Evaluation and avoidance optimization method for external safety risk factors of electric power engineering

Abstract

The invention belongs to the technical field of electric power engineering, and relates to an evaluation and avoidance optimization method for external safety risk factors of electric power engineering. Comprising the following steps: acquiring external safety risk factor data in a full life cycle of the electric power project; preprocessing the external security risk factor data to form a data set; based on the data set, through a dynamic risk assessment model, carrying out dynamic analysis and early warning on potential risks between the electric power engineering and external safety risk factors, and generating a risk assessment result containing risk levels and early warning information; and according to the risk assessment result, generating an avoidance optimization scheme for the external safety risk factor for each stage of planning, design, construction and operation of the electric power project. According to the method, dynamic accurate assessment and prospective active avoidance of the external safety risk of the whole life cycle of the electric power engineering are realized, and the risk resistance and the safety control level of each stage of the electric power engineering are effectively improved.

Description

Technical Field

[0001] This invention belongs to the field of power engineering technology and relates to an assessment and avoidance optimization method for external safety risk factors in power engineering. Background Technology

[0002] As my country's energy structure accelerates its transformation towards clean and low-carbon energy, large-scale construction projects are underway for new energy sources such as wind power and photovoltaics, as well as for essential thermal power plants and transmission lines. These power facilities are widely distributed and highly exposed, and their external environmental safety directly affects their reliable operation throughout their entire lifecycle. However, over a period of several decades, these projects continuously face geological disasters such as earthquakes and landslides, extreme weather events such as typhoons and freezing rain, and multiple external risks from nearby hazardous chemical enterprises and fuel supply disruptions, posing serious threats to planning and site selection, design safety, construction stability, and long-term operation.

[0003] Currently, external risk management in power engineering still suffers from significant deficiencies. Traditional methods often focus on the construction phase or conduct single, static assessments, lacking a systematic risk perspective that covers the entire process from planning and design to construction and operation. Various risk data are scattered, with prominent information silos, making it difficult to achieve comprehensive judgment and dynamic early warning. This can lead to situations where site selection may mistakenly fall into high-risk areas, design standards may not match actual disasters, and the ability to respond to sudden external events during the operation phase is insufficient. Summary of the Invention

[0004] To address the problems in existing technologies, this invention provides an optimization method for assessing and avoiding external safety risk factors in power engineering. This method enables dynamic and accurate assessment and proactive avoidance of external safety risks throughout the entire lifecycle of power engineering, effectively improving the risk resistance capability and safety management level of power engineering at each stage.

[0005] To achieve the above objectives, the present invention employs the following technical solution: In a first aspect, the present invention provides a method for assessing and avoiding external safety risk factors in power engineering, comprising the following steps: Acquire data on external safety risk factors throughout the entire lifecycle of power engineering projects; The external security risk factor data is preprocessed to form a dataset; Based on the dataset, a dynamic risk assessment model is used to dynamically analyze and warn of the potential risks between the power project and external safety risk factors, generating risk assessment results that include risk levels and early warning information. Based on the risk assessment results, optimization schemes for avoiding external safety risk factors are generated for each stage of the planning, design, construction and operation of the power project.

[0006] Preferably, the external security risk factor data includes spatial data, attribute data, and dynamic monitoring data; wherein, spatial data includes GIS vector data and remote sensing image data; attribute data includes text ledgers and policy document data; and dynamic monitoring data includes water quality, vibration, and air pollutant concentration data collected in real time by IoT sensors.

[0007] Preferably, the method for preprocessing the external security risk factor data includes: Perform deduplication and logical error correction cleaning on external security risk factor data; Data on external security risk factors containing sensitive information should be anonymized. Standardize spatial and attribute data to unify spatial reference coordinate systems and data storage formats.

[0008] Preferably, the dynamic risk assessment model includes a natural disaster assessment model, a man-made accident assessment model, and a supply chain risk assessment model; The natural disaster assessment model includes at least one of earthquake risk assessment model, geological disaster assessment model, flood inundation analysis model, and extreme weather assessment model; the man-made accident assessment model includes at least one of terrorist attack threat assessment model, hazardous enterprise accident consequence simulation model, and fire and explosion spread model; the supply chain risk assessment model includes at least one of fuel supply disruption impact model and water shortage early warning model.

