Hanging basket construction violation monitoring system based on AI
The AI-based suspended platform construction violation monitoring system can monitor and issue early warnings for violations during suspended platform operations in real time, thus solving the safety hazards caused by violations and improving construction safety and data processing efficiency.
Patent Information
- Application Number
- CN202411141969.0
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-08-20
- Publication Date
- 2024-11-26
AI Technical Summary
In high-rise buildings and large-scale projects, there are violations of regulations during suspended platform operations, which lead to construction safety hazards that are difficult to effectively monitor and warn of using existing technologies.
An AI-based suspended platform construction violation monitoring system is adopted. The system monitors the support structure and worker movements in real time during the suspended platform operation through a violation data collection module. It combines a distributed processor and a central processor for real-time violation identification and early warning. The system uses high-definition cameras, attitude sensors, infrared sensors and other equipment to collect data, and trains a model through deep learning algorithms to identify and warn of violations.
It enables real-time monitoring and early warning during suspended platform operations, improving construction safety, reducing safety hazards caused by violations, and enhancing data processing efficiency and system reliability.
Smart Images

Figure CN119028068A_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the technical field of hanging baskets, and in particular to an AI-based hanging basket construction violation monitoring system. Background Art
[0002] In high-rise buildings and large-scale projects, hanging basket operations are an indispensable high-altitude construction method. It is common to set up a stable bracket on the parapet of the roof to carry construction personnel and materials for exterior wall cleaning, maintenance, decoration and other operations. This operation mode greatly improves construction efficiency and flexibility, but it also puts extremely high demands on safety. To ensure construction safety, all personnel involved in hanging basket operations must receive strict operation training and safety education, covering equipment operation specifications, emergency response measures and safety awareness training, aiming to reduce accident risks from the source.
[0003] However, in the actual construction process, despite the perfect training system and safety regulations, there are still many illegal operations caused by rushing the construction period, ignoring safety or taking chances, such as overloading building materials and Figure 1 Completing more tasks at one time, or performing unauthorized illegal actions, all of these behaviors seriously violate the safety operating procedures and bring great safety hazards to the construction workers and the surrounding environment. Therefore, it is urgent to develop an AI-based hanging basket construction violation monitoring system to restrain and warn hanging basket operators. Summary of the invention
[0004] The embodiment of the present invention provides an AI-based hanging basket construction violation monitoring system. First, a basic violation recognition model is established in the central processing unit based on the relevant standard data of the hanging basket combined with AI, and the violation recognition model is packaged and deployed in the distributed processor. Then, the force conditions of the bracket and the hanging basket and the workers' violation action information during the hanging basket operation are collected through the violation data collection module of the hanging basket. The collected data is transmitted to the distributed processor for real-time violation judgment, and the result is displayed in the information display and early warning module. At the same time, the collected data is asynchronously transmitted to the central processing unit to train the violation recognition model to improve its accuracy. The system can identify and warn potential violations in real time, effectively assist on-site safety management, improve overall construction safety, and solve the problem of great safety hazards to construction personnel and the surrounding environment caused by illegal overloading and illegal actions in existing hanging basket operations.
[0005] An AI-based suspended basket construction violation monitoring system includes: a violation data collection module for collecting the stress conditions of the support and the suspended basket and the workers' violation action information during the suspended basket operation, including the deformation and stress conditions of the support, the load, tilt angle and displacement information of the suspended basket, and the workers' actions and postures;
[0006] The distributed processor is arranged beside the rooftop hanging basket support and is electrically connected to the violation data collection module, and is used to identify violations of the collected data and send the results to the information display and early warning module;
[0007] A central processor, in communication with the distributed processors, is used to provide the distributed processors with a violation identification sub-model, and iterate and optimize model parameters based on data provided by the distributed processors to improve prediction accuracy and update the violation identification sub-model;
[0008] The information display and warning module is connected to the distributed processor in communication, and provides the hanging basket operation data display and sound and light warning functions based on the analysis results.
