Electric power infrastructure project multi-dimensional safety monitoring and early warning system based on multi-factor algorithm

Abstract

The invention relates to the technical field of electric power infrastructure safety monitoring, and particularly discloses an electric power infrastructure project multi-dimensional safety monitoring and early warning system based on a multi-factor algorithm. The system is provided with a historical monitoring data analysis module, a topographic feature signal acquisition module, a meteorological feature signal acquisition module, an operator feature signal acquisition module and a multi-dimensional safety monitoring qualification judgment module. The method solves the problems that a conventional multi-factor algorithm model generally adopts a static modeling method, parameters cannot be adjusted according to environmental changes and construction stages, and the adaptability of the model is insufficient due to lack of intelligent and adaptive capabilities, and is beneficial to identifying complex risks generated by superposition of factors. The potential problem neglected due to single-dimensional monitoring is avoided, dynamic safety monitoring judgment can be carried out in the construction process, and the safety of the construction process is kept under the dynamic condition.

Description

Technical Field

[0001] The present invention relates to the technical field of power infrastructure safety monitoring, and in particular to a multi-dimensional safety monitoring and early warning system for power infrastructure projects based on a multi-factor algorithm. Background Art

[0002] Power infrastructure projects usually include the construction of large facilities such as transmission lines and substations. The environment of such projects is complex. The construction sites are usually located at high altitudes and across a variety of geological conditions, accompanied by potential risks such as high-altitude operations and heavy machinery operations. It is crucial to ensure the safety of project construction. Traditional monitoring methods are difficult to provide real-time and accurate safety data in complex environments. The safety of power infrastructure projects is affected by many factors, such as geological conditions, meteorological changes, equipment status, and construction personnel behavior. These factors interact with each other, and a multi-factor algorithm is needed to comprehensively evaluate various factors and identify potential risk sources, thereby improving the accuracy and effectiveness of the monitoring system. The safety management of power infrastructure projects requires a rapid response to any potential risks, which requires real-time data monitoring and analysis. Multi-dimensional data can provide more comprehensive safety information for projects. Researching a system that can integrate multi-source heterogeneous data and has real-time processing capabilities is an important means to ensure safety.

[0003] Nowadays, there are still some deficiencies in the research on multi-dimensional safety monitoring and early warning of power infrastructure projects based on multi-factor algorithms. Specifically, the data source of traditional monitoring systems is usually relatively single, lacking the ability to comprehensively collect and integrate multi-dimensional data. A single data source often cannot fully reflect the complexity of safety risks, resulting in insufficient effectiveness and reliability of the monitoring system. Traditional multi-factor algorithm models generally adopt static modeling methods, which cannot adjust parameters according to environmental changes and construction stages, lack intelligence and adaptive capabilities, and lead to insufficient applicability of the model. At the complex and changeable power infrastructure project site, static models are difficult to dynamically reflect the real-time risk level, often resulting in false alarms and missed reports, and lack of accurate risk prediction capabilities. Summary of the invention

[0004] In view of the deficiencies in the prior art, the present invention provides a multi-dimensional safety monitoring and early warning system for power infrastructure projects based on a multi-factor algorithm, which can effectively solve the problems involved in the above-mentioned background technology.

[0005] To achieve the above objectives, the present invention is implemented through the following technical solutions: a multi-dimensional safety monitoring and early warning system for power infrastructure projects based on a multi-factor algorithm, including a historical monitoring data analysis module, a terrain feature signal acquisition module, a meteorological feature signal acquisition module, an operator feature signal acquisition module and a multi-dimensional safety monitoring qualification judgment module, wherein: the historical monitoring data analysis module acquires the historical monitoring data of the power infrastructure project, and determines the multi-dimensional safety monitoring weight setting data set and the multi-dimensional safety monitoring threshold of the power infrastructure project based on the acquired historical monitoring data of the power infrastructure project; the terrain feature signal acquisition module analyzes the terrain features of the power infrastructure project to obtain a terrain feature signal; the meteorological feature signal acquisition module The module analyzes the meteorological characteristics of the power infrastructure project to obtain meteorological characteristic signals; the operator characteristic signal acquisition module analyzes the characteristics of the operators of the power infrastructure project to obtain operator characteristic signals; the multi-dimensional safety monitoring qualified judgment module sets the data set and the multi-dimensional safety monitoring threshold of the power infrastructure project based on the multi-dimensional safety monitoring weight of the power infrastructure project, and combines the terrain characteristic signals, meteorological characteristic signals and operator characteristic signals to judge whether the multi-dimensional safety monitoring of the power infrastructure project is qualified: if the multi-dimensional safety monitoring of the power infrastructure project is qualified, the power infrastructure project will continue to be implemented; if the multi-dimensional safety monitoring of the power infrastructure project is unqualified, a safety warning will be issued to the power infrastructure project and the unqualified level of the power infrastructure project will be determined.

[0006] As a further solution, the historical monitoring data of power infrastructure projects includes the historical frequency of abnormal meteorological conditions, the historical frequency of abnormal operating personnel behavior, and the historical frequency of abnormal operating equipment operation status.

[0007] As a further solution, a multi-dimensional safety monitoring weight setting data set and a multi-dimensional safety monitoring threshold for power infrastructure projects are determined. The specific analysis process is: based on the acquired historical monitoring data of power infrastructure projects, a comprehensive analysis is performed to obtain the historical monitoring constraint factors of power infrastructure projects, and the historical monitoring constraint factors of power infrastructure projects are used as the analysis basis for determining the multi-dimensional safety monitoring weight setting data set and the multi-dimensional safety monitoring threshold for power infrastructure projects; the historical monitoring constraint factors of power infrastructure projects are stored as designated tags, and the designated tags are compared with each set tag stored in the database to obtain the set tag corresponding to the designated tag, and the multi-dimensional safety monitoring weight setting data set of power infrastructure projects corresponding to the set tag stored in the database and the multi-dimensional safety monitoring threshold for power infrastructure projects corresponding to the set tag are obtained; the multi-dimensional safety monitoring weight setting data set for power infrastructure projects specifically includes terrain feature signal weight factors, meteorological feature signal weight factors and operator feature signal weight factors.

