CN113053412A - Sound-based transformer fault identification method - Google Patents
Sound-based transformer fault identification method Download PDFInfo
- Publication number
- CN113053412A CN113053412A CN202110155771.8A CN202110155771A CN113053412A CN 113053412 A CN113053412 A CN 113053412A CN 202110155771 A CN202110155771 A CN 202110155771A CN 113053412 A CN113053412 A CN 113053412A
- Authority
- CN
- China
- Prior art keywords
- transformer
- amplitude
- sound
- harmonic
- signal
- 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
- 238000000034 method Methods 0.000 title claims abstract description 29
- 230000005236 sound signal Effects 0.000 claims abstract description 92
- 230000008859 change Effects 0.000 claims abstract description 32
- 238000007781 pre-processing Methods 0.000 claims abstract description 6
- 230000002093 peripheral effect Effects 0.000 claims description 47
- 230000000750 progressive effect Effects 0.000 claims description 39
- 238000012216 screening Methods 0.000 claims description 22
- 230000035772 mutation Effects 0.000 claims description 16
- 238000012544 monitoring process Methods 0.000 claims description 10
- 238000012545 processing Methods 0.000 claims description 10
- 238000005070 sampling Methods 0.000 claims description 6
- 230000002159 abnormal effect Effects 0.000 claims description 4
- 230000003321 amplification Effects 0.000 claims description 3
- 238000001914 filtration Methods 0.000 claims description 3
- 238000003199 nucleic acid amplification method Methods 0.000 claims description 3
- 230000011218 segmentation Effects 0.000 claims description 3
- 238000010586 diagram Methods 0.000 description 8
- 238000004590 computer program Methods 0.000 description 7
- 238000004422 calculation algorithm Methods 0.000 description 6
- 230000006870 function Effects 0.000 description 4
- 230000003993 interaction Effects 0.000 description 4
- 238000001514 detection method Methods 0.000 description 3
- 238000000605 extraction Methods 0.000 description 3
- 238000004364 calculation method Methods 0.000 description 2
- 238000004891 communication Methods 0.000 description 2
- 230000008569 process Effects 0.000 description 2
- 238000004458 analytical method Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000006243 chemical reaction Methods 0.000 description 1
- 230000017525 heat dissipation Effects 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 230000000737 periodic effect Effects 0.000 description 1
- 230000000007 visual effect Effects 0.000 description 1
Images
Classifications
-
- 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
- G10L25/51—Speech or voice analysis techniques not restricted to a single one of groups G10L15/00 - G10L21/00 specially adapted for particular use for comparison or discrimination
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01H—MEASUREMENT OF MECHANICAL VIBRATIONS OR ULTRASONIC, SONIC OR INFRASONIC WAVES
- G01H17/00—Measuring mechanical vibrations or ultrasonic, sonic or infrasonic waves, not provided for in the preceding groups
-
- 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
- G10L25/03—Speech or voice analysis techniques not restricted to a single one of groups G10L15/00 - G10L21/00 characterised by the type of extracted parameters
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y04—INFORMATION OR COMMUNICATION TECHNOLOGIES HAVING AN IMPACT ON OTHER TECHNOLOGY AREAS
- Y04S—SYSTEMS INTEGRATING TECHNOLOGIES RELATED TO POWER NETWORK OPERATION, COMMUNICATION OR INFORMATION TECHNOLOGIES FOR IMPROVING THE ELECTRICAL POWER GENERATION, TRANSMISSION, DISTRIBUTION, MANAGEMENT OR USAGE, i.e. SMART GRIDS
- Y04S10/00—Systems supporting electrical power generation, transmission or distribution
- Y04S10/50—Systems or methods supporting the power network operation or management, involving a certain degree of interaction with the load-side end user applications
- Y04S10/52—Outage or fault management, e.g. fault detection or location
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Computational Linguistics (AREA)
- Signal Processing (AREA)
- Health & Medical Sciences (AREA)
- Audiology, Speech & Language Pathology (AREA)
- Human Computer Interaction (AREA)
- Acoustics & Sound (AREA)
- Multimedia (AREA)
- General Physics & Mathematics (AREA)
- Protection Of Transformers (AREA)
Abstract
The invention discloses a transformer fault identification method based on sound, which mainly comprises the steps of collecting sound signals beside a transformer and at the periphery of the transformer and preprocessing the sound signals; extracting the amplitude of each harmonic component of the sound signal beside the transformer and the amplitude of each harmonic component of the sound signal at the periphery of the transformer; calculating the amplitude of each harmonic component of the sound signal emitted by the transformer based on the extracted amplitude of each harmonic component; and identifying the running state of the transformer based on the amplitude of each harmonic component of the sound signal emitted by the transformer. The invention can find the transformer fault in time through the characteristics and the abrupt change of the site sound of the transformer, thereby ensuring the safe and stable operation of the transformer.
Description
Technical Field
The invention relates to a sound-based transformer fault identification method, and belongs to the technical field of transformer detection.
Background
The power transformer always generates uniform sound due to mechanical vibration in the operation process, and the sound under normal operation has certain regularity. When a certain fault occurs in the equipment, the sound emitted by the equipment is changed along with the change of the running state. Whether the equipment is in an abnormal operation state or not can be judged through changes of audio characteristics such as tone color, volume, frequency and the like of sound, and even the type and the severity of a fault can be judged.
