Power transmission line early warning system based on multi-modal data analysis

Abstract

The invention discloses a power transmission line early warning system based on multi-modal data analysis, and particularly relates to the technical field of power transmission line monitoring. Comprising a power transmission line monitoring and early warning center module, a power transmission line data acquisition module, a power transmission line multi-modal data analysis module, a power transmission line early warning model construction module, a power transmission line early warning comprehensive analysis module and a power transmission line early warning man-machine interaction module. The power transmission line data acquisition module acquires power transmission line data from a power transmission line early warning database through a sensor technology to obtain multi-modal monitoring data for analyzing power transmission line early warning, and transmits the multi-modal monitoring data to the power transmission line multi-modal data analysis module; through the multi-modal data analysis technology, the environment parameters, the line parameters and the image monitoring parameters of the power transmission line are monitored and analyzed in real time, the operation state and the potential risk of the power transmission line can be reflected more comprehensively, and the accuracy and the reliability of the early warning system are improved.

Description

Technical Field

[0001] The present invention relates to the technical field of power transmission line monitoring, and in particular to a power transmission line early warning system based on multimodal data analysis. Background Art

[0002] Multimodal data analysis technology is an information processing technology that integrates multiple types of data. It aims to obtain more comprehensive and accurate information by comprehensively analyzing different types of data. Transmission lines are an important part of the power system. With the continuous growth of electricity demand, their safe and stable operation is directly related to the reliability of the entire power grid. Multimodal data analysis can comprehensively consider information from different aspects, thereby more comprehensively reflecting the operating status and potential risks of transmission lines.

[0003] In the field of power transmission line monitoring technology, most power transmission lines are built in complex and changeable natural environments, which are easily affected by weather, terrain, human factors and other factors, resulting in frequent failures. The traditional power transmission line monitoring method is that the operation and maintenance personnel regularly conduct field inspections of the transmission lines, and then analyze and model based on a single type of data source, such as relying only on environmental parameters such as temperature and humidity or the electrical parameters of the line itself, and finally judge and predict potential safety hazards based on their own work experience and understanding of the transmission lines.

[0004] Although the traditional early warning method for transmission lines can ensure the safe operation of transmission lines to a certain extent, it has many shortcomings and limitations. For example, affected by human factors (such as operating errors, instrument accuracy, etc.), the accuracy of the monitoring results is insufficient and cannot reflect the operating status of the transmission line in real time; the analysis method of a single data source often cannot fully reflect the operating status and potential risks of the transmission line; due to the limitations of data singleness and analysis methods, the prediction accuracy of traditional early warning systems is often not high enough, and it is difficult to meet the precise needs of the power system for safety monitoring and early warning assessment. Therefore, an early warning system that can integrate multiple data sources and realize multimodal data analysis is needed to improve the accuracy and reliability of early warning. Summary of the invention

[0005] In order to overcome the above-mentioned defects of the prior art, an embodiment of the present invention provides a power transmission line early warning system based on multimodal data analysis to solve the problems raised in the above-mentioned background technology.

[0006] To achieve the above object, the present invention provides the following technical solution: a transmission line early warning system based on multimodal data analysis, comprising:

[0007] Transmission line monitoring and early warning center module: used to monitor the multimodal data of the transmission line in real time, build a transmission line early warning database, receive data analysis results, and send early warning information to the transmission line human-computer interaction module based on the analysis results;

[0008] Transmission line data acquisition module: Through sensor technology, the transmission line data is collected from the transmission line early warning database to obtain multimodal monitoring data for analyzing the transmission line early warning, and the multimodal monitoring data is transmitted to the transmission line multimodal data analysis module;

[0009] Transmission line multimodal data analysis module: Through big data analysis technology, the multimodal monitoring data obtained by the data acquisition module is analyzed, including the transmission line environment monitoring data analysis unit, the transmission line operation monitoring data analysis unit and the transmission line image monitoring data analysis unit, and the analysis results of each analysis unit are output to the transmission line early warning model construction module;

[0010] Transmission line early warning model construction module: used to compare the analysis results of each analysis unit obtained by the data analysis module with the threshold value, issue an early warning for the comparison results that do not meet the early warning threshold value, and transmit the early warning information to the transmission line early warning human-computer interaction module, and at the same time transmit the comparison results that meet the threshold value to the transmission line early warning comprehensive analysis module;

[0011] Transmission line early warning comprehensive analysis module: used to comprehensively analyze the comparison results that meet the threshold obtained by the early warning model construction module, and transmit the comprehensive analysis results to the transmission line early warning human-computer interaction module;

[0012] Transmission line early warning human-computer interaction module: used to receive the early warning information from the early warning model construction module and the comprehensive analysis results from the comprehensive analysis module for human-computer interaction.

