A method and system for risk assessment of overhead lines based on mountain photovoltaic power station

Abstract

The application discloses a mountainous photovoltaic power station-based overhead line risk assessment method and system, relates to the technical field of risk assessment, and solves the technical problem that the prior art fails to fully consider the coupling effect of multiple risk factors under a mountainous environment and the dynamic change characteristics thereof, so that the evaluation result is greatly deviated from the actual working condition of the mountainous field, and the accuracy of the overhead line risk assessment method is low; the risk dimension index is generated based on multi-source data; the risk index weight coefficient is dynamically generated based on the risk dimension index; the line risk assessment result is generated based on the risk dimension index and the risk index weight coefficient, a multi-dimensional risk index system is constructed, the limitation of single factor evaluation is broken through; the dynamic risk index weight coefficient makes the risk assessment adapt to the complex and changeable characteristics of the mountainous environment, the dynamic weight is combined with the multi-dimensional index to generate the evaluation result, and the accuracy of the overhead line risk assessment method is improved.

Description

Technical Field

[0001] This application belongs to the field of risk assessment technology, specifically a risk assessment method and system for overhead lines based on mountain photovoltaic power stations. Background Technology

[0002] Overhead power lines in mountainous photovoltaic power plants serve as crucial channels connecting power generation units to substations and enabling power transmission. Their safe and stable operation directly impacts the overall power generation efficiency and supply reliability of the entire plant. Due to the complex terrain, variable climate, dense vegetation, and frequent geological disasters in mountainous areas, overhead power lines face threats from various natural risks such as lightning strikes, icing, wind deflection, landslides, and tree obstructions, which can easily lead to accidents such as line breaks, power outages, and even equipment damage. Therefore, conducting risk assessments of overhead power lines in mountainous photovoltaic power plants is not only an important prerequisite for identifying potential hazards and optimizing line routes and structural designs, but also a key measure to enhance the overall resilience of the power plant, ensure the stable output of clean energy, and promote the high-quality development of renewable energy.

[0003] Existing technologies for risk assessment of overhead lines often rely on a single factor, failing to fully consider the coupling effect and dynamic changes of multiple risk factors in mountainous environments. This results in significant discrepancies between the assessment results and actual working conditions in mountainous areas, leading to low accuracy in overhead line risk assessment methods. Therefore, further improvements are needed for the risk assessment methods of overhead lines for mountainous photovoltaic power plants. Summary of the Invention

[0004] This application aims to solve at least one of the technical problems existing in the prior art; to this end, this application proposes a risk assessment method and system for overhead lines based on mountain photovoltaic power stations, which is used to solve the technical problem that the prior art often assesses based on a single factor, fails to fully consider the coupling effect and dynamic change characteristics of multiple risk factors in the mountain environment, resulting in a large deviation between the assessment results and the actual working conditions in the mountain area, and thus the accuracy of the overhead line risk assessment method is low.

[0005] To achieve the above objectives, the first aspect of this application provides a risk assessment method for overhead lines based on mountain photovoltaic power stations, comprising: Acquire multi-source data along the target overhead line path; the multi-source data includes micro-topographic data of the line corridor, real-time micro-meteorological data, photovoltaic power output data, and line body status data; Risk dimension indicators are generated based on multi-source data; the risk dimension indicators include meteorological environment risk indicators, electrical operation risk indicators, and line body risk indicators. Risk indicator weight coefficients are dynamically generated based on risk dimension indicators. The route risk assessment results are generated based on risk dimension indicators and risk indicator weighting coefficients.

[0006] This application constructs a comprehensive risk indicator system covering three dimensions: meteorology, electrical, and the line itself, through the above steps, breaking through the limitations of traditional assessment methods that rely on a single factor. It introduces a dynamic weighting mechanism, automatically generating weight coefficients based on the real-time changes of indicators in each risk dimension. This enables the assessment model to adapt to the complex and ever-changing characteristics of the mountainous environment, accurately capturing the actual impact of various risk factors under different periods and operating conditions. By organically integrating dynamic weights with multi-dimensional indicators, the model not only accurately depicts the coupling effect of multiple risk factors in the special mountainous environment, but also fundamentally solves the problem of traditional methods leading to deviations from reality and insufficient accuracy due to single dimensions and static weights. This significantly improves the accuracy and practicality of risk assessment for overhead lines of mountainous photovoltaic power stations.

[0007] Furthermore, the generation of risk dimension indicators based on multi-source data includes: Extract micro-topographical data of the railway corridor, real-time micro-meteorological data, photovoltaic power output data, and railway line status data from multi-source data; Meteorological and environmental risk indicators are obtained by dynamically correcting real-time micro-meteorological data using micro-topographical data of the route corridor. Electrical operation risk indicators were obtained by analyzing the spatiotemporal fluctuation characteristics of photovoltaic power output data. The risk indicators of the line body are obtained by analyzing the status data of the line body. Risk dimension indicators are determined based on meteorological environmental risk indicators, electrical operation risk indicators, and line body risk indicators.

