Intelligent safety monitoring and early warning system and method for climbing operation

Abstract

The invention discloses an intelligent safety monitoring and early warning system and method for climbing operation, and the system comprises a sensing and data collection module which is used for obtaining the operation data of a climbing operator in real time through collection equipment, and transmitting the operation data to a data processing and analysis module; the data processing and analysis module is used for receiving the operation data, performing feature extraction on the data through a deep learning network to obtain key features, performing partition analysis on the climbing operation personnel in the operation area based on the key features, obtaining an analysis result and sending the analysis result to the early warning and feedback module; and the early warning and feedback module is used for receiving the analysis result, generating illegal operation early warning information, generating an early warning report according to the illegal operation early warning information and sending the early warning report to related personnel. According to the method, illegal behaviors and safety risks are recognized in time, early warning is performed in a polymorphic mode, and closed-loop management from operation task acquisition, process dynamic monitoring to post data tracing is formed through deep docking with a power plant two-ticket system, so that the accident response time is shortened.

Description

Technical Field

[0001] This invention relates to the field of monitoring and early warning technology, and in particular to an intelligent safety monitoring and early warning system and method for working at heights. Background Technology

[0002] In the power generation industry, high-altitude operations account for over 60% of core work scenarios such as tower maintenance and boiler upkeep, making them a crucial link in ensuring the stable operation of the power system and a key area for safety risk prevention and control. Statistics show that in 2024, falls from heights accounted for 34% of all safety accidents in power generation companies nationwide, with 72% of these accidents directly related to the improper use of protective equipment or a lack of oversight. The effectiveness of safety management for high-altitude operations directly impacts the stability of power production and the safety of workers. As the power industry continues to raise its requirements for operational safety and standardization, traditional management models relying on passive protective measures are no longer sufficient to meet the needs of modern power generation companies for comprehensive and refined safety management of high-altitude operations. There is an urgent need to build an active monitoring and early warning system using intelligent technologies to reduce accident risks.

[0003] However, existing safety management methods for working at heights have significant shortcomings: On the one hand, traditional passive protective equipment such as safety belts and safety nets can only provide protection after an accident occurs, and cannot provide real-time monitoring and early warning of violations such as workers not wearing safety belts, not hooking them properly, or using them at a low position. Furthermore, hazards such as hook detachment or failure to fasten belts are difficult to detect in a timely manner. On the other hand, the manual supervision model is inefficient and cannot achieve comprehensive and real-time monitoring of workers' posture, the surrounding environment (near power lines, strong winds, lightning), and personnel's vital signs, resulting in blind spots in supervision. At the same time, the existing system lacks effective integration with the power plant's two-ticket system, failing to form a closed-loop management system for pre-operation task assignment, in-operation risk control, and post-operation data traceability. This leads to non-standard operating procedures, delayed risk response, and an average accident response time of more than 8 minutes, making it difficult to meet the efficient and accurate safety management needs of power generation industries for working at heights. Summary of the Invention

[0004] The purpose of this section is to outline some aspects of embodiments of the present invention and to briefly describe some preferred embodiments. Simplifications or omissions may be made in this section, as well as in the abstract and title of this application, to avoid obscuring the purpose of these documents; however, such simplifications or omissions should not be construed as limiting the scope of the invention.

[0005] In view of the aforementioned existing problems, this invention is proposed. Therefore, this invention provides an intelligent safety monitoring and early warning system for high-altitude operations, solving the problems of traditional passive protection measures in the power generation industry being unable to monitor violations in real time, leading to delayed risk response and a lack of closed-loop management.

[0006] To solve the above-mentioned technical problems, the present invention provides the following technical solution: In a first aspect, the present invention provides an intelligent safety monitoring and early warning system for working at heights, comprising: The sensing and data acquisition module is used to acquire the work data of the workers at height in real time through the acquisition device, and transmit the work data to the data processing and analysis module. The data processing and analysis module is used to receive the operation data, extract key features from the data through a deep learning network, perform zoning analysis on the personnel working at height in the operation area based on the key features, obtain the analysis results and send them to the early warning and feedback module. The early warning and feedback module is used to receive the analysis results, generate early warning information for violations, generate an early warning report from the early warning information for violations, and send it to relevant personnel.

