Cable fault intelligent positioning diagnosis method and system based on double-end traveling waves

Abstract

The invention discloses an intelligent cable fault positioning and diagnosing method and system based on double-end traveling waves, and relates to the technical field of cable fault positioning and diagnos.The method comprises the steps that monitoring systems are synchronously arranged at the two ends of a cable line, a self-adaptive signal adjusting mechanism is designed, and double-end data of a transmitting signal and a receiving signal are processed based on the double-end traveling waves; and constructing a topological structure model of the cable network by using the double-end traveling wave data features, training a fault point location by using a double-end data fault training model, and completing diagnosis of intelligent positioning of a cable fault. According to the invention, the problems of signal attenuation and noise interference are solved, the identification capability of a small partial discharge phenomenon is enhanced, the accurate positioning of a fault point in a complex multi-branch cable network is realized, the state of the cable network can be updated in real time, the method adapts to environmental changes, and the timeliness of a diagnosis result is ensured.

Description

Technical Field

[0001] The present invention relates to the technical field of cable fault location diagnosis, and in particular to a cable fault intelligent location diagnosis method and system based on double-end traveling waves. Background Art

[0002] With the continuous development of the global economy and the acceleration of urbanization, modern society has put forward higher requirements for the stability and reliability of power supply. Especially in the context of smart cities and industries, the development of various high-tech industries and the improvement of residents' living standards require that power networks not only cover a wider area, but also be able to carry a larger load. In this case, cables, as an important medium for power transmission, become particularly important for their safety and stability. However, due to natural environmental factors (such as extreme weather), man-made damage and other unforeseen problems, cable failures occur from time to time, which poses a serious threat to the normal operation of the power system. Therefore, there is an urgent need for an efficient and accurate cable fault location and diagnosis method to ensure that the power system can resume normal operation in the shortest time to reduce economic losses and social impacts.

[0003] At present, the existing intelligent cable fault location and diagnosis technology mainly relies on traditional means such as the single-ended traveling wave method or the bridge method. These methods have exposed some limitations in practical applications. When dealing with cable lines under complex terrain conditions, the traditional single-ended traveling wave method is difficult to accurately identify small local discharge phenomena at the far end of the cable. This is mainly due to the influence of signal attenuation and noise interference. When it comes to multi-branch cable networks, existing technologies are often unable to effectively distinguish whether the fault occurs on the trunk cable or the branch cable, resulting in a decrease in positioning accuracy. The lack of ability to identify small local discharge phenomena and the problem of inaccurate fault location in multi-branch cable networks have become a challenge. Summary of the invention

[0004] In view of the problems existing in the existing cable fault intelligent positioning and diagnosis method and system based on double-ended traveling waves, the present invention is proposed.

[0005] Therefore, the present invention aims to solve the problems of signal attenuation, noise interference and insufficient recognition of small partial discharges in the single-ended traveling wave method in complex terrain and multi-branch cable networks in the prior art. The present invention improves the positioning accuracy and reliability through double-ended traveling wave data processing and convolutional neural network feature extraction.

[0006] In order to solve the above technical problems, the present invention provides the following technical solutions: In the first aspect, an embodiment of the present invention provides a cable fault intelligent positioning and diagnosis method based on a double-ended traveling wave, which includes synchronously setting a monitoring system at both ends of the cable line, the monitoring system including a signal transmitting unit and a signal receiving unit, designing an adaptive signal adjustment mechanism, adjusting the environmental condition parameters of the signal transmitting unit and the signal receiving unit, and synchronizing the time of signal transmission and signal reception; Based on the double-ended traveling wave, the double-ended data of the transmitting signal and the receiving signal are processed, the double-ended traveling wave data features in the processing are extracted using a convolutional neural network, and the double-ended traveling wave data features are used to construct a topological structure model of the cable network, wherein the topological structure model includes a recursive neural network model and a double-ended data fault training model; The topological structure model of the cable network is used to establish a database in combination with the length and propagation time of the original cable. The location of the fault point is calculated by using the time difference between the transmitted signal and the received signal tracked by the database and the recursive neural network model. The fault point is trained using a dual-end data fault training model to complete the diagnosis of the intelligent positioning of the cable fault.

[0007] As a preferred solution of the cable fault intelligent positioning and diagnosis method based on double-end traveling waves described in the present invention, wherein: the monitoring system is synchronously set up at both ends of the cable line, including using the time synchronization technology of the satellite navigation system to obtain the parameter configuration of the signal transmitting unit and the signal receiving unit, combined with the atomic clock calibration module, to dynamically correct the electromagnetic interference problem of the time synchronization technology caused by temperature changes. The atomic clock calibration module includes obtaining the parameter configuration of the transmitting unit and the signal receiving unit for nanosecond time synchronization application scenarios by utilizing the quanta of atoms under electromagnetic radiation.