[0008] Furthermore, the method of dynamically correcting real-time micro-meteorological data using micro-topographical data of the railway corridor to obtain meteorological environmental risk indicators includes: Extract the tower base elevation (TH), tower location slope (TWP), tower location aspect (TWX), and terrain type (DL) from the micro-topographic data of the line corridor; Extract wind speed (FS), temperature (WD), humidity (SD), and ground flash density (DM) from real-time micrometeorological data; Several meteorological correction functions are constructed using the tower base elevation TH, tower location slope TWP, tower location aspect TWX, and terrain location index DWZ to correct wind speed, temperature, humidity, and ground flash density in real-time micro-meteorological data. The meteorological correction functions include wind speed correction function, temperature correction function, humidity correction function, and ground flash correction function. Corrected micro-meteorological data is obtained by substituting wind speed, temperature, humidity, and ground flash density from real-time micro-meteorological data into their respective meteorological correction functions; the corrected micro-meteorological data includes corrected wind speed, corrected temperature, corrected humidity, and corrected ground flash density. A meteorological risk quantification function is constructed; the meteorological risk quantification function includes a wind risk quantification function, a wildfire risk quantification function, and a lightning strike risk quantification function. The modified micro-meteorological data is input into the meteorological risk quantification function to obtain several meteorological environmental risk indicators; the meteorological environmental risk indicators include strong wind risk indicators, wildfire risk indicators and lightning strike risk indicators.

[0009] Furthermore, the electrical operation risk indicators obtained by analyzing the spatiotemporal fluctuation characteristics of photovoltaic power output data include: Extract the line power P and harmonic distortion rate (THD) from the photovoltaic output data; The power volatility GBL is calculated using a formula; the formula satisfies: Where t represents the number corresponding to the time point; This is expressed as the line power at time point t; Represented as time intervals; Extract the time points where the power volatility is greater than the volatility threshold as the volatility time points; The ratio of several fluctuation points to a total of several other time points is statistically analyzed, and this ratio is used as the risk of tidal fluctuations. ; Calculate harmonic risk using formula The formula satisfies: ;in, This is expressed as the national standard limit for power grid harmonic distortion rate; Electrical operation risk indicators are determined based on power flow fluctuation risk and harmonic risk.

[0010] Furthermore, the process of obtaining line-specific risk indicators through state analysis of the line-specific status data includes: Obtain high-precision distribution maps of areas prone to geological disasters; Extract the tower location coordinates, tower tilt angle, number of defective insulator discs, number of broken conductor strands, and line commissioning years from the line body data; The risk level of the tower is determined by matching the tower location coordinates with a high-precision geological hazard susceptibility distribution map; the high-precision geological hazard susceptibility distribution map includes high-risk areas, medium-risk areas, and low-risk areas. The tower tilt angle, the number of defective insulator discs, and the number of broken conductor strands are respectively quantified to obtain tilt risk score, insulation defect score, and conductor damage score; The structural state risk is obtained by weighted summation of the tilt risk score, insulation defect score, and conductor damage score; An aging quantification function LHF(XTN) is constructed to characterize the nonlinear relationship between the line's service life (XTN) and its aging risk (XLF); the aging quantification function satisfies: ;in, This represents the threshold for the line's operational lifespan, with specific values ​​set based on experience; k represents the attenuation coefficient, where k>0; its value is also set based on experience. The aging risk XLF of the line is calculated by substituting the line's years of operation into the aging quantification function. The risk index of the line itself is calculated using a formula; the formula satisfies: Where max() represents the maximum value operation, and TFD represents the tower risk level. and Represented as weighting coefficients, and ∈(0,1), and and The sum is 1; the specific value is set based on experience. This is represented as structural state risk.

[0011] Furthermore, the dynamic generation of risk indicator weight coefficients based on risk dimension indicators includes: Obtain a series of historical risk dimension indicators corresponding to the risk dimension indicators; For risk dimension indicators Calculate the information entropy corresponding to the i-th indicator. Where i represents the indicator number in the risk dimension indicators; The objective weight corresponding to the i-th risk dimension indicator is calculated using the formula. The formula satisfies: Where j represents the indicator number in the risk dimension indicators, and ZBS represents the total number of indicators in the risk dimension indicators; Obtaining subjective weights The subjective weights are set by experts based on the importance of several risk dimension indicators for different assessment scenarios. The weighting coefficients of the theoretical risk indicators are calculated using a formula; the formula satisfies: ;in, This represents the evaluation scenario corresponding to the current time point t. This represents the subjective weight of the i-th risk dimension indicator in the assessment scenario at the current time point; This is represented as the adjustment coefficient corresponding to the i-th risk dimension indicator at the current time point t when a weather warning is issued; the specific value is set based on experience. Represented as the fusion coefficient, ∈(0,1), the specific value is set based on experience; The risk indicator weight coefficients are obtained by performing a weight normalization operation on the weight coefficients of several theoretical risk indicators.

[0012] This application introduces information entropy to quantify the historical data volatility and uncertainty of each risk dimension indicator, thereby calculating objective weights based on the data itself. This ensures that the weight allocation process fully respects and reflects the inherent laws of actual data, avoids biases that may arise from subjective judgment, and improves the objectivity and scientific rigor of risk assessment. Simultaneously, to compensate for potential logical deficiencies or limitations of purely data-driven methods in specific contexts, subjective weights set by experts for different assessment scenarios are incorporated, which helps enhance the rationality and interpretability of assessment results under specific conditions. By designing a fusion coefficient to organically combine the aforementioned subjective and objective weights and introducing a dynamic adjustment coefficient linked to a real-time weather warning system, the precise calculation of risk indicator weight coefficients is achieved. This effectively balances the relationship between scientific rigor and rationality, and enables rapid responses to emergencies such as extreme weather. While ensuring the accuracy of risk assessment results, it also enhances their agility and practicality, providing a core guarantee for generating accurate and reliable risk assessments.

