Extra-high voltage engineering digital construction safety risk early warning method based on artificial intelligence
By performing spatiotemporal alignment and standardization on multi-source data from UHV construction sites, dynamically correcting risk thresholds, and calculating safety risk indices by combining personnel density and mechanical stability, the problem of inaccurate risk assessment in UHV construction has been solved, and efficient safety early warning and management have been achieved.
Patent Information
- Application Number
- CN202511547843.8
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2025-10-28
- Publication Date
- 2026-01-13
AI Technical Summary
Existing technologies for UHV transmission engineering construction suffer from several problems, including inconsistent processing of multi-source heterogeneous data, fixed risk thresholds leading to biased early warning results, lack of personnel density, and inaccurate risk assessment and insufficient adaptability due to the lack of joint modeling of mechanical stability and environmental risks.
By collecting multi-source safety data in real time and performing spatiotemporal alignment and standardization, risk parameters are extracted, risk thresholds are dynamically corrected, and a safety risk index is calculated by combining personnel density and mechanical operation stability, and visualized early warning information is pushed out.
It has achieved unified integration of multi-source data and improved the accuracy of risk assessment, thereby enhancing the level of safety management and decision-making effectiveness at construction sites and improving the real-time response capability and accuracy of the early warning system.
Smart Images
Figure CN121330873A_ABST
Abstract
Description
Technical Field
[0001] This invention relates to the field of power engineering construction safety management technology, and in particular to an artificial intelligence-based digital construction safety risk early warning method for ultra-high voltage projects. Background Technology
[0002] Ultra-high voltage (UHV) power transmission projects involve densely populated work sites, large-scale machinery and equipment, and complex and variable environmental conditions, resulting in a high degree of overlap in construction safety risks. As construction progresses, real-time monitoring and risk warning in a dynamic and multi-source construction environment have become crucial for ensuring the safe construction of UHV projects. Traditional safety supervision methods mainly rely on manual inspections and experience-based judgments, which not only suffer from problems such as delayed response and fragmented information, but also lack efficient data fusion and real-time risk perception capabilities when facing complex construction environments and emergencies.
[0003] While existing technologies incorporate some information-based monitoring methods, they generally suffer from the following challenges: First, the lack of unified spatiotemporal alignment and standardized processing for multi-source heterogeneous data after collection leads to insufficient accuracy in subsequent risk assessments. Second, risk thresholds are typically fixed and cannot be dynamically adjusted based on changes in construction stages and environmental factors, easily causing biased early warning results. Third, the lack of joint modeling of personnel density, mechanical stability, and environmental risk indices results in a lack of systematicity and adaptability in the risk assessment process. Therefore, there is an urgent need to propose an artificial intelligence-based digital construction safety risk early warning method for UHV projects to improve the safety management level and risk prevention and control capabilities of UHV construction sites. Summary of the Invention
[0004] To achieve the above objectives, this invention provides an artificial intelligence-based digital construction safety risk early warning method for ultra-high voltage power transmission projects.
[0005] A digital construction safety risk early warning method for ultra-high voltage power transmission projects based on artificial intelligence includes the following steps: S1: Real-time acquisition of multi-source safety data from the UHV construction site, including personnel positioning data, mechanical equipment working status data, and environmental monitoring sensor data, and spatiotemporal alignment and standardization processing to generate a standardized safety data stream; S2: Extract several risk parameters that match the current construction phase from the standardized safety data stream, including personnel density, stability coefficient of large machinery operation, and comprehensive environmental risk index; S3: Based on the current construction stage type and comprehensive environmental risk index, the pre-set basic risk threshold is dynamically corrected to generate a dynamic risk threshold; S4: Input the personnel density and the stability coefficient of large machinery operation into the preset risk assessment model to calculate the safety risk index; S5: Compare the safety risk index with the dynamic risk threshold to determine the risk level and generate structured early warning information; S6: Visualize the structured early warning information and push it to the administrator's terminal.