[0009] Preferably, the method for dynamically analyzing and providing early warning of potential risks between the power project and external safety risk factors includes: Temporal convolutional networks are used to process the temporal data in the dynamic monitoring data and extract temporal features. The temporal features are fused with spatial data and attribute data, and risk probability prediction is performed using the Bayesian LSTM algorithm. The risk assessment results, which include risk level classification and early warning time windows, are generated based on the prediction results.

[0010] Preferably, the method for generating an optimization scheme to avoid the external security risk factors includes: During the planning phase, based on the distribution characteristics and risk levels of external security risk factors, recommended areas and prohibited areas for project site selection are generated. During the design phase, the degree of impact of different engineering schemes on external safety risk factors is simulated, and an optimized design scheme including avoidance distance and protective measures is output. During the construction phase, the spatial relationship between construction activities and external safety risk factors is monitored in real time, and the construction sequence and scope of work are dynamically adjusted. During the operation phase, the cumulative impact of external safety risk factors on the safe operation of the project is assessed by combining long-term monitoring data, and risk prevention and emergency response measures are formulated.

[0011] Preferably, after the step of generating an optimization scheme to avoid the external security risk factors, the method further includes: The dataset, risk assessment results, and avoidance optimization schemes are visualized on an electronic map using a GIS engine. It supports layered rendering based on the type of external safety risk factors, and overlays the planned power engineering lines and sites. A timeline control is provided to display the historical evolution of external safety risk factors and the changes in the scope of risk impact at each stage of power engineering.

[0012] Preferably, after the step of preprocessing the external security risk factor data, the method further includes: Establish a tiered review mechanism, whereby the first-level review body conducts a preliminary review of the processed data, and the second-level review body conducts the final review. The approved data is stored in both relational and non-relational databases, and a spatial index is created using R-tree spatial indexing technology.

[0013] Preferably, the dynamic risk assessment model supports dynamic expansion; the expansion method includes: The newly added or optimized dynamic risk assessment model is determined according to the specific application scenario, triggering the hierarchical review mechanism. After being reviewed and approved by the first-level review body and the second-level review body, the newly added or optimized dynamic risk assessment model is integrated into the dynamic risk assessment model library and associated with the corresponding external safety risk factor type and power engineering stage.

[0014] Secondly, the present invention provides an assessment and avoidance optimization system for external safety risk factors in power engineering, comprising: Data acquisition module: used to acquire data on external safety risk factors throughout the entire lifecycle of a power project; Data preprocessing module: used to preprocess the external security risk factor data to form a dataset; Dynamic risk assessment module: Based on the dataset, it is used to dynamically analyze and warn of potential risks between the power project and external safety risk factors through a dynamic risk assessment model, and generate risk assessment results containing risk level and early warning information; Decision optimization module: Based on the risk assessment results, it generates optimization schemes for avoiding external safety risk factors for each stage of the planning, design, construction and operation of the power project.

[0015] Compared with the prior art, the present invention has the following beneficial effects: This invention lays the foundation for accurate analysis by comprehensively acquiring multidimensional risk factor data; then, through standardized data preprocessing, it ensures the reliability and consistency of the assessment basis; furthermore, it utilizes a dynamic risk assessment model for fusion analysis and predictive early warning, realizing the quantitative identification and forward-looking judgment of potential risks; finally, by generating differentiated avoidance optimization schemes that run through all stages of planning, design, construction, and operation, it directly transforms the assessment conclusions into specific and actionable guidelines, thereby significantly enhancing the proactive defense capabilities and life-cycle safety resilience of power engineering in the face of complex external risks. Attached Figure Description

[0016] To more clearly illustrate the technical solutions of the embodiments of the present invention, the accompanying drawings used in the embodiments will be briefly introduced below. It should be understood that the following drawings only show some embodiments of the present invention and should not be regarded as a limitation on the scope. For those skilled in the art, other related drawings can be obtained based on these drawings without creative effort.

[0017] Figure 1 This is a flowchart of the method of the present invention. Detailed Implementation

[0018] To make the objectives, technical solutions, and advantages of the embodiments of the present invention clearer, the technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. The components of the embodiments of the present invention described and shown in the accompanying drawings can generally be arranged and designed in various different configurations.

[0019] Therefore, the following detailed description of the embodiments of the invention provided in the accompanying drawings is not intended to limit the scope of the claimed invention, but merely to illustrate selected embodiments of the invention. All other embodiments obtained by those skilled in the art based on the embodiments of the invention without inventive effort are within the scope of protection of the invention.

