A power system risk prediction system based on big data analysis

Abstract

The present invention discloses a power system risk prediction system based on big data analysis, which relates to the technical field of power system risk prediction. The system can predict potential risks and take preventive measures in advance by analyzing the deviation trend, temperature and vibration of the transmission line through the deviation risk prediction module and the second risk prediction module. The system establishes a geological data set, associates the geological density md with the extreme weather coefficient Jd and the deviation index Pyx, calculates the influence of the weather environment on the relative deviation, and obtains the first risk index Fxx, which can evaluate the influence of the geological density md, that is, the geological softness and extreme weather on the transmission line, and avoid line damage caused by foundation settlement or bad weather. And the first risk index Fxx is predicted and evaluated to obtain the first maintenance strategy; based on the risk prediction, the system can generate a targeted maintenance strategy to ensure effective protection against geological risks and extreme weather effects.

Description

Technical Field

[0001] The present invention relates to the technical field of power system risk prediction, and in particular to a power system risk prediction system based on big data analysis. Background Art

[0002] With the development of social economy and the acceleration of urbanization, the power transmission system has become one of the infrastructures of modern society. In the power transmission system, overhead transmission lines are important channels for transmitting electricity from power stations to substations and distribution stations.

[0003] In the Chinese invention patent with application number 202111409434.3, the invention discloses a transmission line wind speed monitoring system, including a pole tower, a wire, a fixing seat, a video monitoring device, a wind direction and speed detector, a positioning module, a communication module 1, a main controller, a line tension monitoring and adjustment device, and a line dancing monitoring device. Specifically, a transmission line wind speed monitoring system is provided, which is convenient for adjusting and detecting the tension of the wire, and is convenient for monitoring the dancing and wind deviation of the transmission line. The above monitoring method is mainly to monitor the wind deviation condition, which is convenient for early warning and adjustment of the power line. This wind speed monitoring and correction can indeed improve the risk of the transmission line in the power system. However, wind and rain will not only cause the transmission line to dance, but also the problem of pole displacement and settlement in the long run. The displacement and settlement are closely related to the softness of the geology. The softness of the geology and the soaking of rainwater can easily cause the foundation of the pole to settle, resulting in risks. When the pole is offset or settled, it may cause uneven tension of the transmission line, increasing the risk of line breakage or damage. Summary of the invention

[0004] 1. Technical issues to be resolved

[0005] In view of the deficiencies in the prior art, the present invention provides a power system risk prediction system based on big data analysis to solve the problems mentioned in the background technology.

[0006] (II) Technical solution

[0007] To achieve the above objectives, the present invention is implemented through the following technical solutions: a power system risk prediction system based on big data analysis, comprising:

[0008] The three-dimensional model building module uses GPS and GIS technology to collect information on a number of overhead power transmission lines and corresponding map information, build a three-dimensional map model, and draw the topological structure of the overhead power transmission lines, and mark the geographic coordinates of the overhead power transmission lines, towers, and poles in the three-dimensional map model as the first mark;

[0009] The regional division module is used to divide the transmission line into several areas in the three-dimensional map model according to the line length and population density characteristics, and set monitoring points in each area and set different collection frequencies;

[0010] A first monitoring module is used to install a first monitoring device at a monitoring point, monitor the environmental conditions of the overhead transmission lines in each area, construct an environmental condition data set, generate an extreme weather coefficient Jd from the environmental condition data set, and issue a first warning instruction if the extreme weather coefficient Jd exceeds a first danger threshold Q;

[0011] The deviation risk prediction module, after receiving the first warning instruction, establishes a risk prediction model, performs trend analysis on the deviation of the overhead transmission line, and if the relative deviation index Pyx obtained by the analysis does not meet expectations, obtains the geological density md around the overhead transmission line, establishes a geological data set, associates the geological density md with the extreme weather coefficient Jd and the deviation index Pyx, calculates the influence of the weather environment on the relative deviation, obtains the first risk index Fxx, and predicts and evaluates the first risk index Fxx to obtain the first maintenance strategy;

[0012] The second risk prediction module, after the execution of the first maintenance strategy, installs a second monitoring device at the monitoring point of each regional overhead transmission line, obtains the measured temperature Sw and measured vibration value Sz of the transmission line, and constructs a second risk data set; generates a second risk index Fxx2 from the second risk data set, and if the second risk index Fxx2 exceeds the second danger threshold Q2, issues a second early warning instruction; and matches the corresponding optimization plan in the power transmission line optimization knowledge graph pre-constructed by big data, executes the optimization plan, and optimizes the regional overhead transmission lines.

[0013] Preferably, the overhead power transmission line information includes a unique identification number of each power transmission line, line type, total line length, conductor cross-sectional area, and number of cross arms on each line, and a second mark is made on the three-dimensional map model;

[0014] The line types include high voltage, medium voltage and low voltage.

[0015] Preferably, the area division module includes a line length division unit and a population density division unit;

[0016] The line length division unit is used to divide the transmission line into a plurality of first areas with equal spacing of line length, and to set a first monitoring point in the first area;

[0017] The population density segmentation unit is used to collect the population density in the first monitoring point, obtain the population density value rkmd, and prioritize the population density values ​​rkmd from high to low, perform a third mark in the three-dimensional map model, compare the population density value rkmd with a preset population density threshold value X, and when the population density value rkmd ≥ the population density threshold value X, set the collection frequency in the first monitoring point to 60 seconds / 1-2 times;

[0018] When the population density value rkmd is less than the population density threshold X, the acquisition frequency in the first monitoring point is set to 120-180 seconds / 1-2 times.

