A method, system and terminal for predicting transmission line faults based on spatiotemporal information fusion

Abstract

The present invention belongs to the technical field of power grid fault prediction, and specifically relates to a transmission line fault prediction method, system, and terminal based on spatiotemporal information fusion. The method includes real-time acquisition of transient signals from the transmission line and multidimensional environmental data from the region, including meteorological and geographic parameters. Time periods are divided based on the 24 solar terms, and a dynamic weight matrix is ​​constructed. The initial weights of various environmental factors under different solar terms are trained using historical fault data. By acquiring real-time transient signals from the transmission line and multidimensional environmental data from the region, and constructing a dynamic weight matrix based on the 24 solar terms, the method fully considers the impact of meteorological, geographic, and temporal factors on line faults. This method can more comprehensively reflect the actual operating status of the line, thereby improving the accuracy of fault prediction.

Description

Technical Field

[0001] The present invention relates to a method, system and terminal for predicting power transmission line faults based on spatiotemporal information fusion, and belongs to the technical field of power grid fault prediction. Background Art

[0002] As the scale of the power system continues to expand, overhead transmission lines, as the "aorta" of the power grid, have a direct impact on the safety and reliability of the entire grid. However, long-term exposure to complex and changing natural environments, overhead transmission lines are frequently impacted by extreme weather disasters such as lightning, heavy rain, and icing. These extreme weather conditions not only directly threaten the physical safety of transmission lines but can also lead to serious consequences such as line tripping and cascading grid failures. According to statistics, in my country, over 65% of transmission line tripping accidents each year are caused by severe weather, which not only causes great inconvenience to people's daily lives but also results in billions of yuan in economic losses.

[0003] In addition to the impact of extreme weather, hidden dangers such as line aging, hardware wear, and external damage are also significant factors contributing to transmission line failures. The spatiotemporal coupling of these hidden dangers complicates fault prediction. On the one hand, line aging and hardware wear are long-term and gradual processes, making their impact difficult to accurately quantify. On the other hand, external damage, such as accidental collisions during construction and fallen trees, is sudden and uncertain, posing even greater challenges to fault prediction.

[0004] Existing technologies are mainly divided into two directions: fault prediction methods based on electrical characteristic parameters and fault prediction methods based on environmental characteristic parameters. However, both methods have significant limitations. The fault prediction method based on electrical characteristic parameters mainly relies on real-time monitoring and analysis of electrical quantities such as line current and voltage, but this method is not effective in predicting faults under extreme weather conditions, because electrical characteristic parameters can often only reflect the state after the fault occurs and cannot provide early warning. Although the fault prediction method based on environmental characteristic parameters can take into account the impact of meteorological conditions on line faults, it often ignores factors such as the state of the line itself and external force damage, resulting in inaccurate prediction results. Summary of the Invention

[0005] The purpose of the present invention is to provide a method, system and terminal for predicting power transmission line faults based on spatiotemporal information fusion, so as to solve the problem of inaccurate prediction results.

[0006] To achieve the above-mentioned purpose, the present invention is implemented through the following technical solutions:

[0007] In a first aspect, a transmission line fault prediction method based on spatiotemporal information fusion comprises the following steps:

[0008] Real-time collection of transient signals of the transmission line and multi-dimensional environmental data of the area where the line is located, including meteorological parameters and geographical parameters;

[0009] A dynamic weight matrix is ​​constructed based on historical fault data and the 24 solar terms. The dynamic weight matrix includes the initial weights of various environmental factors under different solar terms.

[0010] Input the multi-dimensional environmental data collected in real time into the risk index model built based on the dynamic weight matrix to calculate the fault risk index of the transmission line;

[0011] Transient signals are used to locate fault points, and the dynamic weight matrix is ​​optimized based on the comparison between actual fault data and predicted results.

[0012] Preferably, the step of obtaining the transient signal of the transmission line and the multi-dimensional environmental data of the area where the transmission line is located specifically includes:

[0013] The meteorological parameters are collected through a distributed sensor array, including wind speed, rainfall, lightning frequency and ice thickness;

[0014] The geographical parameters are obtained based on a geographic information system and include at least one of the geographical coordinates of the area where the transmission line is located, vegetation density, terrain slope, terrain complexity, altitude, and vegetation coverage;

[0015] The transient signal is captured by a transient signal collector installed on a transmission line tower, and includes a transient current or voltage signal when a fault occurs.

[0016] Preferably, the constructing of a dynamic weight matrix includes:

[0017] determining a set of environmental factors, the set comprising wind speed, rainfall, lightning frequency, ice thickness, geographic coordinates, vegetation density, terrain slope, terrain complexity, altitude, and vegetation cover;

[0018] The formula for calculating the initial weights of various environmental factors under different solar terms is:

[0019] ,

[0020] in, For the Environmental factors in the The initial weight under the solar term, For this solar term Number of failures caused by environmental factors, is the number of all environmental factors, is the historical credibility correction factor;

[0021] A dynamic weight matrix containing 24 solar term weight vectors is constructed, where the rows of the matrix correspond to the solar terms and the columns correspond to the environmental factors.

