CN109116196B - Intelligent power cable fault discharge sound identification method - Google Patents
Intelligent power cable fault discharge sound identification method Download PDFInfo
- Publication number
- CN109116196B CN109116196B CN201810737476.1A CN201810737476A CN109116196B CN 109116196 B CN109116196 B CN 109116196B CN 201810737476 A CN201810737476 A CN 201810737476A CN 109116196 B CN109116196 B CN 109116196B
- Authority
- CN
- China
- Prior art keywords
- cable fault
- sound signal
- sound
- data
- fault discharge
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 238000000034 method Methods 0.000 title claims abstract description 42
- 230000005236 sound signal Effects 0.000 claims abstract description 95
- 238000012706 support-vector machine Methods 0.000 claims abstract description 20
- 239000013598 vector Substances 0.000 claims abstract description 20
- 238000006243 chemical reaction Methods 0.000 claims abstract description 5
- 238000012545 processing Methods 0.000 claims description 21
- 238000012549 training Methods 0.000 claims description 12
- 239000011159 matrix material Substances 0.000 claims description 6
- 238000007599 discharging Methods 0.000 claims description 5
- 238000004364 calculation method Methods 0.000 claims description 3
- 238000000605 extraction Methods 0.000 abstract description 5
- 238000001514 detection method Methods 0.000 abstract description 4
- 238000007781 pre-processing Methods 0.000 abstract description 3
- 238000005070 sampling Methods 0.000 abstract description 3
- 238000010586 diagram Methods 0.000 description 12
- 238000010606 normalization Methods 0.000 description 6
- 239000000523 sample Substances 0.000 description 6
- 230000007547 defect Effects 0.000 description 3
- 238000012360 testing method Methods 0.000 description 3
- 230000003321 amplification Effects 0.000 description 2
- 238000003745 diagnosis Methods 0.000 description 2
- 230000005672 electromagnetic field Effects 0.000 description 2
- 230000007613 environmental effect Effects 0.000 description 2
- 238000001914 filtration Methods 0.000 description 2
- 238000005259 measurement Methods 0.000 description 2
- 238000000691 measurement method Methods 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000012544 monitoring process Methods 0.000 description 2
- 238000003199 nucleic acid amplification method Methods 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 230000015556 catabolic process Effects 0.000 description 1
- 238000009413 insulation Methods 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 238000005065 mining Methods 0.000 description 1
- 238000010998 test method Methods 0.000 description 1
- 230000001960 triggered effect Effects 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01R—MEASURING ELECTRIC VARIABLES; MEASURING MAGNETIC VARIABLES
- G01R31/00—Arrangements for testing electric properties; Arrangements for locating electric faults; Arrangements for electrical testing characterised by what is being tested not provided for elsewhere
- G01R31/12—Testing dielectric strength or breakdown voltage ; Testing or monitoring effectiveness or level of insulation, e.g. of a cable or of an apparatus, for example using partial discharge measurements; Electrostatic testing
- G01R31/1209—Testing dielectric strength or breakdown voltage ; Testing or monitoring effectiveness or level of insulation, e.g. of a cable or of an apparatus, for example using partial discharge measurements; Electrostatic testing using acoustic measurements
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01R—MEASURING ELECTRIC VARIABLES; MEASURING MAGNETIC VARIABLES
- G01R31/00—Arrangements for testing electric properties; Arrangements for locating electric faults; Arrangements for electrical testing characterised by what is being tested not provided for elsewhere
- G01R31/12—Testing dielectric strength or breakdown voltage ; Testing or monitoring effectiveness or level of insulation, e.g. of a cable or of an apparatus, for example using partial discharge measurements; Electrostatic testing
- G01R31/1227—Testing dielectric strength or breakdown voltage ; Testing or monitoring effectiveness or level of insulation, e.g. of a cable or of an apparatus, for example using partial discharge measurements; Electrostatic testing of components, parts or materials
- G01R31/1263—Testing dielectric strength or breakdown voltage ; Testing or monitoring effectiveness or level of insulation, e.g. of a cable or of an apparatus, for example using partial discharge measurements; Electrostatic testing of components, parts or materials of solid or fluid materials, e.g. insulation films, bulk material; of semiconductors or LV electronic components or parts; of cable, line or wire insulation
- G01R31/1272—Testing dielectric strength or breakdown voltage ; Testing or monitoring effectiveness or level of insulation, e.g. of a cable or of an apparatus, for example using partial discharge measurements; Electrostatic testing of components, parts or materials of solid or fluid materials, e.g. insulation films, bulk material; of semiconductors or LV electronic components or parts; of cable, line or wire insulation of cable, line or wire insulation, e.g. using partial discharge measurements