[0020] It should be noted that similar labels and letters in the following figures indicate similar items. Therefore, once an item is defined in one figure, it does not need to be further defined and explained in subsequent figures.

[0021] In the description of the embodiments of the present invention, it should be noted that if terms such as "upper," "lower," "horizontal," or "inner" indicate the orientation or positional relationship based on the orientation or positional relationship shown in the accompanying drawings, or the orientation or positional relationship commonly used when the product of the invention is in use, they are only for the convenience of describing the present invention and simplifying the description, and do not indicate or imply that the device or element referred to must have a specific orientation, or be constructed and operated in a specific orientation, and therefore should not be construed as a limitation of the present invention. Furthermore, terms such as "first" and "second" are only used to distinguish descriptions and should not be construed as indicating or implying relative importance.

[0022] Furthermore, the use of the term "horizontal" does not imply that the component must be absolutely horizontal, but rather that it can be slightly tilted. For example, "horizontal" simply means that its direction is more horizontal than "vertical," and does not mean that the structure must be completely horizontal, but can be slightly tilted.

[0023] In the description of the embodiments of the present invention, it should also be noted that, unless otherwise explicitly specified and limited, the terms "set," "install," "connect," and "link" should be interpreted broadly. For example, they can refer to a fixed connection, a detachable connection, or an integral connection; they can refer to a mechanical connection or an electrical connection; they can refer to a direct connection or an indirect connection through an intermediate medium; and they can refer to the internal connection of two components. Those skilled in the art can understand the specific meaning of the above terms in the present invention according to the specific circumstances.

[0024] The present invention will now be described in further detail with reference to the accompanying drawings: The first objective of this invention is to provide a method for assessing and optimizing the avoidance of external safety risk factors in power engineering, such as... Figure 1 As shown, it includes the following steps: Acquire data on external safety risk factors throughout the entire lifecycle of power engineering projects; The external security risk factor data is preprocessed to form a dataset; Based on the dataset, a dynamic risk assessment model is used to dynamically analyze and warn of the potential risks between the power project and external safety risk factors, generating risk assessment results that include risk levels and early warning information. Based on the risk assessment results, optimization schemes for avoiding external safety risk factors are generated for each stage of the planning, design, construction and operation of the power project.

[0025] This invention comprehensively acquires external risk factors affecting power engineering safety by integrating information from multiple sources, including GIS vector data, remote sensing imagery, text ledgers, and IoT sensors, ensuring the breadth and completeness of data coverage. Next, the raw data is cleaned, de-identified, and standardized to eliminate format differences and logical errors, forming a unified and quality-controlled dataset that provides reliable input for subsequent modeling and analysis. Based on this, a dynamic risk assessment model with time-series processing capabilities is introduced, combining spatial and attribute information to probabilistically predict potential threats such as natural disasters, man-made accidents, and supply chain disruptions, and outputs tiered early warning results. Finally, based on the risk assessment conclusions, differentiated and actionable avoidance optimization strategies are generated at different project stages, such as delineating restricted areas during the planning stage, adjusting protection distances during the design stage, dynamically adjusting the work scope during the construction stage, and developing emergency response plans during the operation stage.

[0026] For example, the external security risk factor data includes spatial data, attribute data, and dynamic monitoring data. Spatial data characterizes the distribution and boundaries of external security risk factors in geographic space, forming the basis for spatial correlation analysis and avoidance distance calculation. This type of data includes GIS vector data and remote sensing image data. GIS vector data describes discrete or continuous spatial objects such as earthquake fault zones, landslide hazard areas, and hazardous enterprise locations in geometric forms such as points, lines, and surfaces. It is typically stored in formats such as SHP and GeoJSON and includes coordinate system definitions to support spatial overlay operations. Remote sensing image data acquires information such as land cover, vegetation indices, and land deformation through satellites or drones. It can be used to identify large-scale dynamic processes such as land subsidence, wildfire spread, and flooding. Typical formats are TIFF or multi-band raster data. Attribute data carries non-spatial information related to external security risks, mainly including text ledgers and policy document data. Text-based records, such as historical incidence data of natural epidemic foci, statistics on high-incidence areas of endemic diseases, and lists of hazardous chemical enterprises, are structured or semi-structured information, often in Excel or CSV format. Policy document data includes PDF documents such as national and local meteorological disaster prevention regulations, the content of which can be extracted using natural language processing technology to extract key rules and transform them into risk constraints that the system can recognize. Dynamic monitoring data reflects the real-time status of external safety risk factors evolving over time, continuously collected by an IoT sensor network deployed on-site. This type of data includes, but is not limited to, water quality parameters (such as pH, dissolved oxygen, and heavy metal ion concentration), vibration signals (such as ground pulsation and acceleration changes caused by blasting disturbance), and air pollutant concentrations (such as PM2.5). 2.5 SO2, NO x ).