[0007] As a preferred embodiment of the intelligent safety monitoring and early warning system for high-altitude operations described in this invention, the system acquires operational data of high-altitude workers in real time through data acquisition devices, including: Using sensor devices to collect data on equipment worn by workers at height, their location, and their movement; Use sensing devices to collect near-electricity data and weather parameters; Based on the device wearing data, location data, and motion data, determine whether there is an abnormal state. If there is an abnormal state, execute the first operation. Based on the power data and weather parameters, determine whether there is an operational risk. If there is an operational risk, then execute the second operation.

[0008] As a preferred embodiment of the intelligent safety monitoring and early warning system for high-altitude operations described in this invention, key features are obtained by extracting features from the data through a deep learning network, including: The deep learning network first preprocesses the input job data, converting unstructured data into a standardized feature matrix; After multi-scale dimensionality reduction of the standardized feature matrix by fusion downsampling algorithm, the self-attention pyramid pooling module is used to perform hierarchical attention weight allocation on the dimensionality-reduced features to obtain multi-dimensional features. The multi-dimensional features are fused by a fully connected layer of a deep learning network to output key features of the safety status and environmental risk level of workers working at heights. Hierarchical attention weighting involves assigning higher weights to key features and lower weights to secondary features.

[0009] As a preferred embodiment of the intelligent safety monitoring and early warning system for high-altitude operations described in this invention, the system includes: performing zoning analysis of high-altitude workers in the work area based on the key features, obtaining the analysis results, and sending them to the early warning and feedback module, including: The work area includes a work preparation area, a climbing area, and a high-altitude walking area. Based on the work area and combined with the location data features in the key features, the real-time area where the climbing personnel are located is determined. Establish safety assessment models for different areas: analyze equipment wearing data characteristics in the work preparation area, analyze motion data characteristics in the climbing area, and integrate position data characteristics and motion data characteristics in the high-altitude walking area. The analysis results for each region are compared with preset safety thresholds to generate analysis results that include the type of violation and risk level of the region, and these results are sent to the early warning and feedback module.

[0010] As a preferred embodiment of the intelligent safety monitoring and early warning system for high-altitude operations described in this invention, the method for generating an early warning report from the violation warning information and sending it to relevant personnel includes: Based on the regional violation types and risk levels in the analysis results, corresponding violation warning information is generated. The warning information is then integrated into a warning report containing the time, personnel, violation details, and risk level, and sent to relevant personnel in a polymorphic manner. The early warning reports and corresponding operational data are archived and uploaded to the power plant's two-ticket system to achieve traceability and closed-loop management of early warning information.

[0011] As a preferred embodiment of the intelligent safety monitoring and early warning system for high-altitude operations described in this invention, the power plant's two-ticket system includes: Before the operation, the sensing and data acquisition module obtains the high-altitude operation task information from the power plant's two-ticket system through the data interface, including the operation name, operation time, operation area, list of operators and safety requirements, in order to match the binding relationship between the data acquisition equipment and the operators. During the operation, the data processing and analysis module synchronizes the zoning analysis results to the power plant's two-ticket system in real time, updates the dynamic status of the operation, and enables the two-ticket system to track the operation progress in real time. After generating an early warning report, the early warning and feedback module uploads the early warning information and processing results to the power plant's two-ticket system, and archives them in conjunction with the execution records of work tickets and operation tickets. After the operation is completed, it pushes the full-process data of the operation to the two-ticket system to complete the information for closed-loop management of the operation in the two-ticket system. The power plant's two-ticket system is used to assign tasks, monitor the process, and archive the results of the high-altitude operation.