[0008] As a further solution, the historical monitoring constraint factors of power infrastructure projects are analyzed as follows:

[0009]

[0010] Where δ is the historical monitoring constraint factor of the power infrastructure project, qx is the historical abnormal frequency of meteorological conditions, xw is the historical abnormal frequency of the behavior of operators, sb is the historical abnormal frequency of the operating equipment operation status, μ1 is the compensation factor of the set qx, μ2 is the compensation factor of the set xw, μ3 is the compensation factor of the set sb, and e is a natural constant.

[0011] As a further solution, the terrain characteristics of the power infrastructure project are analyzed. The specific analysis process is: obtaining terrain characteristic data of the power infrastructure project, the terrain characteristic data of the power infrastructure project specifically includes the ground slope angle of the power infrastructure project, the rock joint density of the power infrastructure project, and the ground soil density of the power infrastructure project; based on the acquired terrain characteristic data of the power infrastructure project, a comprehensive analysis is performed to obtain a terrain characteristic signal, and the terrain characteristic signal is used as an analysis basis for judging whether the multi-dimensional safety monitoring of the power infrastructure project is qualified.

[0012] As a further solution, the meteorological characteristics of the power infrastructure projects are analyzed. The specific analysis process is: obtaining meteorological characteristic data of the power infrastructure projects, which specifically include environmental precipitation of the power infrastructure projects, environmental wind speed of the power infrastructure projects, and environmental light intensity deviation rate of the power infrastructure projects; based on the acquired meteorological characteristic data of the power infrastructure projects, a comprehensive analysis is performed to obtain meteorological characteristic signals, which are used as the analysis basis for judging whether the multi-dimensional safety monitoring of the power infrastructure projects is qualified.

[0013] As a further solution, the characteristics of the operators in the power infrastructure projects are analyzed. The specific analysis process is: obtaining the characteristic data of the operators in the power infrastructure projects, which specifically include the blood oxygen saturation of the operators, the body inclination angle of the operators, and the success rate of the facial recognition verification of the operators; based on the obtained characteristic data of the operators in the power infrastructure projects, a comprehensive analysis is performed to obtain the characteristic signals of the operators, and the characteristic signals of the operators are used as the analysis basis for judging whether the multi-dimensional safety monitoring of the power infrastructure projects is qualified.

[0014] As a further solution, it is determined whether the multi-dimensional safety monitoring of power infrastructure projects is qualified. The specific analysis process is as follows: the terrain feature signal weight factor, the meteorological feature signal weight factor and the operator feature signal weight factor are introduced into the multi-dimensional safety monitoring model of power infrastructure projects together with the terrain feature signal, the meteorological feature signal and the operator feature signal to calculate the multi-dimensional safety monitoring factor, which is used as the analysis basis for determining whether the multi-dimensional safety monitoring of power infrastructure projects is qualified; the multi-dimensional safety monitoring factor is compared with the multi-dimensional safety monitoring threshold of the power infrastructure project; if the multi-dimensional safety monitoring factor is not lower than the multi-dimensional safety monitoring threshold of the power infrastructure project, the multi-dimensional safety monitoring of the power infrastructure project corresponding to the multi-dimensional safety monitoring factor is qualified, and the power infrastructure project is continued to be implemented; if the multi-dimensional safety monitoring factor is lower than the multi-dimensional safety monitoring threshold of the power infrastructure project, the multi-dimensional safety monitoring of the power infrastructure project corresponding to the multi-dimensional safety monitoring factor is unqualified, a safety warning is issued for the power infrastructure project, and the unqualified level of the power infrastructure project is determined.

[0015] As a further solution, a multi-dimensional safety monitoring model for power infrastructure projects is proposed. The specific analysis process is as follows:

[0016]

[0017] Where ω is the multi-dimensional safety monitoring factor, α is the terrain characteristic signal, β is the meteorological characteristic signal, γ is the operator characteristic signal, θ1 is the terrain characteristic signal weight factor, θ2 is the meteorological characteristic signal weight factor, θ3 is the operator characteristic signal weight factor, and e is a natural constant.

[0018] As a further solution, the unqualified level of the power infrastructure project is determined. The specific analysis process is: the difference between the multidimensional safety monitoring threshold and the multidimensional safety monitoring factor of the power infrastructure project is recorded as the multidimensional safety monitoring deviation value; the multidimensional safety monitoring deviation value is compared with the multidimensional safety monitoring reference deviation range stored in the database; if the multidimensional safety monitoring deviation value falls within the multidimensional safety monitoring reference deviation range, the unqualified level of the power infrastructure project corresponding to the multidimensional safety monitoring deviation value is level two; if the multidimensional safety monitoring deviation value does not fall within the multidimensional safety monitoring reference deviation range, and the multidimensional safety monitoring deviation value is less than the minimum value in the multidimensional safety monitoring reference deviation range, the unqualified level of the power infrastructure project corresponding to the multidimensional safety monitoring deviation value is level three; if the multidimensional safety monitoring deviation value does not fall within the multidimensional safety monitoring reference deviation range, and the multidimensional safety monitoring deviation value is greater than the maximum value in the multidimensional safety monitoring reference deviation range, the unqualified level of the power infrastructure project corresponding to the multidimensional safety monitoring deviation value is level one.

[0019] Compared with the prior art, the embodiments of the present invention have at least the following advantages or beneficial effects:

[0020] (1) The present invention provides a multi-dimensional safety monitoring and early warning system for power infrastructure projects based on a multi-factor algorithm, and sets adaptive monitoring weights and thresholds based on historical monitoring data. The refined adjustment of data weights and thresholds enables the system to accurately identify potential risks, reduce false alarms and missed alarms, and improve the reliability of the monitoring system. The collection and analysis of characteristic signals from multiple aspects such as terrain, weather, and operating personnel can help identify complex risks caused by the superposition of various factors and avoid ignoring potential problems due to single-dimensional monitoring. The real-time judgment mechanism for qualified and unqualified can perform dynamic safety monitoring and judgment during the construction process. This flexible monitoring mechanism helps to maintain the safety of the construction process under dynamic conditions.

