New energy power station transmission line fault positioning method, device, equipment and medium

Abstract

The embodiment of the invention discloses a new energy power station transmission line fault positioning method and device, equipment and a medium. A specific embodiment of the method comprises the following steps: acquiring a transmission line fault information set and power system topology information; performing multi-channel modal decomposition on the transmission line fault information set, and then performing adaptive signal decomposition to obtain a line fault frequency band information set; determining a line frequency band multi-dimensional fusion entropy set; carrying out traveling wave dispersion compensation on the transmission line fault traveling wave information to obtain compensated transmission line fault traveling wave information; determining an initial line fault distance information set; generating a transmission line section fault probability set; and generating line fault isolation instruction information, and controlling a corresponding circuit breaker set on the transmission line to perform transmission line disconnection processing. According to the embodiment, the cascading trip problem caused by step voltage can be effectively eliminated, the fault positioning accuracy of the new energy power station and the timeliness of timely fault isolation are improved, and the loss rate of the new energy power station is reduced.

Description

Technical Field

[0001] The embodiments disclosed herein relate to the field of computer technology, specifically to a method, apparatus, equipment, and medium for locating faults in transmission lines of new energy power plants. Background Technology

[0002] Driven by the "dual carbon" goal, the scale of new energy power plants such as wind power and photovoltaic power is constantly expanding, and the power grid structure is becoming increasingly complex, becoming an important part of the power supply system. However, the surge in grid-to-ground capacitance current has led to frequent single-phase grounding faults that are difficult to isolate quickly, resulting in significant consumption of power resources. Transmission lines are the key channels connecting new energy power plants and distribution networks, and their stable operation directly affects the power generation efficiency of the power plants and the reliability of the power supply from the distribution network. The common method for fault location in new energy power grid transmission lines is as follows: First, obtain the power plant power information (e.g., zero-sequence voltage, traveling wave signal) from the new energy power plant's distribution network coordination system. Then, use a harmonic analysis algorithm to extract fault features from the power plant power information to obtain a set of power fault signals. Next, use a traveling wave algorithm to locate the fault in the aforementioned power fault signal set to obtain the line fault location information. Finally, using the line fault location information, control the corresponding set of circuit breakers on the transmission line to disconnect the transmission line.

[0003] However, in practice, it has been found that when using the above methods to locate faults in the transmission lines of new energy power plants, the following technical problems often arise: Because the data obtained from only the power plant and grid power information is too singular and one-sided, the power fault information extracted by the harmonic analysis algorithm contains a large amount of mixed mode information, resulting in low quality power fault signals. Furthermore, when using the traveling wave algorithm for fault location, high-frequency components gradually disappear with the distance of the transmission line, causing a shift in the traveling wave peak. This leads to low accuracy in fault location of the transmission line, reduces the timeliness of isolating power faults, and results in higher losses for new energy power plants and higher line losses for transmission lines.

[0004] The information disclosed in this background section is only intended to enhance the understanding of the background of the present disclosure concept, and therefore may contain information that does not constitute prior art known to those skilled in the art. Summary of the Invention

[0005] The summary portion of this disclosure is intended to provide a brief overview of the concepts, which will be described in detail in the detailed description portion. This summary portion is not intended to identify key or essential features of the claimed technical solutions, nor is it intended to limit the scope of the claimed technical solutions.

[0006] Some embodiments of this disclosure propose methods, devices, equipment, and media for locating faults in transmission lines of new energy power plants to solve one or more of the technical problems mentioned in the background section above.

[0007] In a first aspect, some embodiments of this disclosure provide a method for locating faults in transmission lines of a new energy power grid, comprising: acquiring a transmission line fault information set and power system topology information of a new energy power plant distribution network coordination system through a data acquisition sensor set synchronized with a clock; performing multi-channel mode decomposition processing on the aforementioned transmission line fault information set to obtain a transmission line fault mode signal information set; performing adaptive signal decomposition on the aforementioned transmission line fault mode signal information set to obtain a line fault frequency band information set; determining the line frequency band multi-dimensional fusion entropy of each line fault frequency band information in the aforementioned line fault frequency band information set to obtain a line frequency band multi-dimensional fusion entropy set; and determining the line frequency band multi-dimensional fusion entropy based on the aforementioned line frequency band multi-dimensional fusion entropy set. Based on the aforementioned power system topology information, traveling wave dispersion compensation is performed on the traveling wave information of the transmission line faults in the aforementioned transmission line fault information set to obtain compensated traveling wave information of the transmission line faults. Based on the compensated traveling wave information of the transmission line faults and the aforementioned multi-dimensional fusion entropy set of the line frequency band, an initial line fault distance information set is determined. Based on the aforementioned multi-dimensional fusion entropy set of the line frequency band, the aforementioned initial line fault distance information set, and the aforementioned power system topology information, a transmission line segment fault probability set is generated. Based on the aforementioned transmission line segment fault probability set, line fault isolation command information is generated, and based on the aforementioned line fault isolation command information, the corresponding set of circuit breakers on the transmission line is controlled to disconnect the transmission line.

[0008] Secondly, some embodiments of this disclosure provide a fault location device for a new energy power grid transmission line, comprising: an acquisition unit configured to acquire a transmission line fault information set and power system topology information of a new energy power station distribution network collaborative system through a data acquisition sensor set synchronized with a clock; a multi-channel mode decomposition unit configured to perform multi-channel mode decomposition processing on the aforementioned transmission line fault information set to obtain a transmission line fault mode signal information set; an adaptive signal decomposition unit configured to perform adaptive signal decomposition on the aforementioned transmission line fault mode signal information set to obtain a line fault frequency band information set; a first determination unit configured to determine the line frequency band multi-dimensional fusion entropy of each line fault frequency band information in the aforementioned line fault frequency band information set to obtain a line frequency band multi-dimensional fusion entropy set; and a traveling wave dispersion compensation unit configured to... Based on the aforementioned multi-dimensional fusion entropy set of the transmission line frequency band and the aforementioned power system topology information, traveling wave dispersion compensation is performed on the traveling wave information of the transmission line fault in the aforementioned transmission line fault information set to obtain compensated transmission line fault traveling wave information; the second determining unit is configured to determine an initial line fault distance information set based on the aforementioned compensated transmission line fault traveling wave information and the aforementioned multi-dimensional fusion entropy set of the transmission line frequency band; the generating unit is configured to generate a transmission line segment fault probability set based on the aforementioned multi-dimensional fusion entropy set of the transmission line frequency band, the aforementioned initial line fault distance information set, and the aforementioned power system topology information; the transmission line disconnection unit is configured to generate line fault isolation command information based on the aforementioned transmission line segment fault probability set, and control the corresponding circuit breaker set on the transmission line to perform transmission line disconnection processing based on the aforementioned line fault isolation command information.

[0009] Thirdly, some embodiments of this disclosure provide an electronic device, including: one or more processors; and a storage device having one or more programs stored thereon, such that when the one or more programs are executed by the one or more processors, the one or more processors implement the method as described in any implementation of the first aspect.

[0010] Fourthly, some embodiments of this disclosure provide a computer-readable medium having a computer program stored thereon, wherein the computer program, when executed by a processor, implements the method as described in any implementation of the first aspect.

[0011] The above-described embodiments of this disclosure have the following beneficial effects: The fault location method for new energy power plant transmission lines in some embodiments of this disclosure avoids the annihilation of fault current characteristics caused by the arc suppression coil stage, eliminates the cascading tripping problem caused by step voltage, improves the accuracy of fault location in new energy power plants and the timeliness of timely fault isolation, and reduces the loss rate of new energy power plants. Specifically, the reasons for the low accuracy of fault location in related transmission lines, reduced timeliness of power fault isolation, higher losses in new energy power plants, and higher line losses in transmission lines are: the data obtained from only the power plant and grid power information is too singular and one-sided; the power fault information extracted by the harmonic analysis algorithm contains a large amount of mixed modal information, resulting in low quality of the power fault signal; and when using the traveling wave algorithm for fault location, high-frequency components gradually annihilate with the distance of the transmission line, causing the traveling wave peak to shift, leading to low accuracy of fault location in transmission lines, reduced timeliness of power fault isolation, higher losses in new energy power plants, and higher line losses in transmission lines. Based on this, some embodiments of the new energy power plant transmission line fault location method of this disclosure can firstly acquire the transmission line fault information set and power system topology information of the new energy power plant distribution network coordination system through a data acquisition sensor set synchronized with the clock. Here, acquiring the transmission line fault information set and power system topology information, and including both electrical and non-electrical information of the new energy power plant distribution network coordination system, can improve the comprehensiveness of the acquired data and avoid the one-sidedness of single data. Secondly, multi-channel mode decomposition processing is performed on the aforementioned transmission line fault information set to obtain the transmission line fault mode signal information set. Here, mode decomposition processing can effectively suppress the signal frequency aliasing problem in the transmission line fault information set and improve the quality of the transmission line fault mode signals. Thirdly, adaptive signal decomposition is performed on the aforementioned transmission line fault mode signal information set to obtain the line fault frequency band information set. Here, adaptive signal decomposition can improve the optimization of selecting the most suitable signal decomposition level based on the actual scenario characteristics of the transmission line fault information set, achieving focusing on the sensitive frequency band of specific fault features, improving the pertinence and accuracy of signal decomposition, and suppressing the annihilation of fault features. Next, the multi-dimensional fusion entropy of each line fault frequency band in the aforementioned line fault frequency band information set is determined, resulting in a multi-dimensional fusion entropy set of the line frequency band. Here, the output line fault signal frequency band information set, which is difficult to identify due to transient waveforms, can be transformed into an intuitive and quantifiable energy distribution map, facilitating subsequent fault location. Subsequently, based on the aforementioned multi-dimensional fusion entropy set of the line frequency band and the aforementioned power system topology information, traveling wave dispersion compensation is performed on the traveling wave information of the transmission line faults in the aforementioned transmission line fault information set, resulting in compensated traveling wave information of the transmission line faults.Here, by combining multi-dimensional fusion entropy sets of line frequency bands with multi-faceted data from power system topology information, the distortion problem of traveling wave signals during transmission circuit transmission can be effectively solved, improving the accuracy and reliability of fault location. Then, based on the compensated transmission line fault traveling wave information and the multi-dimensional fusion entropy set of line frequency bands, an initial line fault distance information set is determined. This improves the accuracy of the initial line fault distance information. Next, based on the multi-dimensional fusion entropy set of line frequency bands, the initial line fault distance information set, and the power system topology information, a transmission line segment fault probability set is generated. Here, the fault probability is determined again; through two fault location operations, the probability of missed or false detections caused by a single fault location operation can be effectively reduced, improving the accuracy of fault location. Finally, based on the transmission line segment fault probability set, line fault isolation command information is generated, and based on this command information, the corresponding set of circuit breakers on the transmission line is controlled to disconnect the transmission line. This improves the timeliness of fault isolation, simultaneously eliminates cascading trips, enhances the safety of new energy power plants, reduces the damage rate of new energy power plants and the line loss rate of transmission lines, and reduces power consumption. Therefore, this fault location method for the transmission line of the new energy power plant avoids the annihilation of fault current characteristics caused by the arc suppression coil stage, eliminates the cascading tripping problem caused by step voltage, improves the accuracy of fault location and the timeliness of fault isolation in the new energy power plant, and reduces the loss rate of the new energy power plant. Attached Figure Description

