Power transmission line hidden discharge hidden danger monitoring and early warning method and system
By configuring monitoring terminals on the transmission line, collecting and analyzing current data, and using variational modal decomposition and multi-scale convolutional neural network technology to identify and locate hidden danger discharges in real time, the problem of low efficiency in the current technology of hidden danger discharge resolution is solved. , improves the safety and operation and maintenance efficiency of the power grid.
Patent Information
- Application Number
- CN202410874979.9
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-07-02
- Publication Date
- 2024-12-06
AI Technical Summary
The existing methods for detecting hidden dangers and discharges of hidden dangers in transmission lines are costly and inefficient, making it difficult to detect and locate hidden dangers and discharge points in a timely and accurate manner.
The interval configuration monitoring terminal is adopted to collect transmission line data, and through frequency and time domain feature extraction, combined with variational modal decomposition and multi-scale convolutional neural network, we can identify the type of potential hazard discharge and locate the location of its occurrence in real time.
Real-time identification and rapid positioning of hidden danger discharge types is realized, which saves hidden danger classification and positioning time, improves maintenance efficiency, reduces operation and maintenance pressure, and ensures the safe and stable operation of the power grid.
Smart Images

Figure CN119093575A_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the field of electric power technology, and in particular to a method and system for monitoring and warning of potential discharge hazards in power transmission lines. Background Art
[0002] The scale of the power grid is becoming increasingly complex and large. Transmission lines are installed over a wide range, so it is inevitable that there are places with insulation hazards in the transmission corridor. Insulation hazards may cause discharge. If they are not discovered and cleared in time, they may develop into network failures and cause transmission lines to trip, seriously affecting the safe and stable operation of the power grid and social and economic development.
[0003] Traditional technology usually analyzes the type of discharge waveform through manual inspection and finds potential discharge points through field manual line inspection. This method will cause too heavy a burden on manual work, and it is also difficult for manual work to make timely and accurate judgments on the potential discharge currents of a large number of transmission lines, resulting in low efficiency. Summary of the invention
[0004] In view of the above-mentioned problems, the present invention is proposed.
[0005] Therefore, the technical problem solved by the present invention is: the existing technology and existing methods for distinguishing hidden dangers and discharges of power transmission lines have high costs, and how to solve the problem of low efficiency in distinguishing and finding hidden dangers and discharges of power transmission lines.
[0006] To solve the above technical problems, the present invention provides the following technical solutions: a method for monitoring and early warning of hidden dangers of discharge in power transmission lines, comprising configuring monitoring terminals at intervals along the transmission line to collect transmission line data.
[0007] The collected data is stored and the hidden danger information analysis results are output.
[0008] Determine the hidden danger type, location and time of hidden danger discharge of transmission line.
[0009] As a preferred solution of the method for monitoring and early warning of hidden dangers of discharge in transmission lines described in the present invention, it includes installing monitoring terminals at intervals along the transmission line, and each monitoring terminal is provided with a data acquisition module to collect current traveling wave data of the propagation of hidden dangers of discharge in the transmission line.
[0010] The current traveling wave data includes terminal number, voltage level, sampling rate, acquisition time, data length, and current waveform value.
[0011] As a preferred solution of the transmission line hidden danger discharge hazard monitoring and early warning method described in the present invention, it includes reading the hidden danger discharge current data collected in real time by the data acquisition module and reading out the sampling rate and current waveform value, providing data input for the hidden danger discharge type identification unit and the hidden danger discharge positioning unit.
[0012] The hidden danger discharge type identification unit is used to analyze the hidden danger discharge current waveform, perform frequency domain feature extraction and time domain feature extraction respectively, identify the hidden danger discharge type in real time and output the identification result.
[0013] The hidden danger discharge locating unit is used to obtain the time when the hidden danger discharge current traveling wave head reaches different monitoring terminals, calculate the time difference when the traveling wave head reaches each monitoring terminal, and calculate the position of the hidden danger discharge on the line segment in combination with the traveling wave propagation speed.