[0009] Furthermore, the violation data collection module specifically includes a worker motion monitoring unit, a support stability monitoring unit, and a hanging basket force monitoring unit;
[0010] The worker motion monitoring unit includes a high-definition camera, a posture sensor and an infrared sensor. There are two high-definition cameras, which are respectively set on the bracket and one side of the hanging basket to capture the worker's movements from multiple angles. The posture sensor is set in the safety helmet to monitor the worker's posture, movement trajectory and acceleration information in real time; the infrared sensor is set at the guardrail of the hanging basket to detect whether the worker is in a safe area;
[0011] The support stability monitoring unit includes a displacement sensor, a tilt sensor and a stress sensor installed on the key nodes of the roof support. The displacement sensor is used to monitor the small displacement changes of the support, the tilt sensor is used to monitor the tilt angle of the support to ensure that it is within a safe range, and the stress sensor is used to monitor the pressure and tension on the support;
[0012] The force monitoring unit of the hanging basket includes a weighing sensor, a tension sensor and an inclination sensor installed on the suspension system of the hanging basket. The weighing sensor is used to monitor the total weight in the hanging basket in real time to prevent overloading. The tension sensor is used to measure the tension of the wire rope to evaluate whether it is in a safe state. The inclination sensor is used to monitor the inclination angle of the hanging basket to ensure stability during operation.
[0013] Furthermore, the distributed processor specifically includes:
[0014] A data preprocessing unit is used to receive the collected raw data and perform data cleaning, feature data extraction and data standardization. These features serve as input data for subsequent violation identification models.
[0015] The distributed management unit divides the data collected by the violation data collection module according to its units, and at the same time sets up task analysis nodes based on timestamps, and adds the task analysis nodes to the distributed message queue;
[0016] Distributed message queue, used to generate asynchronous task queues and send them to the violation identification sub-model for multi-threaded processing;
[0017] The violation identification sub-model is a sub-model separated from the violation identification model generated in the central processing unit, and is used to analyze and judge the data collected by the violation data collection module;
[0018] The data transceiver unit is connected to the central processing unit for communication and is used to send the collected data to the central processing unit.
[0019] Furthermore, the central processing unit includes:
[0020] A model building unit, which builds an initial violation identification model based on the initial hanging basket design specifications and standard data in the process flow chart;
[0021] AI algorithm unit, which is used to execute violation identification algorithms, including feature extraction, classification and regression tasks;
[0022] The training unit trains the initial model based on the data uploaded by the distributed processors to improve the accuracy and generalization ability of the violation identification model;
[0023] A sub-model splitting unit splits the trained and updated violation recognition model into multiple sub-models according to the functional model;
[0024] The model update unit is used to maintain the update of sub-modules and update the split and packaged sub-models to the distributed processor to ensure the validity and accuracy of the violation data collection module.
[0025] Furthermore, the model building unit includes an action violation model, a support stability judgment model, a hanging basket force judgment model and a violation main model framework;
[0026] The action violation model is used to determine whether the actions of construction workers during hanging basket operation are illegal;
[0027] The support stability judgment model is used to judge whether the weight change of the hanging basket support exceeds the threshold during the operation of the hanging basket;
[0028] The force judgment model of the hanging basket is used to judge the force conditions of the hanging basket during operation, including the weight of the hanging basket itself, the load, and the external wind factors;
[0029] The violation master model framework is the core of the entire model building unit. It is responsible for integrating the data and results of the above three models to build a complete violation master model.
[0030] Furthermore, the submodule splitting unit is split into three independent violation identification sub-models according to the action violation model, the bracket stability judgment model and the hanging basket force judgment model, and provides data import and result export interfaces.
[0031] Furthermore, the information display and early warning module includes an alarm device and an LED display screen arranged on one side of the hanging basket. The LED display screen is used to display the stress conditions of the bracket and the hanging basket in real time, as well as whether the worker's actions are illegal. If any of the stress exceeds the threshold or an illegal action occurs, the alarm device will be controlled to emit an audible and visual alarm.