[0013] Furthermore, the generation of route risk assessment results based on risk dimension indicators and risk indicator weighting coefficients includes: Extract risk dimension indicators and risk indicator weighting coefficients; The comprehensive risk dimension value is obtained by weighting and summing the risk dimension indicators and their corresponding risk indicator weight coefficients. Integrate risk dimension indicators and comprehensive risk dimension values ​​into risk analysis data; Risk analysis data is input into the risk assessment model to obtain the line risk assessment result; the risk assessment model is constructed through an artificial intelligence model and is used to comprehensively assess the line risk results.

[0014] Furthermore, the risk assessment model is constructed using an artificial intelligence model, including: Obtain a number of historical risk analysis data and their corresponding historical route risk assessment results; Several historical risk analysis data and their corresponding historical route risk assessment results are divided into training data, validation data, and test data; data preprocessing is performed on the training data, validation data, and test data to obtain the training set, validation set, and test set. Choose an artificial intelligence model as the base model; The base model is trained on the training set, and the learning rate and hyperparameters are adjusted on the validation set to obtain the pre-trained model. By validating the pre-trained model on the test set, a risk assessment model is finally obtained, which takes risk analysis data as input and outputs the line risk assessment results.

[0015] This application introduces an artificial intelligence model to construct a risk assessment model, which can deeply explore and learn the complex nonlinear coupling relationships and interaction effects among multi-dimensional risk indicators such as meteorology, electrical systems, and physical properties. This allows for the accurate depiction of complex risk scenarios that actually exist in mountainous environments, such as "strong winds accompanied by rainfall exacerbating geological risks" and "the superposition of photovoltaic fluctuations and equipment aging." By learning from massive amounts of historical data, the model can simulate expert-level comprehensive judgment capabilities, achieving in-depth and comprehensive analysis of risk indicators across various dimensions, thus improving the accuracy and reliability of risk assessment results. At the same time, the model has strong generalization capabilities, enabling it to adapt to various complex and rare operating conditions of mountainous photovoltaic power stations. This results in more intelligent and realistic high-precision dynamic risk assessment results, providing unprecedented decision support for the precise prevention and control of line safety operations.

[0016] A second aspect of the present invention provides a risk assessment system for overhead power lines based on mountain photovoltaic power stations, comprising: a data acquisition module and a data analysis module; the data acquisition module and the data analysis module are connected together; The data acquisition module acquires multi-source data along the target overhead line path using data acquisition equipment. The data analysis module includes an indicator quantification unit, a weight generation unit, and a result generation unit; The indicator quantification unit generates risk dimension indicators based on multi-source data. The weight generation unit dynamically generates risk indicator weight coefficients based on risk dimension indicators. The result generation unit generates route risk assessment results based on risk dimension indicators and risk indicator weighting coefficients.

[0017] Another aspect of the present invention provides a computer-readable storage medium storing a computer program that, when executed by a processor, implements a risk assessment system for overhead lines based on a mountain photovoltaic power station according to a second aspect of the present invention.

[0018] Compared with the prior art, the beneficial effects of this application are: 1. This application constructs a risk indicator system covering three dimensions—meteorology, electrical, and physical structure—by generating risk dimension indicators based on multi-source data; dynamically generating risk indicator weight coefficients based on these indicators; and generating line risk assessment results based on the risk dimension indicators and their weight coefficients. This overcomes the limitations of single-factor assessment. Simultaneously, the dynamic generation of weight coefficients based on risk dimension indicators enables the assessment model to adapt to the complex and ever-changing characteristics of mountainous environments, accurately reflecting the actual impact of various risk factors under different periods and operating conditions. Combining dynamic weights with multi-dimensional indicators to generate assessment results accurately depicts the coupling effect of multiple risk factors in the special mountainous environment. This fundamentally solves the problem of large deviations and low accuracy in assessment results caused by the single-dimensional and static nature of traditional methods, thus improving the accuracy of overhead line risk assessment methods.

[0019] 2. This application dynamically corrects real-time micro-meteorological data using micro-topographical data of the transmission line corridor, accurately mapping macro-meteorological data to specific tower locations along the line. This effectively solves the assessment bias caused by the heterogeneity of micro-meteorological conditions in mountainous environments and significantly improves the accuracy of meteorological risk assessment. By analyzing the spatiotemporal fluctuation characteristics of photovoltaic power output data, it characterizes the unique correlation power surge and harmonic risks of photovoltaic power sources, achieving closed-loop risk tracking from the power source side to the transmission line side. By performing state analysis on the transmission line's status data, it unifies the multi-source heterogeneous transmission line data into standardized transmission line risk indicators. This ensures that the generated risk dimension indicators not only comprehensively cover key risk sources but also conform to the actual operating characteristics of mountainous photovoltaic transmission lines, laying a reliable data foundation for subsequent dynamic weight allocation and accurate assessment, and improving the accuracy and practicality of the final risk assessment results.

