Cable fault detection method and system

Abstract

The invention provides a cable fault detection method which comprises the following steps: acquiring waveforms of an incident wave and a reflected wave of a cable to be detected so as to obtain delay time, reflection amplitude and polarity of the reflected wave relative to the incident wave and an energy ratio of the incident wave; wherein the delay time is the difference between the incident wave transmitting time and the first receiving time of the reflected wave; the reflection amplitude is the ratio of the reflection wave amplitude to the incident wave amplitude; the polarities comprise the positive polarity with the same phase of the reflected wave and the incident wave and the negative polarity with the different phase of the reflected wave and the incident wave; the energy ratio is the ratio of the tail waveform energy of the incident wave to the overall waveform energy; and the delay time, the reflection amplitude, the polarity and the energy ratio are imported into a trained SVM model, and the fault type of the cable to be detected is an open-circuit fault, a short-circuit fault, a thermal aging fault or a damp fault. By implementing the method, the limitation of a traditional detection method can be solved, the outage risk of a power system is reduced, the maintenance cost is reduced, and the reliability and stability of power transmission are improved.

Description

Technical Field

[0001] The present invention relates to the technical field of power detection, and in particular to a cable fault detection method and system. Background Art

[0002] With the increasing complexity and intelligence of power systems, cables, as a key component of power systems, undertake important tasks in power transmission and distribution. However, cables may fail during long-term operation due to a variety of factors (such as mechanical damage, environmental factors, aging, overload, etc.). If these failures are not discovered and handled in time, they may cause the shutdown of the power system and even cause major safety accidents. Therefore, how to quickly and accurately detect and locate cable faults has become a technical problem that needs to be solved in the power system.

[0003] At present, traditional cable fault detection methods, such as time domain reflectometry (TDR) and DC test (DC Test), can identify faults to a certain extent, but they usually rely on fixed detection methods and threshold settings, and are difficult to cope with complex fault types and environmental changes.

[0004] Therefore, with the introduction of intelligent algorithms, it is necessary to design a new cable fault detection method that can address the limitations of traditional detection methods, reduce the risk of power system outages, reduce maintenance costs, and improve the reliability and stability of power transmission. Summary of the invention

[0005] The technical problem to be solved by the embodiments of the present invention is to provide a cable fault detection method and system, which can solve the limitations of traditional detection methods, reduce the risk of power system shutdown, reduce maintenance costs, and improve the reliability and stability of power transmission.

[0006] In order to solve the above technical problem, an embodiment of the present invention provides a cable fault detection method, which includes the following steps:

[0007] Obtain the incident wave waveform and reflected wave waveform of the cable to be tested to obtain the delay time, reflection amplitude and polarity of the reflected wave relative to the incident wave, and the energy proportion of the incident wave; wherein the delay time is the difference between the incident wave emission time and the first reception time of the reflected wave; the reflection amplitude is the ratio between the reflected wave amplitude and the incident wave amplitude; the polarity includes a positive polarity for characterizing that the reflected wave and the incident wave have the same phase and a negative polarity for characterizing that the reflected wave and the incident wave have different phases; the energy proportion is the proportion of the tail waveform energy of the incident wave to the overall waveform energy;

[0008] The delay time, reflection amplitude and polarity of the reflected wave relative to the incident wave, and the energy proportion of the incident wave are all imported into the trained SVM model to obtain the fault type of the cable to be tested; wherein the fault type includes open circuit fault, short circuit fault, thermal aging fault and moisture fault.

[0009] Wherein, the method further comprises:

[0010] The fault location of the cable under test is calculated based on the delay time of the reflected wave relative to the incident wave and a given wave propagation velocity, wherein the wave propagation velocity is determined by the material type and dielectric constant of the cable under test.

[0011] Among them, through the formula γ tail =E tail / E total , calculate the energy proportion γ tail ;in,

[0012] E total is the overall waveform energy of the incident wave, and E tail is the waveform energy of the incident wave tail, and t end is the end time of the incident wave; t cut It is the moment when the peak value of the main pulse drops to 10% of the peak value.