[0014] As a preferred solution of the transmission line hidden danger discharge hidden danger monitoring and early warning method described in the present invention, the output hidden danger information analysis result includes frequency domain feature extraction, using variational mode decomposition to extract the intrinsic mode function of the hidden danger discharge current, characterizing the multi-scale frequency domain characteristics of the hidden danger discharge, using VMD to extract the IMFs of the hidden danger discharge, and decomposing the input signal f(t) into k intrinsic mode components through VMD, which is expressed as:
[0015]
[0016] Among them, u k are the intrinsic mode components of the hidden danger discharge current waveform signal, A k (t) is u k The instantaneous amplitude of (t), is the instantaneous phase, and the eigenmode components are decomposed and expressed as:
[0017] Each modal function u k (t) is modulated to its corresponding baseband through Hilbert transform. The goal of the entire decomposition process is to minimize the objective function that traverses all modes and enhances sparsity, expressed as:
[0018]
[0019] Among them, {u k} represents the intrinsic mode function, {ω k ] represents the center frequency of each IMF, β represents the regularization parameter, δ(t) is the impulse function, Represents the partial derivative operation on time t.
[0020] As a preferred solution of the transmission line hidden danger discharge hidden danger monitoring and early warning method of the present invention, wherein: the output hidden danger information analysis result also includes time domain feature extraction, using a multi-scale convolutional neural network to extract the multi-scale time domain features of the IMFs of the hidden danger discharge, characterizing the multi-scale time-frequency composite features of the hidden danger discharge, and the extracted hidden danger discharge IMFs are respectively input into the corresponding convolutional neural network branches C s In the example, each branch outputs a feature map F s , expressed as:
[0021] F s =C s (IMFs)
[0022] The importance weight of each scale feature of the IMFs of the hidden danger discharge is calculated using the fully connected layer and the softmax layer, and the weighted combination is expressed as:
[0023]
[0024] Among them, FC(F s ) represents the sth eigenvector F s Through the output of a fully connected layer, the loss is calculated and the network parameters are updated. The input data passes through the network and the output of each layer is calculated until the final prediction output is obtained. Calculate the gradient of the loss function with respect to each parameter Given the predicted output And the true label y, calculate the cross entropy loss, expressed as:
[0025]
[0026] Where C is the number of categories, α c and γ are the weight and adjustment parameters for category c, respectively. The Adam optimization algorithm is used to update the network parameters according to the gradient of the loss function, which is expressed as:
[0027]
[0028] Among them, θ new represents the updated network parameters, θ old represents the network parameters before updating, η represents the learning rate, represents the gradient of the loss function.
[0029] As a preferred solution of the method for monitoring and early warning of hidden dangers of transmission line discharge according to the present invention, the method for determining the hidden danger type, location and time of hidden danger occurrence of hidden danger discharge of the transmission line includes calculating the Teager energy spectrum of the hidden danger discharge using the Teager energy operator according to the hidden danger discharge current waveform sequence, calibrating the first singular point of the energy spectrum, reading the traveling wave waveform data, applying differential operation to the signal I(n), obtaining I(n-1) and I(n+1), and calculating the Teager energy value, which is expressed as:
[0030] Ψ(I(n))=I 2 (n)-I(n-1)I(n+1)
[0031] Among them, I(n) is the signal value of the current waveform sequence at time n, I(n-1) and I(n+1) are the signal values at the previous moment and the next moment respectively. The cycle is repeated until the energy calculation of the entire signal sequence is completed to obtain the Teager energy spectrum of the signal.