[0012] The above and other features, advantages, and aspects of the embodiments of this disclosure will become more apparent from the accompanying drawings and the following detailed description. Throughout the drawings, the same or similar reference numerals denote the same or similar elements. It should be understood that the drawings are schematic, and elements are not necessarily drawn to scale.

[0013] Figure 1 This is a flowchart of some embodiments of the fault location method for new energy power plant transmission lines according to this disclosure; Figure 2 This is a structural schematic diagram of some embodiments of the fault location device for new energy power plant transmission lines according to the present disclosure; Figure 3 This is a schematic diagram of the structure of an electronic device suitable for implementing some embodiments of the present disclosure. Detailed Implementation

[0014] Embodiments of this disclosure will now be described in more detail with reference to the accompanying drawings. While some embodiments of this disclosure are shown in the drawings, it should be understood that this disclosure can be implemented in various forms and should not be construed as limited to the embodiments set forth herein. Rather, these embodiments are provided to provide a more thorough and complete understanding of this disclosure. It should be understood that the accompanying drawings and embodiments of this disclosure are for illustrative purposes only and are not intended to limit the scope of protection of this disclosure.

[0015] It should also be noted that, for ease of description, only the parts relevant to the invention are shown in the accompanying drawings. Unless otherwise specified, the embodiments and features described in this disclosure can be combined with each other.

[0016] It should be noted that the concepts of "first" and "second" mentioned in this disclosure are used only to distinguish different devices, modules or units, and are not used to limit the order of functions performed by these devices, modules or units or their interdependencies.

[0017] It should be noted that the terms "a" and "a plurality of" used in this disclosure are illustrative rather than restrictive, and those skilled in the art should understand that, unless otherwise expressly indicated in the context, they should be understood as "one or more".

[0018] The names of messages or information exchanged between multiple devices in the embodiments of this disclosure are for illustrative purposes only and are not intended to limit the scope of such messages or information.

[0019] This disclosure will now be described in detail with reference to the accompanying drawings and embodiments.

[0020] Figure 1 A flowchart 100 is shown, illustrating some embodiments of a method for locating faults in transmission lines of new energy power plants according to this disclosure. This method for locating faults in transmission lines of new energy power plants includes the following steps: Step 101: Obtain the transmission line fault information set and power system topology information of the new energy power plant distribution network collaborative system by acquiring the data acquisition sensor set after clock synchronization.

[0021] In some embodiments, the execution entity (e.g., an electronic device) of the above-mentioned new energy power plant transmission line fault location method can acquire the transmission line fault information set and power system topology information of the new energy power plant distribution network collaborative system through a clock-synchronized data acquisition sensor set via wired or wireless connection. The aforementioned new energy power plant distribution network collaborative system can be a system constructed for collaborative detection of the new energy power plant and the distribution network. The data acquisition sensors in the aforementioned data acquisition sensor set can be high-performance sensors used to collect electrical and non-electrical information of the new energy power plant distribution network collaborative system during a short period after a fault occurs. The aforementioned short fault period can be the time span of multiple cycles before and after the fault occurs. For example, if the new energy power plant distribution network collaborative system is a 50Hz power plant, the short fault period can be the three cycles before the fault occurs (each cycle is 20 milliseconds) and the five cycles after the fault occurs, i.e., 160 milliseconds. The aforementioned electrical information may include, but is not limited to, at least one of the following: fault traveling wave signal information, zero-sequence voltage harmonic distortion rate, and transient current phase change. The aforementioned non-electrical information may include, but is not limited to, at least one of the following: cable joint temperature and local pulse intensity information. The aforementioned fault traveling wave signal information can be high-frequency electromagnetic transient signals generated at two locations—the renewable energy power plant and the distribution network—at the moment of the fault, i.e., an instantaneous change in the electric / magnetic field at the fault point, forming an electromagnetic traveling wave propagating along the line. The aforementioned zero-sequence voltage harmonic distortion rate can characterize the frequency domain characteristics of the zero-sequence voltage, i.e., the fault causes harmonic components to appear in the zero-sequence voltage. The aforementioned transient current phase change can characterize the information that the phase of the fault traveling wave signal information will jump at the moment of the fault. The aforementioned local pulse intensity information can be a high-frequency transient signal generated by partial discharge. The aforementioned transmission line fault information set can be electrical and non-electrical information collected within a short period before and after a single-phase ground fault occurs at the renewable energy power plant. The aforementioned power system topology information can be information about the topology formed by the transmission lines as connecting edges and power equipment as nodes in the renewable energy power plant distribution network collaborative system. The aforementioned power system topology information can include, but is not limited to, at least one of the following: sensor location information, transmission line impedance information, transmission line length, and equipment information of each power device.

[0022] Step 102: Perform multi-channel mode decomposition processing on the transmission line fault information set to obtain the transmission line fault mode signal information set.

[0023] In some embodiments, the aforementioned execution entity can perform multi-channel mode decomposition processing on the aforementioned transmission line fault information set to obtain a transmission line fault mode signal information set. The transmission line fault mode signal information in the aforementioned transmission line fault mode signal set can characterize the inherent mode information and state information of a single-phase ground fault. The aforementioned transmission line fault mode signal information set may include: zero-sequence voltage harmonic distortion rate mode information, transient current phase change mode information, cable joint temperature mode information, and local pulse mode information. The zero-sequence voltage harmonic distortion rate mode information can characterize the harmonic components dominated by the focused ground fault, filtering out non-fault distortion information caused by normal load fluctuations in the power grid, voltage sags, etc. The transient current phase change mode information can characterize the jump characteristics of the current phase at the moment of the fault (such as phase offset angle and change duration), eliminating information on phase noise caused by power grid frequency fluctuations and transformer errors. The cable joint temperature mode information can characterize and separate the joint temperature rise trend caused by the ground fault (such as continuous temperature rise caused by increased resistance at the fault point), eliminating interference from random fluctuations in ambient temperature and changes in heat dissipation conditions. Local pulse mode information can characterize the pulse features of partial discharge at the fault point (such as pulse amplitude, repetition frequency, and rising edge) to filter out pseudo pulses caused by power grid electromagnetic interference and sensor noise.

[0024] In some optional implementations of certain embodiments, the above-mentioned multi-channel mode decomposition processing of the above-mentioned transmission line fault information set to obtain the transmission line fault mode signal information set, and the control of the corresponding circuit breaker set on the transmission line to disconnect the transmission line according to the transmission line fault mode signal information set, may include the following steps: The first step is to perform fault information preprocessing on the above-mentioned transmission line fault information set to obtain a preprocessed transmission line fault information set. The fault information preprocessing may include, but is not limited to, at least one of the following: multimodal feature alignment, preliminary noise reduction using a 5th-order Butterworth low-pass filter, amplitude normalization using Z-score normalization, and signal framing.

[0025] The second step involves performing a time-frequency domain transformation on the preprocessed transmission line fault information set to obtain a time-frequency domain information set of line faults. This time-frequency domain information set represents a two-dimensional matrix of frequency components of each frame of preprocessed transmission line fault information at different time points. The horizontal axis of this two-dimensional matrix represents time, and the vertical axis represents frequency. Each element in the matrix represents the energy or amplitude at the corresponding time and frequency. This time-frequency domain transformation can be performed using the CQT (Constant-Q Transform) algorithm to convert the preprocessed transmission line fault information in the time domain to fault information in the time-frequency domain.

[0026] The third step involves generating a line fault mask signal information set based on the aforementioned time-frequency domain information set of the line fault and the preset initial fault parameter set. The line fault mask signal information in this set can be used to suppress mode aliasing caused by uneven distribution of extreme points in the preprocessed transmission line fault information. The aforementioned initial parameter set characterizes the importance of the fault frequency value set and fault amplitude value set extracted from the time-frequency domain information of the line fault to the line fault mask signal information. The preset initial fault parameter set may include: initial fault frequency parameters and initial fault amplitude parameters. The aforementioned line fault mask signal information can be represented as: .

[0027] in, This indicates the signal information of the line fault mask. This represents the initial parameter for the fault amplitude value, and its value range can be [0.01, 4]. Indicates the first Each fault amplitude value. Indicates time. Indicates the order of phases. This indicates the number of phases, and its value can be 16. This represents the initial parameter for the fault frequency, and its value range can be [0.5, 3]. Indicates the first The fourth step involves adding the aforementioned line fault mask signal information set to the preprocessed transmission line fault information set to obtain the fault mask signal information set.