[0021] (2) The present invention obtains historical monitoring data of power infrastructure projects to determine a data set for setting weights for multi-dimensional safety monitoring of power infrastructure projects and thresholds for multi-dimensional safety monitoring of power infrastructure projects. The historical monitoring data can reflect the actual safety status of the project under different environments and construction conditions. The system can set weights for safety monitoring in different dimensions (such as terrain, weather, personnel, etc.) in a targeted manner. The customized weight setting based on historical data allows the system to accurately evaluate the impact of each factor on overall safety, thereby improving the accuracy and effectiveness of monitoring. Dynamic threshold setting can ensure that the system can provide appropriate monitoring and early warning under different environmental conditions. By using historical data to set thresholds and weights, it is possible to adjust monitoring standards based on the actual risk characteristics of the project, thereby reducing invalid alarms, ensuring the effectiveness of alarms, and improving the credibility and reliability of the system. BRIEF DESCRIPTION OF THE DRAWINGS

[0022] The present invention is further described using the accompanying drawings, but the embodiments in the accompanying drawings do not constitute any limitation to the present invention. A person skilled in the art can obtain other drawings based on the following drawings without creative work.

[0023] Figure 1 It is a schematic diagram of system module connection of the present invention.

[0024] Figure 2 A flowchart of the steps for determining whether the multi-dimensional safety monitoring of power infrastructure projects is qualified. DETAILED DESCRIPTION

[0025] The technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, rather than all the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of the present invention.

[0026] See also Figure 1 The embodiment of the present invention provides a technical solution for multi-dimensional safety monitoring and early warning of power infrastructure projects based on a multi-factor algorithm: a multi-dimensional safety monitoring and early warning system for power infrastructure projects based on a multi-factor algorithm, including a historical monitoring data analysis module, a terrain feature signal acquisition module, a meteorological feature signal acquisition module, an operating personnel feature signal acquisition module and a multi-dimensional safety monitoring qualified judgment module.

[0027] The historical monitoring data analysis module obtains the historical monitoring data of the power infrastructure project, and determines the multi-dimensional safety monitoring weight setting data set and the multi-dimensional safety monitoring threshold of the power infrastructure project based on the acquired historical monitoring data of the power infrastructure project.

[0028] Specifically, the historical monitoring data of power infrastructure projects include the historical frequency of abnormal meteorological conditions, the historical frequency of abnormal operating personnel behavior status, and the historical frequency of abnormal operating equipment operation status.

[0029] The frequency of historical abnormal weather conditions refers to the frequency of adverse weather conditions (such as storms, strong winds, high temperatures, extreme low temperatures, etc.) in the project area in the past year or the past quarter. The frequency of historical abnormal behavior of operators refers to the frequency of abnormal behavior of operators (for example, excessive fatigue, failure to wear safety equipment, dangerous postures or irregular operations, etc.) in the past month or year. The frequency of historical abnormal operation of equipment refers to the frequency of abnormal equipment status or failures, abnormal shutdowns, excessive operating temperatures, abnormal current or vibration, etc., of equipment used in the project (such as cranes, hoists, generators, etc.) in the past month or year.

[0030] Frequent abnormal weather conditions (such as frequent extreme weather such as storms, strong winds, and high temperatures) usually increase the frequency of abnormal behavior of personnel. In high or low temperature environments, operators are more likely to become fatigued and have reduced judgment, which affects the safety performance of operators. Frequent abnormal weather conditions can also have an adverse effect on the operating status of equipment. Storms or strong winds may also affect the stability of equipment, such as causing the crane to tilt and equipment parts to become damp, thereby increasing the frequency of abnormal equipment conditions.

[0031] Based on the acquired historical monitoring data of power infrastructure projects, a comprehensive analysis is performed to obtain the historical monitoring constraint factors of power infrastructure projects, and the historical monitoring constraint factors of power infrastructure projects are used as the analysis basis for determining the multi-dimensional safety monitoring weight setting data set and the multi-dimensional safety monitoring threshold of power infrastructure projects; the historical monitoring constraint factors of power infrastructure projects are stored as designated tags, and the designated tags are compared with the set tags stored in the database to obtain the set tags corresponding to the designated tags, and the multi-dimensional safety monitoring weight setting data set of power infrastructure projects corresponding to the set tags stored in the database and the multi-dimensional safety monitoring threshold of power infrastructure projects corresponding to the set tags are obtained; the multi-dimensional safety monitoring weight setting data set of power infrastructure projects specifically includes terrain feature signal weight factors, meteorological feature signal weight factors and operator feature signal weight factors.

[0032] Constraint factors generated based on historical monitoring data can accurately reflect the environmental, meteorological and operating conditions of specific power infrastructure projects. By matching the corresponding set tags, the specific safety monitoring weights and thresholds of the project can be automatically extracted, thereby improving the accuracy of monitoring. By automatically comparing the specified tags with the set tags in the database, the system can quickly determine the appropriate monitoring weights and thresholds, reducing the need for manual settings and adjustments, and greatly improving the efficiency and flexibility of the monitoring system.

[0033] The multi-dimensional safety monitoring weight setting data set includes terrain feature signal weight factors, meteorological feature signal weight factors, and operator feature signal weight factors, which can comprehensively consider various potential safety influencing factors to ensure the comprehensiveness of monitoring. Under different environmental conditions, different factors have different impacts on the overall risk. This dynamic adjustment mechanism enables the monitoring system to be highly sensitive to the changing construction environment, improves the sensitivity and timeliness of risk identification, and prevents missed reports and false reports.

[0034] Specifically, the historical monitoring constraint factors of power infrastructure projects, the specific analysis process is as follows:

[0035]

[0036] Where δ is the historical monitoring constraint factor of the power infrastructure project, qx is the historical abnormal frequency of meteorological conditions, xw is the historical abnormal frequency of the behavior of operators, sb is the historical abnormal frequency of the operating equipment operation status, μ1 is the compensation factor of the set qx, μ2 is the compensation factor of the set xw, μ3 is the compensation factor of the set sb, and e is a natural constant.

[0037] It should be explained that the above-mentioned historical monitoring constraint factors of power infrastructure projects are calculated through the abnormal frequency of historical meteorological conditions, the abnormal frequency of historical operating personnel behavior, and the abnormal frequency of historical operating equipment operation status. After normalization of qx, xw, and sb, the historical monitoring constraint factors can identify and predict high-risk situations that may occur in the future by comprehensively analyzing the abnormal frequencies of meteorology, personnel behavior, and equipment status. For example, if historical data shows that the frequency of abnormal equipment and personnel behavior is high under specific meteorological conditions, their weights can be increased to reduce the possibility of accidents.