[0032] Calculate the transmission line arrival time difference matrix △T and the hidden danger discharge time difference matrix △t. The transmission line arrival time difference matrix in the time difference matrix calculation unit is divided into transmission lines according to the fixed interval length △l. There are i division points. Calculate each division point p i The distance to each monitoring terminal of the transmission line, assuming that there are j monitoring terminals in the line and o j Representation, construct the matrix:
[0033]
[0034] L is the traveling wave path matrix. According to the actual line parameters, the traveling wave velocity is calculated. The elements in L are divided by the traveling wave velocity v1 to obtain the traveling wave propagation time matrix on each path:
[0035]
[0036] Extract the jth column vector in T (j∈{1,2,…,m}) and construct the traveling wave from node p j The arrival time difference matrix when propagating to the end of each line:
[0037]
[0038] Compare the difference between the transmission line arrival time difference matrix △T and the hidden danger discharge time difference matrix Δt. The point corresponding to the △T with the smallest difference from △t is the location where the hidden danger discharge occurs. j -Δt's F-norm, the ΔT corresponding to the minimum value j The corresponding division points are considered to be the hidden danger occurrence points, which are expressed as:
[0039] min{||ΔT j-Δt|| F}
[0040] The information on hidden danger occurrence points is stored and displayed.
[0041] As a preferred solution of the transmission line hidden danger discharge hidden danger monitoring and early warning method described in the present invention, wherein: the storage and display of the hidden danger occurrence point information includes obtaining the latest hidden danger discharge data related information from the data storage module, including terminal number, voltage level, sampling rate, acquisition time, data length, current waveform value, hidden danger type, and visualizing the information obtained by the information acquisition unit on a web page to provide it to operation and maintenance personnel for search and query.
[0042] Another object of the present invention is to provide a transmission line hidden danger discharge hazard monitoring and early warning system, which can identify the hidden danger discharge type and quickly locate the hidden danger discharge point, saving a lot of hidden danger classification time and hidden danger location time, and solving the problem of low efficiency of current transmission line hidden danger discharge identification technology.
[0043] As a preferred solution of the power transmission line hidden danger discharge hidden danger monitoring and early warning system described in the present invention, it includes: a data acquisition module, a data storage module, a hidden danger information generation module, an early warning report generation module, and a hidden danger information display module.
[0044] The path planning module is used to configure monitoring terminals at intervals along the transmission line to collect transmission line data.
[0045] The data storage module is used to store the transmission line hidden danger discharge current traveling wave waveform data collected by each monitoring terminal and the analysis results output by the hidden danger information generation module.
[0046] The hidden danger information generation module is used to determine the hidden danger type, hidden danger occurrence location and hidden danger occurrence time of hidden danger discharge of the transmission line.
[0047] The warning report generation module is used to generate a warning report according to the type, location and time of occurrence of hidden danger discharge of the transmission line.
[0048] The hidden danger information display module is used to visualize the results output by the hidden danger information generation module.
[0049] A computer device includes a memory and a processor, wherein the memory stores a computer program, and the processor executes the computer program to implement a method for monitoring and warning of hidden dangers of power transmission lines and discharge hazards.
[0050] A computer-readable storage medium stores a computer program, which, when executed by a processor, implements the steps of a method for monitoring and early warning of hidden dangers of power transmission lines and discharge hazards.
[0051] Beneficial effects of the present invention: The transmission line hidden danger discharge hidden danger monitoring and early warning method provided by the present invention can identify the hidden danger discharge type in real time and quickly locate the hidden danger discharge point, saving a lot of hidden danger classification time and hidden danger location time, providing a reference for hidden danger removal and maintenance of operation and maintenance personnel, reducing the pressure of operation and maintenance personnel, and improving maintenance efficiency, ensuring the safe and stable operation of the power grid. The present invention achieves better results in terms of efficiency and cost. BRIEF DESCRIPTION OF THE DRAWINGS
[0052] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the accompanying drawings required for use in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other accompanying drawings can be obtained based on these accompanying drawings without paying creative work.
[0053] Figure 1 An overall flow chart of a method for monitoring and early warning of potential discharge hazards in power transmission lines provided in the first embodiment of the present invention.