[0019] Preferably, the environmental condition data set includes but is not limited to the following data: regional real-time wind speed Fs and regional real-time rainfall Jy; the regional real-time wind speed Fs is measured and obtained by the wind speed sensor in the first monitoring device, and the regional real-time rainfall Jy is measured and obtained by the rain gauge in the first monitoring device;

[0020] The extreme weather coefficient Jd is obtained by extracting the regional real-time wind speed Fs and the regional real-time rainfall Jy from the environmental condition data set, performing linear normalization on the regional real-time wind speed Fs and the regional real-time rainfall Jy, and mapping the corresponding data values ​​in the interval [0,1], and then generating the extreme weather coefficient Jd according to the following formula:

[0021]

[0022] in, The maximum wind speed load threshold allowed in the area; is the maximum rainfall load threshold allowed in the region; α and β weight coefficients: 0≤β≤1, 0≤α≤1, and α+β=1, where i=1, 2, …n, n is the number in the monitoring period, which is a positive integer greater than 1;

[0023] The extreme weather coefficient Jd is evaluated. If the extreme weather coefficient Jd exceeds the first danger threshold Q, it indicates that there is a risk of high wind speed and heavy rainfall, and the first warning instruction is issued; if the extreme weather coefficient Jd does not exceed the first danger threshold Q, it indicates that there is no risk of high wind speed and heavy rainfall.

[0024] Preferably, the deviation risk prediction module includes a risk prediction model establishment unit and a second acquisition unit;

[0025] The risk prediction model unit is used to establish a risk prediction model through linear regression, decision tree, random forest, support vector machine or neural network model, collect relevant data of overhead transmission lines, including line deviation, geological data, extreme weather data, and apply the risk prediction model after training and learning;

[0026] The second acquisition unit collects the offset data of the overhead transmission line through an angle sensor and a distance sensor, including the original yaw angle value Phj1 of the tower or the pole, the real-time yaw angle value Phj2, the original distance value JL1 of the adjacent tower, the real-time distance value JL2 of the adjacent tower, the original height Gd1 of the tower, and the real-time sinking height Gd2 of the tower. After dimensionless processing of the above data, the offset index Pyx is generated by the following formula:

[0027]

[0028] In the formula, Indicates the preset tower or pole yaw angle difference threshold. Indicates the difference threshold of the distance between adjacent towers. represents the tower sinking height difference threshold, w1, w2 and w3 represent weight values, and w1+w2+w3=1.0; 0≤w1≤1, 0≤w2≤1, 0≤w3≤1, A represents the first correction constant.

[0029] Preferably, the migration risk prediction module further includes a geological acquisition unit and a first evaluation unit;

[0030] The geological acquisition unit is used to acquire the geological density md around the overhead transmission line through soil sensors to establish a geological data set if the relative offset index Pyx obtained by analysis does not meet expectations;

[0031] The geological density md is correlated with the extreme weather coefficient Jd and the excursion index Pyx, the influence of the weather environment on the relative excursion is calculated, and the first risk index Fxx is obtained:

[0032]

[0033] in, is the influence factor of extreme weather coefficient Jd on the excursion index Pyx, is the influence factor of geological density md on the offset index Pyx; ψ1 and ψ2 are weight coefficients, and 0≤ψ1≤1, 0≤ψ2≤1;

[0034] The first evaluation unit is used to compare the first risk index Fxx with the first risk threshold I. If the first risk index Fxx ≥ the first risk threshold I, it means that the offset is highly affected by weather and geology, and geological protection is required. A first protection strategy is generated to reinforce the deep foundation piles of the regional electric poles, install waterproof barriers around the electric poles, and install retaining walls in the landslide or debris flow area to prevent soil movement from causing unstable foundations of electric poles;

[0035] If the first risk index Fxx is less than the first risk threshold I, indicating that the risk is low, the monitoring data should still be recorded and analyzed regularly to determine trends and changes.

[0036] Preferably, the second risk prediction module includes a third collection unit and a third summary unit;

[0037] The third acquisition unit is used to install thermal imaging scanning equipment and vibration sensors in the monitoring points of the power transmission lines in each area, and respectively obtain the measured temperature Sw and the measured vibration value Sz of the power transmission line during power transmission;

[0038] Cyclic scanning of the temperature distribution of the overhead transmission line, including the temperature of the connection, joint, and insulator position, to obtain the measured temperature Sw of the transmission line;

[0039] Monitor the vibration of the iron tower or electric pole in the overhead transmission line in each monitoring cycle to obtain the measured vibration value Sz;

[0040] The third summarizing unit is used to summarize the measured temperature Sw and measured vibration value Sz of the transmission line obtained through monitoring after several consecutive monitoring cycles, so as to construct a second risk data set.

