Method and device for determining partial discharge position of switch cabinet, and electronic equipment

Abstract

The invention discloses a partial discharge position determination method and device of a switch cabinet and electronic equipment, and relates to the technical field of power system monitoring and fault diagnosis, and the method comprises the steps: collecting a partial discharge signal set of the switch cabinet; converting the partial discharge signal into a frequency domain signal to obtain a frequency domain signal set; performing feature extraction on the partial discharge signal set and the frequency domain signal set to obtain feature vectors; calculating a similarity value between the feature vector and a historical sample feature vector, and calculating a first position coordinate of the partial discharge signal source; calculating a second position coordinate of the partial discharge signal source based on a time difference positioning algorithm; and calculating the position coordinate of the partial discharge signal source based on the first position coordinate, the second position coordinate and the position weight value, and determining the partial discharge position of the switch cabinet. According to the invention, the technical problem of low accuracy of the positioning result in the mode of positioning the partial discharge position of the switch cabinet through a single positioning method in the prior art is solved.

Description

Technical Field

[0001] The present invention relates to the technical field of power system monitoring and fault diagnosis, and in particular to a method for determining a partial discharge position of a switch cabinet, a device thereof, and electronic equipment. Background Art

[0002] In the power system, switchgear is one of the key electrical equipment, and its operating status is directly related to the safety and stability of the entire power grid. Partial discharge is an important precursor to the deterioration and aging of switchgear insulation, and can reflect potential faults inside the equipment. In the power system, there are many locations where partial discharge occurs in power equipment. In recent years, online monitoring technology for partial discharge has been widely used. Sensors installed in the switchgear collect partial discharge signals in real time. However, the current online monitoring system still faces great challenges in fault location, especially in the complex internal environment of the switchgear. How to accurately locate the source of partial discharge signals has become a major problem.

[0003] In the related technologies, commonly used PD signal positioning methods mainly include sensor-based time difference positioning (TDOA) and arrival time method (TOA), etc. These methods can provide the location information of PD signal sources to a certain extent, but due to the complex internal structure of the switch cabinet and the changeable signal propagation path, a single positioning method is often difficult to guarantee the positioning accuracy, resulting in low accuracy of the positioning results, and it is difficult to deal with the PD phenomenon of the switch cabinet in a timely manner.

[0004] To address the above-mentioned problems, no effective solution has been proposed yet. Summary of the invention

[0005] The embodiments of the present invention provide a method and device for determining the partial discharge position of a switch cabinet, and an electronic device thereof, so as to at least solve the technical problem in the related art that the partial discharge position of the switch cabinet is located by a single positioning method, resulting in low positioning result accuracy.

[0006] According to one aspect of an embodiment of the present invention, a method for determining a partial discharge position of a switch cabinet is provided, comprising: collecting a partial discharge signal set of the switch cabinet, wherein the partial discharge signal set includes N partial discharge signals; converting the partial discharge signals in the partial discharge signal set into frequency domain signals to obtain a frequency domain signal set; performing feature extraction on the partial discharge signal set and the frequency domain signal set to obtain a feature vector; calculating a similarity value between the feature vector and a feature vector of a historical sample, and calculating a first position coordinate of a partial discharge signal source of the switch cabinet based on the similarity value; calculating a second position coordinate of the partial discharge signal source of the switch cabinet based on a time difference positioning algorithm; configuring a position weight value for the first position coordinate, calculating the position coordinate of the partial discharge signal source of the switch cabinet based on the first position coordinate, the second position coordinate and the position weight value, and determining the partial discharge position of the switch cabinet based on the position coordinate.

[0007] Optionally, the step of calculating the similarity value between the feature vector and the historical sample feature vector includes: calling the historical sample library, calculating the Euclidean distance between the feature vector and each of the historical sample feature vectors in the historical sample library; and obtaining the similarity value between the feature vector and the historical sample feature vector based on the inverse of the Euclidean distance.

[0008] Optionally, the step of calculating the first position coordinates of the local discharge signal source of the switch cabinet based on the similarity value includes: selecting the historical sample feature vector whose similarity value is greater than or equal to a preset similarity threshold, and obtaining the historical local discharge position corresponding to the historical sample feature vector, and using the historical local discharge position as a similar historical local discharge position of the local discharge position of the switch cabinet, and obtaining the position coordinates of the similar historical local discharge position; using the similarity value between the feature vector and the historical sample feature vector as a similarity weight value of the similar historical local discharge position, and calculating the first position coordinates of the switch cabinet based on the similarity weight value of the similar historical local discharge position and the position coordinates.

[0009] Optionally, the step of calculating the second position coordinates of the local discharge signal source of the switch cabinet based on the time difference positioning algorithm includes: obtaining the time point when each high-frequency current sensor receives the local discharge signal and the sensor position coordinates of each high-frequency current sensor; constructing a linear equation based on the position parameters of the local discharge position and the time difference between each two high-frequency current sensors and the sensor position coordinates of the two high-frequency current sensors; solving the linear equation to obtain the second position coordinates of the local discharge signal source.

[0010] Optionally, the step of performing feature extraction on the local discharge signal set and the frequency domain signal set to obtain a feature vector includes: performing amplitude feature extraction on the local discharge signal to obtain the amplitude feature of the switch cabinet; performing frequency feature extraction on the frequency domain signal of the local discharge signal to obtain the frequency feature of the switch cabinet; constructing an amplitude feature vector based on the amplitude feature, and constructing a frequency feature vector based on the frequency feature; and splicing the amplitude feature vector and the frequency feature vector to obtain the feature vector.

[0011] Optionally, the amplitude feature includes: at least one of the following: a signal peak value and a signal mean value, wherein the signal peak value represents the maximum value of the amplitude of the local discharge signal, and the signal mean value represents the average value of the amplitude of the local discharge signal.

[0012] Optionally, the frequency characteristics include at least one of the following: a signal main frequency, a signal harmonic frequency, and a signal bandwidth, wherein the signal main frequency represents the maximum value of the power spectral density of the frequency domain signal, the signal harmonic frequency is an integer multiple of the signal main frequency, and the signal bandwidth represents the frequency range containing the target energy in the frequency domain signal.

[0013] Optionally, the step of collecting a set of local discharge signals of a switch cabinet includes: deploying high-frequency current sensors at K preset positions of the switch cabinet, where K is a positive integer and K is less than or equal to N; collecting the local discharge signals of the switch cabinet through the high-frequency current sensors to obtain the set of local discharge signals.

