Cable partial discharge positioning device based on oscillatory waves

Abstract

The invention discloses a cable partial discharge positioning device based on oscillatory waves, and the device employs a signal processing algorithm based on artificial intelligence to carry out the waveform semantic analysis of an oscillatory wave measured signal and an ideal analog oscillatory wave signal based on a twinborn feature extraction technology, so as to capture the signal waveform semantics of the two signals. And spatial feature constraint enhancement expression and feature difference calculation are performed on signal waveform semantics of the two signals, so that waveform semantic comparison analysis between the oscillation wave actual measurement signal and the ideal simulation oscillation wave signal is realized, defect positioning is performed, and positioning data of cable partial discharge are generated. Therefore, the intelligent level of the cable partial discharge positioning device can be improved, which is of great significance for preventing cable faults and guaranteeing safe and stable operation of a power system.

Description

Technical Field

[0001] The present application relates to the field of intelligent positioning, and more specifically, to a cable partial discharge positioning device based on oscillation waves. Background Art

[0002] As an indispensable part of the power system, cables play an important role in the power transmission and distribution process. However, due to long-term operation in complex environmental conditions, cables may suffer from insulation aging, moisture, mechanical damage and other problems, which may lead to partial discharge, thus affecting the safe and stable operation of the cables. Partial discharge will not only accelerate the aging of insulation materials, but may also eventually lead to cable failure, resulting in power supply interruption.

[0003] Traditional cable partial discharge detection methods mainly include pulse current method, ultrasonic method, ultra-high frequency method, etc. Although these methods can detect partial discharge phenomena in cables to a certain extent, they have limitations in locating the location of partial discharge sources, which limits their effectiveness in cable maintenance and fault prevention. Specifically, the pulse current method is a method of positioning by detecting high-frequency pulse currents caused by partial discharge. However, this method usually requires the installation of sensors at multiple measurement points and relies on precise time synchronization, which is a challenge for practical applications. In addition, the pulse current method has low sensitivity to low-level partial discharge signals and is difficult to detect early or mild partial discharge phenomena. Moreover, in a complex electromagnetic environment, the pulse current method is susceptible to interference, which affects the accuracy of the detection results.

[0004] The ultrasonic method locates by capturing the sound waves generated by partial discharge. Although this method can detect partial discharge of non-electrical nature, it has high requirements for the propagation path of the sound wave, especially when there are obstacles or the sound wave propagation medium changes, which will affect the positioning accuracy. The ultra-high frequency method uses the ultra-high frequency electromagnetic waves generated by partial discharge for detection. This method can overcome the problem of electromagnetic interference to a certain extent, but for the detection of closed cable systems, the ultra-high frequency signal decays quickly and may not provide sufficient signal strength for positioning.

[0005] Therefore, an optimized cable partial discharge positioning device is desired. Summary of the invention

[0006] In order to solve the above technical problems, the present application is proposed. The embodiment of the present application provides a cable partial discharge positioning device based on oscillation waves, which uses an artificial intelligence-based signal processing algorithm to perform waveform semantic analysis on the oscillation wave measured signal and the ideal simulated oscillation wave signal based on twin feature extraction technology to capture the signal waveform semantics of the two, and after performing spatial feature constraint enhancement expression and feature difference calculation on the signal waveform semantics of the two, the waveform semantic comparison analysis between the oscillation wave measured signal and the ideal simulated oscillation wave signal is realized, so as to locate defects and generate cable partial discharge positioning data. In this way, the intelligence level of the cable partial discharge positioning device can be improved, which is of great significance for preventing cable failures and ensuring the safe and stable operation of power systems.

[0007] According to one aspect of the present application, a cable partial discharge positioning device based on oscillation waves is provided, comprising: A cable pressure module, used to control a high voltage generating unit connected to the cable to generate voltage to the cable in a predetermined mode; An oscillation wave measured signal acquisition module, used for receiving the oscillation wave measured signal collected by a signal acquisition device connected to the cable; An ideal simulated oscillation wave signal acquisition module is used to extract an ideal simulated oscillation wave signal from a database; The cable partial discharge positioning module is used to determine the positioning data of the cable partial discharge based on the comparison analysis between the actual measured oscillation wave signal and the ideal simulated oscillation wave signal.

[0008] Compared with the prior art, the present application provides a cable partial discharge positioning device based on oscillation wave, which uses a signal processing algorithm based on artificial intelligence to perform waveform semantic analysis on the measured oscillation wave signal and the ideal simulated oscillation wave signal based on twin feature extraction technology to capture the signal waveform semantics of the two, and after performing spatial feature constraint enhancement expression and feature difference calculation on the signal waveform semantics of the two, the waveform semantic comparison analysis between the measured oscillation wave signal and the ideal simulated oscillation wave signal is realized, so as to locate defects and generate cable partial discharge positioning data. In this way, the intelligence level of the cable partial discharge positioning device can be improved, which is of great significance for preventing cable failures and ensuring the safe and stable operation of power systems. BRIEF DESCRIPTION OF THE DRAWINGS

[0009] By describing the embodiments of the present application in more detail in conjunction with the accompanying drawings, the above and other purposes, features and advantages of the present application will become more apparent. The accompanying drawings are used to provide a further understanding of the embodiments of the present application and constitute a part of the specification. Together with the embodiments of the present application, they are used to explain the present application and do not constitute a limitation of the present application. In the accompanying drawings, the same reference numerals generally represent the same components or steps.

[0010] Figure 1 is a block diagram of a cable partial discharge positioning device based on oscillation waves according to an embodiment of the present application; Figure 2 It is a data flow diagram of a cable partial discharge locating device based on oscillation waves according to an embodiment of the present application; Figure 3 It is a block diagram of a cable partial discharge locating module in a cable partial discharge locating device based on oscillation waves according to an embodiment of the present application. DETAILED DESCRIPTION

[0011] Below, the exemplary embodiments according to the present application will be described in detail with reference to the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present application, rather than all the embodiments of the present application, and it should be understood that the present application is not limited to the exemplary embodiments described here.

