A non-invasive classification method for short-circuit faults of three-core cables

Abstract

The present invention discloses a non-invasive classification method for short-circuit faults of a three-core cable, which includes the following steps: S1. Create an experimental platform and measure the tangential magnetic field on the surface of the three-core power cable through three magnetoelectric sensors in the experimental platform; place three magnetoelectric sensors on the surface of the three-core power cable, and the three sensors are 120 degrees apart from each other; S2. According to the Concordia transformation, perform modal transformation and dimensionality reduction on the tangential magnetic fields B<subgt;tan1< / subgt>, B<subgt;tan2< / subgt> and B<subgt;tan3< / subgt> at three positions to obtain the magnetic fields in the α and β modes, and draw the curves of B<subgt;α and B<subgt;β in polar coordinates, which is called a magnetic map; S3. Use the random forest algorithm to identify the short-circuit fault types. The present invention adopts the above non-invasive classification method for short-circuit faults of a three-core cable, uses magnetoelectric sensors with strong anti-interference ability and high sensitivity to detect the magnetic field changes on the surface of the three-core cable, and finally applies the random forest algorithm to the fault feature data set to achieve the classification of short-circuit fault types.

Description

Technical Field

[0001] The present invention relates to the technical field of cable fault diagnosis, and particularly to a non-invasive classification method for short-circuit faults of three-core cables. Background Art

[0002] Fault classification plays an important role in the protection of cables. Accurate and rapid fault classification can greatly facilitate fault location and fault isolation, thereby reducing potential hazards in the power system. With the development of cities, underground cables are now widely used. Compared with overhead lines, underground cables are expensive to install, but they are more reliable and have a longer service life compared to overhead lines. Fault detection in underground cables is difficult compared to overhead cables. Underground cables are not easily affected by adverse conditions such as heavy rain, snowfall, and temperature changes. However, due to internal insulation breakdown or external damage, short-circuit faults still occur on the distribution network. For example, a shielding fault is an insulation breakdown that causes physical contact between the phase conductor and the shield. When the shield is grounded, a phase-to-ground fault occurs. The insulation between conductors may break down due to corrosion, resulting in an inter-phase short-circuit fault. Accidental excavation of underground cables may cause a three-phase short circuit. Therefore, in order to minimize economic losses, significantly accelerate system improvement, and ensure the power quality of customers, it must be detected and the fault type quickly identified for subsequent relay tripping, fault location, and fault clearing.

[0003] However, many existing methods mainly rely on phase current measurement to monitor the operating status of cables or overhead lines. For a three-core cable in a packaged form, the total current in the steady state is zero, making traditional inductive phase current measurement techniques ineffective. To overcome this limitation, the present invention proposes a non-invasive online fault diagnosis method based on magnetic induction, providing real-time fault detection and classification functions for distribution cables. Magnetoelectric sensors have become excellent magnetic sensors for measuring the magnetic field generated by current, providing a promising alternative for such applications. Summary of the Invention

[0004] The purpose of the present invention is to provide a non-invasive classification method for short-circuit faults of three-core cables, using magnetoelectric sensors with strong anti-interference ability and high sensitivity to detect the magnetic field changes on the surface of the three-core cable, and finally using the random forest algorithm for the fault feature data set to achieve the classification of short-circuit fault types.

[0005] The present invention provides a non-invasive classification method for short-circuit faults of three-core cables, including the following steps:

[0006] S1. Create an experimental platform, and measure the tangential magnetic field on the surface of the three-core power cable through three magnetoelectric sensors in the experimental platform; place three magnetoelectric sensors on the surface of the three-core power cable, and the three sensors are 120 degrees apart from each other;

[0007] S2. Perform modal transformation and dimensionality reduction on the tangential magnetic fields B at three positions according to the Concordia transformation tan1 , B tan2 and B tan3 to obtain the magnetic fields in the α and β modes, and plot the curves of B α and B β in polar coordinates, which is called a magnetogram; calculate the cosine similarity between B α and B β , the signal power of B α , the signal power of B β , and the sum of their signal powers;

[0008] S3. Based on the extracted fault feature data, use the random forest algorithm to identify the types of short - circuit faults.