[0014] According to another aspect of an embodiment of the present invention, a device for determining a partial discharge position of a switch cabinet is provided, comprising: an acquisition unit, configured to acquire a partial discharge signal set of the switch cabinet, wherein the partial discharge signal set includes N partial discharge signals; a conversion unit, configured to convert the partial discharge signals in the partial discharge signal set into frequency domain signals to obtain a frequency domain signal set; an extraction unit, configured to perform feature extraction on the partial discharge signal set and the frequency domain signal set to obtain a feature vector; a first calculation unit, configured to calculate a similarity value between the feature vector and a feature vector of a historical sample, and calculate a first position coordinate of a partial discharge signal source of the switch cabinet based on the similarity value; a second calculation unit, configured to calculate a second position coordinate of the partial discharge signal source of the switch cabinet based on a time difference positioning algorithm; and a determination unit, configured to configure a position weight value for the first position coordinate, calculate the position coordinate of the partial discharge signal source of the switch cabinet based on the first position coordinate, the second position coordinate and the position weight value, and determine the partial discharge position of the switch cabinet based on the position coordinate.

[0015] Optionally, the first calculation unit includes: a first calculation module, used to call the historical sample library to calculate the Euclidean distance between the feature vector and each of the historical sample feature vectors in the historical sample library; and a first acquisition module, used to obtain the similarity value between the feature vector and the historical sample feature vector based on the inverse of the Euclidean distance.

[0016] Optionally, the first calculation unit also includes: a first selection module, used to select the historical sample feature vector whose similarity value is greater than or equal to a preset similarity threshold, and obtain the historical local discharge position corresponding to the historical sample feature vector, and use the historical local discharge position as a similar historical local discharge position of the local discharge position of the switch cabinet, and obtain the position coordinates of the similar historical local discharge position; a second calculation module, used to use the similarity value between the feature vector and the historical sample feature vector as a similarity weight value of the similar historical local discharge position, and calculate the first position coordinates of the switch cabinet based on the similarity weight value of the similar historical local discharge position and the position coordinates.

[0017] Optionally, the second calculation unit includes: a second acquisition module, used to obtain the time point when each high-frequency current sensor receives the local discharge signal and the sensor position coordinates of each high-frequency current sensor; a first construction module, used to construct a linear equation based on the position parameters of the local discharge position and the time difference between every two high-frequency current sensors and the sensor position coordinates of the two high-frequency current sensors; a first solution module, used to solve the linear equation to obtain the second position coordinates of the local discharge signal source.

[0018] Optionally, the extraction unit includes: a first extraction module, used to extract amplitude features of the local discharge signal to obtain the amplitude features of the switch cabinet; a second extraction module, used to extract frequency features of the frequency domain signal of the local discharge signal to obtain the frequency features of the switch cabinet; a second construction module, used to construct an amplitude feature vector based on the amplitude features, and to construct a frequency feature vector based on the frequency features; a first splicing module, used to splice the amplitude feature vector and the frequency feature vector to obtain the feature vector.

[0019] Optionally, the amplitude feature includes: at least one of the following: a signal peak value and a signal mean value, wherein the signal peak value represents the maximum value of the amplitude of the local discharge signal, and the signal mean value represents the average value of the amplitude of the local discharge signal.

[0020] Optionally, the frequency characteristics include at least one of the following: a signal main frequency, a signal harmonic frequency, and a signal bandwidth, wherein the signal main frequency represents the maximum value of the power spectral density of the frequency domain signal, the signal harmonic frequency is an integer multiple of the signal main frequency, and the signal bandwidth represents the frequency range containing the target energy in the frequency domain signal.

[0021] Optionally, the acquisition unit includes: a first deployment module, used to deploy high-frequency current sensors at K preset positions of the switch cabinet, where K is a positive integer and K is less than or equal to N; a first acquisition module, used to collect local discharge signals of the switch cabinet through the high-frequency current sensor to obtain the local discharge signal set.

[0022] According to another aspect of an embodiment of the present invention, there is also provided an electronic device, comprising one or more processors and a memory, wherein the memory is used to store one or more programs, wherein when the one or more programs are executed by the one or more processors, the one or more processors implement any one of the above-mentioned methods for determining the partial discharge position of a switch cabinet.

[0023] In the present application, the following steps are taken: first, a local discharge signal set of a switch cabinet is collected, wherein the local discharge signal set includes N local discharge signals, and the local discharge signals in the local discharge signal set are converted into frequency domain signals to obtain a frequency domain signal set, and then feature extraction is performed on the local discharge signal set and the frequency domain signal set to obtain a feature vector, and then the similarity value between the feature vector and the feature vector of the historical sample is calculated, and the first position coordinates of the local discharge signal source of the switch cabinet are calculated based on the similarity value, and the second position coordinates of the local discharge signal source of the switch cabinet are calculated based on the time difference positioning algorithm, and finally a position weight value is configured for the first position coordinate, and the position coordinates of the local discharge signal source of the switch cabinet are calculated based on the first position coordinate, the second position coordinate and the position weight value, and the local discharge position of the switch cabinet is determined based on the position coordinates.

[0024] In the present application, frequency domain features and amplitude features are extracted based on the local discharge signal of the switch cabinet, the information in the frequency and amplitude feature vectors is comprehensively utilized, and the similarity value is calculated in combination with the historical sample feature vector. The local discharge position is preliminarily estimated based on the similarity value, and then the local discharge position is estimated and calculated again in combination with the time difference positioning algorithm. The final local discharge position is calculated based on the position data calculated multiple times and the pre-configured weight vector. By performing comprehensive calculations on multi-dimensional information and determining the specific location of the local discharge, the local discharge signal source can be accurately located, and the accuracy of the local discharge positioning results can be improved, thereby solving the technical problem of low accuracy of the positioning result in the related art of locating the local discharge position of the switch cabinet by a single positioning method. BRIEF DESCRIPTION OF THE DRAWINGS

[0025] The drawings described herein are used to provide a further understanding of the present invention and constitute a part of this application. The exemplary embodiments of the present invention and their descriptions are used to explain the present invention and do not constitute an improper limitation of the present invention. In the drawings:

[0026] Figure 1 is a flow chart of an optional method for determining a partial discharge position of a switch cabinet according to an embodiment of the present invention;

[0027] Figure 2 is a schematic diagram of an optional partial discharge position determination process of a switch cabinet according to an embodiment of the present invention;

[0028] Figure 3 is a schematic diagram of an optional device for determining a partial discharge position of a switch cabinet according to an embodiment of the present invention;

[0029] Figure 4 The present invention is a hardware structure block diagram of an electronic device (or mobile device) for determining a partial discharge position of a switch cabinet according to an embodiment of the present invention. DETAILED DESCRIPTION

[0030] In order to enable those skilled in the art to better understand the scheme of the present invention, the technical scheme in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work should fall within the scope of protection of the present invention.

