A power operation site safety risk management and control method based on big data analysis

Abstract

This invention discloses a method and system for dynamic assessment and proactive control of safety risks at power operation sites based on big data analysis, belonging to the field of power safety technology. The method includes: real-time collection of personnel, equipment, environmental, and management data through Internet of Things (IoT) technology; construction of a dynamic risk quantification assessment model integrating spatiotemporal superposition effects to calculate a comprehensive risk value composed of static basic risks and dynamic risk increments; real-time processing and visualization using a distributed streaming computing engine to achieve risk heatmap display and trajectory prediction; triggering graded early warnings based on risk levels, and automatically linking on-site safety devices for proactive intervention in critical situations. This invention achieves panoramic perception, dynamic quantification assessment, intelligent prediction and early warning, and automated linkage control of safety risks, effectively solving the problems of static lag, information silos, and reliance on manual intervention inherent in traditional methods, and significantly improving the safety control capabilities and proactive management level of power operation sites.

Description

Technical Field

[0001] This invention relates to the field of power safety technology, and in particular to a method and system for managing and controlling safety risks at power operation sites based on big data analysis. Background Technology

[0002] As a fundamental lifeline of the national economy, the safety of the power industry's production activities is of paramount importance. Power field operations encompass installation, maintenance, testing, operation, and emergency repairs across power generation, transmission, transformation, and distribution. These operations are characterized by complex environments (such as high altitudes, high voltage levels, underground locations, and confined spaces), numerous equipment, intensive technology, dynamically intertwined hazards, and severe consequences from accidents. For a long time, the power industry has consistently prioritized safety and has established a relatively complete safety management system. However, with the continuous expansion of the power grid, the increasing complexity of equipment, and the accelerating pace of operations, traditional safety management models are increasingly proving inadequate in addressing new risks and recurring problems.

[0003] Traditional on-site safety risk management models for power operations are mainly based on the following three levels: 1. A regulatory control system centered on rules, regulations, and procedural documents: This system relies on mandatory standards such as the "Electric Power Safety Work Regulations," as well as paper-based or rudimentary electronic procedures like work permits, operation tickets, safety briefings, and work instructions. While this system specifies standard operating procedures and safety measures, its implementation heavily depends on personnel's self-discipline, memory, and sense of responsibility, leading to risks of omissions and perfunctory implementation. Furthermore, its static and pre-defined nature makes it difficult to cover the rapidly changing and unpredictable situations on-site.

[0004] 2. A human-based safety management system centered on personnel experience and supervision: Safety risk control primarily relies on the experience and immediate judgment of on-site work supervisors and dedicated monitors. They assess risks through visual observation, questioning, and simple instrument measurements. This model is limited by individual differences in experience, blind spots, physical fatigue, and the potential for complacency, making it prone to misjudgment or omission of risks in complex scenarios. Especially in large-scale, multi-shift operations, a single monitor may find it difficult to fully grasp the overall risk situation.

[0005] In recent years, with the development of technologies such as the Internet of Things and mobile Internet, the industry has seen some technological attempts and improvements aimed at improving on-site safety management, which can be called the "technological upgrade stage." However, there are still obvious limitations: it is impossible to capture the instantaneous changes and combined effects of personnel behavior, equipment status, and environmental factors in real time and comprehensively; risk assessment is mostly based on qualitative or fixed tables, and cannot be dynamically calculated and quantitatively graded based on real-time on-site data; alarms are often aimed at single violations (such as entering a restricted area), failing to combine multi-dimensional information to assess the true risk level of the event, and lacking effective automated intervention methods after the warning; it can only respond after the risk appears or the accident occurs, and cannot predict the trend of risk evolution, let alone implement proactive and coordinated technical interventions before the risk reaches the critical point to achieve "prevention before the event". Summary of the Invention

[0006] The purpose of this invention is to address the problems existing in the background technology by proposing a method for safety risk management and control at power operation sites based on big data analysis.