[0038] Historical monitoring constraint factors are derived from real historical data and can provide a scientific basis for safety management. Compared with single empirical judgment, this data-driven monitoring method is more objective, can formulate safety strategies more scientifically, reduce subjective judgment errors, and improve management accuracy. Historical monitoring constraint factors help projects identify risk points of different frequencies, so as to adjust safety monitoring thresholds more flexibly.

[0039] It should be explained that the compensation factors of qx, xw, and sb set above are obtained from the database. According to the historical data, a mapping set of the historical measured abnormal frequency of meteorological conditions, the historical abnormal frequency of operating personnel behavior status, the historical abnormal frequency of operating equipment operation status and the compensation factors of qx, xw, and sb is established to obtain the compensation factors of qx, xw, and sb corresponding to the current qx, xw, and sb.

[0040] It should be noted that σ1, σ2, σ3, τ1, τ2, τ3, ε1, ε2, and ε3 mentioned below are also obtained through a mapping set of historical data and compensation factors established in a database, that is, the corresponding compensation factors are obtained based on current data.

[0041] The terrain feature signal acquisition module analyzes the terrain features of the power infrastructure project and obtains terrain feature signals.

[0042] The specific analysis process is: obtaining terrain characteristic data of power infrastructure projects, which specifically include the ground slope angle of power infrastructure projects, the rock joint density of power infrastructure projects, and the ground soil density of power infrastructure projects; based on the acquired terrain characteristic data of power infrastructure projects, comprehensive analysis is performed to obtain terrain characteristic signals, which are used as the analysis basis for judging whether the multi-dimensional safety monitoring of power infrastructure projects is qualified.

[0043] The ground slope angle is the angle between the ground surface and the horizontal plane, usually expressed in degrees. The larger the slope angle, the higher the inclination of the ground, and the greater the risk of landslides or soil instability. The rock joint density refers to the number of cracks or joints in the rock per unit area. The higher the joint density, the looser the structure of the rock mass, the lower the stability, and the bearing capacity may also decrease. Soil density is the mass of soil per unit volume, usually expressed in grams per cubic centimeter or kilograms per cubic meter. A higher soil density usually means that the soil is more compact and has a stronger bearing capacity, making it suitable as a building foundation; while a lower density soil may have insufficient bearing capacity and easily cause problems such as foundation settlement and landslides.

[0044] When the ground slope angle is large, the rock and soil layers face a higher risk of slippage and instability, especially in places with steeper slopes. Rock structures with high rock joint density may exacerbate this instability. The more joints there are in the rock layer, the lower the overall strength of the rock mass, the looser the structure, and the more likely it is to slip or collapse along the joint surface. The ground slope angle and soil density directly affect the stability of the foundation. A larger slope angle will cause the soil to be subjected to greater gravity and shear force, and low-density soil is prone to slip or settlement under such conditions. In areas with high slope angles, low-density soil is easily washed away or slides, affecting the stability of the slope. Topographic feature signals can combine these factors to provide an assessment of foundation stability and ensure that the project is built on a reliable foundation.

[0045] The terrain feature signals generated based on data can reduce the reliance on subjective judgment of terrain conditions, and make the monitoring process more accurate through data-driven analysis. Automated terrain signal analysis enables the system to make judgments based on real data, avoiding errors or oversights in manual judgment.

[0046] Terrain characteristic signal, the specific analysis process is as follows:

[0047]

[0048] Wherein, α is the terrain characteristic signal, pd is the ground slope angle of the power infrastructure project, jl is the rock joint density of the power infrastructure project, md is the ground soil density of the power infrastructure project, σ1 is the compensation factor of the set pd, σ2 is the compensation factor of the set jl, and σ3 is the compensation factor of the set md.

[0049] It should be explained that the above terrain characteristic signals are calculated through the ground slope angle of the power infrastructure project, the rock joint density of the power infrastructure project, and the ground soil density of the power infrastructure project. PD, JL, and MD are normalized. By integrating the ground slope angle, rock joint density, and soil density, the terrain characteristic signals can comprehensively evaluate the geological stability of the construction site. This comprehensive assessment enables the project management team to better understand the overall safety of the foundation and predict potential geological risks. The ground slope angle, joint density, and soil density affect each other, and examining a single parameter alone may not be able to fully identify risks. Through the calculation of terrain characteristic signals, the interactive effects of multidimensional geological factors can be captured.

[0050] The meteorological characteristic signal acquisition module analyzes the meteorological characteristics of the power infrastructure project and obtains the meteorological characteristic signal.

[0051] The specific analysis process is as follows: obtaining meteorological characteristic data of power infrastructure projects, which specifically include environmental precipitation of power infrastructure projects, environmental wind speed of power infrastructure projects, and environmental light intensity deviation rate of power infrastructure projects; based on the acquired meteorological characteristic data of power infrastructure projects, comprehensive analysis is performed to obtain meteorological characteristic signals, which are used as the analysis basis for judging whether the multi-dimensional safety monitoring of power infrastructure projects is qualified.

[0052] The deviation rate refers to the ratio of the absolute value of the actual value minus the reference value to the reference value. The environmental precipitation refers to the amount of water that falls on the ground within a certain period of time, usually in millimeters (mm). The amount of precipitation directly affects the wetness of the ground, the saturation state of the soil, and the load of the drainage system. Excessive precipitation may cause landslides, unstable foundations and other problems, posing a threat to the construction and safety of infrastructure projects. The environmental wind speed refers to the speed of horizontal air movement, usually expressed in meters per second (m / s) or kilometers per hour (km / h). Changes in wind speed will affect the safety of high-altitude operations. When the wind speed is too high, it may pose a threat to the balance of personnel and the stability of equipment (such as cranes, hoists, etc.). Continuous strong winds may also cause equipment vibration, shaking, etc., affecting project safety. The environmental light intensity refers to the solar radiation power received per unit area, usually expressed in watts per square meter (W / m 2 )express.