[0006] Optionally, S1 specifically includes: S11: By deploying positioning base stations and wearable tags in the construction area, the spatial coordinate information of each construction worker is obtained in real time, forming a personnel positioning data stream; S12: Based on the status acquisition module installed on large construction machinery, it collects the machinery's operating mode, attitude changes and load parameters to form a data stream of the machinery's working status; S13: Collect data on temperature, humidity, wind speed and harmful gas concentration at the construction site through an environmental monitoring sensor network to form an environmental monitoring data stream; S14: The various types of data acquired from S11 to S13 are spatiotemporally aligned according to a unified timestamp and coordinate system, and the numerical types, sampling frequencies and outliers are standardized to generate a standardized secure data stream in a unified format.
[0007] Optionally, S14 specifically includes: S141: Based on the established unified and coordinated world time format and GNSS geographic reference coordinate system, the time labels and spatial locations in various data streams are uniformly converted to form a unified spatiotemporal reference. S142: Convert data values from different sources into dimensionless standard values, and use linear normalization to compress the original data to the [0,1] interval to unify the numerical scale of various types of data; S143: For data streams with different sampling frequencies, linear interpolation is used to fill in missing data points at a set uniform time interval, so that all data streams have a consistent time step. S144: Perform outlier detection on the normalized data. Use the Z-score method to identify data points with excessive deviation and determine whether they are outliers. If the outlier condition is met, replace them with the mean of the adjacent valid values. S145: All data that has undergone spatiotemporal alignment, numerical normalization, frequency unification, and anomaly handling are structurally integrated to form a standardized secure data stream.
[0008] Optionally, S2 specifically includes: S21: Based on personnel location information in the standardized safety data stream, and combined with the current construction phase's work area, count the number of personnel per unit area and calculate personnel density. ; S22: Based on the mechanical state data in the standardized safety data stream, extract the rate of change of operating posture and the rate of change of load for each large piece of machinery. Calculate the operational stability level using the volatility coefficient to obtain the operational stability coefficient of the large machinery. ; S23: Based on standardized environmental monitoring data, extract environmental factors such as temperature, wind speed, and concentration of harmful gases, calculate the risk score for each factor, and generate a comprehensive environmental risk index according to preset weights. .
[0009] Optionally, S3 specifically includes: S31: Based on the current construction stage type at the construction site, retrieve the corresponding basic risk level coefficient from the preset construction stage risk level mapping table as the initial reference parameter for the correction factor. The construction stage includes foundation excavation, tower foundation pouring, component hoisting, line erection, and acceptance retesting. S32: Based on the comprehensive environmental risk index calculated in S2, find its corresponding environmental sensitivity coefficient in the preset environmental risk impact interval table; S33: Based on the coupling relationship between the risk level coefficient and the environmental sensitivity coefficient during the construction phase, and combined with the critical operation type of the current construction task, the basic risk thresholds are weighted and corrected to form a dynamic risk threshold set oriented towards the current construction status.
[0010] Optionally, S33 specifically includes: S331: Couple and multiply the construction stage risk level coefficient extracted in S31 with the environmental sensitivity coefficient obtained in S32 to calculate the stage-environment joint correction coefficient. S332: Based on the critical operation types involved in the current construction task, extract the corresponding operation type weight coefficients from the preset operation weight table, and combine them with various basic risk thresholds to form the adjusted threshold weighted by operation category. ; S333: Perform the above correction operation sequentially on the basic risk thresholds corresponding to all relevant risk parameters to finally form a dynamic risk threshold set covering the current construction status.
[0011] Optionally, S4 specifically includes: S41: The population density calculated in S2 and stability coefficient of large machinery operation Input into the pre-set risk assessment model; S42: Based on the sensitivity weights of each risk factor defined in the model, the personnel density and operational stability coefficients are weighted and fused separately to obtain the safety risk index of the construction site at the current moment. The expression is; ,in, As a safety risk index; The risk weighting coefficient for population density; This represents the risk weighting coefficient for mechanical stability.