-
- G—PHYSICS
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10L—SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING
- G10L25/00—Speech or voice analysis techniques not restricted to a single one of groups G10L15/00 - G10L21/00
- G10L25/48—Speech or voice analysis techniques not restricted to a single one of groups G10L15/00 - G10L21/00 specially adapted for particular use
Landscapes
- Physics & Mathematics (AREA)
- Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Acoustics & Sound (AREA)
- Computational Linguistics (AREA)
- Signal Processing (AREA)
- Health & Medical Sciences (AREA)
- Audiology, Speech & Language Pathology (AREA)
- Human Computer Interaction (AREA)
- Multimedia (AREA)
- Locating Faults (AREA)
- Testing Relating To Insulation (AREA)
Abstract
An intelligent power cable fault discharge sound identification method belongs to the field of power cable fault detection. The method is characterized in that: the method comprises the following steps: step 1, sampling a sound signal and performing analog-to-digital conversion; step 2, data preprocessing and feature extraction; step 3, sending the extracted feature vectors of the sound signals into a support vector machine for identification and obtaining a judgment result; step 4, if the current sound signal is the cable fault discharge sound, sequentially executing the step 5 to the step 7, and if the current sound signal is the non-cable fault discharge sound, executing the step 7; step 5, storing the data of the current sound signal; step 6, calculating a correlation coefficient; and 7, displaying the judgment result and the sound signal waveform. In the intelligent power cable fault discharge sound identification method, the power cable fault discharge sound can be automatically identified based on a support vector machine, the restriction of depending on personal experience of testers for a long time is eliminated, and the working efficiency of power cable fault fixed point is greatly improved.
Description
Technical Field
An intelligent power cable fault discharge sound identification method belongs to the field of power cable fault detection.
Background
The power cable is widely applied to urban underground power grids, internal power supply circuits of industrial and mining enterprises and underwater power transmission lines crossing rivers and sea. Once a cable breaks down, power failure loss can be caused to enterprise production, inconvenience is brought to life of residents, and therefore the cable needs to be found out as soon as possible to repair the cable.
Finding a cable fault generally needs three steps of fault diagnosis, fault location and fault location. The fault diagnosis is to use tools and equipment such as a universal meter and the like to check the connectivity of each phase of the cable and the insulation resistance value of a fault phase, so as to judge the fault property and select a proper test method for the subsequent steps; the fault location is to measure the length of the cable between a fault point and a test point by using an instrument, so as to generally determine the area where the cable fault is located and reduce the fault finding range; fault spotting is the instrumental detection of the intensity or time of arrival of a fault signal in order to gradually approximate and ultimately confirm the location of the fault.
At present, in a cable fault fixed point link, a fault point is mainly searched at home and abroad by a method for detecting cable fault discharge sound. The method has two implementation modes: acoustic measurement and acoustic-magnetic synchronization.
The working principle of the acoustic measurement method is that an acoustic measurement probe arranged on the ground is used for receiving discharge sound of a cable fault point, sound signals are transmitted to a host machine through the probe, the sound signals are processed through filtering, amplification and the like, the host machine transmits the processed sound signals to a monitoring earphone for a tester to monitor and identify, and the tester judges the distance or the position of the fault point by analyzing the strength change of the discharge sound of faults at different positions.
The working principle of the acousto-magnetic synchronization method is that an acousto-magnetic synchronization detection probe placed on the ground is used for synchronously receiving a sound signal and an electromagnetic field signal generated by cable fault point discharge, the sound signal and the electromagnetic field signal are transmitted to a host machine by the probe, the host machine carries out filtering, amplification and other processing on the two signals, then the sound signal is sent to a monitoring earphone, and meanwhile, the sound waveform, the magnetic field waveform and the difference value (acousto-magnetic delay) between the arrival time of the two signals are displayed on a screen. The tester synthesizes the sound sensed by the earphone and the information displayed by the host computer to analyze, identifies the fault discharge sound and judges the distance or position of the fault point.