[0031] It should be noted that the terms "first", "second", etc. in the specification and claims of the present invention and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchanged where appropriate, so that the embodiments of the present invention described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device that includes a series of steps or units is not necessarily limited to those steps or units that are clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0032] It should be noted that the method and device for determining the partial discharge position of the switch cabinet in the present application can be used in the technical field of power system monitoring and fault diagnosis when the partial discharge position is comprehensively calculated based on frequency and amplitude characteristics and the time difference positioning method. It can also be used in any field other than the technical field of power system monitoring and fault diagnosis when the partial discharge position is comprehensively calculated based on frequency and amplitude characteristics and the time difference positioning method. The application does not limit the application field of the method and device for determining the partial discharge position of the switch cabinet in the present application.

[0033] The following embodiments of the present invention can be applied to various partial discharge position determination systems / applications / equipment of switch cabinets. The present invention proposes an automatic positioning method in partial discharge monitoring of switch cabinets, which realizes the precise positioning of partial discharge signal sources by comprehensively utilizing frequency and amplitude characteristics and combining the time difference positioning method, thereby improving the positioning accuracy and reliability of partial discharge monitoring, and is suitable for online partial discharge monitoring and fault diagnosis of switch cabinets and other equipment in power systems.

[0034] The present invention is described in detail below in conjunction with various embodiments.

[0035] Embodiment 1

[0036] According to an embodiment of the present invention, an embodiment of a method for determining a partial discharge position of a switch cabinet is provided. It should be noted that the steps shown in the flowchart of the accompanying drawings can be executed in a computer system such as a set of computer executable instructions, and although a logical order is shown in the flowchart, in some cases, the steps shown or described can be executed in an order different from that shown here.

[0037] Figure 1 is a flow chart of an optional method for determining a partial discharge position of a switch cabinet according to an embodiment of the present invention, such as Figure 1 As shown, the method comprises the following steps:

[0038] Step S101, collecting a partial discharge signal set of a switch cabinet, wherein the partial discharge signal set includes N partial discharge signals;

[0039] Step S102, converting the local discharges in the local discharge signal set into frequency domain signals to obtain a frequency domain signal set;

[0040] Step S103, extracting features from the local discharge signal set and the frequency domain signal set to obtain a feature vector;

[0041] Step S104, calculating a similarity value between the feature vector and the feature vector of the historical sample, and calculating a first position coordinate of a partial discharge signal source of the switch cabinet based on the similarity value;

[0042] Step S105, calculating the second position coordinates of the partial discharge signal source of the switch cabinet based on the time difference positioning algorithm;

[0043] Step S106, configuring a position weight value for the first position coordinate, calculating the position coordinate of the partial discharge signal source of the switch cabinet based on the first position coordinate, the second position coordinate and the position weight value, and determining the partial discharge position of the switch cabinet based on the position coordinate.

[0044] Through the above steps, firstly, a local discharge signal set of the switch cabinet is collected, wherein the local discharge signal set includes N local discharge signals, and the local discharge signals in the local discharge signal set are converted into frequency domain signals to obtain a frequency domain signal set, and then feature extraction is performed on the local discharge signal set and the frequency domain signal set to obtain a feature vector, and then a similarity value between the feature vector and the feature vector of the historical sample is calculated, and based on the similarity value, a first position coordinate of the local discharge signal source of the switch cabinet is calculated, and based on the time difference positioning algorithm, a second position coordinate of the local discharge signal source of the switch cabinet is calculated, and finally a position weight value is configured for the first position coordinate, and the position coordinate of the local discharge signal source of the switch cabinet is calculated based on the first position coordinate, the second position coordinate and the position weight value, and the local discharge position of the switch cabinet is determined based on the position coordinate.

[0045] In this embodiment, frequency domain features and amplitude features are extracted based on the local discharge signal of the switch cabinet, and the information in the frequency and amplitude feature vectors is comprehensively utilized. The similarity value is calculated in combination with the historical sample feature vector, and the local discharge position is preliminarily estimated based on the similarity value. Then, the local discharge position is estimated and calculated again in combination with the time difference positioning algorithm. The final local discharge position is calculated based on the position data calculated multiple times and the pre-configured weight vector. By performing comprehensive calculations on multi-dimensional information and determining the specific position of the local discharge, the local discharge signal source can be accurately located, and the accuracy of the local discharge positioning results can be improved, thereby solving the technical problem of low accuracy of the positioning result in the related art of locating the local discharge position of the switch cabinet by a single positioning method.

[0046] The embodiment of the present invention is described in detail below in combination with the above steps.

[0047] With the rapid development of the electric power industry, the operational reliability and safety requirements of power equipment are becoming increasingly higher. Partial discharge, as a common fault in the power system, is an important precursor to insulation degradation and aging of power equipment, and can reflect potential faults inside the equipment. Therefore, monitoring and precise positioning of partial discharge phenomena in power equipment are of great significance to the stable operation of the power system.

[0048] In the power system, the internal structure of the switch cabinet is complex and the signal propagation path is changeable. Traditional fault location methods often cannot ensure the positioning accuracy and precision of partial discharge in the switch cabinet. Therefore, in the complex internal environment of the switch cabinet, how to accurately locate the source of the partial discharge signal becomes a major problem.

[0049] The embodiment of the present invention proposes an automatic positioning method in partial discharge monitoring of a switch cabinet. By comprehensively utilizing frequency and amplitude characteristics and combining the time difference positioning method, the precise positioning of the partial discharge signal source is achieved, and the positioning accuracy and reliability of partial discharge monitoring are improved. The method is suitable for online partial discharge monitoring and fault diagnosis of power equipment such as switch cabinets in power systems.

[0050] Step S101, collecting a set of partial discharge signals of a switch cabinet.

[0051] It should be noted that the embodiment of the present invention monitors the switch cabinet in real time and deploys multiple current sensors at preset positions in the switch cabinet. The local discharge signals inside the switch cabinet are collected at different positions by the multiple current sensors to obtain a local discharge signal set including multiple local discharge signals.

[0052] Optionally, the step of collecting a local discharge signal set of the switch cabinet includes: deploying high-frequency current sensors at K preset positions of the switch cabinet, where K is a positive integer and K is less than or equal to N; collecting the local discharge signals of the switch cabinet through the high-frequency current sensors to obtain the local discharge signal set.

[0053] It should be noted that partial discharge is generally accompanied by the generation of high-frequency current. The embodiment of the present invention can summarize the locations where partial discharge is likely to occur based on the working experience in the historical time period, and select multiple preset locations where partial discharge signals can be collected, and deploy high-frequency current sensors at the preset locations to capture and collect partial discharge signals at different locations in real time.

[0054] The collected partial discharge signal is preprocessed, and the preprocessing operation may specifically include: filtering and denoising to remove interference and noise and ensure signal quality. For example, a high-speed data acquisition card may be used to convert the analog signal collected by the sensor into a digital signal, and the signal may be purified through a digital filter.

[0055] Step S102: converting the partial discharge signals in the partial discharge signal set into frequency domain signals to obtain a frequency domain signal set.

[0056] It should be noted that when analyzing the current signal, both the time domain signal and the frequency domain signal contain many features that can reflect the signal characteristics. The collected partial discharge signal is converted into the frequency domain to obtain the frequency domain signal of the partial discharge signal.