[0053] Obtaining meteorological data such as precipitation, wind speed, and light intensity can make a real-time safety assessment of the current construction environment. When the wind speed is too high, it can quickly determine whether to suspend high-altitude operations, and immediately arrange waterproofing and drainage measures when precipitation increases suddenly, thereby effectively avoiding potential risks. Comprehensive analysis of precipitation, wind speed, and light intensity can accurately reflect the impact of current meteorological conditions on construction safety. Combining multi-dimensional meteorological characteristic data can more comprehensively understand the impact of meteorology on construction. A single precipitation or wind speed may not be sufficient to fully reflect environmental risks, but by comprehensively analyzing the meteorological characteristic signals obtained from multiple meteorological data, the impact of meteorological conditions on safety can be more accurately judged, reducing false alarms and missed reports. Multi-dimensional data fusion enables the monitoring system to make a comprehensive judgment on the interaction of multiple risk sources and improve the overall safety management effect.

[0054] Meteorological characteristic signals, the specific analysis process is as follows:

[0055]

[0056] Where β is the meteorological characteristic signal, js is the environmental precipitation of the power infrastructure project, fs is the environmental wind speed of the power infrastructure project, gz is the deviation rate of the environmental light intensity of the power infrastructure project, τ1 is the compensation factor of js, τ2 is the compensation factor of fs, and τ3 is the compensation factor of gz.

[0057] It should be explained that the above-mentioned meteorological characteristic signals are calculated through the deviation rate of environmental precipitation, environmental wind speed and environmental light intensity of power infrastructure projects. js, fs and gz are normalized. Environmental precipitation, wind speed and light intensity will have different types of impacts on construction, and the comprehensive calculation of the deviation rate can summarize these multi-dimensional impacts into an overall meteorological characteristic signal. Meteorological characteristic signals can reflect the deviation of meteorological conditions in real time and provide a scientific basis for data-driven. Compared with simple empirical judgments, the deviation rate is calculated based on historical data and real-time monitoring data, which can more objectively reflect meteorological anomalies and help improve the scientificity and accuracy of decision-making.

[0058] The operator characteristic signal acquisition module analyzes the characteristics of the operators in the power infrastructure project and obtains the operator characteristic signals.

[0059] The specific analysis process is as follows: obtaining characteristic data of operators in power infrastructure projects, which specifically include operators' blood oxygen saturation, operators' body inclination angle, and operators' facial recognition verification success rate; based on the obtained characteristic data of operators in power infrastructure projects, comprehensive analysis is performed to obtain operator characteristic signals, which are used as the analysis basis for judging whether the multi-dimensional safety monitoring of power infrastructure projects is qualified.

[0060] Blood oxygen saturation refers to the saturation percentage of oxygen in the blood, usually expressed as a percentage. Normal blood oxygen saturation is generally between 95% and 100%. Below 90% may indicate a risk of hypoxia. The body tilt angle refers to the degree of inclination of the operator's body relative to the vertical direction. This indicator is used to determine whether the operator is in a stable and safe posture during the operation. A large inclination angle for workers working at heights may indicate a loss of balance or a dangerous state. The face recognition verification success rate refers to the ratio of the number of times an operator successfully passes face recognition verification to the number of attempts when entering a specific area or using specific equipment.

[0061] Blood oxygen saturation is an important indicator of whether workers have sufficient oxygen supply, especially in high-altitude operations, plateaus or confined space operations. If the blood oxygen saturation is too low, workers may experience symptoms such as dizziness, fatigue, and lack of concentration, which directly affect the body's balance and coordination. The success rate of face recognition verification can reflect the identity compliance of workers to a certain extent. If workers are not verified, unauthorized to enter high-risk areas or use specific equipment, they may lack safety training or operating experience, which increases the probability of irregular postures and abnormal tilt angles.

[0062] Real-time feedback on health status can enable the system to identify and alarm in time, ensuring that the workers are always in a healthy state and ensuring construction safety. Posture monitoring helps to improve the system's recognition sensitivity for high-risk behaviors, issue early warnings or reminders in time, ensure that personnel work in a safe state, high-risk areas or important equipment areas, ensure the correctness of personnel identities, avoid safety hazards caused by unauthorized personnel entering by mistake, and improve the compliance of overall safety management. By collecting and analyzing the physiological and behavioral data of workers, the system can automatically monitor the status of workers, reduce misjudgments and neglects that rely on manual observation, and enhance the reliability of safety monitoring. Automated personnel characteristic signal analysis can make safety judgments based on real-time and detailed data support, making the monitoring system more intelligent, reducing negligence in manual management, and improving the accuracy of the system. Reduce operational risks and improve personnel trust and work efficiency.

[0063] The specific analysis process of the operator’s characteristic signal is as follows:

[0064]

[0065] Wherein, γ is the characteristic signal of the operator, xy is the blood oxygen saturation of the operator, qx is the inclination angle of the operator's body, rl is the successful ratio of the operator's face recognition verification, ε1 is the compensation factor of the set xy, ε2 is the compensation factor of the set qx, and ε3 is the compensation factor of the set rl.

[0066] It should be explained that the above-mentioned operator characteristic signals are calculated through the operator's blood oxygen saturation, the operator's body tilt angle, and the operator's face recognition verification success rate. Xy, qx, and rl are normalized. The operator characteristic signals provide all-round monitoring of the operator by integrating three types of data: blood oxygen saturation, tilt angle, and face recognition verification. Blood oxygen saturation reflects health status, body tilt angle represents posture safety, and face recognition verification ensures the identity compliance of the operator. The comprehensive signal ensures that each key factor is taken into account, making the monitoring system more comprehensive and detailed. Real-time calculation of operator characteristic signals can quickly identify possible safety hazards. When low blood oxygen, high tilt angle, or too high a successful identity verification rate occurs, the characteristic signal will comprehensively judge the danger level and trigger an alarm. The system can more accurately identify high-risk situations, issue warnings in time, and take countermeasures.

[0067] The multi-dimensional safety monitoring qualified judgment module sets the data set and the multi-dimensional safety monitoring threshold of the power infrastructure project based on the weight of the power infrastructure project, and combines the terrain feature signals, meteorological feature signals and operator feature signals to judge whether the multi-dimensional safety monitoring of the power infrastructure project is qualified: if the multi-dimensional safety monitoring of the power infrastructure project is qualified, the power infrastructure project will continue to be implemented; if the multi-dimensional safety monitoring of the power infrastructure project is unqualified, a safety warning will be issued for the power infrastructure project and the unqualified level of the power infrastructure project will be determined.