[0041] Preferably, the second risk prediction module further includes a second calculation unit and a second evaluation unit;

[0042] The second calculation unit is used to extract the measured temperature Sw and the measured vibration value Sz of the transmission line in the second risk data set, perform linear normalization processing on the measured temperature Sw and the measured vibration value Sz of the transmission line, and map the corresponding data values ​​in the interval [0,1], and then generate the second risk index Fxx2 according to the following formula:

[0043]

[0044] in, To set the maximum temperature threshold allowed in the area; is the maximum vibration intensity threshold allowed in the area; γ and δ weight coefficients: 0≤γ≤1, 0≤δ≤1, and γ+δ=1, where i=1, 2, …m, m is the number in the monitoring period, which is a positive integer greater than 1;

[0045] The second evaluation unit is used to compare and evaluate the second risk index Fxx2 and the second danger threshold Q2 to obtain a second evaluation result, including:

[0046] If the second risk index Fxx2 ≥ the second danger threshold Q2, the data point is marked as the second risk data point, indicating that the temperature and vibration are abnormal, and a second warning instruction is issued;

[0047] If the second risk index Fxx2 is less than the second danger threshold Q2, it indicates that there is no abnormal risk in temperature and vibration. The monitoring data should still be recorded and analyzed regularly to determine trends and changes.

[0048] Preferably, the second risk prediction module further includes a knowledge graph construction unit and a matching unit;

[0049] The knowledge graph unit is used to capture the power transmission line optimization knowledge graph through big data, which contains relevant knowledge about power transmission lines, including common problems, risk types, optimization strategies and best practices;

[0050] Obtain events, failure cases, and successful optimization cases related to power transmission lines from historical data of the power system;

[0051] Construct a relational network to connect various related concepts and information; including nodes and edges, reflecting the relationship between various parts in the power system;

[0052] The matching unit is used to indicate that there is a risk of abnormal temperature and vibration of the transmission line when the second early warning instruction is triggered, and to match the corresponding optimization plan in the knowledge graph. The optimization plan includes: repairing the second risk data point, replacing parts with loose, oxidized or poor contact of line joints, and reinforcing the connections with anti-corrosion materials, and replacing and installing shock-absorbing devices if the insulation is damaged.

[0053] Preferably, a backup power module is also included. When the plan is executed after the first warning instruction and the second warning instruction are received, during the power outage maintenance of the regional overhead transmission line, backup power supply is provided through the backup power module to continue supplying power in case the main line is damaged.

[0054] (III) Beneficial effects

[0055] The present invention provides a power system risk prediction system based on big data analysis. It has the following beneficial effects:

[0056] (1) The deviation risk prediction module and the second risk prediction module can predict potential risks and take preventive measures in advance by analyzing the deviation trend, temperature and vibration of the transmission line. The system establishes a geological data set and associates it with the extreme weather coefficient and the deviation index. It can evaluate the impact of geological density md, that is, geological softness and extreme weather on the transmission line, and avoid line damage caused by foundation settlement or bad weather. The geological density md is associated with the extreme weather coefficient Jd and the deviation index Pyx, and the degree of influence of the weather environment on the relative deviation is calculated to obtain the first risk index Fxx, and the first risk index Fxx is predicted and evaluated to obtain the first maintenance strategy; based on risk prediction, the system can generate targeted maintenance strategies to ensure effective protection against geological risks and extreme weather impacts.

[0057] (2) By dividing the line length at equal intervals, it is possible to ensure that the monitoring points in each area are relatively uniform, facilitating comprehensive monitoring of the entire line. This approach helps identify potential risks in each area. Considering population density as a factor in dividing areas helps identify high-density areas. These areas generally require higher security and monitoring frequency to reduce potential risks to residents and infrastructure. The collection frequency of monitoring points is adjusted based on the priority of population density. This helps to devote more resources to high-risk areas and improve the effectiveness of monitoring.

[0058] (3) This is a power system risk prediction system based on big data analysis. The deviation risk prediction module includes a risk prediction model unit, a second acquisition unit, a geological acquisition unit and a first evaluation unit, which can monitor and predict the deviation risk of overhead transmission lines through various means. Through comprehensive monitoring and risk prediction, the system can effectively reduce the risk of pole deviation and settlement and ensure the safety of transmission lines. When Fxx≥the first risk threshold I, the system generates a first protection strategy. This may include strengthening the foundation, installing waterproof barriers and retaining walls, etc. to ensure the stability of poles and transmission lines.

[0059] (4) Through thermal imaging equipment, the system can accurately monitor the temperature distribution of transmission lines, especially key parts such as joints, connectors, and insulators. This process can help identify potential hot spots and prevent risks caused by abnormal temperatures. Vibration sensors can monitor the vibration conditions of overhead transmission lines, including the vibration of towers and poles. This helps detect line sway, loose structures, and other conditions that may cause line damage. The second risk index Fxx2 is calculated using temperature and vibration data, providing a comprehensive way to assess risks. This risk index reflects the status of the line in terms of temperature and vibration. If Fxx2 ≥ Q2, the system will issue a second warning instruction. This warning mechanism can promptly remind relevant personnel to take action to avoid accidents caused by abnormal temperature and vibration. BRIEF DESCRIPTION OF THE DRAWINGS

[0060] Figure 1 This is a schematic diagram of a block diagram of a power system risk prediction system based on big data analysis in the present invention. DETAILED DESCRIPTION