[0009] Preferably, in step S1, the experimental platform includes a three - phase programmable AC power supply, a filtering and signal amplification module, an oscilloscope, a three - phase resistive load, a magnetoelectric sensor array, and a three - core power cable;

[0010] The magnetoelectric sensor is composed of two magnetostrictive layers and a middle piezoelectric layer bonded together with epoxy resin glue, placed in a hot press for pressing, and then copper wires are led out from both ends of the magnetostrictive layer;

[0011] Package and fix a single magnetoelectric sensor with a 3D - printed plastic shell and add a permanent magnet;

[0012] Three magnetoelectric sensors are installed on the surface of the three - core power cable through a 3D - printed fixture, and the size of the magnetoelectric sensor is 26mm×6mm×1mm.

[0013] Preferably, in step S1, O is the center point of the three - core cable, A, B, and C are the three - phase conductors, and the coordinates of the centers of the three - phase conductors are (r A , θ A ), (r B , θ B ), and (r C , θ C ). Three magnetoelectric sensors are placed on the surface of the three - core power cable, and the three magnetoelectric sensors are respectively aligned with point O through the connecting lines of the centers of the three - phase conductors A, B, and C. The magnetic flux density at any point P(R, θ) on the surface of the three - core power cable is the vector sum of the magnetic flux densities of the three - phase conductors A, B, and C at this point;

[0014] B P = B AP + B BP + B CP ;

[0015] According to the Biot-Savart law, the magnetic flux density of each phase conductor at P(R,θ) can be expressed as:

[0016]

[0017] where μ0 is the magnetic permeability of vacuum; D iP (i = A,B,C) is the distance from the center of the three-phase conductor to point P; I i (i = A,B,C) is the current of the three-phase conductor;

[0018] The magnetic field at point P(R,θ) is divided into the tangential magnetic field component B tan and the radial magnetic field component B rad , and these two components are transformed from the magnetic field components in the X-axis direction and the Y-axis direction in the XY coordinate system as follows:

[0019]

[0020] where B ix and B iy (i = A,B,C) are the magnetic flux density components in the X-axis direction and the Y-axis direction of the three-phase conductor at point P respectively;

[0021] For a three-core power cable with a symmetric structure, assume the center points of the three-phase conductors are as follows:

[0022]

[0023] where R is the distance from point O to the center of the magnetoelectric sensor; r is the distance from point O to the center of the three-phase conductor; α is the ratio of r to R;

[0024] The tangential magnetic field at any point on the surface of the three-core cable is expressed as:

[0025]

[0026] When θ = θ i (i = A,B,C), B tan (θ) reaches the maximum value. Place the three magnetoelectric sensors at the three positions with the strongest tangential magnetic field. The magnetic fields at these three positions have the following relationship with the three-phase currents:

[0027]

[0028] Preferably, in step S2, according to the Concordia transformation, the tangential magnetic fields B tan1 , B tan2 and B tan3 at the three positions are subjected to modal transformation and dimensionality reduction processing to obtain the magnetic fields B α and B β in the α and β modes,

[0029]

[0030] Preferably, in step S2, the purpose of the cosine similarity is to measure the directional difference between two vectors, which is independent of the length of the vectors. For two n-dimensional vectors a = {x1, x2, …, x n} and b = {y1, y2, …, y n}, the cosine similarity cosθ is defined as:

[0031]

[0032] The cosine similarity CS between B α and B β obtained after the Concordia transformation is defined as:

[0033]

[0034] Preferably, in step S2, if the signal is a periodic signal, the signal power can be obtained by calculating the energy of the signal within one period and dividing it by the length N of the signal:

[0035]

[0036] Calculate the signal power P α and P β for each in a single period, as well as the sum of their powers P s :

[0037]

[0038] Therefore, the present invention adopts the above non-invasive classification method for short-circuit faults of a three-core cable, uses a magnetoelectric sensor with strong anti-interference ability and high sensitivity to detect the magnetic field change on the surface of the three-core cable, and finally applies the random forest algorithm to the fault feature data set to achieve the classification of short-circuit fault types.