[0022] Preferably, the calculation formula of the risk index model is:

[0023] ;

[0024] in, is the failure risk index of the transmission line, The climate group in the dynamic weight matrix Neidi Smoothed weights of environmental-like factors, , is the factor intensity function, Indicates environmental factors, is a multi-factor synergistic term, represents the synergistic amplification factor, It represents the combination of the two most influential environmental factors among the environmental factors facing the current solar term. is the solar term transition function, is the time decay factor, Line vulnerability.

[0025] Preferably, the climate group The 24 solar terms are divided into ice group, lightning group, rainstorm group, strong wind group, warm and humid group and dry group according to their climatic characteristics. The solar terms are numbered in sequence according to the 24 solar terms table, as follows:

[0026] Ice-covered group: Dahan, Xiaohan, Lidong, Xiaoxue, Dongzhi, Daxue; the central solar term is Dahan;

[0027] Lightning Group: Summer Solstice, Lesser Heat, Early Days of Greater Heat, Beginning of Summer; the central solar term is Summer Solstice;

[0028] Heavy rain group: Grain in Ear, Grain Rain, Grain Full, End of Heat; the central solar term is Grain in Ear;

[0029] Gale Group: Spring Equinox, Qingming, Jingzhe, and White Dew; the central solar term is Qingming;

[0030] Warm and humid group: Beginning of Spring, Rain Water, Frost Descent, Cold Dew; the central solar term is Cold Dew;

[0031] Dry group: Beginning of Autumn, Autumnal Equinox, and late period of Great Heat; the central solar term is Autumnal Equinox.

[0032] Preferably, the smoothing weight calculation includes:

[0033] ;

[0034] in, For the climate group The number of solar terms included, is the solar term sequence number of the current solar term, For the climate group The solar term sequence number of the central solar term, is the attenuation coefficient, ;

[0035] The factor intensity function is:

[0036] ;

[0037] in, For the Characteristic coefficients of environmental factors, For the Quasi-real-time environmental factors;

[0038] The multi-factor synergy term is:

[0039] ;

[0040] in, is the synergistic amplification factor, is the synergistic function, The synergy factor represents the Environmental factors and The amplifying effect of the combination of similar environmental factors on risk, is the factor strength function;

[0041] The solar term transition function is:

[0042] ;

[0043] in, is the sequence number of the previous solar term before the current solar term. The next solar term number of the current solar term;

[0044] The time decay factor is:

[0045] ;

[0046] in, is the attenuation rate, , Indicates time;

[0047] The line vulnerability is:

[0048] ;

[0049] in, is the insulation grade, Insulation grade The weight coefficient of is the tower strength, The tower strength The weight coefficient of is the terrain complexity, Terrain complexity The weight coefficient of is the altitude, is the altitude The weight coefficient of .

[0050] Preferably, the optimization dynamic weight matrix includes:

[0051] Filter and reduce noise on transient signals and extract fault characteristic frequencies;

[0052] Based on the multi-frequency ranging method, a fault location equation is established to calculate the distance between the fault point and the monitoring point;

[0053] Use GIS to locate the actual fault tower location;

[0054] The actual and predicted risk indices are compared, and the dynamic weight matrix is ​​updated when the error rate exceeds a threshold.

[0055] Preferably, the specific formula for updating the dynamic weight matrix is ​​as follows:

[0056] ;

[0057] in, After optimization Environmental factors in the The weight under each solar term, For the current Environmental factors in the The weight under each solar term, is the error rate About weight The partial derivative of is the learning rate.

[0058] In a second aspect, the present invention further provides a transmission line fault prediction system based on spatiotemporal information fusion, comprising:

[0059] The data acquisition module is used to collect the transient signals of the transmission line and the multi-dimensional environmental data of the area in real time. The multi-dimensional environmental data includes meteorological parameters and geographical parameters;

[0060] The matrix construction module is used to divide the time periods based on the 24 solar terms, construct a dynamic weight matrix, and train the initial weights of various environmental factors under different solar terms using historical fault data;

[0061] A fault risk index calculation module is used to input the collected multi-dimensional environmental data into a risk index model built based on a dynamic weight matrix to calculate the fault risk index of the transmission line;

[0062] The matrix optimization module is used to locate the fault point using transient signals and, after the fault is located, optimize the dynamic weight matrix based on the comparison between the actual fault data and the predicted results.

[0063] In a third aspect, the present invention provides a terminal, comprising:

[0064] processor;

[0065] a memory for storing execution instructions of the processor;

[0066] The processor is configured to execute the method according to any one of claims 1 to 7.