[0061] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0062] Example 1

[0063] See also Figure 1 The present invention provides a power system risk prediction system based on big data analysis, comprising:

[0064] The three-dimensional model building module uses GPS and GIS technology to collect information on a number of overhead power transmission lines and corresponding map information, build a three-dimensional map model, and draw the topological structure of the overhead power transmission lines, and mark the geographic coordinates of the overhead power transmission lines, towers, and poles in the three-dimensional map model as the first mark;

[0065] The regional division module is used to divide the transmission line into several areas in the three-dimensional map model according to the line length and population density characteristics, and set monitoring points in each area and set different collection frequencies;

[0066] A first monitoring module is used to install a first monitoring device at a monitoring point, monitor the environmental conditions of the overhead transmission lines in each area, construct an environmental condition data set, generate an extreme weather coefficient Jd from the environmental condition data set, and issue a first warning instruction if the extreme weather coefficient Jd exceeds a first danger threshold Q;

[0067] The deviation risk prediction module, after receiving the first warning instruction, establishes a risk prediction model, performs trend analysis on the deviation of the overhead transmission line, and if the relative deviation index Pyx obtained by the analysis does not meet expectations, obtains the geological density md around the overhead transmission line, establishes a geological data set, associates the geological density md with the extreme weather coefficient Jd and the deviation index Pyx, calculates the influence of the weather environment on the relative deviation, obtains the first risk index Fxx, and predicts and evaluates the first risk index Fxx to obtain the first maintenance strategy;

[0068] The second risk prediction module, after the execution of the first maintenance strategy, installs a second monitoring device at the monitoring point of each regional overhead transmission line, obtains the measured temperature Sw and measured vibration value Sz of the transmission line, and constructs a second risk data set; generates a second risk index Fxx2 from the second risk data set, and if the second risk index Fxx2 exceeds the second danger threshold Q2, issues a second early warning instruction; and matches the corresponding optimization plan in the power transmission line optimization knowledge graph pre-constructed by big data, executes the optimization plan, and optimizes the regional overhead transmission lines.

[0069] In this embodiment, by installing monitoring equipment, the wind speed and rainfall key parameters of the transmission line are monitored in real time to build an environmental condition data set, which enables the system to issue the first warning instruction in time before extreme weather occurs.

[0070] The deviation risk prediction module and the second risk prediction module can predict potential risks and take preventive measures in advance by analyzing the deviation trend, temperature and vibration of the transmission line. The system establishes a geological data set and associates it with the extreme weather coefficient and the deviation index. It can evaluate the impact of geological density md, that is, geological softness and extreme weather on the transmission line to avoid line damage caused by foundation settlement or severe weather. The geological density md is associated with the extreme weather coefficient Jd and the deviation index Pyx, and the degree of influence of the weather environment on the relative deviation is calculated to obtain the first risk index Fxx, and the first risk index Fxx is predicted and evaluated to obtain the first maintenance strategy; based on risk prediction, the system can generate targeted maintenance strategies to ensure effective protection against geological risks and extreme weather impacts.

[0071] Example 2: This example is an explanation of Example 1. Figure 1 Specifically, the overhead transmission line information includes, uniquely identifying each transmission line number, line type, total line length, conductor cross-sectional area, and the number of cross arms on each line, and making a second mark on the three-dimensional map model;

[0072] The line types include high voltage, medium voltage and low voltage.

[0073] In this embodiment, each transmission line has a unique number to ensure accurate identification of each line. This helps with management and monitoring and prevents confusion. Differentiating between high-voltage, medium-voltage, and low-voltage lines facilitates analysis and management of different types of lines. High-voltage lines generally require more stringent monitoring, while medium-voltage and low-voltage lines may require different maintenance strategies. Making a second mark in the 3D map model to mark these key points can provide the exact location of the transmission line. This can help identify geographic risks, optimize line layout, and plan monitoring point locations.

[0074] Example 3: In the prior art, regional division is usually based on simple geographical location or power load, without considering more complex factors such as population density and line length. As a result, it is difficult to set appropriate monitoring frequency and maintenance strategy according to the characteristics of specific areas. This example is explained in Example 1, please refer to Figure 1 ,Specifically, the area division module includes a line length segmentation unit and a population density segmentation unit;

[0075] The line length division unit is used to divide the transmission line into a plurality of first areas with equal spacing of line length, and to set a first monitoring point in the first area;

[0076] The population density segmentation unit is used to collect the population density in the first monitoring point, obtain the population density value rkmd, and prioritize the population density values ​​rkmd from high to low, perform a third mark in the three-dimensional map model, compare the population density value rkmd with a preset population density threshold value X, and when the population density value rkmd ≥ the population density threshold value X, set the collection frequency in the first monitoring point to 60 seconds / 1-2 times;

[0077] When the population density value rkmd is less than the population density threshold X, the acquisition frequency in the first monitoring point is set to 120-180 seconds / 1-2 times.