[0008] As a preferred solution of the cable fault intelligent location diagnosis method based on double-ended traveling waves of the present invention, wherein: the design of the adaptive signal adjustment mechanism includes establishing a prediction model by combining historical data with the acquired parameter configuration, wherein the historical data includes a type of environmental condition parameters collected during the previous signal transmission process, and adjusting the signal transmission process based on the prediction model; The establishment of the prediction model includes multi-source heterogeneous data fusion of temperature, humidity and electromagnetic interference intensity of a class of environmental condition parameters, and signal-to-noise ratio, bit error rate and cable operation status of signal quality indicators, wherein the cable operation status includes load current and voltage fluctuation of the cable; The multi-source heterogeneous data fusion includes using a variational autoencoder to enhance the features of a class of environmental condition parameters, extracting deep patterns hidden in the load current and voltage fluctuation data of the cable, and the deep patterns include the nonlinear changes of the signal-to-noise ratio and the bit error rate in the time series; the time series includes the time series features in the historical data, using the dynamic time warping method to align time series of different lengths, constructing a hybrid model of long short-term memory network and attention mechanism, designing an intelligent agent based on reinforcement learning, dynamically adjusting the frequency, power and modulation mode of the signal transmitting unit according to the acquired parameter configuration and signal quality indicators of the signal transmitting unit and the signal receiving unit, and synchronizing the time of signal transmission and signal reception.

[0009] As a preferred solution of the cable fault intelligent location diagnosis method based on double-end traveling waves of the present invention, the processing of the double-end data of the transmitting signal and the receiving signal includes introducing a variational mode decomposition method to decompose the signal received during time synchronization, and extracting the local discharge characteristics of different frequency components of the synchronized signal; Decomposing the received signal during time synchronization includes proposing an adaptive multi-scale variational mode decomposition method based on the variational mode decomposition method, which is used to accurately decompose the time-synchronized received signal, and the adaptive multi-scale variational mode decomposition method includes dynamically adjusting the decomposition scale and center frequency range of the synchronized signal; The decomposition scale includes using fast Fourier transform to perform spectrum analysis on the synchronized signal and extracting features from the spectrum distribution. The features include the main frequency bandwidth, energy distribution ratio, high-frequency noise and low-frequency drift ratio. According to the extracted features, a dynamic K value calculation formula based on energy segmentation is proposed: ; in, represents the decomposition scale, Indicates the total number of sub-bands in which the spectrum is divided, Indicates The energy proportion of each sub-band is Indicates the preset energy threshold, represents the indicator function; The center frequency range includes a frequency peak point for extracting features from the spectrum distribution using a peak detection algorithm, and the calculation formula of the peak detection algorithm is: ; in, Indicates the frequency Spectrum The first derivative of Indicates the frequency Spectrum The second-order derivative of Indicates frequency, represents the user-defined scaling factor, represents the threshold parameter, represents the mean of the spectrum, represents the standard deviation of the spectrum, Represents a set of peak points.

[0010] As a preferred solution of the cable fault intelligent location diagnosis method based on double-ended traveling waves of the present invention, wherein: the center frequency range also includes introducing the signal-to-noise ratio as a constraint condition to optimize the center frequency, and the optimization of the center frequency includes calculating the local signal-to-noise ratio of the frequency bands near each center frequency; When the signal-to-noise ratio is lower than the set threshold When the low frequency band is set, the band is composed of noise, excluding the center frequency corresponding to the noise; When the signal-to-noise ratio is higher than or equal to the set threshold When the high frequency band is set, the band contains effective signal components and the corresponding noise center frequency is retained; The threshold Including setting thresholds based on the statistical properties of the signal-to-noise ratio distribution ; The nearby frequency band range is calculated as: ; in, Indicates the frequency band width, represents the center frequency; The formula for calculating the local signal-to-noise ratio of the frequency band near each center frequency is: ; in, represents the signal power, represents the noise power, Represents the local signal-to-noise ratio at the center frequency.

[0011] As a preferred solution of the cable fault intelligent positioning and diagnosis method based on double-terminal traveling waves of the present invention, wherein: the double-terminal traveling wave data features in the process of extracting and processing using a convolutional neural network include capturing the time distribution characteristics of the signal through a convolutional layer to extract the double-terminal traveling wave data features of the peak point position, and the convolutional neural network includes a one-dimensional convolutional neural network and a two-dimensional convolutional neural network; Convert the transmitted and received signals into CNN input form, which is represented as a one-dimensional time series or a two-dimensional time-frequency spectrum; If it is time series data, it is input into a one-dimensional convolutional neural network; If it is a time-frequency spectrum, it is input into a two-dimensional convolutional neural network; When the time distribution characteristics are captured in the one-dimensional convolutional neural network, the one-dimensional convolutional neural network signal is scanned to extract the double-end traveling wave data features; When the time distribution characteristics are captured in the two-dimensional convolutional neural network, the convolution kernel slides on the time axis and frequency axis to extract the double-end traveling wave data features; The extracted double-terminal traveling wave data features are expressed as vector form, and the formula is: ; in, represents the double-ended traveling wave data eigenvector, represents the feature dimension, represents the feature dimension of the first double-ended traveling wave data feature vector, represents the characteristic dimension of the second double-ended traveling wave data feature vector, Indicates The characteristic dimension of the double-ended traveling wave data feature vector; The construction of the topological structure model of the cable network includes combining the double-ended traveling wave data features with historical data and performing topology through a double-ended data fault training model; The formula for combining the double-ended traveling wave data features with the historical data is: ; in, represents the weight coefficient, represents the double-ended traveling wave data eigenvector, Represents historical data, represents the combined feature vector; The topology training model using the double-ended data fault training model includes: nodes in the cable network are combined with feature vectors It indicates that the output of the double-ended data fault training model is used to adjust the nodes in the cable network; When a fault is detected in a node in the cable network, the weight coefficient is reduced.

