CN112307999B - Transformer running state vibration and noise detection method and system based on ant colony optimization - Google Patents

Transformer running state vibration and noise detection method and system based on ant colony optimization Download PDF

Info

Publication number
CN112307999B
CN112307999B CN202011229107.5A CN202011229107A CN112307999B CN 112307999 B CN112307999 B CN 112307999B CN 202011229107 A CN202011229107 A CN 202011229107A CN 112307999 B CN112307999 B CN 112307999B
Authority
CN
China
Prior art keywords
matrix
row
cyclic delay
column
window
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Active
Application number
CN202011229107.5A
Other languages
Chinese (zh)
Other versions
CN112307999A (en
Inventor
翟明岳
杨雅文
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
North China Electric Power University
Original Assignee
North China Electric Power University
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by North China Electric Power University filed Critical North China Electric Power University
Priority to CN202011229107.5A priority Critical patent/CN112307999B/en
Publication of CN112307999A publication Critical patent/CN112307999A/en
Application granted granted Critical
Publication of CN112307999B publication Critical patent/CN112307999B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

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
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F17/00—Digital computing or data processing equipment or methods, specially adapted for specific functions
    • G06F17/10—Complex mathematical operations
    • G06F17/16—Matrix or vector computation, e.g. matrix-matrix or matrix-vector multiplication, matrix factorization
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00—Computing arrangements based on biological models
    • G06N3/004—Artificial life, i.e. computing arrangements simulating life
    • G06N3/006—Artificial life, i.e. computing arrangements simulating life based on simulated virtual individual or collective life forms, e.g. social simulations or particle swarm optimisation [PSO]
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F2218/00—Aspects of pattern recognition specially adapted for signal processing
    • G06F2218/02—Preprocessing

Landscapes

  • Engineering & Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • Theoretical Computer Science (AREA)
  • General Physics & Mathematics (AREA)
  • Mathematical Physics (AREA)
  • General Engineering & Computer Science (AREA)
  • Data Mining & Analysis (AREA)
  • Computing Systems (AREA)
  • Pure & Applied Mathematics (AREA)
  • Mathematical Optimization (AREA)
  • Mathematical Analysis (AREA)
  • Computational Mathematics (AREA)
  • Software Systems (AREA)
  • Artificial Intelligence (AREA)
  • Biomedical Technology (AREA)
  • General Health & Medical Sciences (AREA)
  • Molecular Biology (AREA)
  • Evolutionary Computation (AREA)
  • Computational Linguistics (AREA)
  • Biophysics (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Health & Medical Sciences (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Signal Processing (AREA)
  • Algebra (AREA)
  • Databases & Information Systems (AREA)
  • Magnetic Resonance Imaging Apparatus (AREA)

Abstract

The embodiment of the invention discloses a transformer running state vibration and noise detection method and system by utilizing ant colony optimization, wherein the method comprises the following steps: step 101, acquiring a signal sequence S acquired according to a time sequence; step 102, generating a cyclic delay signal matrix; 103, generating N window cyclic delay sub-matrixes; step 104 initializing process parameters; step 105, updating process parameters; step 106, calculating an updating difference value and finishing updating; step 107, filtering the N window delay circulation sub-matrixes; step 108, solving ant colony optimization values of N windows; step 109 judges the running state of the transformer.