[0020] 3. This application quantifies the volatility and uncertainty of historical data corresponding to each risk dimension indicator by introducing information entropy, and calculates objective weights accordingly. This ensures that the weight allocation fully respects the inherent laws of the data, avoids subjective assumptions, and improves the objectivity and scientific nature of the assessment. At the same time, by introducing subjective weights set by experts for different assessment scenarios, it compensates for the logical bias that may exist in pure data-driven approaches under specific scenarios, and enhances the rationality and interpretability of the assessment results. Finally, by designing a fusion coefficient to organically combine subjective and objective weights and introducing a dynamic adjustment coefficient linked to real-time weather warnings, the risk indicator weight coefficients are finally calculated. This effectively balances data patterns and expert experience, and can respond quickly to emergencies such as extreme weather. Thus, it achieves a unity of weight allocation in three dimensions: scientificity, rationality, and agility, providing a core guarantee for generating accurate and reliable risk assessment results. Attached Figure Description

[0021] To more clearly illustrate the technical solutions in the embodiments of this application 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 some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0022] Figure 1 This is a flowchart illustrating a risk assessment method for overhead lines based on mountain photovoltaic power stations, as described in this application. Figure 2 This is a schematic diagram illustrating the principle of an overhead line risk assessment system based on a mountain photovoltaic power station, as described in this application. Detailed Implementation

[0023] The technical solutions of this application will be clearly and completely described below with reference to the embodiments. Obviously, the described embodiments are only some embodiments of this application, and not all embodiments. Based on the embodiments of this application, all other embodiments obtained by those of ordinary skill in the art without creative effort are within the scope of protection of this application.

[0024] Please see Figure 1 The first aspect of this application provides a method for risk assessment of overhead lines based on mountain photovoltaic power stations, including: Acquire multi-source data along the target overhead line path; the multi-source data includes micro-topographic data of the line corridor, real-time micro-meteorological data, photovoltaic power output data, and line body status data; Risk dimension indicators are generated based on multi-source data; the risk dimension indicators include meteorological environment risk indicators, electrical operation risk indicators, and line body risk indicators. Risk indicator weight coefficients are dynamically generated based on risk dimension indicators. The route risk assessment results are generated based on risk dimension indicators and risk indicator weighting coefficients.

[0025] The risk dimension indicators generated based on multi-source data in this embodiment include: Extract micro-topographical data of the railway corridor, real-time micro-meteorological data, photovoltaic power output data, and railway line status data from multi-source data; Meteorological and environmental risk indicators are obtained by dynamically correcting real-time micro-meteorological data using micro-topographical data of the route corridor. Electrical operation risk indicators were obtained by analyzing the spatiotemporal fluctuation characteristics of photovoltaic power output data. The risk indicators of the line body are obtained by analyzing the status data of the line body. Risk dimension indicators are determined based on meteorological environmental risk indicators, electrical operation risk indicators, and line body risk indicators.

[0026] In this embodiment, meteorological environmental risk indicators are obtained by dynamically correcting real-time micro-meteorological data using micro-topographical data of the railway corridor, including: Extract the tower base elevation (TH), tower location slope (TWP), tower location aspect (TWX), and terrain type (DL) from the micro-topographic data of the line corridor; Extract wind speed (FS), temperature (WD), humidity (SD), and ground flash density (DM) from real-time micrometeorological data; Several meteorological correction functions for correcting wind speed, temperature, humidity, and ground flash density in real-time micro-meteorological data were constructed using the tower base elevation TH, tower location slope TWP, tower location aspect TWX, and topographic location index DWZ. The meteorological correction functions include wind speed correction function, temperature correction function, humidity correction function, and ground flash density correction function. In this embodiment, the wind speed correction function FSXF satisfies: ;in, This represents the basic terrain coefficient corresponding to the current terrain type. In this embodiment, the terrain types are divided into three categories, including ridges / peaks, slopes, and valleys / depressions. The corresponding basic terrain coefficients are set based on experience. In this embodiment, the basic terrain coefficients corresponding to ridges / peaks, slopes, and valleys / depressions are set to 1.4, 1, and 0.7, respectively. PX represents the slope influence coefficient, PX∈(0,1). The specific value is set based on experience. In this embodiment, PX is set to 0.2. This is expressed as a numerical value converting the slope of the tower position into radians, which is expressed in this embodiment using a formula. Achieve radian conversion; This is expressed as a numerical value converting the slope of the tower position into radians, and the conversion method is the same as... The calculation process is the same; FHD represents the radian of the current prevailing wind direction. The specific value is set according to experience. For example, if the current wind direction is northerly, then FHD is set to 0; if the current wind direction is easterly, then FHD is set to π / 2. The temperature correction function WDXF satisfies: Wherein, WSL represents the temperature decay rate, which is set to -0.65℃ / 100m in this embodiment; JH represents the reference height, which is set to 100m in this embodiment; PTX represents the slope aspect adjustment coefficient, PTX>0; the specific value is set according to experience, and PTX is set to 2 in this embodiment; The humidity correction function SDXF satisfies: Where XWD represents the corrected temperature value after correction by the temperature correction function; e_sat(WD) is the saturated vapor pressure function at temperature WD, calculated using the Magnus formula; This is expressed as the topographic humidity coefficient under the corresponding terrain type. In this embodiment, the basic terrain coefficients corresponding to ridges / peaks, slopes, and valleys / depressions are set to 0.9, 1, and 1.1, respectively. The ground flash density correction function DMXF satisfies: ;in, It is expressed as the average elevation of the base surface of several towers. This represents the terrain correction factor under the corresponding terrain type. In this embodiment, the terrain correction factors corresponding to ridge / peak, slope and valley / depression are set to 1.7, 1 and 0.8 respectively. Corrected micrometeorological data are obtained by substituting wind speed, temperature, humidity, and ground flash density from real-time micrometeorological data into their respective meteorological correction functions; the corrected micrometeorological data includes corrected wind speed, corrected temperature, corrected humidity, and corrected ground flash density. Construct meteorological risk quantification functions; meteorological risk quantification functions include strong wind risk quantification functions, wildfire risk quantification functions, and lightning strike risk quantification functions; The wind risk quantification function in this embodiment satisfies: Where XFS represents the corrected wind speed, This represents the tower design wind speed, which is related to the line design, and the specific value is set based on experience. This is expressed as the wind speed amplification factor. >0; the specific value is set based on experience, and in this embodiment it will be Set to 2; The wildfire risk quantification function satisfies: ZYY represents the vegetation influence factor, which is affected by the vegetation type at the location of the tower. In this embodiment, the vegetation type is divided into flammable vegetation and non-flammable vegetation. When the vegetation type is flammable vegetation, ZYY is set to 1.8; when the vegetation type is non-flammable vegetation, ZYY is set to 0.7. Flammable vegetation includes dry grass and coniferous forest, etc. A, B, and D represent the temperature influence coefficient, humidity influence coefficient, and wind speed influence coefficient, respectively. The specific values ​​are set according to experience. In this embodiment, A, B, and C are set to 2, 2, and 0.5, respectively. C is a small constant, C>0. The specific value is set according to experience. In this embodiment, C is set to 0.5. C is set to prevent the wind speed term from being zero in calm winds, because there is a fire hazard even without wind. XWD, XSD, and XFS represent the corrected temperature, corrected humidity, and corrected wind speed, respectively. JWD represents the base temperature. The specific value is set according to experience. In this embodiment, JWD is set to 25℃. The lightning strike risk quantification function satisfies: ;in, Expressed as corrected ground flash density, YDX represents the pass rate of the grounding resistance of the tower; YDX represents the lightning strike severity coefficient, YDX>0, and the specific value is set according to experience. In this embodiment, YDX is set to 3. This is expressed as the wind speed amplification factor. >0; the specific value is set based on experience, and in this embodiment it will be Set to 2; The modified micro-meteorological data is input into the meteorological risk quantification function to obtain several meteorological environmental risk indicators; the meteorological environmental risk indicators include strong wind risk indicators, wildfire risk indicators and lightning strike risk indicators.