[0012] As a preferred solution of the cable fault intelligent positioning and diagnosis method based on double-ended traveling waves described in the present invention, wherein: the establishment of the database includes establishing a cable network topology database according to the N node positions of the cable, and using a double-ended data fault training model to train the cable network topology database; the training of the cable network topology database includes capturing the loss function in the database, and using the double-ended traveling wave data features to incorporate the loss function in the database into the capture process in real time, so that the model adapts to the changes in the cable network and completes the diagnosis of the intelligent positioning of the cable fault.

[0013] In the second aspect, an embodiment of the present invention provides a cable fault intelligent positioning and diagnosis system based on double-end traveling waves, which includes: an adjustment mechanism module, which synchronously sets up monitoring systems at both ends of the cable line and designs an adaptive signal adjustment mechanism; a processing module, which processes the double-end data of the transmitting signal and the receiving signal based on the double-end traveling wave, uses a convolutional neural network to extract the double-end traveling wave data features in the processing process, and uses the double-end traveling wave data features to construct a topological structure model of the cable network; a diagnosis module, which uses the topological structure model of the cable network and adopts a double-end data fault training model to train the fault point to complete the diagnosis of the intelligent positioning of the cable fault.

[0014] In a third aspect, an embodiment of the present invention provides a computer device, including a memory and a processor, wherein the memory stores a computer program, wherein: when the processor executes the computer program, it implements any step of the above-mentioned cable fault intelligent location and diagnosis method based on double-end traveling waves.

[0015] In a fourth aspect, an embodiment of the present invention provides a computer-readable storage medium having a computer program stored thereon, wherein: when the computer program is executed by a processor, any step of the above-mentioned cable fault intelligent location and diagnosis method based on double-ended traveling waves is implemented.

[0016] The beneficial effects of the present invention are as follows: the present invention improves the accuracy and efficiency of cable fault location by combining double-end traveling wave data processing with intelligent algorithms, solves the problems of signal attenuation and noise interference by using a double-end synchronous monitoring system and an adaptive signal adjustment mechanism, enhances the ability to identify small local discharge phenomena, introduces a convolutional neural network to extract features and construct a cable network topology model, and achieves accurate location of fault points in complex multi-branch cable networks. The signal processing process is optimized by dynamic time warping and variational mode decomposition, which improves the accuracy and reliability of data processing. The database established based on the recursive neural network and double-end data fault training model can update the cable network status in real time, adapt to environmental changes, and ensure the timeliness of the diagnosis results. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the following briefly introduces the drawings required for describing the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work. Among them: Figure 1 A flow chart of a cable fault intelligent positioning and diagnosis method and system based on double-ended traveling waves provided by an embodiment of the present invention.

[0018] Figure 2A schematic diagram of intelligent fault location of a cable fault intelligent location diagnosis method and system based on double-ended traveling waves provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0019] In order to make the above-mentioned purposes, features and advantages of the present invention more obvious and easy to understand, the specific implementation methods of the present invention are described in detail below in conjunction with the drawings of the specification. Obviously, the described embodiments are part of the embodiments of the present invention, but not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary persons in the art without creative work should fall within the scope of protection of the present invention.

[0020] In the following description, many specific details are set forth to facilitate a full understanding of the present invention, but the present invention may also be implemented in other ways different from those described herein, and those skilled in the art may make similar generalizations without violating the connotation of the present invention. Therefore, the present invention is not limited to the specific embodiments disclosed below.

[0021] Secondly, the term "one embodiment" or "embodiment" as used herein refers to a specific feature, structure, or characteristic that may be included in at least one implementation of the present invention. The term "in one embodiment" that appears in different places in this specification does not necessarily refer to the same embodiment, nor does it refer to a separate or selective embodiment that is mutually exclusive with other embodiments.

[0022] The present invention is described in detail with reference to schematic diagrams. When describing the embodiments of the present invention, for the sake of convenience, the cross-sectional diagrams showing the device structure will not be partially enlarged according to the general scale, and the schematic diagrams are only examples, which should not limit the scope of protection of the present invention. In addition, in actual production, the three-dimensional dimensions of length, width and depth should be included.

[0023] At the same time, in the description of the present invention, it should be noted that the directions or positional relationships indicated by the terms "upper, lower, inner and outer" are based on the directions or positional relationships shown in the drawings, and are only for the convenience of describing the present invention and simplifying the description, rather than indicating or implying that the device or element referred to must have a specific direction, be constructed and operated in a specific direction, and therefore cannot be understood as limiting the present invention. In addition, the terms "first, second or third" are only used for descriptive purposes and cannot be understood as indicating or implying relative importance.

[0024] In the present invention, unless otherwise clearly specified and limited, the terms "install, connect, connect" should be understood in a broad sense, for example: it can be a fixed connection, a detachable connection or an integral connection; it can also be a mechanical connection, an electrical connection or a direct connection, or it can be indirectly connected through an intermediate medium, or it can be the internal communication of two components. For ordinary technicians in this field, the specific meanings of the above terms in the present invention can be understood according to specific circumstances.

