CN112446320A - Fuzzy recognition logic gate multiple complementary partial discharge distinguishing device and method - Google Patents
Fuzzy recognition logic gate multiple complementary partial discharge distinguishing device and method Download PDFInfo
- Publication number
- CN112446320A CN112446320A CN202011322970.5A CN202011322970A CN112446320A CN 112446320 A CN112446320 A CN 112446320A CN 202011322970 A CN202011322970 A CN 202011322970A CN 112446320 A CN112446320 A CN 112446320A
- Authority
- CN
- China
- Prior art keywords
- partial discharge
- waveform
- judging
- phase
- noise
- 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.)
- Granted
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2218/00—Aspects of pattern recognition specially adapted for signal processing
- G06F2218/08—Feature extraction
-
- 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
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2218/00—Aspects of pattern recognition specially adapted for signal processing
- G06F2218/12—Classification; Matching
Landscapes
- Engineering & Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Artificial Intelligence (AREA)
- Signal Processing (AREA)
- General Engineering & Computer Science (AREA)
- Testing Relating To Insulation (AREA)
Abstract
The invention provides a fuzzy recognition logic gate multiple complementary partial discharge distinguishing method, which comprises the following steps: s1, judging feature similarity of three-phase phi-Q-N atlas and judging three-phase waveform feature analogy; s2, judging inter-phase correlation; and S3, classifying and judging the position distribution of the real-time signal source. Still provide a fuzzy recognition logic gate multiple complementary partial discharge discriminating device, include: the invention adopts a multi-discrimination program for detection signals, and carries out analysis and artificial intelligence discrimination method through large data accumulated by the system continuously, thereby eliminating the interference of noise signals, improving discrimination precision, reducing misjudgment rate and lightening the workload of operation and maintenance personnel.
Description
Technical Field
The invention relates to the field of three-phase cable partial discharge detection, in particular to a fuzzy recognition logic gate multiple complementary partial discharge distinguishing device and method.
Background
With the rapid development of urban modernization, a large number of high-voltage cable lines are put into operation in urban life, the environment where the cable lines are located is severe, once insulation breakdown failure occurs, large-area power failure can be caused, and production and life are seriously affected. Partial discharge detection is one of effective means for early detecting the insulation defect of a cable line, and a plurality of long-term partial discharge online monitoring devices are installed for ensuring the operation quality of the power cable line. However, it is found through long-time monitoring data that the partial discharge online monitoring device often falsely alarms, and various environmental noises and power system noises are determined as partial discharge signals, so that operation and maintenance personnel need to spend a large amount of manpower and material resources to eliminate and deal with the alarm signals.
In fact, these false alarm signals mainly come from corona signals and environmental noise generated by the cable system, and they have some characteristic quantities of the partial discharge signals to a certain extent, such as discharge quantity Q, density N, phase Φ, duration T, and map similarity, so that the monitoring device system also misjudges the noise signals as partial discharge signals, and further explains the possibility of misjudgment of the existing partial discharge judgment method, such as logic gate judgment and neural network, etc., the logic gate is judged according to the logic relation among the discharge quantity Q, density N, phase Φ, duration T of the partial discharge signals, and the neural network adopts the network model BP method to judge the similarity of the signals, and this judgment method also has the problems of complex learning method, slow learning rate, slow network convergence rate, long training time, too high learning rate, etc., the judgment result depends on the representativeness of the learning sample, the misjudgment rate is high, and the like, which affect the judgment accuracy of the partial discharge online monitoring device and bring much inconvenience to operation and maintenance personnel.
Some methods for eliminating corona signals exist in the prior art means, for example, chinese patent CN106950482B discloses a method for eliminating corona interference based on similarity of inter-phase signal patterns, which judges whether a cable has a partial discharge signal by similarity of inter-phase patterns; however, if only the map similarity is compared, the noise signals such as motor noise and the like can be judged as partial discharge signals by mistake, and the possibility of misjudgment is high, so that operation and maintenance personnel need to spend a large amount of manpower and material resources to review data and process misjudgment alarms.
Disclosure of Invention
The invention provides a fuzzy recognition logic gate multiple complementary partial discharge judgment device and method for overcoming the problems that noise signals such as motor noise and the like are judged as partial discharge signals by mistake and the possibility of misjudgment is high due to the fact that operation and maintenance personnel need to spend a large amount of manpower and material resources to reply data and process misjudgment alarms in the background technology.