[0067] The advantages of the present invention are:

[0068] Improving fault prediction accuracy: This method collects real-time transient signals from power transmission lines and multi-dimensional environmental data from the region where they are located. It then constructs a dynamic weighting matrix based on the 24 solar terms, fully accounting for the impact of meteorological, geographical, and temporal factors on line faults. This approach more comprehensively reflects the actual operating status of power transmission lines, thereby improving the accuracy of fault prediction.

[0069] Enhanced predictive adaptability: The introduction of a dynamic weight matrix enables the present invention to dynamically adjust the weights of various environmental factors based on the climatic characteristics of different solar terms, thereby enhancing the predictive method's adaptability to diverse climate conditions. Furthermore, by comparing actual fault data with predicted results, the dynamic weight matrix is ​​further optimized, enabling the predictive method to continuously learn and improve, enhancing its long-term predictive effectiveness.

[0070] Rapid fault location and response: This system uses transient signals to locate faults, quickly identifying the fault location after it occurs and providing timely and accurate fault information to maintenance personnel. This helps shorten fault repair time, reduce power outage losses, and improve grid stability and reliability. BRIEF DESCRIPTION OF THE DRAWINGS

[0071] The accompanying drawings are used to provide further understanding of the present invention and constitute a part of the specification. They are used to explain the present invention together with the embodiments of the present invention and do not constitute a limitation of the present invention.

[0072] Figure 1 It is a flowchart of a method according to an embodiment of the present invention.

[0073] Figure 2 It is a schematic structural diagram of a system according to an embodiment of the present invention.

[0074] Figure 3 A schematic diagram of the structure of a terminal provided by an embodiment of the present invention.

[0075] In the figure: 210 is a data acquisition module, 220 is a matrix construction module, 230 is a fault risk index calculation module, 240 is a matrix optimization module, 300 is a terminal, 310 is a processor, 320 is a memory, and 330 is a communication module. DETAILED DESCRIPTION

[0076] The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings. 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 making creative efforts are within the scope of protection of the present invention.

[0077] Figure 1 is a schematic flow chart of a method according to an embodiment of the present invention. Figure 1 The execution subject can be a transmission line fault prediction system based on spatiotemporal information fusion. According to different requirements, the order of the steps in the flowchart can be changed, and some steps can be omitted.

[0078] like Figure 1 As shown, the method includes:

[0079] Step S1: real-time collection of transient signals of the transmission line and multi-dimensional environmental data of the area where the line is located, wherein the multi-dimensional environmental data includes meteorological parameters and geographical parameters;

[0080] Step S2: constructing a dynamic weight matrix based on historical fault data and the 24 solar terms, wherein the dynamic weight matrix includes the initial weights of various environmental factors under different solar terms;

[0081] Step S3: input the multi-dimensional environmental data collected in real time into the risk index model constructed based on the dynamic weight matrix to calculate the fault risk index of the transmission line;

[0082] Step S4: Utilize transient signals to locate the fault point, and optimize the dynamic weight matrix based on the comparison between actual fault data and prediction results.

[0083] This method collects real-time transient signals from power transmission lines and multi-dimensional environmental data from the region where they are located. It then constructs a dynamic weighting matrix based on the 24 solar terms, fully accounting for the impact of meteorological, geographical, and temporal factors on line faults. This method more comprehensively reflects the actual operating status of the line, thereby improving the accuracy of fault prediction.

[0084] To facilitate understanding of the present invention, the following further describes the transmission line fault prediction method based on spatiotemporal information fusion provided by the present invention based on the principle of the transmission line fault prediction method based on spatiotemporal information fusion of the present invention, combined with the process of fault prediction of the transmission line based on spatiotemporal information fusion in the embodiment.

[0085] Specifically, the method includes collecting transient signals of the transmission line and multi-dimensional environmental data of the area in real time, where the multi-dimensional environmental data includes meteorological parameters and geographical parameters.

[0086] S101: Meteorological parameters, including wind speed, rainfall, lightning frequency, and ice thickness, are collected through a distributed sensor array. The sensor array includes a tower-mounted LiDAR weather station and an insulator ice monitoring device.

[0087] S102: Obtaining geographic parameters based on GIS, including at least one of geographic coordinates of the area where the transmission line is located, vegetation density, terrain slope, terrain complexity, altitude, and vegetation coverage;

[0088] S103: Capturing transient current or voltage signals when a fault occurs through a transient signal collector installed on a transmission line tower;

[0089] S104: The collected meteorological parameters, transient signals, and geographic parameters are transmitted to a host storing a risk index model via an NB-IoT wireless communication module or a LoRa wireless communication module.