Disclosure of Invention
The invention aims to provide a sound-based transformer fault identification method, which can timely find out transformer faults and ensure safe and stable operation of a transformer by monitoring the characteristics and the abrupt change of field sound of the transformer on line.
In order to achieve the purpose, the technical scheme adopted by the invention is as follows:
the invention provides a sound-based transformer fault identification method, which comprises the following steps:
collecting and preprocessing noise signals beside and around the transformer;
extracting the amplitude of each harmonic component of the sound signal beside the transformer and the amplitude of each harmonic component of the peripheral noise signal of the transformer;
calculating the amplitude of each harmonic component of the sound signal emitted by the transformer based on the extracted amplitude of each harmonic component;
and identifying the state of the transformer based on the amplitude of each harmonic component of the sound signal emitted by the transformer.
Further, the method also comprises the following steps:
2 sound collecting sensors are arranged beside the transformer and used for monitoring sound signals beside the transformer;
and 3 sound collecting sensors are arranged on the periphery of the transformer and used for monitoring the peripheral noise signals of the transformer.
Further, the collecting and preprocessing of the noise signals beside and around the transformer includes:
sequentially carrying out data filtering, signal unification processing, data amplification and data segmentation processing on the sound signals acquired by the sound acquisition sensor;
and the number of the first and second groups,
sound signals above 1500Hz are filtered out.
Further, the extracting the amplitudes of the harmonic components of the sound signal beside the transformer includes:
the average value of the sound signals detected by the 2 sound collecting sensors beside the transformer is used as the sound signal beside the transformer, and every N sound signals are processed1Performing Fourier transform on the sound signal beside the transformer corresponding to each power frequency period every N times2The sub-Fourier transform corresponds to a discrimination period, and the sound signal by the transformer in the i-th discrimination period is calculated2Maximum value Y of amplitude corresponding to k-th harmonic after sub-Fourier transformik_maxAnd minimum value of Yik_min;
According to Yik_maxAnd Yik_minCalculating the average value: y isik_ave=(Yik_max+Yik_min)/2;
Statistics of YijkGreater than Yik_aveIs m, is less than Yik_aveThe number of (a) is n, note,
wherein, YijkThe sound signal of the side of the transformer in the ith judgment period is subjected to jth Fourier transform, and then the kth harmonic corresponds to the amplitude, wherein j is 1,2, ┄ N2,k=1,2,┄30;
If e is less than or equal to 10%, obtaining the amplitude YY corresponding to the kth harmonic of the sound signal beside the ith period-discriminating transformerik=Yik_aveAnd ending;
if e is more than 10% and m is more than or equal to n, let Yik_ave=(Yik_max+Yik_ave) 2, recalculating m and n until e is less than or equal to 10%;
if e > 10% and m < n, let Yik_ave=(Yik_min+Yik_ave) And/2, recalculating m and n until e is less than or equal to 10%.
Further, extracting the amplitude of each harmonic component of the peripheral noise signal of the transformer includes:
taking the average value of sound signals detected by 3 sound acquisition sensors at the periphery of the transformer as a peripheral noise signal, and extracting the direct current component of the peripheral noise signal:
among them, YG0iRepresenting the direct current component, Yg, of the peripheral noise signal of the ith discriminating transformericbaRepresenting a transformer peripheral noise signal corresponding to an a-th sampling point in a b-th power frequency period in a c-th Fourier transform period in an i-th discrimination period, and F representing a sampling period;
calculating the difference between the direct current components of the peripheral noise signal and the peripheral noise signal to obtain the alternating current component of the peripheral noise signal;
and extracting the amplitude of each harmonic component of the alternating current component of the peripheral noise signal by utilizing Fourier transform.
Further, the calculating the amplitudes of the harmonic components of the sound signal emitted by the transformer based on the extracted amplitudes of the harmonic components includes:
carrying out amplitude mutation screening on the amplitude of each harmonic component of the sound signal beside the transformer and the amplitude of each harmonic component of the peripheral noise signal of the transformer;
calculating the amplitude of each harmonic component of the sound signal actually emitted by the transformer based on the amplitude of each harmonic component after screening:
YSik=YYYik-YGGik
wherein YSikFor the i-th discriminating period transformer, the amplitude, YYY, corresponding to the k-th harmonic of the actual sound signalikFor the ith judgment period transformer side sound signal after the amplitude mutation screening, the corresponding amplitude, YGG, of the kth harmonic waveikAnd the amplitude value corresponding to the kth harmonic wave of the peripheral noise signal of the ith period-discriminating transformer after amplitude value mutation screening.
Further, in the above-mentioned case,
carrying out amplitude mutation screening on amplitude values of harmonic components of sound signals beside the transformer, and the method comprises the following steps:
if YYikYYY satisfies the following conditionsik=YYikOtherwise YYYYik=YY(i-1)k,
Wherein E is1kRepresenting the maximum allowable error of the amplitude of the kth harmonic corresponding to the sound signal beside the transformer between two discrimination periods, E1zRepresenting the maximum allowable error of the harmonic amplitude corresponding to the sound signal beside the transformer between two discrimination periods;
carrying out amplitude mutation screening on amplitude values of harmonic components of peripheral noise signals of the transformer, wherein the screening comprises the following steps:
if YGikSatisfy the following conditions, YGGik=YGikOtherwise YGGik=YG(i-1)k,
Wherein, YGikFor discriminating peripheral noise signals of the transformer for the ith cycleAmplitude, E, corresponding to the k-th harmonic2kRepresenting the maximum allowable error of the k-th harmonic amplitude corresponding to the peripheral noise signal of the transformer between two discrimination periods, E2zAnd the maximum allowable error of the harmonic amplitude corresponding to the peripheral noise signal of the transformer between two discrimination periods is represented.