[0039] The technical solution of the present invention will be further described in detail below through the accompanying drawings and embodiments. Description of the Drawings

[0040] Figure 1 is the overall schematic diagram of a non-invasive classification method for short-circuit faults of a three-core cable according to the present invention;

[0041] Figure 2 is the magnetic field on the surface of the three-core cable and the installation positions of the magnetoelectric sensor array for a non-invasive classification method for short-circuit faults of a three-core cable according to the present invention;

[0042] Figure 3In a non-invasive classification method for short-circuit faults of a three-core cable according to the present invention, (a) is the waveform of B when it is AG, α and B β waveform, (b) is the waveform of B when it is BG, α and B β waveform, (c) is the waveform of B when it is CG, α and B β waveform, (d) is the schematic diagram of the magnetic map corresponding to three LG faults;

[0043] Figure 4 In a non-invasive classification method for short-circuit faults of a three-core cable according to the present invention, (a) is the waveform of B when it is AG, α and B β waveform, (b) is the waveform of B when it is AB, α and B β waveform, (c) is the waveform of B when it is ABG, α and B β waveform, (d) is the magnetic map when it is ABCG, (e) is the schematic diagram of the magnetic map corresponding to four faults;

[0044] Figure 5 Schematic diagram of cosine similarity under four short-circuit faults of a non-invasive classification method for short-circuit faults of a three-core cable according to the present invention;

[0045] Figure 6 Power P under four short-circuit faults of a non-invasive classification method for short-circuit faults of a three-core cable according to the present invention α , P β and P s curve graph;

[0046] Figure 7 Classification flow chart of a non-invasive classification method for short-circuit faults of a three-core cable according to the present invention;

[0047] Figure 8 Schematic diagram of the confusion matrix prediction category reflecting the prediction result of a non-invasive classification method for short-circuit faults of a three-core cable according to the present invention. Detailed implementation manner

[0048] The technical solution of the present invention will be further described below through the accompanying drawings and embodiments.

[0049] Unless otherwise defined, the technical terms or scientific terms used in the present invention should have the ordinary meaning understood by those with ordinary skills in the field to which the present invention belongs.

[0050] The words "first", "second" and similar terms used in the present invention do not indicate any order, quantity or importance, but are only used to distinguish different components. Words such as "include" or "comprise" mean that the elements or objects preceding the word include the elements or objects listed after the word and their equivalents, without excluding other elements or objects. Words such as "connect" or "connected" are not limited to physical or mechanical connections, but may include electrical connections, whether direct or indirect. "Up", "down", "left", "right" and the like are only used to indicate relative position relationships. When the absolute position of the object being described changes, the relative position relationship may also change accordingly.

[0051] Example 1

[0052] like Figures 1 - 8 As shown, the present invention provides a non-invasive classification method for a three-core cable short-circuit fault, comprising the following steps: S1, creating an experimental platform, and measuring the tangential magnetic field on the surface of the three-core power cable by three magnetoelectric sensors in the experimental platform; placing three magnetoelectric sensors on the surface of the three-core power cable, with the three sensors being 120 degrees apart from each other;

[0053] In step S1, the experimental platform includes a three-phase programmable AC power supply, a filtering and signal amplification module, an oscilloscope, a three-phase resistive load, a magnetoelectric sensor array, and a three-core power cable;

[0054] The magnetoelectric sensor is made of two magnetostrictive layers and a piezoelectric layer in the middle, which are bonded together with epoxy resin glue. The layers are then pressed in a hot press to achieve solidification, and copper wires are then drawn out from both ends of the magnetostrictive layers.

[0055] A single magnetoelectric sensor is packaged and fixed with a 3D printed plastic shell and a permanent magnet is added.

[0056] Three magnetoelectric sensors are mounted on the surface of a three-core power cable using a 3D printed fixture. The magnetoelectric sensors measure 26mm×6mm×1mm.

[0057] In step S1, O is the center point of the three-core cable, A, B, and C are three-phase conductors, and the coordinates of the centers of the three-phase conductors are (r A ,θ A ), (r B ,θ B ) and (r C ,θ C ), three magnetoelectric sensors are placed on the surface of the three-core power cable. The three magnetoelectric sensors are aligned with the line connecting the centers of the three-phase conductors A, B, and C at point O. The magnetic flux density at any point P(R,θ) on the surface of the three-core power cable is the vector sum of the magnetic flux densities of the three-phase conductors A, B, and C at that point.