[0054] Figure 2 An overall flow chart of a transmission line hidden danger discharge hidden danger monitoring and early warning system provided for the third embodiment of the present invention. DETAILED DESCRIPTION
[0055] In order to make the above-mentioned purposes, features and advantages of the present invention more obvious and easy to understand, the specific implementation methods of the present invention are described in detail below in conjunction with the drawings of the specification. Obviously, the described embodiments are part of the embodiments of the present invention, but not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary persons in the art without creative work should fall within the scope of protection of the present invention.
[0056] Example 1
[0057] Reference Figure 1 , which is an embodiment of the present invention, provides a method for monitoring and early warning of hidden dangers of power transmission lines and discharge hazards, comprising:
[0058] S1: Monitoring terminals are installed at intervals along the transmission line to collect transmission line data.
[0059] Furthermore, monitoring terminals are installed at intervals along the transmission line, and each monitoring terminal is provided with a data acquisition module to collect current traveling wave data of the propagation of hidden danger discharge of the transmission line.
[0060] The current traveling wave data includes terminal number, voltage level, sampling rate, acquisition time, data length, and current waveform value.
[0061] S2: Store the collected data and output the hidden danger information analysis results.
[0062] Furthermore, it includes reading the hidden danger discharge current data collected in real time by the data collection module and reading out the sampling rate and current waveform value, so as to provide data input for the hidden danger discharge type identification unit and the hidden danger discharge positioning unit.
[0063] The hidden danger discharge type identification unit is used to analyze the hidden danger discharge current waveform, perform frequency domain feature extraction and time domain feature extraction respectively, identify the hidden danger discharge type in real time and output the identification result.
[0064] The hidden danger discharge locating unit is used to obtain the time when the hidden danger discharge current traveling wave head reaches different monitoring terminals, calculate the time difference when the traveling wave head reaches each monitoring terminal, and calculate the position of the hidden danger discharge on the line segment in combination with the traveling wave propagation speed.
[0065] It should be noted that the output of hidden danger information analysis results includes frequency domain feature extraction, using variational mode decomposition to extract the intrinsic mode function of hidden danger discharge current, characterizing the multi-scale frequency domain characteristics of hidden danger discharge, using VMD to extract IMFs of hidden danger discharge, and decomposing the input signal f(t) into k intrinsic mode components through VMD, which can be expressed as:
[0066]
[0067] Among them, u k are the intrinsic mode components of the hidden danger discharge current waveform signal, A k (t) is u k The instantaneous amplitude of (t), is the instantaneous phase, and the eigenmode components are decomposed and expressed as:
[0068] Each modal function u k (t) is modulated to its corresponding baseband through Hilbert transform. The goal of the entire decomposition process is to minimize the objective function that traverses all modes and enhances sparsity, expressed as:
[0069]
[0070] Among them, {u k} represents the intrinsic mode function, which is the function decomposed from the hidden danger discharge current waveform signal f(t). Each function u k (t) Capture a specific frequency component of the signal {ω k} represents the center frequency of each IMF, β represents the regularization parameter. By adjusting the size of β, the number of non-zero components in the IMFs can be controlled, thereby improving the separation between modes. δ(t) is the impulse function. Represents the partial derivative operation on time t.
[0071] It should also be noted that the output of the hidden danger information analysis results also includes time domain feature extraction. The multi-scale time domain features of the IMFs of the hidden danger discharge are extracted using a multi-scale convolutional neural network to characterize the multi-scale time-frequency composite features of the hidden danger discharge. The extracted hidden danger discharge IMFs are respectively input into the corresponding convolutional neural network branches C s In the example, each branch outputs a feature map F s , expressed as:
[0072] F s =C s (IMFs)
[0073] The importance weight of each scale feature of the IMFs of the hidden danger discharge is calculated using the fully connected layer and the softmax layer, and the weighted combination is expressed as:
[0074]
[0075] Among them, FC(F s ) represents the sth eigenvector F s The output of a fully connected layer may include a linear transformation, usually of the form W s ·F s +b s , where W s and b s The weight matrix and bias term are used to calculate the loss and update the network parameters. The input data passes through the network and the output of each layer is calculated until the final prediction output is obtained. Calculate the gradient of the loss function with respect to each parameter Given the predicted output And the true label y, calculate the cross entropy loss, expressed as:
[0076]
[0077] Where C is the number of categories, α c and γ are the weight and adjustment parameters for category c, respectively. The Adam optimization algorithm is used to update the network parameters according to the gradient of the loss function, which is expressed as:
[0078]
[0079] Among them, θ new represents the updated network parameters, θ old represents the network parameters before updating, η represents the learning rate, represents the gradient of the loss function.