[0025] Example 1 Reference Figure 1 and Figure 2 , which is the first embodiment of the present invention, and provides a cable fault intelligent location and diagnosis method based on double-ended traveling waves, comprising: S1: A monitoring system is synchronously set up at both ends of the cable line. The monitoring system includes a signal transmitting unit and a signal receiving unit. An adaptive signal adjustment mechanism is designed to adjust the environmental condition parameters of the signal transmitting unit and the signal receiving unit, and synchronize the time of signal transmission and signal reception.

[0026] Among them, the monitoring system is synchronously set up at both ends of the cable line, including using the time synchronization technology of the satellite navigation system to obtain the parameter configuration of the signal transmitting unit and the signal receiving unit, and combining the atomic clock calibration module to dynamically correct the electromagnetic interference problem of the time synchronization technology caused by temperature changes. The atomic clock calibration module includes obtaining the parameter configuration of the transmitting unit and the signal receiving unit for nanosecond time synchronization application scenarios by utilizing the quantum of atoms under electromagnetic radiation.

[0027] S1.1: Designing an adaptive signal adjustment mechanism includes establishing a prediction model by combining the acquired parameter configuration with historical data, where the historical data includes a type of environmental condition parameters collected during previous signal transmission processes, and adjusting the signal transmission process based on the prediction model; Establishing the prediction model involves fusing multi-source heterogeneous data of a class of environmental condition parameters, such as temperature, humidity, and electromagnetic interference intensity, with signal quality indicators, such as signal-to-noise ratio, bit error rate, and cable operation status. The cable operation status includes load current and voltage fluctuation of the cable. Multi-source heterogeneous data fusion includes using variational autoencoders to enhance the features of a class of environmental condition parameters, extracting deep patterns hidden in the load current and voltage fluctuation data of the cable. The deep patterns include the nonlinear changes of signal-to-noise ratio and bit error rate in time series; time series include the time series characteristics in historical data, using dynamic time warping to align time series of different lengths, building a hybrid model of long and short-term memory networks and attention mechanisms, and designing intelligent agents based on reinforcement learning. According to the acquired parameter configurations and signal quality indicators of the signal transmitting unit and the signal receiving unit, the frequency, power and modulation method of the signal transmitting unit are dynamically adjusted to synchronize the time of signal transmission and signal reception.

[0028] S2: Based on the two-end traveling wave, the two-end data of the transmitting signal and the receiving signal are processed, and the two-end traveling wave data features in the processing process are extracted using a convolutional neural network. The two-end traveling wave data features are used to build a topological structure model of the cable network. The topological structure model includes a recursive neural network model and a two-end data fault training model.

[0029] The processing of the dual-end data of the transmitting signal and the receiving signal includes introducing the variational mode decomposition method to decompose the received signal during time synchronization, and extracting the local discharge characteristics of different frequency components of the synchronized signal; Decomposing the received signal during time synchronization includes proposing an adaptive multi-scale variational mode decomposition method based on the variational mode decomposition method, which is used to accurately decompose the received signal during time synchronization. The adaptive multi-scale variational mode decomposition method includes dynamically adjusting the decomposition scale and center frequency range of the synchronized signal. The decomposition scale includes using fast Fourier transform to perform spectrum analysis on the synchronized signal and extracting features from the spectrum distribution. The features include the main frequency bandwidth, energy distribution ratio, high-frequency noise, and the proportion of low-frequency drift. According to the extracted features, a dynamic K value calculation formula based on energy segmentation is proposed: ; in, represents the decomposition scale, Indicates the total number of sub-bands in which the spectrum is divided, Indicates The energy proportion of each sub-band is Indicates the preset energy threshold, represents the indicator function; The center frequency range includes the frequency peak point for extracting features from the spectrum distribution using a peak detection algorithm. The calculation formula of the peak detection algorithm is: ; in, Indicates the frequency Spectrum The first derivative of Indicates the frequency Spectrum The second-order derivative of Indicates frequency, represents the user-defined scaling factor, represents the threshold parameter, represents the mean of the spectrum, represents the standard deviation of the spectrum, Represents a set of peak points.