[0028] The fifth step involves generating a line fault mode signal information set based on the aforementioned fault mask signal information set. The fault mode signal information in this set characterizes the zero-sequence voltage harmonic distortion rate, transient current phase abrupt change information, cable joint temperature, and partial discharge pulse intensity of fault signals at different frequencies from the preprocessed transmission line fault information set. As an example, the execution entity can utilize the MVMD (Multivariate Variational Mode Decomposition) algorithm to generate the fault mode signal information set based on the aforementioned fault mask signal information set.

[0029] The sixth step involves using a fault scattering feature extraction model to extract fault features from the aforementioned line fault mode signal information set, obtaining a fault multi-order scattering feature vector set. The fault multi-order scattering feature vectors in this set characterize the distribution and concentration of information such as instantaneous frequency, instantaneous amplitude, and energy in the frequency domain, including the fault mode signal information. The fault scattering feature extraction model can be a deep neural network model that performs cascaded modal operations and average pooling on the spectral and contour feature vector sets of the input fault mode signal information set to extract four-channel scattering coefficients with translation invariance and deformation stability, and then concatenates these features to output the fault multi-order scattering feature vector set. For example, the fault scattering feature extraction model could be a wavelet scattering convolutional neural network that removes wavelet transform and retains only the convolutional neural network. In practice, the execution entity can first use the Hilbert transform algorithm to extract time-frequency features from the aforementioned fault mode signal information set, obtaining a fault instantaneous spectral distribution feature vector set and a fault instantaneous energy feature vector set. The fault instantaneous spectral distribution feature vectors characterize the instantaneous frequency distribution information. The aforementioned instantaneous energy feature vector of the fault can characterize the instantaneous energy information of the fault signal. Next, the mean, standard deviation, frequency skewness, kurtosis, 25th percentile, and 75th percentile of the instantaneous spectral distribution feature vector set and the instantaneous energy feature vector set of the fault are determined and concatenated to obtain the spectral distribution feature vector. Then, the first-order difference, second-order difference, and mean, standard deviation, frequency skewness, kurtosis, 25th percentile, and 75th percentile of the maximum energy sequence formed by the maximum value elements in each instantaneous energy feature vector set of the fault are determined and concatenated to obtain the fault contour feature vector. Finally, the aforementioned spectral distribution feature vector and the aforementioned fault contour feature vector are input into the fault scattering feature extraction model to obtain the fault multi-order scattering feature vector set.

[0030] Step 7: Perform feature correlation fusion on the above-mentioned fault multi-order scattering feature vector set and the above-mentioned fault mode signal information set to obtain a fault fusion feature vector set. The fault fusion feature vectors in the above-mentioned fault fusion feature vector set can be feature vectors obtained by feature concatenation and fusion of the above-mentioned fault multi-order scattering feature vector set and the above-mentioned fault mode signal information set, followed by feature normalization processing.

[0031] The eighth step is to input the above fault fusion feature vector set into the fully connected layer to obtain the transmission line fault mode signal information set.

[0032] In addressing the aforementioned technical problems in the application scenario—a new energy microgrid encompassing multiple renewable energy sources—the following technical issues often arise: Due to the aliasing of fault signals in the fault mask signal information set collected by the new energy microgrid, the empirical mode decomposition algorithm (EMD) suffers from incomplete signal decomposition and noise data generation, resulting in low mode decomposition accuracy. This leads to low fault location accuracy, slow response time for fault isolation at the new energy power station, high losses at the new energy power station, and high transmission line losses. Based on the characteristics of this application scenario—fault signal mode aliasing, single-phase grounding faults, low signal-to-noise ratio of fault signals, and diverse fault types—we have decided to adopt the following solution: Optionally, generating the line fault mode signal information set based on the aforementioned fault mask signal information set may include the following steps: The first step is to generate a multi-objective function for fault mode decomposition. This multi-objective function can be a function used to balance mode independence, feature signal-to-noise ratio, and reconstruction accuracy in mode decomposition. It can be a weighted sum of each weight value with a mode aliasing exponent function, a fault signal average signal-to-noise ratio function, and a fault signal reconstruction error function. The mode aliasing exponent function can be a function of the sum of the covariances among the modes obtained from mode decomposition and the mean of the sum of the ratios of these sums to the sum of the variances of each mode. The weight values ​​can be predetermined values; for example, the weight values ​​could be 0.5, 0.3, and 0.2, respectively. The parameter set in the multi-objective function can be Gaussian white noise with the feature amplitude to be added during mode decomposition and the total number of decompositions.

[0033] The second step involves a multi-stage predation solution to the aforementioned fault mode decomposition multi-objective function, yielding the target amplitude and the number of target mode decompositions. The number of target mode decompositions can be the total number of mode decompositions required to adapt to the fault mask signal information set. The target amplitude can be the statistical amplitude added to the fault mask signal information set or the amplitude of white noise used to address mode aliasing. In practice, the aforementioned execution entity can utilize an improved marine predator optimization algorithm to perform a multi-stage predation solution to the aforementioned fault mode decomposition multi-objective function, obtaining the target amplitude Gaussian white noise and the number of target mode decompositions. The improved marine predator optimization algorithm can employ the Leiden algorithm to initialize the elite and prey matrices to ensure a uniform distribution of individuals in the population, use the Q-learning algorithm to adaptively select an update strategy to balance the algorithm's exploration and development capabilities, and improve population diversity through a back-learning mechanism to avoid getting trapped in local optima—the MPA (Marine Predators Algorithm). The adaptive selection and update strategy based on the Q-learning algorithm can be the three position update strategies of the MPA algorithm as the action space of the Q-learning algorithm, that is, there are three actions to be executed for each state; after the parent population of the MPA algorithm is updated, the offspring population is obtained, and the number of offspring individuals that are better than the parents is used as the state space of the Q-learning algorithm; the reward function of the Q-learning algorithm is the difference between the average fitness value of the offspring population and the average fitness value of the parent population after the position update, and the ratio of the difference to the average fitness value of the parent population; the algorithm has a decay factor of 0.8 and a learning factor of 0.1.

[0034] The third step involves generating a Gaussian white noise set based on the target amplitude. This Gaussian white noise set can be obtained by independently and randomly sampling from a normally distributed Gaussian function with a mean of 0 and a variance equal to the square of the target amplitude and the variance of the fault mask signal information set. This set is used to assist in separating noise from fault signals at different scales. Each Gaussian white noise item in the set is independent and distinct. In practice, the executing entity can first determine the product of the square of the target amplitude and the variance of the fault mask signal information set as the white noise variance. Then, based on this white noise variance, it can independently and randomly sample from a Gaussian function with a mean of 0 and a variance equal to the white noise variance to obtain the Gaussian white noise set.

[0035] The fourth step is to add the above Gaussian white noise set to the above fault mask signal information set in sequence to obtain the white noise fault signal information set.

[0036] The fifth step is to perform mode decomposition on each white noise fault signal in the above white noise fault signal information set to obtain the target fault mode signal information set. The target fault mode signal in the above target fault mode signal information set can be the first IMF (Intrinsic Mode Function) of the white noise fault signal information after EMD (Empirical Mode Decomposition).

[0037] The sixth step is to determine the mean of the above target fault mode signal information set to obtain the target fault mode mean signal information.

[0038] Step 7: Based on the target fault mode mean signal information, perform the following determination steps: Sub-step 1: Determine the target fault mode signal information set and the target fault mode mean signal information to obtain the fault margin signal information.

[0039] Sub-step 2 involves generating a cyclic white noise fault signal information set based on the number of times the aforementioned determination step has been executed, the fault margin signal information, the aforementioned target amplitude, and the aforementioned Gaussian white noise set. The cyclic white noise fault signal information in the aforementioned cyclic white noise fault signal information set can be obtained by adding white noise to the fault margin signal information.

[0040] As an example, the aforementioned execution entity can first perform empirical mode decomposition on the aforementioned Gaussian white noise set to obtain a set of Gaussian eigenmode signal information groups. Secondly, it can extract the Gaussian eigenmode signal information located at the aforementioned number of executions from each Gaussian eigenmode signal information group in the aforementioned Gaussian eigenmode signal information group, thus obtaining the target Gaussian eigenmode signal information set. Then, it can determine the product of the aforementioned target amplitude and the aforementioned target Gaussian eigenmode signal information set, and the sum of this product and the aforementioned fault margin signal information, as the cyclic white noise fault signal information set.

[0041] Sub-step 3 involves performing empirical mode decomposition (EMD) on the cyclic white noise fault signal information set to obtain the target noise fault mode signal information set. The target noise fault mode signal information in this set can be the first IMF obtained by mode decomposition of the cyclic white noise fault signal information using the EMD algorithm.

[0042] Sub-step 4: Determine the mean of the target noise fault mode signal information set to obtain the target fault intrinsic mode mean signal information.

[0043] Sub-step 5, in response to determining that the number of executions is greater than or equal to the number of times the target mode decomposition has been performed, performs kurtosis autocorrelation filtering on the target noise fault mode signal information set to obtain the line fault mode signal information set, and controls the corresponding circuit breaker set on the transmission line to disconnect the transmission line based on the line fault mode signal information set. In practice, the above-mentioned execution entity can first determine the kurtosis values ​​of the target noise fault mode signal information included in the target noise fault mode signal information set to obtain a kurtosis value set. Then, it can determine the autocorrelation function value set of at least one target noise fault mode signal information with a kurtosis value greater than or equal to a preset kurtosis threshold from the target noise fault mode signal information set. Afterwards, it can filter out the target noise fault mode signal information set corresponding to the autocorrelation function values ​​representing periodicity from the autocorrelation function value set and then perform signal superposition to obtain the line fault mode signal information set. The above control implementation method can refer to the implementation method of steps 102-108.

[0044] Step 8: In response to the determination that the number of executions is less than the target mode decomposition number, the target fault intrinsic mode mean signal information is determined as the target fault mode mean signal information, and the sum of the number of executions and a preset value is determined as the number of executions, so as to execute the above determination step again. The preset value can be a pre-set value, taking the value of 1.