In order to solve the technical problems, the invention adopts the technical scheme that: a fuzzy recognition logic gate multiple complementary partial discharge distinguishing method comprises the following steps:
s1, simultaneously carrying out three-phase phi-Q-N map feature similarity judgment and three-phase waveform feature analogy judgment on the received detection signals, preliminarily judging whether the detection signals are partial discharge or noise respectively, and entering the step S2 if the detection signals are partial discharge judged by the two judgments; otherwise, ending the judgment;
s2, judging inter-phase correlation: judging the waveform polarity of the detection signal, secondarily judging whether the detection signal is partial discharge or noise according to the waveform polarity judging result, and if the detection signal is noise, finishing the judgment; if the partial discharge is detected, preliminarily determining the phase of the partial discharge signal, comparing and judging the discharge quantity of the phase, judging whether the partial discharge is detected to be noise or not again according to the comparison and judgment result of the discharge quantity, and if the partial discharge is detected to be noise, finishing the judgment; if the partial discharge is detected, the phase of the partial discharge signal is finally determined, and then the step S3 is performed;
s3, real-time signal source position distribution classification judgment: reducing waveform data acquired by the phase of the finally determined partial discharge signal into a displayable waveform based on a waveform reduction technology, automatically positioning the detection signal according to the displayable waveform, calculating the occurrence position repetition rate according to the position distribution of automatic positioning, and finally judging partial discharge and sending an alarm signal if the occurrence position repetition rate is greater than a set value; otherwise, judging as noise and ending the judgment.
Further, the three-phase phi-Q-N map feature similarity judgment specifically comprises the following steps: converting the phi-Q-N data storage value of the detection signal into a new map, calculating a new characteristic value of the new map, carrying out similarity one-to-one comparison on the new characteristic value and all map characteristic values in a map library to obtain a plurality of map similarities, outputting a result when the maximum value of all map similarities exceeds a set value, and otherwise, outputting no result; and when a result is output, comparing the new characteristic value with the partial discharge characteristic value samples in the atlas library one by one to obtain a plurality of partial discharge similarities, judging partial discharge when the maximum value of all the partial discharge similarities exceeds a set value, and otherwise, judging noise.
Further, the three-phase waveform feature analogy determination specifically includes: restoring waveform data of the three-phase detection signal into a displayable new waveform shape, comparing the new waveform shape with all waveform shapes in a waveform database one by one to obtain a plurality of waveform similarities, outputting a result when the maximum value of all the waveform similarities is greater than a preset value, and otherwise, outputting no result; and when a result is output, comparing the new waveform shape with the partial discharge waveform samples marked in the waveform database one by one to obtain a plurality of partial discharge waveform similarities, and judging partial discharge when the maximum value of all the partial discharge waveform similarities is greater than a preset value, otherwise, judging noise.
Further, the waveform polarity is determined as: presetting a waveform trigger value in a system, judging that the polarity of a waveform is positive when a first value of waveform data of a detection signal is greater than the waveform trigger value, and otherwise, judging that the polarity of the waveform is negative; when the waveform polarity of one phase in the three-phase cable is opposite to that of other two phases, the two-time judgment is partial discharge, and the phase is preliminarily determined to be the phase of a partial discharge signal; otherwise, judging as noise and ending the judgment.
Further, the discharge amount comparison is judged as: when the discharge amount of the phase where the partial discharge signal is located is determined to be larger than that of the other two phases preliminarily, judging the phase as the partial discharge again, and finally determining the phase as the phase where the partial discharge signal is located; otherwise, judging as noise and ending the judgment.
Further, when the maximum value of all partial discharge similarities exceeds a set value, the new characteristic value mark of the new atlas is stored in the atlas database as a sample.
Further, when the maximum value of all the partial discharge waveform similarities is larger than a preset value, the waveform shape mark of the detection signal is stored in a waveform database as a sample.
The fuzzy recognition logic gate multiple complementary partial discharge distinguishing method is also provided, and comprises the following steps:
the three-phase phi-Q-N map feature similarity judging module is used for judging the three-phase phi-Q-N map feature similarity of the received detection signal and preliminarily judging whether the detection signal is partial discharge or noise;
the three-phase waveform characteristic analogy judging module is used for carrying out three-phase waveform characteristic analogy judgment on the received detection signal and preliminarily judging whether the detection signal is partial discharge or noise;
the interphase correlation judging module is used for judging the advanced waveform polarity of the detection signal which is judged to be partially discharged by the three-phase waveform feature analogy judging module and the three-phase phi-Q-N map feature similarity judging module, judging whether the detection signal is partially discharged or noise secondarily according to the waveform polarity judging result, and finishing the judgment if the detection signal is noise; if the partial discharge is detected, preliminarily determining the phase of the partial discharge signal, comparing and judging the discharge quantity of the phase, judging whether the partial discharge is detected to be noise or not again according to the comparison and judgment result of the discharge quantity, and if the partial discharge is detected to be noise, finishing the judgment; if the partial discharge is adopted, the phase of the partial discharge signal is finally determined;
and the real-time signal source position distribution classification judging module is used for finally judging whether the partial discharge signal is partial discharge or noise according to the position distribution and the occurrence position repetition rate, reducing the waveform data based on the waveform reduction technology according to the phase of the partial discharge signal finally determined by the interphase correlation judging module, automatically positioning various signal sources and finally judging whether the partial discharge signal is partial discharge or noise.