[0068] like Figure 2 As shown in the figure, the specific analysis process is: the terrain feature signal weight factor, meteorological feature signal weight factor and operator feature signal weight factor are introduced into the multi-dimensional safety monitoring model of the power infrastructure project together with the terrain feature signal, meteorological feature signal and operator feature signal to calculate the multi-dimensional safety monitoring factor, which is used as the analysis basis for judging whether the multi-dimensional safety monitoring of the power infrastructure project is qualified; the multi-dimensional safety monitoring factor is compared with the multi-dimensional safety monitoring threshold of the power infrastructure project; if the multi-dimensional safety monitoring factor is not lower than the multi-dimensional safety monitoring threshold of the power infrastructure project, the multi-dimensional safety monitoring of the power infrastructure project corresponding to the multi-dimensional safety monitoring factor is qualified, and the power infrastructure project is continued to be implemented; if the multi-dimensional safety monitoring factor is lower than the multi-dimensional safety monitoring threshold of the power infrastructure project, the multi-dimensional safety monitoring of the power infrastructure project corresponding to the multi-dimensional safety monitoring factor is unqualified, a safety warning is issued for the power infrastructure project and the unqualified level of the power infrastructure project is determined.

[0069] The terrain, weather and personnel characteristic signals are uniformly incorporated into the multi-dimensional safety monitoring model, so that the monitoring factors comprehensively reflect the impact of various key factors on project safety. Multi-dimensional analysis avoids the limitations of single indicator monitoring and can more accurately judge the safety status in complex environments. Multi-dimensional safety monitoring factors are calculated in real time. If they are lower than the preset safety threshold, an early warning is immediately issued and the unqualified level is determined. This mechanism ensures that when the safety risk reaches the critical value, the system can respond immediately, helping project managers to take quick measures to avoid further expansion of the accident. Through the calculation results of the multi-dimensional safety monitoring factors, the system can judge the severity of the risk according to the unqualified level and take corresponding emergency measures.

[0070] Multi-dimensional safety monitoring factors are generated based on data, so that safety judgments have a scientific basis. Managers can rely on monitoring factors to make safety decisions and reduce deviations and errors caused by human judgment. Multi-dimensional safety monitoring factors can comprehensively reflect the potential risks of terrain, weather and personnel. Once the factors are close to or below the threshold, the system can issue early warnings so that managers can take precautions before the risks increase. In specific construction stages or meteorological conditions, the importance of terrain, weather and personnel characteristic signals may be different. Dynamic adjustment of weight factors can ensure that multi-dimensional safety monitoring factors adapt to the current project situation and always provide safety assessments that meet the actual situation. The adaptive capability ensures that the system can maintain efficient monitoring effects in different environments and conditions, and improves the flexibility and applicability of the monitoring system.

[0071] Furthermore, the multi-dimensional safety monitoring model of power infrastructure projects has the following specific analysis process:

[0072]

[0073] Where ω is the multi-dimensional safety monitoring factor, α is the terrain characteristic signal, β is the meteorological characteristic signal, γ is the operator characteristic signal, θ1 is the terrain characteristic signal weight factor, θ2 is the meteorological characteristic signal weight factor, and θ3 is the operator characteristic signal weight factor.

[0074] The above-mentioned multi-dimensional safety monitoring factors are calculated through terrain characteristic signals, meteorological characteristic signals and operator characteristic signals. Integrating terrain, meteorological and personnel characteristic signals into one factor can more comprehensively reflect the overall safety situation of the project site. This covers the influence of the external environment (such as terrain and weather) as well as internal factors (such as the status of operators). This multi-dimensional assessment provides management with a more complete picture of the safety situation, which helps to more accurately judge the current risk level of the project. The multi-dimensional safety monitoring factor is based on the comprehensive analysis results of data, which reduces the subjectivity and arbitrariness of human judgment in safety assessment.

[0075] The difference between the multidimensional safety monitoring threshold and the multidimensional safety monitoring factor of the power infrastructure project is recorded as the multidimensional safety monitoring deviation value; the multidimensional safety monitoring deviation value is compared with the multidimensional safety monitoring reference deviation range stored in the database; if the multidimensional safety monitoring deviation value falls within the multidimensional safety monitoring reference deviation range, the unqualified level of the power infrastructure project corresponding to the multidimensional safety monitoring deviation value is level two; if the multidimensional safety monitoring deviation value does not fall within the multidimensional safety monitoring reference deviation range, and the multidimensional safety monitoring deviation value is less than the minimum value in the multidimensional safety monitoring reference deviation range, the unqualified level of the power infrastructure project corresponding to the multidimensional safety monitoring deviation value is level three; if the multidimensional safety monitoring deviation value does not fall within the multidimensional safety monitoring reference deviation range, and the multidimensional safety monitoring deviation value is greater than the maximum value in the multidimensional safety monitoring reference deviation range, the unqualified level of the power infrastructure project corresponding to the multidimensional safety monitoring deviation value is level one.

[0076] By comparing the deviation value with the reference deviation range, the system can clearly judge the severity of the risk, thereby setting more detailed warning levels (level 1, 2, and 3) for the project to avoid excessive or insufficient alarms. The hierarchical judgment mechanism can quickly identify the severity of the deviation value and arrange corresponding response measures according to different levels. Level 1 failure can initiate mandatory measures such as emergency shutdown and reinforcement, while level 2 and 3 failures can be monitored and restricted.

[0077] The grading mechanism can take different degrees of intervention measures according to the level of deviation value, avoiding focusing all resources on low-risk issues. Using deviation values ​​and reference ranges for safety judgments enables risk assessment to be based on data analysis rather than simple manual experience judgment. This process improves the scientificity and standardization of safety management. According to the actual monitoring data of different stages or conditions, the multi-dimensional safety monitoring thresholds and reference deviation ranges can be dynamically adjusted to make safety management more flexible. The system can adjust the weights and thresholds of different signals according to the on-site environment to ensure that the graded judgments always adapt to the actual on-site situation, making the safety monitoring system more flexible and reliable.