[0012] As shown in this application and claims, unless the context clearly indicates an exception, the words "a", "an", "an" and / or "the" do not refer to the singular and may also include the plural. Generally speaking, the terms "include" and "comprise" only indicate the inclusion of the steps and elements that have been clearly identified, and these steps and elements do not constitute an exclusive list. The method or device may also include other steps or elements.

[0013] Although the present application makes various references to certain modules in the system according to the embodiments of the present application, any number of different modules can be used and run on the user terminal and / or server. The modules are only illustrative, and different aspects of the system and method can use different modules.

[0014] Flowcharts are used in the present application to illustrate the operations performed by the system according to the embodiments of the present application. It should be understood that the preceding or following operations are not necessarily performed accurately in order. On the contrary, various steps may be processed in reverse order or simultaneously as required. Meanwhile, other operations may also be added to these processes, or a certain step or several steps of operations may be removed from these processes.

[0015] Below, the exemplary embodiments according to the present application will be described in detail with reference to the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present application, rather than all the embodiments of the present application, and it should be understood that the present application is not limited to the exemplary embodiments described here.

[0016] The ultrasonic method locates by capturing the sound waves generated by partial discharge. Although this method can detect partial discharge of non-electrical nature, it has high requirements for the propagation path of the sound wave, especially when there are obstacles or the sound wave propagation medium changes, which will affect the positioning accuracy. The ultra-high frequency method uses the ultra-high frequency electromagnetic waves generated by partial discharge for detection. This method can overcome the problem of electromagnetic interference to a certain extent, but for the detection of closed cable systems, the ultra-high frequency signal decays quickly and may not provide sufficient signal strength for positioning. Therefore, an optimized cable partial discharge positioning device is desired. In recent years, with the development of signal processing technology and artificial intelligence, the research on cable partial discharge positioning using oscillation wave technology has gradually increased. The oscillation wave method is a test method that simulates lightning impulses and system operation overvoltages. It can more effectively excite partial discharge points in cables and accurately locate the partial discharge position by analyzing the characteristics of the excited oscillation signal.

[0017] In the technical solution of the present application, a cable partial discharge positioning device based on oscillation waves is proposed. The cable is pressurized at multiple frequencies through a high-voltage generating unit, including 0 times voltage, 0.5 times voltage, 1 times voltage, 1.1 times voltage, 1.3 times voltage, 1.5 times voltage, 1.7 times voltage, 1.8 times voltage and 2.0 times voltage, and the excited oscillation wave signal is detected and collected by a signal acquisition device. Afterwards, the defect is automatically located by comparing and analyzing the measured and collected oscillation wave signal with the pre-stored ideal simulated oscillation wave signal, so as to find the specific location of the cable partial discharge, which is of great significance for ensuring the safe and stable operation of the power grid. Figure 1 It is a block diagram of a cable partial discharge locating device based on oscillation waves according to an embodiment of the present application. Figure 2 FIG. 1 is a schematic diagram of data flow of a cable partial discharge positioning device based on oscillation waves according to an embodiment of the present application. Figure 1 and Figure 2 As shown, according to the embodiment of the present application, the cable partial discharge positioning device 300 based on oscillation wave includes: a cable pressurizing module 310, which is used to control the high-voltage generating unit connected to the cable to generate voltage to the cable in a predetermined mode; an oscillation wave measured signal acquisition module 320, which is used to receive the oscillation wave measured signal collected by the signal acquisition device connected to the cable; an ideal simulated oscillation wave signal acquisition module 330, which is used to extract the ideal simulated oscillation wave signal from the database; a cable partial discharge positioning module 340, which is used to determine the positioning data of the cable partial discharge based on the comparison analysis between the oscillation wave measured signal and the ideal simulated oscillation wave signal.

[0018] Specifically, the cable pressurizing module 310 is used to control the high voltage generating unit connected to the cable to generate voltage to the cable in a predetermined mode. That is, by controlling the high voltage generating unit connected to the cable, a voltage is generated in a predetermined mode and applied to the cable to ensure that the cable works under specific conditions, such as simulating an actual working environment, performing fault detection, etc.

[0019] Specifically, the oscillation wave measured signal acquisition module 320 is used to receive the oscillation wave measured signal collected by the signal acquisition device connected to the cable. That is, the oscillation measured signal acquisition module is used to ensure that the collected signal can be accurately transmitted to the subsequent processing and analysis system for evaluating the status and performance of the cable.

[0020] Specifically, the ideal simulated oscillation wave signal acquisition module 330 is used to extract the ideal simulated oscillation wave signal from the database. That is, the ideal simulated oscillation wave signal acquisition module extracts the pre-stored ideal simulated oscillation wave signal from the database to provide a standard reference signal for comparison and analysis with the actual measurement signal to evaluate the state and performance of the cable.

[0021] Specifically, the cable partial discharge positioning module 340 is used to determine the positioning data of the cable partial discharge based on the comparison analysis between the oscillation wave measured signal and the ideal simulated oscillation wave signal. It should be understood that in the above-mentioned cable partial discharge positioning device based on oscillation waves, how to determine the positioning data of the cable partial discharge based on the comparison analysis between the oscillation wave measured signal and the ideal simulated oscillation wave signal is crucial. It should be understood that since the oscillation wave measured signal reflects the actual state of the partial discharge inside the cable, and the ideal simulated oscillation wave signal is a theoretical signal in the absence of partial discharge. The core of the comparison analysis is to identify the differences between the measured signal and the ideal simulated signal. These differences can be used to identify cable partial discharge and infer the location information of the partial discharge, because partial discharges at different positions will produce signal change patterns that are different from the ideal no partial discharge situation. In a specific example of the present application, Figure 3As shown, the cable partial discharge positioning module 340 includes: a signal waveform semantic encoding unit 341, which is used to perform oscillation waveform semantic encoding on the oscillation wave measured signal and the ideal simulated oscillation wave signal to obtain an oscillation wave measured signal semantic encoding feature map and an oscillation wave ideal simulated signal semantic encoding feature map; a signal semantic feature enhancement unit 342, which is used to perform feature enhancement processing based on spatial constraints on the oscillation wave measured signal semantic encoding feature map and the oscillation wave ideal simulated signal semantic encoding feature map to obtain oscillation wave measured signal enhanced semantic encoding features and oscillation wave ideal simulated signal enhanced semantic encoding features; a defect positioning unit 343, which is used to perform waveform semantic comparative analysis on the oscillation wave measured signal enhanced semantic encoding features and the oscillation wave ideal simulated signal enhanced semantic encoding features to obtain oscillation wave measured-simulated difference semantic encoding features, and perform defect positioning based on the oscillation wave measured-simulated difference semantic encoding features to determine the positioning data of the cable partial discharge.