[0032] The beneficial effects of the above technical solution provided by the embodiment of the present invention include at least:
[0033] The present invention monitors various key parameters in the operation process of the hanging basket in real time, such as the stability of the support, the stress condition of the hanging basket, the operating behavior of the workers, etc., so as to timely discover and warn of potential safety hazards and effectively prevent the occurrence of safety accidents; the violation identification sub-model is deployed in the distributed processor, and the distributed processor is arranged next to the support of the hanging basket, and the electrical connection method between the distributed processor and the violation data acquisition module significantly improves the efficiency of data acquisition to data verification, ensuring the rapid response of its data verification; the distributed management unit and the distributed message queue can simultaneously process a large amount of data from multiple sensors and data sources, improving the efficiency and speed of data processing, and distributing data and tasks on multiple nodes to achieve redundancy and backup, and improving the reliability and availability of the system; during the model training process, the central processing unit can receive the uploaded data from the distributed processor in real time, and train the model according to these data. This real-time feedback and adjustment mechanism enables the system to quickly adapt to changes in the construction environment and changes in violation behaviors, and maintain efficient recognition capabilities.
[0034] Other features and advantages of the present invention will be described in the following description, and partly become apparent from the description, or understood by practicing the present invention. The purpose and other advantages of the present invention can be realized and obtained by the structures particularly pointed out in the written description, claims, and drawings.
[0035] The technical solution of the present invention is further described in detail below through the accompanying drawings and embodiments. BRIEF DESCRIPTION OF THE DRAWINGS
[0036] The accompanying drawings are used to provide a further understanding of the present invention and constitute a part of the specification. Together with the embodiments of the present invention, they are used to explain the present invention and do not constitute a limitation of the present invention. In the accompanying drawings:
[0037] Figure 1 This is a structural schematic diagram of an AI-based hanging basket construction violation monitoring system disclosed in an embodiment of the present invention.
[0038] Reference numerals:
[0039] 10. Illegal data collection module; 11. Worker motion monitoring unit; 1101. High-definition camera; 1102. Posture sensor; 1103. Infrared sensor; 12. Bracket stability monitoring unit; 1201. Displacement sensor; 1202. Tilt sensor; 1203. Stress sensor; 13. Suspension basket force monitoring unit; 1301. Weighing sensor; 1302. Tension sensor; 1303. Tilt sensor; 20. Distributed processor; 21. Data preprocessing unit; 22. Distributed management Unit; 23. Distributed message queue; 24. Violation identification sub-model; 25. Data transceiver unit; 30. Central processing unit; 31. Model building unit; 3101. Action violation model; 3102. Bracket stability judgment model; 3103. Hanging basket force judgment model; 3104. Violation main model framework; 32. AI algorithm unit; 33. Training unit; 34. Sub-model splitting unit; 35. Model update unit; 40. Information display and warning module; 41. Alarm; 42. LED display. DETAILED DESCRIPTION
[0040] The exemplary embodiments of the present disclosure will be described in more detail below with reference to the accompanying drawings. Although the exemplary embodiments of the present disclosure are shown in the accompanying drawings, it should be understood that the present disclosure can be implemented in various forms and should not be limited by the embodiments set forth herein. On the contrary, these embodiments are provided to enable a more thorough understanding of the present disclosure and to fully convey the scope of the present disclosure to those skilled in the art.
[0041] Embodiment 1
[0042] like Figure 1 As shown, an embodiment of the present invention provides an AI-based hanging basket construction violation monitoring system, including: a violation data acquisition module 10, which is used to collect the stress conditions of the bracket and the hanging basket and the workers' violation action information during the hanging basket operation, including the deformation and stress conditions of the bracket, the load, tilt angle and displacement information of the hanging basket, and the workers' actions and postures.
[0043] The violation data collection module 10 specifically includes a worker action monitoring unit 11, a support stability monitoring unit 12 and a hanging basket force monitoring unit 13;
[0044] The worker motion monitoring unit 11 comprises:
[0045] Two high-definition cameras 1101, one is set on the outside of the bracket close to the parapet to capture the movements of workers inside the hanging basket from a bird's-eye view, and the other is set on the side of the guardrail of the hanging basket to capture the movements of workers from a horizontal perspective. The combination of multiple angles ensures that data is collected without blind spots;
[0046] The posture sensor 1102 is worn on the construction worker, such as on a helmet, chest or wrist, to monitor the construction worker's body posture, motion trajectory and acceleration information in real time;
[0047] The infrared sensor 1103 is arranged at the guardrail of the hanging basket. The infrared sensor 1103 is used to monitor the distance between the construction workers and the dangerous area, such as detecting whether the workers are in the safe area to prevent accidents.
