1202 results about "Hazard" patented technology

The invention discloses a plateau mountain road disaster identification method and system based on multi-source remote sensing image restoration and super-resolution reconstruction. The method comprises the following steps: acquiring and preprocessing a multi-source remote sensing image of a plateau mountain region, and extracting landform measurement parameters based on a digital elevation model; a super-resolution reconstruction network fusing deformable convolution and Transform is constructed, and a low-resolution image is reconstructed by using constraint training of a composite loss function containing geomorphic measurement parameters; performing feature extraction and adaptive weighted fusion on the preprocessed image and the reconstructed high-resolution image; based on the fused image, utilizing a multi-task deep learning model to identify landslide, debris flow and roadbed subsidence disasters along the highway; and carrying out morphological optimization and boundary refinement under GIS constraint on an identification result, and outputting a disaster thematic map. According to the invention, the precision and reliability of road disaster identification in a complex terrain environment are effectively improved.

The invention provides a river levee flood control pile foundation stress analysis method and system, and relates to the technical field of river levee flood control pile foundation stress analysis. Multi-channel sensors are arranged on the pile top, the pile side and the pile end, and the sampling frequency is automatically switched along with the flood stage; inverting the soil saturation based on displacement and pore pressure change, dynamically correcting the permeability coefficient and the effective stress, and outputting a space-time coupling parameter matrix; determining a hazard source for the monitoring point, constructing an elliptical search domain by taking the hazard source as a center, and recursively incorporating abnormal points to form a risk area; a seepage-structure full-coupling finite element model is established in the risk area, the outside of the area is simplified through an equivalent spring boundary, and a pile foundation stress-strain field and a safety coefficient are calculated through self-adaptive time step control; and finally, generating a risk report according to safety factor classification, marking a high-risk area, automatically improving the sampling frequency and triggering early warning.

The invention belongs to the technical field of data processing, and particularly relates to a potential safety hazard real-time identification method and system based on a multi-modal large model, the system comprises the multi-modal large model, a field knowledge base and a multi-modal inference engine, the multi-modal large model is responsible for visual feature extraction and scene semantic understanding of an input field image, and the field knowledge base is responsible for field knowledge base analysis; processing a natural language query provided by a user; the domain knowledge base stores construction safety related laws and regulations, guidelines and historical cases, and factual basis is provided for the system through a structured storage and efficient retrieval mechanism; the multi-modal reasoning engine coordinates the whole process of visual understanding, task decomposition, knowledge retrieval and report generation, and is a core control module for realizing multi-modal reasoning and decision making. And refined understanding of entities and hidden dangers in a construction scene is realized. According to the system and the method thereof, the image content and the text specification can be dynamically fused, and missing detection or misjudgment caused by modal splitting in a traditional method is avoided.

The invention provides a chemical potential safety hazard intelligent identification and early warning method. Relates to the field of chemical safety, and discloses a chemical potential safety hazard intelligent identification and early warning method comprising the following steps: S1, preprocessing multi-modal data through a multi-modal feature self-calibration fusion algorithm; s2, constructing a dynamic Bayesian network time-varying coupling evaluation model based on a protection layer theory; s3, related knowledge documents are retrieved by adopting an enhanced RAG technology; s4, carrying out hidden danger identification based on the knowledge-enhanced large model; s5, four-level intelligent early warning is generated based on the risk value calculation model; and S6, optimizing model parameters through deep reinforcement learning. The chemical potential safety hazard intelligent identification and early warning method based on the protective layer theory and the large model technology has the advantages that dynamic risk perception can be realized, cross-modal potential hazards can be accurately identified, an early warning scheme can be quickly generated, and the initiative and scientificity of chemical safety management can be improved.