[0012] As a preferred embodiment of the intelligent safety monitoring and early warning system for high-altitude operations described in this invention, the first operation and the second operation include: The first operation includes: when an abnormal state is detected, the intelligent safety belt monitor will issue an audible and visual alarm to the workers working at height to remind them to correct the situation, and at the same time, the abnormal state data will be transmitted to the data processing and analysis module in real time to trigger key monitoring of the workers; if the abnormal state continues for a preset time, the early warning and feedback module will be automatically activated to push warning information to the management personnel. The second operation includes: when an operational risk is determined to exist, generating a near-electricity warning based on near-electricity data and prompting workers to stay away from energized areas; generating an environmental risk warning based on weather parameters exceeding the threshold; simultaneously triggering an operation suspension suggestion; and having the warning and feedback module push the risk warning and suggestion to the work supervisor to assist in deciding whether to terminate the operation.

[0013] Secondly, the present invention provides a method for an intelligent safety monitoring and early warning system for high-altitude operations, comprising, Real-time data on the work of personnel working at heights is acquired through data acquisition equipment; Based on the operational data, a deep learning network is used to extract key features from the data. Based on the key features, the personnel working at height in the operational area are analyzed by region to obtain the analysis results. Based on the analysis results, a warning message for violation of regulations is generated, and a warning report is generated and sent to relevant personnel.

[0014] Thirdly, the present invention provides a computing device, comprising: Memory and processor; The memory is used to store computer-executable instructions, and the processor is used to execute the computer-executable instructions. When the computer-executable instructions are executed by the processor, they implement the steps of the intelligent safety monitoring and early warning system for high-altitude operations.

[0015] Fourthly, the present invention provides a computer-readable storage medium storing computer-executable instructions that, when executed by a processor, implement the steps of the intelligent safety monitoring and early warning system for high-altitude operations.

[0016] Compared with existing technologies, the beneficial effects of this invention are as follows: This invention achieves accurate analysis of operational data through the collaborative work of sensing and data acquisition modules, data processing and analysis modules, and early warning and feedback modules, combined with deep learning networks. It can not only monitor the equipment wearing, location, movement status, and surrounding environmental parameters of operators in real time, and promptly identify violations and safety risks and issue early warnings in a multi-mode manner, but also form a closed-loop management system from task acquisition and dynamic process monitoring to post-event data traceability by deeply integrating with the power plant's two-ticket system. This shortens accident response time, reduces the incidence of accidents such as falls from heights, improves the real-time, accuracy, and standardization of safety supervision for working at heights, and ensures the life safety of workers working at heights in the power generation industry and the stability of power production. Attached Figure Description

[0017] To more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings used in the following description of the embodiments will be briefly introduced. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0018] Figure 1 This is a schematic diagram of an intelligent safety monitoring and early warning system for high-altitude operations according to an embodiment of the present invention.

[0019] Figure 2 This is a schematic diagram of the network topology of an intelligent safety monitoring and early warning system for high-altitude operations according to an embodiment of the present invention. Detailed Implementation

[0020] To make the above-mentioned objects, features, and advantages of the present invention more apparent and understandable, specific embodiments of the present invention will be described in detail below with reference to the accompanying drawings. Obviously, the described embodiments are only a part of the embodiments of the present invention, and not all of them. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort should fall within the protection scope of the present invention.

[0021] Many specific details are set forth in the following description in order to provide a full understanding of the invention. However, the invention may also be practiced in other ways different from those described herein, and those skilled in the art can make similar extensions without departing from the spirit of the invention. Therefore, the invention is not limited to the specific embodiments disclosed below.

[0022] Secondly, the term "one embodiment" or "embodiment" as used herein refers to a specific feature, structure, or characteristic that may be included in at least one implementation of the present invention. The phrase "in one embodiment" appearing in different places in this specification does not necessarily refer to the same embodiment, nor is it a single or selective embodiment that is mutually exclusive with other embodiments.

[0023] This invention is described in detail with reference to the schematic diagrams. When detailing the embodiments of this invention, for ease of explanation, the cross-sectional views illustrating the device structure may be partially enlarged, not adhering to the usual scale. Furthermore, the schematic diagrams are merely examples and should not be construed as limiting the scope of protection of this invention. In actual fabrication, the three-dimensional spatial dimensions of length, width, and depth should be included.