[0013] Preferably, the multimodal monitoring data in the transmission line data acquisition module includes administrator identity authentication information, transmission line environment monitoring data, transmission line operation monitoring data and transmission line image monitoring data, wherein the transmission line environment monitoring data specifically includes the transmission line ambient temperature, humidity, wind direction and wind speed; the transmission line operation monitoring data specifically includes the current, voltage, resistance and capacitance of the transmission line; the transmission line image monitoring data specifically includes the texture features of the transmission line monitoring image, the color of the monitoring image and the contour shape coordinates of the monitoring image.

[0014] Preferably, the power transmission line environment monitoring data analysis unit: firstly, arrange m measurement points at equal distances along the transmission line, collect the ambient temperature T of each measurement point in real time through sensor technology, and obtain the maximum temperature T along the line respectively. max , minimum temperature T min and the average temperature T avg , we get the ambient temperature gradient change rate ΔT, ΔT = (T max -T min ) / T avg; Then, through sensor technology, the ambient humidity H is continuously measured at N times at equal time intervals within the monitoring period t, and the ambient humidity change rate ΔH is obtained. Among them, H t(I+1) and H t(I) Respectively represent the humidity at time t(I+1) and time t(I), I∈N; secondly, the wind speed V and wind direction θ are collected in real time through sensor technology, where θ is the angle between the wind direction and the line direction; finally, the transmission line thermodynamic warning index TWI is obtained through big data analysis technology, Where ΔH0 represents the reference value of the ambient humidity change rate, V max represents the reference value of ambient wind speed, RI represents the thermal radiation intensity, RI0 represents the reference value of ambient thermal radiation intensity, and a1, a2, a3, a4 and a5 represent the exponential coefficients of each sub-data respectively.

[0015] Preferably, the transmission line operation monitoring data analysis unit: first, through sensor technology, real-time acquisition of the current I and voltage V of the transmission line at n measurement points sampled at equal time intervals within the monitoring time t, obtains the standard deviation of the current б(I) and the average value of the current μ(I), and obtains the current fluctuation coefficient ηI, ηI=б(I) / μ(I); then, through spectrum analysis technology, obtains each harmonic voltage V h , get the voltage distortion rate THD_V at the i-th measurement point i , i∈n, h=2,3,…,H, where H represents the highest harmonic order, V1 i Represents the fundamental amplitude of the voltage at the ith measurement point, V h i Represents the amplitude of each harmonic of the voltage at the i-th measuring point; then, through sensor technology, the resistivity ρ_t1 and temperature T_t1 of the transmission line at time t1, the resistivity ρ_t2 and temperature T_t2 of the transmission line at time t2 are collected in real time to obtain the resistivity temperature coefficient η_ρ, Secondly, through sensor technology, the capacitance C and total current I_tot of the transmission line are collected in real time to obtain the capacitance-current ratio CR. ω represents the angular frequency; finally, the transmission line electrical performance early warning index EWI is obtained through big data analysis technology. Where η_ρ0 represents the reference value of the temperature coefficient of resistivity, and b1, b2, b3 and b4 represent the corresponding weights respectively.

[0016] Preferably, the power transmission line image monitoring data analysis unit: obtains the texture feature value F of the transmission line monitoring history image and the current image at (x, y) by using the monitoring equipment and the image processing technology. old (x,y) and F new(x,y) , get the image texture change rate M and N represent the number of rows and columns of the image matrix respectively; then, the color recognition technology is used to obtain the color pixel CP of the transmission line monitoring image, and the color difference coefficient D_cor between the color of the transmission line and the normal state is obtained. ΔR p , ΔG p , ΔB p represents the change in the three primary colors of red, green and blue at pixel p; then, using shape analysis technology, the three-dimensional coordinate data set C of k sampling points of the line contour in the transmission line monitoring image is obtained, and the shape deviation coefficient D_shape between the transmission line shape and the standard shape is obtained, j∈k,C j represents the three-dimensional coordinates of the jth sampling point, C j0 represents the standard three-dimensional coordinates of the jth sampling point; finally, the transmission line physical damage warning index DWI is obtained through big data analysis technology.

[0017] Where ΔF_img0, D_cor0, and D_shape0 represent the reference values ​​of the image texture change rate, color difference coefficient, and shape deviation coefficient, respectively, and c1, c2, and c3 represent the corresponding weights, respectively.