The invention discloses a hydrogen leakage accident holographic perception and disaster situation dynamic prediction system in a tunnel scene, and belongs to the technical field of hydrogen energy traffic safety and intelligent risk management. According to the system, multi-modal information such as environmental parameters, hydrogen concentration, heat source temperature, leakage acoustic characteristics and vehicle states is collected in real time through a multi-modal sensing unit; abnormal detection, time synchronization and space registration are carried out through the information fusion module to generate fusion data in a unified format; the hazard source analysis module locates a leakage source, estimates a leakage rate, locates an ignition source and extracts disaster characteristics based on the fused data; the disaster dynamic prediction module predicts spatio-temporal evolution of diffusion, combustion and explosion by using an agent model and calculates disaster levels; the feedback early warning unit synchronously outputs the prediction information to the tunnel monitoring platform and issues early warning information; and the data storage and self-optimization module uniformly stores historical data and optimizes the prediction model through incremental learning. The system realizes real-time monitoring, rapid evaluation and intelligent disposal of tunnel hydrogen leakage accidents.

The invention relates to a multi-modal data-driven rail transit construction potential safety hazard identification method and system, and solves the problem that the accuracy and real-time performance of potential hazard identification are insufficient due to the fact that multi-source data cannot realize deep collaboration, and the method comprises the following steps: obtaining multi-modal data containing a BIM + GIS model, an unmanned aerial vehicle image stream and Internet of Things data; according to an edge end-cloud architecture, by taking BIM + GIS coordinates as a reference, the edge end associates and binds data and cleans and transmits the data to the cloud, and the cloud corrects and generates a standardized data set; and the comprehensive risk index is calculated by using an entropy weight method, and a report is generated and pushed to a construction management terminal. The method has the following effects: the multi-modal data barrier is broken, the integrated accurate identification of the hidden hidden danger of the rail transit construction is realized, and the accuracy and efficiency of the construction safety management and control are fundamentally improved.

The invention discloses a business data quality treatment method supporting system hidden danger identification, and relates to the technical field of computer information processing, and the method comprises the steps: S1, collecting a real-time batch tracking data stream from an enterprise inventory system through a multi-source data interface, and obtaining an initial data set containing inconsistent formats and missing batch numbers; s2, scanning a data stream according to the initial data set by applying a preset automatic detection rule, judging positions and types of abnormal points by utilizing a rule matching mode and a threshold comparison mechanism to obtain an abnormal point set, and activating a real-time stream analyzer to process field complete verification to generate an abnormal log record; according to the business data quality treatment method supporting system hidden danger identification, real-time and accurate anomaly detection and repair are realized, the consistency and reliability of inventory data are improved, and the enterprise inventory management efficiency is remarkably optimized.

The invention provides an automatic driving hazard scene detection method and system, electronic equipment and a vehicle, and relates to the technical field of automatic driving. According to the method, a multi-dimensional hazard scene detection rule system is established, so that accurate identification and response to key security events are realized. In the automatic driving operation process, the system continuously collects and compares a vehicle state signal with a preset triggering condition in real time, once any hazard scene condition is met, vehicle burying point data in a preset time window are collected and uploaded to a cloud end, and the vehicle burying point data are stored in the cloud end. Accident scene restoration, system risk assessment and fault root cause analysis are carried out based on the collected data, then a targeted safety repair scheme is generated, vehicle software is remotely upgraded in an OTA mode, closed-loop processing of safety problems and continuous optimization of the system are achieved, the safety, traceability and remote operation and maintenance capacity of the automatic driving system are effectively improved, and the safety and reliability of the automatic driving system are improved. And the running safety of the vehicle is ensured.

The invention relates to the technical field of construction safety, in particular to a trestle construction hazard source assessment method and system, and the method comprises the steps: constructing a hazard source data set corresponding to a trestle construction process, carrying out the entry recording of various potential hazard sources, and setting impact factors for representing risks; collecting field data of the construction process, and associating the field data with the influence factors to obtain risk characterization forming a hazard source; fusing the risk characterization with the environmental parameters, and constructing a space-time risk mapping layer; based on the space-time risk mapping layer, performing quantitative analysis on the hazard source through a multi-factor comprehensive model to obtain risk distribution characteristics in different level intervals; and according to the risk distribution characteristics, generating a space-marked trestle risk map. According to the invention, the problems of strong subjectivity and lack of systematic analysis of existing trestle construction hazard source assessment are effectively solved, the objectivity of risk assessment is enhanced, and the capability of accurately judging the risk state in a complex construction environment is improved.