[0007] The technical solution of this invention: a method for safety risk management and control at power operation sites based on big data analysis, comprising the following steps: S1: Real-time collection of multi-dimensional, multi-source data from power operation sites, including at least personnel data, equipment data, environmental data, and management data; S2: Construct a dynamic risk knowledge graph and a quantitative assessment model based on historical data and expert knowledge. The model is used to calculate the comprehensive risk value consisting of static basic risk and dynamic risk increment. The calculation of dynamic risk increment incorporates the spatiotemporal superposition effect analysis of personnel, equipment and environmental factors. S3: Utilize a streaming computing engine to process real-time data streams, drive the quantitative assessment model to perform periodic dynamic risk assessments, and integrate the assessment results with spatial geographic information for visualization. The visualization includes risk heatmaps, tracking of high-risk individuals, and prediction of future movement trajectories of personnel. S4: Triggers tiered early warnings based on real-time risk levels, and automatically executes or recommends the execution of pre-control instructions linked with on-site safety equipment when the preset highest risk level is reached, thereby achieving proactive risk intervention.

[0008] Preferably, in step S1, personnel data is collected through wearable smart devices, including real-time location, movement trajectory, physiological status, and violations identified by video AI; equipment data includes power equipment operating status parameters and safety tool verification status; environmental data includes real-time meteorological data and work micro-environment data; and management data includes work plans and safety measures obtained from the production management system.

[0009] Preferably, in step S2, the comprehensive risk value R is calculated using the following model: R = R_base + ΔR; Wherein, R_base is a static basic risk value, which is determined based on the preset inherent attributes of the operation. The inherent attributes include the operation type, equipment voltage level, and basic category of the operation environment. ΔR is the dynamic risk increment, calculated by fusing the real-time collected personnel data, equipment data, and environmental data.

[0010] Preferably, in S2, the spatiotemporal superposition effect analysis refers to the following: when two or more independent risk factors occur simultaneously within a set time and space threshold range, the dynamic risk increment will be accumulated according to a nonlinear function.

[0011] Preferably, in step S3, the visualization presentation specifically includes: displaying the regional risk level on a two-dimensional electronic map or a three-dimensional work scene model using heat maps of different colors and intensities; highlighting and labeling identified high-risk personnel or equipment targets; predicting their future short-term movement paths based on their historical movement trajectories and current locations, and forecasting the probability of them entering high-risk areas.

[0012] Preferably, the graded early warning in S4 includes at least four levels: low-risk record prompt, medium-risk mobile terminal push, high-risk on-site sound and light alarm, and emergency risk linkage control.

[0013] Preferably, the emergency risk linkage control specifically involves sending control commands to the intelligent safety devices deployed at the work site. These commands include, but are not limited to, triggering enhanced audible and visual alarms in specific areas, controlling intelligent access control or passageway switches, and electronically locking or unlocking safety tools.

[0014] A power operation site safety risk management and control system based on big data analysis includes: The data acquisition and fusion module is used to execute S1; The risk modeling and computation engine module is used to perform the computational parts of S2 and S3; The visualization and early warning management platform module is used to execute the visualization part of S3 and S4; And, an on-site intelligent linkage execution terminal that is communicatively connected to the early warning and control platform module.

[0015] Preferably, the on-site intelligent linkage execution terminal includes one or more of the following: intelligent sound and light alarm, intelligent access control controller, and intelligent safety tool management cabinet.

[0016] Compared with existing technologies, the beneficial effects of this invention are as follows: By integrating multi-source IoT data and production management information, it achieves panoramic, continuous, and real-time perception of personnel behavior, equipment status, environmental parameters, and management processes. Furthermore, it constructs a dynamic quantitative risk assessment model that integrates spatiotemporal superposition effects, shifting risk assessment from static and qualitative to dynamic and quantitative, enabling precise capture of nonlinear risk escalations caused by the coupling of multiple factors. It also relies on a distributed streaming computing engine to achieve second-level risk recalculation and future trend prediction, driving the evolution of early warning models from post-event alarms to pre-event prevention. Ultimately, this solution comprehensively improves the real-time nature, accuracy, proactivity, and systematic nature of power operation site safety management, significantly enhancing the inherent safety level of power grid enterprises. Attached Figure Description

[0017] Figure 1 This is a flowchart of a method for controlling safety risks at power operation sites based on big data analysis, as proposed in this invention. Detailed Implementation

[0018] The technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, and not all embodiments. Based on the embodiments of this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.