Further, the method also comprises the following steps:
extracting the amplitude of each harmonic component of the sound signal beside the transformer and the amplitude of each harmonic component of the sound signal at the periphery of the transformer in the normal state of the transformer;
calculating the amplitude of each harmonic component of the sound signal actually emitted by the transformer in a normal state;
and taking the maximum value and the minimum value of the amplitude of each harmonic component of the sound signal actually emitted by the transformer in the calculated discrimination period to form the amplitude range of each sub-harmonic component of the sound signal actually emitted by the transformer in the normal state, and storing the amplitude range in a normal sound library.
Further, the identifying the transformer state based on the amplitude of each harmonic component of the sound signal emitted by the transformer includes:
two discrimination modes of the transformer state are defined,
mode 1: determining whether the 30 times transformer sound harmonic amplitude is within the range of the normal sound library,
1a) when the ith judgment period transformer actually sends out the amplitude YS of the 1 st harmonic component of the sound signali1Amplitude range [ YS ] of 1 st harmonic component exceeding normal sound library signal of transformermin1,YSmax1]When the intermediate discrimination variable S is 1;
1b) when the ith judgment period transformer actually sends out the amplitude YS of the 2 nd harmonic component of the sound signali2Amplitude range [ YS ] of 2 nd harmonic component exceeding normal sound library signal of transformermin2,YSmax2]When the intermediate discrimination variable S is 1;
1c) when the ith judgment period transformer actually sends out the 4 th harmonic component amplitude YS of the sound signali4Out of the 4 th harmonic component amplitude range [ YS ] of the normal sound library signal of the transformermin4,YSmax4]When the intermediate discrimination variable S is 1;
1d) when 3 or more frequencies in 30-order harmonic amplitude values of sound signals actually emitted by the ith judgment period transformer exceed the amplitude range of corresponding sub-harmonic components of normal sound library signals of the transformer, the intermediate judgment variable S is 1;
1e) except for 1a), 1b), 1c) and 1d), S is 0;
[YSmink,YSmaxk]representing the amplitude range of the kth harmonic component of the sound signal in the normal state of the transformer, wherein k is 1,2, ┄ 30;
mode 2: judging whether the amplitude-frequency progressive parameter is in a normal range,
calculating amplitude-frequency progressive parameter k of normal sound library signal of transformerl:
Calculating the amplitude-frequency progressive parameter of the actually-emitted sound signal of the ith period-discriminating transformer
The conditions for judging the state of the transformer based on the amplitude-frequency progressive parameters are as follows:
2a) rate of change of amplitude-frequency progressive parameter in i-th discrimination periodMaximum allowable change rate E of amplitude-frequency progressive parameter greater than 1 ste1When T is 1;
2b) rate of change of amplitude-frequency progressive parameter in i-th discrimination periodGreater than the maximum allowable rate of change E of the 2 nd amplitude-frequency progressive parametere2When T is 1;
2c) rate of change of amplitude-frequency progressive parameter in i-th discrimination periodMaximum allowable change rate E of amplitude-frequency progressive parameter greater than 3 rde3When T is 1;
2d) when the number of the 29 amplitude-frequency progressive parameter change rates in the ith judgment period which are larger than the maximum allowable change rate of the corresponding amplitude-frequency progressive parameter is larger than or equal to 3, T is 1;
2e) except for 2a), 2b), 2c) and 2d), T is 0;
taking the result of the two transformer state judging modes as an OR operation, and taking the result as a judging result G of the transformer state, wherein G is equal to S | T;
when G is 1, the state of the transformer is abnormal, namely a fault occurs;
when G is 0, the transformer state is normal.
The invention achieves the following beneficial effects:
the invention provides a sound-based transformer fault identification method, which can be used for timely finding out transformer faults and ensuring safe and stable operation of a transformer by monitoring the characteristics and the abrupt change of field sound of the transformer on line.
Drawings
Fig. 1 is a flow chart of a transformer fault identification method of the invention.
Detailed Description
The invention is further described below. The following examples are only for illustrating the technical solutions of the present invention more clearly, and the protection scope of the present invention is not limited thereby.
The embodiment of the invention provides a sound-based transformer fault recognition device which comprises an external sensor module, a control circuit, a human-computer interaction interface and a communication system.
Specifically, the external sensor module is provided with 5 sound collection sensors, 2 of the sound collection sensors are arranged beside the transformer and used for monitoring the sound of the transformer, and 3 sound collection sensors are arranged on the periphery of the transformer and used for monitoring the surrounding interference noise.
The control circuit is used for extracting the sound signals collected by the external sensor module in real time and comparing the sound signals with the signal amplitude of the normal sound library to realize transformer fault identification.
The human-computer interaction interface is used for setting state reminding and audible and visual alarm, and can monitor the running state of the transformer visually.