[0022] Specifically, the signal waveform semantic encoding unit 341 is used to perform oscillation waveform semantic encoding on the oscillation wave measured signal and the ideal simulated oscillation wave signal to obtain the oscillation wave measured signal semantic encoding feature map and the oscillation wave ideal simulated signal semantic encoding feature map. It should be understood that in the technical solution of the present application, since the oscillation wave measured signal reflects the true state of partial discharge inside the cable, and the ideal simulated oscillation wave signal is a theoretical signal in the absence of partial discharge. By comparing these two signals, the signal characteristic changes caused by partial discharge, such as changes in phase, frequency, amplitude, etc., can be identified. These attributes are closely related to the location of cable partial discharge, which is conducive to accurately identifying and locating cable partial discharge. In addition, it is also considered that the twin detection network can detect the inconspicuous difference characteristics of the oscillation wave measured signal and the ideal simulated oscillation wave signal in the original signal domain, and express this difference characteristic in the feature domain. Based on this, in the technical solution of the present application, the measured oscillation wave signal and the ideal simulated oscillation wave signal are input into an oscillation wave twin detection network including a first waveform semantic encoder and a second waveform semantic encoder to obtain a semantic coding feature map of the measured oscillation wave signal and a semantic coding feature map of the ideal simulated oscillation wave signal.

[0023] Specifically, the signal semantic feature enhancement unit 342 is used to perform feature enhancement processing based on space constraints on the semantic coding feature map of the measured oscillation wave signal and the semantic coding feature map of the ideal simulated oscillation wave signal to obtain the enhanced semantic coding features of the measured oscillation wave signal and the enhanced semantic coding features of the ideal simulated oscillation wave signal. Since the semantic coding feature map of the measured oscillation wave signal and the semantic coding feature map of the ideal simulated oscillation wave signal respectively contain the semantic features of the measured signal waveform and the semantic features of the ideal waveform related to the oscillation wave, these waveform semantic features contain different aspects of features and waveform semantic information such as the phase, frequency, and amplitude of the oscillation wave, these feature information have a mutual correlation relationship, which plays an important role in the subsequent oscillation wave measured-simulated difference semantic feature extraction and cable partial discharge positioning tasks. Therefore, in order to further refine and enhance the effective information expression in these feature maps, thereby improving the accuracy of subsequent positioning, in the technical solution of the present application, the semantic coding feature map of the measured oscillation wave signal and the semantic coding feature map of the ideal simulated oscillation wave signal are further subjected to feature enhancement processing based on space constraints to obtain the enhanced semantic coding features of the measured oscillation wave signal and the enhanced semantic coding features of the ideal simulated oscillation wave signal. In particular, the feature enhancement processing based on spatial constraints can better capture the comprehensive features and detailed information of the measured oscillation wave signal / ideal simulation signal by combining the local features of the waveform semantics of the measured oscillation wave signal / ideal simulation signal with the global context information. This is very important for detecting the subtle differences between the measured semantics and the ideal semantics of the oscillation wave waveform and perceiving the global difference features, which is conducive to the subsequent precise positioning of the partial discharge of the cable.