[0057] Specifically, the frequency domain conversion can use fast Fourier transform to perform fast Fourier transform on the preprocessed time domain signal to convert the time domain signal into a frequency domain signal. The formula of fast Fourier transform is as follows:

[0058]

[0059] Where t is the time variable and f is the frequency variable. x(t) is the time domain signal, which represents the signal value changing with time t. X(f) represents the frequency domain signal (spectrum), which represents the complex value of the signal at frequency f, including amplitude and phase information. j is the imaginary unit, satisfying j 2 =-1, e is the base of natural logarithm, approximately equal to 2.71828, and π is a constant used to convert frequency f into angular frequency.

[0060] Step S103, extracting features from the partial discharge signal set and the frequency domain signal set to obtain feature vectors.

[0061] It should be noted that the embodiment of the present invention performs feature extraction on the collected time domain signal and the converted frequency domain signal to obtain a feature vector representing the partial discharge characteristics, and the feature vector can be used to estimate the partial discharge position.

[0062] Optionally, the step of performing feature extraction on the local discharge signal set and the frequency domain signal set to obtain a feature vector includes: performing amplitude feature extraction on the local discharge signal to obtain the amplitude feature of the switch cabinet; performing frequency feature extraction on the frequency domain signal of the local discharge signal to obtain the frequency feature of the switch cabinet; constructing an amplitude feature vector based on the amplitude feature, and constructing a frequency feature vector based on the frequency feature; and splicing the amplitude feature vector and the frequency feature vector to obtain a feature vector.

[0063] It should be noted that, for the local discharge signal in the local discharge signal set, amplitude feature extraction is performed from the local discharge signal to obtain the amplitude feature of the switch cabinet, and frequency feature extraction is performed on the converted frequency domain signal to obtain the frequency feature of the switch cabinet, and the amplitude feature and frequency feature are encoded to obtain an amplitude feature vector and a frequency feature vector, and finally the amplitude feature vector and the frequency feature vector are spliced ​​to form a comprehensive feature vector.

[0064] Optionally, the amplitude feature includes: at least one of the following: a signal peak value, a signal mean value, wherein the signal peak value represents the maximum value of the amplitude of the partial discharge signal, and the signal mean value represents the average value of the amplitude of the partial discharge signal.

[0065] It should be noted that the amplitude feature extraction includes extracting the peak value, mean value and root mean square value of the partial discharge signal. The signal peak value represents the maximum value of the amplitude of the partial discharge signal, the signal mean value represents the average value of the amplitude of the partial discharge signal, and the root mean square value represents the root mean square of the signal mean value.

[0066] Specifically, the peak value refers to the maximum value of the partial discharge signal, indicating the instantaneous strength of the signal. The peak value reflects the transient characteristics of the partial discharge signal and is an important parameter for evaluating the partial discharge intensity. The calculation formula of the peak value is as follows:

[0067] peak=max(x(t))

[0068] Wherein, peak is the peak value of the partial discharge signal, and x(t) is the amplitude of the partial discharge signal at time t.

[0069] The mean is the average value of the signal, indicating the overall strength of the signal. The mean provides information about the overall level of the partial discharge signal and helps to assess the duration of the partial discharge. The calculation formula for the mean is as follows:

[0070]

[0071] Wherein, mean is the average value of the partial discharge signal, x(t) is the amplitude of the partial discharge signal at time t, and N is the number of partial discharge signal amplitudes.

[0072] The root mean square value can represent the energy of the signal, reflecting the energy intensity of the signal, and can effectively characterize the power level of the partial discharge signal. The calculation formula of the root mean square value is as follows:

[0073]

[0074] Optionally, the frequency characteristics include at least one of the following: signal main frequency, signal harmonic frequency, and signal bandwidth, wherein the signal main frequency represents the maximum value of the power spectral density of the frequency domain signal, the signal harmonic frequency is an integer multiple of the signal main frequency, and the signal bandwidth represents the frequency range containing the target energy in the frequency domain signal.

[0075] It should be noted that frequency characteristics may include the signal main frequency, signal harmonic frequency, and signal bandwidth. The signal main frequency represents the maximum value of the power spectral density of the frequency domain signal, the signal harmonic frequency is an integer multiple of the signal main frequency, and the signal bandwidth represents the frequency range containing the target energy in the frequency domain signal.

[0076] Specifically, frequency feature extraction identifies the main frequency components and their harmonic frequencies in the signal by calculating the power spectrum density of the signal. The power spectrum density calculation formula is as follows:

[0077]

[0078] Among them, PSD(f) represents the power spectrum density of the frequency domain signal, and T is the time length of the frequency domain signal. By analyzing the main frequency components, the main frequency characteristics of the partial discharge signal can be understood, thereby helping to identify different partial discharge sources.

[0079] Signal main frequency f main It is the frequency with the largest power spectrum density value. The calculation formula of the main frequency of the signal is as follows:

[0080]

[0081] The harmonic frequency of the signal is an integer multiple of the main frequency. For example, the second harmonic, third harmonic and fourth harmonic can be calculated. The calculation formula of the harmonic frequency is as follows:

[0082] f harnonic,n =n·f main (n=2,3,4)

[0083] Bandwidth refers to the frequency range that contains the main energy in the signal, which is usually estimated by 3dB bandwidth. 3dB bandwidth refers to the frequency range corresponding to the power spectrum density (PSD) of the signal dropping to half of the peak value (i.e. 3dB point). The calculation formula of bandwidth is as follows:

[0084]

[0085] Step S104: calculating a similarity value between the feature vector and the feature vector of the historical sample, and calculating a first position coordinate of the partial discharge signal source of the switch cabinet based on the similarity value.

[0086] It should be noted that after obtaining the feature vector, by calculating the similarity value between the feature vector and the historical sample feature vector, the position of the local discharge signal source in the switch cabinet can be preliminarily estimated to obtain the first position coordinate. The historical sample feature vector is obtained by analyzing the local discharge phenomenon in the historical time period. By calculating the similarity value between the two, the real-time local discharge signal source can be estimated based on the position information of the local discharge signal source corresponding to the historical sample.

[0087] Optionally, the step of calculating the similarity value between the feature vector and the historical sample feature vector includes: calling the historical sample library, calculating the Euclidean distance between the feature vector and each historical sample feature vector in the historical sample library; and obtaining the similarity value between the feature vector and the historical sample feature vector based on the inverse of the Euclidean distance.

[0088] Optionally, the step of calculating the first position coordinates of the local discharge signal source of the switch cabinet based on the similarity value includes: selecting a historical sample feature vector whose similarity value is greater than or equal to a preset similarity threshold, and obtaining a historical local discharge position corresponding to the historical sample feature vector, and using the historical local discharge position as a similar historical local discharge position of the local discharge position of the switch cabinet, and obtaining the position coordinates of the similar historical local discharge position; using the similarity value between the feature vector and the historical sample feature vector as a similarity weight value of the similar historical local discharge position, and calculating the first position coordinates of the switch cabinet based on the similarity weight value and position coordinates of the similar historical local discharge position.