[0058] B P = B AP + B BP + B CP ;

[0059] According to the Biot - Savart law, the magnetic flux density of each phase conductor at P(R,θ) can be expressed as:

[0060]

[0061] where μ0 is the magnetic permeability of vacuum; D iP (i = A,B,C) is the distance from the center of the three - phase conductor to point P; I i (i = A,B,C) is the current of the three - phase conductor;

[0062] The magnetic field at point P(R,θ) is divided into the tangential magnetic field component B tan and the radial magnetic field component B rad , and these two components are transformed from the magnetic field components in the X - axis direction and Y - axis direction in the XY coordinate system as follows:

[0063]

[0064] where B ix and B iy (i = A,B,C) are the magnetic flux density components in the X - axis direction and Y - axis direction of the three - phase conductor at point P respectively;

[0065] For a three - core power cable with a symmetric structure, assume the center points of the three - phase conductors are as follows:

[0066]

[0067] where R is the distance from point O to the center of the magnetoelectric sensor; r is the distance from point O to the center of the three - phase conductor; α is the ratio of r to R;

[0068] The tangential magnetic field at any point on the surface of the three - core cable is expressed as:

[0069]

[0070] When θ = θ i (i = A,B,C), B tan (θ) reaches the maximum value. Place the three magnetoelectric sensors at the three positions where the tangential magnetic field is the strongest. The magnetic fields at these three positions have the following relationship with the three - phase currents:

[0071]

[0072] S2. According to the Concordia transformation, the tangential magnetic fields B tan1, B tan2 and B tan3 Perform modal transformation and dimensionality reduction processing to obtain the magnetic fields in the α and β modes, and plot B α and B β The curves of the two in polar coordinates, which is called a magnetogram; calculate the cosine similarity of B α and B β , the signal power of B α , the signal power of B β , and the sum of the signal powers of the two;

[0073] In step S2, according to the Concordia transformation, the tangential magnetic fields B tan1 , B tan2 and B tan3 at three positions are subjected to modal transformation and dimensionality reduction processing to obtain the magnetic fields B α and B β in the α and β modes;

[0074]

[0075] The studied short-circuit fault types include ten short-circuit faults: single-phase ground short-circuit (LG): divided into AG, BG, CG; two-phase short-circuit (LL): divided into AB, BC, AC; two-phase ground short-circuit (LLG): divided into ABG, BCG, ACG; and three-phase ground short-circuit (ABCG), a total of ten short-circuit faults, where A, B, and C represent the A-phase, B-phase, and C-phase in a three-phase circuit.

[0076] Figure 3 are the waveforms and magnetograms of B α and B β in the three short-circuit cases (AG, BG, CG) of LG.

[0077] It can be observed that after the fault occurs, after a transient fluctuation of one cycle, the waveform stabilizes again. Therefore, the following description of the waveform characteristics after the fault and the analysis of the magnetogram are only based on the waveform in the second cycle after the fault. It can be seen that:

[0078] Before the fault, the amplitudes of B α and B β are equal, the phase difference between B α and B β is 90°, and the shape of the magnetogram is circular.

[0079] After the AG fault, the amplitude of waveform B[[ID=6l]] α is greater than the amplitude of B β , the phase difference between B α and B β is between 0 - 90°, and the magnetogram is an ellipse, and the long axis of the ellipse faces the first and third quadrants.

[0080] Waveform B after BG fault α The amplitude is similar to B β in amplitude, and B α and B β The phase difference between them is between 90° and 180°, and the magnetic map is also an ellipse, and the long axis of the ellipse points to the second and fourth quadrants.

[0081] Waveform B after CG fault α The amplitude is less than B β in amplitude, and B α and B β The phase difference between them is between 0° and 90°, and the magnetic map is also an ellipse, and the long axis of the ellipse points to the first and third quadrants.

[0082] The elliptical magnetic maps after AG, BG, and CG faults are of equal size.

[0083] Therefore, it can be analyzed that B α and B β The amplitude and the phase difference between them affect the shape of the magnetic map and the orientation of the long axis of the ellipse.

[0084] Then, different types of short - circuit faults are discussed. Considering that analyzing ten short - circuit faults together is likely to cause confusion. Therefore, examples are taken for illustration. That is, for LG, AG is taken as an example; for LL, AB is taken as an example; for LLG, ABG is taken as an example, and ABCG. Figure 4 These are the waveforms of B α and B β and the magnetic maps during these four short - circuit faults.

[0085] It can be seen that: After AG fault, the waveform of B α has an amplitude greater than B β in amplitude, and B α and B β The phase difference between them is between 0° and 90°, and the magnetic map is an ellipse, and the long axis of the ellipse points to the first and third quadrants.

[0086] After AB fault, the waveform of B α has an amplitude greater than B β in amplitude, and B α and B β The phase difference between them is between 90° and 180°, and the magnetic map is an ellipse, and the long axis of the ellipse points to the second and fourth quadrants.