[0024] Furthermore, in the description of this invention, it should be noted that the terms "upper," "lower," "inner," and "outer," etc., indicate the orientation or positional relationship based on the orientation or positional relationship shown in the accompanying drawings. These terms are used only for the convenience of describing the invention and for simplifying the description, and do not indicate or imply that the system or element referred to must have a specific orientation, or be constructed and operated in a specific orientation. Therefore, they should not be construed as limitations on the invention. In addition, the terms "first," "second," or "third" are used for descriptive purposes only and should not be construed as indicating or implying relative importance.

[0025] Unless otherwise explicitly specified and limited, the terms "installation," "connection," and "joining" in this invention should be interpreted broadly. For example, they can refer to fixed connections, detachable connections, or integral connections; similarly, they can refer to mechanical connections, electrical connections, or direct connections, or indirect connections through an intermediate medium, or internal connections between two components. Those skilled in the art can understand the specific meaning of the above terms in this invention based on the specific circumstances.

[0026] Example 1 Reference Figure 1-2 As one embodiment of the present invention, an intelligent safety monitoring and early warning system for high-altitude operations is provided, comprising: The sensing and data acquisition module is used to acquire the work data of the workers at height in real time through the acquisition device and transmit the work data to the data processing and analysis module. The data processing and analysis module is used to receive operational data, extract key features from the data through a deep learning network, perform zoning analysis on the personnel working at height in the operational area based on the key features, obtain the analysis results, and send them to the early warning and feedback module. The early warning and feedback module is used to receive analysis results, generate early warning information for violations, generate early warning reports for violations, and send them to relevant personnel.

[0027] In this embodiment of the application, the operation data of personnel working at heights is acquired in real time through a data acquisition device, including: Using sensor devices to collect data on equipment worn by workers at height, their location, and their movement; Use sensing devices to collect near-electricity data and weather parameters; Based on device wearing data, location data, and motion data, determine whether there is an abnormal state. If an abnormal state is found, execute the first operation. Based on power data and weather parameters, determine whether there is an operational risk. If an operational risk exists, proceed with the second operation.

[0028] Specifically, the first operation includes: when an abnormal state is detected, the intelligent safety belt monitor will issue an audible and visual alarm to the workers working at height to remind them to correct the situation, and at the same time, the abnormal state data will be transmitted to the data processing and analysis module in real time to trigger key monitoring of the workers; if the abnormal state continues for a preset time, the early warning and feedback module will be automatically activated to push warning information to the management personnel. The second operation includes: when an operational risk is determined to exist, generating a near-electricity warning based on near-electricity data and prompting workers to stay away from energized areas; generating an environmental risk warning based on weather parameters exceeding the threshold; simultaneously triggering an operation suspension suggestion; and having the warning and feedback module push the risk warning and suggestion to the work supervisor to assist in deciding whether to terminate the operation.

[0029] In some embodiments, device wearing data is collected by a Hall sensor component integrated into the smart seat belt, including seat belt wearing status (not worn, half worn, fully worn), hook status (both hooks not engaged, one hook not engaged, both hooks not high engaged, one hook not high engaged), and buckle status (not locked, half locked, fully locked). Simultaneously, force distribution data of each fixed point of the multi-point fixed system are collected; location data is collected through the Beidou positioning component, including the real-time coordinates of the operator, the distance to the adjacent dangerous area, and the boundary determination data of the work area, to achieve centimeter-level spatial perception; Motion data is collected through posture displacement sensing components, including the worker's body tilt angle, center of gravity offset, foot movement frequency, height off the ground, whether in a fall state, and duration of silence. At the same time, it captures the stress data of the climbing structure and the subtle vibration waveforms corresponding to the weld cracks in the steel structure. Near-field power data is collected through near-field induction sensing components, including surrounding electric field strength signals and sensing data on the presence of near-field power risks; weather parameters are collected through environmental sensing components, including real-time wind speed, lightning warning signals, and ambient temperature data.