[0080] S3: Determine the type of hidden danger of transmission line discharge, the location of the hidden danger and the time of the hidden danger.
[0081] Furthermore, determining the hidden danger type, location and time of hidden danger discharge of the transmission line includes calculating the Teager energy spectrum of the hidden danger discharge using the Teager energy operator according to the hidden danger discharge current waveform sequence, calibrating the first singular point of the energy spectrum, reading the traveling wave waveform data, applying the differential operation to the signal I(n), obtaining I(n-1) and I(n+1), and calculating the Teager energy value, which is expressed as:
[0082] Ψ(I(n))=I 2 (n)-I(n-1)I(n+1)
[0083] Among them, I(n) is the signal value of the current waveform sequence at time n, I(n-1) and I(n+1) are the signal values at the previous moment and the next moment respectively. The cycle is repeated until the energy calculation of the entire signal sequence is completed to obtain the Teager energy spectrum of the signal.
[0084] Calculate the transmission line arrival time difference matrix △T and the hidden danger discharge time difference matrix △t. The transmission line arrival time difference matrix in the time difference matrix calculation unit is divided into transmission lines according to the fixed interval length △l. There are i division points. Calculate each division point p i The distance to each monitoring terminal of the transmission line, assuming that there are j monitoring terminals in the line and o j Representation, construct the matrix:
[0085]
[0086] L is the traveling wave path matrix. According to the actual line parameters, the traveling wave velocity is calculated. The elements in L are divided by the traveling wave velocity v1 to obtain the traveling wave propagation time matrix on each path:
[0087]
[0088] Extract the jth column vector in T (j∈{1,2,…,m}) and construct the traveling wave from node p j The arrival time difference matrix when propagating to the end of each line:
[0089]
[0090] Compare the difference between the transmission line arrival time difference matrix △T and the hidden danger discharge time difference matrix Δt. The point corresponding to the △T with the smallest difference from △t is the location where the hidden danger discharge occurs. j -Δt F-norm, ΔT corresponding to the minimum value j The corresponding division points are considered to be the hidden danger occurrence points, which are expressed as:
[0091] min{||ΔT j -Δt||F}
[0092] The information on hidden danger occurrence points is stored and displayed.
[0093] It should be noted that the latest hidden danger discharge data related information is obtained from the data storage module, including terminal number, voltage level, sampling rate, acquisition time, data length, current waveform value, hidden danger type, and the information obtained by the information acquisition unit is visualized on the web page and provided to operation and maintenance personnel for search and query.
[0094] Example 2
[0095] An embodiment of the present invention provides a method for monitoring and early warning of hidden dangers of discharge in power transmission lines. In order to verify the beneficial effects of the present invention, scientific demonstration is carried out through economic benefit calculation and simulation experiments.
[0096] First, the system's responsiveness and accuracy were tested by simulating different types of hidden discharge events on the transmission line. The experiment was set up in a controlled environment, with high-precision sensors installed along a 500-kilometer simulated transmission line, with a monitoring terminal set up every 50 kilometers. Each monitoring terminal was equipped with a data acquisition module that could capture and record current waveform data.