[0024] Specifically, the specific process of performing spatial constraint-based feature enhancement processing on the semantic coding feature map of the oscillation wave measured signal and the semantic coding feature map of the oscillation wave ideal simulated signal includes: first, feature dispersion is performed on the semantic coding feature map of the oscillation wave measured signal and the semantic coding feature map of the oscillation wave ideal simulated signal respectively to obtain a set of semantic pixel granularity feature vectors of the oscillation wave measured signal and a set of semantic pixel granularity feature vectors of the oscillation wave ideal simulated signal, and then semantic association constraint score calculation is performed on the set of semantic pixel granularity feature vectors of the oscillation wave measured signal and the set of semantic pixel granularity feature vectors of the oscillation wave ideal simulated signal respectively to obtain a topological representation of the spatial constraint score of the semantic pixel granularity of the oscillation wave measured signal and a topological representation of the spatial constraint score of the semantic pixel granularity of the oscillation wave ideal simulated signal; that is, feature dispersion is performed on the input semantic coding feature map of the oscillation wave measured signal and the semantic coding feature map of the oscillation wave ideal simulated signal along the channel dimension to modulate the feature shapes of the semantic coding feature map of the oscillation wave measured signal and the semantic coding feature map of the oscillation wave ideal simulated signal into a feature distribution set of pixel granularity. Next, the semantic association score between any two oscillation wave measured signal semantic pixel granularity feature vectors in the set of the oscillation wave measured signal semantic pixel granularity feature vectors is calculated to obtain the oscillation wave measured signal pixel granularity semantic association score topological matrix; and the oscillation wave ideal simulation signal pixel granularity semantic association score topological matrix is ​​obtained in the same calculation method. In a specific example, this step first maps the oscillation wave measured signal semantic pixel granularity feature vector and the oscillation wave ideal simulation signal semantic pixel granularity feature vector to the Poincare space, and calculates the Poincare distance between each mapped oscillation wave measured signal semantic pixel granularity feature vector and each oscillation wave ideal simulation signal semantic pixel granularity feature vector as the semantic association score between any two semantic pixel granularity feature vectors. It should be understood that the purpose of mapping each pixel granularity feature vector from the Euclidean space to the Poincare sphere is to ensure that each oscillation wave measured signal semantic pixel granularity feature vector and each oscillation wave ideal simulation signal semantic pixel granularity feature vector can adapt to the geometric characteristics of the hyperbolic space while maintaining the original signal pixel granularity semantic information. Due to the distance characteristics of the Poincare space, even slightly different features can be mapped to relatively distant positions, which helps to improve the model's ability to distinguish the differences in the semantic features of different oscillation wave signal waveforms. Compared with the Euclidean space, the Poincare space can maintain a large difference between features at a smaller spatial cost. Then, based on the spatial distance between any two oscillation wave measured signal semantic pixel granularity feature vectors in the set of the oscillation wave measured signal semantic pixel granularity feature vectors, the oscillation wave measured signal pixel granularity semantic association score topology matrix is ​​spatially focused on attenuation modulation to obtain the oscillation wave measured signal pixel granularity semantic association space soft constraint score topology matrix.In particular, considering that the semantic features of the measured oscillation wave signals in adjacent areas in reality often have stronger correlation than those in distant areas, the spatial attention attenuation modulation is implemented on the pixel granularity semantic association score topological matrix of the measured oscillation wave signal, which can simulate this phenomenon. Such processing helps to construct a spatial soft constraint score topological matrix that is more in line with the actual situation. By introducing spatial soft constraints, the module can adjust the semantic relationship between pixels more finely, thereby improving the feature discrimination. This is crucial for distinguishing normal waveforms of measured oscillation wave signals from waveforms with abnormalities, because they may be visually very similar. In particular, through the spatial constraint mechanism, the module can emphasize the correlation between adjacent pixels, which helps to enhance the spatial coherence of the feature map. In the anomaly detection of measured oscillation wave signals and the identification of cable partial discharge, the waveform features of the abnormal area are often not isolated, but have a certain spatial connection with the waveform features of other areas. Therefore, maintaining this coherence is crucial for accurately identifying and locating cable partial discharge. Furthermore, the spatial soft constraint score topological matrix of the semantic association of the pixel granularity of the measured oscillation wave signal is subjected to dilated convolution coding to capture the semantic association topological features between the semantic pixel granularity feature vectors of each measured oscillation wave signal. Similarly, based on the spatial distance between any two oscillation wave ideal analog signal semantic pixel granularity feature vectors in the set of the oscillation wave ideal analog signal semantic pixel granularity feature vectors, the oscillation wave ideal analog signal semantic association score topology matrix is ​​subjected to spatial attention attenuation modulation to obtain the oscillation wave ideal analog signal semantic association space soft constraint score topology matrix. Finally, the set of the oscillation wave measured signal semantic feature vectors and the oscillation wave measured signal pixel granularity semantic association space soft constraint score topology matrix are input into the graph convolutional coding module to obtain the set of oscillation wave measured signal semantic context pixel granularity feature vectors. The input of the graph convolutional coding module is in the form of a graph, in which the nodes represent the oscillation wave measured signal semantic feature vectors, and the edges represent the relationship between the nodes, i.e., the pixel granularity semantic association space soft constraint score topology feature of the oscillation wave measured signal semantics. And the set of the oscillation wave ideal analog signal semantic context pixel granularity feature vectors is obtained in the same way. Here, the current node state is updated by aggregating the semantic feature information of the measured oscillation wave signal and the semantic feature information of the ideal simulated oscillation wave signal of the neighboring nodes, thereby realizing the learning of the entire graph structure. In this way, the global semantic context association feature expression between the semantic pixel granularity features of each measured oscillation wave signal and the semantic pixel granularity features of each ideal simulated oscillation wave signal is enhanced. Finally, the set of the semantic context pixel granularity feature vectors of the measured oscillation wave signal and the set of the semantic context pixel granularity feature vectors of the ideal simulated oscillation wave signal are reshaped to obtain the enhanced semantic coding feature map of the measured oscillation wave signal.

[0025] Among them, taking the semantic coding feature map of the oscillation wave measured signal as an example, after the feature of the semantic coding feature map of the oscillation wave measured signal is dispersed to obtain a set of semantic pixel granularity feature vectors of the oscillation wave measured signal, the specific process of calculating the semantic association constraint score of the set of semantic pixel granularity feature vectors of the oscillation wave measured signal includes: dispersing the feature of the semantic coding feature map of the oscillation wave measured signal along the channel dimension to obtain a set of semantic pixel granularity feature vectors of the oscillation wave measured signal; calculating the semantic association score between any two semantic pixel granularity feature vectors of the oscillation wave measured signal in the set of semantic pixel granularity feature vectors of the oscillation wave measured signal to obtain the semantic association constraint score of the oscillation wave measured signal. A signal pixel granularity semantic association score topology matrix; based on the spatial distance between any two oscillation wave measured signal semantic pixel granularity feature vectors in the set of the oscillation wave measured signal semantic pixel granularity feature vectors, the oscillation wave measured signal pixel granularity semantic association score topology matrix is ​​subjected to spatial attention attenuation modulation to obtain an oscillation wave measured signal pixel granularity semantic association space soft constraint score topology matrix; the oscillation wave measured signal pixel granularity semantic association space soft constraint score topology matrix is ​​subjected to void convolution coding to obtain an oscillation wave measured signal pixel granularity semantic association space soft constraint score topology feature matrix as the oscillation wave measured signal pixel granularity semantic association space constraint score topology representation.

[0026] More specifically, the specific process of feature dispersion of the semantic coding feature map of the oscillation wave measured signal along the channel dimension includes: performing feature reshaping processing on the semantic coding feature map of the oscillation wave measured signal along the channel dimension to obtain a set of semantic feature vectors of the oscillation wave measured signal; mapping each oscillation wave measured signal semantic feature vector in the set of semantic feature vectors of the oscillation wave measured signal to the Poincare space to obtain a set of semantic pixel granularity feature vectors of the oscillation wave measured signal.