[0045] The above-described technical solution and its related content, as an inventive point of this disclosure, solve the technical problem of "low accuracy of mode decomposition, leading to low accuracy of fault location, low timeliness of response to fault isolation in new energy power plants, high losses in new energy power plants, and high line losses in transmission lines." The factors leading to low accuracy of mode decomposition, resulting in low accuracy of fault location, low timeliness of response to fault isolation in new energy power plants, high losses in new energy power plants, and high line losses in transmission lines are often as follows: Due to the problem of fault signal aliasing in the fault mask signal information set collected by the new energy microgrid, when using the empirical mode decomposition algorithm to decompose the fault mask signal information set, there is incomplete signal decomposition and the generation of noise data, resulting in low accuracy of mode decomposition, which in turn leads to low accuracy of fault location, low timeliness of response to fault isolation in new energy power plants, high losses in new energy power plants, and high line losses in transmission lines. If these factors are solved, the accuracy of mode decomposition and fault location can be improved, the timeliness of response to fault isolation in new energy power plants can be improved, and the losses in new energy power plants and line losses in transmission lines can be reduced. To achieve this effect, this disclosure first utilizes an improved marine predator optimization algorithm to solve the fault mode decomposition (FMD) multi-objective function through multi-stage predation. The FMD multi-objective function comprehensively measures mode independence, feature signal-to-noise ratio, and reconstruction accuracy, avoiding the one-sidedness of a single objective. Furthermore, the improved marine predator optimization algorithm ensures a uniform distribution of individuals in the initial population across the solution space, improving balanced exploration and exploitation capabilities, expanding the search space, preventing local optima, and enhancing solution accuracy. Secondly, by generating the target amplitude, a Gaussian white noise set adapted to the scenario is bound to the fluctuation of the fault mask signal information set, ensuring the effectiveness of mode decomposition while avoiding excessive interference. Next, based on the Gaussian white noise set and the number of target mode decomposition iterations, iterative mode decomposition is performed on the fault mask signal information set. This adaptively decomposes nonlinear and non-stationary fault mask signal information sets and solves the mode aliasing problem. Iterative mode decomposition improves the comprehensiveness of fault feature extraction, avoiding the one-sidedness of focusing only on high-frequency fault signals in a single decomposition. Finally, kurtosis autocorrelation screening and control of the corresponding circuit breaker set on the transmission line are used to disconnect the transmission line. Kurtosis autocorrelation screening can improve the accuracy and quality of the effective fault components included in the obtained line fault mode signal information set, improve the response time of the new energy power station to isolate faults, and reduce the losses of the new energy power station and the line loss of the transmission line.

[0046] Step 103: Perform adaptive signal decomposition on the fault mode signal information set of the transmission line to obtain the fault frequency band information set of the line.

[0047] In some embodiments, the execution entity may perform adaptive signal decomposition on the transmission line fault mode signal information set to obtain a line fault frequency band information set. The line fault frequency band information in the aforementioned line fault frequency band information set may be instantaneous abrupt changes and frequency distribution characteristics of the transmission line fault mode signal information within different specific frequency ranges obtained through adaptive decomposition based on the distribution information of the transmission line fault mode signals.

[0048] In some optional implementations of certain embodiments, the above-mentioned adaptive signal decomposition of the transmission line fault mode signal information set to obtain the line fault frequency band information set may include the following steps: The first step is to determine the wavelet decomposition basis functions based on the aforementioned transmission line fault mode signal information set. These wavelet decomposition basis functions should be those best suited to the characteristics of the transmission line fault mode signal information set, possessing good time-domain localization capabilities, reducing phase distortion (symmetric or approximately symmetric), and having low vanishing moments to avoid smoothing out fault abrupt changes. For example, the wavelet decomposition basis functions could be one of the following: db6 (the 6th order function of the Daubechies wavelet basis functions), sym8 (the 8th order function of the Symlets wavelet basis functions), or the Coiflets series of basis functions. As an example, the executing entity can first adaptively select a set of wavelet decomposition basis functions as the target wavelet decomposition basis function set based on the aforementioned transmission line fault mode signal information set. The target wavelet decomposition basis function set must satisfy the following requirements: strong time-domain localization capability (short compact supports), symmetry or approximately symmetry (reducing phase distortion), and moderate vanishing moments (3rd-6th order, avoiding smoothing out fault abrupt changes). Then, using the BBS (Best Basis Selection) algorithm, with the objective function of minimizing the energy entropy of the fault feature frequency band obtained after decomposition by the target wavelet decomposition basis function, the target wavelet decomposition basis function set is screened to obtain the wavelet decomposition basis functions. The suitability of the wavelet decomposition basis functions is further confirmed through cross-validation (e.g., dividing the signal into transmission line fault mode signal information sets to verify the fault feature extraction accuracy of the target wavelet decomposition basis function set). The second step is to determine the number of wavelet decomposition levels based on the aforementioned transmission line fault mode signal information set and the wavelet decomposition basis functions. The number of wavelet decomposition levels can be the total number of times the transmission line fault mode signal information set is decomposed using the wavelet decomposition basis function set. This ensures that the target frequency band is accurately decomposed to the leaf nodes of the tree, avoiding insufficient decomposition levels leading to frequency band aliasing, or excessive decomposition levels causing redundancy. As an example, the execution entity can use a genetic algorithm based on maximizing the energy proportion of fault sub-bands to determine the number of wavelet decomposition levels based on the aforementioned transmission line fault mode signal information set and the aforementioned wavelet decomposition basis functions.

[0049] The third step involves performing wavelet decomposition on the aforementioned transmission line fault mode signal information set based on the wavelet decomposition level, using the aforementioned wavelet decomposition basis functions, to obtain a line fault decomposition tree. This line fault decomposition tree can be a tree structure representing the overall features and detailed information of the transmission line fault mode signal information set. The root node of the line fault decomposition tree can be the aforementioned transmission line fault mode signal information set, and the progressively generated child nodes can be the low-frequency approximate components and high-frequency detailed components obtained by decomposing the low-frequency approximate components of the transmission line fault mode signal information set using the wavelet decomposition basis function set, with a depth equal to the aforementioned wavelet decomposition level.

[0050] The fourth step is to determine the set of line fault energy proportions and the set of line fault Shannon entropy values ​​for each leaf node in the aforementioned line fault decomposition tree. The line fault energy proportion value in the set of line fault energy proportions characterizes the energy intensity of the frequency band signal of the leaf node in the time domain, i.e., the effect of the amplitude intensity and duration of the fault signal. The larger the line fault energy proportion value, the more fault signals it contains. The line fault energy proportion value can be the ratio of the line fault energy proportion value to the sum of the set of line fault energy proportion values. The line fault Shannon entropy value in the set of line fault Shannon entropy values ​​characterizes the Shannon entropy of the uncertainty and complexity of the signal information contained in the frequency band signal of the leaf node.

[0051] Fifth, based on the aforementioned set of line fault energy proportions and the aforementioned set of line fault Shannon entropy values, redundancy pruning is performed on the leaf nodes of each line fault to obtain a pruned line fault decomposition tree. In practice, the executing entity can remove leaf nodes from the aforementioned line fault leaf nodes whose corresponding line fault energy proportion is less than the energy proportion threshold or whose line fault Shannon entropy value is greater than the average of the line fault Shannon entropy value set. Furthermore, removing the same child node from both corresponding leaf nodes will result in the removal of the desired child nodes, thus obtaining the pruned line fault decomposition tree. The aforementioned child nodes can be any nodes in the line fault decomposition tree other than the individual line fault leaf nodes and the root node.

[0052] The sixth step is to determine the frequency band signal set corresponding to each line fault leaf node in the pruned line fault decomposition tree as the line fault frequency band information set.

[0053] Step 104: Determine the multi-dimensional fusion entropy of each line fault frequency band in the line fault frequency band information set to obtain the multi-dimensional fusion entropy set of the line frequency band.

[0054] In some embodiments, the aforementioned executing entity may determine the line frequency band multi-dimensional fusion entropy of each line fault frequency band information in the aforementioned line fault frequency band information set, thereby obtaining a line frequency band multi-dimensional fusion entropy set. The aforementioned line frequency band multi-dimensional fusion entropy can characterize the energy concentration and temporal pattern repetition of the line fault frequency band information within a specific time-frequency domain range. The larger the line frequency band multi-dimensional fusion entropy, the more fault signals are included in the line fault frequency band information.

[0055] In some optional implementations of certain embodiments, the process of determining the line frequency band multi-dimensional fusion entropy of each line fault frequency band information in the aforementioned line fault frequency band information set to obtain a line frequency band multi-dimensional fusion entropy set may include the following steps: The first step is to normalize the aforementioned line fault frequency band information set to obtain a normalized line fault frequency band information set. This normalization process can be performed on the amplitude values ​​of the line fault frequency band information set.

[0056] The second step involves embedding fault frequency band features into the normalized line fault frequency band information set to obtain a fault frequency band feature vector set. The fault frequency band feature vectors in this set characterize the dynamic structure and complexity of the normalized line fault frequency band information set over time. In practice, the execution entity can first use an average mutual information algorithm to determine the time delay components between the fault frequency band feature vectors included in the fault frequency band feature vector set. These time delay components should be chosen to ensure that the fault frequency band feature vector bases are neither overly correlated, leading to information redundancy, nor overly distant, losing their dynamic connection. Then, using FNN (False Nearest Neighbors), the embedding dimension between the fault frequency band feature vectors included in the fault frequency band feature vector set is determined. This embedding dimension can be a value used to avoid exacerbating noise interference and increasing computational load. Next, the number of normalized output line fault signal frequency band information included in the normalized line fault frequency band information set, and the difference between the difference between the embedding dimension and 1 and the product of the delay time component, are determined as the number of elements to be selected from the normalized line fault frequency band information set, thus obtaining the target frequency band information set. Finally, taking each target frequency band information as the starting point and the aforementioned delay time component as the time interval, a one-dimensional vector set of time interval frequency bands is constructed, and the one-dimensional vector sets of time interval frequency bands are combined to obtain the fault frequency band feature vector set.