Further, the inter-phase correlation judging module includes:
the waveform polarity judging unit is used for presetting a waveform trigger value in the system, judging that the waveform polarity is positive when a first value of waveform data of the detection signal is greater than the waveform trigger value, and judging that the waveform polarity is negative if the first value is not greater than the waveform trigger value; when the waveform polarity of one phase in the three-phase cable is opposite to that of other two phases, the two-time judgment is partial discharge, and the phase is preliminarily determined to be the phase of a partial discharge signal; otherwise, judging as noise and finishing the judgment;
the discharge quantity comparison and judgment unit is used for comparing the discharge quantity of the phase where the partial discharge signal is preliminarily determined by the waveform polarity judgment unit with the discharge quantities of other two phases, judging the phase as partial discharge again when the discharge quantity of the phase where the partial discharge signal is preliminarily determined to be larger than the discharge quantities of the other two phases, and finally determining the phase as the phase where the partial discharge signal is located; otherwise, judging as noise and ending the judgment.
Further, the real-time signal source position distribution classification and discrimination module includes:
the waveform restoring unit is used for restoring the acquired waveform data into a displayable waveform;
the waveform positioning unit is used for automatically positioning the detection signal according to the displayable waveform;
a waveform position repetition rate calculation unit for calculating the occurrence position repetition rate according to the automatically positioned position distribution;
a final judging unit for finally judging whether the partial discharge or the noise is generated according to the repetition rate of the occurrence position;
and the alarm unit is used for receiving the signal of the final judging unit and sending an alarm signal.
Compared with the prior art, the beneficial effects are:
1. the invention adopts multiple discrimination programs of phi-Q-N similarity discrimination, partial discharge waveform characteristic analogy discrimination, partial discharge interphase correlation discrimination and real-time signal source position distribution classification discrimination on detection signals, and carries out analysis and artificial intelligence discrimination method through large data accumulated by the system continuously, thereby eliminating the interference of noise signals, improving discrimination precision, reducing misjudgment rate and reducing the workload of operation and maintenance personnel.
2. The method of the invention has simple learning and high learning speed, and can accumulate big data for a long time to provide a basis for the future discrimination.
Drawings
FIG. 1 is a schematic flow chart of example 1.
FIG. 2 is a schematic flow chart of the feature similarity determination of the three-phase Φ -Q-N spectrum in embodiment 1.
FIG. 3 is a schematic flow chart of the three-phase waveform feature analogy determination in embodiment 1.
Fig. 4 is a flowchart illustrating the inter-correlation determination in embodiment 1.
Fig. 5 is a schematic flowchart of the classification and determination of the location distribution of the real-time signal source in embodiment 1.
Fig. 6 is a schematic view of the position distribution of automatic positioning in embodiment 1.
Detailed Description
The drawings are for illustrative purposes only and are not to be construed as limiting the patent; for the purpose of better illustrating the embodiments, certain features of the drawings may be omitted, enlarged or reduced, and do not represent the size of an actual product; it will be understood by those skilled in the art that certain well-known structures in the drawings and descriptions thereof may be omitted. The positional relationships depicted in the drawings are for illustrative purposes only and are not to be construed as limiting the present patent.
Example 1
As shown in fig. 1, after receiving and processing a received detection signal in a background system, the background system enters a multiple complementary partial discharge discrimination program 100, which mainly includes the following steps:
s1, simultaneously carrying out three-phase phi-Q-N map feature similarity judgment and three-phase waveform feature analogy judgment on the received detection signals, preliminarily judging whether the detection signals are partial discharge or noise respectively, and entering the step S2 if the detection signals are partial discharge judged by the two judgments; otherwise, ending the judgment;
s2, judging inter-phase correlation: judging the waveform polarity of the detection signal, secondarily judging whether the detection signal is partial discharge or noise according to the waveform polarity judging result, and if the detection signal is noise, finishing the judgment; if the partial discharge is detected, preliminarily determining the phase of the partial discharge signal, comparing and judging the discharge quantity of the phase, judging whether the partial discharge is detected to be noise or not again according to the comparison and judgment result of the discharge quantity, and if the partial discharge is detected to be noise, finishing the judgment; if the partial discharge is detected, the phase of the partial discharge signal is finally determined, and then the step S3 is performed;
s3, real-time signal source position distribution classification judgment: reducing waveform data acquired by the phase of the finally determined partial discharge signal into a displayable waveform based on a waveform reduction technology, automatically positioning the detection signal according to the displayable waveform, calculating the occurrence position repetition rate according to the position distribution of automatic positioning, and finally judging partial discharge and sending an alarm signal if the occurrence position repetition rate is greater than a set value; otherwise, judging as noise and ending the judgment.