[0027] More specifically, the specific process of calculating the semantic association score between any two semantic pixel granularity feature vectors of the oscillation wave measured signal in the set of semantic pixel granularity feature vectors of the oscillation wave measured signal includes: calculating the semantic association score between any two semantic pixel granularity feature vectors of the oscillation wave measured signal in the set of semantic pixel granularity feature vectors of the oscillation wave measured signal. The semantic pixel granularity feature vector of the measured oscillation wave signal and the The square of the position difference between the semantic pixel granularity feature vectors of the measured oscillation wave signals is used to obtain the semantic difference norm of the pixel granularity of the measured oscillation wave signals; the calculation constant 1 and the first The difference between the squares of the norms of the semantic pixel granularity feature vectors of the measured oscillation wave signals is used to obtain the The pixel granularity semantic representation of the measured signal of the oscillation wave; the calculation constant 1 and the The difference between the squares of the norms of the semantic pixel granularity feature vectors of the measured oscillation wave signals is used to obtain the The pixel granularity semantic representation of the measured signal of the oscillation wave; calculating the The pixel-granular semantic representation of the measured signal of the oscillation wave and the After multiplying the product of the pixel granularity semantic representations of the oscillation wave measured signal, the semantic difference-norm representation of the pixel granularity of the oscillation wave measured signal is divided by the value after the product to obtain the oscillation wave measured signal semantic oscillation wave measured signal pixel granularity semantic association information representation; after calculating the sum of the double of the oscillation wave measured signal semantic oscillation wave measured signal pixel granularity semantic association information representation and the constant 1, the obtained value is input into the inverse hyperbolic cosine function to obtain the oscillation wave measured signal pixel granularity semantic association score value; multiple oscillation wave measured signal pixel granularity semantic association score values ​​are arranged in a matrix form to obtain the oscillation wave measured signal pixel granularity semantic association score topological matrix.

[0028] More specifically, the specific process of performing spatial attention attenuation modulation on the oscillation wave measured signal pixel granularity semantic association score topological matrix based on the spatial distance between any two oscillation wave measured signal semantic pixel granularity feature vectors in the set of the oscillation wave measured signal semantic pixel granularity feature vectors includes: calculating the first The semantic pixel granularity feature vector of the measured oscillation wave signal and the The spatial distance between the semantic pixel granularity feature vectors of the measured oscillation wave signals is used to obtain the pixel granularity semantic spatial distance representation; the pixel granularity semantic spatial distance representation is calculated as an exponential power, and the natural constant The natural exponential function value with the base is used to obtain the pixel-granularity semantic space distance class support representation; after multiplying the pixel-granularity semantic space distance class support representation by the spatial attention attenuation modulation hyperparameter to obtain the spatial distance attention attenuation representation, the pixel-granularity semantic association score topological matrix of the measured oscillation wave signal is converted into the pixel-granularity semantic association score topological matrix. The eigenvalue of the position is divided by the spatial distance attention attenuation representation to obtain the oscillation wave measured signal pixel granularity semantic association space soft constraint score; multiple oscillation wave measured signal pixel granularity semantic association space soft constraint score are arranged in a matrix form to obtain the oscillation wave measured signal pixel granularity semantic association space soft constraint score topological matrix.

[0029] Furthermore, taking the semantic coding feature map of the oscillation wave measured signal as an example, the specific process of enhancing the semantic coding feature map of the oscillation wave measured signal based on the pixel granularity semantic association space constraint score topological representation of the oscillation wave measured signal includes: inputting the set of semantic feature vectors of the oscillation wave measured signal and the pixel granularity semantic association space soft constraint score topological matrix of the oscillation wave measured signal into a graph convolutional coding module to obtain a set of semantic context pixel granularity feature vectors of the oscillation wave measured signal; and performing feature reshaping on the set of semantic context pixel granularity feature vectors of the oscillation wave measured signal to obtain the oscillation wave measured signal semantic enhancement feature map as the enhanced semantic coding feature of the oscillation wave measured signal.

[0030] In summary, in the above embodiment, taking the oscillation wave measured signal semantic coding feature map as an example, the oscillation wave measured signal semantic coding feature map is subjected to feature enhancement processing based on spatial constraints to obtain the oscillation wave measured signal enhanced semantic coding features, including: performing feature enhancement processing based on spatial constraints on the oscillation wave measured signal semantic coding feature map using the following spatial constraint enhancement formula to obtain the oscillation wave measured signal enhanced semantic coding features; wherein the spatial constraint enhancement formula is: ; Wherein, is the semantic coding feature map of the measured oscillation wave signal, are the height, width and number of channels of the semantic coding feature map of the measured oscillation wave signal, respectively. For feature reshaping, and is the set of semantic feature vectors of the measured oscillation wave signal, The value of is the number of feature vectors in the set of semantic feature vectors of the oscillation wave measured signal, and is the feature transformation weight matrix, and are the first and The semantic pixel granularity feature vector of the measured oscillation wave signal, is the one-norm of the vector, is the inverse hyperbolic cosine function, is the semantic association score calculation operation, is the pixel-level semantic association score topological matrix of the measured oscillation wave signal. The eigenvalues ​​of the positions, It is the spatial distance calculation operation between vectors. is the spatial attention decay modulation hyperparameter, is the topological matrix of the soft constraint score in the pixel-granular semantic association space of the measured oscillation wave signal. The eigenvalues ​​of the positions, is the soft constraint score topological matrix of the pixel granularity semantic association space of the oscillation wave measured signal, It is the hole convolution coding process. is the topological feature matrix of the soft constraint score of the pixel-granular semantic association space of the measured oscillation wave signal, is the graph convolutional encoding operation, is the set of pixel-granularity feature vectors of semantic context of the measured oscillation wave signal, Enhance the semantic coding feature map for the oscillation wave measured signal.