[0078] In a specific embodiment, the historical frequency of abnormal meteorological conditions is 0.2, indicating that unfavorable meteorological conditions occur 20% of the time, the historical frequency of abnormal operator behavior is 0.1, indicating that abnormal operator behavior is monitored 10% of the time, the historical frequency of abnormal equipment operation status is 0.05, indicating that equipment operation is abnormal 5% of the time, the compensation factor of the historical frequency of abnormal meteorological conditions is 1.5, the compensation factor of the historical frequency of abnormal operator behavior status is 2.0, and the compensation factor of the historical frequency of abnormal equipment operation status is 3.0. The historical monitoring constraint factor of the power infrastructure project is calculated to be 1.86, the terrain feature signal weight factor of the power infrastructure project multi-dimensional safety monitoring weight setting data set is determined to be 0.2, the meteorological feature signal weight factor is 0.5, the operator feature signal weight factor is 0.3, and the multi-dimensional safety monitoring threshold of the power infrastructure project is 20.

[0079] The ground slope angle of the power infrastructure project is 15 degrees, the rock joint density of the power infrastructure project is 0.3, the ground soil density of the power infrastructure project is 1.7 grams per cubic meter, the compensation factor of the ground slope angle of the power infrastructure project is 0.7, the compensation factor of the rock joint density of the power infrastructure project is 1.1, and the compensation factor of the ground soil density of the power infrastructure project is 0.9. The calculated terrain characteristic signal is 0.077.

[0080] The environmental precipitation for power infrastructure projects is 120 mm per day, the environmental wind speed for power infrastructure projects is 15 meters per second, the environmental light intensity deviation rate for power infrastructure projects is 0.25, the compensation factor for environmental precipitation for power infrastructure projects is 0.8, the compensation factor for environmental wind speed for power infrastructure projects is 1.2, and the compensation factor for environmental light intensity deviation rate for power infrastructure projects is 0.5. The calculated meteorological characteristic signal is -3.08.

[0081] The operator's blood oxygen saturation is 0.98 (98%), the operator's body inclination angle is 5 degrees, the operator's face recognition verification success rate is 0.95 (95%), the compensation factor of the operator's blood oxygen saturation is 1.1, the compensation factor of the operator's body inclination angle is 0.8, and the compensation factor of the operator's face recognition verification success rate is 1.3. The operator's characteristic signal is calculated to be 4.83.

[0082] The terrain feature signal weight factor, meteorological feature signal weight factor and operator feature signal weight factor are introduced into the multidimensional safety monitoring model of power infrastructure projects together with the terrain feature signal, meteorological feature signal and operator feature signal, and the multidimensional safety monitoring factor is calculated to be 16.02, which is lower than the multidimensional safety monitoring threshold of power infrastructure projects. The multidimensional safety monitoring of the power infrastructure project corresponding to the multidimensional safety monitoring factor is unqualified, and a safety warning is issued for the power infrastructure project and the unqualified level of the power infrastructure project is determined. The difference between the multidimensional safety monitoring threshold of the power infrastructure project and the multidimensional safety monitoring factor is recorded as the multidimensional safety monitoring deviation value of 3.98, which does not fall into the multidimensional safety monitoring reference deviation range of [1, 3.5], and the multidimensional safety monitoring deviation value is greater than the maximum value in the multidimensional safety monitoring reference deviation range. The unqualified level of the power infrastructure project corresponding to the multidimensional safety monitoring deviation value is level one.

[0083] The above contents are merely examples and explanations of the structure of the present invention. The technicians in this technical field may make various modifications or additions to the specific embodiments described or replace them in a similar manner. As long as they do not deviate from the structure of the invention or exceed the scope defined by the claims, they should all fall within the protection scope of the present invention.

Claims

1. A multi-dimensional safety monitoring and early warning system for power infrastructure projects based on a multi-factor algorithm, characterized by: It includes historical monitoring data analysis module, terrain feature signal acquisition module, meteorological feature signal acquisition module, operator feature signal acquisition module and multi-dimensional safety monitoring qualification judgment module, among which: The historical monitoring data analysis module obtains the historical monitoring data of the power infrastructure project, and determines the multi-dimensional safety monitoring weight setting data set and the multi-dimensional safety monitoring threshold of the power infrastructure project based on the obtained historical monitoring data of the power infrastructure project; The terrain characteristic signal acquisition module analyzes the terrain characteristics of the power infrastructure project to obtain a terrain characteristic signal; The meteorological characteristic signal acquisition module analyzes the meteorological characteristics of the power infrastructure project to obtain the meteorological characteristic signal; The operator characteristic signal acquisition module analyzes the characteristics of the operators of the power infrastructure project to obtain the operator characteristic signals; The multi-dimensional safety monitoring qualification judgment module determines whether the multi-dimensional safety monitoring of the power infrastructure project is qualified based on the multi-dimensional safety monitoring weight setting data set and the multi-dimensional safety monitoring threshold of the power infrastructure project, and combines the terrain feature signal, the meteorological feature signal and the operator feature signal: If the multi-dimensional safety monitoring of the power infrastructure project is qualified, the power infrastructure project will continue to be implemented; If the multi-dimensional safety monitoring of the power infrastructure project fails, a safety warning will be issued for the power infrastructure project and the failure level of the power infrastructure project will be determined.

2. The multi-dimensional safety monitoring and early warning system for power infrastructure projects based on a multi-factor algorithm according to claim 1 is characterized by: The historical monitoring data of the power infrastructure project specifically includes the historical frequency of abnormal meteorological conditions, the historical frequency of abnormal behavior of operators, and the historical frequency of abnormal operating status of operating equipment.

3. The multi-dimensional safety monitoring and early warning system for power infrastructure projects based on a multi-factor algorithm according to claim 2 is characterized by: The specific analysis process of determining the multi-dimensional safety monitoring weight setting data set and the multi-dimensional safety monitoring threshold of the power infrastructure project is as follows: Based on the acquired historical monitoring data of power infrastructure projects, the historical monitoring constraint factors of power infrastructure projects are obtained through comprehensive analysis. The historical monitoring constraint factors of power infrastructure projects are used as the analysis basis for determining the multi-dimensional safety monitoring weight setting data set and the multi-dimensional safety monitoring threshold of power infrastructure projects. The historical monitoring constraint factors of the power infrastructure project are stored as designated tags, and the designated tags are compared with the set tags stored in the database to obtain the set tags corresponding to the designated tags, and the multi-dimensional safety monitoring weight setting data set of the power infrastructure project corresponding to the set tags stored in the database and the multi-dimensional safety monitoring threshold of the power infrastructure project corresponding to the set tags are obtained; the multi-dimensional safety monitoring weight setting data set of the power infrastructure project specifically includes terrain feature signal weight factors, meteorological feature signal weight factors and operator feature signal weight factors.

