CN-122009991-A - Intelligent safety monitoring and anti-collision system for tower crane and lifter

CN122009991ACN 122009991 ACN122009991 ACN 122009991ACN-122009991-A

Abstract

The invention provides an intelligent safety monitoring and anti-collision system for a tower crane and a lifter, and relates to the technical field of building construction safety monitoring. The system builds a five-layer architecture of multisource perception, edge calculation, fusion communication, cloud platform and application interaction, wherein a tower crane end integrates a moment sensor, a rotary encoder, a wind speed sensor, a height encoder and a GNSS/RTK dual-mode positioning module, a lifter end is provided with a load sensor, a dual-axis inclination sensor and a network camera, and data intercommunication is realized through a communication network. And constructing a dynamic collision cone model introducing wind speed disturbance compensation by using a distributed space-time coordination mechanism and adopting an LSTM neural network prediction equipment track based on an attention mechanism, and operating an improved ORCA algorithm introducing jerk constraint to realize optimal avoidance of the group tower. The system disclosed by the invention combines the BIM three-dimensional geometric model and real-time working condition data to construct a digital twin body, supports acousto-optic broadcasting linkage alarm, and is suitable for intelligent safety management of large-scale construction projects.

Inventors

DU ZHIXIANG
LI LEI
Hu Lechao
GUI BEN
GUO CHAOHUI
ZENG TING
LIU JIANPING
WANG JUNJIE

Assignees

内蒙古三峡蒙能能源有限公司
三峡陆上新能源投资有限公司
中国长江三峡集团有限公司

Dates

Publication Date: 20260512
Application Date: 20260319

Claims (10)

1. The intelligent safety monitoring and anti-collision system for the tower crane and the lifter is characterized by comprising a multi-source heterogeneous sensor network, an edge gateway, a cloud decision platform and a BIM model server; The sensor network is deployed on the tower crane and the lifter body, acquires working condition parameters and spatial position data, and transmits the working condition parameters and spatial position data to the edge gateway through the network; an edge gateway embeds a dynamic collision cone modeling module and an improved ORCA obstacle avoidance algorithm introducing Jerk (Jerk) constraint, and calculates collision risk among devices in real time; The cloud platform runs an LSTM track prediction model and a double digital twin engine, generates a global risk thermodynamic diagram and optimizes edge gateway model parameters; the system realizes early warning response through a layered collaborative decision mechanism, wherein the layered collaborative decision mechanism comprises an edge emergency braking decision, an edge obstacle avoidance speed planning decision and a cloud model parameter optimization decision.
2. The system of claim 1, wherein dynamic collision cone modeling and coordinate transformation algorithms are used to abstract each tower crane into a motion rigid body model, calculate the relative collision cone for any two tower cranes, and introduce a wind speed disturbance compensation mechanism to improve the prediction robustness.
3. The system of claim 1, wherein an improved ORCA obstacle avoidance algorithm operated by the edge gateway achieves speed smoothing by introducing jerk constraints; Constructing a quadratic programming objective function comprising an efficiency term and a smoothing term, wherein the efficiency term is used for minimizing the deviation between the calculated speed and the preferred speed, and the smoothing term is used for punishing the change rate of acceleration; Solving a quadratic programming objective function, and outputting an optimal avoidance speed instruction meeting the physical characteristics of the motor so as to eliminate mechanical stress on a tower crane structure and current impact on a driving motor caused by speed mutation.
4. The system of claim 1, wherein a dual digital twinning method is constructed, the first is equipment digital twinning based on BIM technology, and the second is personnel digital twinning fusing multi-dimensional data such as identity information, qualification certificates and the like.
5. The system of claim 4, wherein the digital twin of the device comprises component attributes, kinematic pair constraints and mechanical parameters, and is capable of mapping operating condition parameters in real time and deducing future motion trajectories of the device to generate a risk thermodynamic diagram.
6. The system of claim 4, wherein personnel digital twinning is achieved through UWB tags, GNSS positioning and inertial navigation, extended Kalman filter EKF algorithm is adopted to fuse UWB, GNSS and inertial navigation data, and personnel positions are mapped to a BIM model coordinate system through coordinate transformation.
7. The system of claim 2, wherein a distributed status broadcasting mechanism is used between the towers to ensure communication between the towers, and the status snapshot is sent to the cloud offload processing when the local computing resources are insufficient.
8. The system of claim 7, wherein the cloud generates future track thermodynamic diagrams for each tower crane via the LSTM track prediction model, and issues parameter updates to modify the edge gateway model when the predicted track deviates significantly from the current edge gateway calculation.
9. The system of claim 1, wherein the hierarchical system decision mechanism comprises: the first layer edge emergency braking decision is made, and when the risk value exceeds the set emergency threshold value, local braking is directly triggered; performing a second-layer edge obstacle avoidance speed planning decision, and operating an improved ORCA algorithm to solve the optimal avoidance speed; The third layer cloud model parameter optimization decision is made, and a global risk thermodynamic diagram is generated; Wherein the first layer of decisions has the highest priority and cannot be overridden or interrupted by the second or third layer of decisions.
10. The system of claim 9, wherein the third layer cloud model parameter optimization decision comprises continuous learning closed loop, namely edge collection samples, cloud training, model issuing and edge optimization, wherein the model parameters are dynamically adjusted according to real-time working conditions, and computing resources of an edge gateway and a cloud are reasonably distributed.