[0018] Preferably, in the transmission line early warning model construction module, step 1: substitute the analysis result TWI obtained by the transmission line environment monitoring data analysis unit into the formula: γ(TWI)=(TWI-TWI0) / TWI0, wherein TWI represents the transmission line thermodynamic early warning index, TWI0 represents the threshold value, γ(TWI) represents the early warning factor of the transmission line thermodynamic early warning index, if γ(TWI)≤0, it means that the transmission line environment monitoring data is normal; otherwise, if 0<γ(TWI)≤0.2, it means that there is an abnormal state, triggering the first-level early warning level, if 0.2<γ(TWI)≤0.5, it means that a fault is about to occur, triggering the second-level early warning level, if γ(TWI)>0.5, it means that a serious fault occurs, triggering the third-level early warning level, and transmitting the early warning information to the transmission line early warning human-computer interaction module, wherein the early warning information includes the early warning level, early warning content and recommended measures.

[0019] Preferably, in step 2 of the transmission line early warning model construction module: substitute the analysis result EWI obtained by the transmission line operation monitoring data analysis unit into the formula: γ(EWI)=(EWI-EWI0) / EWI0, wherein EWI represents the transmission line electrical performance early warning index, EWI0 represents the threshold value, γ(EWI) represents the early warning factor of the transmission line electrical performance early warning index, if γ(EWI)≤0, it means that the transmission line operation monitoring data is normal; otherwise, if 0<γ(EWI)≤0.2, it means that there is an abnormal state, triggering the first-level early warning level, if 0.2<γ(EWI)≤0.5, it means that a fault is about to occur, triggering the second-level early warning level, if γ(EWI)>0.5, it means that a serious fault occurs, triggering the third-level early warning level, and transmitting the early warning information to the transmission line early warning human-computer interaction module, wherein the early warning information includes the early warning level, early warning content and recommended measures.

[0020] Preferably, in step 3 of the transmission line early warning model construction module: substitute the analysis result DWI obtained by the transmission line image monitoring data analysis unit into the formula: γ(DWI)=(DWI-DWI0) / DWI0, wherein DWI represents the transmission line physical damage early warning index, DWI0 represents the threshold, γ(DWI) represents the early warning factor of the transmission line physical damage early warning index, if γ(DWI)≤0, it means that the transmission line image monitoring data is normal; otherwise, if 0<γ(DWI)≤0.2, it means that there is an abnormal state, triggering the first-level early warning level, if 0.2<γ(DWI)≤0.5, it means that a fault is about to occur, triggering the second-level early warning level, if γ(DWI)>0.5, it means that a serious fault occurs, triggering the third-level early warning level, and transmitting the early warning information to the transmission line early warning human-computer interaction module, wherein the early warning information includes the early warning level, early warning content and recommended measures.

[0021] Technical effects and advantages of the present invention:

[0022] 1. The present invention collects multimodal data of power transmission lines in real time through monitoring equipment and sensor technology, and can comprehensively consider information from different aspects to provide more comprehensive data for analyzing the early warning of power transmission lines, avoid misjudgment caused by single data, and realize comprehensive monitoring and early warning of line status, thereby ensuring the safe and stable operation of the line;

[0023] 2. The present invention uses big data technology to perform multimodal data analysis, and can issue early warnings before a fault occurs or at the initial stage of an abnormal situation, thereby improving the timeliness of early warnings for power transmission lines, gaining more processing time for operation and maintenance personnel, reducing accident losses, and improving the efficiency and quality of operation and maintenance work, thereby ensuring the reliability of power supply for transmission lines;

[0024] 3. The present invention uses multimodal data analysis technology to monitor and analyze the environmental parameters, line parameters and image monitoring parameters of the transmission line in real time, which can more comprehensively reflect the operating status and potential risks of the transmission line, improve the accuracy and reliability of the early warning system, and enable it to cope with complex and changeable natural environmental conditions. BRIEF DESCRIPTION OF THE DRAWINGS

[0025] Figure 1 It is a schematic diagram of the overall process of the present invention. DETAILED DESCRIPTION

[0026] 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.

[0027] See also Figure 1 As shown, the present invention provides a transmission line early warning system based on multimodal data analysis, including a transmission line monitoring and early warning center module, a transmission line data acquisition module, a transmission line multimodal data analysis module, a transmission line early warning model construction module, a transmission line early warning comprehensive analysis module and a transmission line early warning human-computer interaction module.

