Traveling wave positioning method, system, device and medium based on intelligent fuse

Abstract

The present application relates to the field of traveling wave positioning technology, and discloses a traveling wave positioning method, system, device, and medium based on an intelligent fuse. The method includes: installing an intelligent fuse to obtain digital data by high-frequency sampling signals; transmitting the data to a master control fuse to synthesize a zero-sequence quantity to obtain a fault judgment result; constructing a characteristic matrix based on the zero-sequence quantity by applying an adaptive threshold wavelet transform; using an improved algorithm to measure and locate the fault by combining zero-sequence current and traveling wave characteristics; and performing hierarchical protection according to the judgment result and positioning result to obtain maintenance information. The present application is an intelligent device that can accurately locate the fault point and automatically perform differentiated protection actions according to the severity of the fault, thereby significantly shortening the fault search and processing time and improving the operational reliability and maintenance efficiency of the distribution network.

Description

Technical Field

[0001] The present application relates to the field of traveling wave positioning technology, and in particular to a traveling wave positioning method, system, device and medium based on an intelligent fuse. Background Art

[0002] In power distribution networks, traditional fuses are primarily used for overload and short-circuit protection. They interrupt fault currents by melting, preventing equipment damage and fires. These traditional fuses mostly employ simple mechanical structures, relying on the thermal or electrodynamic effects of current to achieve their protective function. Types include cartridge fuses, blade fuses, and drop-out fuses. Drop-out fuses, in particular, are widely used in medium-voltage distribution networks due to their visible disconnection point and ease of replacement. In recent years, with the advancement of power system monitoring technology, some improved fuses have begun to integrate simple current sensing capabilities. However, most remain limited to local display and basic protection functions, hindering remote monitoring and accurate fault location. Meanwhile, various technical solutions exist for fault location on distribution lines, including impedance measurement-based location methods, fault indicator location methods, and the more recently developed traveling wave location technology. However, most of these technologies require specialized distance measurement equipment and are independent of the fuse's protective function.

[0003] However, traditional fuses and existing fault location technologies have significant shortcomings. First, traditional fuses cannot provide information about electrical parameters before and after a fault occurs, nor can they identify the fault type or locate the fault. This necessitates manual line inspections after a fault occurs, which is time-consuming and inefficient. Second, while existing traveling wave ranging technology offers high accuracy, it typically requires expensive, specialized equipment to be installed at both ends of the line. It also places extremely high demands on time synchronization and data processing capabilities, making it difficult to widely apply to the end of the distribution network. Furthermore, while traditional drop-out fuses can interrupt fault currents, they lack the ability to implement differentiated protection strategies and apply the same approach to all fault types, which is neither cost-effective nor conducive to improving grid reliability. Most importantly, existing technical solutions struggle to address the monitoring challenges of the "last mile" of distribution lines, particularly in rural power grids and remote areas. Limited equipment investment and communication capabilities limit the coverage of fault location and intelligent monitoring. Summary of the Invention

[0004] The present application provides a traveling wave positioning method, system, equipment and medium based on smart fuses, which is an intelligent device for accurately locating the fault point and automatically performing differentiated protection actions according to the severity of the fault, thereby significantly shortening the fault search and processing time and improving the operational reliability and maintenance efficiency of the distribution network.

[0005] In a first aspect, the present application provides a traveling wave positioning method based on an intelligent fuse, the traveling wave positioning method based on the intelligent fuse comprising: installing an intelligent fuse on three phases of a distribution line and performing high-frequency sampling on the line signal to obtain digital data including a power frequency signal and a high-frequency signal;

[0006] The digital data is transmitted to a main control fuse, and a zero-sequence quantity synthesis calculation is performed using the main control fuse to obtain a zero-sequence voltage, a zero-sequence current and a fault judgment result;

[0007] Applying adaptive threshold wavelet transform processing to the collected line signal according to the zero-sequence voltage and the zero-sequence current, extracting multi-layer wavelet coefficients and constructing a characteristic vector matrix to obtain anti-interference enhanced traveling wave characteristic information;

[0008] Combining the zero-sequence current and the traveling wave characteristic information, an improved double-terminal positioning algorithm is used to perform distance calculation on the fault point position to obtain a fault section positioning result;

[0009] Based on the fault judgment result and the fault section location result, a hierarchical protection control strategy is executed to obtain predictive maintenance information.

[0010] In a second aspect, the present application provides a traveling wave positioning system based on an intelligent fuse, the traveling wave positioning system based on the intelligent fuse comprising:

[0011] The sampling module is used to install intelligent fuses on the three phases of the distribution line and perform high-frequency sampling on the line signal to obtain digital data containing power frequency signals and high-frequency signals;

[0012] a calculation module, configured to transmit the digital data to a master control fuse, and perform zero-sequence quantity synthesis calculation using the master control fuse to obtain zero-sequence voltage, zero-sequence current, and fault judgment results;

[0013] an extraction module, configured to apply adaptive threshold wavelet transform processing to the collected line signal according to the zero-sequence voltage and the zero-sequence current, extract multi-layer wavelet coefficients and construct a eigenvector matrix to obtain anti-interference enhanced traveling wave characteristic information;

[0014] A distance measurement module is used to combine the zero-sequence current and the traveling wave characteristic information, use an improved double-terminal positioning algorithm to perform distance calculation on the fault point position, and obtain a fault section positioning result;

[0015] The grading module is used to execute a graded protection control strategy based on the fault judgment result and the fault section location result to obtain predictive maintenance information.

[0016] In a third aspect, a traveling wave positioning device based on an intelligent fuse is provided, comprising: a memory and at least one processor, wherein the memory stores instructions; the at least one processor calls the instructions in the memory so that the traveling wave positioning device based on the intelligent fuse executes the above-mentioned traveling wave positioning method based on the intelligent fuse.

[0017] In a fourth aspect, a computer-readable storage medium is provided, wherein instructions are stored in the computer-readable storage medium, which, when executed on a computer, enables the computer to execute the above-mentioned traveling wave positioning method based on the intelligent fuse.

[0018] In the technical solution provided by the present application, by installing intelligent fuses on the three phases of the distribution line and performing high-frequency sampling on the line signals, digital data containing industrial frequency signals and high-frequency signals are obtained, thereby solving the problem that traditional fuses cannot monitor the line status in real time; the digital data is transmitted to the main control fuse and zero-sequence quantity synthesis calculation is performed to obtain zero-sequence voltage, zero-sequence current and fault judgment results, thereby achieving accurate identification of the fault type and improving the accuracy of fault judgment; adaptive threshold wavelet transform is applied to the collected line signal according to the zero-sequence voltage and zero-sequence current, multi-layer wavelet coefficients are extracted and a feature vector matrix is constructed to obtain anti-interference enhanced traveling wave feature information, which greatly improves the anti-interference ability and feature extraction efficiency of traveling wave signal processing; combined with zero-sequence current and traveling wave feature information, an improved two-terminal positioning algorithm is used to measure the distance of the fault point position to obtain accurate fault section positioning results, and the fault positioning accuracy is improved from hundreds of meters of traditional methods to tens of meters; based on the fault judgment results and fault section positioning results, a hierarchical protection control strategy is implemented to obtain intelligent fault isolation and predictive Maintenance information is collected, enabling differentiated control of protection actions and avoiding unnecessary power outages. The present invention fully utilizes the key contributions of artificial intelligence algorithm features to the solution. In particular, adaptive threshold wavelet transform processing and eigenvector matrix construction enable automatic extraction of effective features from complex power signals. The improved two-terminal positioning algorithm greatly improves the accuracy of traveling wave positioning through intelligent parameter adjustment and line impedance correction. The hierarchical protection control strategy utilizes an intelligent decision-making algorithm to achieve differentiated processing based on the nature of the fault. These algorithmic features together constitute the core technical advantage of the present invention and solve the "last mile" monitoring problem of distribution network. In addition, this method also achieves accurate assessment of the fault impact range and predictive maintenance. By analyzing the time series of historical fault data, it identifies equipment degradation trends and fault-prone sections, fundamentally improving the operational reliability and maintenance efficiency of the distribution network and transforming the distribution system from passive protection to active prevention. Practical application has verified that this method can shorten fault processing time from the traditional several hours to tens of minutes, significantly reducing power outage losses and operation and maintenance costs. BRIEF DESCRIPTION OF THE DRAWINGS

[0019] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0020] Figure 1 This is a schematic diagram of an embodiment of a traveling wave positioning method based on an intelligent fuse in an embodiment of the present application;

[0021] Figure 2 This is a schematic diagram of an embodiment of a traveling wave positioning system based on an intelligent fuse in an embodiment of the present application;

[0022] Figure 3 It is a schematic block diagram of the structure of a traveling wave positioning device based on an intelligent fuse in an embodiment of the present invention. DETAILED DESCRIPTION

[0023] The embodiments of the present application provide a traveling wave positioning method, system, device and medium based on an intelligent fuse. The terms "first", "second", "third", "fourth", etc. (if any) in the specification and claims of this application and the above-mentioned drawings are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchangeable where appropriate so that the embodiments described herein can be implemented in an order other than that illustrated or described herein. In addition, the terms "including" or "having" and any variations thereof are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device that includes a series of steps or units is not necessarily limited to those steps or units clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0024] For ease of understanding, the specific process of the embodiment of the present application is described below. Figure 1 In the embodiment of the present application, an embodiment of the traveling wave positioning method based on the intelligent fuse includes:

[0025] Step S101: Install smart fuses on the three phases of the power distribution line and perform high-frequency sampling on the line signal to obtain digital data including power frequency signals and high-frequency signals;

[0026] Step S102: Transmit the digital data to the master control fuse, and use the master control fuse to perform zero-sequence quantity synthesis calculation to obtain zero-sequence voltage, zero-sequence current and fault judgment results;

[0027] Step S103: applying adaptive threshold wavelet transform to the collected line signal according to the zero-sequence voltage and zero-sequence current, extracting multi-layer wavelet coefficients and constructing a eigenvector matrix to obtain anti-interference enhanced traveling wave characteristic information;

[0028] Step S104: combining the zero-sequence current and the traveling wave characteristic information, using the improved two-terminal location algorithm to perform distance calculation on the fault point position, and obtaining the fault section location result;

[0029] Step S105: Based on the fault judgment result and the fault section location result, a hierarchical protection control strategy is executed to obtain predictive maintenance information.