The communication system is used for interaction between the transformer fault identification device and the monitoring system.
In this embodiment, the human-computer interaction interface adopts an anti-interference housing, which is provided with a heat dissipation outlet.
The embodiment of the invention also provides a transformer fault identification method, as shown in fig. 1, which specifically comprises the following steps:
step 1: and preprocessing the collected sound signals.
The sound signal collected by the sound collection sensor needs to be subjected to four links of data filtering, signal unification processing, data amplification, data segmentation and the like in sequence. Meanwhile, according to the analysis of the operation and fault vibration sound of the field transformer, the frequency of the vibration and discharge sound of the transformer rarely appears above 1500Hz, so that sound signals higher than 1500Hz are firstly filtered during pretreatment.
Step 2: the amplitude of the sound signal near the transformer is extracted.
Taking the average value of the sound signals detected by the 2 sound acquisition sensors beside the transformer as the sound signals near the transformer;
for every N1Carrying out Fourier transform once on sound signals near the transformer corresponding to each power frequency period, wherein every N is2The sub-Fourier transform corresponds to a discrimination period, and the sound signal near the transformer with the ith discrimination period is subjected to the jth Fourier transformThe corresponding amplitude of the k-th harmonic after the conversion is Yijk,j=1,2,┄N2,k=1,2,┄30;
Setting the amplitude corresponding to the kth harmonic of the sound signal near the ith discrimination period transformer after being processed as YYikThe calculation method is as follows:
(1) calculating the sound signal passing through N near the i-th discrimination period transformer2Maximum value Y of amplitude corresponding to k-th harmonic after sub-Fourier transformik_maxAnd minimum value of Yik_min;
(2) According to Yik_maxAnd Yik_minCalculating the average value Yik_ave=(Yik_max+Yik_min)/2;
(3) Statistics of YijkGreater than Yik_aveM, is less than Yik_aveThe number n of (a), in terms of,
if e is less than or equal to 10%, YYik=Yik_aveAnd ending;
if e is more than 10% and m is more than or equal to n, let Yik_ave=(Yik_max+Yik_ave) 2, recalculating m and n until e is less than or equal to 10%;
if e > 10% and m < n, let Yik_ave=(Yik_min+Yik_ave) And/2, recalculating m and n until e is less than or equal to 10%.
And step 3: and extracting the amplitude of the peripheral noise signal of the transformer.
The method comprises the steps of monitoring sound interference signals of different frequencies around the transformer by using 3 noise sensors on the periphery of the transformer, wherein the sound interference signals mainly comprise wind sound, rain sound, mechanical collision, vehicle noise, animal sound (including human) and sound of nearby equipment.
The average value of signals collected by 3 noise sensors on the periphery of the transformer is used as a peripheral noise signal, and the direct current component of the peripheral noise signal is firstly extracted, wherein the calculation method comprises the following steps:
in the formula, YG0iRepresenting the direct current component, Yg, of the peripheral noise signal of the ith discriminating transformericbaAnd F represents a sampling period, and the value of F is more than or equal to 3000Hz according to the sampling theorem. In this step, the period, N, is determined1And N2The definition of the method is the same as that of the steps.
The difference between the direct current components of the peripheral noise signal and the peripheral noise signal is the alternating current component of the peripheral noise signal;
extracting the amplitude of the alternating current component of the peripheral noise signal by utilizing Fourier transform, wherein the extraction process is consistent with the extraction process of the amplitude of the sound signal near the transformer, and the corresponding amplitude of the kth harmonic of the peripheral noise signal of the ith discrimination period transformer is YG after extraction processingik。
And 4, step 4: and calculating the amplitude of the sound signal emitted by the transformer.
Firstly, introducing an amplitude mutation screening algorithm to carry out Fourier transform on detection signals of two sound acquisition sensors beside a transformer to obtain amplitude YYikScreening again, YYikThe following conditions should be satisfied:
in the formula, E1kRepresenting the maximum allowable error of the amplitude of the kth harmonic corresponding to the sound signal near the transformer between two discrimination periods; e1zIndicating the maximum allowable error between two discrimination periods of the harmonic amplitude corresponding to the sound signal near the transformer.
When YY isikWhen the conditions are met, introducing an amplitude mutation screening algorithm and then judging the amplitude YYY corresponding to the kth harmonic of the sound signal near the periodic transformerik=YYik(ii) a Otherwise, consider YYikTo interfere with, ignore thisValue, the amplitude YYY corresponding to the k-th harmonic of the sound signal near the i-th discrimination period transformer after introducing the amplitude mutation screening algorithmik=YY(i-1)k。
Fourier transform amplitude YG of detection signals of three sound acquisition sensors at periphery of transformer based on amplitude mutation screening algorithmikPerforming a second screening of YGikThe following conditions should be satisfied:
in the formula, E2kRepresenting the maximum allowable error of the k-th harmonic amplitude corresponding to the peripheral noise signal of the transformer between two discrimination periods; e2zAnd the maximum allowable error of the harmonic amplitude corresponding to the peripheral noise signal of the transformer between two discrimination periods is represented.