[0027] In this embodiment, electrical operation risk indicators are obtained by analyzing the spatiotemporal fluctuation characteristics of photovoltaic power output data, including: Extract the line power P and harmonic distortion rate (THD) from the photovoltaic output data; The power volatility GBL is calculated using the formula; the formula satisfies: Where t represents the number corresponding to the time point; This is expressed as the line power at time point t; Represented as time intervals; The time points at which the power fluctuation rate is greater than the fluctuation threshold are extracted as fluctuation time points; the fluctuation threshold is set based on experience, and in this embodiment, the fluctuation threshold is set to 0.9 times the long-term allowable current carrying capacity of the line; the long-term allowable current carrying capacity of the line in this embodiment is set according to the line. The ratio of several fluctuation points to a total of several other time points is statistically analyzed, and this ratio is used as a measure of the risk of tidal fluctuations. ; Calculate harmonic risk using formula The formula satisfies: ;in, This represents the national standard limit for harmonic distortion rate of the power grid. In this embodiment, the national standard limit for harmonic distortion rate of the power grid at the 35kV level is set to 3%. Electrical operation risk indicators are determined based on power flow fluctuation risk and harmonic risk.

[0028] In this embodiment, the risk indicators of the line body are obtained by performing state analysis on the line body state data, including: Obtain high-precision distribution maps of areas prone to geological disasters; Extract the tower location coordinates, tower tilt angle, number of defective insulator discs, number of broken conductor strands, and line commissioning years from the line body data; The tower location coordinates are matched with a high-precision geological hazard susceptibility zone distribution map to determine the tower risk level; the high-precision geological hazard susceptibility zone distribution map includes high-risk areas, medium-risk areas, and low-risk areas; in this embodiment, the tower risk levels corresponding to high-risk areas, medium-risk areas, and low-risk areas are set to 0.9, 0.5, and 0.2, respectively. The tower tilt angle, the number of defective insulator discs, and the number of broken conductor strands are used to quantify the degree of defect, resulting in tilt risk score, insulation defect score, and conductor damage score. In this embodiment, a formula is used... Calculate the tilt risk score QFF, where QJD represents the tower tilt angle, SYJ represents the design allowable tilt angle, and min() represents the minimum value operation; use the formula... The insulation defect score is calculated as JQF, where QJZS represents the number of defective insulator discs, and JZS represents the total number of insulator discs. This is done using the formula... Calculate the conductor damage score DSF, where DDS represents the number of broken conductor strands and YDS represents the allowable number of broken conductor strands; The structural state risk is obtained by weighted summation of the tilt risk score, insulation defect score, and conductor damage score; in this embodiment, the weight coefficients corresponding to the tilt risk score, insulation defect score, and conductor damage score are set to 0.4, 0.3, and 0.3, respectively. An aging quantization function LHF(XTN) is constructed to characterize the nonlinear relationship between the line's service life (XTN) and the line's aging risk (XLF). The aging quantization function satisfies: ;in, This represents the threshold for the line's operational lifespan, with the specific value set based on experience. In this embodiment, it is set to 25 years. k represents the attenuation coefficient, where k > 0. The specific value is set based on experience, and in this embodiment, k is set to 10. The aging risk XLF of the line is calculated by substituting the line's years of operation into the aging quantification function. The risk indicators of the railway line itself are calculated using a formula; the formula satisfies: Where max() represents the maximum value operation, and TFD represents the tower risk level. and Represented as weighting coefficients, and ∈(0,1), and and The sum is 1; the specific value is set based on experience, and in this embodiment it will be 1. and All are set to 0.5; This is represented as structural state risk.