The invention discloses a comprehensive remote sensing recognition system for hidden danger of ice lake outburst. The system comprises a data acquisition and preprocessing module, an ice lake extraction module, an ice dam stability evaluation module, a risk calculation module and a visualization and early warning module. According to the system, optical images, SAR images, LiDAR point cloud and meteorological data are utilized, firstly, a glacial lake boundary is extracted through a water body index, the area and the volume are calculated, then the water level rising rate is monitored in combination with multi-temporal data, the dam body stability is evaluated by utilizing three-dimensional terrain and deformation parameters, and the dam body stability is evaluated by combining the temperature melting corrosion rate and triggering factors such as rainfall, earthquakes and inflow. And constructing a multi-factor outburst risk index model, and finally carrying out visualization and graded early warning on a result in a GIS platform. The method can achieve the quick, comprehensive and intelligent recognition of the hidden danger of ice lake outburst, has the advantages of being high in monitoring precision, high in automation degree, high in early warning timeliness and the like compared with a traditional single data or experience judgment method, and can be widely applied to the disaster prevention and control work of dense ice lake areas such as the Qinghai-Tibet Plateau and the Himalaya mountain.

The invention discloses a gas safety intelligent inspection method and system, and belongs to the crossing field of artificial intelligence technology and safety production management. The method comprises the following steps: acquiring image data through a field data acquisition terminal; a preliminary hidden danger identification module in the cloud server innovatively adopts a scene perception target detection model and a scene reasoning multi-label model for collaborative analysis; and the comprehensive risk assessment module performs deep correlation analysis on the hidden dangers based on a preset gas safety knowledge graph, and determines a quantitative comprehensive risk value by calculating a basic risk accumulated value of each hidden danger and a correlation risk increment generated by a correlated hidden danger pair. According to the method, the defects that traditional inspection depends on subjective experience and composite risks are difficult to quantify are overcome, amplification risks caused by concurrence of multiple hidden dangers can be accurately identified and quantitatively evaluated, continuous self-improvement of system capability is realized through a closed-loop mechanism, and the intelligent level of gas safety management is remarkably improved.

The invention discloses a power grid facility safety-oriented forest fire spreading early warning method and system, and particularly relates to the field of cloud edge collaboration and danger prediction.The method comprises the steps of arranging a plurality of monitoring nodes in a power grid protection area, collecting monitoring data of temperature, humidity, wind speed, smoke concentration and spectral radiation, and performing early warning on forest fire spreading; matching the monitoring data of each monitoring node with the corresponding acquisition time, and constructing a multi-node environment data set according to a matching result; according to the method, a time rhythm index and multi-node difference identification mechanism is established under a cloud edge collaborative architecture, and an integrated danger prediction process of data synchronization, difference correction and trend solution is realized, so that the problems of virtual height early warning and response lag caused by misjudgment of node data asynchronization and cloud fusion in existing forest fire monitoring are solved.

The invention discloses a storm surge nearshore disaster identification method, device and equipment fused with a typhoon dynamic influence domain, a medium and a product, and relates to the technical field of meteorological disaster monitoring. The method comprises the following steps: acquiring a meteorological ocean reanalysis data set in a historical set age limit of a target area, and preprocessing multi-source data; then background field elimination processing is carried out; determining a dynamic influence radius based on the typhoon intensity grade and the storm surge abnormal data; determining the center position of the typhoon according to the dynamic influence radius, and generating a typhoon dynamic influence domain space mask by adopting a spherical distance calculation method; a near-shore buffer area is determined according to the typhoon dynamic influence domain space mask, and a storm surge disaster area is determined based on a near-shore buffer area constraint and water increase threshold value judgment method; and carrying out storm surge near-shore disaster identification on the basis of the storm surge disaster area by adopting a geographic space visualization method to obtain an identification result. According to the invention, accurate storm surge disaster discrimination can be realized.