[0090] Multiple distributed sensor arrays, consisting of LiDAR weather stations and insulator icing monitoring devices, are installed along the transmission lines. These arrays are mounted on the transmission towers. The LiDAR weather stations monitor wind speed, rainfall, and lightning frequency in real time, while the insulator icing monitoring devices are specifically designed to measure ice thickness. These sensors operate 24 / 7, ensuring data continuity and accuracy. Using Geographic Information System (GIS) technology, detailed geographic parameters of the transmission line area are collected. These parameters include geographic coordinates, vegetation density, terrain slope, terrain complexity, altitude, and vegetation coverage. The GIS platform provides a visual overview of the natural environment surrounding the transmission line, providing important information for subsequent fault prediction. Transient signal collectors are installed on key transmission towers. These collectors monitor and record transient current or voltage signals in real time during faults. These signals are crucial for locating the fault point and analyzing its cause. To ensure real-time and reliable data, NB-IoT or LoRa wireless communication modules are used to transmit the collected meteorological, transient, and geographic parameters. These modules can send data to a host computer that stores risk index models for subsequent analysis and prediction.

[0091] By combining distributed sensor arrays with GIS technology, this invention can comprehensively and accurately collect meteorological and geographic parameters in the area where the transmission lines are located. The collected multi-dimensional environmental data and transient signals provide rich input information for the fault prediction model. This information helps the model more accurately predict the occurrence of faults, thereby improving the accuracy and reliability of fault prediction.

[0092] In addition, based on the 24 solar terms, a dynamic weight matrix is ​​constructed to train the initial weights of various environmental factors in different solar terms using historical fault data. The method includes:

[0093] S201: Determine an environmental factor set, where the environmental factor set includes wind speed, rainfall, lightning frequency, ice thickness, geographic coordinates, vegetation density, terrain slope, terrain complexity, altitude, and vegetation coverage;

[0094] S202: Based on historical fault data, calculate the initial weights of various environmental factors under different solar terms. The calculation formula is:

[0095] ;

[0096] in, For the Environmental factors in the The initial weight under the solar term is used to quantify the environmental factors In the The degree of impact on the fault within each solar term; For this solar term Number of failures caused by environmental factors; For the The total number of failures caused by all environmental factors counted in each solar term; is the number of all environmental factors; is the historical credibility correction coefficient, and its value range is , used to correct the credibility of historical data on weight calculation and adjust the impact of historical fault data on weight;

[0097] S203: Creating a weight vector for each solar term. The dimension of the weight vector is the same as the number of elements in the environmental factor set. Each element in the vector is the initial weight of the corresponding environmental factor in the solar term.

[0098] S204: Combining the weight vectors corresponding to all solar terms into a dynamic weight matrix, where each row of the matrix corresponds to a solar term, and each column corresponds to an environmental factor.

[0099] The order of the 24 solar terms is as follows: 1. Beginning of Spring, 2. Rain Water, 3. Waking of Insects, 4. Vernal Equinox, 5. Pure Brightness, 6. Grain Rain, 7. Beginning of Summer, 8. Grain Full, 9. Grain in Ear, 10. Summer Solstice, 11. Lesser Heat, 12. Greater Heat, 13. Beginning of Autumn, 14. End of Heat, 15. White Dew, 16. Autumnal Equinox, 17. Cold Dew, 18. Frost Descent, 19. Beginning of Winter, 20. Light Snow, 21. Heavy Snow, 22. Winter Solstice, 23. Lesser Cold, 24. Greater Cold.

[0100] In this embodiment, a set of key environmental factors influencing transmission line failures was first determined. These factors include wind speed, rainfall, lightning frequency, ice thickness (all meteorological parameters), as well as geographic coordinates, vegetation density, terrain slope, terrain complexity, altitude, and vegetation coverage (all geographic parameters). These environmental factors were selected based on their significance and measurability in affecting transmission line failures. By constructing a dynamic weight matrix, the present invention considers the differences in the impact of environmental factors on transmission line failures during different solar terms, thereby improving the accuracy of fault prediction. This helps operation and maintenance personnel more accurately assess fault risks and take appropriate preventive measures. Because the dynamic weight matrix is ​​trained based on historical fault data, it can reflect the actual impact of environmental factors on faults during different solar terms. Therefore, the model is highly adaptable and can meet the needs of fault prediction in different seasons and climate conditions. By analyzing the dynamic weight matrix, it can determine which environmental factors have the most significant impact on faults during different solar terms. This helps operation and maintenance personnel develop more targeted operation and maintenance strategies, optimize resource allocation, and improve operation and maintenance efficiency.

[0101] In addition, the calculation formula of the risk index model is:

[0102] ;

[0103] in, is the failure risk index of the transmission line, which is used to quantify the failure risk level of the transmission line; The climate group in the dynamic weight matrix Neidi The smoothed weights of environmental factors are used to classify the 24 solar terms into 6 climate groups according to their climate similarities. ; is the factor strength function, used to characterize the The intensity characteristics of environmental factors; It is a multi-factor synergistic item; is the solar term transition function, is the time decay factor, is the line vulnerability; because it considers the amplification of risk by two environmental factors, Indicates the combination of the two most influential environmental factors among the environmental factors facing the current solar term: (such as {heavy rain, strong wind}, {icing, strong wind}).