[0078] In this embodiment, by dividing the line length at equal intervals, it is possible to ensure that the monitoring points in each area are relatively uniform, which facilitates comprehensive monitoring of the entire line. This approach helps to identify potential risks in each area. Considering population density as a factor in dividing areas helps to identify areas with high population density. These areas generally require higher security and monitoring frequency to reduce potential risks to residents and infrastructure. The collection frequency of monitoring points is adjusted based on the priority of population density. This helps to devote more resources to high-risk areas and improve the effectiveness of monitoring.

[0079] Example 4: This example is an explanation of Example 1. Figure 1 Specifically, the environmental condition data set includes but is not limited to the following data: regional real-time wind speed Fs and regional real-time rainfall Jy; the regional real-time wind speed Fs is obtained by measuring the wind speed sensor in the first monitoring device, and the regional real-time rainfall Jy is obtained by measuring the rain gauge in the first monitoring device;

[0080] The extreme weather coefficient Jd is obtained by extracting the regional real-time wind speed Fs and the regional real-time rainfall Jy from the environmental condition data set, performing linear normalization on the regional real-time wind speed Fs and the regional real-time rainfall Jy, and mapping the corresponding data values ​​in the interval [0,1], and then generating the extreme weather coefficient Jd according to the following formula:

[0081]

[0082] in, The maximum wind speed load threshold allowed in the area; is the maximum rainfall load threshold allowed in the region; α and β weight coefficients: 0≤β≤1, 0≤α≤1, and α+β=1, where i=1, 2, …n, n is the number in the monitoring period, which is a positive integer greater than 1;

[0083] The extreme weather coefficient Jd is evaluated. If the extreme weather coefficient Jd exceeds the first danger threshold Q, it indicates that there is a risk of high wind speed and heavy rainfall, and the first warning instruction is issued; if the extreme weather coefficient Jd does not exceed the first danger threshold Q, it indicates that there is no risk of high wind speed and heavy rainfall.

[0084] In this embodiment, through real-time monitoring and calculation of the extreme weather coefficient Jd, the system can issue a first warning instruction in time before extreme weather conditions occur, providing the power company with sufficient time to take countermeasures.

[0085] Example 5: This example is explained in Example 1. Figure 1 ,Specifically, the offset risk prediction module includes a risk prediction model establishment unit and a second acquisition unit;

[0086] The risk prediction model unit is used to establish a risk prediction model through linear regression, decision tree, random forest, support vector machine or neural network model, collect relevant data of overhead transmission lines, including line deviation, geological data, extreme weather data, and apply the risk prediction model after training and learning;

[0087] The second acquisition unit collects the offset data of the overhead transmission line through an angle sensor and a distance sensor, including the original yaw angle value Phj1 of the tower or the pole, the real-time yaw angle value Phj2, the original distance value JL1 of the adjacent tower, the real-time distance value JL2 of the adjacent tower, the original height Gd1 of the tower, and the real-time sinking height Gd2 of the tower. After dimensionless processing of the above data, the offset index Pyx is generated by the following formula:

[0088]

[0089] In the formula, Indicates the preset tower or pole yaw angle difference threshold. Indicates the difference threshold of the distance between adjacent towers. represents the tower sinking height difference threshold, w1, w2 and w3 represent weight values, and w1+w2+w3=1.0; 0≤w1≤1, 0≤w2≤1, 0≤w3≤1, A represents the first correction constant. The deviation index Pyx is used to monitor the deviation status of the line;

[0090] Specifically, the migration risk prediction module also includes a geological acquisition unit and a first evaluation unit;

[0091] The geological acquisition unit is used to acquire the geological density md around the overhead transmission line through soil sensors if the relative offset index Pyx obtained by analysis does not meet expectations, and to establish a geological data set; this method can identify geological softness and foundation settlement problems;

[0092] The geological density md is correlated with the extreme weather coefficient Jd and the excursion index Pyx, the influence of the weather environment on the relative excursion is calculated, and the first risk index Fxx is obtained:

[0093]

[0094] in, is the influence factor of extreme weather coefficient Jd on the excursion index Pyx, It is the influence factor of geological density md on the offset index Pyx; ψ1 and ψ2 are weight coefficients, and 0≤ψ1≤1, 0≤ψ2≤1; the system can calculate the influence of weather and geological factors on offset. This analysis helps to determine potential offset risks.

[0095] The first evaluation unit is used to compare the first risk index Fxx with the first risk threshold I. If the first risk index Fxx ≥ the first risk threshold I, it means that the offset is highly affected by weather and geology, and geological protection is required. A first protection strategy is generated to reinforce the deep foundation piles of the regional electric poles, install waterproof barriers around the electric poles, and install retaining walls in the landslide or debris flow area to prevent soil movement from causing unstable foundations of electric poles;

[0096] If the first risk index Fxx is less than the first risk threshold I, indicating that the risk is low, the monitoring data should still be recorded and analyzed regularly to determine trends and changes.

[0097] In this embodiment, the deviation risk prediction module includes a risk prediction model unit, a second acquisition unit, a geological acquisition unit and a first evaluation unit, which can monitor and predict the deviation risk of overhead transmission lines through various means. Through comprehensive monitoring and risk prediction, the system can effectively reduce the risk of pole deviation and settlement and ensure the safety of transmission lines. When Fxx≥the first risk threshold I, the system generates a first protection strategy. This may include strengthening the foundation, installing waterproof barriers and retaining walls, etc. to ensure the stability of poles and transmission lines.