As shown in fig. 2, the program for discriminating the local discharge Φ -Q-N map feature similarity uses the latest image recognition technology, so that the learning method is simpler, the discrimination accuracy is higher, and the types of the local discharge signals can be distinguished; the three-phase phi-Q-N map feature similarity judgment specifically comprises the following steps: converting the phi-Q-N data storage values of the detection signals into new maps, calculating new characteristic values of the new maps, carrying out similarity one-to-one comparison on the new characteristic values and all map characteristic values in a map library to obtain a plurality of map similarities, outputting a result when the maximum value of all the map similarities exceeds a set value, and otherwise, outputting no result; and when a result is output, carrying out similarity one-to-one comparison on the new characteristic value and the partial discharge characteristic value samples in the atlas library to obtain a plurality of partial discharge similarities, judging partial discharge when the maximum value of all the partial discharge similarities exceeds a set value, and otherwise judging noise.
As shown in fig. 3, the three-phase waveform feature analogy determination specifically includes: restoring waveform data of the three-phase detection signal into a displayable new waveform shape, comparing the new waveform shape with all waveform shapes in a waveform database one by one to obtain a plurality of waveform similarities, outputting a result when the maximum value of all the waveform similarities is greater than a preset value, and otherwise, outputting no result; when a result is output, comparing the waveform shape characteristics of the detection signal with partial discharge waveform samples marked in a waveform database one by one to obtain a plurality of partial discharge waveform similarities, judging partial discharge when the maximum value of all the partial discharge waveform similarities is larger than a preset value, and otherwise judging noise. The design is added with a partial discharge waveform characteristic analogy discrimination program, and the discrimination step can identify and distinguish signals according to the waveform characteristics of the signals, so that the precision of partial discharge discrimination is further improved.
As shown in fig. 4, the waveform polarity is determined as: presetting a waveform trigger value in a system, judging that the polarity of a waveform is positive when a first value of waveform data of a detection signal is greater than the waveform trigger value, and otherwise, judging that the polarity of the waveform is negative; when the waveform polarity of one phase in the three-phase cable is opposite to that of other two phases, the two-time judgment is partial discharge, and the phase is preliminarily determined to be the phase of a partial discharge signal; otherwise, judging as noise and ending the judgment.
The discharge amount comparison is judged as follows: when the discharge amount of the phase where the partial discharge signal is located is determined to be larger than that of the other two phases preliminarily, judging the phase as the partial discharge again, and finally determining the phase as the phase where the partial discharge signal is located; otherwise, judging as noise and ending the judgment.
When the maximum value of all partial discharge similarities exceeds a set value, simultaneously, taking a new characteristic value mark of a new map as a sample to be stored in a map library for comparison with newly detected data and systematic big data learning; and when the maximum value of all the partial discharge waveform similarities is larger than a preset value, simultaneously storing the waveform shape mark of the detection signal as a sample in a waveform database for comparison with newly detected data.
During the in-service use, after having set up the partial discharge on-line monitoring device, put the sensor acquisition signal through the partial, put signal processing with the partial again and send the detected signal for backstage signal analysis system, start test program system, open the automatic discrimination program switch after, backstage signal analysis system utilizes the method of this embodiment to get into the automatic test state, and its theory of operation is probably as follows: respectively obtaining phi-Q-N-T data and waveform data of the generated cable three phases by testing, starting to judge phi-Q-N atlas feature similarity and waveform feature analogy of detection data of the cable three phases, wherein two judging programs are independent and respectively judge signals detected by the cable three phases, and when the similarity of the detected atlas feature and the similarity of a sample marked as partial discharge in a phi-Q-N atlas database is higher than a certain value, judging the partial discharge, otherwise, judging the partial discharge as noise; and when the detected waveform characteristics are similar to the spectrum marked as the waveform in the waveform spectrum library, judging the partial discharge, otherwise, judging the partial discharge as noise. The pattern feature identification and the partial discharge waveform feature identification are two key discrimination mechanisms which are indispensable to the invention; because only the pattern feature identification is carried out, the interference such as motor noise can be missed; if only the waveform shape is identified, the interference signals such as corona discharge noise can be missed; when the three phases are all partially discharged, judging the polarity of the signal waveform and the magnitude of the discharge capacity by the interphase correlation judging module, and when the polarity of the signal of one phase is opposite to that of the other two phases and the discharge capacity is larger than that of the other two phases, judging the partial discharge, otherwise, judging the partial discharge is noise; as shown in fig. 6, after being determined as an partial discharge signal, the detection signal of the phase calculates the position distribution of the waveform based on a waveform positioning technique, and determines whether the signal is the partial discharge signal according to the occurrence position repetition rate of the waveform, because the position of the partial discharge signal is fixed, because the partial discharge point 200 is fixed, the amplitude level is stable, the repetition rate is high, and the noise 300 is randomly generated, irregular in size, scattered in distribution, and not high in repetition rate; and finally judging the partial discharge to be real if the repetition rate is high, and sending an alarm signal, otherwise, judging the partial discharge to be noise, and finishing the judgment.