[0097] Table 1 Experimental data table
[0098]
[0099]
[0100] Referring to Table 1, it can be seen that our invention can basically replace manual work. By analyzing the synergy of frequency domain and time domain features in detail, we found that the two have different contributions to the identification of different types of hidden dangers. For arc discharge (test numbers 1, 3, 4, etc.), frequency domain feature extraction shows a higher recognition accuracy because it can accurately capture high-frequency changes. Relatively speaking, the characteristics of ground faults (test numbers 2, 5, 7, etc.) are more reflected in time domain changes, so the time domain recognition accuracy is more critical.
[0101] Example 3
[0102] Reference Figure 2 , as an embodiment of the present invention, provides a transmission line hidden danger discharge hidden danger monitoring and early warning system, including a data acquisition module, a data storage module, a hidden danger information generation module, an early warning report generation module, and a hidden danger information display module.
[0103] Among them, the path planning module is used to configure monitoring terminals at intervals along the transmission line to collect transmission line data. The data storage module is used to store the transmission line hidden danger discharge current traveling wave waveform data collected by each monitoring terminal and the analysis results output by the hidden danger information generation module. The hidden danger information generation module is used to determine the hidden danger type, hidden danger location, and hidden danger occurrence time of the transmission line hidden danger discharge. The early warning report generation module is used to generate an early warning report based on the type, location, and time of the transmission line hidden danger discharge. The hidden danger information display module is used to visualize the results output by the hidden danger information generation module.
[0104] If the function is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, or the part that contributes to the prior art, or the part of the technical solution, can be embodied in the form of a software product. The computer software product is stored in a storage medium, including several instructions for a computer device (which can be a personal computer, server, or network device, etc.) to perform all or part of the steps of the methods of each embodiment of the present invention. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), disk or optical disk, etc. Various media that can store program codes.
[0105] The logic and / or steps represented in the flowchart or otherwise described herein, for example, can be considered as an ordered list of executable instructions for implementing logical functions, and can be embodied in any computer-readable medium for use by an instruction execution system, device or apparatus (such as a computer-based system, a system including a processor, or other system that can fetch instructions from an instruction execution system, device or apparatus and execute instructions), or in conjunction with such instruction execution systems, devices or apparatuses. For the purposes of this specification, "computer-readable medium" can be any device that can contain, store, communicate, propagate or transmit a program for use by an instruction execution system, device or apparatus, or in conjunction with such instruction execution systems, devices or apparatuses.
[0106] More specific examples of computer-readable media (a non-exhaustive list) include the following: an electrical connection with one or more wires (electronic device), a portable computer disk case (magnetic device), a random access memory (RAM), a read-only memory (ROM), an erasable and programmable read-only memory (EPROM or flash memory), an optical fiber device, and a portable compact disk read-only memory (CDROM). In addition, the computer-readable medium may even be a paper or other suitable medium on which the program is printed, since the program may be obtained electronically, for example, by optically scanning the paper or other medium, followed by editing, deciphering, or processing in another suitable manner as necessary, and then stored in a computer memory.
[0107] It should be understood that the various parts of the present invention can be implemented by hardware, software, firmware or a combination thereof. In the above-mentioned embodiments, multiple steps or methods can be implemented by software or firmware stored in a memory and executed by a suitable instruction execution system. For example, if implemented by hardware, as in another embodiment, it can be implemented by any one of the following technologies known in the art or their combination: a discrete logic circuit having a logic gate circuit for implementing a logic function for a data signal, a dedicated integrated circuit having a suitable combination of logic gate circuits, a programmable gate array (PGA), a field programmable gate array (FPGA), etc. It should be noted that the above embodiments are only used to illustrate the technical solution of the present invention and are not limited. Although the present invention is described in detail with reference to the preferred embodiments, it should be understood by those skilled in the art that the technical solution of the present invention can be modified or replaced by equivalents without departing from the spirit and scope of the technical solution of the present invention, which should be included in the scope of the claims of the present invention.
[0108] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention rather than to limit it. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical solutions of the present invention may be modified or replaced by equivalents without departing from the spirit and scope of the technical solutions of the present invention, which should all be included in the scope of the claims of the present invention.