[0029] This embodiment integrates micro-topographical data of the transmission line corridor to dynamically correct real-time micro-meteorological information, accurately mapping macro-meteorological data to the specific locations of each tower. This effectively overcomes the assessment bias caused by the high heterogeneity of micro-meteorological data in mountainous environments, significantly improving the spatial accuracy and representativeness of meteorological risk assessment. Simultaneously, by analyzing the spatiotemporal fluctuation characteristics of photovoltaic power output data, it deeply characterizes the unique correlated power surge and harmonic risk features of photovoltaic power sources, achieving closed-loop risk tracking from the power source side to the transmission line side. Based on the analysis of the transmission line's physical condition data, the multi-source heterogeneous transmission line data is uniformly transformed into standardized transmission line risk indicators, ensuring that the constructed risk dimensions not only comprehensively cover key risk sources but also closely align with the actual operating characteristics of mountainous photovoltaic transmission lines. The aforementioned multi-dimensional data fusion and refined modeling provide solid and reliable data support for subsequent dynamic weight allocation and high-precision risk assessment, significantly enhancing the accuracy, adaptability, and engineering practicality of the assessment results.

[0030] In this embodiment, the dynamic generation of risk indicator weight coefficients based on risk dimension indicators includes: Obtain several historical risk dimension indicator sequences corresponding to the risk dimension indicators; in this embodiment, the obtained several historical risk dimension indicator sequences refer to the risk dimension indicators corresponding to the past 30 days. For risk dimension indicators Calculate the information entropy corresponding to the i-th indicator. Where i represents the indicator number in the risk dimension indicators; The objective weight corresponding to the i-th risk dimension indicator is calculated using the formula. The formula satisfies: Where j represents the indicator number in the risk dimension indicators, and ZBS represents the total number of indicators in the risk dimension indicators; Obtaining subjective weights Subjective weights are set by experts to determine the importance of several risk dimension indicators for different assessment scenarios; the assessment scenarios in this embodiment include, but are not limited to, sunny summer days and rainy winter days. The weighting coefficients of the theoretical risk indicators are calculated using a formula; the formula satisfies: ;in, This represents the evaluation scenario corresponding to the current time point t. This represents the subjective weight of the i-th risk dimension indicator in the assessment scenario at the current time point; This represents the adjustment coefficient corresponding to the i-th risk dimension indicator at the current time t when a weather warning is issued. The specific value is set based on experience. In this embodiment, the adjustment coefficient is set to 1 for the absence of a weather warning. When the weather warning is a blue gale warning, the adjustment coefficient corresponding to the gale risk indicator is set to 1.2; when the weather warning is an orange gale warning, the adjustment coefficient corresponding to the gale risk indicator is set to 1.5; when the weather warning is a yellow thunderstorm warning, the adjustment coefficient corresponding to the lightning risk indicator is set to 1.3. The adjustment coefficient is set according to the type and level of the weather warning. Represented as the fusion coefficient, ∈(0, 1), the specific value is set according to experience, and in this embodiment it will be Set to 0.7; The risk indicator weight coefficients are obtained by performing a weight normalization operation on the weight coefficients of several theoretical risk indicators; in this embodiment, the weight normalization operation is to make the sum of the weight coefficients of several risk indicators equal to 1.

[0031] In this embodiment, the generation of route risk assessment results based on risk dimension indicators and risk indicator weighting coefficients includes: Extract risk dimension indicators and risk indicator weighting coefficients; The comprehensive risk dimension value is obtained by weighting and summing the risk dimension indicators and their corresponding risk indicator weight coefficients. Integrate risk dimension indicators and comprehensive risk dimension values ​​into risk analysis data; Risk analysis data is input into the risk assessment model to obtain the route risk assessment results; the risk assessment model is constructed through an artificial intelligence model to comprehensively evaluate the route risk results.

[0032] The risk assessment model in this embodiment is constructed using an artificial intelligence model, including: Obtain a number of historical risk analysis data and their corresponding historical route risk assessment results; Several historical risk analysis data and their corresponding historical route risk assessment results are divided into training data, validation data, and test data; data preprocessing is performed on the training data, validation data, and test data to obtain training sets, validation sets, and test sets; the ratio between the training set, test set, and validation set is 7:2:1; Choose an artificial intelligence model as the base model; artificial intelligence models include DeepSeek models, etc. The base model is trained on the training set, and the learning rate and hyperparameters are adjusted on the validation set to obtain the pre-trained model. By validating the pre-trained model on the test set, a risk assessment model is finally obtained, which takes risk analysis data as input and outputs the line risk assessment results.

[0033] Please see Figure 2 The second aspect of this application provides a risk assessment system for overhead lines based on mountain photovoltaic power stations, including: a data acquisition module and a data analysis module; the data acquisition module and the data analysis module are electrically and / or communicatively connected. Data acquisition module: Acquires multi-source data along the target overhead line path using data acquisition equipment; in this embodiment, the data acquisition equipment includes several sensors, etc. The data analysis module includes an indicator quantification unit, a weight generation unit, and a result generation unit; Indicator Quantification Unit: Generates risk dimension indicators based on multi-source data; Weighting unit: Dynamically generates risk indicator weight coefficients based on risk dimension indicators; Result generation unit: Generates route risk assessment results based on risk dimension indicators and risk indicator weighting coefficients.