In the embodiment, multiple discrimination programs of phi-Q-N similarity discrimination, partial discharge waveform feature analogy discrimination, partial discharge interphase correlation discrimination and real-time signal source position distribution classification discrimination are adopted for detection signals, and a discrimination method of analysis and artificial intelligence is carried out on continuously accumulated big data of a system, so that the interference of noise signals can be eliminated, the discrimination precision is improved, the misjudgment rate is reduced, and the workload of operation and maintenance personnel is reduced; the method is simple in learning and high in learning speed, and can accumulate big data for a long time to provide a basis for future discrimination.
Example 2
The present embodiment provides a fuzzy recognition logic gate multiple complementary partial discharge distinguishing device, which uses the fuzzy recognition logic gate multiple complementary partial discharge distinguishing method in embodiment 1, and includes:
the three-phase phi-Q-N map feature similarity judging module is used for judging the three-phase phi-Q-N map feature similarity of the received detection signal and preliminarily judging whether the detection signal is partial discharge or noise;
the three-phase waveform characteristic analogy judging module is used for carrying out three-phase waveform characteristic analogy judgment on the received detection signal and preliminarily judging whether the detection signal is partial discharge or noise;
the interphase correlation judging module is used for judging the advanced waveform polarity of the detection signal which is judged to be partially discharged by the three-phase waveform feature analogy judging module and the three-phase phi-Q-N map feature similarity judging module, judging whether the detection signal is partially discharged or noise secondarily according to the waveform polarity judging result, and finishing the judgment if the detection signal is noise; if the partial discharge is detected, preliminarily determining the phase of the partial discharge signal, comparing and judging the discharge quantity of the phase, judging whether the partial discharge is detected to be noise or not again according to the comparison and judgment result of the discharge quantity, and if the partial discharge is detected to be noise, finishing the judgment; if the partial discharge is adopted, the phase of the partial discharge signal is finally determined;
and the real-time signal source position distribution classification judging module is used for finally judging whether the partial discharge signal is partial discharge or noise according to the position distribution and the occurrence position repetition rate, reducing the waveform data of the acquired waveform data based on a waveform reduction technology, automatically positioning various signal sources and finally judging whether the partial discharge signal is partial discharge or noise according to the position distribution and the occurrence position repetition rate.
The interphase correlation judging module comprises:
the waveform polarity judging unit is used for presetting a waveform trigger value in the system, judging that the waveform polarity is positive when a first value of waveform data of the detection signal is greater than the waveform trigger value, and judging that the waveform polarity is negative if the first value is not greater than the waveform trigger value; when the waveform polarity of one phase in the three-phase cable is opposite to that of other two phases, the two-time judgment is partial discharge, and the phase is preliminarily determined to be the phase of a partial discharge signal; otherwise, judging as noise and finishing the judgment;
the discharge quantity comparison and judgment unit is used for comparing the discharge quantity of the phase of the partial discharge signal preliminarily determined by the waveform polarity judgment unit with the discharge quantities of other two phases, judging the phase as partial discharge again when the discharge quantity of the phase of the partial discharge signal is larger than that of the other two phases, and finally determining the phase as the phase of the partial discharge signal; otherwise, judging as noise and ending the judgment.
The real-time signal source position distribution classification distinguishing module comprises:
the waveform restoring unit is used for restoring the acquired waveform data into a displayable waveform;
the waveform positioning unit is used for automatically positioning the detection signal according to the displayable waveform;
a waveform position repetition rate calculation unit for calculating the occurrence position repetition rate according to the automatically positioned position distribution;
a final judging unit for finally judging whether the partial discharge or the noise is generated according to the occurrence position repetition rate;
and the alarm unit is used for receiving the signal of the final judging unit and sending an alarm signal.
The embodiment can be used for accurately judging the partial discharge detection signal.
It should be understood that the above-described embodiments of the present invention are merely examples for clearly illustrating the present invention, and are not intended to limit the embodiments of the present invention. Other variations and modifications will be apparent to persons skilled in the art in light of the above description. And are neither required nor exhaustive of all embodiments. Any modification, equivalent replacement, and improvement made within the spirit and principle of the present invention should be included in the protection scope of the claims of the present invention.
