving trajectory diagram under a federated learning framework to obtain an optimized tower crane moving trajectory diagram; and track avoidance execution processing is conducted on the risk tower crane with the track crossing risk, and a tower crane avoidance strategy of the risk tower crane is obtained.

Description

Technical Field

[0001] The present application relates to the field of tower crane control, and in particular to a tower crane cluster collaborative control method, system and medium for smart construction sites. Background Art

[0002] With the surge in the number of super-high-rise buildings and large-scale infrastructure projects, dense deployment of tower cranes (eight or more) on a single construction site has become the norm. Statistics from the Ministry of Housing and Urban-Rural Development show that 67% of tower crane collisions occur in areas where multiple cranes intersect, with 81% of these accidents caused by falling objects in "dynamic blind spots."

[0003] In the traditional manual dispatching model, the main operating process relies on communication via intercom and experience-based prediction. The following defects exist: (1) The human eye's visual range only covers the area around the tower crane; (2) When multiple tower crane operators observe the same area at the same time, the overlap rate of visual angles is relatively small; (3) When the load swings suddenly, the manual response time is long.

[0004] Furthermore, the UWB-based real-time collision avoidance system, which utilizes crane-mounted positioning base stations to measure crane spacing in real time, still has limitations and can only trigger an alarm 1-2 seconds before a collision. Static protection logic cannot predict the trajectory of the hoisted object (for example, when the cable swing angle exceeds 15°, the actual collision range increases by 2.3 times). Furthermore, when multiple cranes enter the warning zone simultaneously, the false alarm rate is high, making it difficult to achieve truly scientific coordinated control of crane clusters. Summary of the Invention

[0005] The embodiments of the present application provide a tower crane cluster collaborative control method, system and medium for smart construction sites, which are used to solve the following technical problems: the existing cluster control between multiple tower cranes mainly relies on manual control, supplemented by simple collision warnings, which can easily cause major safety hazards in complex tower crane operations and make it difficult to achieve intelligent collaborative control of the work of multiple tower cranes.

[0006] The embodiments of this application adopt the following technical solutions: On the one hand, an embodiment of the present application provides a tower crane cluster collaborative control method for a smart construction site, including: using environmental monitoring sensors to predict the trajectory error of the tower crane rope based on the current dynamic environmental characteristics in the current construction area to obtain wind resistance-swing angle coupling error data; based on the wind resistance-swing angle coupling error data, the tower crane rope operation trajectories of the tower crane tasks to be performed in multiple tower cranes are judged for trajectory intersection and overlap in a future time period, and an abnormal tower crane operation trajectory diagram is predicted and determined; the abnormal tower crane operation trajectory diagram is processed based on the optimal path generation under the federated learning framework to obtain an optimized tower crane operation trajectory diagram; based on the optimized tower crane operation trajectory diagram, a risk tower crane with a trajectory intersection risk is processed for trajectory avoidance to obtain a tower crane avoidance strategy for the risk tower crane; through a preset cloud-based collaborative management platform, the tower crane avoidance strategy is correlated with multiple tower cranes to generate a tower crane cluster collaborative control strategy for the future time period.

[0007] By predicting the trajectory error of the tower crane rope, the embodiment of the present application can identify potential trajectory intersections and abnormal situations in advance, thereby avoiding construction accidents and improving the safety of the construction site. In addition, by predicting the trajectory intersection and overlap in future time periods, the operation trajectory of the tower crane can be planned in advance, reducing waiting and adjustment time and improving construction efficiency. Based on the optimization of the tower crane operation trajectory, unnecessary movement and energy consumption can be reduced, which helps to save energy and reduce emissions. Moreover, the use of the federated learning framework for optimal path generation and processing reflects the characteristics of intelligent management and helps to improve the intelligence level of construction management. At the same time, real-time information sharing and collaborative control between multiple tower cranes can be achieved, improving the coordination and response speed of construction. Moreover, through the automated trajectory intersection and overlap judgment and avoidance strategy generation, it is possible to reduce dependence on manual labor, reduce the error rate of manual intervention, and ensure the accuracy of tower crane operations, thereby improving construction quality.

[0008] In a feasible embodiment, before using environmental monitoring sensors to predict the trajectory error of the tower crane rope based on the current dynamic environmental characteristics in the current construction area and obtaining wind resistance-swing angle coupling error data, the method also includes: deploying an ultrasonic anemometer at the end of the tower crane's tower boom and collecting wind data; wherein the wind data includes: wind speed data and wind direction data; deploying a MEMS tilt sensor at the hook connecting shaft of the tower crane and measuring the dynamic angle data of the hoisted object in real time; wherein the dynamic angle data of the hoisted object includes: pitch angle data and yaw angle data; deploying a cable tension sensor to the fixed end of the lifting wire rope of the tower crane and collecting rope dynamic tension data; deploying a temperature and humidity sensor to the top of the tower crane cab of the tower crane and collecting air density parameter data; and determining the wind data, the dynamic angle data of the hoisted object, the dynamic tension data of the rope and the air density parameter data as the external environmental data of the tower crane.

[0009] In a feasible implementation, the trajectory error of the tower crane rope is predicted based on the current dynamic environmental characteristics in the current construction area through environmental monitoring sensors to obtain wind resistance-swing angle coupling error data, specifically including: performing timestamp alignment processing on the multi-type collected data sets in the tower crane external environmental data through the PTP precision clock protocol, and performing noise reduction processing based on the Kalman filter to obtain filtered tower crane external data; performing wind speed vector decomposition processing on the filtered tower crane external data and the wind data to obtain the hoisting object coordinate system; generating a hoisting object swing angle dynamics function based on the swing angle, wind resistance of the wind data in the filtered tower crane external data and the air density compensation of the air density parameter data; and aligning the filtered tower crane external data through XGBoost. The wind speed, wind direction angle, swing angle, swing speed, cable length and hoisting mass are determined as the model input features, and based on the swing angle dynamics function of the hoisted object, the difference calculation is performed on the actual measured swing angle and the swing angle calculated by the physical model to obtain the model target value; according to the model input features and the model target value, the wind resistance term and the swing angle term are trained with residual compensation to generate a wind resistance-swing angle data-driven fusion model; the current tower crane external environment data is input into the wind resistance-swing angle data-driven fusion model to predict and obtain the final predicted swing angle based on the predicted data-driven compensation; through the final predicted swing angle and the cable lifting trajectory, the horizontal offset and the vertical offset of the hoisted object are calculated with trajectory compensation to obtain the wind resistance-swing angle coupling error data based on the standard cable lifting trajectory.