[0013] The embodiment of the present invention further provides another cable fault detection method, the method comprising the following steps:

[0014] Obtain the incident wave waveform and reflected wave waveform of the cable to be tested to obtain the delay time, reflection amplitude and polarity of the reflected wave relative to the incident wave, and the energy proportion of the incident wave; wherein the delay time is the difference between the incident wave emission time and the first reception time of the reflected wave; the reflection amplitude is the ratio between the reflected wave amplitude and the incident wave amplitude; the polarity includes a positive polarity for characterizing that the reflected wave and the incident wave have the same phase and a negative polarity for characterizing that the reflected wave and the incident wave have different phases; the energy proportion is the proportion of the tail waveform energy of the incident wave to the overall waveform energy;

[0015] The delay time, reflection amplitude and polarity of the reflected wave relative to the incident wave, and the energy proportion of the incident wave are introduced into the preset intelligent decision-making classification rules to obtain the fault type of the cable to be tested; wherein the fault type includes open circuit fault, short circuit fault, thermal aging fault and moisture fault.

[0016] The specific steps of importing the delay time, reflection amplitude and polarity of the reflected wave relative to the incident wave and the energy proportion of the incident wave into the preset intelligent decision classification rules to obtain the fault type of the cable to be tested include:

[0017] If the reflection amplitude is greater than a first threshold, the delay time is less than a preset first delay, the polarity is positive, and the energy proportion is less than a first percentage, then the fault type of the cable to be tested is an open circuit fault;

[0018] If the reflection amplitude is less than the second threshold and greater than the third threshold, the delay time is greater than the preset second delay, and the energy proportion is greater than the second percentage, then the fault type of the cable to be tested is a moisture fault;

[0019] If the reflection amplitude is less than the fourth threshold and greater than the fifth threshold, the delay time is less than the second delay and greater than the preset third delay, and the energy proportion is less than the second percentage and greater than the third percentage, then the fault type of the cable to be tested is a thermal aging fault;

[0020] If the reflection amplitude is less than the sixth threshold, the delay time is less than the first time delay, the polarity is negative, and the energy proportion is less than the first percentage, then the fault type of the cable to be tested is a short circuit fault;

[0021] Among them, the first threshold>the second threshold>the fourth threshold>the third threshold>the fifth threshold>the sixth threshold;

[0022] The second percentage>the third percentage>the first percentage;

[0023] The second delay>the third delay>the first delay.

[0024] Wherein, the method further comprises:

[0025] The fault location of the cable under test is calculated based on the delay time of the reflected wave relative to the incident wave and a given wave propagation velocity, wherein the wave propagation velocity is determined by the material type and dielectric constant of the cable under test.

[0026] The embodiment of the present invention further provides another cable fault detection method, the method comprising the following steps:

[0027] Obtaining the incident wave waveform and the reflected wave waveform of the cable to be tested, as well as the current signal and the voltage signal of the cable to be tested;

[0028] A decision tree analysis is performed based on the incident wave waveform, reflected wave waveform, current signal and voltage signal of the cable to be tested to obtain the fault type of the cable to be tested; wherein the fault type includes open circuit fault, short circuit fault and ground fault.

[0029] The specific steps of performing decision tree analysis based on the incident wave waveform, reflected wave waveform, current signal and voltage signal of the cable to be tested to obtain the fault type of the cable to be tested include:

[0030] Detecting the amplitude of the current signal of the cable to be tested;

[0031] When it is detected that the amplitude of the current signal is greater than a preset current threshold, if it is detected that the reflection amplitude formed between the reflected wave and the incident wave is greater than a preset first threshold, then the fault type of the cable under test is an open circuit fault; or, if it is detected that the reflection amplitude is less than the first threshold, then the fault type of the cable under test is a short circuit fault; wherein the reflection amplitude is the ratio between the reflected wave amplitude and the incident wave amplitude;

[0032] When it is detected that the amplitude of the current signal is less than or equal to the current threshold, if it is detected that the voltage signal of the cable to be tested has a sudden change and the mutation amplitude is greater than a preset second threshold, then the fault type of the cable to be tested is a ground fault; or, if it is detected that the voltage signal of the cable to be tested has a sudden change and the mutation amplitude is less than the second threshold, then the fault of the cable to be tested does not exist.