[0030] It is understandable that the execution subject of the present application can be a traveling wave positioning system based on an intelligent fuse, or a terminal or a server, which is not limited here. The embodiment of the present application is described by taking a server as the execution subject as an example.

[0031] Specifically, smart fuses are installed on the three phases of the distribution line and perform high-frequency sampling of the line signals. Equipped with high-frequency current transformers and voltage sensors, the smart fuses sample power line signals at a 2MHz sampling frequency, significantly exceeding the capabilities of traditional sampling equipment. High-frequency sampling can simultaneously capture both the power frequency signal (50Hz) and high-frequency transient signals (in the kilohertz to megahertz range), generating complete digitized data. For example, when a normal power frequency signal with a rated current of 5A flows through the line, the smart fuse captures both this power frequency signal and any possible high-frequency components. These high-frequency components are particularly noticeable in the early stages of a fault and often contain rich fault characteristic information.

[0032] The digitized data is transmitted to the master fuse, with the Phase B smart fuse set as the master fuse and the Phases A and C fuses set as slave fuses. The slave fuses transmit the collected data to the master fuse via 433MHz radio frequency communication. After receiving the three-phase data, the master fuse performs a zero-sequence component synthesis calculation: summing the three-phase voltage vectors and dividing them by three to obtain the zero-sequence voltage, and summing the three-phase current vectors and dividing them by three to obtain the zero-sequence current. The presence of a zero-sequence component is a typical characteristic of a single-phase ground fault. The master fuse determines the fault based on the magnitude and phase relationship of the zero-sequence voltage and current. When the zero-sequence voltage exceeds a preset threshold and the zero-sequence current exceeds another preset threshold, a single-phase ground fault is determined. For phase-to-phase short circuit faults, the diagnosis is primarily based on the characteristics of the phase current abrupt change and the phase-to-phase voltage drop.

[0033] Based on the zero-sequence voltage and current, the collected line signals are processed using an adaptive threshold wavelet transform. The master control fuse dynamically adjusts the wavelet transform processing threshold based on the fault severity. The higher the fault severity, the lower the threshold is used to ensure that more effective information is captured. A wavelet transform is applied to the raw high-frequency data, typically using the db4 wavelet as the mother wavelet function. An 8-layer decomposition is performed to obtain a series of wavelet coefficients in different frequency bands. Particular attention is paid to the detail coefficients in the first two layers, which reflect high-frequency characteristics and correspond to the main frequency components of the fault traveling wave. The system extracts these wavelet coefficients and constructs an eigenvector matrix, forming an information set containing multidimensional features such as the traveling wave amplitude, rise time, spectral distribution, and waveform polarity.

[0034] An improved two-terminal location algorithm combines zero-sequence current and traveling wave characteristics to calculate the distance to the fault point. This algorithm calculates the distance based on the time difference between the arrival of the traveling wave at two measurement points. For example, if the distance to the fault point in the line is L, the distance between the two measurement points (typically a traveling wave location switch on the trunk line and a smart fuse on the branch line) is D, the propagation speed of electromagnetic waves in the line is V, and the time at which the two measurement points capture the traveling wave is T1 and T2, respectively, then the distance S from the fault point to the first measurement point is calculated as S = [D - (T2 - T1) × V] / 2. The improved two-terminal location algorithm incorporates a line impedance correction factor to compensate for distribution line types and materials, improving distance measurement accuracy.

[0035] Based on the fault diagnosis and fault segment location results, a hierarchical protection control strategy is implemented. The system categorizes fault severity into emergency, major, and minor faults. Differentiated protection actions are taken for each fault level. Emergency faults immediately trigger the fuse to cut current; major faults trigger a delayed fuse drop to allow time for temporary self-healing; minor faults are simply recorded without triggering the fuse. Predictive maintenance information is also generated. By analyzing historical fault data over time, it identifies equipment degradation trends and fault-prone sections, predicting potential future failures and guiding maintenance personnel in targeted repairs.

[0036] For example, a three-phase smart fuse on a distribution line captured an abnormal waveform during high-frequency sampling. The main control fuse calculated the zero-sequence voltage to be 6.5 kV (exceeding the 5% threshold of the rated phase voltage of 10 kV) and the zero-sequence current to be 2.6 A (exceeding the 10% threshold of the rated current of 5 A), and determined it to be a C-phase ground fault. The system then performed a wavelet transform on the high-frequency signal, extracted the traveling wave features from the first two layers of wavelet coefficients, and captured the time when the traveling wave arrived at the main line traveling wave positioning switch at 10:15:32.000256 and the time when it arrived at the branch line smart fuse at 10:15:32.000842. It is known that the line length between the two devices is 3000 meters and the electromagnetic wave propagation speed is 2×10 8 m / s. Calculations showed the fault point to be 1,172 meters from the main line's traveling wave positioning switch. The system determined this to be a serious fault, executed a delayed drop action, and generated a fault impact assessment report. This precisely located the fault area and guided maintenance personnel to quickly address it, avoiding a widespread power outage. The system also incorporated the fault data into historical records for future fault prediction analysis.

[0037] In the embodiment of the present application, by installing intelligent fuses on the three phases of the distribution line and performing high-frequency sampling on the line signals, digital data containing power frequency signals and high-frequency signals are obtained, thereby solving the problem that traditional fuses cannot monitor the line status in real time; the digital data is transmitted to the main control fuse and zero-sequence quantity synthesis calculation is performed to obtain zero-sequence voltage, zero-sequence current and fault judgment results, thereby achieving accurate identification of the fault type and improving the accuracy of fault judgment; adaptive threshold wavelet transform processing is applied to the collected line signals according to the zero-sequence voltage and zero-sequence current, multi-layer wavelet coefficients are extracted and a feature vector matrix is constructed to obtain anti-interference enhanced traveling wave feature information, which greatly improves the anti-interference ability and feature extraction efficiency of traveling wave signal processing; combined with zero-sequence current and traveling wave feature information, an improved two-terminal positioning algorithm is used to perform distance calculation on the fault point position to obtain accurate fault section positioning results, and the fault positioning accuracy is improved from hundreds of meters of traditional methods to tens of meters; based on the fault judgment results and fault section positioning results, a hierarchical protection control strategy is implemented to obtain intelligent fault isolation and predictive maintenance. The present invention fully utilizes the key contributions of artificial intelligence algorithm features to the solution. In particular, adaptive threshold wavelet transform processing and eigenvector matrix construction enable the automatic extraction of effective features from complex power signals. The improved two-terminal positioning algorithm greatly improves the accuracy of traveling wave positioning through intelligent parameter adjustment and line impedance correction. The hierarchical protection control strategy utilizes an intelligent decision-making algorithm to achieve differentiated processing based on the nature of the fault. These algorithm features together constitute the core technical advantage of the present invention and solve the "last mile" monitoring problem of distribution network. In addition, the present method also achieves accurate assessment of the fault impact range and predictive maintenance. By analyzing the time series of historical fault data, it identifies equipment degradation trends and fault-prone sections, fundamentally improving the operational reliability and maintenance efficiency of the distribution network and transforming the distribution system from passive protection to active prevention. Practical application verification shows that this method can shorten fault processing time from the traditional several hours to tens of minutes, significantly reducing power outage losses and operation and maintenance costs.

[0038] In a specific embodiment, the process of executing step S101 may specifically include the following steps:

[0039] Traveling wave positioning switches are installed on the trunk line, and smart fuses with GPS timing modules are installed on the three phases of the branch line. The smart fuses are then configured for clock synchronization with a synchronization accuracy of 200 nanoseconds.