The existing acoustic measurement method and the acoustic-magnetic synchronization method still have the following defects in the aspect of fault discharge sound identification: (1) the fault discharge sound identification completely depends on the personal experience of testers, and testers with insufficient experience can hardly accurately identify the fault discharge sound. (2) Due to the large amount of environmental noise and interference present at the test site, it is often difficult for even an experienced tester to accurately distinguish and identify the fault discharge sound. (3) The training time for manually identifying the fault discharge sound is long, the cost is high, and the experience and the skill for manually identifying the fault discharge sound are difficult to teach and inherit from the field environment.
Disclosure of Invention
The technical problem to be solved by the invention is as follows: the method overcomes the defects of the prior art, and provides the intelligent power cable fault discharge sound identification method which is based on the support vector machine, can automatically identify the power cable fault discharge sound, gets rid of the restriction of depending on the personal experience of testers for a long time, and greatly improves the fixed-point working efficiency of the power cable fault.
The technical scheme adopted by the invention for solving the technical problems is as follows: the intelligent power cable fault sound discharge identification method is characterized by comprising the following steps: the method comprises the following steps:
and 7, displaying the judgment result and the sound signal waveform.
Preferably, the feature vector in step 2 includes:
according to data x3(i) Extracting short-time energy distribution pulse width characteristic z of sound signal1:
When the condition is satisfiedOn the premise of (1), define: w is alast=max[1,2,…,n-D+1],wfirst=min[1,2,…,n-D+1]Then z is1Comprises the following steps: z is a radical of1=wlast-wfirst
According to data x3(i) Extracting short-time energy distribution pulse aspect ratio feature z of sound signal2:
According to data x3(i) Extracting short-time energy distribution pulse position characteristic z of sound signal3:
According to data x4(i) Extracting short-time zero-crossing rate characteristic z of sound signal4:
When the condition is satisfiedUnder the premise of (1), define rlast=max[1,2,…,n-D],rfirst=min[1,2,…,n-D]Then z is4Comprises the following steps:
wherein: x is the number of3(i) According to the data x2(i) Calculating short-time energy distribution of the sound signal data with the step length of D; x is the number of4(i) According to the data x3(i) And calculating the short-time zero crossing rate of the sound signal data with the step length of D.
Preferably, the data x of the short-time energy distribution of the sound signal data with the step length D3(i) Comprises the following steps:
wherein: d denotes a step size.
Preferably, the sound signal data with the step length D is data x of short-time zero crossing rate4(i) Comprises the following steps:
wherein: sign is a sign function, th denotes a threshold value greater than zero, i ∈ [1,2, …, n-D ].
Preferably, the calculation formula of the correlation coefficient in step 6 is:
wherein: x is the number ofk(i),xk+1(i),i∈[1,2,…,n]Respectively representing sound signal data acquired twice in succession.
Preferably, the training process of the support vector machine described in step 3 includes the following steps:
step 3-1, respectively preparing M pieces of cable fault discharge sound signal data and non-cable fault discharge sound signal data;
step 3-2, respectively processing the M cable fault discharge sound signal data and the non-cable fault discharge sound signal data to obtain a characteristic matrix zij,i∈[1,2,…,2M],j∈[1,2,3,4],
Wherein, i ═ 1,2, …, M ] is the cable fault discharge acoustic signal eigenvector, i ═ M +1, M +2, …,2M ] is the non-cable fault discharge acoustic signal eigenvector;
3-3, assigning a column vector s of 2M rows, wherein the 1 st to M th rows are assigned to be 1 to represent cable fault discharge sound, and the M +1 th to 2M rows are assigned to be 0 to represent non-cable fault discharge sound;
step 3-4, the matrix zijAnd inputting the sum column vector s into a training function of a support vector machine, and selecting a linear kernel for training.
Compared with the prior art, the invention has the beneficial effects that:
in the intelligent power cable fault discharge sound identification method, the power cable fault discharge sound can be automatically identified based on a support vector machine, the restriction of depending on personal experience of testers for a long time is eliminated, and the working efficiency of power cable fault fixed point is greatly improved.