[0033] Wherein, the method further comprises:

[0034] Based on the incident wave waveform and the reflected wave waveform, the delay time of the reflected wave relative to the incident wave is obtained, and combined with a given wave propagation speed, the fault point position of the cable to be tested is calculated; wherein the wave propagation speed is determined by the material type and dielectric constant of the cable to be tested; and the delay time is the difference between the incident wave emission time and the first reception time of the reflected wave.

[0035] The embodiment of the present invention further provides a cable fault detection system, comprising:

[0036] A cable parameter calculation unit, used to obtain the incident wave waveform and the reflected wave waveform of the cable to be tested, so as to obtain the delay time, reflection amplitude and polarity of the reflected wave relative to the incident wave, and the energy proportion of the incident wave; wherein the delay time is the difference between the incident wave emission time and the first reception time of the reflected wave; the reflection amplitude is the ratio between the reflected wave amplitude and the incident wave amplitude; the polarity includes a positive polarity for characterizing that the reflected wave and the incident wave have the same phase and a negative polarity for characterizing that the reflected wave and the incident wave have different phases; the energy proportion is the proportion of the tail waveform energy of the incident wave to the overall waveform energy;

[0037] The cable fault detection unit is used to import the delay time, reflection amplitude and polarity of the reflected wave relative to the incident wave and the energy proportion of the incident wave into the trained SVM model to obtain the fault type of the cable to be tested; wherein the fault type includes open circuit fault, short circuit fault, thermal aging fault and moisture fault.

[0038] Implementing the embodiments of the present invention has the following beneficial effects:

[0039] The present invention can quickly analyze the cable fault type through intelligent algorithms such as SVM models, intelligent decision-making classification rules and decision trees, thereby solving the limitations of traditional detection methods, reducing the risk of power system shutdown, reducing maintenance costs, and improving the reliability and stability of power transmission. BRIEF DESCRIPTION OF THE DRAWINGS

[0040] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, without paying creative labor, other drawings obtained based on these drawings still belong to the scope of the present invention.

[0041] Figure 1 A flow chart of a cable fault detection method provided by an embodiment of the present invention;

[0042] Figure 2 A flowchart of another cable fault detection method provided by an embodiment of the present invention;

[0043] Figure 3 A flowchart of another cable fault detection method provided by an embodiment of the present invention;

[0044] Figure 4 for Figure 3 A schematic diagram of the structure of the decision tree in step S32;

[0045] Figure 5 A schematic structural diagram of a cable fault detection system provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0046] In order to make the objectives, technical solutions and advantages of the present invention more clear, the present invention will be further described in detail below with reference to the accompanying drawings.

[0047] like Figure 1 As shown in the figure, a cable fault detection method is provided in an embodiment of the present invention, and the method comprises the following steps:

[0048] Step S11, obtaining the incident wave waveform and the reflected wave waveform of the cable to be tested, so as to obtain the delay time, reflection amplitude and polarity of the reflected wave relative to the incident wave, and the energy proportion of the incident wave; wherein the delay time is the difference between the incident wave emission time and the first reception time of the reflected wave; the reflection amplitude is the ratio between the reflected wave amplitude and the incident wave amplitude; the polarity includes a positive polarity for characterizing that the reflected wave and the incident wave have the same phase and a negative polarity for characterizing that the reflected wave and the incident wave have different phases; the energy proportion is the proportion of the tail waveform energy of the incident wave to the overall waveform energy;

[0049] Step S12, the delay time of the reflected wave relative to the incident wave, the reflection amplitude and polarity, and the energy proportion of the incident wave are imported into the trained SVM model to obtain the fault type of the cable to be tested; wherein the fault type includes open circuit fault, short circuit fault, thermal aging fault and moisture fault.

[0050] The specific process is that in step S11, an incident signal is transmitted to the cable to be tested and a reflected signal is received by the TDR instrument, so that the incident wave waveform and its running time, and the reflected wave waveform and its running time recorded by the TDR instrument can be obtained in real time.