[0010] In a feasible implementation, based on the wind resistance-swing angle coupling error data, the trajectory intersection and overlap of the tower crane ropes of multiple tower cranes to perform tower crane tasks in the future time period is judged, and the abnormal tower crane operation trajectory diagram is predicted and determined, specifically including: based on the BIM building information of the current construction area and the position information of each tower crane, a global coordinate system diagram based on time synchronization processing is generated; wherein, the global coordinate system diagram contains a local coordinate system diagram of each tower crane; according to the preset UWB positioning base station unit and the hook inertial navigation unit, and based on the future time period, the tower crane rope operation trajectory in the local coordinate system diagram is subjected to non-disturbance generation processing to obtain the ideal tower crane rope operation trajectory diagram of each tower crane at the same time; through the wind resistance-swing angle coupling error data, the all tower cranes of each tower crane are combined into a global coordinate system diagram based on time synchronization processing; wherein, the global coordinate system diagram contains a local coordinate system diagram of each tower crane; according to the preset UWB positioning base station unit and the hook inertial navigation unit, and based on the future time period, the tower crane rope operation trajectory in the local coordinate system diagram is subjected to disturbance-free generation processing to obtain the ideal tower crane rope operation trajectory diagram of each tower crane at the same time; The coordinate system lines in the ideal tower crane rope operation trajectory diagram are compensated for deviations to obtain the deviation coordinate system lines predicted in the future time period; wherein the deviation coordinate system lines are the tower crane rope operation prediction trajectories of the local coordinate system diagram in each tower crane; according to the global space-time grid corresponding to the global coordinate system diagram, the deviation coordinate system lines of the local coordinate system diagram of each tower crane are subjected to trajectory voxel filling calculations of the safety margin under the radius of the hook influence sphere to obtain the current voxels of each deviation coordinate system line; according to the time slice index, the current voxels of each deviation coordinate system line are subjected to occupation overlap judgment of the heat map generated by clustering of conflicting voxels to determine the abnormal deviation coordinate lines; based on the abnormal deviation coordinate lines, the abnormal tower crane with the risk of lifting and the corresponding abnormal tower crane operation trajectory diagram are determined.

[0011] In a feasible implementation manner, the abnormal tower crane operation trajectory diagram is subjected to optimal path generation processing based on the federated learning framework to obtain an optimized tower crane operation trajectory diagram, specifically comprising: identifying the execution timestamps of the tower crane tasks to be executed for the abnormal tower cranes involved in the abnormal tower crane operation trajectory diagram, determining the task start time node of each tower crane; and judging the latest start time node; extracting the conflict voxel clustering trajectory features of the abnormal tower crane operation trajectory diagram corresponding to the latest start time node, determining the abnormal trajectory features and the corresponding abnormal spatiotemporal features; wherein the abnormal spatiotemporal features are the position coordinate features of the conflict area in the conflict voxel clustering trajectory features and the predicted running time features; through the pre-training federated learning framework The federal model under the framework guides decision-making, and performs trajectory constraint processing on the abnormal trajectory characteristics under the target cost function to obtain a constraint execution action; wherein, the target cost function includes: time cost, energy consumption cost and risk cost; the constraint execution action includes: time lag constraint, hook cargo type constraint and lifting speed constraint; the constraint execution action is judged based on the safety level to determine the optimal constraint execution action; according to the optimal constraint execution action, the deviation coordinate connection in the local coordinate system diagram is subjected to constraint processing under the highest safety level to obtain the optimized deviation coordinate system connection in the future time period; based on the optimized deviation coordinate system connection, the optimized tower crane operation trajectory diagram of the tower crane corresponding to the latest start time node is obtained.

[0012] In a feasible implementation manner, according to the optimized tower crane operation trajectory diagram, the risk tower crane with the risk of trajectory crossing is subjected to trajectory avoidance execution processing to obtain the tower crane avoidance strategy of the risk tower crane, which specifically includes: determining the tower crane corresponding to the optimized tower crane operation trajectory diagram as the risk tower crane with the risk of trajectory crossing; extracting the optimal constraint execution action in the optimized tower crane operation trajectory diagram; making corresponding modifications to the control items in the tower crane task to be executed of the risk tower crane through the data control parameters in the optimal constraint execution action, and generating a trajectory avoidance execution action; based on the trajectory avoidance execution action, generating the tower crane avoidance strategy of the risk tower crane.

[0013] In a feasible implementation, the tower crane avoidance strategy is associated with multiple tower cranes for feedback through a preset cloud-based collaborative management platform to generate a tower crane cluster collaborative control strategy for the future time period, specifically including: sending the tower crane avoidance strategy and the corresponding risk tower crane information to the cloud-based collaborative management platform; according to the avoidance tower crane rope running trajectory of the risk tower crane in the tower crane avoidance strategy in the first future time period, dynamically adjusting the associated trajectory path of the associated tower cranes that have overlapping trajectories with the avoidance tower crane rope running trajectory in the second future time period, and obtaining the associated optimal constraint execution action in the optimized tower crane running trajectory diagram of the associated tower crane; wherein the second future time period is the post-time period of the first future time period; generating the associated lifting execution strategy of the associated tower crane through the associated optimal constraint execution action; generating the tower crane cluster collaborative control strategy based on the tower crane avoidance strategy and the associated lifting execution strategy.

[0014] In a feasible embodiment, after judging the trajectory intersection and overlap of the tower crane ropes of multiple tower cranes to perform tower crane tasks in a future time period based on the wind resistance-swing angle coupling error data and predicting and determining the abnormal tower crane operation trajectory diagram, the method also includes: determining the abnormal tower crane number in the abnormal tower crane operation trajectory diagram as the risky tower crane number; sending the risky tower crane number and the abnormal tower crane operation trajectory diagram to the cloud-based collaborative management platform, and generating lifting warning information; sending the lifting warning information to the associated staff end corresponding to the risky tower crane number, so that the tower crane drivers who are in a mutually collaborative relationship can obtain the lifting warning information.

[0015] On the second aspect, an embodiment of the present application also provides a tower crane cluster collaborative control system for a smart construction site, and the system is capable of executing a tower crane cluster collaborative control method for a smart construction site described in any of the above-mentioned embodiments.