[0040] The high-frequency current transformer and voltage sensor in the intelligent fuse are used to collect data on the line signal to obtain the original analog electrical signal;

[0041] The original analog electrical signal is input into the digital conversion module of the control unit for analog-to-digital conversion processing to obtain digital data;

[0042] Perform noise suppression and frequency band separation on the digitized data to obtain power frequency signal and high frequency signal;

[0043] The amplitude and phase of the power frequency signal are calculated to obtain the phase voltage, phase current, active power, reactive power and power factor parameters of the line operation status, and timestamp information is added to the high-frequency signal and stored in the local memory.

[0044] Specifically, a monitoring network is established on the distribution lines. Traveling wave positioning switches are installed on the trunk lines. The switches are devices used to capture high-frequency fault traveling wave signals and are installed at key nodes of the distribution lines, such as substation outlets or major branch points. Smart fuses are installed on the three phases of the branch lines. Each smart fuse is equipped with a GPS timing module, which obtains standard time by receiving GPS satellite signals with an accuracy of nanoseconds. When configuring the clock synchronization of the smart fuses, a dedicated GPS timing algorithm is used to calibrate the clocks of each smart fuse to the same time reference, ensuring a clock synchronization accuracy of 200 nanoseconds. This high-precision clock synchronization is a key prerequisite for traveling wave positioning, because traveling waves propagate extremely fast. If the clocks are not synchronized, the ranging results will have serious deviations.

[0045] The high-frequency current transformer and voltage sensor in the smart fuse are the core hardware for acquiring line signals. The high-frequency current transformer uses a special magnetic core material with a wide frequency response, capable of capturing both power-frequency and high-frequency current signals. The voltage sensor uses capacitive voltage division technology to safely convert high voltage into a low-voltage signal. These two sensors continuously collect line signals, generating raw analog electrical signals. These raw analog signals contain electrical characteristics but have not yet been digitized and cannot be directly used for computer analysis.

[0046] The raw analog electrical signal is input into the control unit's digital conversion module, which primarily consists of a high-speed analog-to-digital converter (A / D converter) with a sampling frequency of up to 2 MHz, significantly higher than the sampling frequency of traditional power systems. During the A / D conversion process, the control unit samples the analog signal at a fixed interval (0.5 microseconds), converting the analog quantity into a digital quantity with each sample, forming a series of discrete digital values. These digital values are arranged in chronological order to form a digital data stream.

[0047] Noise suppression utilizes digital filtering techniques, primarily including mean filtering, median filtering, and low-pass filtering. Mean filtering smoothes data by calculating the average of data points within a sliding window; median filtering removes spike noise by taking the median value of the data within the window; and low-pass filtering retains low-frequency components and suppresses high-frequency noise. Frequency band separation utilizes frequency domain analysis to decompose the signal into different frequency bands. Fourier transforms are used to convert the time domain signal into the frequency domain. Frequency thresholds are then set to identify frequency components around 50 Hz as power frequency signals and those in the several kilohertz to megahertz range as high-frequency signals. Inverse transforms are then performed to separate the power frequency and high-frequency signals. The power frequency signal primarily reflects the normal operation of the line, requiring amplitude and phase calculations. Amplitude calculations utilize the root mean square method, taking the square root of the sum of squares of the sampling points within a power frequency cycle. Phase calculations are performed using zero transition detection or the phase component of the Fourier transform. These calculations yield the phase voltage, phase current, active power, reactive power, and power factor parameters of the line's operating status. Active power is calculated by multiplying the instantaneous voltage and current values and averaging them over a period of time. Reactive power is calculated by analyzing the phase difference between voltage and current. Power factor is the ratio of active power to apparent power. These parameters comprehensively reflect the electrical operating status of the line.

[0048] When processing high-frequency signals, the intelligent fuse adds a timestamp to each sampled data point. This timestamp is derived from the GPS timing module and has an accuracy of 200 nanoseconds. The timestamp-equipped high-frequency signal data is stored in local memory, forming the foundational data for traveling wave positioning. The local memory utilizes high-speed flash memory, providing ample storage capacity for high-frequency sampled data within a short period of time.

[0049] In a specific embodiment, the process of executing step S102 may specifically include the following steps:

[0050] The digitized data is sent to the main phase intelligent fuse through the radio frequency communication module to obtain a three-phase synchronous data set;

[0051] Perform timestamp verification on the three-phase synchronous data set, filter out data whose time synchronization error exceeds the preset threshold, and obtain the target three-phase data;

[0052] The target three-phase data is input into the deep learning transformer model to perform three-phase voltage vector sum operation, and combined with time series data prediction to obtain the real-time value of zero-sequence voltage;

[0053] Input the target three-phase data into the zero-sequence current calculation unit to perform three-phase current vector sum operation to obtain the real-time value of the zero-sequence current;

[0054] The fault type judgment logic is executed according to the real-time value of the zero-sequence voltage and the real-time value of the zero-sequence current. When the real-time value of the zero-sequence voltage exceeds a first preset threshold and the real-time value of the zero-sequence current exceeds a second preset threshold, it is determined to be a single-phase grounding fault. When the current of any two phases increases and the corresponding phase-to-phase voltage decreases, it is determined to be a phase-to-phase short circuit fault, and a fault type identification result is obtained;

[0055] Based on the fault type identification result, the phase whose phase voltage and zero-sequence voltage vector sum is less than the original phase voltage is determined to be the grounded phase, and the fault judgment result is obtained.

[0056] Specifically, the digitized data is transmitted to the master phase intelligent fuse via an RF communication module, which operates in the 433MHz frequency band, which offers excellent transmission range and penetration. The slave fuses (typically phases A and C) package their collected digitized data into data frames, which contain information such as the sampled data, device identification, and sampling timestamp. After adding a CRC checksum to the data frames, the frames are sent point-to-point via the RF communication module to the master fuse (typically phase B). After receiving the data from the three phases, the master fuse unpacks the data and sorts it by timestamp, forming a synchronized three-phase data set. The timestamp check process checks the timestamp information in the data frames and aligns the three-phase data according to the timestamps. A preset threshold of 200 nanoseconds is set based on the synchronization accuracy of the GPS timing module. The master fuse checks the timestamp difference of each data point. If the timestamp of a data point differs by more than 200 nanoseconds from the timestamps of the corresponding phase data, the data point is marked as an anomaly. The method of filtering out abnormal data is to replace it with the interpolation of adjacent valid data points or to directly discard the data point. The data after timestamp verification is the target three-phase data.

[0057] The zero-sequence voltage calculation unit uses a recurrent neural network algorithm, which constructs a deep learning model containing a gated recurrent unit (GRU). This algorithm can effectively capture the time series characteristics and inter-phase relationships of three-phase voltage data. The model input layer receives three-phase voltage time series data containing a historical window, extracts time domain features through two bidirectional GRU hidden layers, and then maps them to the output layer through a fully connected layer to obtain the real-time zero-sequence voltage value. This model is trained with historical data from a large-scale distribution network and uses an attention mechanism to automatically identify voltage characteristics at key time points. Compared with traditional vector sum calculation methods, it has higher noise immunity and adaptability to nonlinear distortion. The calculated real-time zero-sequence voltage value changes over time, reflecting the dynamic changes in the line zero-sequence voltage.

[0058] The process of inputting the target three-phase data into the zero-sequence current calculation unit for the three-phase current vector sum calculation is similar to the zero-sequence voltage calculation. The zero-sequence current calculation unit uses a three-phase current vector sum algorithm to perform vector addition on the three-phase currents based on their amplitude and phase, then divides the result by 3 to obtain the zero-sequence current. The specific calculation process is as follows: first, the three-phase currents are expressed as amplitude and phase. Then, the real and imaginary parts of the three-phase currents are summed. The sum of the real and imaginary parts is divided by 3, and finally, the amplitude and phase of the zero-sequence current are synthesized. The calculated real-time zero-sequence current value reflects the dynamic changes in the line zero-sequence current and is an important basis for determining the fault type. The fault type determination logic is designed based on power system fault characteristics, with different judgment conditions for different fault types. For a single-phase grounding fault, the judgment condition is: the real-time zero-sequence voltage value exceeds a first preset threshold value and the real-time zero-sequence current value exceeds a second preset threshold value. The first preset threshold value is typically set at 5% of the rated phase voltage, and the second preset threshold value is typically set at 10% of the rated current. When both the zero-sequence voltage and zero-sequence current meet the threshold conditions, a single-phase grounding fault is determined. For a phase-to-phase short circuit fault, the judgment criteria are: a significant increase in the current between any two phases and a significant decrease in the corresponding phase-to-phase voltage. A phase-to-phase short circuit typically manifests as the short-circuit phase current reaching several times the normal current, while the phase-to-phase voltage drops to tens of percent of the normal voltage. By executing the fault type judgment logic, a fault type identification result is obtained, clearly distinguishing whether the fault type is a single-phase ground fault or a phase-to-phase short circuit. Based on the fault type identification result, the specific fault phase is further determined. For a single-phase ground fault, it is necessary to determine which phase is grounded. This is done by comparing the vector sum of each phase voltage and the zero-sequence voltage with the original phase voltage. The specific judgment logic is: the vector sum of each phase voltage and the zero-sequence voltage is calculated. If the vector sum of a phase is less than the original voltage, the phase is determined to be grounded. This judgment is based on power system fault theory. In a single-phase ground fault, the voltage of the faulted phase is opposite to the zero-sequence voltage, resulting in the vector sum being less than the original phase voltage.