[0031] Specifically, the defect location unit 343 is used to perform waveform semantic comparison analysis on the enhanced semantic coding features of the oscillation wave measured signal and the enhanced semantic coding features of the ideal simulated signal of the oscillation wave to obtain the semantic coding features of the measured-simulated difference of the oscillation wave, and perform defect location based on the semantic coding features of the measured-simulated difference of the oscillation wave to determine the location data of the partial discharge of the cable. In a specific example of the present application, first, the enhanced semantic coding feature map of the measured signal of the oscillation wave and the enhanced semantic coding feature map of the ideal simulated signal of the oscillation wave are input into a waveform semantic comparison analysis network to obtain the semantic coding feature map of the measured-simulated difference of the oscillation wave as the semantic coding feature of the measured-simulated difference of the oscillation wave; that is, the enhanced semantics of the measured signal of the oscillation wave and the enhanced semantics of the ideal simulated signal are analyzed for differences through the waveform semantic comparison analysis network, so as to obtain the semantic coding feature map of the measured-simulated difference of the oscillation wave. In particular, in a specific example of the present application, waveform semantic comparison analysis can be achieved by positionally differentiating feature graphs, so that the more essential and subtle differences between the measured signal of the oscillation wave and the ideal simulated signal of the oscillation wave can be revealed, thereby helping to more accurately identify which features are caused by partial discharge in the cable and which features are normal signal features. This waveform semantic comparison analysis method helps to eliminate other interference factors and improve the accuracy of positioning. Furthermore, the oscillation wave measured-simulated difference semantic encoding feature graph is input into a decoder-based defect location module to obtain the location data of the cable partial discharge. That is, the difference characteristics between the measured waveform semantics of the oscillation wave and the rational simulated waveform semantics are used to locate defects and generate the location data of the cable partial discharge. In this way, the intelligence level of the cable partial discharge location device can be improved, which is of great significance for preventing cable failures and ensuring the safe and stable operation of power systems.

[0032] Preferably, when the oscillation wave measured signal enhanced semantic coding feature map and the oscillation wave ideal simulated signal enhanced semantic coding feature map respectively represent the spatial distribution soft constraint enhanced image semantic features of the oscillation wave measured signal and the ideal simulated oscillation wave signal, when performing waveform semantic comparative analysis on them, the imbalance of local soft constraint enhanced spatial distribution differences under different image semantics will also make the spatial composite semantic representation of the oscillation wave measured-simulated difference semantic coding feature map have a complex spatial structure based on different local spatial distribution structures, thereby expecting to improve its decoding regression convergence and generalization effects under complex spatial structures.

[0033] Therefore, in a preferred example of the present application, after inputting the oscillation wave measured-simulated difference semantic coding feature map into a decoder-based defect location module to obtain the location data of the cable partial discharge, the oscillation wave measured-simulated difference semantic coding feature map is optimized, specifically including: The absolute value sum of each eigenvalue of the oscillation wave measured-simulated difference semantic coding feature map is calculated to obtain the first oscillation wave measured-simulated difference semantic coding space structure value, and the square root of the sum of the squares of each eigenvalue of the oscillation wave measured-simulated difference semantic coding feature map is calculated to obtain the second oscillation wave measured-simulated difference semantic coding space structure value, that is: ;in, , are the eigenvalues ​​of the oscillatory wave measured-simulated difference semantic encoding feature map, is the spatial structure value of the measured-simulated difference semantic encoding of the first oscillation wave, is the spatial structure value of the semantic encoding of the measured-simulated difference of the second oscillation wave; Multiply each eigenvalue of the oscillation wave measured-simulated difference semantic coding feature map by the first oscillation wave measured-simulated difference semantic coding space structure value and the second oscillation wave measured-simulated difference semantic coding space structure value respectively to obtain a first oscillation wave measured-simulated difference semantic coding structure reference value and a second oscillation wave measured-simulated difference semantic coding structure reference value corresponding to each eigenvalue; Multiplying each eigenvalue of the oscillation wave measured-simulated difference semantic coding feature map by the scale of the oscillation wave measured-simulated difference semantic coding feature map and the square root of the scale to obtain a first oscillation wave measured-simulated difference semantic coding scale transformation value and a second oscillation wave measured-simulated difference semantic coding scale transformation value corresponding to each eigenvalue; Dividing the first oscillation wave measured-simulated difference semantic coding structure reference value by the difference between the first oscillation wave measured-simulated difference semantic coding space structure value and the first oscillation wave measured-simulated difference semantic coding scale transformation value to obtain the first oscillation wave measured-simulated difference semantic coding transformation adjustment value; Dividing the second oscillation wave measured-simulated difference semantic coding structure reference value by the difference between the second oscillation wave measured-simulated difference semantic coding space structure value and the second oscillation wave measured-simulated difference semantic coding scale transformation value to obtain the second oscillation wave measured-simulated difference semantic coding transformation adjustment value; and Calculate the weighted sum of the first oscillation wave measured-simulated difference semantic coding transformation adjustment value and the second oscillation wave measured-simulated difference semantic coding transformation adjustment value to obtain each feature value of the optimized oscillation wave measured-simulated difference semantic coding feature map.

[0034] It is expressed as: ;in, , ,and , , and are the feature matrix width, feature matrix height and number of channels of the oscillatory wave measured-simulated difference semantic coding feature map, respectively. is the scale of the oscillatory wave measured-simulated difference semantic encoding feature map, is the first oscillation wave measured-simulated difference semantic coding transformation adjustment value, is the second oscillation wave measured-simulated difference semantic coding transformation adjustment value, is a first oscillation wave measured-simulated difference semantic coding transformation feature adjustment map composed of the first oscillation wave measured-simulated difference semantic coding transformation adjustment values, is the second oscillation wave measured-simulated difference semantic coding transformation feature adjustment map composed of the second oscillation wave measured-simulated difference semantic coding transformation adjustment values, is added by position, It is the point multiplication by position. is a weighted hyperparameter, It is the optimized oscillation wave measured-simulated difference semantic encoding feature map.