Description

Intelligent safety monitoring and anti-collision system for tower crane and lifter Technical Field The invention relates to the technical field of building construction safety monitoring, in particular to an intelligent safety monitoring and anti-collision system for a tower crane and a lifter. Background With the rapid development of large-scale capital construction projects, the tower crane and the lifter are used as core construction equipment, and the cooperative operation scene is increasingly frequent. However, because the running track of the equipment is complex, the operation space is limited, the environmental interference is variable, collision accidents are very easy to occur in the process of cross operation, and equipment damage, casualties and engineering delay are caused. The prior art has the defects that the prior art depends on GNSS/RTK dual-mode positioning equipment, and alarms through presetting a fixed safety distance threshold. The scheme does not consider the dynamic motion characteristics and environmental disturbance of equipment, so that collision prediction accuracy is low, false report or missing report is easy to occur, dynamic change of real working conditions cannot be adapted, part of systems upload equipment position data to a cloud server, the cloud server analyzes collision risk and issues instructions, but the architecture has obvious response delay, is difficult to intervene in time in an emergency avoidance scene, and meanwhile, network transmission dependence is high, data loss is easy to occur in a construction site signal weak or congestion area, and real-time requirements of safety response cannot be met. Under the common environments of construction sites such as strong wind, rain and fog, the precision of the traditional positioning equipment is reduced, and collision prediction distortion is caused. Therefore, an intelligent safety solution capable of realizing real-time prediction of dynamic collision risk, layered real-time response, complex environment self-adaption and full scene collaborative monitoring is needed to fill the technical blank of the industry. Disclosure of Invention The invention aims to solve the technical problem of providing an intelligent safety monitoring and anti-collision system for a tower crane and a lifter, which solves the problem of cooperative safety control under the crossing working scene of a construction site tower crane group and the lifter, and maximizes the working efficiency on the premise of ensuring absolute safety. The technical scheme adopted by the invention is to provide an intelligent safety monitoring and anti-collision system for a tower crane and a lifter, which comprises a multi-source heterogeneous sensor network, an edge gateway, a cloud decision platform and a BIM model server; The sensor network is deployed on the tower crane and the lifter body, acquires working condition parameters and spatial position data, and transmits the working condition parameters and spatial position data to the edge gateway through the network; an edge gateway embeds a dynamic collision cone modeling module and an improved ORCA (Optimal Reciprocal Collision Avoidance) obstacle avoidance algorithm introducing Jerk (Jerk) constraint, calculates collision risk among devices in real time, and directly triggers local braking when a risk value exceeds an emergency threshold; The cloud platform runs an LSTM track prediction model and a double digital twin engine, generates a global risk thermodynamic diagram and optimizes edge gateway model parameters; the system performs early warning response and continuous learning closed loop through a layered collaborative decision mechanism. Preferably, a dynamic collision cone modeling and coordinate transformation algorithm is adopted, each tower crane is abstracted into a motion rigid body model, the relative collision cone is calculated for any two tower cranes, and a wind speed disturbance compensation mechanism is introduced to improve the prediction robustness. Preferably, an improved ORCA obstacle avoidance algorithm operated by the edge gateway realizes speed smoothing by introducing jerk constraint; Constructing a quadratic programming objective function comprising an efficiency term and a smoothing term, wherein the efficiency term is used for minimizing the deviation between the calculated speed and the preferred speed, and the smoothing term is used for punishing the change rate of acceleration; Solving a quadratic programming objective function, and outputting an optimal avoidance speed instruction meeting the physical characteristics of the motor so as to eliminate mechanical stress on a tower crane structure and current impact on a driving motor caused by speed mutation. Preferably, a double digital twin method is constructed, wherein the first party is equipment digital twin based on BIM technology, and the second party is personnel digital twin fusing multidimensional data such