[0057] The third step is to determine the fault signal frequency band distance information set of the aforementioned fault frequency band feature vector set. The fault signal frequency band distance information in this set can be Chebyshev distance, which characterizes the similarity between fault frequency band feature vectors.

[0058] The fourth step is to generate a frequency band fuzzy entropy set based on the aforementioned fault signal frequency band distance information set. The frequency band fuzzy entropy in this set characterizes the temporal sequence complexity of the fault signal frequency band distance information; the larger the frequency band fuzzy entropy, the greater the complexity of the fault signal frequency band distance information. As an example, the executing entity can use the fuzzy entropy calculation formula to generate the frequency band fuzzy entropy set based on the aforementioned fault signal frequency band distance information set.

[0059] Fifth, based on the aforementioned fault frequency band feature vector set and the aforementioned fault signal frequency band distance information set, a fault frequency band sample entropy set is generated. The fault frequency band sample entropy in this set can be a numerical value representing the complexity of the time series by measuring the probability of new patterns arising in the signal; the larger the fault frequency band sample entropy, the greater the complexity of the fault signal frequency band distance information. As an example, the aforementioned execution entity can use the sample entropy calculation formula to generate the fault frequency band sample entropy set based on the aforementioned fault signal frequency band distance information set.

[0060] The sixth step involves extracting the frequency band envelope signal from the aforementioned line fault frequency band information set to obtain a fault frequency band envelope signal set. The fault frequency band envelope signal in this set can be a signal envelope reflecting the changing trend of the signal amplitude of the output line fault signal frequency band information. This frequency band envelope signal extraction can be performed using the Hilbert transform algorithm.

[0061] Step 7: Determine the envelope probability distribution entropy set of the aforementioned fault frequency band envelope signal set. The envelope probability distribution entropy in this set can be represented by the Shannon entropy, which characterizes the complexity of the fault frequency band envelope signal. In practice, the executing entity can first perform signal probability distribution statistics on the fault frequency band envelope signal set using histograms to obtain the envelope probability distribution information set. Then, using the formula for calculating Shannon entropy, determine the Shannon entropy set of the envelope probability distribution information set, which serves as the envelope probability distribution entropy set.

[0062] Step 8: Determine the fault band energy entropy set of the normalized line fault frequency band information set. The fault band energy entropy in this set characterizes the node energy proportion, i.e., the probability distribution, of the normalized output line fault signal frequency band information. It quantifies the entropy value of the uniformity of energy distribution across frequency bands. The smaller the fault band energy entropy, the more concentrated the energy included in the normalized output line fault signal frequency band information. This determination can be made using the Renyi energy spectrum entropy calculation formula.

[0063] Step nine involves weighted summation of the aforementioned frequency band fuzzy entropy set, the aforementioned fault frequency band sample entropy set, the aforementioned envelope probability distribution entropy set, and the aforementioned fault frequency band energy entropy set to obtain a multi-dimensional fusion entropy set for the line frequency band. In practice, the executing entity can first determine the mutual information set and information entropy set of the aforementioned frequency band fuzzy entropy set, the aforementioned fault frequency band sample entropy set, the aforementioned envelope probability distribution entropy set, the aforementioned fault frequency band energy entropy set, and the fault tag. The aforementioned fault tag can be a reference identifier used to quantify the fault information set of the transmission line and to obtain a vector value through real-number encoding. Secondly, the ratio of the product of each mutual information in the mutual information set and its corresponding information entropy to the sum of the corresponding products of the mutual information set and information entropy is determined as a weight value set. Then, the Pearson correlation coefficient set of the aforementioned envelope probability distribution entropy set and the aforementioned fault frequency band energy entropy set is determined, and for the envelope probability distribution entropy and fault frequency band energy entropy corresponding to a correlation coefficient greater than or equal to a preset threshold (e.g., 0.8), the entropy with lower corresponding mutual information is deleted to obtain a redundancy-removed entropy set. Next, the entropy set of the envelope probability distribution corresponding to the correlation coefficient threshold, the entropy set of the fault frequency band energy, the entropy set after removing redundancy, the aforementioned frequency band fuzzy entropy set, and the aforementioned fault frequency band sample entropy set are used as the target entropy set. Finally, the target entropy set and the corresponding weighted numerical set are weighted and summed to obtain the multi-dimensional fused entropy set of the line frequency band.

[0064] Step 105: Based on the line frequency band energy spectrum entropy set and power system topology information, perform traveling wave dispersion compensation on the traveling wave information of the transmission line fault in the transmission line fault information set to obtain the compensated traveling wave information of the transmission line fault.

[0065] In some embodiments, the aforementioned execution entity can perform traveling wave dispersion compensation on the traveling wave information of the transmission line fault information set based on the aforementioned multi-dimensional fused entropy set of the transmission band and the aforementioned power system topology information, to obtain the compensated traveling wave information of the transmission line fault. The compensated traveling wave information of the transmission line fault can be the traveling wave information obtained by correcting and restoring the waveform distortion and wavefront blurring caused by dispersion effects during the propagation of the transmission line fault signal information in the transmission line cable.

[0066] In some optional implementations of certain embodiments, the above-mentioned method of performing traveling wave dispersion compensation on the traveling wave information of the transmission line fault information set based on the multi-dimensional fused entropy set of the transmission band and the power system topology information to obtain the compensated traveling wave information of the transmission line fault may include the following steps: The first step is to perform high-pass filtering signal separation on the fault traveling wave signal information set included in the aforementioned transmission line fault information set to obtain the target fault traveling wave signal information. This target fault traveling wave signal information can be information that retains dispersion-sensitive high-frequency traveling wave signals. The high-pass filtering signal separation can be performed using an FIR (Finite Impulse Response Filter) high-pass filter.

[0067] The second step involves constructing a traveling wave deconvolution filter function based on the aforementioned power system topology information. This function can be used to counteract the dispersion effects of the fault traveling wave signal information during transmission through the transmission lines included in the power system topology, thereby restoring the original waveform of the fault traveling wave signal information. As an example, the executing entity can first perform a Fast Fourier Transform on the fault traveling wave signal information set to obtain the fault traveling wave frequency domain signal information set. Next, it can determine the sum of the squares of the absolute values ​​of the differences between the ratios of the fault traveling wave frequency domain signal information set and the exponent of the product of the line propagation constant and the transmission line length (base e), as the line parameter fitting error function. Then, it can solve the line parameter fitting error function using the least squares method to obtain the real-time line parameter set. Finally, it can determine the reciprocal of the sum of the exponent function of the product of the line propagation constant and the transmission line length (base e) and the regularization term, as the traveling wave deconvolution filter function.

[0068] The third step involves performing traveling wave dispersion compensation on the target fault traveling wave signal information set based on the aforementioned traveling wave deconvolution filter function, resulting in compensated traveling wave information for the transmission line fault. As an example, the execution entity can first perform a Fast Fourier Transform (FFT) on the aforementioned traveling wave deconvolution filter function, multiply it with the fault traveling wave frequency domain signal information set, and then perform an Inverse Fast Fourier Transform (IFT) to obtain a convolution-compensated fault traveling wave signal information set. Then, post-processing is performed on this convolution-compensated fault traveling wave signal information set to obtain a post-processed traveling wave signal information set, which serves as the compensated transmission line fault traveling wave information. This post-processing can be performed by removing signals from the convolution-compensated fault traveling wave signal information set whose amplitude is less than or equal to 0.05 multiplied by the maximum value in the fault traveling wave frequency domain signal information set.

[0069] Step 106: Determine the initial line fault distance information set based on the compensated transmission line fault traveling wave information and the multi-dimensional fusion entropy set of the line frequency band.

[0070] In some embodiments, the execution entity may determine an initial line fault distance information set based on the compensated transmission line fault traveling wave information and the multi-dimensional fusion entropy set of the line frequency band. The initial line fault distance information in the initial line fault distance information set may be the distance values ​​of distance sensors for transmission lines that may experience faults.

[0071] As an example, the aforementioned execution entity can first select the smallest value from the multi-dimensional fusion entropy set of the aforementioned line frequency bands as the target fusion entropy. Secondly, after performing wavelet packet decomposition on the aforementioned initial fault traveling wave compensation signal information set, the time-domain information of the line fault frequency band information corresponding to the aforementioned target fusion entropy is extracted. Subsequently, using the modulus maximum wavefront detection algorithm, wavefront detection processing is performed on the aforementioned time-domain information to obtain the traveling wave arrival time set. Then, the product of the ratio of 1 to the aforementioned compensated transmission line fault traveling wave information and 1000, the difference between the product of 1 and 0.005, and the product of the product of the product of 1 and the center frequency of the line fault frequency band information corresponding to the aforementioned target fusion entropy, is determined as the traveling wave propagation correction wave velocity. Finally, using a two-end traveling wave ranging algorithm, based on the aforementioned traveling wave propagation correction wave velocity, the aforementioned traveling wave arrival time set, and the transmission line lengths included in the aforementioned power system topology information, the initial line fault distance information set is determined.

[0072] Step 107: Generate a fault probability set for transmission line sections based on the multi-dimensional fusion entropy set of the line frequency band, the initial line fault distance information set, and the power system topology information.

[0073] In some embodiments, the execution entity may generate a transmission line segment fault probability set based on the multi-dimensional fusion entropy set of the line frequency band, the initial line fault distance information set, and the power system topology information. The transmission line segment fault probability in the transmission line segment fault probability set can characterize the probability value of a line fault occurring based on the initial line fault distance information.