[0027] For example, a method for preprocessing the external security risk factor data includes: External safety risk factor data undergoes deduplication and logical error correction. Deduplication identifies data entries with the same spatial location, timestamp, and attribute characteristics, prioritizing the most authoritative records from their sources to avoid redundant data interfering with analysis results. Logical error correction is performed based on a pre-defined rule base, such as checking whether geological disaster sites are located within reasonable geomorphic units or whether flood inundation areas exceed watershed boundaries. Upon detecting anomalies, a manual review process or an automatic correction mechanism is triggered.

[0028] Data containing sensitive information about external security risk factors is anonymized. For data items containing precise geographic locations (such as latitude and longitude coordinates), critical infrastructure identifiers, or other controlled information, anonymization is performed using methods such as offset perturbation, coordinate fuzzification, and attribute generalization (e.g., replacing specific company names with "a certain chemical company"). The anonymization strategy can be dynamically adjusted according to the risk level to ensure that it meets both the needs of GIS spatial analysis and complies with relevant national regulations on geographic information security.

[0029] Spatial and attribute data are standardized to unify the spatial reference coordinate system and data storage format. Attribute data is named, standardized in terms of units and coded according to a unified metadata standard to ensure that the risk classification in text ledgers and policy documents is consistent with the main database. Remote sensing image data is normalized according to resolution, band combination and projection method to facilitate subsequent model calls.

[0030] For example, the dynamic risk assessment model includes a natural disaster assessment model, a man-made accident assessment model, and a supply chain risk assessment model; The natural disaster assessment model includes at least one of the following: earthquake risk assessment model, geological disaster assessment model, flood inundation analysis model, and extreme weather assessment model. The earthquake risk assessment model, based on regional seismic motion parameter zoning maps, active fault distribution data, and historical earthquake statistics, combines probabilistic seismic hazard analysis (PSA) to calculate peak ground acceleration (PGA) at different return periods, thereby assessing the potential damage to critical facilities such as substation foundations and transmission towers. The geological disaster assessment model integrates factors such as digital elevation models (DEM), soil and rock types, rainfall intensity, and spatiotemporal distribution, using information content methods or physical driving models (such as TRIGRS) to zonate the susceptibility and hazard of geological disasters such as landslides and debris flows, predicting the spatiotemporal probability of disasters occurring under heavy rainfall conditions. Flood inundation analysis models rely on hydrodynamic simulation tools (such as HEC-RAS or MIKE FLOOD) to integrate river cross-sections, topographic elevations, and design storm runoff hydrographs. These models simulate the inundation extent, water depth, and flow velocity under different frequency flood events, identifying flood-risk points at low-lying sites or along river routes. Extreme weather assessment models combine numerical weather prediction outputs with empirical wind field models (such as the Holland model) to predict maximum wind speed, wind direction changes, and duration under typhoon paths, assessing the impact of strong winds on wind turbine blades, transmission line galloping, and tower structural stability.

[0031] The human-caused accident assessment model includes at least one of the following: a terrorist attack threat assessment model, a hazardous enterprise accident consequence simulation model, and a fire and explosion diffusion model. The terrorist attack threat assessment model constructs a multi-indicator system encompassing target importance, protection level, surrounding security situation, and public opinion intelligence. It employs fuzzy comprehensive evaluation or Bayesian network algorithms to quantify the likelihood of deliberate attacks on critical power facilities, assisting in the formulation of differentiated security strategies. The hazardous enterprise accident consequence simulation model targets major hazard sources such as adjacent chemical industrial parks and oil and gas storage and transportation facilities. It uses a Gaussian plume model to simulate the diffusion path of toxic gas leaks, employs the TNT equivalent method to estimate the overpressure attenuation law of the explosion shock wave, or calculates the fire impact radius based on a thermal radiation model, thereby determining whether sensitive units such as substations and control rooms are within the hazard range. The fire and explosion diffusion model is applicable to areas prone to wildfires or densely packed combustible materials within factory areas. It combines vegetation load, humidity, wind speed, and terrain slope, using cellular automata or Lagrange particle tracking methods to simulate the direction and speed of fire spread, providing early warning of the risk period and spatial segment where transmission corridors may be ignited.