[0104] The risk index model in the present invention realizes a refined assessment of the risk of transmission line failure by integrating multiple dimensions such as dynamic weight matrix, factor intensity function, multi-factor synergy term, solar term transition function, time attenuation factor and line vulnerability. This assessment method not only considers the impact of a single environmental factor on the failure, but also considers the interaction between multiple factors and the impact of time changes on the risk, thereby improving the accuracy and comprehensiveness of the risk assessment. The dynamic weight matrix in the model classifies the 24 solar terms into 6 climate groups according to climate similarity, and calculates the smoothed weights of the environmental factors in each climate group (for example, the ice-covered group includes the solar terms: Winter Solstice (s=22), Minor Cold (s=23), Major Cold (s=24), and Light Snow (s=20). The central solar term of the group =22 (Winter Solstice). Attenuation coefficient =0.2, historical credibility correction coefficient =1.0). This design enables the model to adaptively adjust to fault characteristics under different climatic conditions, better reflecting the varying impacts of environmental factors under different climatic conditions and improving the model's climate adaptability. By introducing a factor intensity function, the model can quantitatively characterize the intensity characteristics of each environmental factor, such as wind speed and rainfall. This helps operators more intuitively understand the contribution of each environmental factor to the risk of transmission line failures, enabling the development of more effective prevention and control measures. The multi-factor synergy term plays a key role in the model, accounting for the impact of interactions between different environmental factors on fault risk. This approach is more realistic, as in actual operation, transmission line failures are often caused by the combined effects of multiple environmental factors. By considering the synergistic effects of multiple factors, the model can more accurately assess fault risk. The introduction of a solar term transition function and a time decay factor allows the model to account for the impact of solar term changes and the passage of time on fault risk. This helps operators dynamically adjust maintenance strategies based on seasonal variations and the passage of time, ensuring the safe and stable operation of transmission lines. Line vulnerability is a key parameter in the model, reflecting the fault resilience of the transmission line. By assessing line vulnerability, operations and maintenance personnel can understand the risk differences of different transmission lines under the same environmental conditions, thereby formulating differentiated operations and maintenance strategies and improving operations and maintenance efficiency.

[0105] Specifically, based on the traditional climate characteristics and main risk factors of the 24 solar terms, the solar terms are divided into six climate groups according to the following standards, as shown in Table 1.

[0106] Table 1 is the correspondence table between the 24 solar terms and climate groups

[0107]

[0108] Furthermore, the climate group in the dynamic weight matrix Internal environmental factors The smoothing weight The calculation formula is:

[0109] ;

[0110] in, For the climate group The number of solar terms included; is the solar term sequence number of the current solar term, For the climate group The solar term sequence number of the central solar term; is the attenuation coefficient, ;

[0111] Factor strength function The calculation formula is:

[0112] ;

[0113] in, For the Characteristic coefficients of environmental factors, For the Quasi-real-time environmental factors;

[0114] Multi-factor synergy The calculation formula is:

[0115] ;

[0116] in, is the synergistic amplification factor, is the synergistic function, The synergy factor represents the Environmental factors and The amplifying effect of the combination of similar environmental factors on risk;

[0117] Solar term transition function The calculation formula is:

[0118] ;

[0119] in, is the current solar term number, is the sequence number of the previous solar term before the current solar term. The next solar term number of the current solar term;

[0120] Time decay factor The calculation formula is:

[0121] ;

[0122] in, is the attenuation rate, , Indicates time. Various environmental factors do not change suddenly, but gradually decay, and the impact of sudden disasters (such as lightning) is controlled by time decay.

[0123] Line vulnerability The calculation formula is:

[0124] ;

[0125] in, is the insulation grade, Insulation grade The weight coefficient of is the tower strength, The tower strength The weight coefficient of is the terrain complexity, Terrain complexity The weight coefficient of is the altitude, is the altitude The weight coefficient of .

[0126] The present invention considers the smoothing weights, real-time intensity characteristics and multi-factor synergy of environmental factors under different climatic conditions, so that the risk assessment model can more accurately reflect the fault risk level of transmission lines in different environments. By introducing the solar term transition function and time attenuation factor, the model can take into account the impact of time changes and seasonal changes on fault risks, thereby improving the adaptability and flexibility of the model. Based on accurate risk assessment results, operation and maintenance personnel can formulate more scientific and reasonable operation and maintenance plans, give priority to high-risk areas and time periods, and improve operation and maintenance efficiency and resource utilization. By timely identifying and handling high-risk factors and taking targeted prevention and control measures, the failure probability and loss degree of transmission lines can be effectively reduced, and the safe and stable operation of the power system can be guaranteed.