[0030] Furthermore, when processing the dual-end data of the transmitting signal and the receiving signal based on the dual-end traveling wave, the variational mode decomposition method is introduced to decompose the time-synchronized signal, extract the local discharge characteristics of different frequency components, and divide the spectrum into 10 sub-bands. Analysis shows that the main frequency band width is concentrated in the range of 30 kHz to 70 kHz, among which the energy of the fourth sub-band accounts for the highest proportion, reaching 40%; high-frequency noise accounts for 15% of the total energy, and low-frequency drift accounts for 10% of the total energy. The calculation shows that the optimal decomposition scale is 6 segments, and the peak detection algorithm is used to optimize the center frequency range. Assuming that at a frequency of 50 kHz, it is determined by calculation that the point meets the peak condition, and it is included in the peak point set to further improve the signal decomposition accuracy. The processing and extraction data of the dual-end data are shown in Table 1 below: Table 1 Processing and extraction data table of double-end data Parameter name Value and unit Remark Number of sub-bands 10 Total number of sub-bands into which the spectrum is divided Main frequency bandwidth lower limit 30 kHz The lower limit of the main frequency bandwidth range Upper limit of main frequency bandwidth 70 kHz Upper limit of the main frequency bandwidth range Energy proportion of the 4th sub-band 40% The sub-band with the highest energy share in the main frequency band High frequency noise energy ratio 15% The proportion of high-frequency noise to total energy Low frequency drift energy ratio 10% The proportion of low frequency drift to total energy Optimal decomposition scale 6 segments The calculated optimal decomposition scale Peak detection frequency 50 kHz Frequency points in the peak detection algorithm Among them, Table 1 summarizes the key data in the cable fault location method based on double-ended traveling waves, and Table 2 shows that the number of sub-bands divided by the spectrum is 10, and the main frequency band width ranges from 30 to 70 kHz. The energy of the fourth sub-band accounts for the highest proportion, reaching 40%, while high-frequency noise and low-frequency drift account for 15% and 10% of the total energy respectively. The optimal decomposition scale is calculated to be 6 segments, and the peak point with a frequency of 50 kHz is determined in the peak detection algorithm. These data provide an important basis for signal decomposition and feature extraction, thereby effectively supporting the construction of cable network topology model and fault diagnosis.

[0031] S2.1: The center frequency range also includes introducing the signal-to-noise ratio as a constraint condition to optimize the center frequency. The optimization of the center frequency includes calculating the local signal-to-noise ratio of the frequency bands near each center frequency. When the signal-to-noise ratio is lower than the set threshold When the low frequency band is set, the band is composed of noise, excluding the center frequency corresponding to the noise; When the signal-to-noise ratio is higher than or equal to the set threshold When the high frequency band is set, the band contains effective signal components and the corresponding noise center frequency is retained; Threshold Including setting thresholds based on the statistical properties of the signal-to-noise ratio distribution ; The nearby frequency band range is calculated as: ; in, Indicates the frequency band width, represents the center frequency; The formula for calculating the local signal-to-noise ratio for the frequency band near each center frequency is: ; in, represents the signal power, represents the noise power, Represents the local signal-to-noise ratio at the center frequency.

[0032] S2.2: using a convolutional neural network to extract double-terminal traveling wave data features during the processing, including capturing the time distribution characteristics of the signal through a convolutional layer to extract the double-terminal traveling wave data features of the peak point position, the convolutional neural network including a one-dimensional convolutional neural network and a two-dimensional convolutional neural network; Convert the transmitted and received signals into CNN input form, which is represented as a one-dimensional time series or a two-dimensional time-frequency spectrum; If it is time series data, it is input into a one-dimensional convolutional neural network; If it is a time-frequency spectrum, it is input into a two-dimensional convolutional neural network; When the time distribution characteristics are captured in the one-dimensional convolutional neural network, the one-dimensional convolutional neural network signal is scanned to extract the double-end traveling wave data features; When the time distribution characteristics are captured in the two-dimensional convolutional neural network, the convolution kernel slides on the time axis and frequency axis to extract the double-end traveling wave data features; The extracted double-terminal traveling wave data features are expressed as vector form, and the formula is: ; in, represents the double-ended traveling wave data eigenvector, represents the feature dimension, represents the feature dimension of the first double-ended traveling wave data feature vector, represents the characteristic dimension of the second double-ended traveling wave data feature vector, Indicates The characteristic dimension of the double-ended traveling wave data feature vector; Constructing the topological structure model of the cable network includes combining the characteristics of the two-end traveling wave data with the historical data and topologically training the model through the two-end data fault; The formula for combining the characteristics of double-ended traveling wave data with historical data is: ; in, represents the weight coefficient, represents the double-ended traveling wave data eigenvector, Represents historical data, represents the combined feature vector; The topology training model based on the double-ended data fault includes the nodes in the cable network being composed of the combined feature vectors It indicates that the output of the double-ended data fault training model is used to adjust the nodes in the cable network; When a fault is detected in a node in the cable network, the weight coefficient is reduced.

[0033] S3: Use the topological structure model of the cable network, combined with the length and propagation time of the original cable to establish a database. Use the database and the recursive neural network model to track the time difference between the transmitted signal and the received signal to calculate the location of the fault point. Use the dual-end data fault training model to train the fault point and complete the diagnosis of the intelligent positioning of the cable fault.

[0034] Among them, establishing a database includes establishing a cable network topology database according to the N node positions of the cable, using a double-ended data fault training model to train the cable network topology database, and training the cable network topology database includes capturing the loss function in the database, using double-ended traveling wave data features to incorporate the loss function in the database into the real-time capture process, so that the model adapts to changes in the cable network and completes the diagnosis of intelligent positioning of cable faults.

[0035] In a preferred embodiment, a cable fault intelligent positioning and diagnosis system based on double-end traveling waves includes an adjustment mechanism module, which synchronously sets up monitoring systems at both ends of the cable line and designs an adaptive signal adjustment mechanism; a processing module, which processes the double-end data of the transmitting signal and the receiving signal based on the double-end traveling wave, uses a convolutional neural network to extract the double-end traveling wave data features in the processing process, and uses the double-end traveling wave data features to construct a topological structure model of the cable network; a diagnosis module, which uses the topological structure model of the cable network and adopts a double-end data fault training model to train the fault point to complete the diagnosis of the intelligent positioning of the cable fault.