The invention discloses a remote sensing satellite network security situation awareness method and system with dual prevention mechanisms, and the method comprises the steps: obtaining multi-source heterogeneous data from a remote sensing satellite ground system network, and generating a structured data set through cleaning, denoising and standardization processing; and according to the structured data set, recording network assets by adopting an asset identification algorithm, and generating a risk thermodynamic diagram of the network assets through a Bayesian network model and an entropy weight method. And according to the risk thermodynamic diagram and the structured data set, adopting a deep learning model to detect abnormal traffic and behaviors, and generating a hidden danger list marked with priorities through a general vulnerability scoring standard and a threat intelligence library. And according to the risk thermodynamic diagram and the hidden danger list, constructing a dynamic security situation map by adopting a graph database and a community discovery algorithm. Therefore, the real-time fusion capability of multi-source heterogeneous data is improved, a dynamic attack chain reasoning mechanism is enhanced, and collaborative decision-making of risk early warning and hidden danger treatment is realized.

The invention discloses a road and bridge support hidden danger monitoring and early warning method and system, and belongs to the technical field of road and bridge support hidden danger intelligent monitoring. Constructing a theoretical transfer relation model based on the synchronous vehicle load parameters and the synchronous support mechanical response parameters; generating a modified theoretical model based on the synchronous environment temperature parameters and the theoretical transfer relation model; obtaining a response residual error based on the corrected theoretical model, the synchronous vehicle load parameter and the synchronous support mechanical response parameter; acquiring a hidden danger characteristic mode based on the response residual error and the synchronous structure attitude parameter; acquiring a risk probability value based on the hidden danger feature mode; and obtaining graded early warning information based on the risk probability value and the hidden danger characteristic mode. According to the road and bridge support hidden danger monitoring and early warning method and system disclosed by the invention, the problems of false alarm and missing alarm in the prior art can be solved, and the accuracy and reliability of road and bridge support hidden danger monitoring are greatly improved.

The invention discloses a construction potential safety hazard identification method and system based on multi-agent cooperation. The method comprises the steps that an intelligent agent network is constructed, the intelligent agent network comprises a plurality of intelligent agents responsible for different tasks, and the intelligent agents cooperatively work in a serial mode and a parallel mode; obtaining construction related data; performing preliminary identification of potential safety hazards to obtain a preliminary analysis result; verifying and optimizing the potential safety hazard based on the preliminary analysis result in combination with an intelligent agent network to obtain a verification result; correcting the preliminary analysis result based on the verification result to obtain a conclusion of hidden danger identification and risk assessment; and generating a standardized security management document based on the conclusion according to the selected document type. By implementing the method provided by the invention, more accurate hidden danger identification, risk assessment and regulation matching can be realized, standardized and high-quality safety management documents can be generated, the working efficiency can be improved, and the professionality and accuracy of the documents can be ensured, so that the construction safety management practice is effectively supported.

The invention relates to the technical field of ownership intelligence, in particular to a ownership intelligence fuzzy language instruction recognition method based on scene risk guidance. In order to solve the problem that a fuzzy language instruction recognition method in the prior art easily causes understanding deviation and potential safety hazards, the invention provides an intelligent fuzzy language instruction recognition method based on scene risk guidance, which comprises the following steps of: 1) constructing a scene risk map according to a basic risk and a distance risk; 2) identifying an instruction type; 3) instruction analysis and risk assessment; and 4) instruction rewriting and object identification replacement. According to the method, a risk perception mechanism is introduced, the high-risk behavior execution probability caused by semantic deviation of the intelligent robot is effectively reduced, the understanding accuracy and interaction safety of the intelligent robot in a real scene are improved, and the method is suitable for a complex application environment with high requirements for task reliability and behavior controllability of the intelligent robot.