[0051] According to the waveform of the incident wave and the waveform of the reflected wave, the emission time of the incident wave and the first reception time of the reflected wave can be extracted, and the difference between the two can be calculated to determine the delay time of the reflected wave relative to the incident wave;

[0052] By formula That is, the reflected wave amplitude A refl With the incident wave amplitude A in The reflection amplitude A is obtained by the ratio between norm ;

[0053] The polarity is determined as positive polarity, which indicates that the reflected wave and the incident wave have the same phase, or negative polarity, which indicates that the reflected wave and the incident wave have different phases. Of course, the reflected wave amplitude A can also be used to determine the reflected wave amplitude. norm Greater than 0 means positive polarity, the reflected wave amplitude is A norm If it is less than 0, it is negative polarity and the polarity is determined;

[0054] By formula γ tail =E tail / E total , calculate the energy proportion of the tail waveform of the incident wave in the overall waveform γ tail ; Among them, E total is the overall waveform energy of the incident wave, and E tail is the waveform energy of the incident wave tail, and t end is the end time of the incident wave; t cutThe moment when the peak value of the main pulse drops to 10% of the peak value. Of course, the overall waveform energy E of the incident wave total and the incident wave tail waveform energy E tail It can also be calculated using a discrete formula, which will not be described here.

[0055] It should be noted that the thermal aging phenomenon is that the insulating material degrades due to high temperature, resulting in local cracks or air gaps, which leads to impedance discontinuity, causing the signal to be reflected multiple times at the defects, and discrete reflected pulses appearing at the tail of the waveform. The energy decays slowly and the tail energy ratio increases.

[0056] The phenomenon of moisture is that moisture increases the dielectric constant of insulation, resulting in an increase in distributed capacitance, and the high-frequency components of the signal are absorbed, causing the reflected signal to exhibit a "tailing" phenomenon of continuous attenuation (similar to the low-pass filtering effect), and the tail energy lasts longer.

[0057] In step S12, first, construct an SVM model with a multi-dimensional feature vector input, and construct a sample data set accordingly. Each sample corresponds to a known fault type (such as open circuit, short circuit, thermal aging, moisture, etc.). Use the labeled training data (features of different types of faults) to train the SVM model. Select a suitable kernel function (such as RBF kernel) and penalty parameter C, optimize the classification boundary of SVM, and thus obtain a trained SVM model; wherein the multi-dimensional feature vector includes delay time, reflection amplitude, polarity, and energy proportion, etc.

[0058] Secondly, the delay time, reflection amplitude and polarity of the reflected wave relative to the incident wave and the energy proportion of the incident wave obtained in step S11 are all imported into the trained SVM model, and the fault type of the cable to be tested can be obtained as one of open circuit fault, short circuit fault, thermal aging fault and moisture fault.

[0059] In an embodiment of the present invention, the method further comprises: calculating the fault point position of the cable to be tested according to the delay time of the reflected wave relative to the incident wave and in combination with a given wave propagation speed; wherein the wave propagation speed is determined by the material type and dielectric constant of the cable to be tested, for example Among them, ε r is the dielectric constant; c is the wave speed in vacuum.

[0060] That is, through the formula Get the fault point location L of the cable to be tested; where v is the given wave propagation speed, t d is the delay time.

[0061] like Figure 2 As shown in the figure, another cable fault detection method is provided in an embodiment of the present invention, and the method comprises the following steps:

[0062] Step S21, obtaining the incident wave waveform and the reflected wave waveform of the cable to be tested, so as to obtain the delay time, reflection amplitude and polarity of the reflected wave relative to the incident wave, and the energy proportion of the incident wave; wherein the delay time is the difference between the incident wave emission time and the first reception time of the reflected wave; the reflection amplitude is the ratio between the reflected wave amplitude and the incident wave amplitude; the polarity includes a positive polarity for characterizing that the reflected wave and the incident wave have the same phase and a negative polarity for characterizing that the reflected wave and the incident wave have different phases; the energy proportion is the proportion of the tail waveform energy of the incident wave to the overall waveform energy;

[0063] Step S22, the delay time, reflection amplitude and polarity of the reflected wave relative to the incident wave, and the energy proportion of the incident wave are introduced into a preset intelligent decision-making classification rule to obtain the fault type of the cable to be tested; wherein the fault type includes open circuit fault, short circuit fault, thermal aging fault and moisture fault.

[0064] The specific process is that in step S21, an incident signal is transmitted to the cable to be tested and a reflected signal is received by the TDR instrument, so that the incident wave waveform and its running time, and the reflected wave waveform and its running time recorded by the TDR instrument can be obtained in real time.