The intelligent power cable fault discharge sound identification method can automatically identify the power cable fault discharge sound, so that the influence of a large amount of environmental noise and interference existing on the site is greatly reduced.
The defect that long-time training is needed when an acoustic magnetic synchronization method is carried out in the prior art is overcome, and the training cost and labor cost of enterprises are greatly reduced.
Drawings
Fig. 1 is a flow chart of an intelligent sound-discharge identification method for power cable faults.
Fig. 2 is a cable fault discharge sound original waveform diagram of an example 1 of an intelligent power cable fault discharge sound identification method.
Fig. 3 is a diagram of cable fault sound discharging and direct current removing waveforms in the power cable fault sound discharging intelligent identification method example 1.
Fig. 4 is a normalized waveform diagram of cable fault discharge sound in the example 1 of the intelligent identification method of power cable fault discharge sound.
Fig. 5 is a waveform diagram of short-time energy distribution of cable fault discharge sound in the example 1 of the intelligent identification method of power cable fault discharge sound.
Fig. 6 is a waveform diagram of a short-time zero-crossing rate of cable fault discharge sound in the power cable fault discharge sound intelligent identification method example 1.
Fig. 7 is a waveform diagram of cable fault discharge sound secondary acquisition in the power cable fault discharge sound intelligent identification method example 1.
Fig. 8 is a diagram of a non-cable fault discharge sound original waveform in an example 2 of an intelligent power cable fault discharge sound identification method.
Fig. 9 is a diagram of a non-cable fault sound discharging and direct current removing waveform of an example 2 of an intelligent power cable fault sound discharging identification method.
Fig. 10 is a normalized waveform diagram of non-cable fault sound discharge in the power cable fault sound intelligent identification method example 2.
Fig. 11 is a waveform diagram of short-time energy distribution of non-cable fault discharge sound in the power cable fault discharge sound intelligent identification method example 2.
Fig. 12 is a waveform diagram of a short-time zero-crossing rate of non-cable fault discharge sound in an example 2 of an intelligent identification method for power cable fault discharge sound.
Fig. 13 is a waveform diagram of a non-cable fault discharge sound secondary collection in the power cable fault discharge sound intelligent identification method example 2.
Detailed Description
Fig. 1 to 13 illustrate preferred embodiments of the present invention, and the present invention will be further described with reference to fig. 1 to 13.
As shown in fig. 1, an intelligent sound identification method for power cable fault discharge includes the following steps:
in the process of the power cable fault fixed-point test, the whole cable line can generate a pulse magnetic field signal at the cable fault point breakdown moment, sound signal data acquisition is triggered by the pulse magnetic field signal, a section of sound signal data with the time length T from the fault discharge moment is recorded, and analog-to-digital conversion is carried out on the sound signal data.
And 2, preprocessing the digitized sound signal such as direct current removal, normalization, feature extraction and the like.
In most cases, a unipolar A/D converter is adopted for sound signal data acquisition, DC component removal processing is firstly carried out on the acquired data, and original data x output by the N-bit A/D converter0(i),i∈[1,2,…,n]Data x after DC component removal processing1(i) Comprises the following steps:
x1(i)=x0(i)-2N-1,i∈[1,2,…,n]
then the data x after the DC component removal processing is carried out1(i) Carrying out normalization processing to obtain a normalization processing result x2(i):
Then to the normalized data x2(i) Processing to calculate short-time energy distribution x of sound signal data with step length D3(i):
For normalized data x3(i) Processing to calculate the short-time zero-crossing rate x of the sound signal data with the step length D4(i):
Where sign is a sign function and th is a threshold value greater than zero.