[0127] Finally, the transient signal is used to locate the fault point. After the fault is located, the dynamic weight matrix is ​​optimized based on the comparison between the actual fault data and the predicted results. The method includes:

[0128] S401: filtering and denoising the transient signal captured by the transient signal collector, and extracting the fault characteristic frequency component;

[0129] S402: Establishing a fault location equation based on the multi-frequency ranging method to calculate the distance between the fault point and the monitoring point;

[0130] S403: Determine the tower number of the fault point based on GIS and send it to the maintenance personnel;

[0131] S404: Calculate the actual fault risk index based on the actual fault information recorded by the maintenance personnel, and calculate the error rate based on the actual fault risk index and the fault risk index output by the risk index model; and optimize the dynamic weight matrix when the error rate is greater than a preset error threshold.

[0132] Furthermore, steps S401 and S402 may directly adopt the traveling wave method, omitting the filtering and noise reduction process.

[0133] As a refinement of the above embodiment, the formula for optimizing the dynamic weight matrix is:

[0134] ;

[0135] in, After optimization Environmental factors in the The weight under each solar term, For the current Environmental factors in the The weight under each solar term, is the error rate About weight The partial derivative of is the learning rate.

[0136] The present invention captures transient signals through a transient signal collector and, after filtering and noise reduction processing, can effectively remove noise interference and extract the characteristic frequency components of the fault, thereby more accurately reflecting the electrical characteristics when the fault occurs. This provides a solid foundation for subsequent fault location. The fault location equation established based on the multi-frequency ranging method can accurately calculate the distance between the fault point and the monitoring point. Combined with GIS technology, the specific location of the fault point can be further determined, achieving rapid and accurate positioning of the fault point. Accurate fault location can quickly guide maintenance personnel to the fault site, reducing the time for troubleshooting and improving operation and maintenance efficiency. At the same time, the tower number determined by GIS technology allows maintenance personnel to directly locate specific transmission line equipment, further shortening maintenance time. After fault location, based on the comparison of actual fault data with the predicted results, the error of the prediction model can be discovered in a timely manner, and the prediction accuracy can be improved by optimizing the dynamic weight matrix, thereby avoiding ineffective operation and maintenance and waste of resources caused by inaccurate predictions. By optimizing the dynamic weight matrix, the risk prediction model can be better adapted to different environmental conditions and fault types, improving the generalization ability of the model. This helps operations personnel more accurately assess failure risks, develop effective prevention and control measures, and reduce the probability of failures. Optimizing the dynamic weight matrix is ​​an ongoing process. As actual failure data accumulates, the model will be continuously optimized and refined, further improving the accuracy of risk predictions.

[0137] It is important to emphasize that after a fault occurs, the rich frequency information in the transient signal is used to locate the fault. Fault location is to better modify the model parameters of the fault prediction function, so that faults can be predicted and prevented in advance, and the fault point can be quickly located after a fault occurs.

[0138] This paper combines the traditional Chinese 24 solar terms climate patterns with modern meteorological forecasts through dynamic spatiotemporal coupling to establish a dynamic weight matrix. This approach establishes a nonlinear synergistic mechanism, transcending traditional linear superposition and introducing the exponential amplification effect of the combined disaster C. This approach incorporates a dual temporal dimension: encompassing both the macroscopic solar term cycle (Γ) and the microscopic duration of the disaster (Φ).

[0139] In some embodiments, the transmission line fault prediction system 200 based on spatiotemporal information fusion may include a plurality of functional modules composed of computer program segments. The computer program of each program segment in the transmission line fault prediction system 200 based on spatiotemporal information fusion may be stored in a memory of a computer device and executed by at least one processor to perform (see Figure 1 Description) Transmission line fault prediction function based on spatiotemporal information fusion.

[0140] In this embodiment, the transmission line fault prediction system 200 based on spatiotemporal information fusion can be divided into multiple functional modules according to the functions it performs, such as Figure 2 As shown. The functional modules may include: a data acquisition module 210, a matrix construction module 220, a fault risk index calculation module 230, and a matrix optimization module 240. A module, as referred to in the present invention, refers to a series of computer program segments that can be executed by at least one processor and perform fixed functions, and is stored in a memory. In this embodiment, the functions of each module will be described in detail in subsequent embodiments.

[0141] Specifically, the data acquisition module is used to collect transient signals of the transmission line and multi-dimensional environmental data of the area in real time. The multi-dimensional environmental data includes meteorological parameters and geographical parameters. The matrix construction module is used to divide the time period based on the 24 solar terms, construct a dynamic weight matrix, and train the initial weights of various environmental factors in different solar terms through historical fault data. The fault risk index calculation module is used to input the collected multi-dimensional environmental data into the risk index model constructed based on the dynamic weight matrix to calculate the fault risk index of the transmission line. The matrix optimization module is used to locate the fault point using transient signals and, after the fault is located, optimize the dynamic weight matrix based on the comparison between the actual fault data and the predicted results.