[0059] In a specific embodiment, the process of executing step S103 may specifically include the following steps:

[0060] Setting a dynamic processing threshold for the line signal based on the amplitude of the zero-sequence voltage and the zero-sequence current to obtain an adaptive signal processing threshold;

[0061] Input the line signal into the wavelet transform processing unit, use the mother wavelet function to decompose the signal, and obtain eight layers of wavelet decomposition coefficients;

[0062] Adaptive signal processing threshold is applied to filter the detail coefficients in the eight-layer wavelet decomposition coefficients to obtain high-frequency characteristic coefficients.

[0063] The high-frequency feature coefficients are input into the sliding window analysis unit, and the analysis window of fixed length is set with a window overlap ratio of 50% to obtain the feature analysis segment of the continuous time series;

[0064] Four characteristic parameters, namely, traveling wave amplitude, rise time, spectrum distribution and waveform polarity, are extracted from the characteristic analysis segments of the continuous time series to obtain a multi-dimensional characteristic parameter set.

[0065] The multidimensional feature parameter set is organized into a structured feature vector matrix and timestamp information is added to obtain anti-interference enhanced traveling wave feature information.

[0066] Specifically, the dynamic processing threshold automatically adjusts based on fault severity, ensuring that valid traveling wave signals are captured under varying fault conditions. A mapping relationship is established between zero-sequence quantities and thresholds. When the zero-sequence voltage amplitude exceeds 5% of the rated phase voltage and the zero-sequence current amplitude exceeds 10% of the rated current, indicating a high fault severity, a lower processing threshold is set to capture more traveling wave information. When the zero-sequence quantity is small, a higher threshold is set to filter out more interference signals. The threshold is calculated using a piecewise linear approach. The upper and lower threshold limits are first determined, and then linear interpolation is performed between the upper and lower limits based on the actual zero-sequence quantity values. For example, when the rated phase voltage is 10 kV and the rated current is 5 A, if the zero-sequence voltage is detected to be 1 kV (10% of the rated value) and the zero-sequence current is 1 A (20% of the rated value), the processing threshold is set to 80% of the baseline threshold, forming an adaptive signal processing threshold.

[0067] The wavelet transform provides both time-domain and frequency-domain information for a signal, making it suitable for analyzing non-stationary signals such as fault waves. The wavelet transform processing unit utilizes the discrete wavelet transform algorithm, using db4 (Daubechies 4th order) as the mother wavelet function, which is highly sensitive to spikes. The discrete wavelet transform process involves high-pass filtering and low-pass filtering. High-pass filtering yields detail coefficients (high-frequency information), while low-pass filtering yields approximation coefficients (low-frequency information). Eight iterative decompositions yield eight layers of wavelet decomposition coefficients, including an eighth-layer approximation coefficient and eight detail coefficients (d1 to d8) of varying scales. The lower-layer detail coefficients reflect the high-frequency characteristics of the signal, the higher-layer detail coefficients reflect the mid-frequency characteristics, and the approximation coefficients reflect the low-frequency characteristics.

[0068] Adaptive signal processing thresholds are applied to the detail coefficients within the eight-layer wavelet decomposition coefficients for coefficient screening. This coefficient screening employs a hard thresholding method, setting coefficients below the threshold to zero while retaining those above the threshold, thereby removing the effects of noise. The adaptive signal processing thresholds are adjusted when applied to detail coefficients at different layers. Typically, higher thresholds are used for low-layer detail coefficients (corresponding to high-frequency components) and lower thresholds are used for high-layer detail coefficients (corresponding to mid-frequency components). This differentiated processing accounts for the characteristics of noise distribution in different frequency bands. After coefficient screening, the remaining coefficients primarily reflect the characteristics of the fault traveling wave, forming high-frequency characteristic coefficients. These high-frequency characteristic coefficients are primarily concentrated in layers d1 to d4 and contain the key information about the fault traveling wave.

[0069] Sliding window analysis uses fixed-length windows to segment the signal. The window length is typically set to 2 milliseconds, with a 50% overlap between adjacent windows, meaning each window movement is 1 millisecond. The sliding window moves incrementally along the time axis, analyzing the high-frequency characteristic coefficients within each window to form a series of feature analysis segments. Each feature analysis segment is associated with a specific time point, marking the specific moment in time at which the segment occurred.

[0070] The traveling wave amplitude parameter is obtained by calculating the maximum peak value of the signal within the window and reflects the strength of the traveling wave. The rise time parameter is obtained by calculating the time required for the signal to rise from 10% of its peak value to 90% of its peak value and reflects the steepness of the traveling wave. The spectrum distribution parameter is obtained by performing a fast Fourier transform on the signal within the window and calculating the energy ratio of different frequency bands, reflecting the frequency domain characteristics of the traveling wave. The waveform polarity parameter is obtained by determining the positive and negative directions of the initial waveform and reflects the orientation of the fault point relative to the measurement point. These four characteristic parameters together constitute a multidimensional characteristic parameter set that comprehensively describes the characteristics of the traveling wave signal. Each parameter has a physical meaning: a larger amplitude indicates a more severe fault, a shorter rise time indicates a steeper traveling wave front, and a greater number of high-frequency components in the spectrum distribution indicates a sharper traveling wave signal. The waveform polarity is directly related to the determination of the fault direction.

[0071] The eigenvector matrix adopts a two-dimensional structure with rows representing time series and columns representing different eigenvalues. Each matrix element corresponds to the value of a specific eigenvalue at a specific moment. The matrix also contains precise timestamp information, marking the sampling moment for each row of data. These timestamps are derived from the GPS timing module and have an accuracy of 200 nanoseconds. This structured eigenvector matrix facilitates subsequent algorithm processing, particularly the application of traveling wave positioning algorithms.

[0072] In a specific embodiment, the process of executing step S104 may specifically include the following steps:

[0073] The fault section is determined based on the zero-sequence current. When the zero-sequence current exceeds a first preset threshold, the main line traveling wave positioning switch and the branch line intelligent fuse are selected as measurement points. When the zero-sequence current is lower than the first preset threshold but higher than a second preset threshold, two adjacent intelligent fuses are selected as measurement points to obtain the traveling wave information of the two end measurement points involved in the positioning calculation.

[0074] Extract the traveling wave arrival timestamp from the traveling wave information at both ends of the measurement point, calculate the difference in the arrival time of the traveling waves at both ends, and obtain the fault traveling wave propagation time difference;

[0075] Multiply the fault traveling wave propagation time difference by the propagation speed of the electromagnetic wave in the line, and subtract the resulting product from the line length between the two measuring points to obtain twice the fault distance value;

[0076] Divide twice the fault distance value by two to get the target distance value from the fault point to the head-end measurement point;

[0077] The target distance value is matched with the line topology. When the fault is located at a T-junction, the traveling wave reflection characteristics are used for secondary verification. When the fault is located on a straight line, the position is directly confirmed to obtain the preliminary fault section location result.

[0078] The preliminary fault section location results are compared with the historical fault database, and the deviation values between the actual and calculated locations of similar historical faults are extracted. The deviation values are adjusted according to the current line load rate and seasonal factors to obtain the fault section location results.

[0079] Specifically, the zero-sequence current is used to determine the segments. Zero-sequence current is determined using a dual-threshold mechanism, with the first preset threshold typically set at 15% of the rated current and the second preset threshold set at 5% of the rated current. When the main control fuse detects a zero-sequence current exceeding the first preset threshold, it indicates that the fault area is relatively clear and the fault is severe. In this case, the traveling wave positioning switch on the trunk line and the smart fuse on the branch line are selected as the measurement point combination. This combination is suitable for situations where the fault occurs in the connection area between the trunk and the branch. When the zero-sequence current is lower than the first preset threshold but higher than the second preset threshold, it indicates that the fault is minor or located far away. In this case, two adjacent smart fuses are selected as the measurement point combination. This combination is suitable for situations where the fault occurs at the end of the branch line. This adaptive selection mechanism determines the two-end measurement points that best suit the current fault situation, and extracts complete traveling wave information from these two measurement points, including traveling wave waveform, amplitude, phase, and precise timestamp data.

[0080] The traveling wave arrival timestamp is extracted from the traveling wave information at both measurement points. This timestamp represents the precise moment when the fault traveling wave first arrives at the measurement point. It is determined using the traveling wave characteristic information extracted through wavelet transform. The arrival of the traveling wave is determined using a threshold detection method. The moment when the characteristic signal amplitude first exceeds the preset threshold is recorded as the traveling wave arrival time. The traveling wave arrival times are recorded at each measurement point, and the difference between these two times is calculated to obtain the fault traveling wave propagation time difference.

[0081] Multiply the fault wave propagation time difference by the electromagnetic wave propagation speed in the line, and then subtract the resulting product from the line length between the two measurement points. The electromagnetic wave propagation speed in power lines depends on the line type. For overhead lines, it is usually 2 / 3 the speed of light; for cable lines, it is 1 / 3 to 1 / 2 the speed of light. The line length between the two measurement points refers to the distance measured along the actual path of the line, taking into account bends and turns. When calculating, subtract the product of the time difference and the speed from the line length. The result is the sum of the distances from the fault point to the two measurement points, which is twice the fault distance.