[0036] The above-mentioned unit modules may be embedded in or independent of a processor in a computer device in the form of hardware, or may be stored in a memory in a computer device in the form of software, so that the processor can call and execute operations corresponding to the above-mentioned modules.

[0037] The computer device may be a terminal, and the computer device includes a processor, a memory, a communication interface, a display screen and an input device connected via a system bus. The processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The communication interface of the computer device is used to communicate with an external terminal in a wired or wireless manner, and the wireless manner can be achieved through WIFI, an operator network, NFC (near field communication) or other technologies. The display screen of the computer device may be a liquid crystal display screen or an electronic ink display screen, and the input device of the computer device may be a touch layer covering the display screen, or a key, trackball or touchpad provided on the housing of the computer device, or an external keyboard, touchpad or mouse, etc.

[0038] In summary, the present invention improves the accuracy and efficiency of cable fault location by combining double-end traveling wave data processing with intelligent algorithms, solves the problems of signal attenuation and noise interference by using a double-end synchronous monitoring system and an adaptive signal adjustment mechanism, enhances the ability to identify small local discharge phenomena, introduces a convolutional neural network to extract features and construct a cable network topology model, and achieves accurate location of fault points in complex multi-branch cable networks. The signal processing process is optimized by dynamic time warping and variational mode decomposition, which improves the accuracy and reliability of data processing. The database established based on recursive neural networks and double-end data fault training models can update the cable network status in real time, adapt to environmental changes, and ensure the timeliness of diagnostic results.

[0039] Example 2 Reference Figure 1 and Figure 2 , which is the second embodiment of the present invention, and this embodiment provides a cable fault intelligent location and diagnosis method based on double-ended traveling waves. In order to verify the beneficial effects of the present invention, scientific demonstration is carried out through simulation experiments.

[0040] In the process of optimizing the center frequency, when the statistical characteristics analysis results of the signal-to-noise ratio distribution show that the average value of the signal-to-noise ratio is 15dB, the standard deviation is 3dB, and the threshold is set to 12dB, in the frequency band range calculation formula near the center frequency, assuming that the center frequency is 50 kHz and the frequency band width is 10 kHz, the nearby frequency band range is 45 kHz to 55 kHz. When calculating the local signal-to-noise ratio of the frequency band near each center frequency, assuming that the signal power is 0.8 and the noise power is 0.2, the formula is calculated to obtain The local signal-to-noise ratio of the center frequency is 4dB. Since this value is lower than the set threshold of 12dB, the frequency band is judged as a low frequency band, and the corresponding center frequency of 50 kHz is excluded. For another center frequency of 70 kHz, the nearby frequency band ranges from 65 kHz to 75 kHz. The local signal-to-noise ratio calculated by the same method is 16dB, which is higher than the set threshold of 12dB. Therefore, the frequency band is judged as a high frequency band, and the corresponding center frequency of 70 kHz is retained. The center frequency optimization data is shown in Table 2 below: Table 2 Center frequency optimization data table Parameter name Value and unit Remark Average signal-to-noise ratio 15 dB Statistical analysis results of signal-to-noise ratio distribution Signal-to-noise ratio standard deviation 3 dB Statistical analysis results of signal-to-noise ratio distribution Threshold 12 dB Threshold set according to signal-to-noise ratio distribution Center frequency 1 50 kHz Initial center frequency Bandwidth 10 kHz Frequency band calculation parameters around the center frequency Frequency band range (50 kHz) 45-55 kHz Frequency band with center frequency around 50 kHz Signal power (50 kHz) 0.8 Signal power at center frequency 50 kHz Noise power (50 kHz) 0.2 Noise power at center frequency 50 kHz Local signal-to-noise ratio (50 kHz) 4 dB Local signal-to-noise ratio at center frequency 50 kHz Center frequency 2 70 kHz Another initial center frequency Frequency band range (70 kHz) 65-75 kHz Frequency band with center frequency around 70 kHz Local signal-to-noise ratio (70 kHz) 16 dB Local signal-to-noise ratio at center frequency 70 kHz Table 2 shows the key data in the center frequency optimization process, including the average and standard deviation of the signal-to-noise ratio, the set threshold, and the frequency band range near the two center frequencies, signal power, noise power and local signal-to-noise ratio. By calculating and comparing the local signal-to-noise ratio and the threshold, the center frequency of 50 kHz in the low frequency band is excluded, and the center frequency of 70 kHz in the high frequency band is retained, thereby achieving effective optimization of the center frequency. The comparison between the present invention and the prior art is shown in Table 3 below: Table 3 Comparison table between the present invention and the prior art Compare Projects Prior art Technical solution of the present invention Signal processing methods Single-ended traveling wave method or bridge method is difficult to handle signal attenuation problems in complex terrain and multi-branch cable networks Double-ended traveling wave data processing combined with adaptive multi-scale variational mode decomposition method effectively reduces signal attenuation and noise interference Partial discharge feature extraction capability Insufficient ability to identify small partial discharge phenomena The convolutional neural network (CNN) is introduced to extract the characteristics of double-terminal traveling wave data, which significantly improves the recognition accuracy of small partial discharge. Frequency Optimization Mechanism Lack of SNR optimization for center frequency Set thresholds based on signal-to-noise ratio distribution, dynamically optimize center frequency, and exclude low signal-to-noise ratio frequency bands Topology Modeling It is difficult to accurately distinguish the fault points of the trunk cable and the branch cable Using recursive neural network model and two-terminal data fault training model to build cable network topology and improve positioning accuracy Environmental adaptability Unable to adapt to fluctuations in signal quality caused by changes in environmental conditions such as temperature and humidity Design an adaptive signal adjustment mechanism to dynamically correct the signal transmission process by combining historical data and prediction models Database update capability The database update is delayed, making it difficult to reflect the cable network status in real time Capture the loss function in the database in real time and incorporate the characteristics of the two-terminal traveling wave data to ensure that the model adapts to dynamic changes in the network Table 3 clearly shows the optimization and improvement of the technical solution of the present invention in signal processing, feature extraction, frequency optimization, topology modeling, environmental adaptability and database update.