[0032] The supply chain risk assessment model includes at least one of a fuel supply disruption impact model and a water shortage early warning model. The fuel supply disruption impact model focuses on major energy inputs such as coal and natural gas, integrating factors such as local supply capacity, transportation network (railways, ports, pipelines), inventory levels, and response time of alternative solutions. It uses system dynamics or Monte Carlo simulation methods to analyze the probability of supply disruptions caused by factors such as geopolitical conflicts, extreme weather, or traffic accidents, and the degree of impact on the continuity of power generation. The water shortage early warning model targets projects with high cooling water demand, such as thermal power and nuclear power plants. Based on watershed hydrological monitoring data, water withdrawal permits, climate change trends, and competition for agricultural / industrial water use, it constructs a water pressure index to identify risk windows of insufficient cooling water supply during dry seasons, supporting operational scheduling optimization and the deployment of water-saving measures.

[0033] For example, a method for dynamically analyzing and providing early warning of potential risks between the power project and external safety risk factors includes: Temporal convolutional networks are used to process the temporal data in the dynamic monitoring data and extract temporal features. The temporal features are fused with spatial data and attribute data, and risk probability prediction is performed using the Bayesian LSTM algorithm. The risk assessment results, which include risk level classification and early warning time windows, are generated based on the prediction results.

[0034] This approach combines temporal convolutional networks with Bayesian LSTM, retaining the powerful nonlinear fitting capabilities of deep neural networks while enhancing the reliability and interpretability of prediction results. This addresses the challenge of traditional static assessment methods struggling to handle complex spatiotemporally coupled risks. Therefore, it can more accurately identify risk evolution trends, issue tiered warnings in advance, and significantly improve the proactive prevention and control capabilities and emergency response efficiency of power projects throughout their entire lifecycle.

[0035] For example, the method for generating an optimization scheme to avoid the external security risk factors includes: During the planning phase, based on the distribution characteristics and risk levels of external safety risk factors, recommended areas and prohibited areas for project site selection are generated. Specifically, based on the spatial distribution characteristics and corresponding risk levels of external safety risk factors such as earthquake zones, geological disaster-prone areas, flood inundation areas, and the distribution of hazardous enterprises, a spatial overlay analysis algorithm is used to automatically delineate suitable recommended areas for construction and prohibited areas that should be strictly avoided.

[0036] During the design phase, the system simulates the varying degrees to which different engineering schemes are affected by external safety risks, outputting optimized design schemes that include avoidance distances and protective measures. Taking power transmission line route design as an example, when the line needs to cross mountainous areas or be near oil and gas pipelines, physical simulation modules such as wind deflection, vibration, and explosion shock wave propagation can be loaded onto a 3D geographic model to quantify the differences in the degree of impact from extreme weather, human accidents, and other factors under different route schemes. Based on the simulation results, the system automatically generates design optimization suggestions that include minimum avoidance distance recommendations and the addition of protective measures such as crash barriers or firebreaks, thereby minimizing potential safety threats while ensuring functional requirements.

[0037] During the construction phase, the spatial relationship between construction activities and external safety risk factors is monitored in real time, and the construction sequence and work scope are dynamically adjusted. The location, operating status, and surrounding environmental parameters of construction machinery are acquired in real time to construct a dynamic spatial relationship map between construction activities and external safety risk factors. Once construction vehicles are detected entering marked ground subsidence sensitive areas or forest areas prone to wildfires, the system immediately triggers an early warning mechanism and pushes adjustment instructions to on-site management personnel, prompting them to suspend related operations or change the construction sequence and work scope.

[0038] During the operation phase, the system combines long-term monitoring data to assess the cumulative impact of external safety risk factors on the safe operation of the project, and formulates risk prevention and emergency response measures. For example, for photovoltaic power plants that are exposed to strong winds and sandstorms for a long time, the system can analyze the relationship between the wear rate of the component surface and the cleaning cycle, propose differentiated operation and maintenance strategies, and extend the equipment life.