When YGikWhen the conditions are met, the amplitude YGG corresponding to the kth harmonic of the peripheral noise signal of the ith discrimination period transformer is introduced into the amplitude mutation screening algorithmik=YGik(ii) a Otherwise consider YGikIf the value is ignored for interference, the amplitude value mutation screening algorithm is introduced, and then the amplitude YGG corresponding to the k-th harmonic of the peripheral noise signal of the i-th discrimination period transformer is introducedik=YG(i-1)k。
According to YYYikAnd YGGikThe corresponding amplitude YS of the kth harmonic of the sound signal actually emitted by the ith period-discriminating transformer can be obtainedikI.e. YSik=YYYik-YGGik。
Based on the method, the amplitude corresponding to the sound signal sent by the transformer in the normal state can be obtained, namely the normal sound library signal.
Considering that the amplitude corresponding to the sound signal sent out by the transformer in the normal state is not a fixed value and should be changed within a certain range, N is carried out on the sound signal sent out by the transformer in the normal state3(N3Fourier transform of more than or equal to 100) discrimination periods, taking N3The maximum amplitude corresponding to the kth harmonic in each discrimination period is YSmaxk,N3The minimum amplitude corresponding to the k-th harmonic in each discrimination period is YSminkThat is, the corresponding amplitude of the kth harmonic wave of the sound signal generated under the normal state of the transformer is [ YSmink,YSmaxk]To change between.
And 5: and judging the running state of the transformer.
Two discrimination modes of the running state of the transformer are defined.
Mode 1: judging whether the sound harmonic amplitude of the 30-time transformer is in the range of a normal sound library, wherein the specific judgment conditions are as follows:
1a) when the ith discrimination period transformer actually sends out the amplitude YS of the 1 st harmonic component (50Hz) of the sound signali1Amplitude range [ YS ] of 1 st harmonic component exceeding normal sound library signal of transformermin1,YSmax1]When the intermediate discrimination variable S is 1;
1b) when the ith discrimination period transformer actually sends out the amplitude YS of the 2 nd harmonic component (100Hz) of the sound signali2Amplitude range [ YS ] of 2 nd harmonic component exceeding normal sound library signal of transformermin2,YSmax2]When the intermediate discrimination variable S is 1;
1c) when the ith discrimination period transformer actually sends out the 4 th harmonic component (200Hz) amplitude YS of the sound signali4Out of the 4 th harmonic component amplitude range [ YS ] of the normal sound library signal of the transformermin4,YSmax4]When the intermediate discrimination variable S is 1;
1d) when the ith judgment period transformer actually sends out 30 harmonic amplitude YS of sound signalikWherein 3 or more frequencies exceed the amplitude range [ YS ] of subharmonic component corresponding to the normal sound library signal of the transformermink,YSmaxk]When the intermediate discrimination variable S is 1;
1e) except 1a), 1b), 1c) and 1d), S is 0.
Mode 2: judging whether the amplitude-frequency progressive parameter is in a normal range,
signal amplitude-frequency progressive parameter k for transformer normal sound banklCan be expressed as:
amplitude-frequency progressive parameter for judging actually-sent sound signal of i-th period transformerCan be expressed as:
the judgment condition of the running state of the transformer based on the amplitude-frequency progressive parameters is as follows:
2a) rate of change of amplitude-frequency progressive parameter in i-th discrimination periodMaximum allowable change rate E of amplitude-frequency progressive parameter greater than 1 ste1When T is 1;
2b) rate of change of amplitude-frequency progressive parameter in i-th discrimination periodGreater than the maximum allowable rate of change E of the 2 nd amplitude-frequency progressive parametere2When T is 1;
2c) rate of change of amplitude-frequency progressive parameter in i-th discrimination periodMaximum allowable change rate E of amplitude-frequency progressive parameter greater than 3 rde3When T is 1;
2d) when the number of the 29 amplitude-frequency progressive parameter change rates in the ith judgment period which are larger than the maximum allowable change rate of the corresponding amplitude-frequency progressive parameter is larger than or equal to 3, T is 1;
2e) except 2a), 2b), 2c) and 2d), T is 0.
And taking the result of the two transformer operation state judging modes as an OR operation to be used as a judging result G of the transformer operation state, namely G is equal to S | T.
When G is 1, the operation state of the transformer is abnormal;
when G is 0, the transformer operation state is normal.
As will be appreciated by one skilled in the art, embodiments of the present application may be provided as a method, system, or computer program product. Accordingly, the present application may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present application may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and the like) having computer-usable program code embodied therein.
The present application is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the application. It will be understood that each flow and/or block of the flow diagrams and/or block diagrams, and combinations of flows and/or blocks in the flow diagrams and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
Finally, it should be noted that: the above embodiments are only for illustrating the technical solutions of the present invention and not for limiting the same, and although the present invention is described in detail with reference to the above embodiments, those of ordinary skill in the art should understand that: modifications and equivalents may be made to the embodiments of the invention without departing from the spirit and scope of the invention, which is to be covered by the claims.
Claims (9)
1. A sound-based transformer fault identification method is characterized by comprising the following steps:
collecting and preprocessing noise signals beside and around the transformer;
extracting the amplitude of each harmonic component of the sound signal beside the transformer and the amplitude of each harmonic component of the peripheral noise signal of the transformer;
calculating the amplitude of each harmonic component of the sound signal emitted by the transformer based on the extracted amplitude of each harmonic component;
and identifying the state of the transformer based on the amplitude of each harmonic component of the sound signal emitted by the transformer.