The invention discloses a risk assessment method for a supercritical carbon dioxide conveying pipeline and related equipment, and the method comprises the steps: constructing a fault tree model for a failure event of the pipeline; obtaining a consequence event corresponding to the failure event, and constructing a consequence model according to the consequence event; based on the fault tree model and the consequence model, obtaining a bow-tie model of the supercritical carbon dioxide conveying pipeline; obtaining a plurality of groups of evaluation data of the plurality of evaluation policies for the basic event in the bow-tie model, and obtaining a failure probability corresponding to the basic event based on the plurality of groups of evaluation data; and obtaining an occurrence probability of a leakage consequence corresponding to the basic event based on the failure probability, and performing hazard assessment on the leakage consequence based on the occurrence probability to obtain an assessment result. According to the method, the occurrence frequency of consequences in various risk scenes is accurately calculated, the problem that the risk in the actual conveying process cannot be accurately reflected is avoided, and the design and implementation of subsequent risk management decisions and optimization measures can be effectively supported.

A method and apparatus for assessing the hazard of rainfall-induced landslide clusters, and a computer device. The method comprises: acquiring historical rainfall-induced landslide cluster data from past intense rainfall events to construct landslide sample data; performing analysis on the basis of landslide attribute parameters and rainfall-induced landslide cluster data distribution information of the landslide sample data to obtain landslide development characteristics; on the basis of landslide geographical features and geometric features, using the landslide sample data and a plurality of candidate landslide-influencing indexes to analyze underlying patterns of landslide occurrence, so as to establish a landslide hazard evaluation index system; and performing correlation analysis on the plurality of candidate landslide-influencing indexes to determine a target landslide-influencing index, and combining the target landslide-influencing index with the landslide hazard evaluation index system to obtain a landslide hazard assessment model constructed on the basis of an automated machine learning framework. The efficiency of rainfall-induced landslide cluster hazard assessment can be improved and the accuracy of rainfall-induced landslide cluster hazard assessment can be effectively enhanced.

The invention discloses a multi-disaster-bearing body marine disaster risk assessment method based on a sensitive matrix, and relates to the technical field of marine science, the method comprises the following steps: defining a marine disaster assessment area, and determining multiple disaster-inducing factor types in the assessment area; and sorting the distribution characteristics of various disaster-bearing bodies in the evaluation area, and determining an evaluation object. According to the multi-disaster-bearing body marine disaster risk assessment method based on the sensitive matrix, the sensitive matrix of the disaster-inducing factors and the disaster-bearing bodies is constructed, the sensitivity difference of different disaster-bearing bodies to the disaster-inducing factors is quantified, the loss difference of different disaster-bearing bodies under similar disasters can be accurately described, the limitation of a traditional single disaster assessment method is avoided, and the risk assessment accuracy is improved. The method comprehensively analyzes the potential threats of disasters to different disaster-bearing bodies, improves the overall precision of risk assessment, and guarantees that the vulnerability degrees of the different disaster-bearing bodies are accurately reflected when the different disaster-bearing bodies face specific disaster-inducing factors through sensitive matrix normalization.

The invention discloses a campus potential safety hazard supervision system based on artificial intelligence, which belongs to the technical field of campus security and protection, and specifically comprises the following steps: collecting campus environment data through a multi-mode sensor network and converting the campus environment data into an underlying physical event stream; performing matching reasoning by utilizing a causal rule in a preset campus safety knowledge base, and generating a potential safety hazard hypothesis containing an expected consequence event sequence and an initial confidence coefficient; difference nodes are determined through comparative analysis, and key verification evidence types are selected; performing time sequence matching degree calculation based on the verification event sequence acquired in an enhanced manner, and generating a risk assessment value corresponding to each potential safety hazard hypothesis; a standardized handling protocol is automatically triggered when the risk assessment value exceeds a threshold. According to the invention, through a multi-level causal reasoning and verification mechanism, the problem of a gap between a physical sensing signal and behavior semantics in the prior art is effectively solved, and accurate identification and rapid disposal of campus potential safety hazards are realized.