[0019] It should be noted that the terms "first," "second," etc., in the specification, claims, and accompanying drawings of this application are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that the embodiments of this application described herein can be implemented in orders other than those illustrated or described herein. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover non-exclusive inclusion; for example, a process, method, system, product, or server that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or devices.

[0020] It should be noted that the following description covers various aspects of embodiments within the scope of the appended claims. It will be apparent that the aspects described herein can be embodied in a wide variety of forms, and any particular structure and / or function described herein is merely illustrative. Based on this application, those skilled in the art will understand that one aspect described herein can be implemented independently of any other aspect, and two or more of these aspects can be combined in various ways. For example, any number of aspects set forth herein can be used to implement the device and / or practice the method. Additionally, this device and / or method can be implemented using structures and / or functionalities other than one or more of the aspects set forth herein.

[0021] Firstly, this invention provides a method for managing safety risks at power operation sites based on big data analysis, such as... Figure 1 As shown, it includes the following steps: S1: Real-time collection of multi-dimensional, multi-source data from power operation sites, including at least personnel data, equipment data, environmental data, and management data; Specifically, personnel data is collected through wearable smart devices, including real-time location, movement trajectory, physiological status, and violations identified through video AI; equipment data includes operating status parameters of power equipment and calibration status of safety tools; environmental data includes real-time meteorological data and work micro-environment data; and management data includes work plans and safety measures obtained from the production management system.

[0022] It should be noted that personnel data is collected through smart safety helmets, smart name tags, positioning tags, and wearable physiological monitoring devices worn by workers. This data includes their unique identification, real-time high-precision location (such as UWB and Bluetooth AOA), movement trajectory, posture (for fall detection), and physiological indicators such as heart rate. Simultaneously, smart video cameras deployed in key areas of the work site, using built-in or backend AI algorithms, identify unsafe behaviors by personnel in real time. Equipment data is obtained in real time from the sensors, monitoring units, and production management systems of the power equipment itself to obtain the operating status parameters of the power equipment involved in the operation; Environmental data is collected in real time from micro weather stations and sensor networks deployed at and around the work site, including meteorological and environmental information (such as wind speed, wind direction, rainfall, and lightning monitoring information) and operational micro-environmental parameters (such as ambient temperature, humidity, SF6 gas concentration, oxygen content, and noise level). The management data automatically extracts structured information related to the current work site from the company's unified production management information system, work permit management system, and hazard investigation system. This includes, but is not limited to: work task content, work permit number and safety measure requirements, operation permit steps, work plan time, on-site investigation records, and accident cases of similar historical operations.

[0023] S2: Construct a dynamic risk knowledge graph and a quantitative assessment model based on historical data and expert knowledge. The model is used to calculate the comprehensive risk value consisting of static basic risk and dynamic risk increment. The calculation of dynamic risk increment incorporates the spatiotemporal superposition effect analysis of personnel, equipment and environmental factors. Specifically, the spatiotemporal superposition effect analysis refers to the following: when two or more independent risk factors occur simultaneously within a set time and space threshold range, the dynamic risk increment will be accumulated according to a nonlinear function.