[0048] The support stability monitoring unit 12 includes a displacement sensor 1201, a tilt sensor 1202 and a stress sensor 1203 installed on the key nodes of the roof support, wherein the displacement sensor 1201 is used to monitor the small displacement changes of the support, the tilt sensor 1202 is used to monitor the tilt angle of the support to ensure that it is within a safe range, and the stress sensor 1203 is used to monitor the pressure and tension on the support and evaluate its stress state.
[0049] The hanging basket force monitoring unit 13 includes a weighing sensor 1301, a tension sensor 1302 and an inclination sensor 1303 installed on the hanging basket's suspension system, wherein the weighing sensor 1301 is installed on the hanging basket's suspension system to monitor the total weight in the hanging basket in real time to prevent overloading, the tension sensor 1302 is used to measure the tension of the wire rope to evaluate whether it is in a safe state, and the inclination sensor 1303 is used to monitor the inclination angle of the hanging basket to ensure stability during operation.
[0050] In this embodiment, the distributed processor 20 is arranged next to the rooftop hanging basket bracket and is electrically connected to the violation data collection module 10, and is used to realize instant processing of the collected data and rapid identification of violation behaviors. Compared with sending the data to the upper server for processing and feedback, this method improves the data processing efficiency and ensures the real-time nature of the identification. Once a violation is detected, the alarm information is immediately sent to the information display and early warning module 40.
[0051] The distributed processor 20 specifically includes:
[0052] The data preprocessing unit 21 is used to receive the collected raw data and perform data cleaning, feature data extraction and data standardization according to its own functional division. These features serve as input data for the subsequent violation recognition model.
[0053] The distributed management unit 22 divides the data collected by the violation data collection module 10 according to its unit function, and establishes a task analysis node based on the timestamp, and adds the task analysis node to the distributed message queue 23 to realize asynchronous processing and load balancing of tasks. At the same time, the management unit monitors the status of the queue to ensure that tasks are executed in sequence and system resources are fully utilized.
[0054] The distributed message queue 23 uses an asynchronous message passing mechanism to pass tasks and data from the distributed management unit 22 to the violation identification sub-model 24. This approach has the following advantages:
[0055] There is no need for direct communication between the distributed management unit 22 and the violation identification sub-model 24, which reduces the coupling between systems;
[0056] The violation identification sub-model 24 can process messages asynchronously, thus improving the processing capability and response speed of the system;
[0057] Through the buffering and scheduling mechanism of the message queue, balanced distribution of tasks can be achieved to avoid overloading of certain nodes.
[0058] The violation identification sub-model 24 is a sub-model separated from the violation identification model generated in the central processing unit 30, and is used to analyze and determine the data collected by the violation data collection module 10. By passing the data in the queue into the violation identification sub-model 24, the result of whether there is a violation can be quickly obtained.
[0059] The data transceiver unit 25 is connected to the central processing unit 30 for communication and is used to send the collected data to the central processing unit 30 .
[0060] In this embodiment, the central processor 30 is communicatively connected with the distributed processor 20 to provide the distributed processor 20 with a violation identification sub-model 24, and iterates and optimizes model parameters based on the data provided by the distributed processor 20 to improve the accuracy of the prediction and update the violation identification sub-model 24.
[0061] Among them, the central processing unit 30 includes a model building unit 31, an AI algorithm unit 32, a training unit 33, a sub-model splitting unit 34 and a model updating unit 35.
[0062] The model building unit 31 builds an initial violation identification model based on the initial hanging basket design specifications and standard data in the process flow chart.
[0063] Specifically, the model building unit 31 includes an action violation model 3101, a support stability judgment model 3102, a hanging basket force judgment model 3103 and a violation main model framework 3104;
[0064] Action violation model 3101 is used to determine whether the actions of construction workers during hanging basket operation are in violation of regulations;
[0065] The support stability judgment model 3102 is used to judge whether the weight change of the hanging basket support exceeds a threshold value during the operation of the hanging basket;
[0066] The hanging basket force judgment model 3103 is used to judge the force condition of the hanging basket during operation, including the weight of the hanging basket itself, the load, and the external wind force factors;
[0067] The main violation model framework 3104 is the core of the entire model building unit 31 and is responsible for integrating the data and results of the above three models to build a complete main violation model;
[0068] Through the above four functional modules, the model building unit 31 can comprehensively and accurately monitor various violations and safety hazards in the hanging basket construction process, providing a strong guarantee for construction safety and efficiency.