[0082] Dividing twice the fault distance value by two yields the target distance from the fault point to the head-end measurement point. This step converts the calculated result into the form required for practical engineering applications. The head-end measurement point typically refers to the measurement point where the traveling wave first reaches, or a pre-designated reference measurement point. The target distance directly represents the distance from the fault point along the actual line path to the head-end measurement point. Line topology matching is performed on the target distance value. This requires considering the actual structure of the distribution line to map the calculated distance value to the actual line. When the fault is located at a T-junction, relying solely on distance calculation can lead to misjudgment due to the complex reflection and transmission phenomena of traveling waves at the branch point. Therefore, secondary verification is required using traveling wave reflection characteristics. Traveling wave reflection characteristics refer to the waveform characteristics of the traveling wave reflected from the branch point or fault point back to the measurement point, including polarity, amplitude, and arrival time. By analyzing these characteristics, it is possible to determine whether the fault occurs at a branch point or on a straight line segment. When the fault is located on a straight line, the traveling wave propagation path is clear, and the location can be directly confirmed without further verification. The results of line topology matching provide a preliminary fault segment location, clearly indicating the specific line segment where the fault is located.

[0083] The preliminary fault section location results are compared with a historical fault database, which records information about past faults, including fault type, location, calculated location, actual location, and environmental conditions. The database is searched to identify historical fault cases with similar fault type and location to the current fault, and the deviation between the calculated and actual locations in these cases is extracted. This deviation reflects the systematic error of the location algorithm under specific conditions and is caused by various factors, such as line parameter variations and measurement errors. The master control fuse dynamically adjusts the deviation based on the current line load factor and seasonal factors. Line load factor affects line temperature, which in turn affects the propagation speed of electromagnetic waves. Seasonal factors such as temperature and humidity can also affect line characteristics. The adjusted deviation is applied to the preliminary location results to obtain a more accurate fault section location.

[0084] In a specific embodiment, the process of executing step S105 may specifically include the following steps:

[0085] The severity of the fault judgment results is evaluated. According to the amplitude and duration of zero-sequence voltage and zero-sequence current, the fault is divided into three levels: emergency fault, serious fault and minor fault, and the fault severity classification result is obtained;

[0086] Formulate differentiated protection action plans based on the fault severity classification results and fault section location results. For emergency faults, the fuse will immediately perform a drop action. For severe faults, the fuse will perform a delayed drop action. For minor faults, the fuse will only be recorded without performing a drop action. The intelligent fuse drop control instruction is then obtained.

[0087] The intelligent fuse drop control instruction is transmitted to the corresponding intelligent fuse control unit, triggering the drop mechanism of the intelligent fuse to perform the breaking operation, thereby achieving the physical isolation effect of the fault section;

[0088] Conduct correlation analysis between the fault section location results and the distribution system topology, define the affected user range and key load conditions, and obtain a fault impact assessment report;

[0089] Upload the fault diagnosis results, fault section location results, and fault impact assessment report to the distribution automation system master station via the 4G communication module, generate a maintenance work order containing the fault point latitude and longitude coordinates, fault type, fault time, and recommended treatment plan, and obtain dispatch information from the operation and maintenance personnel;

[0090] Perform time series analysis on all previous failure data to identify equipment degradation trends and failure-frequently occurring sections, and obtain predictive maintenance information.

[0091] Specifically, a basic score is set based on the zero-sequence voltage amplitude. When the zero-sequence voltage exceeds 20% of the rated phase voltage, the basic score is 10 points; when it exceeds 10% but is less than 20%, the basic score is 5 points; and when it is less than 10% but greater than 5%, the basic score is 2 points. The basic score is then corrected based on the zero-sequence current amplitude. When the zero-sequence current exceeds 30% of the rated current, the basic score is increased by 5 points; when it exceeds 15% but is less than 30%, the basic score is increased by 3 points; and when it is less than 15% but greater than 5%, the basic score is increased by 1 point. A second correction is made based on the fault duration. If the duration exceeds 5 seconds, the basic score is increased by 3 points; if it exceeds 1 second but is less than 5 seconds, the basic score is increased by 1 point; and if it is less than 1 second, no points are added. The final score categorizes the fault into three levels: a score of 12 or greater is considered an emergency fault; a score between 6 and 11 is considered a severe fault; and a score of 5 or less is considered a minor fault.

[0092] Differentiated protection action plans are developed based on the fault severity classification and fault location, employing intelligent decision-making logic. For emergency faults, the fuse tripping action is immediately executed, without waiting or secondary confirmation, directly triggering the fuse tripping mechanism. Emergency faults are typically severe short circuits or three-phase imbalances, which pose a significant threat to equipment. For severe faults, a delayed tripping action is executed, typically with a delay of 0.5 to 2 seconds. During this time, the fault status is continuously monitored. If the fault resolves itself, the tripping command is canceled; if the fault persists, the tripping action is executed after the delay expires. Minor faults are recorded, but the tripping action is not executed. Fault information is stored and reported, without powering off. Differentiated protection action plans are automatically generated by the master control fuse based on preset logic, producing precise intelligent fuse tripping control instructions. These instructions include the action type (immediate tripping, delayed tripping, or no tripping), the target fuse identifier, and the execution time. For emergency and severe faults, the master control fuse transmits the tripping control instructions to the target fuse via 433MHz radio frequency communication. After receiving the command, the control unit of the target fuse first verifies the command's integrity and validity, then activates the fuse's drop mechanism. This mechanism is an electromagnetic release device that releases the mechanical lock by energizing the electromagnetic coil, generating a magnetic field that causes the fuse tube to drop under gravity, physically disconnecting the circuit. During the drop process, a position sensor monitors the position of the fuse tube in real time. When a complete drop signal is detected, the control unit generates a disconnect confirmation message and feeds it back to the master fuse via radio frequency communication, forming a closed-loop control system to ensure the faulty section is physically isolated.

[0093] The fault section location results are correlated with the distribution system topology. This correlation analysis first extracts network structure information related to the fault section from the distribution network topology database to determine the electrical connections upstream and downstream of the fault point. The affected distribution transformer substations are then identified, and the specific scope of the power outage is determined by tracing all distribution transformers downstream of the fault point. For each affected distribution transformer substation, user information within the substation is further extracted, including user type (residential, industrial and commercial, agricultural, or special user) and user importance level. Important loads such as hospitals, schools, and government agencies are specifically marked to determine whether there is an emergency power supply demand. This information is integrated to generate a fault impact assessment report, which details the number of affected substations, the number of users, the critical load conditions, and the estimated economic losses.

[0094] Uploading fault diagnosis results, fault section location, and fault impact assessment reports to the distribution automation system master station via the 4G communication module is a key step in achieving information sharing. The 4G communication module built into the master control fuse utilizes the mobile communication network to package information into standard data frames and transmit them to the distribution automation system master station via an encrypted channel. Upon receiving this information, the master station stores it in the fault management database and simultaneously plots the latitude and longitude coordinates of the fault point on an electronic map using a GIS (Geographic Information System). Based on the fault type, location, and impact area, the system automatically generates a maintenance work order. This work order includes a precise description of the fault point, fault type, onset time, severity, impact area, and a recommended solution. Once generated, the work order is pushed to the nearest maintenance personnel via SMS or mobile apps, allowing them to distribute information and provide guidance for on-site repair work.

[0095] Time series analysis of historical fault data is a core component of predictive maintenance. Using sliding window technology, this approach conducts statistical and trend analysis on fault data over a specific time period (e.g., six months or one year). The analysis categorizes fault data by line segment, fault type, and environmental conditions. The frequency, interval, and severity trends of each type of fault are then calculated. Using algorithms such as linear regression and exponential smoothing, the failure probability of each line segment over the next period is predicted. For line segments with a significant increase in fault frequency, further analysis is conducted to identify possible signs of equipment degradation, such as increased fusing and increased zero-sequence current fluctuations. By combining information such as equipment installation time, operating environment, and load conditions, an equipment degradation assessment model is developed to predict the equipment's remaining lifespan. Ultimately, predictive maintenance information is generated, including a list of high-risk line segments, recommended maintenance times, and key inspection items, providing data support for planned maintenance.