[0012] Optionally, S5 specifically includes: S51: Receive the security risk index calculated in S4 and the dynamic risk threshold set formed in S3, and retrieve the corresponding risk judgment threshold from the dynamic risk threshold set according to the parameter type corresponding to the security risk index. S52: Compare the safety risk index with the corresponding dynamic risk threshold, and determine the risk level of the current state of the construction site based on the comparison results; S53: Based on the determined risk level, generate structured early warning information, including risk level label, trigger parameter category, safety risk index value, corresponding dynamic threshold and determination timestamp.
[0013] Optionally, S52 specifically includes: S521: Receive the dynamic risk assessment threshold range retrieved in S51, and obtain the corresponding security risk index at the current moment. ; S522: Security Risk Index The risk level of the current construction site is determined by comparing the value with the dynamic risk threshold range and determining the risk level corresponding to the current state of the construction site based on the range in which it falls. Specifically, when... When, it is judged as low risk; when The risk was determined to be controllable; when When, it is judged as a risk to be concerned; when It was determined to be high-risk; among them, The upper limit threshold is set for low risk. This is the upper limit threshold for controllable risk; To focus on the upper limit threshold of risk; S523: Based on the judgment result of S522, output the risk level label corresponding to the current moment of the construction site.
[0014] Optionally, S6 specifically includes: S61: The structured early warning information generated in S5 is graphically processed according to the set visualization template, which includes risk level color indicators, parameter comparison bar charts, dynamic threshold trend charts, and early warning timestamp fields. S62: The visualized warning information is pushed to the authorized management personnel terminal using a message push protocol.
[0015] The beneficial effects of this invention are: This invention achieves unified spatiotemporal alignment and standardization of multi-source safety data from ultra-high voltage construction sites, enabling the fusion of personnel positioning, machinery and equipment operating status, and environmental monitoring data under the same data benchmark. This provides a high-quality input foundation for subsequent risk parameter extraction and modeling, thereby avoiding the problem of inaccurate risk assessment caused by scattered data sources and inconsistent formats.
[0016] This invention introduces a dynamic correction mechanism for risk level coefficients and environmental sensitivity coefficients during the construction phase, and combines personnel density and mechanical operation stability parameters. It calculates a safety risk index through a pre-set risk assessment model, compares it with a dynamic threshold to determine the risk level, and then pushes the results to the system for visualization. This improves the accuracy of on-site safety management and the effectiveness of decision-making. Attached Figure Description
[0017] To more clearly illustrate the technical solutions in this invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only for this invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.
[0018] Figure 1 This is a schematic diagram of the construction safety risk early warning method according to an embodiment of the present invention; Figure 2 This is a schematic diagram of the process for generating dynamic risk thresholds according to an embodiment of the present invention. Detailed Implementation
[0019] The present invention will now be described in detail with reference to the accompanying drawings and specific embodiments. It should also be noted that, to make the embodiments more comprehensive, the following embodiments are the best and preferred embodiments, and those skilled in the art can use other alternative methods to implement some well-known technologies; moreover, the accompanying drawings are only for more specific description of the embodiments and are not intended to specifically limit the present invention.
[0020] like Figures 1-2 As shown, an artificial intelligence-based digital construction safety risk early warning method for ultra-high voltage power transmission projects includes the following steps: S1: Real-time acquisition of multi-source safety data from the UHV construction site, including personnel positioning data, mechanical equipment working status data, and environmental monitoring sensor data, and spatiotemporal alignment and standardization processing to generate a standardized safety data stream; S1 specifically includes: S11: By deploying positioning base stations and wearable tags in the construction area, the spatial coordinate information of each construction worker is obtained in real time, forming a personnel positioning data stream; S12: Based on the status acquisition module installed on large construction machinery, it collects the machinery's operating mode, attitude changes and load parameters to form a data stream of the machinery's working status; S13: Collect data on temperature, humidity, wind speed and harmful gas concentration at the construction site through an environmental monitoring sensor network to form an environmental monitoring data stream; S14: All types of data acquired from S11 to S13 are spatiotemporally aligned according to a unified timestamp and coordinate system, and the numerical types, sampling frequencies, and outliers are standardized to generate a standardized safety data stream in a unified format. By integrating multi-source heterogeneous data through spatiotemporal alignment and standardization, the consistency and timeliness of data in the subsequent risk assessment process can be ensured, and the real-time response capability and accuracy of the early warning system to the construction site status can be improved.