2. The method of claim 1, further comprising:
2 sound collecting sensors are arranged beside the transformer and used for monitoring sound signals beside the transformer;
and 3 sound collecting sensors are arranged on the periphery of the transformer and used for monitoring the peripheral noise signals of the transformer.
3. The method for identifying the fault of the transformer based on the sound as claimed in claim 2, wherein the step of collecting and preprocessing the noise signals beside and around the transformer comprises the following steps:
sequentially carrying out data filtering, signal unification processing, data amplification and data segmentation processing on the sound signals acquired by the sound acquisition sensor;
and the number of the first and second groups,
sound signals above 1500Hz are filtered out.
4. The method for identifying the fault of the transformer based on the sound as claimed in claim 2, wherein the extracting the amplitudes of the harmonic components of the sound signal beside the transformer comprises:
the average value of the sound signals detected by the 2 sound collecting sensors beside the transformer is used as the sound signal beside the transformer, and every N sound signals are processed1Performing Fourier transform on the sound signal beside the transformer corresponding to each power frequency period every N times2The sub-Fourier transform corresponds to a discrimination period, and the sound signal by the transformer in the i-th discrimination period is calculated2Maximum value Y of amplitude corresponding to k-th harmonic after sub-Fourier transformik_maxAnd minimum value of Yik_min;
According to Yik_maxAnd Yik_minCalculating the average value: y isik_ave=(Yik_max+Yik_min)/2;
Statistics of YijkGreater than Yik_aveIs m, is less than Yik_aveThe number of (a) is n, note,
wherein, YijkThe amplitude corresponding to the kth harmonic wave of the sound signal beside the transformer in the ith discrimination period after the jth Fourier transformValue j 1,2, ┄ N2,k=1,2,┄30;
If e is less than or equal to 10%, obtaining the amplitude YY corresponding to the kth harmonic of the sound signal beside the ith period-discriminating transformerik=Yik_aveAnd ending;
if e is more than 10% and m is more than or equal to n, let Yik_ave=(Yik_max+Yik_ave) 2, recalculating m and n until e is less than or equal to 10%;
if e > 10% and m < n, let Yik_ave=(Yik_min+Yik_ave) And/2, recalculating m and n until e is less than or equal to 10%.
5. The method of claim 4, wherein extracting amplitudes of harmonic components of the peripheral noise signal of the transformer comprises:
taking the average value of sound signals detected by 3 sound acquisition sensors at the periphery of the transformer as a peripheral noise signal, and extracting the direct current component of the peripheral noise signal:
among them, YG0iRepresenting the direct current component, Yg, of the peripheral noise signal of the ith discriminating transformericbaRepresenting a transformer peripheral noise signal corresponding to an a-th sampling point in a b-th power frequency period in a c-th Fourier transform period in an i-th discrimination period, and F representing a sampling period;
calculating the difference between the direct current components of the peripheral noise signal and the peripheral noise signal to obtain the alternating current component of the peripheral noise signal;
and extracting the amplitude of each harmonic component of the alternating current component of the peripheral noise signal by utilizing Fourier transform.
6. The method of claim 5, wherein the calculating the amplitudes of the harmonic components of the sound signal emitted by the transformer based on the extracted amplitudes of the harmonic components comprises:
carrying out amplitude mutation screening on the amplitude of each harmonic component of the sound signal beside the transformer and the amplitude of each harmonic component of the peripheral noise signal of the transformer;
calculating the amplitude of each harmonic component of the sound signal actually emitted by the transformer based on the amplitude of each harmonic component after screening:
YSik=YYYik-YGGik
wherein YSikFor the i-th discriminating period transformer, the amplitude, YYY, corresponding to the k-th harmonic of the actual sound signalikFor the ith judgment period transformer side sound signal after the amplitude mutation screening, the corresponding amplitude, YGG, of the kth harmonic waveikAnd the amplitude value corresponding to the kth harmonic wave of the peripheral noise signal of the ith period-discriminating transformer after amplitude value mutation screening.
7. The method of claim 6, wherein the step of identifying the fault comprises,
carrying out amplitude mutation screening on amplitude values of harmonic components of sound signals beside the transformer, and the method comprises the following steps:
if YYikYYY satisfies the following conditionsik=YYikOtherwise YYYYik=YY(i-1)k,
Wherein E is1kRepresenting the maximum allowable error of the amplitude of the kth harmonic corresponding to the sound signal beside the transformer between two discrimination periods, E1zRepresenting the maximum allowable error of the harmonic amplitude corresponding to the sound signal beside the transformer between two discrimination periods;
carrying out amplitude mutation screening on amplitude values of harmonic components of peripheral noise signals of the transformer, wherein the screening comprises the following steps:
if YGikSatisfy the following conditions, YGGik=YGikOtherwise YGGik=YG(i-1)k,
Wherein, YGikFor the ith discrimination period transformer peripheral noise signal k harmonic corresponding amplitude, E2kRepresenting the maximum allowable error of the k-th harmonic amplitude corresponding to the peripheral noise signal of the transformer between two discrimination periods, E2zAnd the maximum allowable error of the harmonic amplitude corresponding to the peripheral noise signal of the transformer between two discrimination periods is represented.