[0030] In some embodiments, when the device wearing data determines that there are abnormalities such as not wearing a safety belt or not having the double hooks attached, or when the device location data determines that the device is close to a dangerous area, or when the motion data determines that the tilt angle exceeds 30°, the device is silent for more than 5 minutes, or a fall trajectory appears, the first operation is performed: the smart safety belt monitor immediately issues an audible and visual alarm to remind the worker, and at the same time marks the abnormal data as high priority and transmits it to the data processing and analysis module, triggering dynamic key tracking of the worker and updating its status data every 2 seconds; When the electric field strength exceeds the safety threshold based on near-electricity data, or when the wind force is determined to be ≥6 based on weather parameters and a lightning warning is received, the second operation is executed: the system displays a text prompt on the smart safety belt terminal, and at the same time, the warning and feedback module pushes warning information containing the risk type, the location of the workers, and suggestions for suspending or evacuating the work to the person in charge.

[0031] In this embodiment of the application, key features are obtained by extracting features from data using a deep learning network, including: Deep learning networks first preprocess the input task data, converting unstructured data into a standardized feature matrix; After multi-scale dimensionality reduction of the standardized feature matrix by fusion downsampling algorithm, the self-attention pyramid pooling module is used to perform hierarchical attention weight allocation on the dimensionality-reduced features to obtain multi-dimensional features. By fusing multi-dimensional features through a fully connected layer of a deep learning network, key features of the safety status and environmental risk level of workers working at heights are output. Hierarchical attention weighting involves assigning higher weights to key features and lower weights to secondary features.

[0032] In some embodiments, during the preprocessing stage of work data, differentiated processing methods are adopted for different types of unstructured data: data cleaning is performed on the equipment wearing data and motion data collected by the sensing devices to remove outliers caused by equipment vibration, and the data is mapped to the [0,1] interval through normalization processing; coordinate transformation is performed on the location data to unify it into three-dimensional coordinate values ​​under the local coordinate system of the work area; near power data and weather parameters are digitally encoded to convert analog signals into 16-bit precision digital signals and discrete signals into binary identifiers, and finally all processed data are integrated to form a standardized feature matrix with unified dimensions.

[0033] In some embodiments, the fusion downsampling algorithm adopts a dual-branch fusion structure of max pooling and average pooling to perform multi-scale dimensionality reduction on the standardized feature matrix. The max pooling branch retains the peak information of key abrupt features such as device wearing abnormalities and drop impacts in the feature matrix, while the average pooling branch retains the overall distribution information of smooth features such as position changes and heart rate trends. The dual-branch output results are weighted and fused by weight coefficients, which reduces the amount of data while avoiding the loss of key features, especially ensuring the integrity of features of small-sized safety equipment.

[0034] In some embodiments, the self-attention pyramid pooling module constructs a 3-layer pyramid structure to perform hierarchical sampling on the dimensionality-reduced features. The bottom window focuses on local detail features such as short-term fluctuations in abnormal footstep frequency, the middle window captures regional correlation features such as the coupling relationship between body tilt angle and center of gravity shift, and the top window extracts global trend features such as the heart rate change trend throughout the operation. Simultaneously, a self-attention mechanism is introduced to calculate the attention weight of each feature channel. Key feature channels such as device not being worn, high risk of near-electric shock, and fall status are assigned high weights of 0.8-0.9, while secondary feature channels such as ambient temperature and normal walking gait are assigned low weights of 0.1-0.3. This achieves accurate differentiation of feature importance and finally outputs a weighted feature vector containing multi-dimensional information of local, regional, and global dimensions.

[0035] In some embodiments, the fully connected layer of the deep learning network has three hidden layers with 512, 256, and 128 neurons respectively. The ReLU activation function is used to perform a non-linear transformation on the multi-dimensional features. The first hidden layer integrates device wearing and movement features, the second hidden layer integrates location and environmental features, and the third hidden layer integrates vital signs and historical violation features. Finally, the softmax activation function outputs two types of key feature results: one is the safety status characteristics of workers working at heights, such as the probability distribution of violations like not wearing a safety belt, using equipment at a low height, falls, and being silent; a probability ≥ 0.8 indicates a violation. The other is the environmental risk level characteristics, such as the classification of near-electricity risk, strong wind risk, and lightning risk, divided by risk probability into "low risk" ≤ 0.3, "medium risk" 0.3-0.7, and "high risk" ≥ 0.7, providing accurate feature input for subsequent zoning analysis.