Claims
1. A method for monitoring and early warning of hidden dangers of power transmission lines and discharge hazards. It is characterized in that include: Monitoring terminals are deployed at intervals along the transmission lines to collect transmission line data; Store the collected data and output the hidden danger information analysis results; Determine the hidden danger type, location and time of hidden danger discharge of transmission line.
2. The method for monitoring and early warning of potential discharge hazards of power transmission lines as claimed in claim 1, Features: The method includes installing monitoring terminals at intervals along the transmission line, each monitoring terminal is provided with a data acquisition module to collect current traveling wave data of the transmission line hidden danger discharge propagation; The current traveling wave data includes terminal number, voltage level, sampling rate, acquisition time, data length, and current waveform value.
3. The method for monitoring and early warning of potential discharge hazards of power transmission lines as claimed in claim 2, Features: The method includes reading the hidden danger discharge current data collected in real time by the data collection module and reading the sampling rate and current waveform value, providing data input for the hidden danger discharge type identification unit and the hidden danger discharge positioning unit; The hidden danger discharge type identification unit is used to analyze the hidden danger discharge current waveform, perform frequency domain feature extraction and time domain feature extraction respectively, identify the hidden danger discharge type in real time and output the identification result; The hidden danger discharge locating unit is used to obtain the time when the hidden danger discharge current traveling wave head reaches different monitoring terminals, calculate the time difference when the traveling wave head reaches each monitoring terminal, and calculate the position of the hidden danger discharge on the line segment in combination with the traveling wave propagation speed.
4. The method for monitoring and early warning of potential discharge hazards of power transmission lines as claimed in claim 3, Features: The output hidden danger information analysis results include frequency domain feature extraction, using variational mode decomposition to extract the intrinsic mode function of the hidden danger discharge current, characterizing the multi-scale frequency domain characteristics of the hidden danger discharge, using VMD to extract the IMFs of the hidden danger discharge, and decomposing the input signal f(t) into k intrinsic mode components through VMD, which is expressed as: Among them, u k are the intrinsic mode components of the hidden danger discharge current waveform signal, A k (t) is u k The instantaneous amplitude of (t), is the instantaneous phase, and the eigenmode components are decomposed and expressed as: Each modal function u k (t) is modulated to its corresponding baseband through Hilbert transform. The goal of the entire decomposition process is to minimize the objective function that traverses all modes and enhances sparsity, expressed as: Among them, {u k } represents the intrinsic mode function, {ω k } represents the center frequency of each IMF, β represents the regularization parameter, δ(t) is the impulse function, Represents the partial derivative operation with respect to time t.
5. The method for monitoring and early warning of potential discharge hazards of power transmission lines as claimed in claim 4, Features: The output of the hidden danger information analysis result also includes time domain feature extraction, using a multi-scale convolutional neural network to extract the multi-scale time domain features of the IMFs of the hidden danger discharge, characterizing the multi-scale time-frequency composite features of the hidden danger discharge, and inputting the extracted hidden danger discharge IMFs into the corresponding convolutional neural network branches C s In the example, each branch outputs a feature map F s , expressed as: F s =C s (IMFs) The importance weight of each scale feature of the IMFs of the hidden danger discharge is calculated using the fully connected layer and the softmax layer, and the weighted combination is expressed as: Among them, FC(F s ) represents the sth eigenvector F s Through the output of a fully connected layer, the loss is calculated and the network parameters are updated. The input data passes through the network and the output of each layer is calculated until the final prediction output is obtained. Calculate the gradient of the loss function with respect to each parameter Given the predicted output And the true label y, calculate the cross entropy loss, expressed as: Where C is the number of categories, α c and γ are the weight and adjustment parameters for category c, respectively. The Adam optimization algorithm is used to update the network parameters according to the gradient of the loss function, which is expressed as: Among them, θ new represents the updated network parameters, θ old represents the network parameters before updating, η represents the learning rate, represents the gradient of the loss function.