4. The multi-dimensional safety monitoring and early warning system for power infrastructure projects based on a multi-factor algorithm according to claim 3 is characterized by: The specific analysis process of the historical monitoring constraint factors of the power infrastructure project is as follows: Where δ is the historical monitoring constraint factor of the power infrastructure project, qx is the historical abnormal frequency of meteorological conditions, xw is the historical abnormal frequency of the behavior of operators, sb is the historical abnormal frequency of the operating equipment operation status, μ1 is the compensation factor of the set qx, μ2 is the compensation factor of the set xw, μ3 is the compensation factor of the set sb, and e is a natural constant.

5. The multi-dimensional safety monitoring and early warning system for power infrastructure projects based on a multi-factor algorithm according to claim 1 is characterized by: The analysis of the terrain characteristics of the power infrastructure project is carried out as follows: Obtaining terrain feature data of the power infrastructure project, the terrain feature data of the power infrastructure project specifically includes the ground slope angle of the power infrastructure project, the rock joint density of the power infrastructure project, and the ground soil density of the power infrastructure project; Based on the acquired terrain feature data of the power infrastructure project, a comprehensive analysis is performed to obtain the terrain feature signal, which is used as the analysis basis for judging whether the multi-dimensional safety monitoring of the power infrastructure project is qualified.

6. The multi-dimensional safety monitoring and early warning system for power infrastructure projects based on a multi-factor algorithm according to claim 1 is characterized by: The above analysis of meteorological characteristics of power infrastructure projects is as follows: Obtain meteorological characteristic data of power infrastructure projects, which specifically include environmental precipitation of power infrastructure projects, environmental wind speed of power infrastructure projects, and environmental light intensity deviation rate of power infrastructure projects; Based on the acquired meteorological characteristic data of power infrastructure projects, meteorological characteristic signals are obtained through comprehensive analysis. The meteorological characteristic signals are used as the analysis basis for judging whether the multi-dimensional safety monitoring of power infrastructure projects is qualified.

7. The multi-dimensional safety monitoring and early warning system for power infrastructure projects based on a multi-factor algorithm according to claim 1 is characterized by: The above analysis of the characteristics of the operators of the power infrastructure project is as follows: Obtaining characteristic data of operators of power infrastructure projects, including blood oxygen saturation of operators, body inclination angle of operators, and success rate of facial recognition verification of operators; Based on the acquired characteristic data of operators in power infrastructure projects, a comprehensive analysis is performed to obtain the operator characteristic signals, which serve as the analysis basis for judging whether the multi-dimensional safety monitoring of power infrastructure projects is qualified.

8. The multi-dimensional safety monitoring and early warning system for power infrastructure projects based on a multi-factor algorithm according to claim 3 is characterized by: The specific analysis process for judging whether the multi-dimensional safety monitoring of power infrastructure projects is qualified is as follows: The weight factors of terrain characteristic signals, meteorological characteristic signals and operator characteristic signals are introduced into the multi-dimensional safety monitoring model of power infrastructure projects together with terrain characteristic signals, meteorological characteristic signals and operator characteristic signals to calculate the multi-dimensional safety monitoring factors, which are used as the analysis basis for judging whether the multi-dimensional safety monitoring of power infrastructure projects is qualified; Compare the multi-dimensional safety monitoring factors with the multi-dimensional safety monitoring thresholds of power infrastructure projects; If the multi-dimensional safety monitoring factor is not lower than the multi-dimensional safety monitoring threshold of the power infrastructure project, the multi-dimensional safety monitoring of the power infrastructure project corresponding to the multi-dimensional safety monitoring factor is qualified, and the power infrastructure project will continue to be implemented; If the multi-dimensional safety monitoring factor is lower than the multi-dimensional safety monitoring threshold of the power infrastructure project, the multi-dimensional safety monitoring of the power infrastructure project corresponding to the multi-dimensional safety monitoring factor will fail, and a safety warning will be issued for the power infrastructure project and the unqualified level of the power infrastructure project will be determined.

9. The multi-dimensional safety monitoring and early warning system for power infrastructure projects based on a multi-factor algorithm according to claim 8 is characterized by: The multi-dimensional safety monitoring model for power infrastructure projects has the following specific analysis process: Where ω is the multi-dimensional safety monitoring factor, α is the terrain characteristic signal, β is the meteorological characteristic signal, γ is the operator characteristic signal, θ1 is the terrain characteristic signal weight factor, θ2 is the meteorological characteristic signal weight factor, θ3 is the operator characteristic signal weight factor, and e is a natural constant.

10. The multi-dimensional safety monitoring and early warning system for power infrastructure projects based on a multi-factor algorithm according to claim 8 is characterized by: Determine the unqualified level of power infrastructure projects. The specific analysis process is as follows: The difference between the multi-dimensional safety monitoring threshold and the multi-dimensional safety monitoring factor of the power infrastructure project is recorded as the multi-dimensional safety monitoring deviation value; Compare the multi-dimensional safety monitoring deviation value with the multi-dimensional safety monitoring reference deviation range stored in the database; If the multi-dimensional safety monitoring deviation value falls within the multi-dimensional safety monitoring reference deviation range, the unqualified level of the power infrastructure project corresponding to the multi-dimensional safety monitoring deviation value is level 2; If the multi-dimensional safety monitoring deviation value does not fall within the multi-dimensional safety monitoring reference deviation range, and the multi-dimensional safety monitoring deviation value is less than the minimum value in the multi-dimensional safety monitoring reference deviation range, then the unqualified level of the power infrastructure project corresponding to the multi-dimensional safety monitoring deviation value is level three; If the multi-dimensional safety monitoring deviation value does not fall within the multi-dimensional safety monitoring reference deviation range, and the multi-dimensional safety monitoring deviation value is greater than the maximum value in the multi-dimensional safety monitoring reference deviation range, then the unqualified level of the power infrastructure project corresponding to the multi-dimensional safety monitoring deviation value is level one.

Images