[0024] It should be noted that S2 includes the following specific steps: S21: Based on power grid safety regulations, industry standards, historical accident case databases, expert experience manuals, etc., a structured risk knowledge base is constructed using knowledge engineering techniques. This knowledge graph uses "risk events" as nodes, defining entities such as personnel, equipment, tools, environment, and management activities, as well as the multidimensional relationships between them, forming risk chains and related networks; S22: Establish a dynamic risk quantification assessment model, which adopts a hierarchical and integrated computational framework, including: Basic Risk Layer: Based on inherent attributes such as work type, voltage level, and equipment type, and in accordance with procedural requirements, an initial basic risk value R_base is assigned. This value is determined before the work begins and is relatively static. Dynamic Risk Increment Layer: This is the key to this invention. The model receives the fused data stream from step S1 in real time and calculates the dynamic risk increment ΔR. The calculation of ΔR comprehensively considers four types of dynamic factors: Personnel behavior factors: Quantified based on the number, type, duration, and degree of abnormality in the physiological state of personnel based on location and video AI recognition of violations; Equipment status factor: quantified based on the deviation between real-time monitoring parameters of the equipment and normal thresholds, and the compliance status of safety tools; Environmental disturbance factor: Quantifying the hazard level of the current operation type based on real-time environmental data (such as wind speed and lightning); Spatiotemporal superposition factor: This invention specifically introduces a spatiotemporal superposition effect function Φ. This function identifies and quantifies the coupling effect of different risk factors in time and space. For example, when two independent risk events, "lifting operation" and "personnel activity below," occur simultaneously in the same time and space (the boom's slewing radius and the area below), their combined risk is far greater than the simple sum of the two. The Φ function quantifies this coupled risk by calculating the spatiotemporal proximity between risk entities (personnel, equipment) and applying a nonlinear weighting amplification mechanism. S23: The final overall risk value R is calculated using the following formula: R=R_base+ΔR=R_base+α*F_person+β*F_equipment+γ*F_environment+Φ(F_i,F_j,T,S); Where F_person, F_equipment, and F_environment are the quantified values ​​of personnel, equipment, and environmental factors, respectively; α, β, and γ are their dynamic weighting coefficients, which can be adaptively adjusted according to the operation stage; Φ is the spatiotemporal superposition function; F_i and F_j are the risk factors that cause superposition; and T and S are the time window and spatial distance parameters.

[0025] It should also be noted that R_base is a static basic risk value, which is determined based on the preset inherent attributes of the operation. The inherent attributes include the operation type, equipment voltage level, and basic category of the operation environment. ΔR is the dynamic risk increment, which is calculated by fusing the real-time collected personnel data, equipment data and environmental data. It includes at least: personnel behavior risk factors based on the quantification of personnel violations and physiological states, equipment anomaly risk factors based on the deviation of equipment real-time status from thresholds, environmental disturbance risk factors based on the deviation of environmental parameters from safe working conditions, and spatiotemporal superposition effect factors reflecting the nonlinear growth risk generated when at least two independent risk factors are coupled in the spatiotemporal dimension.

[0026] S3: Utilize a streaming computing engine to process real-time data streams, drive the quantitative assessment model to perform periodic dynamic risk assessments, and integrate the assessment results with spatial geographic information for visualization. The visualization includes risk heatmaps, tracking of high-risk individuals, and prediction of future movement trajectories of personnel. Specifically, the visualization includes: displaying regional risk levels on a two-dimensional electronic map or a three-dimensional work scene model using heat maps of different colors and intensities; highlighting and labeling identified high-risk personnel or equipment targets; predicting their future short-term movement paths based on their historical movement trajectories and current locations, and forecasting their probability of entering high-risk areas.

[0027] Specifically, this step utilizes a distributed streaming computing engine (such as Apache Flink, Spark Streaming) to continuously process the massive real-time data stream generated in step S1, driving the quantitative evaluation model in step S2 to recalculate and update risk values ​​at the second or even millisecond level, ensuring the real-time nature of risk assessment.

[0028] In addition, the calculated real-time risk information is deeply integrated with high-precision two-dimensional electronic maps and three-dimensional digital power plant models, and displayed intuitively through a visualization management platform. This includes: generating a dynamically changing risk heat map on the electronic map using different colors based on the real-time risk values ​​of each area; highlighting high-risk individuals identified by the system with icons, replaying their trajectories, and adding labels to display their specific risk descriptions and levels; and predicting their possible short-term (e.g., 30-60 seconds) movement paths in the future using trajectory prediction algorithms (such as social force models and LSTM neural networks) based on their historical movement trajectories, current speed, and direction, and performing collision detection with static hazard sources (energized compartments) and dynamic hazard sources (mobile devices) to predict the probability and time of their entry into high-risk areas, and displaying this information in the form of visual prompt lines or probability clouds.

[0029] In step S3, the real-time data stream is processed using a streaming computing engine, specifically including: S31: The streaming computing engine continuously consumes the real-time data stream from step S1 with a time granularity of milliseconds or seconds; S32: Perform real-time calculations on the real-time data stream, including data cleaning, format standardization, extraction and transformation of key feature fields, and perform sliding or scrolling aggregation on the data according to a preset time window; S33: Based on the aggregated real-time data, the dynamic risk quantification assessment model is dynamically triggered and executed to complete the calculation and update of the risk value. The calculation is a stateful calculation that can maintain and update intermediate states, including personnel location trajectory and equipment abnormality duration. S34: The calculated real-time risk value, risk level, and associated risk event description are output to the visualization module and early warning control module in real time in the form of an event stream.