[0041] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention rather than to limit it. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical solutions of the present invention may be modified or replaced by equivalents without departing from the spirit and scope of the technical solutions of the present invention, which should all be included in the scope of the claims of the present invention.

Claims

1. A cable fault intelligent location and diagnosis method based on double-ended traveling waves, characterized in that: include, A monitoring system is synchronously set at both ends of the cable line, the monitoring system includes a signal transmitting unit and a signal receiving unit, and an adaptive signal adjustment mechanism is designed to adjust the environmental condition parameters of the signal transmitting unit and the signal receiving unit, and synchronize the time of signal transmission and signal reception; Based on the double-ended traveling wave, the double-ended data of the transmitting signal and the receiving signal are processed, the double-ended traveling wave data features in the processing are extracted using a convolutional neural network, and the double-ended traveling wave data features are used to construct a topological structure model of the cable network, wherein the topological structure model includes a recursive neural network model and a double-ended data fault training model; The topological structure model of the cable network is used to establish a database in combination with the length and propagation time of the original cable. The location of the fault point is calculated by using the time difference between the transmitted signal and the received signal tracked by the database and the recursive neural network model. The fault point is trained using a dual-end data fault training model to complete the diagnosis of the intelligent positioning of the cable fault.

2. The cable fault intelligent location diagnosis method based on double-ended traveling waves according to claim 1 is characterized in that: The monitoring system is synchronously set up at both ends of the cable line, including using the time synchronization technology of the satellite navigation system to obtain the parameter configuration of the signal transmitting unit and the signal receiving unit, and combining with the atomic clock calibration module to dynamically correct the electromagnetic interference problem of the time synchronization technology caused by temperature changes. The atomic clock calibration module includes obtaining the parameter configuration of the transmitting unit and the signal receiving unit for nanosecond time synchronization application scenarios by utilizing the quanta of atoms under electromagnetic radiation.

3. The cable fault intelligent location diagnosis method based on double-ended traveling waves according to claim 2 is characterized in that: The design of the adaptive signal adjustment mechanism includes establishing a prediction model by combining the acquired parameter configuration with historical data, wherein the historical data includes a type of environmental condition parameters collected during previous signal transmission processes, and adjusting the signal transmission process based on the prediction model; The establishment of the prediction model includes multi-source heterogeneous data fusion of temperature, humidity and electromagnetic interference intensity of a class of environmental condition parameters, and signal-to-noise ratio, bit error rate and cable operation status of signal quality indicators, wherein the cable operation status includes load current and voltage fluctuation of the cable; The multi-source heterogeneous data fusion includes using a variational autoencoder to enhance the features of a class of environmental condition parameters, extracting deep patterns hidden in the load current and voltage fluctuation data of the cable, and the deep patterns include the nonlinear changes of the signal-to-noise ratio and the bit error rate in the time series; the time series includes the time series features in the historical data, using the dynamic time warping method to align time series of different lengths, constructing a hybrid model of long short-term memory network and attention mechanism, designing an intelligent agent based on reinforcement learning, dynamically adjusting the frequency, power and modulation mode of the signal transmitting unit according to the acquired parameter configuration and signal quality indicators of the signal transmitting unit and the signal receiving unit, and synchronizing the time of signal transmission and signal reception.

4. The cable fault intelligent location and diagnosis method based on double-ended traveling waves according to claim 3 is characterized in that: The processing of the double-end data of the transmitting signal and the receiving signal includes introducing a variational mode decomposition method to decompose the received signal during time synchronization, and extracting the local discharge characteristics of different frequency components of the synchronized signal; Decomposing the received signal during time synchronization includes proposing an adaptive multi-scale variational mode decomposition method based on the variational mode decomposition method, which is used to accurately decompose the time-synchronized received signal, and the adaptive multi-scale variational mode decomposition method includes dynamically adjusting the decomposition scale and center frequency range of the synchronized signal; The decomposition scale includes using fast Fourier transform to perform spectrum analysis on the synchronized signal and extracting features from the spectrum distribution. The features include the main frequency bandwidth, energy distribution ratio, high-frequency noise and low-frequency drift ratio. According to the extracted features, a dynamic K value calculation formula based on energy segmentation is proposed: ； in, represents the decomposition scale, Indicates the total number of sub-bands in which the spectrum is divided, Indicates The energy proportion of each sub-band is Indicates the preset energy threshold, represents the indicator function; The center frequency range includes a frequency peak point for extracting features from the spectrum distribution using a peak detection algorithm, and the calculation formula of the peak detection algorithm is: ； in, Indicates the frequency Spectrum The first derivative of Indicates the frequency Spectrum The second-order derivative of Indicates frequency, represents the user-defined scaling factor, represents the threshold parameter, represents the mean of the spectrum, represents the standard deviation of the spectrum, Represents a set of peak points.