[0028] The transmission line monitoring and early warning center module is connected to all modules in the system, the transmission line data acquisition module is connected to the transmission line multimodal data analysis module, the transmission line early warning model construction module is respectively connected to the transmission line early warning comprehensive analysis module, the transmission line multimodal data analysis module and the transmission line early warning human-computer interaction module, and the transmission line early warning human-computer interaction module is connected to the transmission line early warning comprehensive analysis module.

[0029] Transmission line monitoring and early warning center module: used to monitor the multimodal data of the transmission line in real time, build a transmission line early warning database, receive data analysis results, and send early warning information to the transmission line human-computer interaction module based on the analysis results;

[0030] It should be specifically explained in this embodiment that the transmission line early warning database includes but is not limited to the surrounding environment parameters of the transmission line, the state parameters of the operating conductors of the transmission line, the image parameters of the insulators, conductors and other components on the transmission line, and the shape parameters of the supporting structures such as towers and poles.

[0031] Transmission line data acquisition module: Through sensor technology, the transmission line data is collected from the transmission line early warning database to obtain multimodal monitoring data for analyzing the transmission line early warning, and the multimodal monitoring data is transmitted to the transmission line multimodal data analysis module;

[0032] What needs to be specifically explained in this embodiment is that the multimodal monitoring data includes administrator identity authentication information, transmission line environment monitoring data, transmission line operation monitoring data and transmission line image monitoring data, wherein the transmission line environment monitoring data specifically includes the transmission line environmental temperature, humidity, wind direction and wind speed; the transmission line operation monitoring data specifically includes the current, voltage, resistance and capacitance of the transmission line; the transmission line image monitoring data specifically includes the texture features of the transmission line monitoring image, the color of the monitoring image and the contour shape coordinates of the monitoring image.

[0033] Transmission line multimodal data analysis module: Through big data analysis technology, the multimodal monitoring data obtained by the data acquisition module is analyzed, including the transmission line environment monitoring data analysis unit, the transmission line operation monitoring data analysis unit and the transmission line image monitoring data analysis unit, and the analysis results of each analysis unit are output to the transmission line early warning model construction module. The multimodal monitoring data analysis includes the following steps:

[0034] What needs to be specifically explained in this embodiment is that the transmission line environment monitoring data analysis unit is used to analyze the transmission line environment monitoring data, the transmission line operation monitoring data analysis unit is used to analyze the transmission line operation monitoring data, and the transmission line image monitoring data analysis unit is used to calculate the transmission line image monitoring data.

[0035] Step 1: Transmission line environmental monitoring data analysis unit: First, m measurement points are arranged at equal distances along the transmission line, and the ambient temperature T of each measurement point is collected in real time through sensor technology, and the maximum temperature T along the line is obtained respectively. max , minimum temperature T min and the average temperature T avg , we get the ambient temperature gradient change rate ΔT, ΔT = (T max -T min ) / T avg ; Then, through sensor technology, the ambient humidity H is continuously measured at N times at equal time intervals within the monitoring period t, and the ambient humidity change rate ΔH is obtained. Among them, H t(I+1) and H t(I) Respectively represent the humidity at time t(I+1) and time t(I), I∈N; secondly, the wind speed V and wind direction θ are collected in real time through sensor technology, where θ is the angle between the wind direction and the line direction; finally, the transmission line thermodynamic warning index TWI is obtained through big data analysis technology, Where ΔH0 represents the reference value of the ambient humidity change rate, V maxIt represents the reference value of ambient wind speed, RI represents the thermal radiation intensity, the radiation intensity from the sun or other heat sources, RI0 represents the reference value of ambient thermal radiation intensity, a1, a2, a3, a4 and a5 represent the exponential coefficients of each sub-data, which are used to adjust the contribution to the thermodynamic early warning index of the transmission line;

[0036] What needs to be specifically explained in this embodiment is that the ambient temperature gradient reflects the temperature difference at different locations along the line. A significant temperature gradient may cause uneven thermal expansion of the conductors, increase line tension, and even cause the risk of line breakage; the humidity change rate reflects the change in humidity per unit time, which has an important impact on the insulation performance and corrosion rate of the transmission line; the influence of wind speed and wind direction on the line is taken into account, which is an important indicator for evaluating the mechanical stability and dancing risk of the line; strong thermal radiation may cause the line temperature to rise, increase thermal expansion and thermodynamic stress.