8. The method of claim 6, further comprising:
extracting the amplitude of each harmonic component of the sound signal beside the transformer and the amplitude of each harmonic component of the sound signal at the periphery of the transformer in the normal state of the transformer;
calculating the amplitude of each harmonic component of the sound signal actually emitted by the transformer in a normal state;
and taking the maximum value and the minimum value of the amplitude of each harmonic component of the sound signal actually emitted by the transformer in the calculated discrimination period to form the amplitude range of each sub-harmonic component of the sound signal actually emitted by the transformer in the normal state, and storing the amplitude range in a normal sound library.
9. The method of claim 8, wherein the identifying the transformer state based on the amplitudes of the harmonic components of the sound signal emitted by the transformer comprises:
two discrimination modes of the transformer state are defined,
mode 1: determining whether the 30 times transformer sound harmonic amplitude is within the range of the normal sound library,
1a) when the ith judgment period transformer actually sends out the amplitude YS of the 1 st harmonic component of the sound signali1Amplitude range [ YS ] of 1 st harmonic component exceeding normal sound library signal of transformermin1,YSmax1]In time, inThe intermediate discrimination variable S is 1;
1b) when the ith judgment period transformer actually sends out the amplitude YS of the 2 nd harmonic component of the sound signali2Amplitude range [ YS ] of 2 nd harmonic component exceeding normal sound library signal of transformermin2,YSmax2]When the intermediate discrimination variable S is 1;
1c) when the ith judgment period transformer actually sends out the 4 th harmonic component amplitude YS of the sound signali4Out of the 4 th harmonic component amplitude range [ YS ] of the normal sound library signal of the transformermin4,YSmax4]When the intermediate discrimination variable S is 1;
1d) when 3 or more frequencies in 30-order harmonic amplitude values of sound signals actually emitted by the ith judgment period transformer exceed the amplitude range of corresponding sub-harmonic components of normal sound library signals of the transformer, the intermediate judgment variable S is 1;
1e) except for 1a), 1b), 1c) and 1d), S is 0;
[YSmink,YSmaxk]representing the amplitude range of the kth harmonic component of the sound signal in the normal state of the transformer, wherein k is 1,2, ┄ 30;
mode 2: judging whether the amplitude-frequency progressive parameter is in a normal range,
calculating amplitude-frequency progressive parameter k of normal sound library signal of transformerl:
Calculating the amplitude-frequency progressive parameter of the actually-emitted sound signal of the ith period-discriminating transformer
The conditions for judging the state of the transformer based on the amplitude-frequency progressive parameters are as follows:
2a) rate of change of amplitude-frequency progressive parameter in i-th discrimination periodMaximum allowable change rate E of amplitude-frequency progressive parameter greater than 1 ste1When T is 1;
2b) rate of change of amplitude-frequency progressive parameter in i-th discrimination periodGreater than the maximum allowable rate of change E of the 2 nd amplitude-frequency progressive parametere2When T is 1;
2c) rate of change of amplitude-frequency progressive parameter in i-th discrimination periodMaximum allowable change rate E of amplitude-frequency progressive parameter greater than 3 rde3When T is 1;
2d) when the number of the 29 amplitude-frequency progressive parameter change rates in the ith judgment period which are larger than the maximum allowable change rate of the corresponding amplitude-frequency progressive parameter is larger than or equal to 3, T is 1;
2e) except for 2a), 2b), 2c) and 2d), T is 0;
taking the result of the two transformer state judging modes as an OR operation, and taking the result as a judging result G of the transformer state, wherein G is equal to S | T;
when G is 1, the state of the transformer is abnormal, namely a fault occurs;
when G is 0, the transformer state is normal.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202110155771.8A CN113053412B (en) | 2021-02-04 | 2021-02-04 | Transformer fault identification method based on sound |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202110155771.8A CN113053412B (en) | 2021-02-04 | 2021-02-04 | Transformer fault identification method based on sound |
Publications (2)
Publication Number | Publication Date |
---|---|
CN113053412A true CN113053412A (en) | 2021-06-29 |
CN113053412B CN113053412B (en) | 2023-12-22 |
Family
ID=76508855
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202110155771.8A Active CN113053412B (en) | 2021-02-04 | 2021-02-04 | Transformer fault identification method based on sound |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN113053412B (en) |
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN115240691A (en) * | 2022-09-23 | 2022-10-25 | 山西振中电力股份有限公司 | Substation equipment running state monitoring control system based on data analysis |
CN117095695A (en) * | 2023-10-19 | 2023-11-21 | 国网山西省电力公司超高压变电分公司 | Wide-area voiceprint compression acquisition method and system for transformer body |
Citations (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP2004080952A (en) * | 2002-08-21 | 2004-03-11 | Toshiba Corp | Power failure detecting system |
AU2005100274A4 (en) * | 2004-03-31 | 2005-06-23 | Kapur, Ruchika Ms | Method and apparatus for analyising sound |