6. The method for monitoring and early warning of potential discharge hazards of power transmission lines as claimed in claim 5, Features: The method of determining the hidden danger type, hidden danger occurrence location and hidden danger occurrence time of the transmission line hidden danger discharge comprises calculating the Teager energy spectrum of the hidden danger discharge using the Teager energy operator according to the hidden danger discharge current waveform sequence, calibrating the first singular point of the energy spectrum, reading the traveling wave waveform data, applying a differential operation to the signal I(n) to obtain I(n-1) and I(n+1), and calculating the Teager energy value, which is expressed as: Ψ(I(n))=I 2 (n)-I(n-1)I(n+1) Among them, I(n) is the signal value of the current waveform sequence at time n, I(n-1) and I(n+1) are the signal values at the previous and next moments respectively, and the cycle is repeated until the energy calculation of the entire signal sequence is completed to obtain the Teager energy spectrum of the signal; Calculate the transmission line arrival time difference matrix △T and the hidden danger discharge time difference matrix △t. The transmission line arrival time difference matrix in the time difference matrix calculation unit is divided into transmission lines according to the fixed interval length △l. There are i division points. Calculate each division point p i The distance to each monitoring terminal of the transmission line, assuming that there are j monitoring terminals in the line and o j Representation, construct the matrix: L is the traveling wave path matrix. According to the actual line parameters, the traveling wave velocity is calculated by dividing the elements in L by the traveling wave velocity v 1 , we get the propagation time matrix of the traveling wave on each path: Extract the jth column vector in T (j∈{1,2,…,m}) and construct the traveling wave from node p j The arrival time difference matrix when propagating to the end of each line: Compare the difference between the transmission line arrival time difference matrix △T and the hidden danger discharge time difference matrix Δt. The point corresponding to the △T with the smallest difference from △t is the location where the hidden danger discharge occurs. j -Δt F-norm, ΔT corresponding to the minimum value j The corresponding division points are considered to be the hidden danger occurrence points, which are expressed as: min{||ΔT j -Δt|| F } The information on hidden danger occurrence points is stored and displayed.
7. The method for monitoring and early warning of potential discharge hazards of power transmission lines as claimed in claim 6, Features: The storing and displaying of the hidden danger occurrence point information includes obtaining the latest hidden danger discharge data related information from the data storage module, including terminal number, voltage level, sampling rate, acquisition time, data length, current waveform value, hidden danger type, and visualizing the information obtained by the information acquisition unit on a web page to provide it to operation and maintenance personnel for search and query.
8. A system using the method for monitoring and early warning of potential discharge hazards of power transmission lines as claimed in any one of claims 1 to 7, Features: It includes data acquisition module, data storage module, hidden danger information generation module, early warning report generation module and hidden danger information display module; The path planning module is used to configure monitoring terminals at intervals along the transmission line to collect transmission line data; The data storage module is used to store the transmission line hidden danger discharge current traveling wave waveform data collected by each monitoring terminal and the analysis results output by the hidden danger information generation module; The hidden danger information generation module is used to determine the hidden danger type, hidden danger occurrence location, and hidden danger occurrence time of the hidden danger discharge of the transmission line; The warning report generation module is used to generate a warning report according to the type, location and time of the hidden danger discharge of the transmission line; The hidden danger information display module is used to visualize the results output by the hidden danger information generation module.
9. A computer device comprising a memory and a processor, wherein the memory stores a computer program. It is characterized in that When the processor executes the computer program, the steps of the method for monitoring and early warning of hidden dangers of power transmission lines according to any one of claims 1 to 7 are implemented.
10. A computer-readable storage medium having a computer program stored thereon, It is characterized in that When the computer program is executed by a processor, the steps of the method for monitoring and early warning of hidden dangers of power transmission lines and discharge hazards described in any one of claims 1 to 7 are implemented.
Citation Information
Cited By
Power transmission line channel potential safety hazard monitoring and early warning method and equipment
CN121456819A