And finally, performing feature extraction on the normalized data, wherein the feature extraction specifically comprises the following steps:
(1) according to data x3(i) Extracting short-time energy distribution pulse width characteristic z of sound signal1:
When the condition is satisfiedOn the premise of (1), define: w is alast=max[1,2,…,n-D+1],wfirst=min[1,2,…,n-D+1]Then z is1Comprises the following steps: z is a radical of1=wlast-wfirst
(2) According to data x3(i) Extracting short-time energy distribution pulse aspect ratio feature z of sound signal2:
(3) According to data x3(i) Extracting short-time energy distribution pulse position characteristic z of sound signal3:
(4) According to data x4(i)Extracting short-time zero-crossing rate characteristic z of sound signal4:
When the condition is satisfiedUnder the premise of (1), define rlast=max[1,2,…,n-D],rfirst=min[1,2,…,n-D]Then z is4Comprises the following steps:
characteristic z as described above1、z2、z3、z4Forming a sound signal feature vector z ═ z1、z2、z3、z4}。
and (3) sending the sound characteristic information extracted in the step (2) into a support vector machine, judging the sound characteristic information by the support vector machine, and judging whether the current sound signal belongs to cable fault discharge sound.
Before the support vector machine is used for voice feature information recognition, the support vector machine needs to be trained, and the specific training process comprises the following steps:
and 3-1, respectively preparing M pieces of cable fault discharge sound signal data and non-cable fault discharge sound signal data according to the sound signal data acquisition requirements.
Step 3-2, according to the data preprocessing and feature extraction requirements, respectively processing M cable fault discharge sound signal data and non-cable fault discharge sound signal data to obtain a feature matrix zij,i∈[1,2,…,2M],j∈[1,2,3,4]. Wherein, i ═ 1,2, …, M]Is a cable fault discharge sound signal characteristic vector, i ═ M +1, M +2, …,2M]Is a non-cable fault discharge acoustic signal feature vector.
And 3-3, assigning a column vector s of 2M rows, wherein the 1 st to Mth rows are assigned to be 1 (indicating that the cable fault discharge sound is generated), and the M +1 th to 2M rows are assigned to be 0 (indicating that the cable fault discharge sound is not generated).
Step 3-4, the matrix zijAnd inputting the sum column vector s into a training function of a support vector machine, and selecting a linear kernel for training.
And 4, judging whether the current sound signal is the cable fault discharge sound, if so, sequentially executing the step 5 to the step 7, and if not, executing the step 7.
And 5, storing the data of the current sound signal.
repeating the step 1 and the step 2, collecting the second sound signal, digitalizing the second sound signal, performing DC removal and normalization processing, extracting the data of the second sound signal, and calculating the twice sound signal data x according to the sound signal data collected twice successivelyk(i),xk+1(i),i∈[1,2,…,n]Correlation coefficient C of (a):
after the correlation coefficient C of the current two times of sound signal data is obtained through calculation, the correlation coefficient C is compared with a preset correlation coefficient threshold value C0And comparing, and confirming whether the sound signal acquired for the first time is the cable fault discharge sound again.
And 7, displaying the judgment result and the sound signal waveform.
The above steps are described in detail below by an example of a cable fault discharge sound and an example of a non-cable fault discharge sound, respectively. Example 1: when the sound information is a cable fault discharge sound:
Using normalized data x2(i) Calculating the short-time energy distribution x of the sound signal data with the step length D of 503(i) (as shown in FIG. 5), a short-time zero-crossing rate x with a threshold th of 0.5 is calculated4(i) (as shown in fig. 6).
Using short-time energy distribution data x3(i) Calculating the short-time energy distribution pulse width characteristic z195, aspect ratio feature z20.0024, position feature z3121. Using short-time zero-crossing rate data x4(i) Calculating short-time zero-crossing rate characteristic z4=500。z1、z2、z3、z4The component eigenvector z is {95,0.0024,121,500 }.
And 3-5, sending the characteristic vector z {95,0.0024,121,500} into a support vector machine, judging by the support vector machine to obtain a conclusion that the sound signal is cable fault discharge sound, and storing the data of the current sound signal.
And 7, displaying the judgment result that the current sound information is the cable fault discharge sound and the waveform of the sound information.
Example 2: when the sound information is non-cable fault discharge sound:
Utilizing normalized data x'2(i) Calculating short-time energy distribution x 'of sound signal data with step D of 50'3(i) (see FIG. 11), a short-time zero-crossing rate x 'with a threshold th of 0.5 is calculated'4(i) (as shown in fig. 12).