CN104167207A (en) * | 2014-06-20 | 2014-11-26 | 国家电网公司 | Equipment sound identification method based on transformer substation patrol inspection robot |
CN109029582A (en) * | 2018-08-17 | 2018-12-18 | 国网江苏省电力有限公司盐城供电分公司 | A kind of Power Transformer Faults on-line detecting system based on many kinds of parameters acquisition |
CN111141979A (en) * | 2019-12-31 | 2020-05-12 | 福建睿思特科技股份有限公司 | Fault judgment method for substation automation equipment |
CN112014774A (en) * | 2020-03-26 | 2020-12-01 | 中国铁建电气化局集团第二工程有限公司 | Transformer fault inspection system and method based on sound processing |
CN112305462A (en) * | 2020-11-09 | 2021-02-02 | 北京中拓新源科技有限公司 | System for recognizing typical faults of transformer based on transformer sound |
-
2021
- 2021-02-04 CN CN202110155771.8A patent/CN113053412B/en active Active
Patent Citations (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP2004080952A (en) * | 2002-08-21 | 2004-03-11 | Toshiba Corp | Power failure detecting system |
AU2005100274A4 (en) * | 2004-03-31 | 2005-06-23 | Kapur, Ruchika Ms | Method and apparatus for analyising sound |
CN104167207A (en) * | 2014-06-20 | 2014-11-26 | 国家电网公司 | Equipment sound identification method based on transformer substation patrol inspection robot |
CN109029582A (en) * | 2018-08-17 | 2018-12-18 | 国网江苏省电力有限公司盐城供电分公司 | A kind of Power Transformer Faults on-line detecting system based on many kinds of parameters acquisition |
CN111141979A (en) * | 2019-12-31 | 2020-05-12 | 福建睿思特科技股份有限公司 | Fault judgment method for substation automation equipment |
CN112014774A (en) * | 2020-03-26 | 2020-12-01 | 中国铁建电气化局集团第二工程有限公司 | Transformer fault inspection system and method based on sound processing |
CN112305462A (en) * | 2020-11-09 | 2021-02-02 | 北京中拓新源科技有限公司 | System for recognizing typical faults of transformer based on transformer sound |
Non-Patent Citations (2)
Title |
---|
LIHUA LIN ET AL.: "Research on Transformer Audio Fault Identification Method Based on Neural Network", 《2019 INTERNATIONAL CONFERENCE ON INTELLIGENT TRANSPORTATION, BIG DATA & SMART CITY (ICITBS)》 * |
黄立新等: "变压器异常运行及故障浅析", 《农村电气化》, vol. 2 * |
Cited By (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN115240691A (en) * | 2022-09-23 | 2022-10-25 | 山西振中电力股份有限公司 | Substation equipment running state monitoring control system based on data analysis |
CN115240691B (en) * | 2022-09-23 | 2022-12-06 | 山西振中电力股份有限公司 | Substation equipment running state monitoring control system based on data analysis |
CN117095695A (en) * | 2023-10-19 | 2023-11-21 | 国网山西省电力公司超高压变电分公司 | Wide-area voiceprint compression acquisition method and system for transformer body |
CN117095695B (en) * | 2023-10-19 | 2023-12-22 | 国网山西省电力公司超高压变电分公司 | Wide-area voiceprint compression acquisition method and system for transformer body |
Also Published As
Publication number | Publication date |
---|---|
CN113053412B (en) | 2023-12-22 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN109616140B (en) | Abnormal sound analysis system | |
CN102828919B (en) | Acoustics monitors method, acoustical monitoring systems and the heavy equipment external member of wind turbine | |
JP4242422B2 (en) | Sudden event recording and analysis system | |
CN113053412B (en) | Transformer fault identification method based on sound | |
CN111354366B (en) | Abnormal sound detection method and abnormal sound detection device | |
CN107527617A (en) | Monitoring method, apparatus and system based on voice recognition | |
JPH09166483A (en) | Method and apparatus for monitoring equipment | |
CN106934421A (en) | Converting station electric power transformer fault detecting system and detection method based on 2DPCA and SVM | |
CN102148032A (en) | Abnormal sound detection method and system for ATM (Automatic Teller Machine) | |
CN108169639A (en) | Method based on the parallel long identification switch cabinet failure of Memory Neural Networks in short-term | |
CN112834224B (en) | Nuclear power steam turbine generator health state assessment method and system | |
CN109443769B (en) | Motor bearing state detection method, system and device and readable storage medium | |
CN112857767B (en) | Hydro-turbo generator set rotor fault acoustic discrimination method based on convolutional neural network | |
CN110530507B (en) | Edge calculation method, medium, and system for monitoring rotating device | |
CN106198765B (en) | A kind of acoustic signal recognition methods for Metal Crack monitoring | |
CN111223261A (en) | Composite intelligent production security system and security method thereof | |
CN116717437A (en) | Wind turbine generator system fault monitoring method and system | |
CN112454008A (en) | Cutting platform service life prediction method and system based on network model and readable storage medium | |
CN116778964A (en) | Power transformation equipment fault monitoring system and method based on voiceprint recognition | |
CN112666430B (en) | Intelligent fault detection method and system for voiceprint of transformer | |
JPH09229762A (en) | Method and apparatus for monitoring of abnormality of instrument | |
CN115911623A (en) | Battery thermal runaway diagnosis method and system of energy storage system based on acoustic signals | |
JP2003202260A (en) | Sound source identifying device, sudden event detecting device, and device for automatically recording sudden event | |
JP3012449B2 (en) | Method and apparatus for identifying acoustic signal | |
CN109236586A (en) | Wind-driven generator bolt failure monitoring method based on sound collection |
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 |