[0021] S14 specifically includes: S141: Based on the established Coordinated Universal Time (UTC) format and GNSS geographic reference coordinate system, the time stamps and spatial locations in various data streams are uniformly converted, the original timestamps are standardized to UTC time format, and the original coordinates are projected onto the unified spatial reference system to form a unified spatiotemporal reference. S142: Convert data values from different sources into dimensionless standard values, and use a linear normalization method to compress the original data to the [0,1] interval, unifying the numerical scale of various data types. The conversion formula is as follows: ,in, The original data values, and These are the minimum and maximum values for this type of data, respectively. These are the normalized standard values; S143: For data streams with different sampling frequencies, linear interpolation is used to fill in missing data points at a set uniform time interval, so that all data streams have a consistent time step. The interpolation formula is: ,in, The estimated value of the interpolation point. Valid data values at both ends of the interpolation interval For the time to be interpolated, The timestamps corresponding to the data values at both ends; S144: Perform outlier detection on the normalized data. Use the Z-score method to identify data points with excessive deviations and determine if they are outliers. If the outlier criteria are met, replace them with the mean of the adjacent valid values. The determination formula is as follows: ,in, These are the original data values before normalization; This is the mean of this type of data; This represents the standard deviation of this type of data; The Z-score corresponding to the current data point; if ,in If so, it is considered abnormal; S145: All data that has undergone spatiotemporal alignment, numerical normalization, frequency unification, and anomaly handling are structurally integrated to form a standardized security data stream, which is then output for use in subsequent risk parameter extraction steps. Through the above steps, the standardized fusion of multi-source heterogeneous data in spatiotemporal dimensions and numerical characteristics can be achieved, ensuring that the data input has structural consistency and logical continuity before risk assessment, thereby improving the accuracy of subsequent risk determination and system response efficiency.
[0022] S2: Extract several risk parameters that match the current construction phase from the standardized safety data stream, including personnel density, stability coefficient of large machinery operation, and comprehensive environmental risk index; S2 specifically includes: S21: Based on personnel location information in the standardized safety data stream, and combined with the current construction phase's work area, count the number of personnel per unit area and calculate personnel density. This is used to reflect the distribution of people in a local space; the formula is: ,in, This represents the total number of people in the construction area at the current moment. This represents the area of the current construction zone. S22: Based on the mechanical state data in the standardized safety data stream, extract the rate of change of operating posture and the rate of change of load for each large piece of machinery. Calculate the operational stability level using the volatility coefficient to obtain the operational stability coefficient of the large machinery. The formula is: ,in, This is the operational stability coefficient; This represents the magnitude of the attitude angle change. This represents the maximum permissible value for the attitude angle; This represents the magnitude of load variation. This represents the maximum allowable load value. S23: Based on standardized environmental monitoring data, extract environmental factors such as temperature, wind speed, and concentration of harmful gases, calculate the risk score for each factor, and generate a comprehensive environmental risk index according to preset weights. The formula is: ,in, It is a comprehensive environmental risk index; For the first Risk scores for each environmental factor; For the first The weights of each environmental factor; The total number of environmental factors; the above steps, through the joint extraction of personnel density, mechanical stability and comprehensive environmental index, can achieve a quantitative description of key risk parameters at the construction site, and improve the accuracy of input to the subsequent risk assessment model and the pertinence of the judgment basis.