[0016] On the third aspect, an embodiment of the present application also provides a non-volatile computer storage medium, which is a non-volatile computer-readable storage medium. The non-volatile computer-readable storage medium stores at least one program, each of which includes instructions. When the instructions are executed by the terminal, the terminal executes a tower crane cluster collaborative control method for a smart construction site described in any of the above embodiments.

[0017] This application provides a method, system, and medium for collaborative control of a tower crane cluster for a smart construction site. Compared with the prior art, the embodiments of this application have the following beneficial technical effects: 1. Improve construction safety: By predicting the trajectory error of tower crane ropes, potential trajectory intersections and abnormal situations can be identified in advance, thereby avoiding construction accidents and improving construction site safety.

[0018] 2. Optimize tower crane operation efficiency: By predicting the intersection and overlap of trajectories in future time periods, the operation trajectory of the tower crane can be planned in advance, reducing waiting and adjustment time and improving construction efficiency.

[0019] 3. Reduce energy consumption: By optimizing the tower crane's operating trajectory, unnecessary movement and energy consumption can be reduced, which helps save energy and reduce emissions.

[0020] 4. Improving the level of intelligent construction management: Using the federated learning framework to generate optimal paths reflects the characteristics of intelligent management and helps to improve the level of intelligent construction management.

[0021] 5. Real-time collaborative control: Through the cloud-based collaborative management platform, real-time information sharing and collaborative control can be achieved among multiple tower cranes, improving the coordination and response speed of construction.

[0022] 6. Adaptability to dynamic environments: Environmental monitoring sensors can monitor the dynamic environmental characteristics of the construction area in real time, enabling the tower crane cluster to adapt to environmental changes and ensure the continuity and stability of construction.

[0023] 7. Reduced human intervention: Automated trajectory intersection detection and avoidance strategy generation can reduce reliance on human intervention and lower the error rate of human intervention.

[0024] 8. Improve construction quality: Through precise trajectory control, the accuracy of tower crane operation can be ensured, thereby improving construction quality. BRIEF DESCRIPTION OF THE DRAWINGS

[0025] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the following briefly introduces the drawings required for the embodiments or the description of the prior art. Obviously, the drawings described below are only some embodiments described in the present application. For those skilled in the art, other drawings can be obtained based on these drawings without creative work. In the drawings: Figure 1 A flowchart of a tower crane cluster collaborative control method for a smart construction site provided in an embodiment of the present application; Figure 2 A schematic structural diagram of a tower crane cluster collaborative control system for a smart construction site provided in an embodiment of the present application. DETAILED DESCRIPTION

[0026] In order to enable those skilled in the art to better understand the technical solutions in this application, the following will clearly and completely describe the technical solutions in the embodiments of this application in conjunction with the drawings in the embodiments of this application. Obviously, the embodiments described are only part of the embodiments of this application, not all of the embodiments. Based on the embodiments of this specification, all other embodiments obtained by ordinary technicians in this field without making creative efforts should fall within the scope of protection of this application.

[0027] The embodiment of the present application provides a method for collaborative control of a tower crane cluster for a smart construction site, such as Figure 1 As shown, the tower crane cluster collaborative control method for a smart construction site specifically includes steps S101-S105: S101. Using environmental monitoring sensors, predict the trajectory error of the tower crane rope based on the current dynamic environmental characteristics in the current construction area to obtain wind resistance-swing angle coupling error data.

[0028] Specifically, various environmental monitoring sensors need to be deployed in the tower crane equipment first, namely: (1) The ultrasonic anemometer is deployed at the end of the tower crane's tower boom to collect wind data. The wind data includes: wind speed data and wind direction data. (2) The MEMS tilt sensor is deployed at the hook connection shaft of the tower crane to measure the dynamic angle data of the hoisted object in real time. The dynamic angle data of the hoisted object includes: pitch angle data and yaw angle data. (3) The cable tension sensor is deployed to the fixed end of the tower crane's lifting wire rope and collects the dynamic tension data of the rope. (4) The temperature and humidity sensor is deployed on the top of the tower crane's tower crane cab and collects air density parameter data. Finally, the wind data, the dynamic angle data of the hoisted object, the dynamic tension data of the rope and the air density parameter data are determined as the external environmental data of the tower crane.

[0029] Furthermore, the PTP precision clock protocol is used to align the timestamps of the various data sets collected from the crane's external environment. Kalman filtering is then used to reduce noise, resulting in filtered crane external data. This filtered crane external data is then combined with wind data for wind speed vector decomposition to obtain the coordinate system for the hoisted object.

[0030] In one embodiment, it is necessary to synchronize and filter the multi-source data of the tower crane external environment data, which can be in the form of code, for example: def preprocess_data(): # Timestamp alignment (PTP Precision Clock Protocol) synced_data = time_align(wind_data, angle_data, tension_data) # Kalman filter noise reduction (taking inclination data as an example) kf = KalmanFilter(F=1, H=1, Q=0.003, R=0.5) clean_angle = kf.filter(synced_data['angle']) # Wind speed vector decomposition (converted to the hoisting object coordinate system) wind_vector = transform_coord(wind_data, crane_orientation) return { 'wind': wind_vector, 'angle': clean_angle, 'tension':tension_data} Furthermore, based on the swing angle, wind resistance of the wind force data in the filtered tower crane external data and the air density compensation of the air density parameter data, a dynamic function of the swing angle of the hoisted object is generated. In one embodiment, the dynamic function of the swing angle of the hoisted object can be: , where θ is the swing angle (radians); , and represents wind resistance; , and represents air density compensation; m is the weight of the cargo in the hook, b is a mathematical constant, and g is the acceleration of gravity.

[0031] Furthermore, through XGBoost, the wind speed, wind direction angle, swing angle, swing speed, cable length and hoisting mass in the filtered tower crane external data are determined as model input features, and based on the swing angle dynamics function of the hoisted object, the difference between the actual measured swing angle and the swing angle calculated by the physical model is calculated to obtain the model target value.

[0032] In one embodiment, XGBoost is used to learn the physical model residual, where the model input features of the model = [wind speed, wind direction angle, swing angle, swing speed, cable length, hoisting mass]; the model target value = the actual measured swing angle - the swing angle calculated by the physical model; for example: model = xgb.XGBRegressor(objective='reg:squarederror'); model.fit(X_train, y_residual), and finally the residual compensation model is trained.