[0098] Example 6: This example is explained in Example 1. Figure 1 ,Specifically, the second risk prediction module includes a third collection unit and a third summary unit;

[0099] The third acquisition unit is used to install thermal imaging scanning equipment and vibration sensors in the monitoring points of the power transmission lines in each area, and respectively obtain the measured temperature Sw and the measured vibration value Sz of the power transmission line during power transmission;

[0100] Cyclic scanning of the temperature distribution of the overhead transmission line, including the temperature of the connection, joint, and insulator position, to obtain the measured temperature Sw of the transmission line;

[0101] Monitor the vibration of the iron tower or electric pole in the overhead transmission line in each monitoring cycle to obtain the measured vibration value Sz;

[0102] The third summarizing unit is used to summarize the measured temperature Sw and measured vibration value Sz of the transmission line obtained through monitoring after several consecutive monitoring cycles, so as to construct a second risk data set.

[0103] Specifically, the second risk prediction module further includes a second calculation unit and a second evaluation unit;

[0104] The second calculation unit is used to extract the measured temperature Sw and the measured vibration value Sz of the transmission line in the second risk data set, perform linear normalization processing on the measured temperature Sw and the measured vibration value Sz of the transmission line, and map the corresponding data values ​​in the interval [0,1], and then generate the second risk index Fxx2 according to the following formula:

[0105]

[0106] in, To set the maximum temperature threshold allowed in the area; is the maximum vibration intensity threshold allowed in the area; γ and δ weight coefficients: 0≤γ≤1, 0≤δ≤1, and γ+δ=1, where i=1, 2, …m, m is the number in the monitoring period, which is a positive integer greater than 1;

[0107] The second evaluation unit is used to compare and evaluate the second risk index Fxx2 and the second danger threshold Q2 to obtain a second evaluation result, including:

[0108] If the second risk index Fxx2 ≥ the second danger threshold Q2, the data point is marked as the second risk data point, indicating that the temperature and vibration are abnormal, and a second warning instruction is issued;

[0109] If the second risk index Fxx2 is less than the second danger threshold Q2, it indicates that there is no abnormal risk in temperature and vibration. The monitoring data should still be recorded and analyzed regularly to determine trends and changes.

[0110] In this embodiment, through thermal imaging equipment, the system can accurately monitor the temperature distribution of the transmission line, especially key parts such as joints, connectors, insulators, etc. This process can help identify potential hot spots and prevent risks caused by abnormal temperatures. Vibration sensors can monitor the vibration conditions of overhead transmission lines, including vibrations of towers and poles. This helps detect situations such as line dancing and loose structures that may cause line damage. The second risk index Fxx2 is calculated using temperature and vibration data, providing a comprehensive way to assess risks. This risk index reflects the status of the line in terms of temperature and vibration. If Fxx2≥Q2, the system will issue a second early warning instruction. This early warning mechanism can promptly remind relevant personnel to take action to avoid accidents caused by abnormal temperature and vibration.

[0111] Example 7, this example is explained in Example 6, please refer to Figure 1 ,Specifically, the second risk prediction module also includes a knowledge graph construction unit and a matching unit;

[0112] The knowledge graph unit is used to capture the power transmission line optimization knowledge graph through big data, which contains relevant knowledge about power transmission lines, including common problems, risk types, optimization strategies and best practices;

[0113] Obtain events, failure cases, and successful optimization cases related to power transmission lines from historical data of the power system;

[0114] Construct a relational network to connect various related concepts and information; including nodes and edges, reflecting the relationship between various parts in the power system;

[0115] The matching unit is used to indicate that there is a risk of abnormal temperature and vibration of the transmission line when the second early warning instruction is triggered, and to match the corresponding optimization plan in the knowledge graph. The optimization plan includes: repairing the second risk data point, replacing parts with loose, oxidized or poor contact of line joints, and reinforcing the connections with anti-corrosion materials, and replacing and installing shock-absorbing devices if the insulation is damaged.

[0116] In this embodiment, when the matching unit triggers the second warning instruction, it automatically matches the corresponding optimization plan according to the information in the knowledge graph. This intelligent matching method ensures that the system can quickly find a suitable solution when a risk occurs. The optimization plan can be customized according to the specific risk type, such as replacing parts with loose, oxidized or poor contact of line joints, or reinforcing the joints with anti-corrosion materials. This targeted optimization strategy helps to quickly solve problems and reduce risks. The knowledge graph unit obtains events, failure cases and successful optimization cases related to power transmission lines from the historical data of the power system through big data capture. This knowledge acquisition method based on big data can continuously enrich the knowledge graph and ensure the timely update of its content. Through intelligent risk matching and response, the system can take quick action after triggering an early warning to ensure the stability of the power transmission line.

[0117] Example 8, this example is explained in Example 1, please refer to Figure 1 Specifically, it also includes a backup power module. When the first warning instruction and the second warning instruction are received and the plan is executed, during the power outage maintenance of the regional overhead transmission line, the backup power module is used to provide backup power to prevent the main line from being damaged and continue to supply power.