[0036] In this embodiment of the application, the work area includes a work preparation area, a climbing area, and a high-altitude walking area. Based on the work area and combined with the location data features in the key features, the real-time area where the climbing personnel are located is determined. Establish safety assessment models for different areas: analyze equipment wearing data characteristics in the work preparation area, analyze motion data characteristics in the climbing area, and integrate position data characteristics and motion data characteristics in the high-altitude walking area. The analysis results for each region are compared with preset safety thresholds to generate analysis results that include the type of violation and risk level of the region, and these results are sent to the early warning and feedback module.

[0037] In this embodiment of the application, generating a warning report from the violation warning information and sending it to relevant personnel includes: Based on the regional violation types and risk levels in the analysis results, corresponding violation warning information is generated. The warning information is then integrated into a warning report containing the time, personnel, violation details, and risk level, and sent to relevant personnel in a polymorphic manner. The early warning reports and corresponding operational data are archived and uploaded to the power plant's two-ticket system to achieve traceability and closed-loop management of early warning information.

[0038] It should be noted that the power plant's two-ticket system mainly includes work tickets and operation tickets. Work tickets are used to clarify the scope of tasks, safety measures, qualifications of operators, and supervision requirements for production operations such as working at heights, ensuring that safety conditions are confirmed before the operation. Operation tickets are used to standardize equipment operation procedures to avoid safety accidents caused by improper operation. Together, they constitute the basis for the whole-process safety management of the power generation industry, including pre-operation approval, in-operation control, and post-operation acceptance, and are a key link in the standardization of power plant safety production.

[0039] In this embodiment of the application, the sensing and data acquisition module obtains the high-altitude operation task information from the power plant's two-ticket system through the data interface before the operation, including the operation name, operation time, operation area, list of operators and safety requirements, in order to match the binding relationship between the acquisition equipment and the operators; During the operation, the data processing and analysis module synchronizes the zoning analysis results to the power plant's two-ticket system in real time, updates the dynamic status of the operation, and enables the two-ticket system to track the operation progress in real time. After generating an early warning report, the early warning and feedback module uploads the early warning information and processing results to the power plant's two-ticket system, and archives them in conjunction with the execution records of work tickets and operation tickets. After the operation is completed, it pushes the full-process data of the operation to the two-ticket system to complete the information for closed-loop management of the operation in the two-ticket system. The power plant's two-ticket system is used to assign tasks, monitor the process, and archive the results of the high-altitude operation.

[0040] In some embodiments, before the operation, the sensing and data acquisition module obtains the high-altitude operation task information from the power plant's two-ticket system through the data interface, which needs to be matched with the work ticket. For example, if the work ticket indicates that the operation area is the maintenance of the 5-meter platform of Boiler No. 3, the module binds the location monitoring parameters of the corresponding area to ensure that the acquisition equipment only captures data from the personnel working in that area. In some embodiments, the data processing and analysis module synchronizes the partition analysis results to the two-ticket system during the operation and needs to update the status of the work ticket operation progress column in real time. When there are illegal analysis results such as low hanging and high use, the two-ticket system can automatically mark the operation as abnormal and trigger the management personnel review process. In some embodiments, the warning information and processing results uploaded by the warning and feedback module need to be associated with the work permit safety measure execution record and operation ticket operation steps. For example, the near-electricity warning processing result needs to correspond to the verification record of the anti-electric shock measures in the work permit. The full-process data pushed after the operation is completed is used in the operation acceptance stage of the two-ticket system to complete the final status update of the work permit and the operation completion confirmation of the operation ticket. Ultimately, it realizes the closed-loop management of high-altitude operations from task assignment, process monitoring to result archiving, which meets the full-process control requirements of the power plant's two-ticket system.