[0065] According to the waveform of the incident wave and the waveform of the reflected wave, the emission time of the incident wave and the first reception time of the reflected wave can be extracted, and the difference between the two can be calculated to determine the delay time of the reflected wave relative to the incident wave;

[0066] By formula That is, the reflected wave amplitude A refl With the incident wave amplitude A in The reflection amplitude A is obtained by the ratio between norm ;

[0067] The polarity is determined as positive polarity, which indicates that the reflected wave and the incident wave have the same phase, or negative polarity, which indicates that the reflected wave and the incident wave have different phases. Of course, the reflected wave amplitude A can also be used to determine the reflected wave amplitude. norm Greater than 0 means positive polarity, the reflected wave amplitude is A norm If it is less than 0, it is negative polarity and the polarity is determined;

[0068] By formula γ tail =E tail / E total , calculate the energy proportion of the tail waveform of the incident wave in the overall waveform γ tail ; Among them, E total is the overall waveform energy of the incident wave, and E tail is the incident wave tail waveform energy, and t end is the end time of the incident wave; tcut The moment when the peak value of the main pulse drops to 10% of the peak value. Of course, the overall waveform energy E of the incident wave total and the incident wave tail waveform energy E tail It can also be calculated using a discrete formula, which will not be described here.

[0069] It should be noted that the thermal aging phenomenon is that the insulating material degrades due to high temperature, resulting in local cracks or air gaps, which leads to impedance discontinuity, causing the signal to be reflected multiple times at the defects, and discrete reflected pulses appearing at the tail of the waveform. The energy decays slowly and the tail energy ratio increases.

[0070] The phenomenon of moisture is that moisture increases the dielectric constant of insulation, resulting in an increase in distributed capacitance, and the high-frequency components of the signal are absorbed, causing the reflected signal to exhibit a "tailing" phenomenon of continuous attenuation (similar to the low-pass filtering effect), and the tail energy lasts longer.

[0071] In step S22, first, multiple comparison thresholds, percentages and delays are set for subsequent formulation of intelligent decision-making classification rules, such as the first threshold 0.8> the second threshold 0.6> the fourth threshold 0.5> the third threshold 0.3> the fifth threshold 0.2> the sixth threshold -0.8; the second percentage 15%> the third percentage 5%> the first percentage 0%; the second delay 200s> the third delay 10s> the first delay 0.1s;

[0072] Secondly, in the intelligent decision-making classification rule, if the reflection amplitude A norm Greater than the first threshold 0.8, delay time t d Less than the first delay 0.1s, positive polarity, and energy proportion γ tail When it is less than the first percentage 0% (i.e., no tailing or multiple reflections), the fault type of the cable to be tested is an open circuit fault;

[0073] In the intelligent decision-making classification rule, if the reflection amplitude A norm Less than the second threshold 0.6 and greater than the third threshold 0.3, delay time t d Greater than the second delay 200s, and energy proportion γ tail When it is greater than the second percentage of 15%, the fault type of the tested cable is obtained as a moisture fault;

[0074] In the intelligent decision-making classification rule, if the reflection amplitude A norm Less than the fourth threshold 0.5 and greater than the fifth threshold 0.2, delay time t d Less than the second delay 200s and greater than the third delay 10s, and energy proportion γ tail When it is less than the second percentage of 15% and greater than the third percentage of 5%, the fault type of the tested cable is obtained as a thermal aging fault;

[0075] In the intelligent decision-making classification rule, if the reflection amplitude A norm Less than the sixth threshold -0.8, delay time t d Less than the first delay 0.1s, negative polarity, and energy proportion γ tail When it is less than the first percentage 0% (i.e., no tailing or multiple reflections), the fault type of the tested cable is obtained as a short circuit fault;

[0076] In one example, as shown in Table 1 below, intelligent decision classification rules for open circuit faults, short circuit faults, thermal aging faults, and moisture faults are shown.

[0077] Table 1

[0078]

[0079] In an embodiment of the present invention, the method further comprises: calculating the fault point position of the cable to be tested according to the delay time of the reflected wave relative to the incident wave and in combination with a given wave propagation speed; wherein the wave propagation speed is determined by the material type and dielectric constant of the cable to be tested, for example Among them, ε r is the dielectric constant; c is the wave speed in vacuum.