[0069] The AI algorithm unit 32 is used to execute the violation identification algorithm, including feature extraction, classification and regression tasks. It mainly uses a deep learning algorithm to extract features useful for violation identification from input data, and uses an optimization algorithm to adjust model parameters, such as gradient descent and Adam, to improve the recognition accuracy.
[0070] The training unit 33 trains the initial model based on the data uploaded by the distributed processor 20 to improve the accuracy and generalization ability of the violation identification model. The implementation method includes the following steps:
[0071] Step 1, receiving real-time or historical data from the distributed processor 20, including samples of normal and illegal operations;
[0072] Step 2: Enhance the received data, such as rotation, scaling, noise addition, etc., to increase data diversity;
[0073] Step 3: Use the enhanced data to train the model and optimize the model parameters through iteration;
[0074] Step 4: Evaluate the model performance on the validation set, such as accuracy, recall, and F1 score.
[0075] The sub-model splitting unit 34 splits the trained and updated violation recognition model into a plurality of sub-models according to the functional model.
[0076] Among them, the sub-module splitting unit is split into three independent violation identification sub-models 24 according to the action violation model 3101, the bracket stability judgment model 3102 and the hanging basket force judgment model 3103, and provides data import and result export interfaces. This splitting method can make the functions of the violation identification sub-model 24 in the distributed processor 20 relatively independent, so as to increase the verification efficiency and correctness of different functional data in the violation data acquisition module 10 and avoid data interference.
[0077] The model updating unit 35 is used to maintain the update of the sub-modules and update the split and packaged sub-models to the distributed processor 20 to ensure the validity and accuracy of the violation data collection module 10.
[0078] In this embodiment, the information display and warning module 40 is connected to the distributed processor 20 for communication, and provides a display of the hanging basket operation data and an audio and visual warning function based on the analysis results.
[0079] Specifically, the information display and warning module 40 includes an alarm 41 and an LED display screen 42 arranged on one side of the hanging basket. The LED display screen 42 is used to display the stress conditions of the bracket and the hanging basket in real time, as well as whether the worker's actions are illegal. If any of the stress exceeds the threshold or there is an illegal action, the alarm 41 will be controlled to emit an audible and visual alarm.
[0080] As a preferred embodiment, the hanging basket construction violation monitoring system also includes an emergency protection module, which includes:
[0081] Height adjustment unit: when workers are not wearing safety equipment or the basket is overloaded, the system automatically adjusts the height of the basket and lowers it to a safe area, and resumes work after the problem is resolved;
[0082] Safety locking unit: In an emergency, the system activates the safety locking device to fix the hanging basket in its current position to prevent it from falling out of control due to external force or failure;
[0083] The remote intervention unit allows the security manager to remotely take over the basket control system through the central processor 30, and perform emergency operations or issue instructions to the basket to ensure rapid response and effective handling in emergency situations.
[0084] Embodiment 2
[0085] The distributed processor 20 also includes an identification and evaluation unit, which is used to determine the recognition speed of the data in the distributed message queue 23 in the violation identification sub-model 24 and the matching degree of the data with the model. When the recognition speed exceeds the set threshold or its matching degree is lower than the threshold, the current task queue data is actively sent to the central processor 30, and a scheduling instruction is issued to increase the computing power of the central processor 30 to analyze and process the current queue, thereby ensuring its recognition response speed and effectiveness.
[0086] It should be understood that the specific order or hierarchy of steps in the disclosed process is an example of an exemplary method. Based on design preferences, it should be understood that the specific order or hierarchy of steps in the process can be rearranged without departing from the scope of protection of the present disclosure. The attached method claims present the elements of the various steps in an exemplary order and are not intended to be limited to the specific order or hierarchy described.