[0037] Step 2: Transmission line operation monitoring data analysis unit: First, through sensor technology, the current I and voltage V of the transmission line are sampled at n measurement points at equal time intervals within the monitoring time t in real time, and the standard deviation of the current б(I) and the average value of the current μ(I) are obtained to obtain the current fluctuation coefficient ηI, ηI=б(I) / μ(I); then, through spectrum analysis technology, the harmonic voltage V of each sub-harmonic is obtained. h , get the voltage distortion rate THD_V at the i-th measurement point i , i∈n, h=2,3,…,H, where H represents the highest harmonic order, V1 i Represents the fundamental amplitude of the voltage at the ith measurement point, V h i Represents the amplitude of each harmonic of the voltage at the i-th measuring point; then, through sensor technology, the resistivity ρ_t1 and temperature T_t1 of the transmission line at time t1, the resistivity ρ_t2 and temperature T_t2 of the transmission line at time t2 are collected in real time to obtain the resistivity temperature coefficient η_ρ, Secondly, through sensor technology, the capacitance C and total current I_tot of the transmission line are collected in real time to obtain the capacitance-current ratio CR. ω represents the angular frequency; finally, the transmission line electrical performance early warning index EWI is obtained through big data analysis technology. Where η_ρ0 represents the reference value of the temperature coefficient of resistivity, which is usually taken as the value at a certain standard temperature, and b1, b2, b3 and b4 represent the corresponding weights, for example, b1 = 0.25, b2 = 0.25, b3 = 0.25 and b4 = 0.25;

[0038] What needs to be specifically explained in this embodiment is that by monitoring current fluctuations, the early warning system can promptly detect potential current anomalies, thereby triggering the early warning mechanism to avoid serious consequences such as circuit damage or fire; by monitoring the voltage distortion rate, the early warning system can identify voltage quality problems and take corresponding measures to correct them; by monitoring the resistivity temperature coefficient, the early warning system can evaluate the performance of the line at different temperatures, and promptly detect resistance anomalies caused by temperature changes, thereby preventing faults caused by overheating or overload; by monitoring the capacitance-current ratio, the early warning system can promptly detect capacitive faults, thereby avoiding potential risks such as insulation damage or short circuits.

[0039] Step 3: Transmission line image monitoring data analysis unit: Through the monitoring equipment, using image processing technology, obtain the texture feature value F of the transmission line monitoring history image and the current image at (x, y) old (x,y) and F new (x,y) , get the image texture change rate ΔF_img, M and N represent the number of rows and columns of the image matrix respectively; then, the color recognition technology is used to obtain the color pixel CP of the transmission line monitoring image, and the color difference coefficient D_cor between the color of the transmission line and the normal state is obtained. ΔR p , ΔG p , ΔB p represents the change in the three primary colors of red, green and blue at pixel p; then, using shape analysis technology, the three-dimensional coordinate data set C of k sampling points of the line contour in the transmission line monitoring image is obtained, and the shape deviation coefficient D_shape between the transmission line shape and the standard shape is obtained, j∈k,C j represents the three-dimensional coordinates of the jth sampling point, C j0 represents the standard three-dimensional coordinates of the jth sampling point; finally, the transmission line physical damage warning index DWI is obtained through big data analysis technology. Where ΔF_img0, D_cor0, and D_shape0 represent the reference values ​​of the image texture change rate, color difference coefficient, and shape deviation coefficient, respectively, and c1, c2, and c3 represent the corresponding weights, such as c1 = 0.4, c2 = 0.3, and c3 = 0.3;

[0040] What needs to be specifically explained in this embodiment is that by calculating the image texture change rate, the early warning system can timely detect cracks in insulators, conductors and other components on the transmission line, thereby triggering a physical damage early warning; by calculating the color anomaly coefficient, the early warning system can identify areas where components on the transmission line have color anomalies such as oxidation, corrosion or burning, and then determine whether there is a risk of physical damage; by calculating the shape deformation degree, the early warning system can timely detect when supporting structures such as towers and poles on the transmission line are tilted, bent or broken, their shapes will change, thereby determining whether there is a risk of collapse or breakage;

[0041] Transmission line early warning model construction module: used to compare the analysis results of each analysis unit obtained by the data analysis module with the threshold value, issue an early warning for the comparison results that do not meet the early warning threshold value, and transmit the early warning information to the transmission line early warning human-computer interaction module, and at the same time transmit the comparison results that meet the threshold value to the transmission line early warning comprehensive analysis module. The early warning model construction includes the following steps:

[0042] Step 1: Substitute the analysis result TWI obtained by the transmission line environment monitoring data analysis unit into the formula: γ(TWI)=(TWI-TWI0) / TWI0, where TWI represents the transmission line thermodynamic warning index, TWI0 represents the threshold, and γ(TWI) represents the warning factor of the transmission line thermodynamic warning index. If γ(TWI)≤0, it means that the transmission line environment monitoring data is normal; otherwise, if 0<γ(TWI)≤0.2, it means that there is an abnormal state, triggering the first-level warning level, and attention is required. If 0.2<γ(TWI)≤0.5, it means that a fault is about to occur, triggering the second-level warning level, and inspection is required. If γ(TWI)>0.5, it means that a serious fault occurs, triggering the third-level warning level, and repair or replacement is required. The warning information is transmitted to the transmission line warning human-computer interaction module, where the warning information includes the warning level, warning content and recommended measures. The warning content indicates that the environmental temperature gradient is abnormal, which may cause uneven thermal expansion of the conductor, increase the line tension, and even cause the risk of disconnection. The recommended measures are to strengthen the inspection and maintenance of the line and optimize the line direction and layout.

[0043] Step 2: Substitute the analysis result EWI obtained by the transmission line operation monitoring data analysis unit into the formula: γ(EWI)=(EWI-EWI0) / EWI0, where EWI represents the transmission line electrical performance warning index, EWI0 represents the threshold, and γ(EWI) represents the warning factor of the transmission line electrical performance warning index. If γ(EWI)≤0, it means that the transmission line operation monitoring data is normal; otherwise, if 0<γ(EWI)≤0.2, it means that there is an abnormal state, triggering the first-level warning level, and attention is needed. If 0.2<γ(EW If γ(EWI)≤0.5, it indicates that a fault is about to occur, triggering the second-level warning level and requiring inspection. If γ(EWI)>0.5, it indicates that a serious fault has occurred, triggering the third-level warning level and requiring repair or replacement. The warning information is transmitted to the transmission line warning human-computer interaction module, where the warning information includes the warning level, warning content and recommended measures. For example, if the warning levels are level one, two and three, the warning content is that the current fluctuation rate is too high, which may cause line overload and heating. The recommended measures are to check the line load, adjust the load distribution, and strengthen inspections.

[0044] Step 3: Substitute the analysis result DWI obtained by the transmission line image monitoring data analysis unit into the formula: γ(DWI)=(DWI-DWI0) / DWI0, where DWI represents the transmission line physical damage warning index, DWI0 represents the threshold, and γ(DWI) represents the warning factor of the transmission line physical damage warning index. If γ(DWI)≤0, it means that the transmission line image monitoring data is normal; otherwise, if 0<γ(DWI)≤0.2, it means that there is an abnormal state, triggering the first-level warning level, and attention is required. If 0.2<γ(DWI)≤0.5, it means that a fault is about to occur, triggering the second-level warning level, and inspection is required. If γ(DWI)>0.5, it means that a serious fault occurs, triggering the third-level warning level, and repair or replacement is required. The warning information is transmitted to the transmission line warning human-computer interaction module, where the warning information includes the warning level, warning content and recommended measures. For example, the warning levels are one, two and three, and the warning content is that cracks appear in insulators, conductors and other components on the transmission line, and the recommended measures are to take repair or replacement.

[0045] Transmission line early warning comprehensive analysis module: used to comprehensively analyze the comparison results that meet the threshold obtained by the early warning model construction module, and transmit the comprehensive analysis results to the transmission line early warning human-computer interaction module. The comprehensive analysis model is: CWI = d1×γ(TWI)+d2×γ(EWI)+d3×γ(DWI), where CWI represents the comprehensive early warning index of the multimodal transmission line, d1 represents the weight of the early warning factor γ(TWI) of the transmission line thermodynamic early warning index, d2 represents the weight of the early warning factor γ(EWI) of the transmission line electrical performance early warning index, and d3 represents the weight of the early warning factor γ(DWI) of the transmission line physical damage early warning index;

[0046] Transmission line early warning human-computer interaction module: used to receive the early warning information of the early warning model construction module and the comprehensive analysis results of the comprehensive analysis module for human-computer interaction. If the comprehensive analysis result of the multimodal transmission line comprehensive early warning index belongs to the set allowable range, it means that the transmission line monitoring is good. Otherwise, the administrator is prompted to take timely measures to conduct a comprehensive inspection of the transmission line to ensure the safe and stable operation of the line.

[0047] Finally: The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present invention should be included in the protection scope of the present invention.