[0142] Figure 3 This is a structural diagram of a terminal 300 provided in an embodiment of the present invention. The terminal 300 can be used to execute the transmission line fault prediction method based on spatiotemporal information fusion provided in an embodiment of the present invention.

[0143] The terminal 300 may include a processor 310, a memory 320, and a communication module 330. These components communicate via one or more buses. Those skilled in the art will appreciate that the server structure shown in the figure does not limit the present invention. The server structure may be a bus structure or a star structure, and may include more or fewer components than shown, or may combine certain components or arrange the components differently.

[0144] Memory 320 can be used to store execution instructions of processor 310. Memory 320 can be implemented by any type of volatile or non-volatile storage device, or a combination thereof, such as static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic memory, flash memory, magnetic disk, or optical disk. When the execution instructions in memory 320 are executed by processor 310, terminal 300 can perform some or all of the steps in the above-described method embodiments.

[0145] The processor 310 is the control center of the storage terminal. It uses various interfaces and lines to connect various parts of the entire electronic terminal. It runs or executes software programs and / or modules stored in the memory 320, and calls data stored in the memory to perform various functions of the electronic terminal and / or process data. The processor can be composed of an integrated circuit (IC), for example, it can be composed of a single packaged IC, or it can be composed of multiple packaged ICs with the same or different functions. For example, the processor 310 can only include a central processing unit (CPU). In an embodiment of the present invention, the CPU can be a single computing core or multiple computing cores.

[0146] The communication module 330 is used to establish a communication channel so that the storage terminal can communicate with other terminals, receive user data sent by other terminals, or send user data to other terminals.

[0147] In this specification, the same or similar parts between the various embodiments can be referred to each other. In particular, for the terminal embodiment, since it is basically similar to the method embodiment, the description is relatively simple, and the relevant parts can be referred to the description in the method embodiment.

[0148] In the several embodiments provided by the present invention, it should be understood that the disclosed systems and methods can be implemented in other ways. For example, the system embodiments described above are merely illustrative. For example, the division of the modules is merely a logical function division. In actual implementation, there may be other division methods, such as multiple modules or components can be combined or integrated into another system, or some features can be ignored or not executed. In addition, the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of systems or modules, and can be electrical, mechanical or other forms.

[0149] The modules described as separate components may or may not be physically separate, and the components shown as modules may or may not be physical modules, that is, they may be located in one place or distributed across multiple network modules. Some or all of the modules may be selected to achieve the purpose of the present embodiment according to actual needs.

[0150] In addition, each functional module in each embodiment of the present invention may be integrated into one processing module, or each module may exist physically separately, or two or more modules may be integrated into one module.

[0151] Although the present invention has been described in detail with reference to the accompanying drawings and in conjunction with preferred embodiments, the present invention is not limited thereto. Without departing from the spirit and essence of the present invention, persons of ordinary skill in the art may make various equivalent modifications or substitutions to the embodiments of the present invention, and such modifications or substitutions shall be within the scope of the present invention. Any changes or substitutions that can be easily conceived by persons skilled in the art within the technical scope disclosed in the present invention shall be within the scope of protection of the present invention.

Claims

1. A transmission line fault prediction method based on spatiotemporal information fusion, characterized in that: The following steps are involved: Real-time collection of transient signals of the transmission line and multi-dimensional environmental data of the area where the line is located, including meteorological parameters and geographical parameters; A dynamic weight matrix is ​​constructed based on historical fault data and the 24 solar terms. The dynamic weight matrix includes the initial weights of various environmental factors under different solar terms. Input the multi-dimensional environmental data collected in real time into the risk index model built based on the dynamic weight matrix to calculate the fault risk index of the transmission line; Use transient signals to locate fault points and optimize the dynamic weight matrix based on the comparison between actual fault data and predicted results; The step of obtaining the transient signal of the transmission line and the multi-dimensional environmental data of the area where the transmission line is located specifically includes: The meteorological parameters are collected through a distributed sensor array, including wind speed, rainfall, lightning frequency and ice thickness; The geographical parameters are obtained based on a geographic information system and include at least one of the geographical coordinates of the area where the transmission line is located, vegetation density, terrain slope, terrain complexity, altitude, and vegetation coverage; The transient signal is captured by a transient signal collector installed on a transmission line tower, including a transient current or voltage signal when a fault occurs; The constructing of the dynamic weight matrix comprises: determining a set of environmental factors, the set comprising wind speed, rainfall, lightning frequency, ice thickness, geographic coordinates, vegetation density, terrain slope, terrain complexity, altitude, and vegetation cover; The formula for calculating the initial weights of various environmental factors under different solar terms is: ， in, For the Environmental factors in the The initial weight under the solar term, For this solar term Number of failures caused by environmental factors, is the number of all environmental factors, is the historical credibility correction factor; Construct a dynamic weight matrix containing 24 solar terms weight vectors, where the rows correspond to solar terms and the columns correspond to environmental factors; The calculation formula of the risk index model is: ； in, is the failure risk index of the transmission line, The climate group in the dynamic weight matrix Neidi Smoothed weights of environmental-like factors, , is the factor intensity function, Indicates environmental factors, is a multi-factor synergistic term, represents the synergistic amplification factor, It represents the combination of the two most influential environmental factors among the environmental factors facing the current solar term. is the solar term transition function, is the time decay factor, Line vulnerability.