[0074] In some optional implementations of certain embodiments, generating a transmission line segment fault probability set based on the multi-dimensional fused entropy set of the line frequency band, the initial line fault distance information set, and the power system topology information may include the following steps: The first step involves inputting the aforementioned multi-dimensional fused entropy set of the transmission line frequency band and the aforementioned power system topology information into the fault topology graph convolutional network included in the fault time-series graph convolutional localization model to obtain a transmission line topology feature vector set. The fault time-series convolutional localization model may further include a fault time-series localization network. The fault time-series graph convolutional localization model can be a deep neural network model that performs graph feature extraction and time-series feature extraction on the input multi-dimensional fused entropy set of the transmission line frequency band and the aforementioned power system topology information to output a fault time-series feature vector set. The fault topology graph convolutional network can be a model that performs graph convolutional fusion processing on the input multi-dimensional fused entropy set of the transmission line frequency band and the aforementioned power system topology information to output a transmission line topology feature vector set. For example, the fault topology graph convolutional network can be a graph convolutional network. The fault time-series localization network can be a model that performs time-series localization processing on the input transmission line topology feature vector set to output a fault time-series feature vector set. For example, the fault time-series localization network can be a long short-term memory neural network model. The transmission line topology feature vector set mentioned above can characterize the multi-source information of each node in the topology information of the above circuit system, and also aggregate the feature information of adjacency information.

[0075] The second step involves inputting the aforementioned transmission line topology feature vector set into the aforementioned fault timing location network to obtain a fault timing feature vector set. The fault timing feature vectors in this set can characterize the timing information of the fault occurrence.

[0076] The third step involves performing feature decision filtering on the aforementioned transmission line topology feature vector set and fault timing feature vector set to obtain a filtered fault feature vector set. In practice, the executing entity can utilize a decision tree forest to perform feature decision filtering on the aforementioned transmission line topology feature vector set and fault timing feature vector set to obtain a filtered fault feature vector set.

[0077] The fourth step involves updating the initial line fault distance information set based on the filtered fault feature vector set to obtain a fault probability set for the transmission line segment. This fault probability set can be a probability threshold indicating the presence of a fault within the transmission line segment, rather than a single fault distance, thus mitigating the error risk associated with point-level positioning. In practice, the executing entity can utilize a logistic regression layer to update the initial line fault distance information set based on the filtered fault feature vector set to obtain the fault probability set for the transmission line segment.

[0078] Step 108: Generate line fault isolation instruction information based on the fault probability set of the transmission line section, and control the corresponding circuit breaker set on the transmission line to disconnect the transmission line based on the line fault isolation instruction information.

[0079] In some embodiments, the execution entity can generate line fault isolation instruction information based on the fault probability set of the transmission line section, and control the corresponding set of circuit breakers on the transmission line to disconnect the transmission line based on the line fault isolation instruction information. The line fault isolation instruction information can be instruction information used to control the set of circuit breakers to perform corresponding actions to reduce the impact of faults on the new energy power plant. The circuit breakers in the set of circuit breakers can be hardware devices used to control the on / off state of the transmission line.

[0080] In addressing the aforementioned technical problems in the application scenario—high electricity demand during holidays—the following technical issues arise: High electricity demand during holidays results in low tolerance for power outages, and there are critical load areas such as hospitals and industrial facilities. Existing fault isolation methods only consider rapid disconnection, leading to overly simplistic considerations and the possibility of secondary faults on adjacent transmission lines after isolation. This results in low stability of the power plant distribution network coordination system, inability to adapt to different fault types, and increased operational frequency and equipment wear on transmission lines. Based on the characteristics of this application scenario—complex new energy and distribution network topology, diverse and high-density loads, short outage times for timely response, and rapid fault isolation—we have decided to adopt the following solution: In some optional implementations of certain embodiments, the process of generating line fault isolation instruction information based on the fault probability set of the transmission line section, and controlling the corresponding set of circuit breakers on the transmission line to disconnect the transmission line based on the line fault isolation instruction information, may include the following steps: The first step is to determine the fault location information set of the transmission line based on the aforementioned fault probability set of the transmission line section. The fault location information set can be the location information of the fault originating on the transmission line. In practice, the executing entity can determine the transmission line fault location information set as the initial line fault distance information set corresponding to the aforementioned fault probability set of the transmission line section.

[0081] The second step involves generating a fault isolation candidate path set based on the aforementioned transmission line fault location information set and the aforementioned power system topology information. The fault isolation candidate paths in this set can be isolation paths formed by combining operations on corresponding circuit breaker sets used to isolate the propagation of faults in the transmission lines.

[0082] As an example, the aforementioned execution entity can utilize the maximum flow minimum cut algorithm to generate a set of candidate paths for fault isolation based on the aforementioned transmission line fault location information set and the aforementioned power system topology information.

[0083] The third step involves determining the objective functions for maximizing load recovery, minimizing the number of circuit breaker operations, and minimizing network loss for each candidate path in the aforementioned fault isolation candidate path set. These objective functions constitute the fault isolation objective function set. Specifically, the objective function for maximizing load recovery can be a function that maximizes the user load restored to the non-faulty area after transmission line fault isolation. This function can also be a function of summing the products of the priority weight of each load and the restoration power of each load on each candidate path. The objective function for minimizing the number of circuit breaker operations can be a function that isolates the transmission line fault by operating the minimum number of circuit breakers. The objective function for minimizing network loss can be a function that minimizes the energy consumed by the transmission line due to the fault. Finally, the objective function for minimizing network loss can be a function of summing the products of the square of the power flow current corresponding to each candidate path, the corresponding line resistance, and the operating time after fault isolation.

[0084] The fourth step involves determining the power system flow constraint function, transmission line capacity constraint function, power system operation constraint function, and voltage-capacitance constraint function based on the aforementioned power system topology information. These constitute the fault isolation constraint function set. The power system flow constraint function characterizes the current or power on the fault isolation candidate path, ensuring it does not exceed a preset current threshold range. This prevents transmission lines from burning out due to overload or power equipment from being damaged by no-load overvoltage. The preset current threshold range can be a pre-defined maximum and minimum value of the flow current; the specific value can be determined based on specific circumstances and is not limited here. The transmission line capacity constraint function characterizes the actual transmission capacity on the fault isolation candidate path, ensuring it does not exceed the rated capacity. This prevents insulation aging on transmission lines. The power system operation constraint function ensures that the sum of the total load and total network loss equals the total power generation. This ensures power balance in the new energy power plant distribution network coordination system and prevents frequency collapse. The voltage-capacitance constraint function ensures that the actual voltage of each node in the power system topology information does not exceed the upper and lower limits specified by the new energy power plant distribution network coordination system. This ensures power quality and prevents voltage exceedances from affecting the normal operation of power equipment.

[0085] The fifth step involves performing multi-objective decision processing on the aforementioned fault isolation objective function set and fault isolation constraint function set to obtain a multi-objective fault isolation function. This multi-objective fault isolation function can be a function that transforms the aforementioned fault isolation objective function set and fault isolation constraint function set into a single comprehensive function. In practice, the executing entity can utilize a non-dominated sorting method to perform multi-objective decision processing on the aforementioned fault isolation objective function set and fault isolation constraint function set to obtain the multi-objective fault isolation function.

[0086] Step 6: Based on the aforementioned multi-objective fault isolation function, determine the candidate path isolation performance set of the aforementioned fault isolation candidate path set. The candidate path isolation performance in the aforementioned candidate path isolation performance set characterizes the isolation safety level of the transmission line faults isolated by the candidate path. As an example, the executing entity can determine the number of constraints that each candidate path in the aforementioned fault isolation candidate path set satisfies from the aforementioned fault isolation constraint function set, obtaining a constraint quantity set. Next, input the aforementioned fault isolation candidate path set into the aforementioned multi-objective fault isolation function to obtain an isolation function value set. Then, determine the ratio of each constraint quantity in the constraint quantity set to the number of fault isolation constraint functions included in the aforementioned fault isolation constraint function set, as a constraint ratio set. Finally, determine the sum of each constraint ratio in the aforementioned constraint ratio set and the corresponding isolation function value in the aforementioned isolation function value set, as the candidate path isolation performance, obtaining the candidate path isolation performance set.

[0087] Step 7: Based on the aforementioned candidate path isolation performance set, dynamically update and optimize the aforementioned fault isolation candidate path set to obtain the target fault isolation candidate path. The target fault isolation candidate path can be the most suitable and effective fault isolation candidate path in the aforementioned fault isolation candidate path set. As an example, the executing entity can use the fuzzy comprehensive evaluation method to conduct a multi-dimensional risk assessment of the aforementioned fault isolation candidate path set, obtaining a candidate path risk assessment value set. The candidate path risk assessment values ​​in the aforementioned candidate path risk assessment value set can be a weighted sum of the reliability risk value of the circuit breaker set included in the fault isolation candidate path, the power supply reliability risk value of the fault isolation candidate path, and the operational safety risk value of the fault isolation candidate path. Then, using a subjective and objective assignment method, determine the target weight value set of the candidate path risk assessment value set and the aforementioned candidate path isolation performance set. Then, perform a weighted sum of the target weight value set, the aforementioned candidate path risk assessment value set, and the aforementioned candidate path isolation performance set to obtain the target path performance value set. Finally, select the fault isolation candidate path corresponding to the target path performance value with the largest value from the aforementioned target path performance value set as the target fault isolation candidate path.