[0080] That is, through the formula Get the fault point location L of the cable to be tested; where v is the given wave propagation speed, t d is the delay time.

[0081] like Figure 3 As shown in the figure, another cable fault detection method is provided in an embodiment of the present invention, and the method comprises the following steps:

[0082] Step S31, obtaining the incident wave waveform and the reflected wave waveform of the cable to be tested, as well as the current signal and the voltage signal of the cable to be tested;

[0083] Step S32: Perform decision tree analysis based on the incident wave waveform, reflected wave waveform, current signal and voltage signal of the cable to be tested to obtain the fault type of the cable to be tested; wherein the fault type includes open circuit fault, short circuit fault and ground fault.

[0084] The specific process is as follows: in step S31, the TDR instrument transmits an incident signal to the cable to be tested and receives a reflected signal, so that the incident wave waveform and its running time, the reflected wave waveform and its running time recorded by the TDR instrument can be obtained in real time. In addition, the current signal and voltage signal of the cable to be tested are obtained respectively through the current and voltage sensors.

[0085] It is understandable that, based on the incident wave waveform and the reflected wave waveform, the incident wave emission time and the reflected wave first reception time can be extracted, and the difference between the two can be calculated to determine the delay time of the reflected wave relative to the incident wave.

[0086] In step S32, first, by formula That is, the reflected wave amplitude A refl With the incident wave amplitude A in The reflection amplitude A is obtained by the ratio between norm ; and, detecting whether a mutation occurs by observing the voltage change of the voltage signal.

[0087] Secondly, build a decision tree (such as Figure 4 As shown), and according to the incident wave waveform, reflected wave waveform, current signal and voltage signal of the cable to be tested, the specific fault types of the cable to be tested are analyzed and obtained, including:

[0088] Detecting the amplitude of the current signal of the cable to be tested;

[0089] When the amplitude of the current signal is detected to be greater than the preset current threshold (such as 10A), if the reflection amplitude A formed between the reflected wave and the incident wave is detected norm If the reflection amplitude A is greater than the first threshold value (such as 1), the fault type of the cable under test is an open circuit fault; or norm is less than a first threshold value (such as 1), then the fault type of the cable to be tested is a short circuit fault;

[0090] When it is detected that the amplitude of the current signal is less than or equal to the current threshold (such as 10A), if it is detected that the voltage signal of the cable to be tested has a sudden change and the mutation amplitude is greater than a preset second threshold (such as 5V), then the fault type of the cable to be tested is a ground fault; or, if it is detected that the voltage signal of the cable to be tested has a sudden change and the mutation amplitude is less than the second threshold (such as 5V), then the fault of the cable to be tested does not exist.

[0091] In an embodiment of the present invention, the method further comprises: obtaining a delay time of the reflected wave relative to the incident wave based on the incident wave waveform and the reflected wave waveform, and calculating the fault point position of the cable to be tested according to the delay time of the reflected wave relative to the incident wave and in combination with a given wave propagation speed; wherein the wave propagation speed is determined by the material type and dielectric constant of the cable to be tested, for example Among them, ε r is the dielectric constant; c is the wave speed in vacuum.

[0092] That is, through the formula Get the fault point location L of the cable to be tested; where v is the given wave propagation speed, t dis the delay time, which is the difference between the time when the incident wave is emitted and the time when the reflected wave is first received.

[0093] like Figure 5 As shown in the figure, a cable fault detection system is provided in an embodiment of the present invention, comprising:

[0094] The cable parameter calculation unit 110 is used to obtain the incident wave waveform and the reflected wave waveform of the cable to be tested, so as to obtain the delay time, reflection amplitude and polarity of the reflected wave relative to the incident wave, and the energy proportion of the incident wave; wherein the delay time is the difference between the incident wave emission time and the first reception time of the reflected wave; the reflection amplitude is the ratio between the reflected wave amplitude and the incident wave amplitude; the polarity includes a positive polarity for characterizing that the reflected wave and the incident wave have the same phase and a negative polarity for characterizing that the reflected wave and the incident wave have different phases; the energy proportion is the proportion of the tail waveform energy of the incident wave to the overall waveform energy;

[0095] The cable fault detection unit 120 is used to import the delay time, reflection amplitude and polarity of the reflected wave relative to the incident wave and the energy proportion of the incident wave into the trained SVM model to obtain the fault type of the cable to be tested; wherein the fault type includes open circuit fault, short circuit fault, thermal aging fault and moisture fault.