Utilizing short time energy distribution data x'3(i) Calculating the short-time energy distribution pulse width characteristic z1'-615, aspect ratio feature z'2=1.41×10-4Position feature z'3426. Utilizing short-time zero-crossing rate data x'4(i) Calculating short-time zero-crossing rate feature z'4=1826。z1’、z’2、z’3、z’4Component feature vector z' ═ {615,1.41 × 10-4,426,1826}。
Step 3-4, the feature vector z' {615,1.41 × 10-4426,1826, sending the sound signal into a support vector machine, and obtaining the conclusion that the sound signal is the non-cable fault discharge sound after the judgment by the support vector machine.
And 7, displaying the judgment result that the current sound information is the non-cable fault discharge sound and the waveform of the sound information.
The conclusion that the sound signal is not the cable fault discharge sound can also be verified through the step 6:
the sound signal x 'with the duration of 100ms is collected again'k+1(i) The waveform is as shown in FIG. 13, and the data of the audio signal and the data x 'of the audio signal acquired last time are combined'k(i) (i.e. x'0(i) Waveform is shown in fig. 8), calculating a correlation coefficient, obtaining the correlation coefficient C' of the two sound signals to be 0.025, and finally confirming that the current sound information is the non-cable fault discharge sound.
The foregoing is directed to preferred embodiments of the present invention, other and further embodiments of the invention may be devised without departing from the basic scope thereof, and the scope thereof is determined by the claims that follow. However, any simple modification, equivalent change and modification of the above embodiments according to the technical essence of the present invention are within the protection scope of the technical solution of the present invention.
Claims (5)
1. A power cable fault sound-discharging intelligent identification method is characterized in that: the method comprises the following steps:
step 1, starting to sample sound signals at the moment of cable fault discharge and carrying out analog-to-digital conversion to obtain original data x0(i);
Step 2, carrying out DC removal processing on the digitized sound signal to obtain data x1(i) Then, the data without the direct current processing is normalized to obtain data x2(i) Finally, extracting the feature vector of the sound signal;
step 3, sending the extracted feature vectors of the sound signals into a support vector machine for identification and obtaining a judgment result;
step 4, judging whether the front sound signal is cable fault discharge sound, if the front sound signal is cable fault discharge sound, sequentially executing the step 5 to the step 7, and if the front sound signal is non-cable fault discharge sound, executing the step 7;
step 5, storing the data of the current sound signal;
step 6, collecting the sound signals for the second time and calculating the correlation coefficient;
step 7, displaying the judgment result and the sound signal waveform;
the feature vector in step 2 includes:
according to data x3(i) Extracting short-time energy distribution pulse width characteristic z of sound signal1:
When the condition is satisfiedi∈[1,2,…,n-D+1]On the premise of (1), define: w is alast=max[1,2,…,n-D+1],wfirst=min[1,2,…,n-D+1]Then z is1Comprises the following steps: z is a radical of1=wlast-wfirst
According to data x3(i) Extracting short-time energy distribution pulse aspect ratio feature z of sound signal2:
According to data x3(i) Extracting short-time energy distribution pulse position characteristic z of sound signal3:
According to data x4(i) Extracting short-time zero-crossing rate characteristic z of sound signal4:
When the condition is satisfiedi∈[1,2,…,n-D]Under the premise of (1), define rlast=max[1,2,…,n-D],rfirst=min[1,2,…,n-D]Then z is4Comprises the following steps:
wherein: x is the number of3(i) According to the data x2(i) Calculating short-time energy distribution of the sound signal data with the step length of D; x is the number of4(i) According to the data x3(i) And calculating the short-time zero crossing rate of the sound signal data with the step length of D.
3. The intelligent acoustic identification method for power cable fault discharge according to claim 1, characterized in that: the sound signal data with the step length of D has the short-time zero crossing rate x4(i) Comprises the following steps:
wherein: sign is a sign function, th denotes a threshold value greater than zero, i ∈ [1,2, …, n-D ].
4. The intelligent acoustic identification method for power cable fault discharge according to claim 1, characterized in that: the calculation formula of the correlation coefficient in step 6 is as follows:
wherein: x is the number ofk(i),xk+1(i),i∈[1,2,…,n]Respectively representing sound signal data acquired twice in succession.