Claims

1. A transmission line early warning system based on multimodal data analysis, characterized in that: include: Transmission line monitoring and early warning center module: used to monitor the multimodal data of the transmission line in real time, build a transmission line early warning database, receive data analysis results, and send early warning information to the transmission line human-computer interaction module based on the analysis results; Transmission line data acquisition module: Through sensor technology, the transmission line data is collected from the transmission line early warning database to obtain multimodal monitoring data for analyzing the transmission line early warning, and the multimodal monitoring data is transmitted to the transmission line multimodal data analysis module; Transmission line multimodal data analysis module: Through big data analysis technology, the multimodal monitoring data obtained by the data acquisition module is analyzed, including the transmission line environment monitoring data analysis unit, the transmission line operation monitoring data analysis unit and the transmission line image monitoring data analysis unit, and the analysis results of each analysis unit are output to the transmission line early warning model construction module; Transmission line early warning model construction module: used to compare the analysis results of each analysis unit obtained by the data analysis module with the threshold value, issue an early warning for the comparison results that do not meet the early warning threshold value, and transmit the early warning information to the transmission line early warning human-computer interaction module, and at the same time transmit the comparison results that meet the threshold value to the transmission line early warning comprehensive analysis module; Transmission line early warning comprehensive analysis module: used to comprehensively analyze the comparison results that meet the threshold obtained by the early warning model construction module, and transmit the comprehensive analysis results to the transmission line early warning human-computer interaction module; Transmission line early warning human-computer interaction module: used to receive the early warning information from the early warning model construction module and the comprehensive analysis results from the comprehensive analysis module for human-computer interaction.

2. The power transmission line early warning system based on multimodal data analysis according to claim 1, characterized in that: The multimodal monitoring data in the transmission line data acquisition module includes administrator identity authentication information, transmission line environment monitoring data, transmission line operation monitoring data and transmission line image monitoring data, wherein the transmission line environment monitoring data specifically includes the transmission line environment temperature, humidity, wind direction and wind speed; the transmission line operation monitoring data specifically includes the current, voltage, resistance and capacitance of the transmission line; the transmission line image monitoring data specifically includes the texture features of the transmission line monitoring image, the color of the monitoring image and the contour shape coordinates of the monitoring image.

3. The power transmission line early warning system based on multimodal data analysis according to claim 1, characterized in that: The power transmission line environment monitoring data analysis unit: firstly, m measuring points are arranged at equal distances along the transmission line, and the ambient temperature T of each measuring point is collected in real time through sensor technology, and the maximum temperature T along the line is obtained respectively. max , minimum temperature T min and the average temperature T avg , we get the ambient temperature gradient change rate ΔT, ΔT = (T max -T min ) / T avg ; Then, through sensor technology, the ambient humidity H is continuously measured at N times at equal time intervals within the monitoring period t, and the ambient humidity change rate ΔH is obtained. Among them, H t(I+1) and H t(I) Respectively represent the humidity at time t(I+1) and time t(I), I∈N; secondly, the wind speed V and wind direction θ are collected in real time through sensor technology, where θ is the angle between the wind direction and the line direction; finally, the transmission line thermodynamic warning index TWI is obtained through big data analysis technology, Where ΔH0 represents the reference value of the ambient humidity change rate, V max represents the reference value of ambient wind speed, RI represents the thermal radiation intensity, RI0 represents the reference value of ambient thermal radiation intensity, and a1, a2, a3, a4 and a5 represent the exponential coefficients of each sub-data respectively.

4. The power transmission line early warning system based on multimodal data analysis according to claim 1, characterized in that: The transmission line operation monitoring data analysis unit: first, through sensor technology, real-time acquisition of the current I and voltage V of the transmission line at n measurement points sampled at equal time intervals within the monitoring time t, obtains the standard deviation of the current б(I) and the average value of the current μ(I), and obtains the current fluctuation coefficient ηI, ηI=б(I) / μ(I); then, through spectrum analysis technology, obtains each harmonic voltage V h , get the voltage distortion rate THD_V at the i-th measurement point i , Where H represents the highest harmonic order, V1 i Represents the fundamental amplitude of the voltage at the ith measurement point, V h i Represents the amplitude of each harmonic of the voltage at the i-th measuring point; then, through sensor technology, the resistivity ρ_t1 and temperature T_t1 of the transmission line at time t1, the resistivity ρ_t2 and temperature T_t2 of the transmission line at time t2 are collected in real time to obtain the resistivity temperature coefficient η_ρ, Secondly, through sensor technology, the capacitance C and total current I_tot of the transmission line are collected in real time to obtain the capacitance-current ratio CR. ω represents the angular frequency; finally, the transmission line electrical performance early warning index EWI is obtained through big data analysis technology. Where η_ρ0 represents the reference value of the temperature coefficient of resistivity, and b1, b2, b3 and b4 represent the corresponding weights respectively.