[0041] This embodiment provides a method for intelligent safety monitoring and early warning of high-altitude operations, including: Real-time data on the work of personnel working at heights is acquired through data acquisition equipment; Based on the operational data, key features are extracted from the data using a deep learning network. Based on these key features, the personnel working at height in the operational area are analyzed in different zones to obtain the analysis results. Based on the analysis results, generate early warning information for violations, generate early warning reports for violations, and send them to relevant personnel.

[0042] This embodiment also provides a computing device suitable for intelligent safety monitoring and early warning systems for high-altitude operations, including: The system includes a memory and a processor. The memory stores computer-executable instructions, and the processor executes these instructions to implement the intelligent safety monitoring and early warning system for high-altitude operations as described in the above embodiments.

[0043] This embodiment also provides a storage medium on which a computer program is stored. When the program is executed by a processor, it implements the intelligent safety monitoring and early warning system for high-altitude operations as proposed in the above embodiments.

[0044] The storage medium proposed in this embodiment belongs to the same inventive concept as the intelligent safety monitoring and early warning system for high-altitude operations proposed in the above embodiments. Technical details not described in detail in this embodiment can be found in the above embodiments, and this embodiment has the same beneficial effects as the above embodiments.

[0045] Based on the above description of the implementation methods, those skilled in the art can clearly understand that the present invention can be implemented using software and necessary general-purpose hardware, and of course, it can also be implemented using hardware, but in many cases the former is a better implementation method. Based on this understanding, the technical solution of the present invention, or the part that contributes to the prior art, can be embodied in the form of a software product. This computer software product can be stored in a computer-readable storage medium, such as a computer floppy disk, read-only memory (ROM), random access memory (RAM), flash memory, hard disk, or optical disk, etc., including several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute the methods of the various embodiments of the present invention.

[0046] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and not to limit it. Although the present invention has been described in detail with reference to preferred embodiments, those skilled in the art should understand that modifications or equivalent substitutions can be made to the technical solutions of the present invention without departing from the spirit and scope of the technical solutions of the present invention, and all such modifications or substitutions should be covered within the scope of the claims of the present invention.

Claims

1. An intelligent safety monitoring and early warning system for high-altitude operations, characterized in that, include: The sensing and data acquisition module is used to acquire the work data of the workers at height in real time through the acquisition device, and transmit the work data to the data processing and analysis module. The data processing and analysis module is used to receive the operation data, extract key features from the data through a deep learning network, perform zoning analysis on the personnel working at height in the operation area based on the key features, obtain the analysis results and send them to the early warning and feedback module. The early warning and feedback module is used to receive the analysis results, generate early warning information for violations, generate an early warning report from the early warning information for violations, and send it to relevant personnel.

2. The intelligent safety monitoring and early warning system for high-altitude operations as described in claim 1, characterized in that, Real-time data on the work of personnel working at heights is acquired through data acquisition devices, including: Using sensor devices to collect data on equipment worn by workers at height, their location, and their movement; Use sensing devices to collect near-electricity data and weather parameters; Based on the device wearing data, location data, and motion data, determine whether there is an abnormal state. If there is an abnormal state, execute the first operation. Based on the power data and weather parameters, determine whether there is an operational risk. If there is an operational risk, then execute the second operation.

3. The intelligent safety monitoring and early warning system for high-altitude operations as described in claim 2, characterized in that, Key features are obtained by extracting features from data using deep learning networks, including: The deep learning network first preprocesses the input job data, converting unstructured data into a standardized feature matrix; After multi-scale dimensionality reduction of the standardized feature matrix by fusion downsampling algorithm, the self-attention pyramid pooling module is used to perform hierarchical attention weight allocation on the dimensionality-reduced features to obtain multi-dimensional features. The multi-dimensional features are fused by a fully connected layer of a deep learning network to output key features of the safety status and environmental risk level of workers working at heights. Hierarchical attention weighting involves assigning higher weights to key features and lower weights to secondary features.