[0087] In the above detailed description, various features are grouped together in a single embodiment to simplify the disclosure. This method of disclosure should not be interpreted as reflecting an intention that the embodiments of the claimed subject matter require more features than are clearly stated in each claim. On the contrary, as reflected in the appended claims, the invention is in a state of having less than all the features of the disclosed individual embodiments. Therefore, the appended claims are hereby expressly incorporated into the detailed description, with each claim standing on its own as a separate preferred embodiment of the invention.
[0088] Those skilled in the art will also appreciate that the various illustrative logic blocks, modules, circuits, and algorithmic steps described in conjunction with the embodiments herein can all be implemented as electronic hardware, computer software, or a combination thereof. In order to clearly illustrate the interchangeability between hardware and software, various illustrative components, blocks, modules, circuits, and steps are generally described above around their functions. Whether such functions are implemented as hardware or software depends on specific applications and the design constraints imposed on the entire system. A skilled person can implement the described functions in an alternative manner for each specific application, but such implementation decisions should not be interpreted as departing from the scope of protection of the present disclosure.
[0089] The steps of the method or algorithm described in conjunction with the embodiments herein may be directly embodied as hardware, a software module executed by a processor, or a combination thereof. The software module may be located in a RAM memory, a flash memory, a ROM memory, an EPROM memory, an EEPROM memory, a register, a hard disk, a mobile disk, a CD-ROM, or any other form of storage medium well known in the art. An exemplary storage medium is connected to the processor so that the processor can read information from the storage medium and can write information to the storage medium. Of course, the storage medium may also be an integral part of the processor. The processor and the storage medium may be located in an ASIC. The ASIC may be located in a user terminal. Of course, the processor and the storage medium may also be present in a user terminal as discrete components.
[0090] For software implementation, the techniques described in this application can be implemented with modules (e.g., procedures, functions, etc.) that perform the functions described in this application. These software codes can be stored in a memory unit and executed by a processor. The memory unit can be implemented within the processor or outside the processor. In the latter case, it is coupled to the processor in a communication manner via various means, which are well known in the art.
[0091] The above description includes examples of one or more embodiments. Of course, it is impossible to describe all possible combinations of components or methods for the purpose of describing the above embodiments, but it should be recognized by those skilled in the art that the various embodiments may be further combined and arranged. Therefore, the embodiments described herein are intended to cover all such changes, modifications and variations that fall within the scope of protection of the appended claims. In addition, with respect to the term "comprising" used in the specification or claims, the word is covered in a manner similar to the term "including", just as "including," is explained as a transitional word in the claims. In addition, any term "or" used in the specification of the claims is intended to mean "non-exclusive or".
Claims
1. An AI-based hanging basket construction violation monitoring system, characterized in that: include: The violation data collection module (10) is used to collect the stress conditions of the support and the hanging basket and the workers' violation action information during the hanging basket operation, including the deformation and stress conditions of the support, the load, tilt angle and displacement information of the hanging basket, and the workers' actions and postures; A distributed processor (20) is arranged beside the rooftop hanging basket support and is electrically connected to the violation data collection module (10) for identifying violations of the collected data and sending the results to the information display and warning module (40); A central processor (30) is connected to the distributed processor (20) for providing the distributed processor (20) with a violation identification sub-model (24), iterating and optimizing model parameters based on data provided by the distributed processor (20), improving prediction accuracy, and updating the violation identification sub-model (24); The information display and warning module (40) is connected to the distributed processor (20) for communication and provides a display of the hanging basket operation data and an audible and visual warning function based on the analysis result.
2. The AI-based hanging basket construction violation monitoring system according to claim 1, characterized in that: The violation data collection module (10) specifically includes a worker action monitoring unit (11), a support stability monitoring unit (12) and a hanging basket force monitoring unit (13); The worker motion monitoring unit (11) comprises a high-definition camera (1101), a posture sensor (1102) and an infrared sensor (1103), wherein two high-definition cameras (1101) are respectively arranged on one side of the support and the hanging basket to capture the worker's motion from multiple angles; the posture sensor (1102) is arranged in the safety helmet to monitor the worker's posture, motion trajectory and acceleration information in real time; the infrared sensor (1103) is arranged at the guardrail of the hanging basket to detect whether the worker is in a safe area; A support stability monitoring unit (12) comprises a displacement sensor (1201), a tilt sensor (1202) and a stress sensor (1203) installed at a key node of the roof support, wherein the displacement sensor (1201) is used to monitor a small displacement change of the support, the tilt sensor (1202) is used to monitor the tilt angle of the support to ensure that it is within a safe range, and the stress sensor (1203) is used to monitor the pressure and tension borne by the support; The hanging basket force monitoring unit (13) comprises a weighing sensor (1301), a tension sensor (1302) and an inclination sensor (1303) installed on the hanging basket's suspension system, wherein the weighing sensor (1301) is used to monitor the total weight in the hanging basket in real time to prevent overloading, the tension sensor (1302) is used to measure the tension of the wire rope to evaluate whether it is in a safe state, and the inclination sensor (1303) is used to monitor the inclination angle of the hanging basket to ensure stability during operation.