[0023] S3: Based on the current construction stage type and comprehensive environmental risk index, the pre-set basic risk threshold is dynamically corrected to generate a dynamic risk threshold; S3 specifically includes: S31: Based on the current construction stage type at the construction site, retrieve the corresponding basic risk level coefficient from the preset construction stage risk level mapping table as the initial reference parameter for the correction factor. The construction stages include foundation excavation, tower foundation pouring, component hoisting, line erection, and acceptance re-measurement. Table 1 Risk Level Mapping Table for Construction Stage Table 1 establishes a mapping between the current construction stage and the corresponding basic risk level coefficient; the larger the coefficient, the greater the difficulty of the operation and the lower the safety tolerance, and the more stringent risk judgment benchmark needs to be set; the coefficient value can be set based on historical safety accident statistics or industry safety management experience.
[0024] S32: Based on the comprehensive environmental risk index calculated in S2, find the corresponding environmental sensitivity coefficient in the preset environmental risk impact interval table. This coefficient is used to reflect the amplification effect of the current environmental state on construction risks. Table 2 Environmental Risk Impact Range Table Table 2 above is used to map the comprehensive environmental risk index calculated in S2 to the corresponding environmental sensitivity coefficient; the environmental sensitivity coefficient value is used to represent the amplification effect of environmental factors on safety risks in the process of risk level correction; when the comprehensive environmental risk index is higher, it indicates that the environment is more severe and the system should improve its response sensitivity to safety events.
[0025] S33: Based on the coupling relationship between the risk level coefficient and the environmental sensitivity coefficient of the construction stage, and combined with the critical operation type of the current construction task, the basic risk thresholds are weighted and corrected to form a dynamic risk threshold set for the current construction status. The above steps achieve dynamic threshold correction through the joint implementation of construction stage and environmental status, which can effectively enhance the adaptability of the early warning mechanism in the context of changing construction situations and make risk assessment more targeted and real-time.
[0026] S33 specifically includes: S331: Couple and multiply the construction stage risk level coefficient extracted in S31 with the environmental sensitivity coefficient obtained in S32 to calculate the stage-environment joint correction coefficient, which serves as the proportional factor for adjusting the basic threshold. ,in, For joint correction coefficients, This refers to the risk level coefficient during the construction phase. Environmental sensitivity coefficient; S332: Based on the critical operation types involved in the current construction task, extract the corresponding operation type weight coefficients from the preset operation weight table, and combine them with various basic risk thresholds to form the adjusted threshold weighted by operation category. Its expression is: ,in, For the first The risk threshold is dynamically adjusted. For the first The basic risk threshold corresponding to the item; For the first The weighting coefficients corresponding to the task types; Table 3 Task Weighting Table Table 3 above is used to assign different weighting factors to each risk parameter item for the critical operation types involved in the current construction task; the weighting coefficient is used to adjust the degree of influence of a certain type of operation on the overall risk threshold. The higher the coefficient, the greater the contribution of the operation to the construction safety risk.
[0027] S333: Perform the above correction operation sequentially on the basic risk thresholds corresponding to all relevant risk parameters to form a dynamic risk threshold set covering the current construction state, which is used for subsequent safety risk index determination steps. The above steps dynamically adjust the basic risk thresholds by coupling and correcting the construction stage, environmental state and task type. This not only improves the adaptability of the early warning system to complex construction scenarios, but also enhances the pertinence of risk determination results and the feasibility of engineering.
[0028] S4: Input the personnel density and the stability coefficient of large machinery operation into the preset risk assessment model to calculate the safety risk index; S4 specifically includes: S41: The population density calculated in S2 and stability coefficient of large machinery operation The data is input into the preset risk assessment model according to the set data structure format. The risk assessment model is a multi-factor risk scoring model based on linear weighting rules, which is used to comprehensively quantify the safety risk level of the construction site. S42: Based on the sensitivity weights of each risk factor defined in the model, the personnel density and operational stability coefficients are weighted and fused separately to obtain the safety risk index of the construction site at the current moment. The expression is; ,in, As a safety risk index; The risk weighting coefficient for population density; The risk weight coefficient for mechanical stability satisfies The above steps, by integrating two key indicators reflecting crowd gathering and machinery operation status into a unified risk index, not only achieve quantitative integration of different types of safety risks, but also significantly improve the sensitivity and practicality of risk assessment, providing a reliable basis for dynamic early warning.