[0087] After ABG fault, the waveform of B α has an amplitude greater than B β in amplitude, and B α and B β The phase difference between them is between 90° and 180°, and the magnetic map is an ellipse, and the long axis of the ellipse points to the first and third quadrants.

[0088] Waveform B after ABCG faultα The amplitude is equal to B β Amplitude, B α With B β The phase difference is 90°, and the shape of the magnetic map is circular.

[0089] The sizes of the magnetic maps under AG, AB, ABG, and ABCG are not equal.

[0090] From Figures 3 - 4 the analysis, it can be seen that B α and B β The waveform amplitude sizes and the phase differences between them will affect the shape and size of the magnetic map after the fault. Therefore, cosine similarity is proposed to measure the phase difference relationship between the waveforms of B α and B β and signal power is used to calculate the waveform size of B α and B β

[0091] In step S2, cosine similarity measures the similarity between two vectors by measuring the cosine of the angle between them, and its value is between -1 and 1. The purpose of cosine similarity is to measure the directional difference between two vectors, which is independent of the length of the vectors, and its definition is:

[0092]

[0093] The cosine similarity CS between B α and B β obtained after the Concordia transformation is defined as:

[0094]

[0095] Taking one cycle (T = 0.02s) as the calculation basis, based on Figure 4 the waveforms, calculate the cosine similarity between B α and B β before and after the fault for each short-circuit fault, and then plot the calculation results as a dot-line graph. Figure 5 Dot-line graphs of the cosine similarity for LG (taking AG as an example), LL (taking AB as an example), LLG (taking ABG as an example), and ABCG faults are given.

[0096] Figure 5 It shows that the cosine similarity before the fault is equal to 0. After the short-circuit fault occurs, the cosine similarity changes and reaches a steady state after 1 cycle of transient transition. At steady state, the cosine similarity values of AG, AB, ABG, and ABCG are different.

[0097] ​In step S2, for a general signal, the signal power is calculated as the sum of the squares of the signal divided by the signal length. If the signal is periodic, the signal power can be calculated by calculating the energy of the signal within one period and dividing it by the length N of the signal:

[0098]

[0099] Calculate the signal power P in a single cycle α With P β , and both power and P s :

[0100]

[0101] Then, based on Figure 4 The waveform of Figure 6 The signal power P from before the fault to LG (AG as an example), LL (AB as an example), LLG (ABG as an example) and ABCG faults is plotted. α 、P β and P s Point-line graph.

[0102] Four types of post-fault steady-state P α The sizes are not equal, but some are close and some are quite different. β and P s The same situation exists.

[0103] Finally, based on B α With B β The waveform of the second cycle after the fault is calculated for CS and P under ten short-circuit faults. α , P β and P s , forming a fault feature dataset. Then, considering different combinations of fault locations and fault resistances, 50 samples are obtained for each short-circuit fault type, and the normal state (N) is also taken into consideration for comparison.

[0104] S3. Based on the extracted fault feature data, the random forest algorithm is used to identify the short circuit fault type.

[0105] The random forest algorithm achieved an accuracy of 99.45% and took 0.05 seconds to classify. The confusion matrix is shown below, where the values on the diagonal represent correctly classified samples and the values on the off-diagonal represent incorrectly classified samples.

[0106] Therefore, the present invention adopts the above non-invasive classification method for short-circuit faults of a three-core cable, uses a magnetoelectric sensor with strong anti-interference ability and high sensitivity to detect the magnetic field change on the surface of the three-core cable, and uses the Concordia transform to perform modal transformation on the three magnetic fields measured by the magnetoelectric sensor array to generate magnetic fields B α and B β , and draws the graphs of the two in polar coordinates, which is called a magnetogram; according to the waveform signals and magnetogram features of magnetic fields B α and B β , four fault features are extracted based on signal power and cosine similarity, and then a feature data set is obtained; finally, the random forest algorithm is used for the fault feature data set to achieve the classification of short-circuit fault types.

[0107] The above embodiments are only used to illustrate the technical solutions of the present invention and are not intended to limit them. Although the present invention has been described in detail with reference to the preferred embodiments, those of ordinary skill in the art should understand that they can still modify the technical solutions of the present invention or make equivalent replacements, and these modifications or equivalent replacements cannot make the modified technical solutions deviate from the spirit and scope of the technical solutions of the present invention.