[0034] This embodiment constructs a risk assessment system through an advanced artificial intelligence model, which can deeply explore and learn the complex nonlinear coupling relationships and dynamic interaction effects among multi-dimensional risk indicators such as meteorology, electrical systems, and the line itself. It accurately depicts real and typical composite risk scenarios in special mountainous environments, such as "strong winds accompanied by heavy rainfall exacerbating slope instability" and "the superposition of drastic fluctuations in photovoltaic output and equipment aging effects." Through training on massive amounts of historical operation and fault data, it simulates expert-level comprehensive judgment capabilities, achieving in-depth and comprehensive integrated analysis of various risk dimensions, significantly improving the accuracy, robustness, and credibility of the assessment results.

[0035] Another embodiment of this application provides a computer-readable storage medium storing a computer program that, when executed by a processor, implements a risk assessment system for overhead lines based on a mountain photovoltaic power station according to a second aspect embodiment of this application.

[0036] Some of the data in the above formula are calculated by removing dimensions and taking their numerical values. The formula is the closest to the real situation obtained by software simulation of a large amount of collected data. The preset parameters and preset thresholds in the formula are set by those skilled in the art according to the actual situation or obtained through simulation of a large amount of data.

[0037] The working principle of this application is as follows: Multi-source data is acquired along the target overhead line route; risk dimension indicators are generated based on the multi-source data; risk indicator weight coefficients are dynamically generated based on the risk dimension indicators; and line risk assessment results are generated based on the risk dimension indicators and risk indicator weight coefficients. This constructs a risk indicator system covering three dimensions: meteorology, electrical, and physical structure, overcoming the limitations of single-factor assessment. Simultaneously, the dynamic generation of weight coefficients based on the risk dimension indicators enables the assessment model to adapt to the complex and ever-changing characteristics of the mountainous environment, accurately reflecting the actual impact of various risk factors under different periods and operating conditions. The dynamic weights are combined with multi-dimensional indicators to generate assessment results, accurately depicting the coupling effect of multiple risk factors in the special mountainous environment. This fundamentally solves the problem of traditional methods, which suffer from large deviations between assessment results and actual operating conditions due to single dimensions and static rigidity, resulting in low accuracy. It improves the accuracy of overhead line risk assessment methods and avoids the problem that existing technologies often rely on single factors for assessment, failing to fully consider the coupling effect and dynamic characteristics of multiple risk factors in the mountainous environment, leading to large deviations between assessment results and actual operating conditions in mountainous areas, resulting in low accuracy of overhead line risk assessment methods.

[0038] The above embodiments are only used to illustrate the technical methods of this application and are not intended to limit it. Although this application has been described in detail with reference to preferred embodiments, those skilled in the art should understand that modifications or equivalent substitutions can be made to the technical methods of this application without departing from the spirit and scope of the technical methods of this application.

Claims

1. A risk assessment method for overhead lines based on mountain photovoltaic power stations, characterized in that, include: Acquire multi-source data along the target overhead line path; the multi-source data includes micro-topographic data of the line corridor, real-time micro-meteorological data, photovoltaic power output data, and line body status data; Risk dimension indicators are generated based on multi-source data; the risk dimension indicators include meteorological environment risk indicators, electrical operation risk indicators, and line body risk indicators. Risk indicator weight coefficients are dynamically generated based on risk dimension indicators. The route risk assessment results are generated based on risk dimension indicators and risk indicator weighting coefficients.

2. The method for risk assessment of overhead lines based on mountain photovoltaic power stations according to claim 1, characterized in that, The risk dimension indicators generated based on multi-source data include: Extract micro-topographical data of the railway corridor, real-time micro-meteorological data, photovoltaic power output data, and railway line status data from multi-source data; Meteorological and environmental risk indicators are obtained by dynamically correcting real-time micro-meteorological data using micro-topographical data of the route corridor. Electrical operation risk indicators were obtained by analyzing the spatiotemporal fluctuation characteristics of photovoltaic power output data. The risk indicators of the line body are obtained by analyzing the status data of the line body. Risk dimension indicators are determined based on meteorological environmental risk indicators, electrical operation risk indicators, and line body risk indicators.

3. The method for risk assessment of overhead lines based on mountain photovoltaic power stations according to claim 2, characterized in that, The method of dynamically correcting real-time micro-meteorological data using micro-topographical data of the railway corridor to obtain meteorological environmental risk indicators includes: Extract the tower base elevation (TH), tower location slope (TWP), tower location aspect (TWX), and terrain type (DL) from the micro-topographic data of the line corridor; Extract wind speed (FS), temperature (WD), humidity (SD), and ground flash density (DM) from real-time micrometeorological data; Several meteorological correction functions are constructed using the tower base elevation TH, tower location slope TWP, tower location aspect TWX, and terrain location index DWZ to correct wind speed, temperature, humidity, and ground flash density in real-time micro-meteorological data. The meteorological correction functions include wind speed correction function, temperature correction function, humidity correction function, and ground flash correction function. Corrected micro-meteorological data is obtained by substituting wind speed, temperature, humidity, and ground flash density from real-time micro-meteorological data into their respective meteorological correction functions; the corrected micro-meteorological data includes corrected wind speed, corrected temperature, corrected humidity, and corrected ground flash density. A meteorological risk quantification function is constructed; the meteorological risk quantification function includes a wind risk quantification function, a wildfire risk quantification function, and a lightning strike risk quantification function. The modified micro-meteorological data is input into the meteorological risk quantification function to obtain several meteorological environmental risk indicators; the meteorological environmental risk indicators include strong wind risk indicators, wildfire risk indicators and lightning strike risk indicators.