[0039] For example, after the step of generating an optimization scheme to avoid the external security risk factors, the method further includes: The dataset, risk assessment results, and avoidance optimization schemes are visualized on an electronic map using a GIS engine. Specifically, the GIS engine loads preprocessed external safety risk factor data (such as geological disaster boundaries and flood inundation areas), risk level distribution maps output by the model (such as coloring of high / medium / low risk areas), and structured or unstructured information such as site selection recommendation areas, prohibited areas, and protective measure suggestions generated at each stage into a web-based or desktop electronic map in the form of vector layers, raster layers, or annotation symbols.

[0040] The system supports layered rendering based on the type of external safety risk factor, and overlays power engineering planning lines and sites. Users can selectively enable or disable specific risk layers according to management needs, such as independently viewing peak ground acceleration zoning maps, landslide susceptibility maps, and hazardous enterprise distribution maps. Overlay observation can be achieved by adjusting layer transparency. Each risk factor corresponds to an independent data layer with independent style configuration rules (such as color gradient, line type, and fill pattern), facilitating the differentiation of spatial distribution characteristics of different types of risks. Furthermore, the system supports fusion calculations of multiple risk layers to generate comprehensive risk heat maps, aiding in the identification of areas with overlapping multiple risks. Simultaneously, by overlaying power engineering planning lines and sites, key indicators such as the minimum distance and overlap area between engineering facilities and risk sources can be directly measured on the map interface, providing quantitative basis for subsequent avoidance decisions.

[0041] It provides a timeline control to display the historical evolution of external safety risk factors and the changes in the risk impact range at each stage of power engineering. Users can drag the time slider or set a time interval to replay the risk evolution trajectory of a specific area over the past few years. For example, it can dynamically play the changing trend of flood inundation area in a river basin over the past decade, or the process of the annual expansion of ground subsidence in a mining area. Simultaneously, it integrates with the power engineering's time schedule (planning → design → construction → operation) to synchronously display the projection results of the risk impact range at each stage, such as the increased risk of temporary landslides caused by rainfall during construction, and the increased frequency of extreme weather events due to climate change during the operation period.

[0042] For example, after the step of preprocessing the external security risk factor data, the method further includes: Establish a tiered review mechanism, whereby the first-level review body conducts a preliminary review of the processed data, and the second-level review body conducts the final review. The approved data is stored in both relational and non-relational databases, and a spatial index is created using R-tree spatial indexing technology.

[0043] The first-level review body is typically the data review personnel designated by the local branch office or project site. They are responsible for the initial verification of locally collected and pre-processed data, checking aspects including, but not limited to, whether coordinate accuracy meets standards, whether attribute fields are missing, whether sensitive information has been anonymized, and whether the data source is reliable. The second-level review body is the professional approval team or data center administrator at the head office level, responsible for the final approval. They focus on reviewing cross-regional consistency, model adaptability, and the existence of potential security or legal risks. Only after data passes both levels of review can it enter the formal database storage stage. This mechanism effectively prevents data pollution caused by misoperation, format errors, or malicious uploads, enhancing the system's overall data governance capabilities. Through R-tree spatial indexing technology, large-scale spatial overlay analysis can be completed in milliseconds, supporting real-time responses for functions such as visualization, avoidance scheme generation, and dynamic early warning. For example, when assessing the distribution of natural disease foci around a newly built photovoltaic power plant during the operation phase, the system uses the R-tree index to quickly filter out relevant areas within a 10-kilometer radius, and automatically generates a risk warning report by combining this with disease information in the attribute database.

[0044] For example, the dynamic risk assessment model supports dynamic expansion; the expansion method includes: The newly added or optimized dynamic risk assessment model is determined according to the specific application scenario, triggering the hierarchical review mechanism. After being reviewed and approved by the first-level review body and the second-level review body, the newly added or optimized dynamic risk assessment model is integrated into the dynamic risk assessment model library and associated with the corresponding external safety risk factor type and power engineering stage.

[0045] This invention achieves a sustainable enhancement of the ability to assess external security risks. Because the system allows for the flexible introduction or improvement of risk assessment models based on actual engineering scenarios, and its scientific validity and compliance are ensured through rigorous two-level review, and standardized management is achieved through model library integration and classification association, it can effectively address the challenges of new, regional, or complex external security risks, thereby improving the adaptability and foresight of the overall assessment system.