[0029] S5: Compare the safety risk index with the dynamic risk threshold to determine the risk level and generate structured early warning information; S5 specifically includes: S51: Receive the security risk index calculated in S4 and the dynamic risk threshold set formed in S3, and retrieve the corresponding risk judgment threshold from the dynamic risk threshold set according to the parameter type corresponding to the security risk index. The retrieval steps in S51 above are as follows: Based on the composition of the safety risk index generated in S4, analyze whether the index originates from personnel density and mechanical operation stability coefficient, and determine its dominant parameter type; Based on predefined parameter-threshold label mapping rules, the dominant parameter type of the risk index is mapped to the corresponding threshold category label in the dynamic threshold set, for example: The threshold label corresponding to population density is the density category; The threshold label corresponding to mechanical stability is mechanical category; In the dynamic risk threshold set generated in S3, the risk judgment threshold range corresponding to the determined category label is retrieved and used as a benchmark for comparison with the risk index.
[0030] S52: Compare the safety risk index with the corresponding dynamic risk threshold, and determine the risk level of the current state of the construction site based on the comparison results. The risk levels include low risk, controllable risk, risk of concern, and high risk. Each risk level corresponds to a threshold range. S53: Based on the determined risk level, generate structured early warning information, including risk level label, trigger parameter category, safety risk index value, corresponding dynamic threshold and judgment timestamp; the above steps, by mapping the risk index to the dynamic threshold and forming a structured early warning output, can not only realize the real-time classification and judgment of complex construction conditions, but also improve the interpretability of early warning information and the communication between systems, providing an executable data foundation for risk intervention and control.
[0031] S52 specifically includes: S521: Receive the dynamic risk assessment threshold range retrieved in S51, and obtain the corresponding security risk index at the current moment. Confirm their positional relationship within the threshold range; S522: Security Risk Index The risk level of the current construction site is determined by comparing the value with the dynamic risk threshold range and determining the risk level corresponding to the current state of the construction site based on the range in which it falls. Specifically, when... When, it is judged as low risk; when The risk was determined to be controllable; when When, it is judged as a risk to be concerned; when It was determined to be high-risk; among them, The upper limit threshold is set for low risk. This is the upper limit threshold for controllable risk; This serves as both the upper limit and lower limit for assessing risk; S523: Based on the judgment result of S522, output the risk level label corresponding to the current moment of the construction site; the above steps, by accurately mapping the safety risk index with the multi-level dynamic threshold range, can realize the quantitative classification and judgment of the construction risk level, avoid the difference of human subjective judgment, and improve the system's risk perception capability and response decision accuracy in complex environments.
[0032] S6: Visualize the structured early warning information and push it to the administrator's terminal; S6 specifically includes: S61: The structured early warning information generated in S5 is graphically processed according to the set visualization template. The visualization template includes risk level color indicators, parameter comparison bar charts, dynamic threshold trend charts, and early warning timestamp fields. S62: The visualized early warning information is pushed to the authorized management personnel's terminals using a message push protocol, including mobile applications, main control screens, and tablet devices. During the push process, communication mechanisms based on local area networks or public networks are supported to ensure that the early warning information is delivered to the target terminal in a short time. By graphically displaying the early warning information and pushing it to the management terminal, the above steps enable intuitive perception and rapid response to safety risks at the construction site, which helps to improve the judgment efficiency and decision-making accuracy of management personnel.
[0033] This invention encompasses any substitutions, modifications, equivalent methods, and solutions made within the spirit and scope of this invention. To provide the public with a thorough understanding of this invention, specific details are described in detail in the following preferred embodiments; however, those skilled in the art will fully understand the invention even without these details. Furthermore, to avoid unnecessary misunderstanding of the essence of this invention, well-known methods, processes, procedures, components, and circuits are not described in detail.