[0089] It should be noted that the step of calculating the first position coordinates includes:

[0090] Similarity calculation, calculate the feature vector T corresponding to the local discharge signal collected in real time real and the historical sample feature vector T sample The Euclidean distance between them. The Euclidean distance formula is as follows:

[0091]

[0092] Among them, d(T real ,T sample ) is the Euclidean distance between the feature vector and the feature vector of the historical sample, represents the i-th eigenvector, Represents the i-th historical sample feature vector.

[0093] The similarity can be calculated by the reciprocal of the Euclidean distance. The similarity calculation formula is as follows:

[0094]

[0095] Among them, S(T real ,T sample ) represents the similarity value between the feature vector and the feature vector of the historical sample. The higher the similarity value, the higher the match between the real-time signal and the historical sample, which helps to accurately identify the signal source.

[0096] Signal source matching matches the feature vector of the real-time collected signal with the feature vector of the historical sample in the historical sample library to find a batch of samples with high similarity, thereby obtaining the k most similar samples, and the corresponding similarity values ​​are S1, S2,…, Sk.

[0097] Signal source matching position estimation, the first position coordinates of the partial discharge signal source are calculated by comprehensive feature matching results, so as to preliminarily estimate the position of the signal source. When calculating, the similarity value is used as the similarity weight value of the similar samples. The position of the i-th similar sample is set as (x i ,yi ,z i ), the similarity value (i.e. similarity weight value) is S i , the calculation formula of the first position coordinate is as follows:

[0098]

[0099] Finally, the first position coordinate of the partial discharge signal source is Position(x s ,y s , z s ).

[0100] Step S105: calculating the second position coordinates of the partial discharge signal source of the switch cabinet based on the time difference positioning algorithm.

[0101] It should be noted that in order to calculate more accurate position coordinates of the discharge signal source, the embodiment of the present invention calculates the second position coordinates of the local discharge signal source using a time difference positioning algorithm based on the positions of multiple sensors and signal reception times, based on the comprehensive use of frequency and amplitude characteristics to calculate the first position coordinates.

[0102] Optionally, the step of calculating the second position coordinates of the local discharge signal source of the switch cabinet based on the time difference positioning algorithm includes: obtaining the time point when each high-frequency current sensor receives the local discharge signal and the sensor position coordinates of each high-frequency current sensor; constructing a linear equation based on the position parameters of the local discharge position and the time difference between each two high-frequency current sensors and the sensor position coordinates of the two high-frequency current sensors; solving the linear equation to obtain the second position coordinates of the local discharge signal source.

[0103] Specifically, when calculating the second position coordinates, the position coordinates of multiple sensors that collected the same local discharge signal source and the time points when the local discharge signals were received are determined according to the characteristics of the local discharge signals collected by the multiple sensors, a linear equation is constructed using the position parameters of the local discharge position and the position coordinates and time points of the multiple sensors, and the linear equation is solved to obtain the second position coordinates of the local discharge signal source.

[0104] Specifically, assuming that the location coordinates of the partial discharge signal source are (x, y, z), the sensor S i The position of (x i ,y i ,z i ), the signal reaches the sensor S i The time is t i , the speed of sound is v, and the linear equation constructed according to the position coordinates of the partial discharge signal source, the position coordinates of the sensor and the time point of receiving the partial discharge signal is expressed as:

[0105]

[0106] Among them, t ij is the time difference between the signals received by sensor i and sensor j, t i is the time point when sensor i receives the partial discharge signal, t j is the time point when sensor j receives the partial discharge signal.

[0107] By solving the above equations, the position of the local discharge signal source can be estimated to obtain the second position coordinates.

[0108] Step S106, configuring a position weight value for the first position coordinate, calculating the position coordinate of the partial discharge signal source of the switch cabinet based on the first position coordinate, the second position coordinate and the position weight value, and determining the partial discharge position of the switch cabinet based on the position coordinate.

[0109] It should be noted that the embodiment of the present invention can optimize the position of the signal source and reduce the positioning error through weight allocation and weighted average position calculation, and combines the similarity value and geometric position to ensure the accuracy of the positioning result. The final partial discharge signal source position coordinates are obtained by weighted calculation of the first position coordinates and the second position coordinates, and the position weight value a of the time difference positioning is set. The comprehensive position is calculated by the weighted average method, and the final calculated partial discharge position is expressed as:

[0110] Position=Position(x,y,z)·a+Position(x s ,y s ,z s )·(1-a)

[0111] Wherein, Position represents the final position coordinates of the partial discharge signal source, Position(x, y, z) represents the second position coordinates of the partial discharge signal source calculated by the time difference positioning method, and Position(x s ,y s ,z s ) represents the first position coordinate of the local discharge signal source calculated based on the similarity value, and a represents a preset position weight value.

[0112] Another optional specific implementation is described in detail below.

[0113] An embodiment of the present invention provides an automatic positioning method for partial discharge monitoring of a switch cabinet. By comprehensively utilizing frequency and amplitude characteristics and combining the time difference positioning method, the precise positioning of the partial discharge signal source can be achieved, thereby improving the positioning accuracy and reliability of partial discharge monitoring. The method is suitable for online partial discharge monitoring and fault diagnosis of switch cabinets and other equipment in power systems. Figure 2is a schematic diagram of an optional partial discharge position determination process of a switch cabinet according to an embodiment of the present invention, such as Figure 2 As shown in the figure, the process of determining the partial discharge position of the switch cabinet includes:

[0114] Step 1: signal acquisition and preprocessing;

[0115] Step 2: frequency feature extraction;

[0116] Step 3: amplitude feature extraction;

[0117] Step 4: feature fusion;

[0118] Step 5, calculating the second position coordinates of the partial discharge signal source by using a time difference positioning algorithm;

[0119] Step six, calculating the first position coordinates of the partial discharge signal source through comprehensive matching and positioning;

[0120] Step seven, performing comprehensive position calculation using the first position coordinates and the second position coordinates to determine the partial discharge position in the switch cabinet.

[0121] The embodiment of the present invention achieves accurate positioning of the partial discharge signal source by fusing frequency and amplitude features and combining the time difference positioning method. The comprehensive analysis of frequency and amplitude features enables a more accurate association between different signal features, thereby reducing the error in the traditional single positioning method. For example, by extracting the main frequency component of the signal through the frequency feature and extracting the energy information of the signal through the amplitude feature, the location and nature of the partial discharge source can be more accurately identified. This combination of multi-dimensional features significantly improves the positioning accuracy, making the positioning results more reliable and accurate.