5. The power transmission line early warning system based on multimodal data analysis according to claim 1, characterized in that: The power transmission line image monitoring data analysis unit: uses the image processing technology to obtain the texture feature value F of the transmission line monitoring history image and the current image at (x, y) through the monitoring equipment old (x,y) and F new (x,y) , get the image texture change rate ΔF_img, M and N represent the number of rows and columns of the image matrix respectively; then, the color recognition technology is used to obtain the color pixel CP of the transmission line monitoring image, and the color difference coefficient D_cor between the color of the transmission line and the normal state is obtained. ΔR p , ΔG p , ΔB p represents the change in the three primary colors of red, green and blue at pixel p; then, using shape analysis technology, the three-dimensional coordinate data set C of k sampling points of the line contour in the transmission line monitoring image is obtained, and the shape deviation coefficient D_shape between the transmission line shape and the standard shape is obtained, j∈k,C j represents the three-dimensional coordinates of the jth sampling point, C j0 represents the standard three-dimensional coordinates of the jth sampling point; finally, the transmission line physical damage warning index DWI is obtained through big data analysis technology. Where ΔF_img0, D_cor0, and D_shape0 represent the reference values ​​of image texture change rate, color difference coefficient, and shape deviation coefficient, respectively, and c1, c2, and c3 represent the corresponding weights, respectively.

6. The power transmission line early warning system based on multimodal data analysis according to claim 1, characterized in that: Step 1 in the transmission line early warning model construction module: Substitute the analysis result TWI obtained by the transmission line environment monitoring data analysis unit into the formula: γ(TWI)=(TWI-TWI0) / TWI0, wherein TWI represents the transmission line thermodynamic early warning index, TWI0 represents the threshold value, γ(TWI) represents the early warning factor of the transmission line thermodynamic early warning index, if γ(TWI)≤0, it means that the transmission line environment monitoring data is normal; otherwise, if 0<γ(TWI)≤0.2, it means that there is an abnormal state, triggering the first-level early warning level, if 0.2<γ(TWI)≤0.5, it means that a fault is about to occur, triggering the second-level early warning level, if γ(TWI)>0.5, it means that a serious fault occurs, triggering the third-level early warning level, and transmitting the early warning information to the transmission line early warning human-computer interaction module, wherein the early warning information includes the early warning level, early warning content and recommended measures.

7. The power transmission line early warning system based on multimodal data analysis according to claim 1, characterized in that: Step 2 in the transmission line early warning model construction module: Substitute the analysis result EWI obtained by the transmission line operation monitoring data analysis unit into the formula: γ(EWI)=(EWI-EWI0) / EWI0, wherein EWI represents the transmission line electrical performance early warning index, EWI0 represents the threshold, γ(EWI) represents the early warning factor of the transmission line electrical performance early warning index, if γ(EWI)≤0, it means that the transmission line operation monitoring data is normal; otherwise, if 0<γ(EWI)≤0.2, it means that there is an abnormal state, triggering the first-level early warning level, if 0.2<γ(EWI)≤0.5, it means that a fault is about to occur, triggering the second-level early warning level, if γ(EWI)>0.5, it means that a serious fault occurs, triggering the third-level early warning level, and transmitting the early warning information to the transmission line early warning human-computer interaction module, wherein the early warning information includes the early warning level, early warning content and recommended measures.

8. The power transmission line early warning system based on multimodal data analysis according to claim 1, characterized in that: Step 3 in the transmission line early warning model construction module: Substitute the analysis result DWI obtained by the transmission line image monitoring data analysis unit into the formula: γ(DWI)=(DWI-DWI0) / DWI0, wherein DWI represents the transmission line physical damage early warning index, DWI0 represents the threshold, γ(DWI) represents the early warning factor of the transmission line physical damage early warning index, if γ(DWI)≤0, it means that the transmission line image monitoring data is normal; otherwise, if 0<γ(DWI)≤0.2, it means that there is an abnormal state, triggering the first-level early warning level, if 0.2<γ(DWI)≤0.5, it means that a fault is about to occur, triggering the second-level early warning level, if γ(DWI)>0.5, it means that a serious fault occurs, triggering the third-level early warning level, and transmitting the early warning information to the transmission line early warning human-computer interaction module, wherein the early warning information includes the early warning level, early warning content and recommended measures.

Images