[0033] Furthermore, residual compensation training is performed on the wind resistance and swing angle terms based on the model input features and target values ​​to generate a wind resistance-swing angle data-driven fusion model. The current crane external environment data is then input into this wind resistance-swing angle data-driven fusion model to predict and derive the final predicted swing angle based on the predicted data-driven compensation.

[0034] Furthermore, by finally predicting the swing angle and cable lifting trajectory, trajectory compensation calculations are performed on the horizontal and vertical offsets of the hoisted object to obtain the windage-swing angle coupling error data based on the standard cable lifting trajectory.

[0035] In one embodiment, a wind resistance-swing angle data-driven fusion model is used to predict dynamic errors. Inputs include current environmental parameters: wind speed v_wind, wind direction φ, air density ρ, and hoisting status: cable length L, hoisted weight m, and current swing angle θ. Physical base values ​​are then calculated and driven to compensate for the predicted data, i.e., trajectory compensation is calculated for the horizontal and vertical offsets of the hoisted object. The code that can be used is, for example: F_wind = 0.5 * ρ * C_d * A * v_wind**2 θ_physical = solve_pendulum_eq(F_wind, L, m) # Solve the differential equation residual = model.predict([[v_wind, φ, θ, θ_velocity, L, m]]) θ_pred = θ_physical + residual # Final predicted swing angle Finally, trajectory error mapping processing is performed, that is, trajectory compensation calculation is performed on the horizontal and vertical offsets of the hoisted object to obtain the horizontal offset Δx and vertical offset Δy. Then, based on the final predicted swing angle and the sequential predicted changes of the cable lifting trajectory, the trajectory error calculation of the standard cable lifting trajectory is performed to obtain the windage-swing angle coupling error data.

[0036] S102: Based on the wind resistance-swing angle coupling error data, the trajectory intersection and overlap of the tower crane rope operation trajectories of the tower crane tasks to be performed in multiple tower cranes in the future time period are judged to predict and determine the abnormal tower crane operation trajectory diagram.

[0037] Specifically, it is also necessary to generate a global coordinate system diagram based on time synchronization processing based on the BIM building information of the current construction area and the location information of each tower crane. The global coordinate system diagram contains the local coordinate system diagram of each tower crane.

[0038] Furthermore, according to the preset UWB positioning base station unit and the hook inertial navigation unit, and based on the future time period, the tower crane rope operation trajectory in the local coordinate system diagram is processed without disturbance, and the ideal tower crane rope operation trajectory diagram of each tower crane at the same time is obtained.

[0039] It should be noted that a UWB positioning base station is a wireless device based on ultra-wideband (UWB) technology, primarily used for high-precision indoor and outdoor positioning. By receiving signals from positioning tags and calculating location information, it achieves real-time tracking with centimeter-level accuracy. The UWB (Ultra-Wide Band) positioning base station transmits nanosecond-level narrow pulse signals and uses algorithms such as time difference of arrival (TDOA) or angle of arrival (PDOA) to accurately measure the distance or angle to the tag, ultimately determining the target's location through triangulation.

[0040] In one embodiment, the crane rope trajectories must first be uniformly processed in time and space, requiring coordinate system conversion and time synchronization. A global coordinate system is first established: using the construction site reference control point as the origin (RTK positioning accuracy of ±1cm), then all crane pose transformation functions are calculated based on the crane rotation angle and crane base coordinates, generating a time-synchronized global coordinate system diagram. The crane rope trajectories in the local coordinate system diagram are then undisturbed and generated within the same future time period (e.g., 20 seconds) using a preset UWB positioning base unit and hook inertial navigation unit. This generates an ideal crane rope trajectory diagram for each crane at the same time.

[0041] In one implementation, regarding the generation of a single tower crane trajectory prediction diagram, the following code may be used, for example: # Input: current state + operation instructions + environment data def predict_trajectory(crane_state, command, env_data): # 1. Basic kinematic prediction base_path = kinematic_model(command, crane_state) # 2. Injected windage-swing angle error wind_sway = wind_sway_predictor(env_data)# Call the aforementioned coupling model compensated_path = [] for t in range(0, 20):# Predict the next 20 seconds (step size 0.1 seconds) point = base_path[t] # Calculate wind displacement vector (magnitude + direction) offset = calc_wind_offset(wind_sway[t], point.height) compensated_path.append(point + offset) # 3. Add inertia delay compensation final_path = inertia_compensate(compensated_path) return final_path Finally, the ideal tower crane rope operation trajectory diagram of each tower crane at the same time (20 seconds in the future) is predicted and output.

[0042] Furthermore, using the windage-angle coupling error data, the coordinate system lines in each crane's ideal crane rope trajectory diagram are compensated for deviations, resulting in a predicted deviation coordinate system line for the future time period. The deviation coordinate system line represents the predicted crane rope trajectory for each crane's local coordinate system diagram.

[0043] Furthermore, according to the global space-time grid corresponding to the global coordinate system diagram, the deviation coordinate system connection line of each tower crane local coordinate system diagram is filled with trajectory voxels of the safety margin under the hook influence sphere radius to obtain the current voxel of each deviation coordinate system connection line.

[0044] In one embodiment, the global coordinate map needs to be divided into a spatiotemporal grid, with a spatial resolution of 0.5m×0.5m×0.5m (X / Y / Z) and a temporal resolution of 0.2 seconds (covering a total of 100 time slices for a 20-second prediction). Then, using the trajectory voxel filling algorithm, the deviation coordinate system of each crane's local coordinate system is connected to calculate the trajectory voxel filling of the safety margin under the hook influence sphere radius, that is: def voxelize_trajectory(trajectory): voxel_grid = np.zeros((100,200,200))# Time slice × space grid for t, point in enumerate(trajectory): # Calculate the radius of the hook's influence sphere (size of the hoisted object + safety margin) radius = load_radius + 1.5 # 1.5m safety margin # Mark placeholder voxels x_idx, y_idx, z_idx = coord_to_voxel(point) mark_sphere(voxel_grid[t], x_idx, y_idx, z_idx, radius) return voxel_grid Finally, the current voxel of each deviation coordinate system line is obtained.