[0122] The embodiments of the present invention realize real-time online monitoring and automatic fault location of partial discharge signals, reducing the reliance on manual detection. By deploying multiple sensors such as high-frequency current sensors in the switch cabinet and combining them with high-speed data acquisition cards, the system can collect and process partial discharge signals in real time. This automated monitoring and location method not only improves the monitoring efficiency, but also significantly shortens the fault response time. Maintenance personnel can quickly locate the fault point and take corresponding measures through real-time monitoring data, thereby improving the reliability and safety of power equipment.

[0123] The following is a detailed description in conjunction with another embodiment.

[0124] Embodiment 2

[0125] A partial discharge position determination device for a switch cabinet provided in this embodiment includes multiple implementation units, each implementation unit corresponds to each implementation step in the above-mentioned embodiment 1. Its specific implementation methods and beneficial effects can refer to the above-mentioned method embodiments and will not be repeated here.

[0126] Figure 3 is a schematic diagram of an optional device for determining a partial discharge position of a switch cabinet according to an embodiment of the present invention, such as Figure 3 As shown, the device for determining the partial discharge position of the switch cabinet may include: a collection unit 31, a conversion unit 32, an extraction unit 33, a first calculation unit 34, a second calculation unit 35, and a determination unit 36, wherein:

[0127] A collection unit 31 is used to collect a partial discharge signal set of the switch cabinet, wherein the partial discharge signal set includes N partial discharge signals;

[0128] A conversion unit 32, configured to convert the local discharge signals in the local discharge signal set into frequency domain signals to obtain a frequency domain signal set;

[0129] An extraction unit 33, used to extract features from the local discharge signal set and the frequency domain signal set to obtain a feature vector;

[0130] A first calculation unit 34 is used to calculate a similarity value between the feature vector and the historical sample feature vector, and calculate a first position coordinate of a partial discharge signal source of the switch cabinet based on the similarity value;

[0131] A second calculation unit 35, configured to calculate a second position coordinate of a partial discharge signal source of the switch cabinet based on a time difference positioning algorithm;

[0132] The determination unit 36 ​​is used to configure a position weight value for the first position coordinate, calculate the position coordinate of the partial discharge signal source of the switch cabinet based on the first position coordinate, the second position coordinate and the position weight value, and determine the partial discharge position of the switch cabinet based on the position coordinate.

[0133] The above-mentioned device for determining the position of partial discharge of the switch cabinet collects the partial discharge signal set of the switch cabinet through the collection unit 31, wherein the partial discharge signal set includes N partial discharge signals; the partial discharge signals in the partial discharge signal set are converted into frequency domain signals through the conversion unit 32 to obtain the frequency domain signal set; the partial discharge signal set and the frequency domain signal set are extracted by the extraction unit 33 to obtain a feature vector; the similarity value between the feature vector and the feature vector of the historical sample is calculated by the first calculation unit 34, and the first position coordinate of the partial discharge signal source of the switch cabinet is calculated based on the similarity value; the second calculation unit 35 calculates the second position coordinate of the partial discharge signal source of the switch cabinet based on the time difference positioning algorithm; the determination unit 36 ​​configures the position weight value for the first position coordinate, calculates the position coordinate of the partial discharge signal source of the switch cabinet based on the first position coordinate, the second position coordinate and the position weight value, and determines the partial discharge position of the switch cabinet based on the position coordinate.

[0134] In this embodiment, frequency domain features and amplitude features are extracted based on the local discharge signal of the switch cabinet, and the information in the frequency and amplitude feature vectors is comprehensively utilized. The similarity value is calculated in combination with the historical sample feature vector, and the local discharge position is preliminarily estimated based on the similarity value. Then, the local discharge position is estimated and calculated again in combination with the time difference positioning algorithm. The final local discharge position is calculated based on the position data calculated multiple times and the pre-configured weight vector. By performing comprehensive calculations on multi-dimensional information and determining the specific position of the local discharge, the local discharge signal source can be accurately located, and the accuracy of the local discharge positioning results can be improved, thereby solving the technical problem of low accuracy of the positioning result in the related art of locating the local discharge position of the switch cabinet by a single positioning method.

[0135] Optionally, the first calculation unit 34 includes: a first calculation module, used to call the historical sample library and calculate the Euclidean distance between the feature vector and each historical sample feature vector in the historical sample library; a first acquisition module, used to obtain the similarity value between the feature vector and the historical sample feature vector based on the inverse of the Euclidean distance.

[0136] Optionally, the first calculation unit 34 also includes: a first selection module, used to select a historical sample feature vector whose similarity value is greater than or equal to a preset similarity threshold, and obtain a historical local discharge position corresponding to the historical sample feature vector, and use the historical local discharge position as a similar historical local discharge position of the local discharge position of the switch cabinet, and obtain the position coordinates of the similar historical local discharge position; a second calculation module, used to use the similarity value between the feature vector and the historical sample feature vector as a similarity weight value of the similar historical local discharge position, and calculate the first position coordinates of the switch cabinet based on the similarity weight value and position coordinates of the similar historical local discharge position.

[0137] Optionally, the second calculation unit 35 includes: a second acquisition module, used to obtain the time point when each high-frequency current sensor receives the local discharge signal and the sensor position coordinates of each high-frequency current sensor; a first construction module, used to construct a linear equation based on the position parameters of the local discharge position and the time difference between every two high-frequency current sensors and the sensor position coordinates of the two high-frequency current sensors; a first solution module, used to solve the linear equation to obtain the second position coordinates of the local discharge signal source.

[0138] Optionally, the extraction unit 33 includes: a first extraction module, used to extract amplitude features of the local discharge signal to obtain the amplitude features of the switch cabinet; a second extraction module, used to extract frequency features of the frequency domain signal of the local discharge signal to obtain the frequency features of the switch cabinet; a second construction module, used to construct an amplitude feature vector based on the amplitude feature, and to construct a frequency feature vector based on the frequency feature; a first splicing module, used to splice the amplitude feature vector and the frequency feature vector to obtain a feature vector.

[0139] Optionally, the amplitude feature includes: at least one of the following: a signal peak value, a signal mean value, wherein the signal peak value represents the maximum value of the amplitude of the partial discharge signal, and the signal mean value represents the average value of the amplitude of the partial discharge signal.

[0140] Optionally, the frequency characteristics include at least one of the following: signal main frequency, signal harmonic frequency, and signal bandwidth, wherein the signal main frequency represents the maximum value of the power spectral density of the frequency domain signal, the signal harmonic frequency is an integer multiple of the signal main frequency, and the signal bandwidth represents the frequency range containing the target energy in the frequency domain signal.

[0141] Optionally, the acquisition unit 31 includes: a first deployment module, used to deploy high-frequency current sensors at K preset positions of the switch cabinet, where K is a positive integer and K is less than or equal to N; a first acquisition module, used to collect local discharge signals of the switch cabinet through high-frequency current sensors to obtain a local discharge signal set.