5. The intelligent acoustic identification method for power cable fault discharge according to claim 1, characterized in that: the training process of the support vector machine in the step 3 comprises the following steps:
step 3-1, respectively preparing M pieces of cable fault discharge sound signal data and non-cable fault discharge sound signal data;
step 3-2, respectively processing the M cable fault discharge sound signal data and the non-cable fault discharge sound signal data to obtain a characteristic matrix zij,i∈[1,2,…,2M],j∈[1,2,3,4],
Wherein, i ═ 1,2, …, M ] is the cable fault discharge acoustic signal eigenvector, i ═ M +1, M +2, …,2M ] is the non-cable fault discharge acoustic signal eigenvector;
3-3, assigning a column vector s of 2M rows, wherein the 1 st to M th rows are assigned to be 1 to represent cable fault discharge sound, and the M +1 th to 2M rows are assigned to be 0 to represent non-cable fault discharge sound;
step 3-4, the matrix zijAnd inputting the sum column vector s into a training function of a support vector machine, and selecting a linear kernel for training.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201810737476.1A CN109116196B (en) | 2018-07-06 | 2018-07-06 | Intelligent power cable fault discharge sound identification method |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201810737476.1A CN109116196B (en) | 2018-07-06 | 2018-07-06 | Intelligent power cable fault discharge sound identification method |
Publications (2)
Publication Number | Publication Date |
---|---|
CN109116196A CN109116196A (en) | 2019-01-01 |
CN109116196B true CN109116196B (en) | 2020-09-25 |
Family
ID=64823074
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201810737476.1A Active CN109116196B (en) | 2018-07-06 | 2018-07-06 | Intelligent power cable fault discharge sound identification method |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN109116196B (en) |
Families Citing this family (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN112013425B (en) * | 2019-05-30 | 2021-12-03 | 宁波方太厨具有限公司 | Electric quantity detection method and detection system for gas cooker |
CN113327629A (en) * | 2021-05-06 | 2021-08-31 | 上海交通大学 | Power equipment sound diagnosis method and system |
CN113759208A (en) * | 2021-06-02 | 2021-12-07 | 青岛鼎信通讯股份有限公司 | Abnormal waveform identification method based on fault indicator |
CN113466616A (en) * | 2021-06-22 | 2021-10-01 | 海南电网有限责任公司乐东供电局 | Method and device for quickly positioning cable fault point |
CN115762529A (en) * | 2022-10-17 | 2023-03-07 | 国网青海省电力公司海北供电公司 | Method for preventing cable from being broken outside by using voice recognition perception algorithm |
Citations (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN1821795A (en) * | 2006-03-29 | 2006-08-23 | 保定天威集团有限公司 | Method and its device for detecting discharge fault position of high voltage electric equipment |
CN102426835A (en) * | 2011-08-30 | 2012-04-25 | 华南理工大学 | Method for identifying local discharge signals of switchboard based on support vector machine model |
CN102628917A (en) * | 2012-04-25 | 2012-08-08 | 广州供电局有限公司 | Partial discharge recognition method and system |
KR101410733B1 (en) * | 2013-01-10 | 2014-06-24 | 한국전기연구원 | Partial discharge measurement device using reference MIC and method which can guide fault position |
CN104409073A (en) * | 2014-11-04 | 2015-03-11 | 贵阳供电局 | Substation equipment sound and voice identification method |
CN106782505A (en) * | 2017-02-21 | 2017-05-31 | 南京工程学院 | A kind of method based on electric discharge voice recognition high-tension switch cabinet state |
Family Cites Families (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
TW201432279A (en) * | 2013-02-05 | 2014-08-16 | Tzu-Feng Wanglee | Method of utilizing vocal features for determining malfunctions of electrical equipment caused by arc discharge, mechanical vibration and abnormal displacement |
-
2018
- 2018-07-06 CN CN201810737476.1A patent/CN109116196B/en active Active
Patent Citations (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN1821795A (en) * | 2006-03-29 | 2006-08-23 | 保定天威集团有限公司 | Method and its device for detecting discharge fault position of high voltage electric equipment |
CN102426835A (en) * | 2011-08-30 | 2012-04-25 | 华南理工大学 | Method for identifying local discharge signals of switchboard based on support vector machine model |
CN102628917A (en) * | 2012-04-25 | 2012-08-08 | 广州供电局有限公司 | Partial discharge recognition method and system |