[0035] That is, in this preferred example, for the spatial structure information of the feature set of the oscillation wave measured-simulated difference semantic coding feature map in the high-dimensional space, the scale-based frame transformation of each feature value of the oscillation wave measured-simulated difference semantic coding feature map is performed by taking the class norm space structured representation of the oscillation wave measured-simulated difference semantic coding feature map as the reference window, and the spatial structure-based frame attention weight adjustment of each feature value of the oscillation wave measured-simulated difference semantic coding feature map is realized to ensure the spatial transformation invariance of the oscillation wave measured-simulated difference semantic coding feature map under the interaction of feature space, thereby improving the convergence and generalization effect of the decoding regression of the feature set of the oscillation wave measured-simulated difference semantic coding feature map under the complex spatial structure representation, and improving the accuracy of the cable partial discharge positioning data obtained by inputting it into the defect positioning module based on the decoder. In this way, the intelligence level of the cable partial discharge positioning device can be improved, which is of great significance for preventing cable failures and ensuring the safe and stable operation of the power system.

[0036] As described above, the cable partial discharge positioning device 300 based on oscillation waves according to the embodiment of the present application can be implemented in various wireless terminals, such as a server with a cable partial discharge positioning algorithm based on oscillation waves. In a possible implementation, the cable partial discharge positioning device 300 based on oscillation waves according to the embodiment of the present application can be integrated into the wireless terminal as a software module and / or a hardware module. For example, the cable partial discharge positioning device 300 based on oscillation waves can be a software module in the operating system of the wireless terminal, or can be an application developed for the wireless terminal; of course, the cable partial discharge positioning device 300 based on oscillation waves can also be one of the many hardware modules of the wireless terminal.

[0037] Alternatively, in another example, the oscillation wave-based cable partial discharge locating device 300 and the wireless terminal may also be separate devices, and the oscillation wave-based cable partial discharge locating device 300 may be connected to the wireless terminal via a wired and / or wireless network, and transmit interactive information in accordance with an agreed data format.

[0038] The embodiments of the present disclosure have been described above, and the above description is exemplary, not exhaustive, and is not limited to the disclosed embodiments. Many modifications and changes will be apparent to those of ordinary skill in the art without departing from the scope and spirit of the described embodiments. The selection of terms used herein is intended to best explain the principles of the embodiments, practical applications, or improvements to the technology in the market, or to enable other persons of ordinary skill in the art to understand the embodiments disclosed herein.

Claims

1. A cable partial discharge positioning device based on oscillation waves, characterized in that: include: A cable pressure module, used to control a high voltage generating unit connected to the cable to generate voltage to the cable in a predetermined mode; An oscillation wave measured signal acquisition module, used for receiving the oscillation wave measured signal collected by a signal acquisition device connected to the cable; An ideal simulated oscillation wave signal acquisition module is used to extract an ideal simulated oscillation wave signal from a database; A cable partial discharge positioning module, used to determine the positioning data of the cable partial discharge based on the comparison and analysis between the measured oscillation wave signal and the ideal simulated oscillation wave signal; Among them, the cable partial discharge positioning module includes: a signal waveform semantic encoding unit, which is used to perform oscillation waveform semantic encoding on the oscillation wave measured signal and the ideal simulated oscillation wave signal to obtain an oscillation wave measured signal semantic encoding feature map and an oscillation wave ideal simulated signal semantic encoding feature map; a signal semantic feature enhancement unit, which is used to perform feature enhancement processing based on spatial constraints on the oscillation wave measured signal semantic encoding feature map and the oscillation wave ideal simulated signal semantic encoding feature map to obtain oscillation wave measured signal enhanced semantic coding features and oscillation wave ideal simulated signal enhanced semantic coding features; a defect positioning unit, which is used to perform waveform semantic comparative analysis on the oscillation wave measured signal enhanced semantic coding features and the oscillation wave ideal simulated signal enhanced semantic coding features to obtain oscillation wave measured-simulated difference semantic coding features, and perform defect positioning based on the oscillation wave measured-simulated difference semantic coding features to determine the positioning data of the cable partial discharge.

2. The cable partial discharge positioning device based on oscillation waves according to claim 1, characterized in that: The signal waveform semantic encoding unit is used to: input the measured oscillation wave signal and the ideal simulated oscillation wave signal into an oscillation wave twin detection network including a first waveform semantic encoder and a second waveform semantic encoder to obtain a semantic encoding feature map of the measured oscillation wave signal and a semantic encoding feature map of the ideal simulated oscillation wave signal.

3. The cable partial discharge locating device based on oscillation wave according to claim 2, characterized in that: The signal semantic feature enhancement unit comprises: A semantic association constraint score calculation subunit is used to perform feature dispersion on the semantic coding feature map of the oscillation wave measured signal to obtain a set of semantic pixel granularity feature vectors of the oscillation wave measured signal, and then perform semantic association constraint score calculation on the set of semantic pixel granularity feature vectors of the oscillation wave measured signal to obtain a topological representation of the semantic association space constraint score of the pixel granularity of the oscillation wave measured signal; The oscillation wave measured signal semantic enhancement subunit is used to enhance the semantic coding feature map of the oscillation wave measured signal based on the pixel granularity semantic association space constraint score topological representation of the oscillation wave measured signal to obtain the enhanced semantic coding feature of the oscillation wave measured signal.