[0034] The above description is only a preferred embodiment of the present invention. It should be noted that for those skilled in the art, several improvements and modifications can be made without departing from the principle of the present invention, and these improvements and modifications should also be considered within the scope of protection of the present invention.
Claims
1. A digital construction safety risk early warning method for ultra-high voltage power transmission projects based on artificial intelligence, characterized in that, Includes the following steps: S1: Real-time acquisition of multi-source safety data from the UHV construction site, including personnel positioning data, mechanical equipment working status data, and environmental monitoring sensor data, and spatiotemporal alignment and standardization processing to generate a standardized safety data stream; S2: Extract several risk parameters that match the current construction phase from the standardized safety data stream, including personnel density, stability coefficient of large machinery operation, and comprehensive environmental risk index; S3: Based on the current construction stage type and comprehensive environmental risk index, the pre-set basic risk threshold is dynamically corrected to generate a dynamic risk threshold; S4: Input the personnel density and the stability coefficient of large machinery operation into the preset risk assessment model to calculate the safety risk index; S5: Compare the safety risk index with the dynamic risk threshold to determine the risk level and generate structured early warning information; S6: Visualize the structured early warning information and push it to the administrator's terminal.
2. The method for early warning of digital construction safety risks in ultra-high voltage power transmission projects based on artificial intelligence, as described in claim 1, is characterized in that... S1 specifically includes: S11: By deploying positioning base stations and wearable tags in the construction area, the spatial coordinate information of each construction worker is obtained in real time, forming a personnel positioning data stream; S12: Based on the status acquisition module installed on large construction machinery, it collects the machinery's operating mode, attitude changes and load parameters to form a data stream of the machinery's working status; S13: Collect data on temperature, humidity, wind speed and harmful gas concentration at the construction site through an environmental monitoring sensor network to form an environmental monitoring data stream; S14: The various types of data acquired from S11 to S13 are spatiotemporally aligned according to a unified timestamp and coordinate system, and the numerical types, sampling frequencies and outliers are standardized to generate a standardized secure data stream in a unified format.
3. The method for early warning of digital construction safety risks in ultra-high voltage power transmission projects based on artificial intelligence, as described in claim 2, is characterized in that... S14 specifically includes: S141: Based on the established unified and coordinated world time format and GNSS geographic reference coordinate system, the time labels and spatial locations in various data streams are uniformly converted to form a unified spatiotemporal reference. S142: Convert data values from different sources into dimensionless standard values, and use linear normalization to compress the original data to the [0,1] interval to unify the numerical scale of various types of data; S143: For data streams with different sampling frequencies, linear interpolation is used to fill in missing data points at a set uniform time interval, so that all data streams have a consistent time step. S144: Perform outlier detection on the normalized data. Use the Z-score method to identify data points with excessive deviation and determine whether they are outliers. If the outlier condition is met, replace them with the mean of the adjacent valid values. S145: All data that has undergone spatiotemporal alignment, numerical normalization, frequency unification, and anomaly handling are structurally integrated to form a standardized secure data stream.
4. The method for early warning of digital construction safety risks in ultra-high voltage power transmission projects based on artificial intelligence, as described in claim 1, is characterized in that... S2 specifically includes: S21: Based on personnel location information in the standardized safety data stream, and combined with the current construction phase's work area, count the number of personnel per unit area and calculate personnel density. ; S22: Based on the mechanical state data in the standardized safety data stream, extract the rate of change of operating posture and the rate of change of load for each large piece of machinery. Calculate the operational stability level using the volatility coefficient to obtain the operational stability coefficient of the large machinery. ; S23: Based on standardized environmental monitoring data, extract environmental factors such as temperature, wind speed, and concentration of harmful gases, calculate the risk score for each factor, and generate a comprehensive environmental risk index according to preset weights. .