Description

Transformer running state vibration and noise detection method and system based on ant colony optimization
Technical Field
The invention relates to the field of electric power, in particular to a method and a system for detecting vibration and sound of a transformer in an operation state.
Background
With the high-speed development of the smart grid, the safe and stable operation of the power equipment is particularly important. At present, the detection of the operating state of the power equipment with ultrahigh voltage and above voltage grades, especially the detection of the abnormal state, is increasingly important and urgent. As an important component of an electric power system, a power transformer is one of the most important electrical devices in a substation, and its reliable operation is related to the safety of a power grid.
The basic principle of the transformer operation state detection is to extract each characteristic quantity in the transformer operation, analyze, identify and track the characteristic quantity so as to monitor the abnormal operation state of the transformer. The current common detection methods for the operation state of the transformer include a pulse current method and an ultrasonic detection method for detecting partial discharge, a frequency response method for detecting winding deformation, a vibration detection method for detecting mechanical and electrical faults, and the like. The detection methods mainly detect the insulation condition and the mechanical structure condition of the transformer, wherein the detection of the vibration signal (vibration sound) of the transformer is the most comprehensive, and the fault and the abnormal state of most transformers can be reflected.
Although the transformer vibration and sound detection method is widely applied to monitoring the running state of the transformer and the technology is relatively mature, the vibration and sound detection method utilizes the vibration signal sent by the transformer and is easily influenced by the environmental noise, so that the method often cannot obtain satisfactory results when being applied in the actual working environment.
Disclosure of Invention
As mentioned above, the transformer vibration and noise detection method is widely applied to monitoring the operation state of the transformer, and the technology is relatively mature, but because the vibration and noise detection method utilizes the vibration signal emitted by the transformer, the vibration and noise detection method is easily affected by the environmental noise, and therefore, the method often fails to obtain satisfactory results when being applied in the actual working environment.
The invention aims to provide a transformer running state vibration sound detection method and system based on ant colony optimization. The method has better robustness and simpler calculation.
In order to achieve the purpose, the invention provides the following scheme:
a transformer running state vibration and noise detection method using ant colony optimization comprises the following steps:
step 101, acquiring a signal sequence S acquired according to a time sequence;
step 102, generating a cyclic delay signal matrix, specifically: the cyclic delay signal matrix is denoted as D, and the ith row and jth column elements thereof are denoted as DijThe formula used is:
Figure GDA0003277629290000011
wherein:
Figure GDA0003277629290000012
is the | i-1+ j |' of the signal sequence SNThe number of the elements is one,
|i-1+j|Nmeaning that the remainder is taken modulo N for i-1+ j,
i is 1,2, N is a row number,
j is 1,2, N is a column number,
n is the length of the signal sequence S;
step 103, generating N window cyclic delay sub-matrices, specifically: the K window cyclic delay sub-matrix is marked as JKThe formula used is:
Figure GDA0003277629290000021
wherein:
dK-1,K-1is the K-1 column element of the K-1 row of the cyclic delay signal matrix D,
dK,K-1is the K-1 column element of the K-th row of the cyclic delay signal matrix D,
dK+1,K-1: the K +1 row, the K-1 column element of the cyclic delay signal matrix D
dK-1,K+1Is the K-1 row and the K +1 column elements of the cyclic delay signal matrix D,
dK,K+1is the K +1 th row element of the cyclic delay signal matrix D,
dK+1,K+1is the element of the K +1 th row and the K +1 th column of the cyclic delay signal matrix D,
dK-1,Kis the K-1 row and the K column element of the cyclic delay signal matrix D,
dK+1,Kis the K +1 row and K column elements of the cyclic delay signal matrix D,
dK,Kis the Kth row and the Kth column element of the cyclic delay signal matrix D,
if K-1<1, K-1 is set to K,
if K +1 > N, K +1 is set to N,
k is 1,2, N is a window serial number;
step 104 initializes process parameters, specifically: the process parameters comprise an influence factor alpha, an evaporation rate rho, a constant factor C, an iteration control parameter k and a connection matrix gamma; the initialized value of the connection matrix gamma is recorded as gamma0(ii) a The initialization formula used is:
α＝0.41
ρ＝0.6
C＝0.0001
k＝0
γ0＝03×3；
step 105 updates process parameters, specifically: the updated value of the k +1 th step of the connection matrix gamma is recorded as gammak+1The element in the first row and the m column is marked as
Figure GDA0003277629290000022
The update formula used is:
Figure GDA0003277629290000023
wherein:
Figure GDA0003277629290000031
in order to be an ant colony pheromone,
Figure GDA0003277629290000032
the distance of the ant colony is used,
t is the sampling interval of the signal sequence S,
Figure GDA0003277629290000033
updating the k-th step of the connection matrix gamma with the new value gammakThe row l and the column m elements,
l is 1,2,3 is a connection row number,
m is 1,2 and 3 are connecting column serial numbers;
step 106, obtaining an update difference value and ending the update, specifically: the updated difference is recorded as epsilon, and the solving formula is as follows:
ε＝|γk+1-γk|
if the updating difference value epsilon meets the formula epsilon is more than or equal to 0.001, adding 1 to the value of the iteration control parameter k, and returning to the step 105 and the step 106 for updating again; otherwise, iteration is finished and a filter factor omega is obtainedlmHas a value of