[0030] S4: Triggers graded early warnings based on real-time risk levels, and automatically executes or recommends the execution of pre-control instructions linked with on-site safety equipment when the preset highest risk level is reached, thereby achieving proactive risk intervention; Specifically, the graded early warning system in S4 includes at least four levels: low-risk record notification, medium-risk mobile push notification, high-risk on-site audible and visual alarm, and emergency risk linkage control. The emergency risk linkage control specifically involves sending control commands to the intelligent safety devices deployed at the work site. These commands include, but are not limited to, triggering enhanced audible and visual alarms in specific areas, controlling intelligent access control or passageway switches, and electronically locking or unlocking safety tools.

[0031] It should be noted that in this embodiment, Level 1 is low risk, when the risk value R is below a general threshold. The system automatically records the risk log and provides a notification on the statistics panel of the background visual dashboard, without any proactive alarm. Level 2 is medium risk, when the risk value R exceeds a general threshold. The system automatically generates a warning message and pushes it to the mobile application terminals (such as mobile APP, smart bracelet vibration) of the on-site work supervisor, safety officer, and relevant management personnel to remind them to pay attention. Level 3 is high risk, when the risk value R reaches a relatively high threshold. Based on the Level 2 response, the system automatically triggers the on-site deployed audible and visual alarm devices (such as smart warning lights, voice broadcasts) to provide audible and visual alerts in the specific risk area, attracting the attention of all personnel on site. Level 4 is critical risk, when the risk value R reaches or exceeds the critical threshold, indicating that it may immediately lead to serious consequences. At this time, while responding at Level 3, the system automatically generates and executes predetermined linkage control commands, which is the core of the "proactive management" achieved by this invention.

[0032] When the system determines that the distance between personnel and live conductors remains below the safe distance and shows no signs of stopping, it can send commands to the "intelligent forced isolation device" or "audio-visual deterrent device" in the area, triggering flashing lights and directional loud noise warnings, and even remotely controlling the activation of temporary physical isolation facilities (such as automatic lifting guardrails). In cases of fire, toxic gas leaks, or other emergencies, it automatically activates the intelligent emergency lighting and evacuation guidance system, planning and illuminating the optimal escape route. During voltage testing and grounding, it can activate the "intelligent safety tool control cabinet," which can only unlock after the current grounding connection point complies with regulations and is confirmed by the system; or, in emergencies, it can remotely lock equipment that may require dangerous operation.

[0033] In an exemplary embodiment of this application, a power operation site safety risk management and control system based on big data analysis is also provided, including: The data acquisition and fusion module is used to execute S1; The risk modeling and computation engine module is used to perform the computational parts of S2 and S3; The visualization and early warning management platform module is used to execute the visualization part of S3 and S4; And, an on-site intelligent linkage execution terminal that is communicatively connected to the early warning and control platform module.

[0034] Specifically, the on-site intelligent linkage execution terminal includes one or more of the following: intelligent sound and light alarm, intelligent access control controller, and intelligent safety tool management cabinet.

[0035] In an exemplary embodiment of this application, an electronic device capable of implementing the above-described method is also provided.

[0036] Those skilled in the art will understand that various aspects of this application can be implemented as a system, method, or program product. Therefore, various aspects of this application can be specifically implemented in the following forms: a completely hardware implementation, a completely software implementation (including firmware, microcode, etc.), or a combination of hardware and software implementations, collectively referred to herein as a "circuit," "module," or "system."

[0037] An electronic device according to this embodiment of the present application. The electronic device is merely an example and should not be construed as limiting the functionality and scope of use of the embodiments of this application.

[0038] Electronic devices are manifested in the form of general-purpose computing devices. Components of an electronic device may include, but are not limited to: at least one processor, at least one memory, and buses connecting different system components (including memory and processor).

[0039] The memory stores program code that can be executed by a processor, causing the processor to perform the steps described in the "Exemplary Methods" section above, according to various exemplary embodiments of this application.