[0096] Implementing the embodiments of the present invention has the following beneficial effects:

[0097] The present invention can quickly analyze the cable fault type through intelligent algorithms such as SVM models, intelligent decision-making classification rules and decision trees, thereby solving the limitations of traditional detection methods, reducing the risk of power system shutdown, reducing maintenance costs, and improving the reliability and stability of power transmission.

[0098] It is worth noting that in the above system embodiment, the various system modules included are only divided according to functional logic, but are not limited to the above division, as long as the corresponding functions can be achieved; in addition, the specific names of the various functional modules are only for the convenience of distinguishing each other, and are not used to limit the scope of protection of the present invention.

[0099] A person skilled in the art can understand that all or part of the steps in the above-mentioned embodiment method can be completed by instructing related hardware through a program, and the program can be stored in a computer-readable storage medium, such as ROM / RAM, disk, CD-ROM, etc.

[0100] The above disclosure is only the preferred embodiment of the present invention, which certainly cannot be used to limit the scope of the present invention. Therefore, equivalent changes made according to the claims of the present invention are still within the scope of the present invention.

Claims

1. A cable fault detection method, characterized in that: The method comprises the following steps: Obtain the incident wave waveform and reflected wave waveform of the cable to be tested to obtain the delay time, reflection amplitude and polarity of the reflected wave relative to the incident wave, and the energy proportion of the incident wave; wherein the delay time is the difference between the incident wave emission time and the first reception time of the reflected wave; the reflection amplitude is the ratio between the reflected wave amplitude and the incident wave amplitude; the polarity includes a positive polarity for characterizing that the reflected wave and the incident wave have the same phase and a negative polarity for characterizing that the reflected wave and the incident wave have different phases; the energy proportion is the proportion of the tail waveform energy of the incident wave to the overall waveform energy; The delay time, reflection amplitude and polarity of the reflected wave relative to the incident wave, and the energy proportion of the incident wave are all imported into the trained SVM model to obtain the fault type of the cable to be tested; wherein the fault type includes open circuit fault, short circuit fault, thermal aging fault and moisture fault.

2. The cable fault detection method according to claim 1, characterized in that: The method further comprises: The fault location of the cable under test is calculated based on the delay time of the reflected wave relative to the incident wave and a given wave propagation velocity, wherein the wave propagation velocity is determined by the material type and dielectric constant of the cable under test.

3. The cable fault detection method according to claim 2, characterized in that: By formula γ tail =E tail / E total , the energy proportion γ is calculated tail ; in, E total is the overall waveform energy of the incident wave, and E tail is the incident wave tail waveform energy, and t end is the end time of the incident wave; t cut It is the moment when the peak value of the main pulse drops to 10% of the peak value.

4. A cable fault detection method, characterized in that: The method comprises the following steps: Obtain the incident wave waveform and reflected wave waveform of the cable to be tested to obtain the delay time, reflection amplitude and polarity of the reflected wave relative to the incident wave, and the energy proportion of the incident wave; wherein the delay time is the difference between the incident wave emission time and the first reception time of the reflected wave; the reflection amplitude is the ratio between the reflected wave amplitude and the incident wave amplitude; the polarity includes a positive polarity for characterizing that the reflected wave and the incident wave have the same phase and a negative polarity for characterizing that the reflected wave and the incident wave have different phases; the energy proportion is the proportion of the tail waveform energy of the incident wave to the overall waveform energy; The delay time, reflection amplitude and polarity of the reflected wave relative to the incident wave, and the energy proportion of the incident wave are introduced into the preset intelligent decision-making classification rules to obtain the fault type of the cable to be tested; wherein the fault type includes open circuit fault, short circuit fault, thermal aging fault and moisture fault.