Claims

1. A non-invasive classification method for three-core cable short-circuit faults, characterized in that: The following steps are involved: S1. Create an experimental platform and use three magnetoelectric sensors in the experimental platform to measure the tangential magnetic field on the surface of the three-core power cable. Place three magnetoelectric sensors on the surface of the three-core power cable, with the three sensors 120 degrees apart from each other. S2, according to Concordia transformation, the tangential magnetic field B at three positions tan1 、B tan2 and B tan3 Perform modal transformation and dimensionality reduction to obtain the magnetic field under α and β modes, and draw B α With B β The curves of the two in polar coordinates are called magnetic diagrams; calculate each short circuit fault B α With B β The cosine similarity of B α The signal power, B β The signal power of and the sum of the signal powers of the two; S3. Based on the extracted fault feature data, the random forest algorithm is used to identify the short circuit fault type.

2. The non-invasive classification method for a three-core cable short-circuit fault according to claim 1 is characterized in that: In step S1, the experimental platform includes a three-phase programmable AC power supply, a filtering and signal amplification module, an oscilloscope, a three-phase resistive load, a magnetoelectric sensor array, and a three-core power cable; The magnetoelectric sensor is made of two magnetostrictive layers and a piezoelectric layer in the middle, which are bonded together with epoxy resin glue and pressed in a hot press. Copper wires are then drawn out from both ends of the magnetostrictive layers. A single magnetoelectric sensor is packaged and fixed with a 3D printed plastic shell and a permanent magnet is added. Three magnetoelectric sensors are mounted on the surface of a three-core power cable using a 3D printed fixture. The magnetoelectric sensors measure 26mm×6mm×1mm.

3. The non-invasive classification method for a three-core cable short-circuit fault according to claim 1, characterized in that: In step S1, O is the center point of the three-core cable, A, B, and C are three-phase conductors, and the coordinates of the centers of the three-phase conductors are (r A ,θ A ), (r B ,θ B ) and (r C ,θ C ), three magnetoelectric sensors are placed on the surface of the three-core power cable. The three magnetoelectric sensors are aligned with the line connecting the centers of the three-phase conductors A, B, and C at point O. The magnetic flux density at any point P(R,θ) on the surface of the three-core power cable is the vector sum of the magnetic flux densities of the three-phase conductors A, B, and C at that point. B P =B AP +B BP +B CP ; According to the Biot-Savart law, the magnetic flux density of each phase conductor at P(R,θ) can be expressed as: Where μ0 is the vacuum permeability; D iP (i=A, B, C) is the distance from the center of the three-phase conductor to point P; I i (i=A, B, C) is the three-phase conductor current; The magnetic field at point P(R,θ) is divided into the tangential magnetic field component B tan and the radial magnetic field component B rad , these two components are transformed from the X-axis magnetic field component and the Y-axis magnetic field component in the XY coordinate system as follows: Among them, B ix and B iy (i=A, B, C) are the magnetic flux density components in the X-axis and Y-axis directions of the three-phase conductors at point P respectively; For a three-core power cable with a symmetrical structure, it is assumed that the center points of the three-phase conductors are as follows: Where R is the distance from point O to the center of the magnetoelectric sensor; r is the distance from point O to the center of the three-phase conductor; α is the ratio of r to R; The tangential magnetic field at any point on the surface of a three-core cable is expressed as: When θ=θ i (i=A,B,C), B tan (θ) is maximized, and three magnetoelectric sensors are placed at the three locations where the tangential magnetic field is strongest. The magnetic field at these three locations has the following relationship with the three-phase current:

4. The non-invasive classification method for a three-core cable short-circuit fault according to claim 1, characterized in that: In step S2, the tangential magnetic fields B at the three locations are transformed into tan1 、B tan2 and B tan3 Perform modal transformation and dimensionality reduction to obtain the magnetic field B under α and β modes α With B β :

5. The non-invasive classification method for a three-core cable short-circuit fault according to claim 1, characterized in that: In step S2, the purpose of cosine similarity is to measure the directional difference between two vectors. It is independent of the length of the vector. For two n-dimensional vectors a={x1,x2,…,x n } and b={y1,y2,…,y n The cosine similarity cosθ of} is defined as: B obtained after Concordia transformation α With B β The cosine similarity CS between is defined as:

6. The non-invasive classification method for three-core cable short-circuit fault according to claim 1, characterized in that: In step S2, if the signal is a periodic signal, the signal power can be obtained by calculating the energy of the signal within one period and dividing it by the length N of the signal: Calculate the signal power P in each single cycle α With P β , and both power and P s :

Images