[0046] The second objective of this invention is to provide an assessment and avoidance optimization system for external safety risk factors in power engineering, comprising: Data acquisition module: used to acquire data on external safety risk factors throughout the entire lifecycle of a power project; Data preprocessing module: used to preprocess the external security risk factor data to form a dataset; Dynamic risk assessment module: Based on the dataset, it is used to dynamically analyze and warn of potential risks between the power project and external safety risk factors through a dynamic risk assessment model, and generate risk assessment results containing risk level and early warning information; Decision optimization module: Based on the risk assessment results, it generates optimization schemes for avoiding external safety risk factors for each stage of the planning, design, construction and operation of the power project.

[0047] The system provides a comprehensive and diverse information foundation through a data acquisition module, ensuring the breadth and depth of risk identification; the data preprocessing module, through standardized data governance, guarantees the accuracy and consistency of the data sources upon which subsequent analysis relies; the dynamic risk assessment module, as the core analysis unit, uses advanced model algorithms to achieve precise quantification and forward-looking early warning of potential risks, significantly improving risk perception capabilities; and the decision optimization module transforms assessment conclusions into specific action guidelines, providing scientific decision support for each stage of the project, ultimately effectively enhancing the risk resistance capability and safe operation level of the power project throughout its entire life cycle.

[0048] In one embodiment of the present invention, a computer device is provided, comprising a processor and a memory. The memory stores a computer program, which includes program instructions. The processor executes the program instructions stored in the computer storage medium. The processor may be a Central Processing Unit (CPU), or other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. It is the computing and control core of the terminal, suitable for implementing one or more instructions, specifically suitable for loading and executing one or more instructions from the computer storage medium to achieve corresponding method flows or corresponding functions. The processor in this embodiment can be used for operating methods for assessing and avoiding optimization of external safety risk factors in power engineering.

[0049] This invention also provides a storage medium, specifically a computer-readable storage medium (Memory), which is a memory device in a computer device used to store programs and data. It is understood that the computer-readable storage medium here can include both the built-in storage medium in the computer device and extended storage media supported by the computer device. The computer-readable storage medium provides storage space that stores the terminal's operating system. Furthermore, this storage space also stores one or more instructions suitable for loading and execution by a processor. These instructions can be one or more computer programs (including program code). It should be noted that the computer-readable storage medium here can be high-speed RAM or non-volatile memory, such as at least one disk storage device. The processor can load and execute one or more instructions stored in the computer-readable storage medium to implement the corresponding steps of the assessment and avoidance optimization method for external safety risk factors in power engineering described in the above embodiments.

[0050] Those skilled in the art will understand that embodiments of the present invention can be provided as methods, systems, or computer program products. Therefore, the present invention can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, the present invention can take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0051] This invention is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the invention. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, generate instructions for implementing the flowchart illustrations and / or block diagrams. Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.

[0052] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1 One or more processes and / or boxes Figure 1The function specified in one or more boxes.

[0053] These computer program instructions may also be loaded onto a computer or other programmable data processing equipment to cause a series of operational steps to be performed on the computer or other programmable equipment to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable equipment for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.

[0054] Finally, 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 the above embodiments, those skilled in the art should understand that modifications or equivalent substitutions can still be made to the specific implementation of the present invention. Any modifications or equivalent substitutions that do not depart from the spirit and scope of the present invention should be covered within the scope of protection of the claims of the present invention.

Claims

1. A method for assessing and optimizing the avoidance of external safety risk factors in power engineering, characterized in that, Includes the following steps: Acquire data on external safety risk factors throughout the entire lifecycle of power engineering projects; The external security risk factor data is preprocessed to form a dataset; Based on the dataset, a dynamic risk assessment model is used to dynamically analyze and warn of the potential risks between the power project and external safety risk factors, generating risk assessment results that include risk levels and early warning information. Based on the risk assessment results, optimization schemes for avoiding external safety risk factors are generated for each stage of the planning, design, construction and operation of the power project.

2. The method for assessment and avoidance optimization of external safety risk factors in power engineering according to claim 1, characterized in that, The external security risk factor data includes spatial data, attribute data, and dynamic monitoring data; among which, spatial data includes GIS vector data and remote sensing image data; attribute data includes text ledgers and policy document data; and dynamic monitoring data includes water quality, vibration, and air pollutant concentration data collected in real time by IoT sensors.