5. The cable fault detection method according to claim 4, characterized in that: The specific steps of importing the delay time, reflection amplitude and polarity of the reflected wave relative to the incident wave and the energy proportion of the incident wave into the preset intelligent decision classification rules to obtain the fault type of the cable to be tested include: If the reflection amplitude is greater than a first threshold, the delay time is less than a preset first delay, the polarity is positive, and the energy proportion is less than a first percentage, then the fault type of the cable to be tested is an open circuit fault; If the reflection amplitude is less than the second threshold and greater than the third threshold, the delay time is greater than the preset second delay, and the energy proportion is greater than the second percentage, then the fault type of the cable to be tested is a moisture fault; If the reflection amplitude is less than the fourth threshold and greater than the fifth threshold, the delay time is less than the second delay and greater than the preset third delay, and the energy proportion is less than the second percentage and greater than the third percentage, then the fault type of the cable to be tested is a thermal aging fault; If the reflection amplitude is less than the sixth threshold, the delay time is less than the first time delay, the polarity is negative, and the energy proportion is less than the first percentage, then the fault type of the cable to be tested is a short circuit fault; Among them, the first threshold>the second threshold>the fourth threshold>the third threshold>the fifth threshold>the sixth threshold; The second percentage>the third percentage>the first percentage; The second delay>the third delay>the first delay.

6. The cable fault detection method according to claim 4, characterized in that: The method further comprises: The fault location of the cable under test is calculated based on the delay time of the reflected wave relative to the incident wave and a given wave propagation velocity, wherein the wave propagation velocity is determined by the material type and dielectric constant of the cable under test.

7. A cable fault detection method, characterized in that: The method comprises the following steps: Obtaining the incident wave waveform and the reflected wave waveform of the cable to be tested, as well as the current signal and the voltage signal of the cable to be tested; A decision tree analysis is performed based on the incident wave waveform, reflected wave waveform, current signal and voltage signal of the cable to be tested to obtain the fault type of the cable to be tested; wherein the fault type includes open circuit fault, short circuit fault and ground fault.

8. The cable fault detection method according to claim 7, characterized in that: The specific steps of performing decision tree analysis based on the incident wave waveform, reflected wave waveform, current signal and voltage signal of the cable to be tested to obtain the fault type of the cable to be tested include: Detecting the amplitude of the current signal of the cable to be tested; When it is detected that the amplitude of the current signal is greater than a preset current threshold, if it is detected that the reflection amplitude formed between the reflected wave and the incident wave is greater than a preset first threshold, then the fault type of the cable under test is an open circuit fault; or, if it is detected that the reflection amplitude is less than the first threshold, then the fault type of the cable under test is a short circuit fault; wherein the reflection amplitude is the ratio between the reflected wave amplitude and the incident wave amplitude; When it is detected that the amplitude of the current signal is less than or equal to the current threshold, if it is detected that the voltage signal of the cable to be tested has a sudden change and the mutation amplitude is greater than a preset second threshold, then the fault type of the cable to be tested is a ground fault; or, if it is detected that the voltage signal of the cable to be tested has a sudden change and the mutation amplitude is less than the second threshold, then the fault of the cable to be tested does not exist.

9. The cable fault detection method according to claim 8, characterized in that: The method further comprises: Based on the incident wave waveform and the reflected wave waveform, the delay time of the reflected wave relative to the incident wave is obtained, and combined with a given wave propagation speed, the fault point position of the cable to be tested is calculated; wherein the wave propagation speed is determined by the material type and dielectric constant of the cable to be tested; and the delay time is the difference between the incident wave emission time and the first reception time of the reflected wave.

10. A cable fault detection system, characterized in that: include: A cable parameter calculation unit, used to obtain the incident wave waveform and the reflected wave waveform of the cable to be tested, so as to obtain the delay time, reflection amplitude and polarity of the reflected wave relative to the incident wave, and the energy proportion of the incident wave; wherein the delay time is the difference between the incident wave emission time and the first reception time of the reflected wave; the reflection amplitude is the ratio between the reflected wave amplitude and the incident wave amplitude; the polarity includes a positive polarity for characterizing that the reflected wave and the incident wave have the same phase and a negative polarity for characterizing that the reflected wave and the incident wave have different phases; the energy proportion is the proportion of the tail waveform energy of the incident wave to the overall waveform energy; The cable fault detection unit is used to import the delay time, reflection amplitude and polarity of the reflected wave relative to the incident wave and the energy proportion of the incident wave into the trained SVM model to obtain the fault type of the cable to be tested; wherein the fault type includes open circuit fault, short circuit fault, thermal aging fault and moisture fault.

Images