3. The AI-based hanging basket construction violation monitoring system as claimed in claim 2 is characterized in that: The distributed processor (20) specifically includes: A data preprocessing unit (21) is used to receive the collected raw data and perform data cleaning, feature data extraction and data standardization on the raw data, and these features are used as input data for a subsequent violation identification model; The distributed management unit (22) divides the data collected by the violation data collection module (10) into units, establishes a task analysis node based on a timestamp, and adds the task analysis node to a distributed message queue (23); A distributed message queue (23) is used to generate an asynchronous task queue and send it to the violation identification sub-model (24) for multi-threaded processing; The violation identification sub-model (24) is a sub-model separated from the violation identification model generated in the central processing unit (30), and is used to analyze and judge the data collected by the violation data collection module (10); The data transceiver unit (25) is connected to the central processor (30) for communication and is used to send the collected data to the central processor (30).
4. The AI-based hanging basket construction violation monitoring system as claimed in claim 3 is characterized in that: The central processing unit (30) comprises: A model building unit (31) builds an initial violation identification model based on the initial hanging basket design specification and standard data in the process flow chart; An AI algorithm unit (32), for executing a violation identification algorithm, including feature extraction, classification, and regression tasks; A training unit (33) trains the initial model based on the data uploaded by the distributed processor (20) to improve the accuracy and generalization ability of the violation identification model; A sub-model splitting unit (34) splits the trained and updated violation recognition model into multiple sub-models according to the functional model; The model updating unit (35) is used to maintain the updating of the sub-modules and update the split and packaged sub-models to the distributed processor (20) to ensure the validity and accuracy of the illegal data collection module (10).
5. The AI-based hanging basket construction violation monitoring system as claimed in claim 4 is characterized in that: The model building unit (31) includes an action violation model (3101), a support stability judgment model (3102), a hanging basket force judgment model (3103) and a violation main model framework (3104); The action violation model (3101) is used to determine whether the actions of the construction personnel during the hanging basket operation are illegal; The support stability judgment model (3102) is used to judge whether the weight change of the hanging basket support exceeds a threshold value during the operation of the hanging basket; The hanging basket force judgment model (3103) is used to judge the force condition of the hanging basket during operation, including the weight of the hanging basket itself, the load and the external wind force factors; The main violation model framework (3104) is the core of the entire model building unit (31), and is responsible for integrating the data and results of the above three models to build a complete main violation model.
6. The AI-based hanging basket construction violation monitoring system as claimed in claim 5, characterized in that: The submodule splitting unit is split into three independent violation identification submodels (24) according to the action violation model (3101), the support stability judgment model (3102) and the hanging basket force judgment model (3103), and provides data import and result export interfaces.
7. The AI-based hanging basket construction violation monitoring system according to claim 1, characterized in that: The information display and warning module (40) comprises an alarm (41) and an LED display screen (42) arranged on one side of the hanging basket. The LED display screen (42) is used to display the stress conditions of the bracket and the hanging basket in real time, and to indicate whether the worker's actions are in violation of regulations. If any stress exceeds a threshold or a violation of regulations occurs, the alarm (41) is controlled to emit an audible and visual alarm.
Citation Information
Cited By
Balancing device and method for monitoring walking of hanging basket
CN119803775A
System for supporting curtain wall construction hanging basket at light well to bear force by means of scaffold
CN120315481A
New energy intelligent operation and maintenance system for building construction hanging basket
CN122186927A