3. The method for assessing and avoiding external safety risk factors in power engineering according to claim 2, characterized in that, The method for preprocessing the external security risk factor data includes: Perform deduplication and logical error correction cleaning on external security risk factor data; Data on external security risk factors containing sensitive information should be anonymized. Standardize spatial and attribute data to unify spatial reference coordinate systems and data storage formats.

4. The method for assessment and avoidance optimization of external safety risk factors in power engineering according to claim 1, characterized in that, The dynamic risk assessment model includes a natural disaster assessment model, a man-made accident assessment model, and a supply chain risk assessment model. The natural disaster assessment model includes at least one of earthquake risk assessment model, geological disaster assessment model, flood inundation analysis model, and extreme weather assessment model; the man-made accident assessment model includes at least one of terrorist attack threat assessment model, hazardous enterprise accident consequence simulation model, and fire and explosion diffusion model; and the supply chain risk assessment model includes at least one of fuel supply disruption impact model and water shortage early warning model.

5. The method for assessment and avoidance optimization of external safety risk factors in power engineering according to claim 1, characterized in that, Methods for dynamically analyzing and providing early warning of potential risks between the power project and external safety risk factors include: Temporal convolutional networks are used to process the temporal data in the dynamic monitoring data and extract temporal features. The temporal features are fused with spatial data and attribute data, and risk probability prediction is performed using the Bayesian LSTM algorithm. The risk assessment results, which include risk level classification and early warning time windows, are generated based on the prediction results.

6. The method for assessment and avoidance optimization of external safety risk factors in power engineering according to claim 1, characterized in that, The method for generating an optimization scheme to avoid the external security risk factors includes: During the planning phase, based on the distribution characteristics and risk levels of external security risk factors, recommended areas and prohibited areas for project site selection are generated. During the design phase, the degree of impact of different engineering schemes on external safety risk factors is simulated, and an optimized design scheme including avoidance distance and protective measures is output. During the construction phase, the spatial relationship between construction activities and external safety risk factors is monitored in real time, and the construction sequence and scope of work are dynamically adjusted. During the operation phase, the cumulative impact of external safety risk factors on the safe operation of the project is assessed by combining long-term monitoring data, and risk prevention and emergency response measures are formulated.

7. The method for assessment and avoidance optimization of external safety risk factors in power engineering according to claim 1, characterized in that, After generating the optimization scheme for avoiding the aforementioned external security risk factors, the method further includes: The dataset, risk assessment results, and avoidance optimization schemes are visualized on an electronic map using a GIS engine. It supports layered rendering based on the type of external safety risk factors, and overlays the planned power engineering lines and sites. A timeline control is provided to display the historical evolution of external safety risk factors and the changes in the scope of risk impact at each stage of power engineering.

8. The method for assessment and avoidance optimization of external safety risk factors in power engineering according to claim 1, characterized in that, After the step of preprocessing the external security risk factor data, the method further includes: Establish a tiered review mechanism, whereby the first-level review body conducts a preliminary review of the processed data, and the second-level review body conducts the final review. The approved data is stored in both relational and non-relational databases, and a spatial index is created using R-tree spatial indexing technology.

9. The method for assessment and avoidance optimization of external safety risk factors in power engineering according to claim 8, characterized in that, The dynamic risk assessment model supports dynamic expansion. The extension method includes: The newly added or optimized dynamic risk assessment model is determined according to the specific application scenario, triggering the hierarchical review mechanism. After being reviewed and approved by the first-level review body and the second-level review body, the newly added or optimized dynamic risk assessment model is integrated into the dynamic risk assessment model library and associated with the corresponding external safety risk factor type and power engineering stage.

10. A system for assessing and optimizing the avoidance of external safety risk factors in power engineering, characterized in that, include: Data acquisition module: used to acquire data on external safety risk factors throughout the entire lifecycle of a power project; Data preprocessing module: used to preprocess the external security risk factor data to form a dataset; Dynamic risk assessment module: Based on the dataset, it is used to dynamically analyze and warn of potential risks between the power project and external safety risk factors through a dynamic risk assessment model, and generate risk assessment results containing risk level and early warning information; Decision optimization module: Based on the risk assessment results, it generates optimization schemes for avoiding external safety risk factors for each stage of the planning, design, construction and operation of the power project.

Images