[0118] In this embodiment, the backup power module provides backup power supply when the main line is out of power for maintenance, ensuring the continuous power supply of key loads and important equipment. This helps to maintain normal social and economic activities and prevent major losses caused by power outages. During maintenance or accidents, the backup power module can prevent large-scale power outages and reduce the vulnerability of the power system. This redundant design improves the reliability of the power system. When an early warning instruction is received and a power outage is required for maintenance, the backup power module can ensure the stability of the emergency response and ensure that key power services can still be provided during maintenance.

[0119] Although embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that various changes, modifications, substitutions and variations may be made to the embodiments without departing from the principles and spirit of the present invention, and that the scope of the present invention is defined by the appended claims and their equivalents.

Claims

1. A power system risk prediction system based on big data analysis, characterized by: include, The three-dimensional model building module uses GPS and GIS technology to collect information on a number of overhead power transmission lines and corresponding map information, build a three-dimensional map model, and draw the topological structure of the overhead power transmission lines, and mark the geographic coordinates of the overhead power transmission lines, towers, and poles in the three-dimensional map model as the first mark; The regional division module is used to divide the transmission line into several areas in the three-dimensional map model according to the line length and population density characteristics, and set monitoring points in each area and set different collection frequencies; A first monitoring module is used to install a first monitoring device at a monitoring point, monitor the environmental conditions of the overhead transmission lines in each area, construct an environmental condition data set, generate an extreme weather coefficient Jd from the environmental condition data set, and issue a first warning instruction if the extreme weather coefficient Jd exceeds a first danger threshold Q; The environmental condition data set includes but is not limited to the following data: regional real-time wind speed Fs and regional real-time rainfall Jy; the regional real-time wind speed Fs is obtained by measuring the wind speed sensor in the first monitoring device, and the regional real-time rainfall Jy is obtained by measuring the rain gauge in the first monitoring device; The extreme weather coefficient Jd is obtained by extracting the regional real-time wind speed Fs and the regional real-time rainfall Jy from the environmental condition data set, performing linear normalization on the regional real-time wind speed Fs and the regional real-time rainfall Jy, and mapping the corresponding data values ​​in the interval [0,1], and then generating the extreme weather coefficient Jd according to the following formula: in, The maximum wind speed load threshold allowed in the area; is the maximum rainfall load threshold allowed in the region; α and β weight coefficients: 0≤β≤1, 0≤α≤1, and α+β=1, where i=1, 2, …n, n is the number in the monitoring period, which is a positive integer greater than 1; The extreme weather coefficient Jd is evaluated. If the extreme weather coefficient Jd exceeds the first danger threshold Q, it indicates that there is a risk of high wind speed and heavy rainfall, and the first warning instruction is issued; if the extreme weather coefficient Jd does not exceed the first danger threshold Q, it indicates that there is no risk of high wind speed and heavy rainfall; The deviation risk prediction module, after receiving the first warning instruction, establishes a risk prediction model, performs trend analysis on the deviation of the overhead transmission line, and if the relative deviation index Pyx obtained by the analysis does not meet expectations, obtains the geological density md around the overhead transmission line, establishes a geological data set, associates the geological density md with the extreme weather coefficient Jd and the deviation index Pyx, calculates the influence of the weather environment on the relative deviation, obtains the first risk index Fxx, and predicts and evaluates the first risk index Fxx to obtain the first maintenance strategy; The deviation risk prediction module includes a risk prediction model establishment unit and a second acquisition unit; The risk prediction model unit is used to establish a risk prediction model through linear regression, decision tree, random forest, support vector machine or neural network model, collect relevant data of overhead transmission lines, including line deviation, geological data, extreme weather data, and apply the risk prediction model after training and learning; The second acquisition unit collects the offset data of the overhead transmission line through an angle sensor and a distance sensor, including the original yaw angle value Phj1 of the tower or the pole, the real-time yaw angle value Phj2, the original distance value JL1 of the adjacent tower, the real-time distance value JL2 of the adjacent tower, the original height Gd1 of the tower, and the real-time sinking height Gd2 of the tower. After dimensionless processing of the above data, the offset index Pyx is generated by the following formula: In the formula, Indicates the preset tower or pole yaw angle difference threshold. Indicates the difference threshold of the distance between adjacent towers. represents the tower sinking height difference threshold, w1, w2 and w3 represent weight values, and w1+w2+w3=1.0; 0≤w1≤1, 0≤w2≤1, 0≤w3≤1, A represents the first correction constant; The migration risk prediction module also includes a geological acquisition unit and a first evaluation unit; The geological acquisition unit is used to acquire the geological density md around the overhead transmission line through soil sensors to establish a geological data set if the relative offset index Pyx obtained by analysis does not meet expectations; The geological density md is correlated with the extreme weather coefficient Jd and the excursion index Pyx, the influence of the weather environment on the relative excursion is calculated, and the first risk index Fxx is obtained: in, is the influence factor of extreme weather coefficient Jd on the excursion index Pyx, is the influence factor of geological density md on the offset index Pyx; ψ1 and ψ2 are weight coefficients, and 0≤ψ1≤1, 0≤ψ2≤1; The first evaluation unit is used to compare the first risk index Fxx with the first risk threshold I. If the first risk index Fxx ≥ the first risk threshold I, it means that the offset is highly affected by weather and geology, and geological protection is required. A first protection strategy is generated to reinforce the deep foundation piles of the regional electric poles, install waterproof barriers around the electric poles, and install retaining walls in the landslide or debris flow area to prevent soil movement from causing unstable foundations of electric poles; If the first risk index Fxx is less than the first risk threshold I, indicating a low risk, the monitoring data should still be recorded and analyzed regularly to identify trends and changes; The second risk prediction module, after the first maintenance strategy is executed, installs a second monitoring device at the monitoring point of each regional overhead transmission line, obtains the measured temperature Sw and the measured vibration value Sz of the transmission line, and constructs a second risk data set; generates a second risk index Fxx2 from the second risk data set, and issues a second early warning instruction if the second risk index Fxx2 exceeds the second danger threshold Q2; and matches the corresponding optimization scheme in the power transmission line optimization knowledge graph pre-constructed by big data, executes the optimization scheme, and optimizes the regional overhead transmission line; The second risk prediction module also includes a knowledge graph construction unit and a matching unit; The knowledge graph unit is used to capture the power transmission line optimization knowledge graph through big data, which contains relevant knowledge about power transmission lines, including common problems, risk types, optimization strategies and best practices; Obtain events, failure cases, and successful optimization cases related to power transmission lines from historical data of the power system; Construct a relational network to connect various related concepts and information; including nodes and edges, reflecting the relationship between various parts in the power system; The matching unit is used to indicate that there is a risk of abnormal temperature and vibration of the transmission line when the second early warning instruction is triggered, and to match the corresponding optimization plan in the knowledge graph. The optimization plan includes: repairing the second risk data point, replacing parts with loose, oxidized or poor contact of line joints, and reinforcing the connections with anti-corrosion materials, and replacing and installing shock-absorbing devices if the insulation is damaged.