[0088] Step 8: Based on the aforementioned target fault isolation candidate paths, generate line fault isolation instruction information, and based on the aforementioned line fault isolation instruction information, control the corresponding circuit breaker set on the transmission line to disconnect the transmission line. The aforementioned line fault isolation instruction information can be instruction information for opening or closing the circuit breaker set included in the aforementioned target fault isolation candidate paths. As an example, the executing entity can parse the status information corresponding to the circuit breaker set on the aforementioned target fault isolation candidate paths to obtain the line fault isolation instruction information. The above technical content and related content, as an inventive point of this disclosure, solve the technical problem mentioned in the background art: "The stability of the energy power plant distribution network collaborative system is low, it cannot adapt to the isolation of different fault types in the energy power plant distribution network collaborative system, and the number of operations on the transmission line increases equipment wear." Factors contributing to the low stability of power plant distribution network coordination systems, their inability to adapt to different fault types, and the increased number of transmission line operations leading to equipment wear are often as follows: High electricity demand during holidays and periods with low tolerance for power outages, coupled with the presence of critical load areas such as hospitals and industrial facilities, result in current fault isolation systems only considering rapid disconnection, leading to overly simplistic considerations and the possibility of secondary faults occurring on adjacent transmission lines after isolation. This further exacerbates the low stability of power plant distribution network coordination systems, their inability to adapt to different fault types, and the increased number of transmission line operations leading to equipment wear. Addressing these factors can improve the stability of power plant distribution network coordination systems, effectively adapt to different fault types, reduce the number of transmission line operations, and decrease equipment wear. To achieve this, this disclosure first determines the fault location information set of transmission lines through the fault probability set of transmission line segments. This allows for compatibility with location uncertainties and improves the robustness of subsequent isolation. Secondly, generating a set of objective functions and constraint functions for fault isolation allows for a balance between power supply reliability, equipment lifespan, and the economic efficiency of the distribution network coordination system for new energy power plants. This avoids the one-sidedness of optimizing a single objective. The load priority weighting introduced in the load recovery objective function prioritizes the recovery of high-priority loads, reducing the impact of faults in critical areas. Furthermore, the comprehensive constraint set of the fault isolation constraint function set, including circuit breaker operation counts, power flow, and capacitance, ensures the safe and stable operation of the power grid after the isolation command is executed, effectively isolating secondary faults and power equipment losses. Then, by dynamically updating and optimizing the candidate path isolation performance set, the path performance indicators can be dynamically calculated based on real-time power grid conditions (topology, load, power flow), ensuring the timeliness and effectiveness of the target path. This avoids the rigidity of static solutions and dynamically adapts to fault isolation in different scenarios.Finally, generating line fault isolation command information and controlling the corresponding circuit breaker set on the transmission line to disconnect the transmission line can improve the accuracy of isolation, shorten the isolation power outage time and the scope of the impact of the fault, and improve the stability and fault resistance of the new energy power plant distribution network collaborative system.

[0089] Further reference Figure 2 As an implementation of the methods shown in the above figures, this disclosure provides some embodiments of a fault location device for transmission lines of new energy power plants. These device embodiments are similar to... Figure 1 Corresponding to the method embodiments shown, this new energy power plant transmission line fault location device can be specifically applied to various electronic devices.

[0090] like Figure 2 As shown, a fault location device 200 for transmission lines in a new energy power plant includes: an acquisition unit 201, a multi-channel mode decomposition unit 202, an adaptive signal decomposition unit 203, a determination unit 204, a traveling wave dispersion compensation unit 205, a second determination unit 206, and a generation unit 207. The acquisition unit 201 is configured to acquire a set of transmission line fault information and power system topology information of the new energy power plant distribution network collaborative system through a data acquisition sensor set synchronized with a clock. The multi-channel mode decomposition unit 202 is configured to perform multi-channel mode decomposition processing on the aforementioned transmission line fault information set to obtain a set of transmission line fault mode signal information. The adaptive signal decomposition unit 203 is configured to perform adaptive signal decomposition on the aforementioned transmission line fault mode signal information set to obtain a set of line fault frequency band information. The determination unit 204 is configured to determine the line frequency band multi-dimensional fusion entropy of each line fault frequency band information in the aforementioned line fault frequency band information set to obtain a set of line frequency band multi-dimensional fusion entropy. The traveling wave dispersion compensation unit 205 is configured to: perform traveling wave dispersion compensation on the traveling wave information of the transmission line fault in the transmission line fault information set based on the multi-dimensional fusion entropy set of the transmission line frequency band and the power system topology information, to obtain the compensated traveling wave information of the transmission line fault. The second determining unit 206 is configured to: determine the initial line fault distance information set based on the compensated traveling wave information of the transmission line fault and the multi-dimensional fusion entropy set of the transmission line frequency band. The generating unit 207 is configured to: generate a transmission line segment fault probability set based on the multi-dimensional fusion entropy set of the transmission line frequency band, the initial line fault distance information set, and the power system topology information. The transmission line disconnection unit 208 is configured to: generate line fault isolation command information based on the transmission line segment fault probability set, and control the corresponding circuit breaker set on the transmission line to perform transmission line disconnection processing based on the line fault isolation command information.

[0091] It is understandable that the various units and references recorded in the fault location device 200 for new energy power plant transmission lines are related. Figure 1 The steps in the described method correspond to each other. Therefore, the operations, features, and beneficial effects described above for the method also apply to the fault location device 200 for transmission lines of new energy power plants and the units contained therein, and will not be repeated here.

[0092] The following is for reference. Figure 3 It shows a schematic diagram of the structure of an electronic device (e.g., an electronic device) 300 suitable for implementing some embodiments of the present disclosure. Figure 3 The electronic device shown is merely an example and should not be construed as limiting the functionality and scope of the embodiments of this disclosure.

[0093] like Figure 3 As shown, the electronic device 300 may include a processing unit (e.g., a central processing unit, a graphics processing unit, etc.) 301, which can perform various appropriate actions and processes according to a program stored in a read-only memory (ROM) 302 or a program loaded from a storage device 308 into a random access memory (RAM) 303. The RAM 303 also stores various programs and data required for the operation of the electronic device 300. The processing unit 301, ROM 302, and RAM 303 are interconnected via a bus 304. An input / output (I / O) interface 305 is also connected to the bus 304.

[0094] Typically, the following devices can be connected to I / O interface 305: input devices 306 including, for example, touchscreens, touchpads, keyboards, mice, cameras, microphones, accelerometers, gyroscopes, etc.; output devices 307 including, for example, liquid crystal displays (LCDs), speakers, vibrators, etc.; storage devices 308 including, for example, magnetic tapes, hard disks, etc.; and communication devices 309. Communication device 309 allows electronic device 300 to communicate wirelessly or wiredly with other devices to exchange data. Although Figure 3 An electronic device 300 with various devices is shown; however, it should be understood that it is not required to implement or possess all of the devices shown. More or fewer devices may be implemented or possessed alternatively. Figure 3 Each box shown can represent a device or multiple devices as needed.

[0095] In particular, according to some embodiments of this disclosure, the processes described above with reference to the flowcharts can be implemented as computer software programs. For example, some embodiments of this disclosure include a computer program product comprising a computer program carried on a computer-readable medium, the computer program containing program code for performing the methods shown in the flowcharts. In such embodiments, the computer program can be downloaded and installed from a network via communication device 309, or installed from storage device 308, or installed from ROM 302. When the computer program is executed by processing device 301, it performs the functions defined in the methods of some embodiments of this disclosure.

[0096] It should be noted that, in some embodiments of this disclosure, the computer-readable medium described above may be a computer-readable signal medium or a computer-readable storage medium, or any combination thereof. A computer-readable storage medium may be, for example,—but not limited to—an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination thereof. More specific examples of a computer-readable storage medium may include, but are not limited to: an electrical connection having one or more wires, a portable computer disk, a hard disk, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage device, magnetic storage device, or any suitable combination thereof. In some embodiments of this disclosure, a computer-readable storage medium may be any tangible medium containing or storing a program that can be used by or in conjunction with an instruction execution system, apparatus, or device. In some embodiments of this disclosure, a computer-readable signal medium may include a data signal propagated in baseband or as part of a carrier wave, carrying computer-readable program code. Such propagated data signals may take various forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination thereof. A computer-readable signal medium can be any computer-readable medium other than a computer-readable storage medium, which can send, propagate, or transmit a program for use by or in connection with an instruction execution system, apparatus, or device. The program code contained on the computer-readable medium can be transmitted using any suitable medium, including but not limited to: wires, optical fibers, RF (radio frequency), etc., or any suitable combination thereof.

[0097] In some implementations, clients and servers can communicate using any currently known or future-developed network protocol such as HTTP (Hypertext Transfer Protocol) and can interconnect with digital data communication (e.g., communication networks) of any form or medium. Examples of communication networks include local area networks (“LANs”), wide area networks (“WANs”), the Internet (e.g., the Internet of Things), and peer-to-peer networks (e.g., ad hoc peer-to-peer networks), as well as any currently known or future-developed networks.

[0098] The aforementioned computer-readable medium may be included in the aforementioned electronic device; or it may exist independently and not assembled into the electronic device. The aforementioned computer-readable medium carries one or more programs, which, when executed by the electronic device, cause the electronic device to: acquire, through a clock-synchronized data acquisition sensor set, a transmission line fault information set and power system topology information of the new energy power plant distribution network collaborative system; perform multi-channel mode decomposition processing on the aforementioned transmission line fault information set to obtain a transmission line fault mode signal information set; perform adaptive signal decomposition on the aforementioned transmission line fault mode signal information set to obtain a line fault frequency band information set; determine the line frequency band multi-dimensional fusion entropy of each line fault frequency band information in the aforementioned line fault frequency band information set to obtain a line frequency band multi-dimensional fusion entropy set; and, based on the aforementioned line frequency band... Using a multi-dimensional fusion entropy set and the aforementioned power system topology information, traveling wave dispersion compensation is performed on the traveling wave information of the transmission line faults in the aforementioned transmission line fault information set to obtain compensated transmission line fault traveling wave information. Based on the compensated transmission line fault traveling wave information and the aforementioned multi-dimensional fusion entropy set of the line frequency band, an initial line fault distance information set is determined. Based on the aforementioned multi-dimensional fusion entropy set of the line frequency band, the aforementioned initial line fault distance information set, and the aforementioned power system topology information, a transmission line segment fault probability set is generated. Based on the aforementioned transmission line segment fault probability set, line fault isolation command information is generated, and based on the aforementioned line fault isolation command information, the corresponding circuit breaker set on the transmission line is controlled to disconnect the transmission line.

[0099] Computer program code for performing operations of some embodiments of this disclosure can be written in one or more programming languages ​​or a combination thereof, including object-oriented programming languages ​​such as Java, Smalltalk, and C++, and conventional procedural programming languages ​​such as the "C" language or similar programming languages. The program code can be executed entirely on the user's computer, partially on the user's computer, as a standalone software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In cases involving remote computers, the remote computer can be connected to the user's computer via any type of network—including a local area network (LAN) or a wide area network (WAN)—or can be connected to an external computer (e.g., via the Internet using an Internet service provider).