[0045] Furthermore, based on the time slice index, the current voxel of each deviation coordinate line is subjected to a heat map occupancy overlap check generated by clustering conflicting voxels to identify the abnormal deviation coordinate line. Finally, based on the abnormal deviation coordinate line, abnormal tower cranes with lifting risks are identified, along with the corresponding abnormal tower crane operation trajectory map.

[0046] In one embodiment, the conflict marker based on the time slice index may adopt a code, for example: __global__ void detect_collision(int *grid, int *conflict_map) { int t = blockIdx.x; / / time slice index int x = threadIdx.x; int y = threadIdx.y; int z = threadIdx.z; / / If the current voxel is occupied by ≥ 2 tower cranes if (grid[t][x][y][z]>= 2) { atomicAdd(&conflict_map[t], 1); / / Mark conflict } } In one embodiment, a dynamic heat map is also used to perform occupancy overlap judgment on the heat map generated by the conflicting voxel clusters for the current voxel of each deviation coordinate system connection, that is, to determine which two or more coordinate connections have conflicts, for example: # Generate heatmap based on conflict voxel clustering heatmap = np.zeros(space_grid) for t in range(100): cluster_labels = DBSCAN(voxel_conflicts[t], eps=3, min_samples=5) for cluster in unique_clusters: # Calculate the center of mass of the conflict area centroid = calc_centroid(cluster) #Diffusion heat value centered on the center of mass heatmap = gaussian_filter(heatmap, centroid, sigma=2.0) Finally, the abnormal deviation coordinate connection lines are screened out, and based on the abnormal deviation coordinate connection lines, the abnormal tower cranes with lifting risks and the corresponding abnormal tower crane operation trajectory diagrams are determined.

[0047] As a feasible implementation, the abnormal crane number in the abnormal crane trajectory diagram is identified as the risk crane number. The risk crane number and the abnormal crane trajectory diagram are then sent to a cloud-based collaborative management platform, where a lifting warning message is generated. Finally, the lifting warning message is sent to the associated staff terminal corresponding to the risk crane number, allowing all crane operators in the collaborative relationship to receive the lifting warning message.

[0048] S103: The abnormal tower crane operation trajectory diagram is processed by optimal path generation based on the federated learning framework to obtain an optimized tower crane operation trajectory diagram.

[0049] Specifically, the abnormal cranes involved in the abnormal crane operation trajectory diagram are first identified with the execution timestamps of the related crane tasks to be executed, and the task start time node of each crane is determined. The latest start time node is also determined.

[0050] Furthermore, the abnormal crane trajectory corresponding to the latest start-up time node is processed to extract the relevant conflict voxel cluster trajectory features, and the abnormal trajectory features and corresponding abnormal spatiotemporal features are determined. The abnormal spatiotemporal features are the location coordinate features of the conflict area in the conflict voxel cluster trajectory features and the predicted operation time features.

[0051] In one embodiment, step 1: identifying abnormal crane task timestamps: 1.1. Collect real-time operating data of all tower cranes in the current construction area.

[0052] 1.2. For each abnormal tower crane in the abnormal tower crane operation trajectory diagram, extract the timestamp of its task execution.

[0053] 1.3. Analyze timestamp data to determine the task start time node for each abnormal tower crane.

[0054] 1.4. Mark the latest time node when tasks are started in all abnormal tower cranes.

[0055] Step 2: Conflict voxel clustering trajectory feature extraction: 2.1. For the abnormal tower crane with the latest start time node determined in step 1, extract the conflict voxel data of its running trajectory.

[0056] 2.2. Use spatial analysis algorithms to cluster conflict voxels and identify conflict areas.

[0057] 2.3. Extract the location coordinate features of the conflict area, including latitude, longitude, altitude, and other information.

[0058] 2.4. Predict the trajectory of the abnormal tower crane in the future operation time and extract the predicted operation time features.

[0059] Step 3: Determine the abnormal spatiotemporal characteristics: 3.1. Combine the location coordinate features extracted in step 2 and the predicted running time features to form an abnormal spatiotemporal feature set.

[0060] 3.2. Analyze the abnormal spatiotemporal feature set and determine the abnormal trajectory characteristics, including trajectory stability, speed changes, etc.

[0061] 3.3. Determine the relationship between the spatiotemporal characteristics of anomalies and the safety and efficiency of tower crane operations.

[0062] Furthermore, the federated model within the pre-trained federated learning framework guides decision-making, applying trajectory constraints to abnormal trajectory features under a target cost function to generate constrained execution actions. The target cost function includes time cost, energy cost, and risk cost. Constrained execution actions include time lag constraints, hook cargo type constraints, and lifting speed constraints.

[0063] In one embodiment, a communication protocol for a federated learning framework is designed based on the transport layer, security layer, and federation layer. Distributed model training is then performed to obtain a pre-trained federated learning framework for abnormal trajectory features under a target cost function, for example: def federated_aggregation(): while not convergence: # 1. Select 10% edge nodes selected_nodes = random_select(edges, 0.1) # 2. Distribute the global model broadcast(global_model) # 3. Local training (edge-side execution) # Local execution on edge devices: for epoch in range(5):# Local 5-round iteration local_grad = compute_grad(local_data, global_model) local_model = sgd_update(local_model, local_grad) # 4. Security Aggregation encrypted_grads = [] for node in selected_nodes: grad = receive_encrypted_grad(node) encrypted_grads.append(paillier_add(grad))# Homomorphic encryption accumulation # 5. Model Update global_grad = paillier_decrypt(encrypted_grads) global_model = update_model(global_model, global_grad) Finally, based on the trajectory constraint processing, the constraint execution action is obtained.

[0064] As a feasible implementation method, the constraint execution actions can be: postponing the execution start plan time of the tower crane; changing the type, size and weight of the hook cargo, etc.; reducing the lifting speed, etc., and performing decentralized scoring calculations to obtain constraint conditions based on the target cost function.

[0065] Furthermore, the constraint execution action is judged based on the safety level to determine the optimal constraint execution action. Specifically, the constraints mentioned above are evaluated to determine the optimal constraint execution action that meets the highest safety level and minimizes costs. Based on the optimal constraint execution action, the deviation coordinate lines in the local coordinate system diagram are then processed for the constraints at the highest safety level to obtain the optimized deviation coordinate system lines for the future time period. Specifically, the deviation coordinate system lines are fine-tuned based on the data adjustment parameters corresponding to the optimal constraint execution action, thereby generating the optimized deviation coordinate system lines.