5. The cable fault intelligent location diagnosis method based on double-ended traveling waves according to claim 4 is characterized in that: The center frequency range also includes introducing the signal-to-noise ratio as a constraint condition to optimize the center frequency, and the optimization of the center frequency includes calculating the local signal-to-noise ratio of the frequency band near each center frequency; When the signal-to-noise ratio is lower than the set threshold When the low frequency band is set, the band is composed of noise, excluding the center frequency corresponding to the noise; When the signal-to-noise ratio is higher than or equal to the set threshold When the high frequency band is set, the band contains effective signal components and the corresponding noise center frequency is retained; The threshold Including setting thresholds based on the statistical properties of the signal-to-noise ratio distribution ; The nearby frequency band range is calculated as: ； in, Indicates the frequency band width, represents the center frequency; The formula for calculating the local signal-to-noise ratio of the frequency band near each center frequency is: ； in, represents the signal power, represents the noise power, Represents the local signal-to-noise ratio at the center frequency.

6. The cable fault intelligent location diagnosis method based on double-ended traveling waves according to claim 5, characterized in that: The double-terminal traveling wave data features in the process of extracting the double-terminal traveling wave data features using the convolutional neural network include capturing the time distribution characteristics of the signal through a convolutional layer to extract the double-terminal traveling wave data features of the peak point position, and the convolutional neural network includes a one-dimensional convolutional neural network and a two-dimensional convolutional neural network; Convert the transmitted and received signals into CNN input form, which is represented as a one-dimensional time series or a two-dimensional time-frequency spectrum; If it is time series data, it is input into a one-dimensional convolutional neural network; If it is a time-frequency spectrum, it is input into a two-dimensional convolutional neural network; When the time distribution characteristics are captured in the one-dimensional convolutional neural network, the one-dimensional convolutional neural network signal is scanned to extract the double-end traveling wave data features; When the time distribution characteristics are captured in the two-dimensional convolutional neural network, the convolution kernel slides on the time axis and frequency axis to extract the double-end traveling wave data features; The extracted double-terminal traveling wave data features are expressed as vector form, and the formula is: ； in, represents the double-ended traveling wave data eigenvector, represents the feature dimension, represents the feature dimension of the first double-ended traveling wave data feature vector, represents the characteristic dimension of the second double-ended traveling wave data feature vector, Indicates The characteristic dimension of the double-ended traveling wave data feature vector; The construction of the topological structure model of the cable network includes combining the double-ended traveling wave data features with historical data and performing topology through a double-ended data fault training model; The formula for combining the double-ended traveling wave data features with the historical data is: ； in, represents the weight coefficient, represents the double-ended traveling wave data eigenvector, Represents historical data, represents the combined feature vector; The topology training model using the double-ended data fault training model includes: nodes in the cable network are combined with feature vectors It indicates that the output of the double-ended data fault training model is used to adjust the nodes in the cable network; When a fault is detected in a node in the cable network, the weight coefficient is reduced.

7. The cable fault intelligent location diagnosis method based on double-ended traveling waves according to claim 6 is characterized in that: The establishment of the database includes establishing a cable network topology database according to the N node positions of the cable, and using a double-end data fault training model to train the cable network topology database. The training of the cable network topology database includes capturing the loss function in the database, and using the double-end traveling wave data features to incorporate the loss function in the database into the capture process in real time, so that the model adapts to the changes in the cable network and completes the diagnosis of intelligent positioning of cable faults.

8. A cable fault intelligent positioning and diagnosis system based on double-ended traveling waves, based on the cable fault intelligent positioning and diagnosis method based on double-ended traveling waves according to any one of claims 1 to 7, characterized in that: include, The adjustment mechanism module sets up monitoring systems at both ends of the cable line simultaneously and designs an adaptive signal adjustment mechanism; A processing module processes the double-ended data of the transmitting signal and the receiving signal based on the double-ended traveling wave, uses a convolutional neural network to extract the double-ended traveling wave data features in the processing process, and uses the double-ended traveling wave data features to construct a topological structure model of the cable network; The diagnosis module uses the topological structure model of the cable network and the double-end data fault training model to train the fault point and complete the diagnosis of the intelligent positioning of the cable fault.

9. A computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the steps of the cable fault intelligent location and diagnosis method based on double-ended traveling waves described in any one of claims 1 to 7 are implemented.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the cable fault intelligent location and diagnosis method based on double-ended traveling waves described in any one of claims 1 to 7 are implemented.

Images