KR101410733B1 (en) * | 2013-01-10 | 2014-06-24 | 한국전기연구원 | Partial discharge measurement device using reference MIC and method which can guide fault position |
CN104409073A (en) * | 2014-11-04 | 2015-03-11 | 贵阳供电局 | Substation equipment sound and voice identification method |
CN106782505A (en) * | 2017-02-21 | 2017-05-31 | 南京工程学院 | A kind of method based on electric discharge voice recognition high-tension switch cabinet state |
Non-Patent Citations (2)
Title |
---|
"利用盲源分离技术提取地下电缆故障放电声的研究";陈志坚 等;《城市建设理论研究(电子版)》;20131115(第25期);1-5 * |
基于超声波信号的局部放电故障识别算法研究;周玲;《中国优秀硕士学位论文全文数据库 工程科技Ⅱ辑》;20140115(第 01 期);C042-261 * |
Also Published As
Publication number | Publication date |
---|---|
CN109116196A (en) | 2019-01-01 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN109116196B (en) | Intelligent power cable fault discharge sound identification method | |
CN109782274B (en) | Water damage identification method based on time-frequency statistical characteristics of ground penetrating radar signals | |
CN104007374B (en) | Inference signal prevention method in converter transformer partial discharge detection experiment | |
CN108562821B (en) | Method and system for determining single-phase earth fault line selection of power distribution network based on Softmax | |
CN111007365A (en) | Ultrasonic partial discharge identification method and system based on neural network | |
CN106228107B (en) | A kind of supersonic guide-wave broken rail monitoring method based on independent component analysis | |
CN111896616B (en) | Gas-liquid two-phase flow pattern identification method based on acoustic emission-BP neural network | |
CN106338237A (en) | Transformer winding deformation detection method based on frequency response impedance method | |
CN114217164B (en) | Cable fault distance measurement method and system based on discharge waveform intelligent identification | |
CN105488520A (en) | Multi-resolution singular-spectrum entropy and SVM based leakage acoustic emission signal identification method | |
CN110954033A (en) | Concrete crack depth detection method and system | |
CN113092946A (en) | Method and device for positioning ground fault of multi-branch overhead-cable mixed line of power distribution network | |
CN109827081A (en) | A kind of buried drain pipe road plugging fault and branch pipe tee connection part diagnostic method based on acoustics active detecting | |
CN113805018A (en) | Intelligent identification method for partial discharge fault type of 10kV cable of power distribution network | |
CN110568073B (en) | Method for picking up impact signal in noise environment | |
CN116776279A (en) | Multi-mode data collaborative power transmission line flash explosion early warning abnormal target detection method | |
CN104977602B (en) | A kind of control method and device of earthquake data acquisition construction | |
CN107192892B (en) | Thunder positioning system automatic trigger method based on lightning electromagnetic signal identification technology | |
CN106646138B (en) | Distribution net work earthing fault localization method based on the conversion of more sample frequency wavelet character energy | |
CN112215307A (en) | Method for automatically detecting signal abnormality of seismic instrument by applying machine learning | |
CN110716199B (en) | Geological radar marking method for automatically distinguishing multiple types of defects by computer | |
CN116660800A (en) | Weak fault diagnosis method for airplane cable | |
CN115144259B (en) | Method and system for detecting deformation resistance of steel | |
CN115255567B (en) | Welding deviation real-time detection method and system based on frequency domain and time-frequency domain characteristics | |
CN106019042A (en) | Method of identifying high voltage cable inner insulation defect type based on specific chromatograms |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
GR01 | Patent grant | ||
GR01 | Patent grant | ||
TR01 | Transfer of patent right |
Effective date of registration: 20210727 Address after: No.16, Sanying Road, Zhangdian District, Zibo City, Shandong Province Patentee after: SHANDONG KEHUI POWER AUTOMATION Co.,Ltd. Patentee after: QINGDAO KEHUI ELECTRIC Co.,Ltd. Address before: No.16, Sanying Road, Zhangdian District, Zibo City, Shandong Province Patentee before: SHANDONG KEHUI POWER AUTOMATION Co.,Ltd. |
|
TR01 | Transfer of patent right |