Claims (10)
1. A fuzzy recognition logic gate multiple complementary partial discharge distinguishing method is characterized by comprising the following steps:
s1, simultaneously carrying out three-phase phi-Q-N map feature similarity judgment and three-phase waveform feature analogy judgment on the received detection signals, preliminarily judging whether the detection signals are partial discharge or noise respectively, and entering the step S2 if the detection signals are partial discharge judged by the two judgments; otherwise, ending the judgment;
s2, judging inter-phase correlation: judging the waveform polarity of the detection signal, secondarily judging whether the detection signal is partial discharge or noise according to the waveform polarity judging result, and if the detection signal is noise, finishing the judgment; if the partial discharge is detected, preliminarily determining the phase of the partial discharge signal, comparing and judging the discharge quantity of the phase, judging whether the partial discharge is detected to be noise or not again according to the comparison and judgment result of the discharge quantity, and if the partial discharge is detected to be noise, finishing the judgment; if the partial discharge is detected, the phase of the partial discharge signal is finally determined, and then the step S3 is performed;
s3, real-time signal source position distribution classification judgment: reducing waveform data acquired by the phase of the finally determined partial discharge signal into a displayable waveform based on a waveform reduction technology, automatically positioning the detection signal according to the displayable waveform, calculating the occurrence position repetition rate according to the position distribution of automatic positioning, and finally judging partial discharge and sending an alarm signal if the occurrence position repetition rate is greater than a set value; otherwise, judging as noise and ending the judgment.
2. The method for discriminating multiple complementary partial discharge of a fuzzy discrimination logic gate according to claim 1, wherein the discrimination of the feature similarity of the three-phase phi-Q-N map specifically comprises: converting the phi-Q-N data storage value of the detection signal into a new map, calculating a new characteristic value of the new map, carrying out similarity one-to-one comparison on the new characteristic value and all map characteristic values in a map library to obtain a plurality of map similarities, outputting a result when the maximum value of all map similarities exceeds a set value, and otherwise, outputting no result; and when a result is output, comparing the new characteristic value with the partial discharge characteristic value samples in the atlas library one by one to obtain a plurality of partial discharge similarities, judging partial discharge when the maximum value of all the partial discharge similarities exceeds a set value, and otherwise, judging noise.
3. The method according to claim 1, wherein the waveform data of the three-phase detection signal is restored to a displayable new waveform shape, the new waveform shape is compared with all waveform shapes in the waveform database one by one to obtain a plurality of waveform similarities, when a maximum value of all the waveform similarities is greater than a preset value, a result is output, otherwise, no result is obtained; and when a result is output, comparing the new waveform shape with the partial discharge waveform samples marked in the waveform database one by one to obtain a plurality of partial discharge waveform similarities, and judging partial discharge when the maximum value of all the partial discharge waveform similarities is greater than a preset value, otherwise, judging noise.
4. The method according to claim 1, wherein the waveform polarity is determined as: presetting a waveform trigger value in a system, judging that the polarity of a waveform is positive when a first value of waveform data of a detection signal is greater than the waveform trigger value, and otherwise, judging that the polarity of the waveform is negative; when the waveform polarity of one phase in the three-phase cable is opposite to that of other two phases, the two-time judgment is partial discharge, and the phase is preliminarily determined to be the phase of a partial discharge signal; otherwise, judging as noise and ending the judgment.
5. The fuzzy recognition logic gate multiple complementary partial discharge discrimination method of claim 1, wherein the discharge amount comparison discrimination is: when the discharge amount of the phase where the partial discharge signal is located is determined to be larger than that of the other two phases preliminarily, judging the phase as the partial discharge again, and finally determining the phase as the phase where the partial discharge signal is located; otherwise, judging as noise and ending the judgment.
6. The method according to claim 2, wherein when the maximum value of all partial discharge similarities exceeds a set value, the new eigenvalue of the new atlas is marked and stored as a sample in the atlas database.
7. The method according to claim 3, wherein when the maximum value of the similarity of all partial discharge waveforms is greater than a predetermined value, the waveform shape flag of the detection signal is stored as a sample in a waveform database.
8. A fuzzy recognition logic gate multiple complementary partial discharge discriminating device is characterized by comprising:
the three-phase phi-Q-N map feature similarity judging module is used for judging the three-phase phi-Q-N map feature similarity of the received detection signal and preliminarily judging whether the detection signal is partial discharge or noise;
the three-phase waveform characteristic analogy judging module is used for carrying out three-phase waveform characteristic analogy judgment on the received detection signal and preliminarily judging whether the detection signal is partial discharge or noise;
the interphase correlation judging module is used for judging the advanced waveform polarity of the detection signal which is judged to be partially discharged by the three-phase waveform feature analogy judging module and the three-phase phi-Q-N map feature similarity judging module, judging whether the detection signal is partially discharged or noise secondarily according to the waveform polarity judging result, and finishing the judgment if the detection signal is noise; if the partial discharge is detected, preliminarily determining the phase of the partial discharge signal, comparing and judging the discharge quantity of the phase, judging whether the partial discharge is detected to be noise or not again according to the comparison and judgment result of the discharge quantity, and if the partial discharge is detected to be noise, finishing the judgment; if the partial discharge is adopted, the phase of the partial discharge signal is finally determined;
and the real-time signal source position distribution classification judging module is used for reducing the waveform data according to the phase of the partial discharge signal finally determined by the interphase correlation judging module, automatically positioning various signal sources and finally judging whether the partial discharge signal is noise or not according to the position distribution and the occurrence position repetition rate.