4. The intelligent safety monitoring and early warning system for high-altitude operations as described in claim 3, characterized in that, Based on the aforementioned key features, a zoned analysis of personnel working at heights in the work area is performed, and the analysis results are obtained and sent to the early warning and feedback module, including: The work area includes a work preparation area, a climbing area, and a high-altitude walking area. Based on the work area and combined with the location data features in the key features, the real-time area where the climbing personnel are located is determined. Establish safety assessment models for different areas: analyze equipment wearing data characteristics in the work preparation area, analyze motion data characteristics in the climbing area, and integrate position data characteristics and motion data characteristics in the high-altitude walking area. The analysis results for each region are compared with preset safety thresholds to generate analysis results that include the type of violation and risk level of the region, and these results are sent to the early warning and feedback module.

5. The intelligent safety monitoring and early warning system for high-altitude operations as described in claim 4, characterized in that, The aforementioned violation warning information will be used to generate a warning report and sent to relevant personnel, including: Based on the regional violation types and risk levels in the analysis results, corresponding violation warning information is generated. The warning information is then integrated into a warning report containing the time, personnel, violation details, and risk level, and sent to relevant personnel in a polymorphic manner. The early warning reports and corresponding operational data are archived and uploaded to the power plant's two-ticket system to achieve traceability and closed-loop management of early warning information.

6. The intelligent safety monitoring and early warning system for high-altitude operations as described in claim 5, characterized in that, The power plant two-ticket system includes: Before the operation, the sensing and data acquisition module obtains the high-altitude operation task information from the power plant's two-ticket system through the data interface, including the operation name, operation time, operation area, list of operators and safety requirements, in order to match the binding relationship between the data acquisition equipment and the operators. During the operation, the data processing and analysis module synchronizes the zoning analysis results to the power plant's two-ticket system in real time, updates the dynamic status of the operation, and enables the two-ticket system to track the operation progress in real time. After generating an early warning report, the early warning and feedback module uploads the early warning information and processing results to the power plant's two-ticket system, and archives them in conjunction with the execution records of work tickets and operation tickets. After the operation is completed, it pushes the full-process data of the operation to the two-ticket system to complete the information for closed-loop management of the operation in the two-ticket system. The power plant's two-ticket system is used to assign tasks, monitor the process, and archive the results of the high-altitude operation.

7. The intelligent safety monitoring and early warning system for high-altitude operations as described in claim 2, characterized in that, The first and second operations include: The first operation includes: when an abnormal state is detected, the intelligent safety belt monitor will issue an audible and visual alarm to the workers working at height to remind them to correct the situation, and at the same time, the abnormal state data will be transmitted to the data processing and analysis module in real time to trigger key monitoring of the workers; if the abnormal state continues for a preset time, the early warning and feedback module will be automatically activated to push warning information to the management personnel. The second operation includes: when an operational risk is determined to exist, generating a near-electricity warning based on near-electricity data and prompting workers to stay away from energized areas; generating an environmental risk warning based on weather parameters exceeding the threshold; simultaneously triggering an operation suspension suggestion; and having the warning and feedback module push the risk warning and suggestion to the work supervisor to assist in deciding whether to terminate the operation.

8. A method for applying to an intelligent safety monitoring and early warning system for high-altitude operations, characterized in that, include, Real-time data on the work of personnel working at heights is acquired through data acquisition equipment; Based on the operational data, a deep learning network is used to extract key features from the data. Based on the key features, the personnel working at height in the operational area are analyzed by region to obtain the analysis results. Based on the analysis results, a warning message for violation of regulations is generated, and a warning report is generated and sent to relevant personnel.

9. An electronic device, comprising: Memory and processor; The memory is used to store computer-executable instructions, and the processor is used to execute the computer-executable instructions. When the computer-executable instructions are executed by the processor, they implement the steps of the intelligent safety monitoring and early warning system for high-altitude operations as described in any one of claims 1 to 7.

10. A computer-readable storage medium storing computer-executable instructions that, when executed by a processor, implement the steps of the intelligent safety monitoring and early warning system for high-altitude operations as described in any one of claims 1 to 7.

Images