[0040] The storage may include readable media in the form of volatile storage, such as random access memory (RAM) and / or cache memory, and may further include read-only memory (ROM).

[0041] The storage may also include programs / utilities having a set (at least one) of program modules, including but not limited to: an operating system, one or more applications, other program modules, and program data, each or some combination of these examples may include an implementation of a network environment.

[0042] A bus can represent one or more of several bus architectures, including a memory bus or memory controller, a peripheral bus, a graphics acceleration port, a processor, or a local bus that uses any of the various bus architectures.

[0043] The electronic device can also communicate with one or more external devices (such as keyboards, pointing devices, Bluetooth devices, etc.), one or more devices that enable a user to interact with the electronic device, and / or any device that enables the electronic device to communicate with one or more other computing devices (such as routers, modems, etc.). This communication can be performed via input / output (I / O) interfaces. Furthermore, the electronic device can communicate with one or more networks (such as local area networks (LANs), wide area networks (WANs), and / or public networks, such as the Internet) via a network adapter. As shown in the figure, the network adapter communicates with other modules of the electronic device via a bus. It should be understood that, although not shown in the figure, other hardware and / or software modules can be used in conjunction with the electronic device, including but not limited to: microcode, device drivers, redundant processors, external disk drive arrays, RAID systems, tape drives, and data backup storage systems.

[0044] Through the above description of the embodiments, those skilled in the art will readily understand that the exemplary embodiments described herein can be implemented by software or by combining software with necessary hardware. Therefore, the technical solutions according to the embodiments of this application can be embodied in the form of a software product, which can be stored in a non-volatile storage medium (such as a CD-ROM, USB flash drive, external hard drive, etc.) or on a network, including several instructions to cause a computing device (such as a personal computer, server, terminal device, or network device, etc.) to execute the methods according to the embodiments of this application.

[0045] In exemplary embodiments of this application, a computer-readable storage medium is also provided, on which a program product capable of implementing the methods described above is stored. In some possible implementations, various aspects of this application may also be implemented as a program product including program code, which, when the program product is run on a terminal device, causes the terminal device to perform the steps of the various exemplary embodiments of this application described in the "Exemplary Methods" section above.

[0046] The program product may employ any combination of one or more readable media. A readable medium may be a readable signal medium or a readable storage medium. A readable storage medium may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination thereof. More specific examples of readable storage media (a non-exhaustive list) include: electrical connections having one or more wires, portable disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination thereof.

[0047] Computer-readable signal media may include data signals propagated in baseband or as part of a carrier wave, carrying readable program code. Such propagated data signals may take various forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination thereof. A readable signal medium may also be any readable medium other than a readable storage medium, capable of sending, propagating, or transmitting programs for use by or in conjunction with an instruction execution system, apparatus, or device.

[0048] The program code contained on the readable medium may be transmitted using any suitable medium, including but not limited to wireless, wired, optical fiber, RF, etc., or any suitable combination thereof.

[0049] Program code for performing the operations of this application can be written in any combination of one or more programming languages, including object-oriented programming languages ​​such as Java and C++, and conventional procedural programming languages ​​such as C or similar languages. The program code can execute entirely on the user's computing device, partially on the user's computing device, as a standalone software package, partially on the user's computing device and partially on a remote computing device, or entirely on a remote computing device or server. In cases involving remote computing devices, the remote computing device can be connected to the user's computing device via any type of network, including a local area network (LAN) or a wide area network (WAN), or it can be connected to an external computing device (e.g., via the Internet using an Internet service provider).

[0050] Furthermore, the above figures are merely illustrative of the processes included in the method according to exemplary embodiments of this application, and are not intended to be limiting. It is readily understood that the processes shown in the above figures do not indicate or limit the temporal order of these processes. Additionally, it is readily understood that these processes may be executed synchronously or asynchronously, for example, in multiple modules.

[0051] It should be noted that although several modules or units for the device used to perform actions have been mentioned in the detailed description above, this division is not mandatory. In fact, according to the embodiments of this application, the features and functions of two or more modules or units described above can be embodied in one module or unit. Conversely, the features and functions of one module or unit described above can be further divided and embodied by multiple modules or units.