2. The method for predicting power transmission line faults based on spatiotemporal information fusion according to claim 1, characterized in that: The climate group The 24 solar terms are divided into ice group, lightning group, rainstorm group, strong wind group, warm and humid group and dry group according to their climatic characteristics. The solar terms are numbered in sequence according to the 24 solar terms table, as follows: Ice-covered group: Dahan, Xiaohan, Lidong, Xiaoxue, Dongzhi, Daxue; the central solar term is Dahan; Lightning Group: Summer Solstice, Lesser Heat, Early Days of Greater Heat, Beginning of Summer; the central solar term is Summer Solstice; Heavy rain group: Grain in Ear, Grain Rain, Grain Full, End of Heat; the central solar term is Grain in Ear; Gale Group: Spring Equinox, Qingming, Jingzhe, and White Dew; the central solar term is Qingming; Warm and humid group: Beginning of Spring, Rain Water, Frost Descent, Cold Dew; the central solar term is Cold Dew; Dry group: Beginning of Autumn, Autumnal Equinox, and late period of Great Heat; the central solar term is Autumnal Equinox.

3. The method for predicting power transmission line faults based on spatiotemporal information fusion according to claim 1, characterized in that: The smoothing weight calculation includes: ； in, For the climate group The number of solar terms included, is the solar term sequence number of the current solar term, For the climate group The solar term sequence number of the central solar term, is the attenuation coefficient, ; The factor intensity function is: ； in, For the Characteristic coefficients of environmental factors, For the Quasi-real-time environmental factors; The multi-factor synergy term is: ； in, is the synergistic amplification factor, is the synergistic function, The synergy factor represents the Environmental factors and The amplifying effect of the combination of similar environmental factors on risk, is the factor strength function; The solar term transition function is: ； in, is the sequence number of the previous solar term before the current solar term. The next solar term number of the current solar term; The time decay factor is: ； in, is the attenuation rate, , Indicates time; The line vulnerability is: ； in, is the insulation grade, Insulation grade The weight coefficient of is the tower strength, The tower strength The weight coefficient of is the terrain complexity, Terrain complexity The weight coefficient of is the altitude, is the altitude The weight coefficient of .

4. The method for predicting power transmission line faults based on spatiotemporal information fusion according to claim 2, characterized in that: The optimization dynamic weight matrix includes: Filter and reduce noise on transient signals and extract fault characteristic frequencies; Based on the multi-frequency ranging method, a fault location equation is established to calculate the distance between the fault point and the monitoring point; Use GIS to locate the actual fault tower location; The actual and predicted risk indices are compared, and the dynamic weight matrix is ​​updated when the error rate exceeds a threshold.

5. The method for predicting power transmission line faults based on spatiotemporal information fusion according to claim 4, characterized in that: The specific formula for updating the dynamic weight matrix is ​​as follows: ； in, After optimization Environmental factors in the The weight under each solar term, For the current Environmental factors in the The weight under each solar term, is the error rate About weight The partial derivative of is the learning rate.

6. A transmission line fault prediction system based on spatiotemporal information fusion using the method according to any one of claims 1 to 5, characterized in that: include: The data acquisition module is used to collect the transient signals of the transmission line and the multi-dimensional environmental data of the area in real time. The multi-dimensional environmental data includes meteorological parameters and geographical parameters; The matrix construction module is used to divide the time periods based on the 24 solar terms, construct a dynamic weight matrix, and train the initial weights of various environmental factors under different solar terms using historical fault data; A fault risk index calculation module is used to input the collected multi-dimensional environmental data into a risk index model built based on a dynamic weight matrix to calculate the fault risk index of the transmission line; The matrix optimization module is used to locate the fault point using transient signals and, after the fault is located, optimize the dynamic weight matrix based on the comparison between the actual fault data and the predicted results.

7. A terminal, characterized in that: include: processor; a memory for storing execution instructions of the processor; The processor is configured to execute the method according to any one of claims 1 to 5.

Images