The invention discloses a coal mine hidden danger event intelligent reasoning method based on a knowledge graph, and belongs to the technical field of coal mine safety, and the method specifically comprises the steps: obtaining a to-be-deduced entity with a real-time data flow recognition state parameter exceeding a threshold value range; calling a state transition rule set according to the entity type and constructing an independent deduction process; executing state transition calculation in each deduction process to generate a state evolution sequence; state combination matching is carried out based on the relation mode of the static knowledge graph, and entity state pairs meeting relation triggering conditions are recognized; establishing a cross-process data channel between the related deduction processes and performing parameter conversion; state deduction is executed again based on the input parameters, and deduction network topology is constructed; and finally, a complete hidden danger evolution path is obtained through reverse tracking parameter transfer relation integration. According to the method, dynamic deduction of the coal mine hidden danger forming process and accurate identification of the linkage risk conduction path are realized, and the accuracy of potential safety hazard early warning is effectively improved.

The invention relates to the technical field of engineering monitoring, in particular to a bridge structure state monitoring method and system based on digital twinning, and the method comprises the steps: building a multi-source monitoring data matrix based on a data timestamp; establishing a geometric model, a material attribute model and a load model of a bridge structure based on the multi-source monitoring data matrix, and fusing to obtain a bridge digital twin initial model; and carrying out structural mechanical analysis based on the bridge digital twin initial model to obtain stress distribution data of each region of the bridge. Through real-time acquisition and analysis of multi-source monitoring data, the method can dynamically evaluate the structural state of the bridge and timely identify potential safety hazards, so that the safety of the bridge is improved; and through calibration of the initial model, the obtained digital twin precise model reflects the real state of the bridge, and a more accurate data basis is provided for subsequent structural analysis.

The invention discloses a generative AI-based disease and insect pest identification evaluation and multi-modal question and answer method, and relates to the technical field of crop disease and insect pest prevention, and the method comprises the steps: obtaining multi-modal data containing a standardized image and a structured text feature; utilizing a pre-trained pest and disease target detection model to identify the spatial position of a pest and disease target in the image, and cutting to obtain a target area image; a color feature vector and a shape feature vector of the target area are extracted, text features are combined, semantic enhancement and cross-modal alignment are performed through generative AI, and an explicit feature vector of diseases and insect pests is constructed; matching and analyzing with a preset disease and pest knowledge base, and identifying disease and pest types; quantifying the damage degree of the diseases and pests according to the characteristic parameter change characteristics to obtain a damage grade judgment result; generating a question-answer reply based on the type identification result and the hazard level; according to the method, the problems that the disease and pest recognition accuracy is limited, the harm degree is difficult to quantify and intelligent multi-modal decision question and answer support cannot be provided are solved.

The invention relates to the technical field of geological disaster hidden danger recognition, in particular to a geological disaster hidden danger recognition method based on InSAR and semi-supervised learning, which comprises the steps of dividing hydrological sensitivity of a monitoring area according to a regional underground water unit supply schematic diagram, and setting an InSAR data sampling frequency; acquiring earth surface time sequence displacement data, including accumulated displacement, displacement rate and displacement acceleration, by using a set sampling frequency for preliminarily identifying a potential hidden danger area; geological radar detection is carried out in the potential hidden danger area, underground structure features are evaluated through a geological radar profile map, and a multi-source feature vector is constructed; according to the method, the hydrological sensitivity of the monitoring area is divided according to the regional groundwater unit supply schematic diagram, and the InSAR data sampling frequency is set, so that the problem that the high-risk area is not monitored in time due to the fact that the hydrological sensitivity change is not considered because the conventional monitoring frequency mostly adopts a fixed sampling interval is solved.