[0096] For example, during winter rain and snow, the B-phase master intelligent fuse detected a zero-sequence voltage of 2.5 kV (25% of the rated phase voltage of 10 kV), a zero-sequence current of 2.3 A (46% of the rated current of 5 A), and a fault duration of 3 seconds on a 10 kV distribution line. According to the scoring mechanism, the zero-sequence voltage is assigned a base score of 10 points, the zero-sequence current correction adds 5 points, and the duration correction adds 1 point, for a total score of 16 points, resulting in an emergency fault. Simultaneously, the traveling wave location algorithm determined that the fault was located in a mountainous section of the line 2.3 kilometers from the substation. The master fuse immediately generated a trip control command, which was transmitted via 433 MHz radio frequency communication to the corresponding intelligent fuse, triggering the trip mechanism to operate. The power was disconnected within 0.1 seconds of the fault onset. The position sensor confirmed the trip completion and provided status feedback. The system then conducted a correlation analysis of the fault sections and determined that it affected three distribution substations and a total of 120 customers, including a township health center (a critical load). All information is uploaded to the distribution automation master station via a 4G module. The system automatically generates a maintenance work order, providing the precise fault location (longitude 119.xx, latitude 30.xx), fault type (single-phase ground fault), occurrence time (2023-12-15 08:23:45), and recommended actions to regional operations and maintenance personnel. Time series analysis also revealed that this section had experienced four similar faults in the past six months, a significantly higher frequency than other sections. Predictive analysis indicated possible aging of the line's insulators, suggesting a comprehensive inspection and, if necessary, replacement of insulators along the entire line in addition to addressing this current fault. Based on the precise location and recommended actions, operations and maintenance personnel proceeded directly to the fault site and discovered that an insulator had been damaged by heavy rain and snow loads, resulting in contact between the phase conductor and the tower and causing a single-phase ground fault. The entire fault handling process, from initiation to repair, took only 1.5 hours, saving over three hours compared to traditional methods.

[0097] In a specific embodiment, the process of performing the step of correlating the fault section location result with the power distribution system topology may specifically include the following steps:

[0098] The fault section location result is spatially mapped with the distribution network topology data to determine the line section where the fault point is located and the electrical connection relationship, and obtain the network topology breakpoint location;

[0099] Identify all power distribution nodes that cannot obtain power supply based on the network topology breakpoint location and obtain the precise boundary of the power outage range;

[0100] Cluster analysis is performed on the distribution transformer area data within the precise power outage range, and stratified according to power supply capacity and load characteristics to obtain graded load impact data;

[0101] Extract the first-level security user information from the hierarchical load impact data and combine it with the backup power supply configuration status to obtain the emergency power supply demand list;

[0102] Based on the precise outage boundary and graded load impact data, the load loss quantitative index is calculated, and the economic loss model is established using the time weighting factor to obtain the time-based impact severity curve;

[0103] The network topology breakpoint location, precise power outage boundary, graded load impact data, emergency power supply demand list and time-based impact severity curve are integrated into a hierarchical structure report to obtain a fault impact assessment report.

[0104] Specifically, the fault segment location results are spatially mapped with the distribution network topology data. This spatial mapping process utilizes the line geometry and electrical connection relationships pre-stored in the distribution network topology database to convert the distance value to the fault point calculated by traveling wave location into specific physical location coordinates. In implementation, segment information for the faulty line is extracted from the distribution network topology database, including the start and end coordinates, length, and connection relationships of each segment. The distance value from the fault point to a reference point is then used to locate the fault on the line, determining the specific segment and its precise position within that segment. This process takes into account the actual alignment and curvature of the line. The fault point is located by accumulating the lengths of each segment until the accumulated value exceeds or equals the fault distance. Simultaneously, electrical connection information for the faulty line segment is extracted, including the location and operating status of upstream and downstream switches, fuses, and junction boxes. A local electrical connection diagram is then drawn, ultimately determining the network topology breakpoint—the point where the network is disconnected due to the fault. The outage scope is determined by identifying all distribution nodes without power based on the location of the network topology breakpoint. An electrical connectivity analysis algorithm is used to trace all nodes without power downstream from the network topology breakpoint. Starting from the breakpoint, the algorithm traverses all downstream branches of the network graph, marking all nodes without power. In implementation, a directed graph model of the distribution network is first established, with nodes representing equipment such as substations, distribution transformers, and junction boxes, and edges representing line connections. A breadth-first search is then performed, starting from the power supply node, marking all reachable nodes as energized. The network topology breakpoint is removed from the graph, and a breadth-first search is performed again, starting from the power supply node. All unreachable nodes are considered out of power. By comparing the differences between the two search results, the set of nodes without power due to the fault is precisely determined, forming the precise outage boundary. This boundary is stored as both a node list and a set of geographic coordinates.

[0105] Cluster analysis first extracts characteristic data from all distribution substations within the outage area, including transformer capacity, number of users, user type distribution, and peak-valley load differences. K-means or hierarchical clustering algorithms are then used to categorize substations into different levels based on power supply capacity and load characteristics. Power supply capacity categorization is typically based on transformer rated capacity, with loads below 100 kVA considered small, 100-315 kVA considered medium, and 315 kVA and above considered large. Load characteristic categorization considers factors such as peak-valley differences in the load curve, power factor, and seasonal variations, categorizing loads into stable, fluctuating, and spiky types. The clustering process calculates the Euclidean distance or cosine similarity between the feature vectors of each substation, grouping substations with similar characteristics into the same category. The resulting tiered load impact data includes information such as the number of substations, total capacity, number of users, and typical load curves for each level, providing a data foundation for fault impact assessment. Level 1 guaranteed users are specialized users with extremely high power supply reliability requirements, such as hospitals, schools, government agencies, and communication base stations. The extraction process first queries the user database for information on all users within the power outage range, and selects users belonging to the first-level protection category based on the preset user importance grading standards. These users are then further analyzed to extract key information such as their power consumption capacity, critical load descriptions, and maximum allowable power outage time. At the same time, the backup power configuration status of these users is queried, including the capacity and sustainable power supply time of their own generators, UPS systems, or dual power switching devices. By comparing the user's critical load requirements with the backup power capacity, the actual impact of the power outage on these users is assessed to determine whether additional emergency power supply measures are needed. The assessment results form an emergency power supply demand list, which includes a list of users who need priority to restore power or require support from mobile generators, as well as the specific needs and contact information of each user.

[0106] Based on precise outage boundaries and tiered load impact data, load loss quantitative indicators are calculated. These indicators encompass three dimensions: outage capacity, outage energy, and economic loss. Outage capacity is directly derived from the tiered load impact data and represents the total transformer capacity affected by the outage. Outage energy is calculated using typical load curves. This method multiplies the typical load factor of each substation at different times by the transformer capacity, and then multiplies this by the outage duration to obtain the estimated outage energy. Economic loss calculations incorporate a time-weighted factor. The economic losses caused by outages vary significantly across time periods. For example, daytime outages on weekdays have a much greater impact on industrial and commercial users than nighttime outages. Time-weighted factors are derived from historical data and are typically categorized into weekday daytime, weeknight, weekend, and holiday periods. Each period is assigned a different economic loss coefficient per unit of energy. Multiplying the outage energy by the corresponding economic loss coefficient yields an estimated economic loss for each time period. This creates a time-based impact severity curve, visually demonstrating the changing impact of the fault over time.

[0107] Integrating the network topology breakpoint location, precise outage boundary, tiered load impact data, emergency power supply demand list, and time-based impact severity curves into a hierarchical report structure is a key step in producing the final FIA report. This integration process utilizes a hierarchical data organization approach, arranging various types of information according to spatial and logical relationships. The report begins with a fault overview section, including basic information such as the fault occurrence time, type, and network topology breakpoint location. Next, the outage boundary section includes a textual description and map display of the precise outage boundary. Next, the customer impact section includes statistical tables and charts of tiered load impact data. This is followed by a focus section listing key customer information from the emergency power supply demand list. Finally, the economic assessment section presents time-based impact severity curves and overall economic loss estimates. Standardized data formats and uniform information coding are used during this integration process to ensure consistency and readability. A unique identifier is also generated for the report to facilitate subsequent querying and statistical analysis. The resulting FIA report contains both detailed technical data and clear reference value for management decision-making.

[0108] The above describes the traveling wave positioning method based on the intelligent fuse in the embodiment of the present application. The following describes the traveling wave positioning system based on the intelligent fuse in the embodiment of the present application. Figure 2 In the embodiment of the present application, an embodiment of a traveling wave positioning system based on an intelligent fuse includes:

[0109] The sampling module 201 is used to install intelligent fuses on the three phases of the distribution line and perform high-frequency sampling on the line signal to obtain digital data including power frequency signals and high-frequency signals;

[0110] The calculation module 202 is used to transmit the digital data to the main control fuse, and use the main control fuse to perform zero-sequence quantity synthesis calculation to obtain zero-sequence voltage, zero-sequence current and fault judgment results;

[0111] An extraction module 203 is configured to apply adaptive threshold wavelet transform processing to the collected line signal according to the zero-sequence voltage and the zero-sequence current, extract multi-layer wavelet coefficients and construct a eigenvector matrix to obtain anti-interference enhanced traveling wave characteristic information;

[0112] The distance measurement module 204 is configured to combine the zero-sequence current and the traveling wave characteristic information to perform distance calculation on the fault point using an improved two-terminal location algorithm to obtain a fault section location result;

[0113] The grading module 205 is configured to execute a graded protection control strategy based on the fault judgment result and the fault section location result to obtain predictive maintenance information.