4. The method for risk assessment of overhead lines based on mountain photovoltaic power stations according to claim 2, characterized in that, The electrical operation risk indicators obtained by analyzing the spatiotemporal fluctuation characteristics of photovoltaic power output data include: Extract the line power P and harmonic distortion rate (THD) from the photovoltaic output data; The power volatility GBL is calculated using a formula; the formula satisfies: Where t represents the number corresponding to the time point; This is expressed as the line power at time point t; Represented as time intervals; Extract the time points where the power volatility is greater than the volatility threshold as the volatility time points; The ratio of several fluctuation points to a total of several other time points is statistically analyzed, and this ratio is used as the risk of tidal fluctuations. ; Calculate harmonic risk using formula The formula satisfies: ;in, This is expressed as the national standard limit for power grid harmonic distortion rate; Electrical operation risk indicators are determined based on power flow fluctuation risk and harmonic risk.

5. The method for risk assessment of overhead lines based on mountain photovoltaic power stations according to claim 2, characterized in that, The process of obtaining line-specific risk indicators through state analysis of line-specific status data includes: Obtain high-precision distribution maps of areas prone to geological disasters; Extract the tower location coordinates, tower tilt angle, number of defective insulator discs, number of broken conductor strands, and line commissioning years from the line body data; The risk level of the tower is determined by matching the tower location coordinates with a high-precision geological hazard susceptibility distribution map; the high-precision geological hazard susceptibility distribution map includes high-risk areas, medium-risk areas, and low-risk areas. The tower tilt angle, the number of defective insulator discs, and the number of broken conductor strands are respectively quantified to obtain tilt risk score, insulation defect score, and conductor damage score; The structural state risk is obtained by weighted summation of the tilt risk score, insulation defect score, and conductor damage score; An aging quantification function LHF(XTN) is constructed to characterize the nonlinear relationship between the line's service life (XTN) and its aging risk (XLF); the aging quantification function satisfies: ;in, This represents the threshold for the line's operational lifespan; k represents the attenuation coefficient, k>0; The aging risk XLF of the line is calculated by substituting the line's years of operation into the aging quantification function. The risk index of the line itself is calculated using a formula; the formula satisfies: Where max() represents the maximum value operation, and TFD represents the tower risk level. and Represented as weighting coefficients, and ∈(0,1), and and The sum is 1; This is represented as structural state risk.

6. The method for risk assessment of overhead lines based on mountain photovoltaic power stations according to claim 1, characterized in that, The dynamic generation of risk indicator weight coefficients based on risk dimension indicators includes: Obtain a series of historical risk dimension indicators corresponding to the risk dimension indicators; For risk dimension indicators Calculate the information entropy corresponding to the i-th indicator. Where i represents the indicator number in the risk dimension indicators; The objective weight corresponding to the i-th risk dimension indicator is calculated using the formula. The formula satisfies: Where j represents the indicator number in the risk dimension indicators, and ZBS represents the total number of indicators in the risk dimension indicators; Obtaining subjective weights The subjective weights are set by experts based on the importance of several risk dimension indicators for different assessment scenarios. The weighting coefficient of the theoretical risk indicator is calculated using the formula. The formula satisfies: ;in, This represents the evaluation scenario corresponding to the current time point t. This represents the subjective weight of the i-th risk dimension indicator in the assessment scenario at the current time point; This is represented as the adjustment coefficient corresponding to the i-th risk dimension indicator at the current time t when a weather warning is issued; Represented as the fusion coefficient, ∈(0,1); The risk indicator weight coefficients are obtained by performing a weight normalization operation on the weight coefficients of several theoretical risk indicators.

7. The method for risk assessment of overhead lines based on mountain photovoltaic power stations according to claim 1, characterized in that, The method for generating route risk assessment results based on risk dimension indicators and risk indicator weighting coefficients includes: Extract risk dimension indicators and risk indicator weighting coefficients; The comprehensive risk dimension value is obtained by weighting and summing the risk dimension indicators and their corresponding risk indicator weight coefficients. Integrate risk dimension indicators and comprehensive risk dimension values ​​into risk analysis data; Risk analysis data is input into the risk assessment model to obtain the line risk assessment result; the risk assessment model is constructed through an artificial intelligence model and is used to comprehensively assess the line risk results.

8. The method for risk assessment of overhead lines based on mountain photovoltaic power stations according to claim 7, characterized in that, The risk assessment model is constructed using an artificial intelligence model, including: Obtain a number of historical risk analysis data and their corresponding historical route risk assessment results; Several historical risk analysis data and their corresponding historical route risk assessment results are divided into training data, validation data, and test data; data preprocessing is performed on the training data, validation data, and test data to obtain the training set, validation set, and test set. Choose an artificial intelligence model as the base model; The base model is trained on the training set, and the learning rate and hyperparameters are adjusted on the validation set to obtain the pre-trained model. By validating the pre-trained model on the test set, a risk assessment model is finally obtained, which takes risk analysis data as input and outputs the line risk assessment results.

9. A risk assessment system for overhead lines based on mountain photovoltaic power stations, characterized in that, include: Data acquisition module and data analysis module; The data acquisition module and the data analysis module are connected; The data acquisition module acquires multi-source data along the target overhead line path using data acquisition equipment. The data analysis module includes an indicator quantification unit, a weight generation unit, and a result generation unit; The indicator quantification unit generates risk dimension indicators based on multi-source data. The weight generation unit dynamically generates risk indicator weight coefficients based on risk dimension indicators. The result generation unit generates route risk assessment results based on risk dimension indicators and risk indicator weighting coefficients.

10. A computer-readable storage medium, applied to the overhead line risk assessment system based on a mountain photovoltaic power station as described in claim 9, characterized in that, The computer program is stored on the computer-readable storage medium.

Images