The invention discloses an early warning grade evaluation method based on an urban pollution industrial site, relates to the technical field of industrial site early warning evaluation, and solves the technical problems of incomplete overall evaluation and lack of systematic analysis process and data processing correction caused by analysis of a single evaluation index. According to the method, pollution factor indexes are integrated in a three-dimensional mode through the pollutant standard exceeding multiple mean value, the specific pollutant toxicity coefficient and the pollution plume diffusion area proportion, the pollution intensity is reflected, toxicity hazards and spatial diffusion risks are considered, the soil pollution area is calculated through the Kriging interpolation method, the groundwater pollution plume area is predicted through the MODFLOW model, and the groundwater pollution plume area is predicted through the MODFLOW model. The overlapping area is processed through a maximum area method, repeated statistics is avoided, the accuracy of pollution range data is improved, different threshold values are set, standardized matching of comprehensive indexes and early warning levels is achieved, corresponding management and control measures are defined for all the early warning levels, abstract comprehensive indexes are converted into specific practical operation guidance, and hierarchical management and control can be conveniently carried out.

The invention belongs to the technical field of unmanned aerial vehicle inspection, and discloses an unmanned aerial vehicle inspection method and device based on visual sensing and a readable storage medium, multi-modal visual data is preprocessed in real time through an edge calculation unit carried by an unmanned aerial vehicle, and only key defect data is transmitted by using a quantum encryption communication link; rapid early warning can be achieved, the timeliness requirement of emergency disposal is met, and the risk of fault expansion caused by delay is avoided; through a multi-modal data fusion algorithm, performing deep fusion on defect types, laser radar high-precision coordinates, hyper-spectral environment risk data and personnel information associated with biological characteristics with the digital twin model constructed in the step S1, and generating a defect-coordinate-environment-personnel holographic mark packet; operation and maintenance personnel do not need to manually match in discrete data, integrated information can be directly obtained, high-risk hidden danger omission caused by information splitting is effectively avoided, an inspection closed loop of recognition-positioning-evaluation is formed, and the defect management efficiency is improved.

The application belongs to the field of park unmanned inspection safety monitoring, and specifically discloses a park unmanned inspection safety monitoring system based on intelligent property, which comprises the following steps: acquiring a UAV inspection path by counting each missing space and each intersection space in a park, and discovering safety hazards in hidden spaces in the park in a timely manner; acquiring a redundant material heat conductivity index in each key space and an overlapping area of the redundant material heat conductivity index and an illumination area, evaluating a cumulative spontaneous combustion effect index between the redundant material heat conductivity index and a meteorological environment, combining a pollution rate of the redundant material in each key space, analyzing a safety coefficient of the redundant material in each key space, and helping to discover spontaneous combustion risks and environmental pollution problems in a timely manner; analyzing priority weight values of each passage path to which each key space belongs, determining a UAV inspection optimized path, and further optimizing the inspection optimized path by extracting historical inspection data, so that the UAV inspection path is more in line with actual requirements of the park.

The invention relates to a power transmission line operation state intelligent identification and analysis method, and belongs to the technical field of power transmission line state analysis. The method comprises the following steps: acquiring soil water content and foundation settlement data in real time, recognizing tower node displacement accumulation and a stress transfer path in combination with environmental factors such as temperature, humidity and wind speed, accurately judging a structural deformation abnormal region, and generating a stress concentration and transfer prediction chart through multi-source data fusion and historical data contrastive analysis. According to the method, the coordinates of potential safety hazard parts are dynamically calibrated, infinitesimal displacement monitoring errors are eliminated, finally, a tower overall structure safety evaluation report and maintenance management measures are output, through full-link data analysis and dynamic calibration, the monitoring precision and early warning capacity of tower stability under geological condition changes are remarkably improved, and safe operation of power transmission facilities is guaranteed.

A method to identify which safety leading indicators are not capturing hazards during safety inspections that later contribute to safety incidents and to identify blind spots in safety inspections. The method includes inputting a plurality of incident reports from the worksite and a plurality of inspection reports from the worksite into a system that uses machine learning (ML) and artificial intelligence (AI); identifying socio-technical factors influencing safety risks at the worksite using unsupervised clustering for topic modeling; evaluating semantic similarity between the plurality of incident report and the plurality of inspection reports conducted in a preceding time period to detect missing socio-technical factors not captured during safety inspections; and providing the identified socio-technical factors previously not captured during safety inspections to a stakeholder for development of modified inspection checklists tailored to capture the identified socio-technical factors previously not captured during safety inspection.