[0114] Through the coordinated cooperation of the above components, by installing intelligent fuses on the three phases of the distribution line and performing high-frequency sampling on the line signals, digital data containing power frequency signals and high-frequency signals are obtained, which solves the problem that traditional fuses cannot monitor the line status in real time; the digital data is transmitted to the main control fuse and the zero-sequence quantity synthesis calculation is performed to obtain the zero-sequence voltage, zero-sequence current and fault judgment results, thereby realizing the accurate identification of the fault type and improving the accuracy of fault judgment; the adaptive threshold wavelet transform is applied to the collected line signal according to the zero-sequence voltage and zero-sequence current, the multi-layer wavelet coefficients are extracted and the characteristic vector matrix is constructed to obtain the anti-interference enhanced traveling wave feature information, which greatly improves the anti-interference ability and feature extraction efficiency of traveling wave signal processing; combined with the zero-sequence current and traveling wave feature information, the improved two-terminal positioning algorithm is used to measure the distance of the fault point position, obtain the accurate fault section positioning result, and improve the fault positioning accuracy from hundreds of meters of the traditional method to tens of meters; based on the fault judgment results and the fault section positioning results, a hierarchical protection control strategy is implemented to obtain intelligent fault isolation and early warning The present invention fully utilizes the key contributions of artificial intelligence algorithm features to the solution. In particular, adaptive threshold wavelet transform processing and eigenvector matrix construction enable the automatic extraction of effective features from complex power signals. The improved two-terminal positioning algorithm greatly improves the accuracy of traveling wave positioning through intelligent parameter adjustment and line impedance correction. The hierarchical protection control strategy utilizes an intelligent decision-making algorithm to achieve differentiated processing based on the nature of the fault. These algorithmic features together constitute the core technical advantage of the present invention and solve the "last mile" monitoring problem of distribution network. In addition, this method also enables accurate assessment of the fault impact range and predictive maintenance. By analyzing the time series of historical fault data, it identifies equipment degradation trends and fault-prone sections, fundamentally improving the operational reliability and maintenance efficiency of the distribution network and transforming the distribution system from passive protection to active prevention. Practical application has verified that this method can shorten fault handling time from the traditional several hours to tens of minutes, significantly reducing power outage losses and operation and maintenance costs.

[0115] above Figure 2 The traveling wave positioning system based on the smart fuse in the embodiment of the present invention is described in detail from the perspective of modular functional entities. The traveling wave positioning device based on the smart fuse in the embodiment of the present invention is described in detail from the perspective of hardware processing.

[0116] Figure 3This is a schematic diagram of the structure of a traveling wave locating device based on a smart fuse, provided by an embodiment of the present invention. The traveling wave locating device 300 based on a smart fuse may vary significantly depending on configuration or performance. It may include one or more central processing units (CPUs) 310 (e.g., one or more processors), a memory 320, and one or more storage media 330 (e.g., one or more mass storage devices) storing application programs 333 or data 332. The memory 320 and storage medium 330 may be either transient or persistent storage. The program stored in the storage medium 330 may include one or more modules (not shown), each of which may include a series of instruction operations within the traveling wave locating device 300 based on a smart fuse. Furthermore, the processor 310 may be configured to communicate with the storage medium 330, executing the series of instruction operations stored in the storage medium 330 on the traveling wave locating device 300 based on a smart fuse, thereby implementing the steps of the traveling wave locating method based on a smart fuse described above.

[0117] The traveling wave positioning device 300 based on the smart fuse may further include one or more power supplies 340, one or more wired or wireless network interfaces 350, one or more input and output interfaces 360, and / or one or more operating systems 331, such as Windows Server, Mac OS X, Unix, Linux, FreeBSD, etc. It will be understood by those skilled in the art that Figure 3 The structure of the traveling wave locating device based on the smart fuse shown does not constitute a limitation on the traveling wave locating device based on the smart fuse provided by the present invention, and may include more or fewer components than shown in the figure, or combine certain components, or arrange the components differently.

[0118] The present invention also provides a computer-readable storage medium, which may be a non-volatile computer-readable storage medium or a volatile computer-readable storage medium. The computer-readable storage medium stores instructions, which, when executed on a computer, enable the computer to execute the steps of the traveling wave positioning method based on an intelligent fuse.

[0119] Those skilled in the art will clearly understand that, for the convenience and brevity of description, the specific working processes of the above-described systems, systems and units can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0120] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, or the part that contributes to the prior art, or all or part of the technical solution can be embodied in the form of a software product. The computer software product is stored in a storage medium and includes several instructions for enabling a traveling wave positioning device based on an intelligent fuse (which can be a personal computer, server, or network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present invention. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM), random access memory (RAM), disk or optical disk, and other media that can store program code.

[0121] The above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit the same. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the various embodiments of the present invention.

Claims

1. A traveling wave positioning method based on intelligent fuse, characterized in that: The method comprises: Smart fuses are installed on the three phases of the distribution line and high-frequency sampling is performed on the line signals to obtain digital data containing power frequency signals and high-frequency signals. A traveling wave positioning switch is installed on the trunk line, and smart fuses with GPS timing modules are installed on the three phases of the branch line. The smart fuses are then configured for clock synchronization with a synchronization accuracy of 200 nanoseconds. The digital data is transmitted to the main control fuse, and the main control fuse is used to perform zero-sequence quantity synthesis calculation to obtain zero-sequence voltage, zero-sequence current and fault judgment results, including: The digitized data is sent to the main phase intelligent fuse through the radio frequency communication module to obtain a three-phase synchronous data set; the three-phase synchronous data set is timestamp checked to filter out data with a time synchronization error exceeding a preset threshold to obtain target three-phase data; the target three-phase data is input into the zero-sequence voltage calculation unit to perform a three-phase voltage vector sum operation to obtain a zero-sequence voltage real-time value; the target three-phase data is input into the zero-sequence current calculation unit to perform a three-phase current vector sum operation to obtain a zero-sequence current real-time value; the fault type judgment logic is executed according to the zero-sequence voltage real-time value and the zero-sequence current real-time value, and when the zero-sequence voltage real-time value exceeds a first preset threshold and the zero-sequence current real-time value exceeds a second preset threshold, it is determined to be a single-phase grounding fault, and when the current of any two phases increases and the corresponding phase-to-phase voltage decreases, it is determined to be a phase-to-phase short circuit fault, and a fault type identification result is obtained; based on the fault type identification result, the phase whose phase voltage and zero-sequence voltage vector sum is less than the original phase voltage is determined to be a grounded phase, and a fault judgment result is obtained; Applying adaptive threshold wavelet transform processing to the collected line signal according to the zero-sequence voltage and the zero-sequence current, extracting multi-layer wavelet coefficients and constructing a characteristic vector matrix to obtain anti-interference enhanced traveling wave characteristic information, including: setting a dynamic processing threshold for the line signal based on the amplitude of the zero-sequence voltage and the zero-sequence current to obtain an adaptive signal processing threshold; Input the line signal into the wavelet transform processing unit, use the mother wavelet function to decompose the signal, and obtain eight layers of wavelet decomposition coefficients; apply the adaptive signal processing threshold to the detail coefficients in the eight layers of wavelet decomposition coefficients to filter the coefficients to obtain high-frequency characteristic coefficients; input the high-frequency characteristic coefficients into the sliding window analysis unit, set the analysis window of fixed length and the window overlap ratio to 50%, and obtain the characteristic analysis segment of the continuous time series; extract four types of characteristic parameters of the characteristic analysis segment of the continuous time series, namely, traveling wave amplitude, rise time, spectrum distribution and waveform polarity, to obtain a multidimensional characteristic parameter set; organize the multidimensional characteristic parameter set into a structured characteristic vector matrix, and add timestamp information to obtain anti-interference enhanced traveling wave characteristic information; Combined with the zero-sequence current and the traveling wave characteristic information, an improved two-end positioning algorithm is used to perform distance calculation on the fault point position to obtain the fault section positioning result, including: judging the line range where the fault section is located according to the zero-sequence current, when the zero-sequence current exceeds the first preset threshold, selecting the main line traveling wave positioning switch and the branch line intelligent fuse as the measurement point, when the zero-sequence current is lower than the first preset threshold but higher than the second preset threshold, selecting two adjacent intelligent fuses as the measurement point, and obtaining the traveling wave information of the two end measurement points involved in the positioning calculation; extracting the traveling wave arrival timestamp from the traveling wave information of the two end measurement points, calculating the difference between the traveling wave arrival times at the two ends, and obtaining the fault traveling wave propagation time difference; and using the fault traveling wave propagation time as the measurement point. The difference is multiplied by the propagation speed of electromagnetic waves in the line, and the product is subtracted from the line length between the two end measurement points to obtain twice the fault distance value; the twice fault distance value is divided by two to obtain the target distance value from the fault point to the head end measurement point; the target distance value is matched with the line topology, and when the fault is located at a T-junction, the traveling wave reflection feature is used for secondary verification; when the fault is located on a straight line, the position is directly confirmed to obtain a preliminary fault section location result; the preliminary fault section location result is compared with the historical fault database, and the deviation value between the actual location and the calculated location of similar historical faults is extracted. The deviation value is adjusted according to the current line load rate and seasonal factors to obtain the fault section location result; Based on the fault judgment result and the fault section location result, a hierarchical protection control strategy is executed to obtain predictive maintenance information.