[0052] The above are merely specific embodiments of this application, but the scope of protection of this application is not limited thereto. Any variations or substitutions that can be easily conceived by those skilled in the art within the technical scope disclosed in this application should be included within the scope of protection of this application. Therefore, the scope of protection of this application should be determined by the scope of the claims.

Claims

1. A power operation site safety risk management and control method based on big data analysis, characterized in that, Includes the following steps: S1: Real-time collection of multi-dimensional, multi-source data from power operation sites, including at least personnel data, equipment data, environmental data, and management data; S2: Construct a dynamic risk knowledge graph and a quantitative assessment model based on historical data and expert knowledge. The model is used to calculate the comprehensive risk value consisting of static basic risk and dynamic risk increment. The calculation of dynamic risk increment incorporates the spatiotemporal superposition effect analysis of personnel, equipment and environmental factors. S3: Utilize a streaming computing engine to process real-time data streams, drive the quantitative assessment model to perform periodic dynamic risk assessments, and integrate the assessment results with spatial geographic information for visualization. The visualization includes risk heatmaps, tracking of high-risk individuals, and prediction of future movement trajectories of personnel. S4: Triggers tiered early warnings based on real-time risk levels, and automatically executes or recommends the execution of pre-control instructions linked with on-site safety equipment when the preset highest risk level is reached, thereby achieving proactive risk intervention.

2. The power operation site safety risk management and control method based on big data analysis according to claim 1, characterized in that, In S1, personnel data is collected through wearable smart devices, including real-time location, movement trajectory, physiological status, and violations identified by video AI; equipment data includes power equipment operating status parameters and safety tool verification status; environmental data includes real-time meteorological data and work micro-environment data; and management data includes work plans and safety measures obtained from the production management system. 3.The power operation site safety risk management and control method based on big data analysis of claim 1, wherein, In step S2, the comprehensive risk value R is calculated using the following model: R = R_base + ΔR; Wherein, R_base is a static basic risk value, which is determined based on the preset inherent attributes of the operation. The inherent attributes include the operation type, equipment voltage level, and basic category of the operation environment. ΔR is the dynamic risk increment, calculated by fusing the real-time collected personnel data, equipment data, and environmental data.

4. The method for safety risk management and control at power operation sites based on big data analysis according to claim 2, characterized in that, In S2, the spatiotemporal superposition effect analysis refers to the following: when two or more independent risk factors occur simultaneously within a set time and space threshold range, the dynamic risk increment will be accumulated according to a nonlinear function.

5. The method for safety risk management and control at power operation sites based on big data analysis according to claim 1, characterized in that, In S3, the visualization presentation specifically includes: displaying the risk level of the area on a two-dimensional electronic map or a three-dimensional work scene model using heat maps of different colors and intensities; highlighting and labeling identified high-risk personnel or equipment targets; predicting their future short-term movement paths based on their historical movement trajectories and current locations, and forecasting the probability of them entering high-risk areas.

6. The method for safety risk management and control at power operation sites based on big data analysis according to claim 1, characterized in that, The graded early warning system in S4 includes at least four levels: low-risk record notification, medium-risk mobile push notification, high-risk on-site audio-visual alarm, and emergency risk linkage control.

7. A method for safety risk management and control at power operation sites based on big data analysis according to claim 6, characterized in that, The emergency risk linkage control specifically involves sending control commands to the intelligent safety devices deployed at the work site. These commands include, but are not limited to, triggering enhanced audible and visual alarms in specific areas, controlling intelligent access control or passageway switches, and electronically locking or unlocking safety tools.

8. A power operation site safety risk management and control system based on big data analysis, based on the method described in any one of claims 1-7, characterized in that, include: The data acquisition and fusion module is used to execute S1; The risk modeling and computation engine module is used to perform the computational parts of S2 and S3; The visualization and early warning management platform module is used to execute the visualization part of S3 and S4; And, an on-site intelligent linkage execution terminal that is communicatively connected to the early warning and control platform module.

9. A method for safety risk management and control at power operation sites based on big data analysis according to claim 8, characterized in that, The on-site intelligent linkage execution terminal includes one or more of the following: intelligent sound and light alarm, intelligent access control controller, and intelligent safety tool management cabinet.

Images