2. The power system risk prediction system based on big data analysis according to claim 1, characterized in that: The overhead power transmission line information includes unique identification of each power transmission line number, line type, total line length, conductor cross-sectional area, and number of cross arms on each line, and a second mark is made on the three-dimensional map model; The line types include high voltage, medium voltage and low voltage.

3. The power system risk prediction system based on big data analysis according to claim 1 is characterized by: The area division module includes a route length division unit and a population density division unit; The line length division unit is used to divide the transmission line into a plurality of first areas with equal spacing of line length, and to set a first monitoring point in the first area; The population density segmentation unit is used to collect the population density in the first monitoring point, obtain the population density value rkmd, and prioritize the population density values ​​rkmd from high to low, perform a third mark in the three-dimensional map model, compare the population density value rkmd with a preset population density threshold value X, and when the population density value rkmd ≥ the population density threshold value X, set the collection frequency in the first monitoring point to 60 seconds / 1-2 times; When the population density value rkmd is less than the population density threshold X, the acquisition frequency in the first monitoring point is set to 120-180 seconds / 1-2 times.

4. The power system risk prediction system based on big data analysis according to claim 1 is characterized by: The second risk prediction module includes a third collection unit and a third summary unit; The third acquisition unit is used to install thermal imaging scanning equipment and vibration sensors in the monitoring points of the power transmission lines in each area, and respectively obtain the measured temperature Sw and the measured vibration value Sz of the power transmission line during power transmission; Cyclic scan of the temperature distribution of the overhead transmission line, including the temperature of the connection, joint, and insulator position, to obtain the measured temperature Sw of the transmission line; Monitor the vibration of the iron tower or electric pole in the overhead transmission line in each monitoring cycle to obtain the measured vibration value Sz; The third summarizing unit is used to summarize the measured temperature Sw and measured vibration value Sz of the transmission line obtained through monitoring after several consecutive monitoring cycles, so as to construct a second risk data set.

5. The power system risk prediction system based on big data analysis according to claim 4 is characterized by: The second risk prediction module also includes a second calculation unit and a second evaluation unit; The second calculation unit is used to extract the measured temperature Sw and the measured vibration value Sz of the transmission line in the second risk data set, perform linear normalization processing on the measured temperature Sw and the measured vibration value Sz of the transmission line, and map the corresponding data values ​​in the interval [0,1], and then generate the second risk index Fxx2 according to the following formula: in, To set the maximum temperature threshold allowed in the area; is the maximum vibration intensity threshold allowed in the area; γ and δ weight coefficients: 0≤γ≤1, 0≤δ≤1, and γ+δ=1, where i=1, 2, …m, m is the number in the monitoring period, which is a positive integer greater than 1; The second evaluation unit is used to compare and evaluate the second risk index Fxx2 and the second danger threshold Q2 to obtain a second evaluation result, including: If the second risk index Fxx2 ≥ the second danger threshold Q2, the data point is marked as the second risk data point, indicating that the temperature and vibration are abnormal, and a second warning instruction is issued; If the second risk index Fxx2 is less than the second danger threshold Q2, it indicates that there is no abnormal risk in temperature and vibration. The monitoring data should still be recorded and analyzed regularly to determine trends and changes.

6. The power system risk prediction system based on big data analysis according to claim 5 is characterized by: It also includes a backup power module. When the plan is executed after the first warning instruction and the second warning instruction are received, the backup power module is used to provide backup power during the power outage maintenance of the regional overhead transmission lines to ensure that power can continue to be supplied when the main line is damaged.

Images