9. The fuzzy recognition logic gate multiple complementary partial discharge discriminating device of claim 8 wherein said inter-phase correlation discriminating module comprises:
the waveform polarity judging unit is used for presetting a waveform trigger value in the system, judging that the waveform polarity is positive when a first value of waveform data of the detection signal is greater than the waveform trigger value, and judging that the waveform polarity is negative if the first value is not greater than the waveform trigger value; when the waveform polarity of one phase in the three-phase cable is opposite to that of other two phases, the two-time judgment is partial discharge, and the phase is preliminarily determined to be the phase of a partial discharge signal; otherwise, judging as noise and finishing the judgment;
the discharge quantity comparison and judgment unit is used for comparing the discharge quantity of the phase where the partial discharge signal is preliminarily determined by the waveform polarity judgment unit with the discharge quantities of other two phases, judging the phase as partial discharge again when the discharge quantity of the phase where the partial discharge signal is preliminarily determined to be larger than the discharge quantities of the other two phases, and finally determining the phase as the phase where the partial discharge signal is located; otherwise, judging as noise and ending the judgment.
10. The apparatus of claim 8, wherein the real-time signal source location distribution classification module comprises:
the waveform restoring unit is used for restoring the acquired waveform data into a displayable waveform;
the waveform positioning unit is used for automatically positioning the detection signal according to the displayable waveform;
a waveform position repetition rate calculation unit for calculating the occurrence position repetition rate according to the automatically positioned position distribution;
a final judging unit for finally judging whether the partial discharge or the noise is generated according to the repetition rate of the occurrence position;
and the alarm unit is used for receiving the signal of the final judging unit and sending an alarm signal.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011322970.5A CN112446320B (en) | 2020-11-23 | 2020-11-23 | Fuzzy recognition logic gate multiple complementary partial discharge distinguishing device and method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011322970.5A CN112446320B (en) | 2020-11-23 | 2020-11-23 | Fuzzy recognition logic gate multiple complementary partial discharge distinguishing device and method |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN112446320A true CN112446320A (en) | 2021-03-05 |
| CN112446320B CN112446320B (en) | 2022-03-29 |
Family
ID=74738688
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202011322970.5A Active CN112446320B (en) | 2020-11-23 | 2020-11-23 | Fuzzy recognition logic gate multiple complementary partial discharge distinguishing device and method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112446320B (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113238128A (en) * | 2021-05-11 | 2021-08-10 | 广州智丰电气科技有限公司 | Circulating progressive partial discharge discrimination method |
| CN113821427A (en) * | 2020-06-18 | 2021-12-21 | 北京新能源汽车股份有限公司 | Test result detection method and device |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| EP2321661A1 (en) * | 2008-08-06 | 2011-05-18 | Eskom Holdings Limited | Partial discharge monitoring method and system |
| US20110172970A1 (en) * | 2008-07-14 | 2011-07-14 | Chang-Won Kang | Apparatus for removing the partial discharge noise of an electrical power facility and apparatus for detecting a partial discharge generated section |
| CN103645425A (en) * | 2013-11-15 | 2014-03-19 | 广东电网公司电力科学研究院 | High-voltage cable insulation defect partial discharge on-line monitoring diagnosis method |
| US20150185270A1 (en) * | 2012-12-28 | 2015-07-02 | State Grid Corporation Of China | Method for recognizing transformer partial discharge pattern based on singular value decomposition algorithm |
| CN105203936A (en) * | 2015-10-26 | 2015-12-30 | 云南电网有限责任公司电力科学研究院 | Method for determining power cable partial discharge defect type based on spectral analysis |
| CN106950482A (en) * | 2017-05-09 | 2017-07-14 | 广东电网有限责任公司珠海供电局 | A kind of corona ELIMINATION OF ITS INTERFERENCE method based on alternate signal collection of illustrative plates similarity relation |
| CN109633395A (en) * | 2019-01-24 | 2019-04-16 | 保定华创电气有限公司 | A kind of measurement of local discharge signal and localization method |
| CN109799434A (en) * | 2019-03-01 | 2019-05-24 | 深圳供电局有限公司 | PD Pattern Recognition system and method |
-
2020
- 2020-11-23 CN CN202011322970.5A patent/CN112446320B/en active Active