4. The cable partial discharge locating device based on oscillation waves according to claim 3 is characterized in that: The semantic association constraint score calculation subunit includes: A feature dispersion secondary subunit is used to perform feature dispersion on the semantic coding feature map of the oscillation wave measured signal along the channel dimension to obtain a set of semantic pixel granularity feature vectors of the oscillation wave measured signal; The oscillation wave measured signal pixel granularity semantic association score calculation secondary subunit is used to calculate the semantic association score between any two oscillation wave measured signal semantic pixel granularity feature vectors in the set of the oscillation wave measured signal semantic pixel granularity feature vectors to obtain the oscillation wave measured signal pixel granularity semantic association score topological matrix; A spatial attention attenuation modulation secondary subunit is used to perform spatial attention attenuation modulation on the oscillation wave measured signal pixel granularity semantic association score topology matrix based on the spatial distance between any two oscillation wave measured signal semantic pixel granularity feature vectors in the set of the oscillation wave measured signal semantic pixel granularity feature vectors to obtain the oscillation wave measured signal pixel granularity semantic association spatial soft constraint score topology matrix; The dilated convolution secondary subunit is used to perform dilated convolution encoding on the oscillation wave measured signal pixel granularity semantic association space soft constraint score topology matrix to obtain the oscillation wave measured signal pixel granularity semantic association space soft constraint score topology feature matrix as the oscillation wave measured signal pixel granularity semantic association space constraint score topology representation.

5. The cable partial discharge locating device based on oscillation waves according to claim 4, characterized in that: The characteristic dispersion secondary subunit is used for: Performing feature reshaping processing on the semantic encoding feature map of the oscillation wave measured signal along the channel dimension to obtain a set of semantic feature vectors of the oscillation wave measured signal; Each oscillation wave measured signal semantic feature vector in the set of oscillation wave measured signal semantic feature vectors is mapped to the Poincare space to obtain the set of oscillation wave measured signal semantic pixel granularity feature vectors.

6. The cable partial discharge locating device based on oscillation waves according to claim 5, characterized in that: The oscillation wave measured signal pixel granularity semantic association score calculation secondary subunit is used to: Calculate the first pixel in the set of semantic pixel granularity feature vectors of the measured oscillation wave signal The semantic pixel granularity feature vector of the measured oscillation wave signal and the The square of the position difference between the semantic pixel granularity feature vectors of the oscillation wave measured signal is used to obtain the semantic difference norm of the pixel granularity of the oscillation wave measured signal; Calculate the constant 1 and the The difference between the squares of the norms of the semantic pixel granularity feature vectors of the measured oscillation wave signals is used to obtain the Pixel-granular semantic representation of the measured signal of an oscillating wave; Calculate the constant 1 and the The difference between the squares of the l-norm of the semantic pixel granularity feature vectors of the measured oscillation wave signals is used to obtain the Pixel-granular semantic representation of the measured signal of an oscillating wave; Calculate the The pixel-granular semantic representation of the measured signal of the oscillation wave and the After multiplying the product of the pixel granularity semantic representations of the oscillation wave measured signal, the pixel granularity semantic difference-norm representation of the oscillation wave measured signal is divided by the value after the product to obtain the oscillation wave measured signal semantic pixel granularity semantic association information representation; After calculating the sum of the double of the semantic association information of the oscillation wave measured signal pixel granularity and the constant 1, the obtained value is input into the inverse hyperbolic cosine function to obtain the semantic association score value of the oscillation wave measured signal pixel granularity; Arrange a plurality of the oscillation wave measured signal pixel granularity semantic association score values ​​into a matrix form to obtain the oscillation wave measured signal pixel granularity semantic association score topological matrix.

7. The cable partial discharge locating device based on oscillation waves according to claim 6, characterized in that: The spatial attention attenuation modulation secondary subunit is used for: Calculate the The semantic pixel granularity feature vector of the measured oscillation wave signal and the The spatial distance between the semantic pixel granularity feature vectors of the measured signals of the oscillation waves is used to obtain the pixel granularity semantic spatial distance representation; Calculating a natural exponential function value with the pixel granularity semantic space distance represented as an exponential power and the natural constant e as the base to obtain a pixel granularity semantic space distance class support representation; After multiplying the pixel-granular semantic space distance class support representation by the spatial attention attenuation modulation hyperparameter to obtain the spatial distance attention attenuation representation, the pixel-granular semantic association score topology matrix of the oscillation wave measured signal is converted into the first The characteristic value of the position is divided by the spatial distance attention attenuation representation to obtain the pixel granularity semantic association space soft constraint score of the oscillation wave measured signal; Arrange the plurality of the oscillation wave measured signal pixel granularity semantic association space soft constraint scores into a matrix form to obtain the oscillation wave measured signal pixel granularity semantic association space soft constraint score topology matrix.

8. The cable partial discharge locating device based on oscillation waves according to claim 7, characterized in that: The oscillation wave measured signal semantic enhancement subunit is used to: Inputting the set of semantic feature vectors of the oscillation wave measured signal and the soft constraint score topology matrix of the pixel granularity semantic association space of the oscillation wave measured signal into a graph convolutional coding module to obtain a set of semantic context pixel granularity feature vectors of the oscillation wave measured signal; The set of pixel granularity feature vectors of the semantic context of the oscillation wave measured signal is reshaped to obtain a semantic enhancement feature map of the oscillation wave measured signal as the enhanced semantic coding feature of the oscillation wave measured signal.

9. The cable partial discharge locating device based on oscillation waves according to claim 8, characterized in that: The defect locating unit comprises: A waveform semantic contrast analysis subunit is used to input the oscillation wave measured signal enhanced semantic coding feature map and the oscillation wave ideal simulated signal enhanced semantic coding feature map into a waveform semantic contrast analysis network to obtain an oscillation wave measured-simulated difference semantic coding feature map as the oscillation wave measured-simulated difference semantic coding feature; The decoding subunit is used to input the oscillation wave measured-simulated difference semantic coding feature map into a decoder-based defect location module to obtain the location data of the cable partial discharge.

10. The cable partial discharge locating device based on oscillation waves according to claim 9, characterized in that: The waveform semantic comparison and analysis subunit is used to calculate the positional difference between the oscillation wave measured signal enhanced semantic coding feature map and the oscillation wave ideal simulated signal enhanced semantic coding feature map to obtain the oscillation wave measured-simulated difference semantic coding feature map.

Images