[0100] The flowcharts and block diagrams in the accompanying drawings illustrate the architecture, functionality, and operation of possible implementations of systems, methods, and computer program products according to various embodiments of this disclosure. In this regard, each block in a flowchart or block diagram may represent a module, segment, or portion of code containing one or more executable instructions for implementing a specified logical function. It should also be noted that in some alternative implementations, the functions indicated in the blocks may occur in a different order than those indicated in the drawings. For example, two consecutively indicated blocks may actually be executed substantially in parallel, and they may sometimes be executed in reverse order, depending on the functions involved. It should also be noted that each block in the block diagrams and / or flowcharts, and combinations of blocks in the block diagrams and / or flowcharts, can be implemented using a dedicated hardware-based system that performs the specified function or operation, or using a combination of dedicated hardware and computer instructions.

[0101] The units described in some embodiments of this disclosure can be implemented in software or hardware. The described units can also be housed in a processor; for example, a processor may be described as including an acquisition unit, a multi-channel mode decomposition unit, an adaptive signal decomposition unit, a determination unit, a traveling wave dispersion compensation unit, a second determination unit, and a generation unit. The names of these units do not necessarily limit the specific unit; for example, the acquisition unit may also be described as "a unit that acquires a set of transmission line fault information and power system topology information of a new energy power plant distribution network coordinated system by acquiring a set of data acquisition sensors synchronized with a clock."

[0102] The functions described above in this document can be performed at least in part by one or more hardware logic components. For example, exemplary types of hardware logic components that can be used, without limitation, include: field-programmable gate arrays (FPGAs), application-specific integrated circuits (ASICs), application-specific standard products (ASSPs), system-on-a-chip (SoCs), complex programmable logic devices (CPLDs), and so on.

[0103] The above description is merely a selection of preferred embodiments of this disclosure and an explanation of the technical principles employed. Those skilled in the art should understand that the scope of the invention involved in the embodiments of this disclosure is not limited to technical solutions formed by specific combinations of the above-described technical features, but should also cover other technical solutions formed by arbitrary combinations of the above-described technical features or their equivalents without departing from the above-described inventive concept. For example, technical solutions formed by substituting the above-described features with (but not limited to) technical features with similar functions disclosed in the embodiments of this disclosure.

Claims

1. A method for locating faults in transmission lines of new energy power plants, comprising: By acquiring a set of data sensors synchronized with the clock, the fault information set of the transmission line and the power system topology information of the new energy power plant distribution network collaborative system are obtained; The fault information set of the transmission line is subjected to multi-channel mode decomposition processing to obtain the fault mode signal information set of the transmission line; Adaptive signal decomposition is performed on the fault mode signal information set of the transmission line to obtain the line fault frequency band information set; The line frequency band multi-dimensional fusion entropy of each line fault frequency band information in the line fault frequency band information set is determined to obtain the line frequency band multi-dimensional fusion entropy set. Based on the multi-dimensional fusion entropy set of the line frequency band and the power system topology information, the traveling wave information of the transmission line fault in the transmission line fault information set is subjected to traveling wave dispersion compensation to obtain the compensated transmission line fault traveling wave information. Based on the compensated transmission line fault traveling wave information and the line frequency band multi-dimensional fusion entropy set, the initial line fault distance information set is determined; Based on the multi-dimensional fusion entropy set of the line frequency band, the initial line fault distance information set, and the power system topology information, a fault probability set for the transmission line section is generated. Based on the fault probability set of the transmission line section, generate line fault isolation instruction information, and based on the line fault isolation instruction information, control the corresponding circuit breaker set on the transmission line to disconnect the transmission line.

2. The method according to claim 1, wherein, The multi-channel mode decomposition process is performed on the transmission line fault information set to obtain a transmission line fault mode signal information set, including: The fault information set of the transmission line is preprocessed to obtain the preprocessed fault information set of the transmission line. The preprocessed transmission line fault information set is transformed in the time-frequency domain to obtain the line fault time-frequency domain information set. Based on the time-frequency domain information set of the line fault and the preset initial fault parameter set, a line fault mask signal information set is generated; The line fault mask signal information set is added to the preprocessed transmission line fault information set to obtain the fault mask signal information set. Based on the fault mask signal information set, a fault mode signal information set is generated; Using a fault scattering feature extraction model, fault features are extracted from the fault mode signal information set to obtain a fault multi-order scattering feature vector set; The fault multi-order scattering feature vector set and the fault mode signal information set are fused by feature correlation to obtain the fault fused feature vector set; The fault fusion feature vector set is input into the fully connected layer to obtain the transmission line fault mode signal information set.

3. The method according to claim 1, wherein, The adaptive signal decomposition of the fault mode signal information set of the transmission line to obtain the line fault frequency band information set includes: Based on the fault mode signal information set of the transmission line, determine the wavelet decomposition basis functions; The number of wavelet decomposition layers is determined based on the fault mode signal information set of the transmission line and the wavelet decomposition basis functions. Based on the wavelet decomposition basis function, the fault mode signal information set of the transmission line is decomposed based on the wavelet decomposition level to obtain the line fault decomposition tree. Determine the set of line fault energy proportion values ​​and the set of line fault Shannon entropy values ​​for each line fault leaf node included in the line fault decomposition tree. Based on the set of line fault energy proportions and the set of line fault Shannon entropy values, redundancy pruning is performed on each line fault leaf node to obtain a pruned line fault decomposition tree. The frequency band signal set corresponding to each line fault leaf node included in the pruned line fault decomposition tree is determined as the line fault frequency band information set.

4. The method according to claim 1, wherein, The process of determining the line frequency band multi-dimensional fusion entropy of each line fault frequency band information in the line fault frequency band information set yields a line frequency band multi-dimensional fusion entropy set, including: The line fault frequency band information set is normalized to obtain a normalized line fault frequency band information set. The normalized line fault frequency band information set is subjected to fault frequency band feature embedding to obtain a fault frequency band feature vector set; Determine the fault signal frequency band distance information set of the fault frequency band feature vector set; Based on the fault signal frequency band distance information set, a frequency band fuzzy entropy set is generated; Based on the fault frequency band feature vector set and the fault signal frequency band distance information set, a fault frequency band sample entropy set is generated; The frequency band envelope signal is extracted from the fault frequency band information set of the line to obtain the fault frequency band envelope signal set; Determine the entropy set of the envelope probability distribution of the fault frequency band envelope signal set; Determine the fault band energy entropy set of the normalized line fault band information set; The frequency band fuzzy entropy set, the fault frequency band sample entropy set, the envelope probability distribution entropy set, and the fault frequency band energy entropy set are weighted and summed to obtain the line frequency band multi-dimensional fused entropy set.

5. The method according to claim 1, wherein, The method involves performing traveling wave dispersion compensation on the traveling wave information of the transmission line fault information set based on the multi-dimensional fused entropy set of the transmission band and the power system topology information to obtain compensated traveling wave information of the transmission line fault, including: The fault traveling wave signal information set included in the transmission line fault information set is subjected to high-pass filtering signal separation to obtain the target fault traveling wave signal information; Based on the power system topology information, a traveling wave deconvolution filter function is constructed. Based on the traveling wave deconvolution filter function, traveling wave dispersion compensation is performed on the target fault traveling wave signal information set to obtain the compensated transmission line fault traveling wave information.

6. The method according to claim 1, wherein, The step of generating a transmission line segment fault probability set based on the multi-dimensional fused entropy set of the line frequency band, the initial line fault distance information set, and the power system topology information includes: The multi-dimensional fusion entropy set of the line frequency band and the power system topology information are input into the fault topology graph convolutional network included in the fault time sequence graph convolutional localization model to obtain the transmission line topology feature vector set. The fault time sequence convolutional localization model further includes: a fault time sequence localization network. The transmission line topology feature vector set is input into the fault timing location network to obtain the fault timing feature vector set. The transmission line topology feature vector set and the fault timing feature vector set are subjected to feature decision filtering to obtain a filtered fault feature vector set. Based on the filtered fault feature vector set, the initial line fault distance information set is updated to obtain the fault probability set of the transmission line section.

7. A fault location device for a new energy power plant transmission line, comprising: The acquisition unit is configured to acquire the transmission line fault information set and power system topology information of the new energy power plant distribution network coordination system through a data acquisition sensor set synchronized with the clock. A multi-channel mode decomposition unit is configured to perform multi-channel mode decomposition processing on the transmission line fault information set to obtain a transmission line fault mode signal information set. An adaptive signal decomposition unit is configured to perform adaptive signal decomposition on the transmission line fault mode signal information set to obtain a line fault frequency band information set. The first determining unit is configured to determine the line frequency band multi-dimensional fusion entropy of each line fault frequency band information in the line fault frequency band information set, thereby obtaining a line frequency band multi-dimensional fusion entropy set. The traveling wave dispersion compensation unit is configured to perform traveling wave dispersion compensation on the traveling wave information of the transmission line fault information set based on the multi-dimensional fusion entropy set of the line frequency band and the power system topology information, so as to obtain the compensated traveling wave information of the transmission line fault. The second determining unit is configured to determine an initial line fault distance information set based on the compensated transmission line fault traveling wave information and the line frequency band multi-dimensional fusion entropy set. The generation unit is configured to generate a transmission line segment fault probability set based on the multi-dimensional fusion entropy set of the line frequency band, the initial line fault distance information set, and the power system topology information. The transmission line disconnection unit is configured to generate line fault isolation instruction information based on the fault probability set of the transmission line section, and to control the corresponding circuit breaker set on the transmission line to perform transmission line disconnection processing based on the line fault isolation instruction information.

8. An electronic device, comprising: One or more processors; Storage device, on which one or more programs are stored, When the one or more programs are executed by the one or more processors, the one or more processors implement the method as described in any one of claims 1-6.

9. A computer-readable medium having a computer program stored thereon, wherein, When the computer program is executed by a processor, it implements the method as described in any one of claims 1-6.

Images