[0066] Furthermore, based on the connection of the optimized deviation coordinate system, the optimized tower crane operation trajectory diagram of the tower crane corresponding to the latest start time node is obtained.

[0067] S104. According to the optimized tower crane operation trajectory diagram, a trajectory avoidance process is performed on the risky tower crane with a trajectory crossing risk, and a tower crane avoidance strategy for the risky tower crane is obtained.

[0068] Specifically, the tower crane corresponding to the optimized tower crane operation trajectory diagram is first determined as a risky tower crane with a trajectory intersection risk.

[0069] Furthermore, the optimal constraint execution action in the optimized tower crane operation trajectory diagram is extracted.

[0070] Furthermore, the data control parameters in the optimal constraint execution action are used to modify the control items in the crane task to be executed for the risky crane, generating a trajectory avoidance execution action. Finally, based on the trajectory avoidance execution action, a crane avoidance strategy is generated for the risky crane.

[0071] S105. Through the preset cloud collaborative management platform, the tower crane avoidance strategy is correlated with multiple tower cranes to generate a tower crane cluster collaborative control strategy for the future time period.

[0072] Specifically, the tower crane avoidance strategy and the corresponding risky tower crane information need to be sent to the cloud-based collaborative management platform.

[0073] Furthermore, based on the avoidance crane rope trajectory of the risky crane in the crane avoidance strategy in the first future time period, the associated cranes whose trajectories overlap with the avoidance crane rope trajectory in the second future time period are dynamically adjusted to obtain the associated optimal constraint execution actions in the optimized crane trajectory graph for the associated cranes. The second future time period is a period subsequent to the first future time period.

[0074] Furthermore, by associating the optimal constraint execution actions, the associated lifting execution strategy of the associated tower crane is generated. Finally, based on the tower crane avoidance strategy and the associated lifting execution strategy, the tower crane cluster collaborative control strategy is generated.

[0075] In one embodiment, after the tower crane avoidance strategy is determined, the avoidance strategy and the corresponding risk tower crane information are uploaded to the cloud collaborative management platform through the data interface. Ensure that the uploaded data includes the identification information of the risk tower crane, the specific details of the avoidance strategy, and the execution time. Then, according to the avoidance strategy received by the cloud collaborative management platform, the tower crane in the first future time period begins to perform the avoidance action. Monitor the running trajectory of the avoidance tower crane rope of the risk tower crane and record its real-time data. Then analyze the running trajectory of the avoidance tower crane rope in the first future time period to predict the possible trajectory intersection and overlap in the second future time period. Identify the associated tower cranes whose trajectories overlap with the running trajectory of the avoidance tower crane rope. Dynamically adjust the trajectory paths of these associated tower cranes to avoid intersection and overlap.

[0076] In one embodiment, an optimized tower crane operation trajectory diagram of the associated tower crane is generated based on the dynamically adjusted trajectory path. Then, the associated optimal constraint execution action in the optimized trajectory diagram is determined. Then, based on the associated optimal constraint execution action in the above embodiment, an associated lifting execution strategy of the associated tower crane is generated. The strategy should include the adjustment of parameters such as lifting height, speed, and time. Then, the tower crane avoidance strategy and the associated lifting execution strategy are combined to generate the final tower crane cluster collaborative control strategy. The strategy should ensure the safe and efficient operation of all tower cranes during the construction process. Finally, the generated collaborative control strategy is issued to all relevant tower cranes. The operating status of the tower crane cluster is monitored in real time, including the position, speed, trajectory, etc. of the tower crane. Therefore, according to the real-time monitoring data, the strategy is adjusted as necessary to adapt to changes in the construction site.

[0077] In addition, the embodiment of the present application also provides a tower crane cluster collaborative control system for a smart construction site, such as Figure 2 As shown, the tower crane cluster collaborative control system 200 specifically includes: The environment monitoring module 210 is used to predict the trajectory error of the tower crane rope based on the current dynamic environment characteristics in the current construction area through the environment monitoring sensor, and obtain wind resistance-swing angle coupling error data.

[0078] The abnormal trajectory identification module 220 is used to determine the trajectory overlap of the rope running trajectories of the tower cranes to be executed in the future time period based on the wind resistance-swing angle coupling error data, and predict and determine the abnormal tower crane running trajectory diagram.

[0079] The optimal path generation module 230 is used to perform optimal path generation processing on the abnormal tower crane operation trajectory diagram based on the federated learning framework to obtain an optimized tower crane operation trajectory diagram.

[0080] The avoidance calculation module 240 is used to perform trajectory avoidance processing on risky tower cranes with trajectory crossing risks according to the optimized tower crane operation trajectory diagram, and obtain a tower crane avoidance strategy for the risky tower cranes.

[0081] The collaborative control module 250 is used to provide associated feedback of the tower crane avoidance strategy to multiple tower cranes through a preset cloud collaborative management platform, and generate a tower crane cluster collaborative control strategy for a future time period.

[0082] By predicting the trajectory error of the tower crane rope, the embodiment of the present application can identify potential trajectory intersections and abnormal situations in advance, thereby avoiding construction accidents and improving the safety of the construction site. In addition, by predicting the trajectory intersection and overlap in future time periods, the operation trajectory of the tower crane can be planned in advance, reducing waiting and adjustment time and improving construction efficiency. Based on the optimization of the tower crane operation trajectory, unnecessary movement and energy consumption can be reduced, which helps to save energy and reduce emissions. Moreover, the use of the federated learning framework for optimal path generation and processing reflects the characteristics of intelligent management and helps to improve the intelligence level of construction management. At the same time, real-time information sharing and collaborative control between multiple tower cranes can be achieved, improving the coordination and response speed of construction. Moreover, through the automated trajectory intersection and overlap judgment and avoidance strategy generation, it is possible to reduce dependence on manual labor, reduce the error rate of manual intervention, and ensure the accuracy of tower crane operations, thereby improving construction quality.

[0083] The various embodiments in this application are described in a progressive manner. Similar portions between the various embodiments can be referred to in conjunction with each other. Each embodiment focuses on the differences between the other embodiments. In particular, the device and medium embodiments are generally similar to the method embodiments, so their descriptions are relatively simple. For relevant portions, refer to the descriptions of the method embodiments.