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20110172970A1 (en) * | 2008-07-14 | 2011-07-14 | Chang-Won Kang | Apparatus for removing the partial discharge noise of an electrical power facility and apparatus for detecting a partial discharge generated section |
| EP2321661A1 (en) * | 2008-08-06 | 2011-05-18 | Eskom Holdings Limited | Partial discharge monitoring method and system |
| US20150185270A1 (en) * | 2012-12-28 | 2015-07-02 | State Grid Corporation Of China | Method for recognizing transformer partial discharge pattern based on singular value decomposition algorithm |
| CN103645425A (en) * | 2013-11-15 | 2014-03-19 | 广东电网公司电力科学研究院 | High-voltage cable insulation defect partial discharge on-line monitoring diagnosis method |
| CN105203936A (en) * | 2015-10-26 | 2015-12-30 | 云南电网有限责任公司电力科学研究院 | Method for determining power cable partial discharge defect type based on spectral analysis |
| CN106950482A (en) * | 2017-05-09 | 2017-07-14 | 广东电网有限责任公司珠海供电局 | A kind of corona ELIMINATION OF ITS INTERFERENCE method based on alternate signal collection of illustrative plates similarity relation |
| CN109633395A (en) * | 2019-01-24 | 2019-04-16 | 保定华创电气有限公司 | A kind of measurement of local discharge signal and localization method |
| CN109799434A (en) * | 2019-03-01 | 2019-05-24 | 深圳供电局有限公司 | PD Pattern Recognition system and method |
Non-Patent Citations (1)
| Title |
|---|
| 罗新，等: "基于小波包分解的XLPE配电电缆局部放电波形特征提取与识别", 《高压电器》 * |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113821427A (en) * | 2020-06-18 | 2021-12-21 | 北京新能源汽车股份有限公司 | Test result detection method and device |
| CN113238128A (en) * | 2021-05-11 | 2021-08-10 | 广州智丰电气科技有限公司 | Circulating progressive partial discharge discrimination method |
Also Published As
| Publication number | Publication date |
|---|---|
| CN112446320B (en) | 2022-03-29 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111024728B (en) | Railway detection method and system based on computer vision and ultrasonic flaw detection | |
| CN112446320B (en) | Fuzzy recognition logic gate multiple complementary partial discharge distinguishing device and method | |
| CN113124929A (en) | Transformer substation multi-parameter signal acquisition comprehensive analysis system and method | |
| CN106093722B (en) | A kind of positioning and recognition methods of cable local discharge | |
| CN104994334A (en) | Automatic substation monitoring method based on real-time video | |
| CN111007365A (en) | Ultrasonic partial discharge identification method and system based on neural network | |
| CN112669879B (en) | Air conditioner indoor unit noise anomaly detection method based on time-frequency domain deep learning algorithm | |
| CN115128345B (en) | Power grid safety early warning method and system based on harmonic monitoring | |
| CN111398798A (en) | Circuit breaker energy storage state identification method based on vibration signal interval characteristic extraction | |
| CN113805018A (en) | Intelligent identification method for partial discharge fault type of 10kV cable of power distribution network | |
| CN113607271A (en) | GIL defect online monitoring system and method based on vibration signals | |
| CN108682101A (en) | Vibration optical fiber intrusion event detection method based on double threshold method | |
| Niu et al. | Identification of partial discharge phenomena in HVDC apparatus | |
| CN106324437A (en) | Method for detecting hidden discharge current based on voltage extreme value | |
| CN111767913A (en) | Motor train unit vehicle fault dynamic image detection method based on deep learning | |
| CN112801466A (en) | Method and system for early warning illegal operation of oil discharge operation of gas station | |
| CN116845863A (en) | Terminal power grid abnormal equipment access alarm method and device based on space-time track | |
| CN106443238B (en) | High-voltage equipment state evaluation method, online monitoring device evaluation method and device | |
| CN110346032A (en) | A kind of Φ-OTDR vibration signal end-point detecting method combined based on constant false alarm with zero-crossing rate | |
| CN110674827A (en) | Equipment state visual detection method integrating deep learning and morphological filtering | |
| CN107909757B (en) | Vibration source early warning method of optical fiber vibration safety early warning system based on sequential detection | |
| CN111025288B (en) | Security radar monitoring device and system | |
| CN115690659A (en) | Transformer substation safety detection method and device under shielding condition | |
| CN109917245B (en) | Ultrasonic detection partial discharge signal mode identification method considering phase difference | |
| CN110907544B (en) | Identification method for abnormal step data of content of dissolved gas in transformer oil |
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 |