5. The method for early warning of digital construction safety risks in ultra-high voltage power transmission projects based on artificial intelligence, as described in claim 1, is characterized in that... S3 specifically includes: S31: Based on the current construction stage type at the construction site, retrieve the corresponding basic risk level coefficient from the preset construction stage risk level mapping table as the initial reference parameter for the correction factor. The construction stage includes foundation excavation, tower foundation pouring, component hoisting, line erection, and acceptance retesting. S32: Based on the comprehensive environmental risk index calculated in S2, find its corresponding environmental sensitivity coefficient in the preset environmental risk impact interval table; S33: Based on the coupling relationship between the risk level coefficient and the environmental sensitivity coefficient during the construction phase, and combined with the critical operation type of the current construction task, the basic risk thresholds are weighted and corrected to form a dynamic risk threshold set oriented towards the current construction status.
6. The method for early warning of digital construction safety risks in ultra-high voltage power transmission projects based on artificial intelligence, as described in claim 5, is characterized in that... Specifically, S33 includes: S331: Couple and multiply the construction stage risk level coefficient extracted in S31 with the environmental sensitivity coefficient obtained in S32 to calculate the stage-environment joint correction coefficient. S332: Based on the critical operation types involved in the current construction task, extract the corresponding operation type weight coefficients from the preset operation weight table, and combine them with various basic risk thresholds to form the adjusted threshold weighted by operation category. ; S333: Perform the above correction operation sequentially on the basic risk thresholds corresponding to all relevant risk parameters to finally form a dynamic risk threshold set covering the current construction status.
7. The method for early warning of digital construction safety risks in ultra-high voltage projects based on artificial intelligence, as described in claim 4, is characterized in that... S4 specifically includes: S41: The population density calculated in S2 and stability coefficient of large machinery operation Input into the pre-set risk assessment model; S42: Based on the sensitivity weights of each risk factor defined in the model, the personnel density and operational stability coefficients are weighted and fused separately to obtain the safety risk index of the construction site at the current moment. The expression is; ,in, As a safety risk index; The risk weighting coefficient for population density; This represents the risk weighting coefficient for mechanical stability.
8. The method for early warning of digital construction safety risks in ultra-high voltage projects based on artificial intelligence, as described in claim 7, is characterized in that... S5 specifically includes: S51: Receive the security risk index calculated in S4 and the dynamic risk threshold set formed in S3, and retrieve the corresponding risk judgment threshold from the dynamic risk threshold set according to the parameter type corresponding to the security risk index. S52: Compare the safety risk index with the corresponding dynamic risk threshold, and determine the risk level of the current state of the construction site based on the comparison results; S53: Based on the determined risk level, generate structured early warning information, including risk level label, trigger parameter category, safety risk index value, corresponding dynamic threshold and determination timestamp.
9. A method for early warning of digital construction safety risks in ultra-high voltage power transmission projects based on artificial intelligence, as described in claim 8, is characterized in that... S52 specifically includes: S521: Receive the dynamic risk assessment threshold range retrieved in S51, and obtain the corresponding security risk index at the current moment. ; S522: Security Risk Index The risk level of the current construction site is determined by comparing the value with the dynamic risk threshold range and determining the risk level corresponding to the current state of the construction site based on the range in which it falls. Specifically, when... When, it is judged as low risk; when The risk was determined to be controllable; when When, it is judged as a risk to be concerned; when It was determined to be high-risk; among them, The upper limit threshold for low risk; This is the upper limit threshold for controllable risk; To focus on the upper limit threshold of risk; S523: Based on the judgment result of S522, output the risk level label corresponding to the current moment of the construction site.
10. A method for early warning of safety risks in digital construction of ultra-high voltage power transmission projects based on artificial intelligence, as described in claim 1, is characterized in that... S6 specifically includes: S61: The structured early warning information generated in S5 is graphically processed according to the set visualization template, which includes risk level color indicators, parameter comparison bar charts, dynamic threshold trend charts, and early warning timestamp fields. S62: The visualized warning information is pushed to the authorized management personnel terminal using a message push protocol.