[0084] The devices and media provided in the embodiments of the present application correspond one-to-one to the methods. Therefore, the devices and media also have similar beneficial technical effects to their corresponding methods. Since the beneficial technical effects of the methods have been described in detail above, the beneficial technical effects of the devices and media will not be repeated here.

[0085] Those skilled in the art will appreciate that the embodiments of the present application may be provided as methods, systems, or computer program products. Therefore, the present application may take the form of an entirely hardware embodiment, an entirely software embodiment, or an embodiment combining software and hardware. Furthermore, the present application may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to magnetic disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0086] The present application is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems), and computer program products according to the embodiments of the present application. It should be understood that each process and / or block in the flowchart and / or block diagram, as well as the combination of processes and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 a process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0087] These computer program instructions may also be stored in a computer readable memory that can direct a computer or other programmable data processing device to work in a specific manner, so that the instructions stored in the computer readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 a process or multiple processes and / or boxes Figure 1 The function specified in one or more boxes.

[0088] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operational steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing the instructions executed on the computer or other programmable device for implementing the process. Figure 1 a process or multiple processes and / or boxes Figure 1 A step that specifies a function in one or more boxes.

[0089] In a typical configuration, a computing device includes one or more processors (CPUs), input / output interfaces, network interfaces, and memory.

[0090] Memory may include non-permanent storage in a computer-readable medium, in the form of random access memory (RAM) and / or non-volatile memory, such as read-only memory (ROM) or flash RAM. Memory is an example of a computer-readable medium.

[0091] Computer-readable media includes both permanent and non-permanent, removable and non-removable media that can be implemented using any method or technology for information storage. Information can be computer-readable instructions, data structures, program modules, or other data. Examples of computer storage media include, but are not limited to, phase-change RAM (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technologies, compact disc read-only memory (CD-ROM), digital versatile disc (DVD) or other optical storage, magnetic cassettes, magnetic disk storage or other magnetic storage devices, or any other non-transmission media that can be used to store information that can be accessed by a computing device. As defined herein, computer-readable media does not include transitory computer-readable media, such as modulated data signals and carrier waves.

[0092] It should also be noted that the terms "comprises," "includes," or any other variations thereof are intended to encompass non-exclusive inclusion, such that a process, method, commodity, or apparatus that includes a series of elements includes not only those elements but also other elements not explicitly listed, or includes elements inherent to such process, method, commodity, or apparatus. In the absence of further limitations, an element defined by the phrase "comprises a ..." does not exclude the presence of other identical elements in the process, method, commodity, or apparatus that includes the element.

[0093] The foregoing is merely an embodiment of the present application and is not intended to limit the present application. For those skilled in the art, the present application may have various modifications and variations. Any modifications, equivalent replacements, improvements, etc. made within the spirit and principles of the present application should all be included within the scope of the specification of the present application.

Claims

1. A tower crane cluster collaborative control method for a smart construction site, characterized in that: The method comprises: Through environmental monitoring sensors, the trajectory error of the tower crane rope is predicted based on the current dynamic environmental characteristics in the current construction area, and the wind resistance-swing angle coupling error data is obtained; Based on the wind resistance-swing angle coupling error data, the trajectory intersection and overlap of the tower crane rope running trajectories of the tower cranes to be executed in the future time period is judged, and the abnormal tower crane running trajectory diagram is predicted and determined; The abnormal tower crane operation trajectory diagram is processed by optimal path generation based on the federated learning framework to obtain an optimized tower crane operation trajectory diagram; According to the optimized tower crane operation trajectory diagram, a risk tower crane with a trajectory intersection risk is subjected to trajectory avoidance execution processing to obtain a tower crane avoidance strategy for the risk tower crane; Through the preset cloud-based collaborative management platform, the tower crane avoidance strategy is fed back to multiple tower cranes to generate a tower crane cluster collaborative control strategy for the future time period.

2. A tower crane cluster collaborative control method for a smart construction site according to claim 1, characterized in that: Before predicting the trajectory error of the tower crane rope based on the current dynamic environmental characteristics in the current construction area using an environmental monitoring sensor to obtain windage-swing angle coupling error data, the method further includes: An ultrasonic anemometer is deployed at the end of the tower crane's boom to collect wind data, wherein the wind data includes wind speed data and wind direction data; A MEMS tilt sensor is deployed at the hook connection shaft of the tower crane to measure the dynamic angle data of the hoisted object in real time; wherein the dynamic angle data of the hoisted object includes: pitch angle data and yaw angle data; Deploy a cable tension sensor to the fixed end of the hoisting wire rope of the tower crane and collect dynamic tension data of the rope; Deploy a temperature and humidity sensor on the top of the tower crane cab and collect air density parameter data; The wind force data, the dynamic angle data of the hoisted object, the dynamic tension data of the rope and the air density parameter data are determined as the external environment data of the tower crane.

3. The method for collaborative control of a tower crane cluster for a smart construction site according to claim 2, characterized in that: Environmental monitoring sensors are used to predict the trajectory error of the tower crane rope based on the current dynamic environmental characteristics in the current construction area, and windage-angle coupling error data is obtained, specifically including: Through the PTP precision clock protocol, the multi-type collected data sets in the tower crane external environment data are timestamp aligned, and the Kalman filter is used for noise reduction to obtain filtered tower crane external data; Perform wind speed vector decomposition processing on the filtered tower crane external data and the wind force data to obtain a hoisting object coordinate system; Generate a swing angle dynamics function of a hoisted object based on the swing angle and wind resistance of the wind force data in the filtered tower crane external data and the air density compensation of the air density parameter data; Using XGBoost, the wind speed, wind direction, swing angle, swing speed, cable length, and hoisted mass in the filtered tower crane external data are determined as model input features. Based on the swing angle dynamics function of the hoisted object, the difference between the actual measured swing angle and the swing angle calculated by the physical model is calculated to obtain the model target value. Performing residual compensation training on the wind resistance term and the swing angle term according to the model input features and the model target value to generate a wind resistance-swing angle data driven fusion model; Inputting the current tower crane external environment data into the wind resistance-swing angle data driven fusion model to predict and obtain the final predicted swing angle based on the predicted data driven compensation; The horizontal and vertical offsets of the hoisted object are calculated by trajectory compensation using the final predicted swing angle and the cable lifting trajectory to obtain the windage-swing angle coupling error data based on the standard cable lifting trajectory.