[0142] The above-mentioned partial discharge position determination device of the switch cabinet may further include a processor and a memory. The above-mentioned acquisition unit 31, conversion unit 32, extraction unit 33, first calculation unit 34, second calculation unit 35, determination unit 36, etc. are all stored in the memory as program units, and the processor executes the above-mentioned program units stored in the memory to realize corresponding functions.

[0143] The processor includes a kernel, which retrieves the corresponding program unit from the memory. One or more kernels can be set, and the specific location of the local discharge source of the switch cabinet can be determined by adjusting the kernel parameters.

[0144] The above-mentioned memory may include non-permanent memory in a computer-readable medium, random access memory (RAM) and / or non-volatile memory, such as read-only memory (ROM) or flash RAM, and the memory includes at least one storage chip.

[0145] According to another aspect of an embodiment of the present invention, a computer-readable storage medium is further provided, the computer-readable storage medium including a stored computer program, wherein when the computer program is running, the device where the computer-readable storage medium is located is controlled to execute any one of the above-mentioned methods for determining the partial discharge position of a switch cabinet.

[0146] According to another aspect of an embodiment of the present invention, there is also provided an electronic device, comprising one or more processors and a memory, wherein the memory is used to store one or more programs, wherein when the one or more programs are executed by one or more processors, the one or more processors implement any one of the above-mentioned methods for determining the partial discharge position of a switch cabinet.

[0147] According to another aspect of an embodiment of the present invention, a computer program product is further provided. The computer program product includes a computer program, wherein when the computer program is executed by a processor, any of the above-mentioned methods for determining a partial discharge position of a switch cabinet is implemented.

[0148] The present application also provides a computer program product, which, when executed on a data processing device, is suitable for executing a program that is initialized with the following method steps: collecting a local discharge signal set of a switch cabinet, wherein the local discharge signal set includes N local discharge signals; converting the local discharge signals in the local discharge signal set into frequency domain signals to obtain a frequency domain signal set; performing feature extraction on the local discharge signal set and the frequency domain signal set to obtain a feature vector; calculating a similarity value between the feature vector and a historical sample feature vector, and calculating a first position coordinate of a local discharge signal source of the switch cabinet based on the similarity value; calculating a second position coordinate of the local discharge signal source of the switch cabinet based on a time difference positioning algorithm; configuring a position weight value for the first position coordinate, calculating the position coordinate of the local discharge signal source of the switch cabinet based on the first position coordinate, the second position coordinate and the position weight value, and determining the local discharge position of the switch cabinet based on the position coordinate.

[0149] The present application also provides a computer program product, which, when executed on a data processing device, is also suitable for executing a program initialized with the following method steps: the step of calculating the similarity value between the feature vector and the historical sample feature vector includes: calling the historical sample library, calculating the Euclidean distance between the feature vector and each historical sample feature vector in the historical sample library; and obtaining the similarity value between the feature vector and the historical sample feature vector based on the inverse of the Euclidean distance.

[0150] The present application also provides a computer program product, which, when executed on a data processing device, is also suitable for executing a program that is initialized with the following method steps: the step of calculating the first position coordinates of the local discharge signal source of the switch cabinet based on the similarity value includes: selecting a historical sample feature vector whose similarity value is greater than or equal to a preset similarity threshold, and obtaining the historical local discharge position corresponding to the historical sample feature vector, using the historical local discharge position as a similar historical local discharge position of the local discharge position of the switch cabinet, and obtaining the position coordinates of the similar historical local discharge position; using the similarity value between the feature vector and the historical sample feature vector as a similarity weight value of the similar historical local discharge position, and calculating the first position coordinates of the switch cabinet based on the similarity weight value and position coordinates of the similar historical local discharge position.

[0151] The present application also provides a computer program product, which, when executed on a data processing device, is also suitable for executing a program that initializes the following method steps: the step of calculating the second position coordinates of the local discharge signal source of the switch cabinet based on the time difference positioning algorithm includes: obtaining the time point when each high-frequency current sensor receives the local discharge signal and the sensor position coordinates of each high-frequency current sensor; constructing a linear equation based on the position parameters of the local discharge position and the time difference between each two high-frequency current sensors and the sensor position coordinates of the two high-frequency current sensors; solving the linear equation to obtain the second position coordinates of the local discharge signal source.

[0152] The present application also provides a computer program product, which, when executed on a data processing device, is also suitable for executing a program that is initialized with the following method steps: extracting features from a local discharge signal set and a frequency domain signal set, and the step of obtaining a feature vector includes: extracting amplitude features from the local discharge signal to obtain the amplitude features of the switch cabinet; extracting frequency features from the frequency domain signal of the local discharge signal to obtain the frequency features of the switch cabinet; constructing an amplitude feature vector based on the amplitude features, and constructing a frequency feature vector based on the frequency features; and splicing the amplitude feature vector and the frequency feature vector to obtain a feature vector.

[0153] The present application also provides a computer program product, which, when executed on a data processing device, is also suitable for executing a program that is initialized with the following method steps: the amplitude characteristics include: at least one of the following: signal peak value, signal mean value, wherein the signal peak value represents the maximum value of the amplitude of the local discharge signal, and the signal mean value represents the average value of the amplitude of the local discharge signal.

[0154] The present application also provides a computer program product, which, when executed on a data processing device, is also suitable for executing a program initialized with the following method steps: the frequency characteristics include at least one of the following: signal main frequency, signal harmonic frequency, signal bandwidth, wherein the signal main frequency represents the maximum value of the power spectral density of the frequency domain signal, the signal harmonic frequency is an integer multiple of the signal main frequency, and the signal bandwidth represents the frequency range containing the target energy in the frequency domain signal.

[0155] The present application also provides a computer program product, which, when executed on a data processing device, is also suitable for executing a program that initializes the following method steps: the step of collecting a set of local discharge signals of a switch cabinet comprises: deploying high-frequency current sensors at K preset positions of the switch cabinet, where K is a positive integer and K is less than or equal to N; collecting local discharge signals of the switch cabinet through high-frequency current sensors to obtain a set of local discharge signals.

[0156] Figure 4 1 is a hardware structure block diagram of an electronic device (or mobile device) for determining a partial discharge position of a switch cabinet according to an embodiment of the present invention. Figure 4 As shown, the electronic device may include one or more ( Figure 4 402a, 402b, ..., 402n are used to illustrate) processor 402 (processor 402 may include but is not limited to a processing device such as a microprocessor MCU or a programmable logic device FPGA), memory 404 for storing data. In addition, it may also include: a display, an input / output interface (I / O interface), a universal serial bus (USB) port (which may be included as one of the ports of the I / O interface), a network interface, a keyboard, a power supply and / or a camera. It can be understood by those skilled in the art that Figure 4 The structure shown is only for illustration and does not limit the structure of the above electronic device. Figure 4 More or fewer components as shown, or with Figure 4 Different configurations are shown.