2. The traveling wave positioning method based on the intelligent fuse according to claim 1 is characterized in that: The method of installing intelligent fuses on the three phases of the power distribution line and performing high-frequency sampling on the line signal to obtain digital data containing power frequency signals and high-frequency signals includes: Install a traveling wave positioning switch on the trunk line, install smart fuses with GPS timing modules on the three phases of the branch line, and perform clock synchronization configuration on the smart fuses. The synchronization accuracy of the clock synchronization configuration is 200 nanoseconds. The high-frequency current transformer and voltage sensor in the intelligent fuse are used to collect data on the line signal to obtain the original analog electrical signal; Inputting the original analog electrical signal into the digital conversion module of the control unit for analog-to-digital conversion processing to obtain digital data; Performing noise suppression and frequency band separation processing on the digitized data to obtain a power frequency signal and a high frequency signal; The amplitude and phase of the power frequency signal are calculated to obtain the phase voltage, phase current, active power, reactive power and power factor parameters of the line operation status, and timestamp information is added to the high frequency signal and stored in the local memory.

3. The traveling wave positioning method based on the intelligent fuse according to claim 1, characterized in that: The step of executing a hierarchical protection control strategy based on the fault judgment result and the fault section location result to obtain predictive maintenance information includes: Performing a severity evaluation on the fault judgment result, classifying the fault into three levels: emergency fault, serious fault, and minor fault according to the amplitude and duration of the zero-sequence voltage and zero-sequence current, and obtaining a fault severity classification result; Formulate differentiated protection action plans based on the fault severity classification results and the fault section location results, immediately execute the drop action for emergency faults, execute the delayed drop action for severe faults, and only record the drop without executing the drop for minor faults, and obtain the intelligent fuse drop control instruction; The intelligent fuse drop control instruction is transmitted to the corresponding intelligent fuse control unit, triggering the drop mechanism of the intelligent fuse to perform a breaking operation, thereby achieving a physical isolation effect of the fault section; Conduct correlation analysis on the fault section location results and the distribution system topology, define the affected user range and key load conditions, and obtain a fault impact assessment report; Upload the fault judgment result, the fault section location result, and the fault impact assessment report to the distribution automation system master station via the 4G communication module, generate a maintenance work order containing the longitude and latitude coordinates of the fault point, fault type, fault time, and recommended treatment plan, and obtain dispatch information from the operation and maintenance personnel; Perform time series analysis on all previous failure data to identify equipment degradation trends and failure-frequently occurring sections, and obtain predictive maintenance information.

4. The traveling wave positioning method based on the intelligent fuse according to claim 3 is characterized in that: The fault section location result is correlated with the distribution system topology and analyzed to define the affected user range and critical load conditions, and obtain a fault impact assessment report, including: Perform spatial mapping of the fault section location result with the distribution network topology data to determine the line section where the fault point is located and the electrical connection relationship, and obtain the network topology breakpoint location; Identify all power distribution nodes that cannot obtain power supply according to the network topology breakpoint location to obtain the precise power outage range boundary; Performing cluster analysis on the distribution transformer area data within the precise power outage range, stratifying them according to power supply capacity and load characteristics, and obtaining graded load impact data; Extracting first-level security user information from the hierarchical load impact data and combining it with the backup power supply configuration status to obtain an emergency power supply demand list; Calculating a load loss quantification index based on the precise outage range boundary and the graded load impact data, establishing an economic loss model using a time weighting factor, and obtaining a time-based impact severity curve; The network topology breakpoint location, the precise power outage range boundary, the graded load impact data, the emergency power supply demand list and the time-divided impact severity curve are integrated into a hierarchical structure report to obtain a fault impact assessment report.

5. A traveling wave positioning system based on intelligent fuse, characterized in that: For implementing the traveling wave positioning method based on the smart fuse according to any one of claims 1 to 4, the traveling wave positioning system based on the smart fuse comprises: A sampling module is used to install smart fuses on the three phases of the distribution line and perform high-frequency sampling on the line signals to obtain digital data containing power frequency signals and high-frequency signals. A traveling wave positioning switch is installed on the trunk line, and smart fuses with GPS timing modules are installed on the three phases of the branch line. The smart fuses are then configured for clock synchronization with a synchronization accuracy of 200 nanoseconds. The calculation module is used to transmit the digital data to the main control fuse, and use the main control fuse to perform zero-sequence quantity synthesis calculation to obtain zero-sequence voltage, zero-sequence current and fault judgment results, including: sending the digital data to the main phase intelligent fuse through the radio frequency communication module to obtain a three-phase synchronous data set; performing time stamp verification processing on the three-phase synchronous data set, screening out data with time synchronization errors exceeding a preset threshold, and obtaining target three-phase data; inputting the target three-phase data into the zero-sequence voltage calculation unit to perform three-phase voltage vector sum operation to obtain the real-time value of the zero-sequence voltage; inputting the target three-phase data into the zero-sequence voltage calculation unit to perform three-phase voltage vector sum operation to obtain the real-time value of the zero-sequence voltage; The zero-sequence current calculation unit performs a three-phase current vector sum operation to obtain a real-time zero-sequence current value; a fault type judgment logic is executed based on the real-time zero-sequence voltage value and the real-time zero-sequence current value, and when the real-time zero-sequence voltage value exceeds a first preset threshold value and the real-time zero-sequence current value exceeds a second preset threshold value, it is determined to be a single-phase grounding fault; when the currents of any two phases increase and the corresponding inter-phase voltage decreases, it is determined to be an inter-phase short circuit fault, thereby obtaining a fault type identification result; based on the fault type identification result, a phase whose phase voltage and zero-sequence voltage vector sum is less than the original phase voltage is determined to be a grounded phase, thereby obtaining a fault judgment result; An extraction module is configured to apply adaptive threshold wavelet transform processing to the collected line signal based on the zero-sequence voltage and the zero-sequence current, extract multi-layer wavelet coefficients and construct a feature vector matrix to obtain anti-interference enhanced traveling wave characteristic information, including: setting a dynamic processing threshold for the line signal based on the amplitude of the zero-sequence voltage and the zero-sequence current to obtain an adaptive signal processing threshold; inputting the line signal into a wavelet transform processing unit, performing signal decomposition using a mother wavelet function to obtain eight layers of wavelet decomposition coefficients; applying the adaptive signal processing threshold to filter the detail coefficients in the eight layers of wavelet decomposition coefficients to obtain high-frequency characteristic coefficients; inputting the high-frequency characteristic coefficients into a sliding window analysis unit, setting an analysis window of a fixed length with a window overlap ratio of 50%, and obtaining a characteristic analysis segment of a continuous time series; extracting four characteristic parameters of traveling wave amplitude, rise time, spectrum distribution, and waveform polarity from the characteristic analysis segment of the continuous time series to obtain a multidimensional characteristic parameter set; organizing the multidimensional characteristic parameter set into a structured characteristic vector matrix and adding timestamp information to obtain anti-interference enhanced traveling wave characteristic information; The distance measurement module is used to combine the zero-sequence current and the traveling wave characteristic information, use the improved two-end positioning algorithm to perform distance calculation on the fault point position, and obtain the fault section positioning result, including: judging the line range where the fault section is located according to the zero-sequence current, when the zero-sequence current exceeds the first preset threshold, selecting the main line traveling wave positioning switch and the branch line intelligent fuse as the measurement point, when the zero-sequence current is lower than the first preset threshold but higher than the second preset threshold, selecting two adjacent intelligent fuses as the measurement point, and obtaining the traveling wave information of the two end measurement points involved in the positioning calculation; extracting the traveling wave arrival timestamp from the traveling wave information of the two end measurement points, calculating the difference between the traveling wave arrival times at the two ends, and obtaining the fault traveling wave propagation time difference; and using the fault traveling wave as the measurement point. The propagation time difference is multiplied by the propagation speed of the electromagnetic wave in the line, and the resulting product is subtracted from the line length between the two end measurement points to obtain twice the fault distance value; the twice fault distance value is divided by two to obtain the target distance value from the fault point to the head-end measurement point; the target distance value is matched with the line topology, and when the fault is located at a T-junction, the traveling wave reflection feature is used for secondary verification; when the fault is located on a straight line, the location is directly confirmed to obtain a preliminary fault section location result; the preliminary fault section location result is compared with a historical fault database, and the deviation between the actual location and the calculated location of similar historical faults is extracted. The deviation value is adjusted according to the current line load rate and seasonal factors to obtain the fault section location result; The grading module is used to execute a graded protection control strategy based on the fault judgment result and the fault section location result to obtain predictive maintenance information.

6. A traveling wave positioning device based on an intelligent fuse, characterized in that: The method comprises a memory and a processor, wherein the memory stores a computer program that can be run on the processor, and when the processor executes the computer program, the traveling wave positioning method based on the intelligent fuse according to any one of claims 1 to 4 is implemented.

7. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the processor is enabled to perform the traveling wave positioning method based on the smart fuse according to any one of claims 1 to 4.

Images