4. The tower crane cluster collaborative control method for a smart construction site according to claim 1, characterized in that: Based on the wind resistance-swing angle coupling error data, the trajectory overlap of the tower crane ropes of multiple tower cranes to be used for tower crane tasks in the future time period is judged, and the abnormal tower crane trajectory diagram is predicted and determined, specifically including: Based on the BIM building information of the current construction area and the position information of each tower crane, a global coordinate system diagram based on time synchronization processing is generated; wherein the global coordinate system diagram includes a local coordinate system diagram of each tower crane; According to the preset UWB positioning base station unit and the hook inertial navigation unit, and based on the future time period, the tower crane rope operation trajectory in the local coordinate system diagram is subjected to non-disturbance generation processing to obtain an ideal tower crane rope operation trajectory diagram for each tower crane at the same time; Using the windage-angle coupling error data, the coordinate system connection line in the ideal tower crane rope operation trajectory diagram of each tower crane is compensated for deviation to obtain a deviation coordinate system connection line predicted in the future time period; wherein the deviation coordinate system connection line is a tower crane rope operation prediction trajectory of the local coordinate system diagram of each tower crane; According to the global space-time grid corresponding to the global coordinate system diagram, the deviation coordinate system connection line of each tower crane local coordinate system diagram is subjected to trajectory voxel filling calculation of the safety margin under the hook influence sphere radius to obtain the current voxel of each deviation coordinate system connection line; According to the time slice index, the current voxel of each deviation coordinate system connection is subjected to the occupancy coincidence judgment of the heat map generated by the conflicting voxel clustering, and the abnormal deviation coordinate connection is determined; Based on the abnormal deviation coordinate connection line, the abnormal tower crane with the lifting risk and the corresponding abnormal tower crane operation trajectory diagram are determined.

5. The tower crane cluster collaborative control method for a smart construction site according to claim 1, characterized in that: The abnormal tower crane operation trajectory graph is subjected to optimal path generation processing based on the federated learning framework to obtain an optimized tower crane operation trajectory graph, specifically including: Identify the execution timestamps of the to-be-executed tower crane tasks for the abnormal tower cranes involved in the abnormal tower crane operation trajectory diagram, determine the task start time node of each tower crane, and determine the latest start time node; Extracting relevant conflict voxel clustering trajectory features from the abnormal tower crane operation trajectory graph corresponding to the latest start-up time node to determine the abnormal trajectory features and corresponding abnormal spatiotemporal features; wherein the abnormal spatiotemporal features are the position coordinate features of the conflicting area in the conflict voxel clustering trajectory features and the predicted operation time features; The decision is guided by a federated model in a pre-trained federated learning framework, and the abnormal trajectory features are subjected to trajectory constraints under a target cost function to obtain a constrained execution action. The target cost function includes: time cost, energy cost, and risk cost; the constrained execution action includes: time lag constraint, hook cargo type constraint, and lifting speed constraint. Performing an execution judgment on the constraint execution action based on the security level to determine the optimal constraint execution action; According to the optimal constraint, an action is executed to perform constraint processing under the highest safety level on the deviation coordinate connection line in the local coordinate system diagram to obtain an optimized deviation coordinate system connection line in the future time period; Based on the optimized deviation coordinate system connection, the optimized tower crane operation trajectory diagram of the tower crane corresponding to the latest start time node is obtained.

6. The tower crane cluster collaborative control method for a smart construction site according to claim 1, characterized in that: According to the optimized tower crane operation trajectory diagram, a risk tower crane with a trajectory intersection risk is subjected to trajectory avoidance execution processing, and a tower crane avoidance strategy for the risk tower crane is obtained, specifically including: Determine the tower crane corresponding to the optimized tower crane operation trajectory diagram as the risky tower crane with a trajectory intersection risk; Extracting the optimal constraint execution action in the optimized tower crane operation trajectory diagram; By using the data control parameters in the optimal constraint execution action, the control items in the to-be-executed crane task of the risky crane are modified accordingly to generate a trajectory avoidance execution action; Based on the trajectory avoidance execution action, the tower crane avoidance strategy of the risky tower crane is generated.

7. The method for collaborative control of a tower crane cluster for a smart construction site according to claim 1, characterized in that: Through the preset cloud-based collaborative management platform, the tower crane avoidance strategy is fed back to multiple tower cranes to generate a tower crane cluster collaborative control strategy for the future time period, specifically including: Sending the tower crane avoidance strategy and corresponding risky tower crane information to the cloud collaborative management platform; According to the avoidance tower crane rope running trajectory of the risky tower crane in the tower crane avoidance strategy in the first future time period, dynamically adjust the associated trajectory path of the associated tower crane whose trajectory overlaps with the avoidance tower crane rope running trajectory in the second future time period, and obtain the associated optimal constraint execution action in the optimized tower crane running trajectory diagram of the associated tower crane; wherein the second future time period is a post-time period of the first future time period; Generate an associated lifting execution strategy for the associated tower crane by executing the associated optimal constraint action; Based on the tower crane avoidance strategy and the associated lifting execution strategy, the tower crane cluster collaborative control strategy is generated.

8. The tower crane cluster collaborative control method for a smart construction site according to claim 1, characterized in that: After determining the trajectory overlap of the rope running trajectories of the tower cranes to be used for the tower crane tasks in a future time period based on the wind resistance-swing angle coupling error data and predicting and determining an abnormal tower crane running trajectory diagram, the method further includes: Determine the abnormal tower crane number in the abnormal tower crane operation trajectory diagram as the risk tower crane number; Send the risk tower crane number and the abnormal tower crane operation trajectory diagram to the cloud collaborative management platform, and generate lifting warning information; The lifting warning information is sent to the associated staff end corresponding to the risk tower crane number, so that the tower crane drivers who are in a collaborative relationship with each other can obtain the lifting warning information.

9. A tower crane cluster collaborative control system for a smart construction site, characterized in that: The system is capable of executing a tower crane cluster collaborative control method for a smart construction site according to any one of claims 1-8.

10. A non-volatile computer storage medium, characterized in that The storage medium is a non-volatile computer-readable storage medium, which stores at least one program. Each of the programs includes instructions. When the instructions are executed by the terminal, the terminal executes a tower crane cluster collaborative control method for a smart construction site according to any one of claims 1-8.

Images