[0157] The serial numbers of the above embodiments of the present invention are only for description and do not represent the advantages or disadvantages of the embodiments.

[0158] In the above embodiments of the present invention, the description of each embodiment has its own emphasis. For parts that are not described in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0159] In the several embodiments provided in this application, it should be understood that the disclosed technical content can be implemented in other ways. Among them, the device embodiments described above are only schematic. For example, the division of the units can be a logical function division. There may be other division methods in actual implementation. For example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of units or modules, which can be electrical or other forms.

[0160] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple units. Some or all of the units may be selected according to actual needs to achieve the purpose of the present embodiment.

[0161] In addition, each functional unit in each embodiment of the present invention may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of software functional units.

[0162] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art, or all or part of the technical solution can be embodied in the form of a software product, and the computer software product is stored in a storage medium, including a number of instructions for a computer device (which can be a personal computer, a server or a network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present invention. The aforementioned storage medium includes: U disk, read-only memory (ROM, Read-On lyMemory), random access memory (RAM, Random Access Memory), mobile hard disk, magnetic disk or optical disk and other media that can store program codes.

[0163] The above is only a preferred embodiment of the present invention. It should be pointed out that for ordinary technicians in this technical field, several improvements and modifications can be made without departing from the principle of the present invention. These improvements and modifications should also be regarded as the scope of protection of the present invention.

Claims

1. A method for determining a partial discharge position of a switch cabinet, characterized in that: include: Collecting a partial discharge signal set of the switch cabinet, wherein the partial discharge signal set includes N partial discharge signals; Converting the local discharge signals in the local discharge signal set into frequency domain signals to obtain a frequency domain signal set; Performing feature extraction on the local discharge signal set and the frequency domain signal set to obtain a feature vector; Calculating a similarity value between the feature vector and a historical sample feature vector, and calculating a first position coordinate of a partial discharge signal source of the switch cabinet based on the similarity value; Calculate the second position coordinates of the partial discharge signal source of the switch cabinet based on the time difference positioning algorithm; A position weight value is configured for the first position coordinate, the position coordinate of the partial discharge signal source of the switch cabinet is calculated based on the first position coordinate, the second position coordinate and the position weight value, and the partial discharge position of the switch cabinet is determined based on the position coordinate.

2. The determination method according to claim 1, characterized in that: The step of calculating the similarity value between the feature vector and the feature vector of the historical sample comprises: Calling a historical sample library, and calculating the Euclidean distance between the feature vector and each of the historical sample feature vectors in the historical sample library; A similarity value between the feature vector and a feature vector of a historical sample is obtained based on the inverse of the Euclidean distance.

3. The determination method according to claim 2, characterized in that: The step of calculating the first position coordinates of the partial discharge signal source of the switch cabinet based on the similarity value comprises: Selecting the historical sample feature vector whose similarity value is greater than or equal to a preset similarity threshold, and obtaining the historical partial discharge position corresponding to the historical sample feature vector, taking the historical partial discharge position as a similar historical partial discharge position of the partial discharge position of the switch cabinet, and obtaining the position coordinates of the similar historical partial discharge position; The similarity value between the feature vector and the historical sample feature vector is used as the similarity weight value of the similar historical partial discharge position, and the first position coordinate of the switch cabinet is calculated based on the similarity weight value of the similar historical partial discharge position and the position coordinate.

4. The determination method according to claim 1, characterized in that: The step of calculating the second position coordinates of the partial discharge signal source of the switch cabinet based on the time difference positioning algorithm includes: Acquire the time point at which each high-frequency current sensor receives the partial discharge signal and the sensor position coordinates of each high-frequency current sensor; Constructing a linear equation based on the position parameters of the partial discharge position, the time difference between each two high-frequency current sensors, and the sensor position coordinates of the two high-frequency current sensors; The linear equation is solved to obtain the second position coordinates of the partial discharge signal source.

5. The determination method according to claim 1, characterized in that: The step of extracting features from the partial discharge signal set and the frequency domain signal set to obtain a feature vector comprises: Extracting amplitude characteristics of the partial discharge signal to obtain amplitude characteristics of the switch cabinet; Extracting frequency characteristics of the frequency domain signal of the partial discharge signal to obtain frequency characteristics of the switch cabinet; constructing an amplitude feature vector based on the amplitude feature, and constructing a frequency feature vector based on the frequency feature; The amplitude feature vector and the frequency feature vector are concatenated to obtain the feature vector.

6. The determination method according to claim 5, characterized in that: The amplitude feature includes: at least one of the following: a signal peak value and a signal mean value, wherein the signal peak value represents the maximum value of the amplitude of the partial discharge signal, and the signal mean value represents the average value of the amplitude of the partial discharge signal.

7. The determination method according to claim 5, characterized in that: The frequency characteristics include at least one of the following: a signal main frequency, a signal harmonic frequency, and a signal bandwidth, wherein the signal main frequency represents the maximum value of the power spectrum density of the frequency domain signal, the signal harmonic frequency is an integer multiple of the signal main frequency, and the signal bandwidth represents the frequency range containing the target energy in the frequency domain signal.

8. The determination method according to claim 1, characterized in that: The steps of collecting the partial discharge signal set of the switch cabinet include: Deploy high-frequency current sensors at K preset positions of the switch cabinet, where K is a positive integer and K is less than or equal to N; The local discharge signal of the switch cabinet is collected by the high-frequency current sensor to obtain the local discharge signal set.

9. A device for determining the position of partial discharge of a switch cabinet, characterized in that: include: A collection unit, used for collecting a partial discharge signal set of the switch cabinet, wherein the partial discharge signal set includes N partial discharge signals; A conversion unit, configured to convert the local discharge signals in the local discharge signal set into frequency domain signals to obtain a frequency domain signal set; An extraction unit, used for performing feature extraction on the partial discharge signal set and the frequency domain signal set to obtain a feature vector; A first calculation unit, configured to calculate a similarity value between the feature vector and a historical sample feature vector, and calculate a first position coordinate of a partial discharge signal source of the switch cabinet based on the similarity value; A second calculation unit, used for calculating the second position coordinates of the partial discharge signal source of the switch cabinet based on a time difference positioning algorithm; A determination unit is used to configure a position weight value for the first position coordinate, calculate the position coordinate of the local discharge signal source of the switch cabinet based on the first position coordinate, the second position coordinate and the position weight value, and determine the local discharge position of the switch cabinet based on the position coordinate.

10. An electronic device, characterized in that: The method comprises one or more processors and a memory, wherein the memory is used to store one or more programs, wherein when the one or more programs are executed by the one or more processors, the one or more processors implement the method for determining the partial discharge position of the switch cabinet as claimed in any one of claims 1 to 8.

Images