Figure GDA0003277629290000034
Step 107, filtering the N window delay circulation sub-matrices, specifically: filtering the K window cyclic delay sub-matrixThe latter result is denoted yKThe filtering formula is as follows:
Figure GDA0003277629290000035
wherein:
Figure GDA0003277629290000036
cyclically delaying the submatrix J for the Kth windowKRow i, column m element of (1);
step 108, solving ant colony optimization values of N windows, specifically: the K window ant colony optimization value is recorded as HKThe formula used is:
HK＝||YG||F
wherein:
Figure GDA0003277629290000037
in the form of an intermediate circulant matrix,
Figure GDA0003277629290000038
is a linear gradient matrix, and the linear gradient matrix,
||YG||Frepresenting the Frobenius norm of the matrix YG,
σ is the mean square error of the signal sequence S;
step 109, judging the running state of the transformer, specifically: if the K window ant colony optimization value HKIs greater than or equal to
Figure GDA0003277629290000039
The transformer is in an abnormal operation state at the Kth point; otherwise, the transformer is in a normal operation state.
An ant colony optimized transformer operating condition vibro-acoustic detection system, comprising:
the module 201 acquires a signal sequence S acquired in time sequence;
module 202 generates a matrix of cyclic delay signalsThe body is as follows: the cyclic delay signal matrix is denoted as D, and the ith row and jth column elements thereof are denoted as DijThe formula used is:
Figure GDA0003277629290000042
wherein:
Figure GDA0003277629290000043
is the | i-1+ j |' of the signal sequence SNThe number of the elements is one,
|i-1+j|Nmeaning that the remainder is taken modulo N for i-1+ j,
i is 1,2, N is a row number,
j is 1,2, N is a column number,
n is the length of the signal sequence S;
the module 203 generates N window cyclic delay sub-matrices, specifically: the K window cyclic delay sub-matrix is marked as JKThe formula used is:
Figure GDA0003277629290000041
wherein:
dK-1,K-1is the K-1 column element of the K-1 row of the cyclic delay signal matrix D,
dK,K-1is the K-1 column element of the K-th row of the cyclic delay signal matrix D,
dK+1,K-1: the K +1 row, the K-1 column element of the cyclic delay signal matrix D
dK-1,K+1Is the K-1 row and the K +1 column elements of the cyclic delay signal matrix D,
dK,K+1is the K +1 th row element of the cyclic delay signal matrix D,
dK+1,K+1is the element of the K +1 th row and the K +1 th column of the cyclic delay signal matrix D,
dK-1,Kis that it isThe K-1 row and K column elements of the cyclic delay signal matrix D,
dK+1,Kis the K +1 row and K column elements of the cyclic delay signal matrix D,
dK,Kis the Kth row and the Kth column element of the cyclic delay signal matrix D,
if K-1<1, K-1 is set to K,
if K +1 > N, K +1 is set to N,
k is 1,2, N is a window serial number;
the module 204 initializes process parameters, specifically: the process parameters comprise an influence factor alpha, an evaporation rate rho, a constant factor C, an iteration control parameter k and a connection matrix gamma; the initialized value of the connection matrix gamma is recorded as gamma0(ii) a The initialization formula used is:
α＝0.41
ρ＝0.6
C＝0.0001
k＝0
γ0＝03×3；
the module 205 updates the process parameters, specifically: the updated value of the k +1 th step of the connection matrix gamma is recorded as gammak+1The element in the first row and the m column is marked as
Figure GDA0003277629290000051
The update formula used is:
Figure GDA0003277629290000052
wherein:
Figure GDA0003277629290000053
in order to be an ant colony pheromone,
Figure GDA0003277629290000054
the distance of the ant colony is used,
t is the sampling interval of the signal sequence S,
Figure GDA0003277629290000055
updating the k-th step of the connection matrix gamma with the new value gammakThe row l and the column m elements,
l is 1,2,3 is a connection row number,
m is 1,2 and 3 are connecting column serial numbers;
the module 206 calculates an update difference and finishes updating, specifically: the updated difference is recorded as epsilon, and the solving formula is as follows:
ε＝|γk+1-γk|
if the update difference epsilon satisfies the formula epsilon is more than or equal to 0.001, adding 1 to the value of the iteration control parameter k, and returning to the module 205 and the module 206 for updating again; otherwise, iteration is finished and a filter factor omega is obtainedlmHas a value of
Figure GDA0003277629290000056
The module 207 filters the N window delay cyclic sub-matrices, specifically: filtering the K window cyclic delay sub-matrix, and recording the filtered result as yKThe filtering formula is as follows:
Figure GDA0003277629290000057
wherein:
Figure GDA0003277629290000058
cyclically delaying the submatrix J for the Kth windowKRow i, column m element of (1);
the module 208 calculates ant colony optimization values for N windows, specifically: the K window ant colony optimization value is recorded as HKThe formula used is:
HK＝||YG||F
wherein:
Figure GDA0003277629290000061
in the form of an intermediate circulant matrix,
Figure GDA0003277629290000062
is a linear gradient matrix, and the linear gradient matrix,
||YG||Frepresenting the Frobenius norm of the matrix YG,
σ is the mean square error of the signal sequence S;
the module 209 determines the running state of the transformer, specifically: if the K window ant colony optimization value HKIs greater than or equal to
Figure GDA0003277629290000063
The transformer is in an abnormal operation state at the Kth point; otherwise, the transformer is in a normal operation state.
According to the specific embodiment provided by the invention, the invention discloses the following technical effects:
as mentioned above, the transformer vibration and noise detection method is widely applied to monitoring the operation state of the transformer, and the technology is relatively mature, but because the vibration and noise detection method utilizes the vibration signal emitted by the transformer, the vibration and noise detection method is easily affected by the environmental noise, and therefore, the method often fails to obtain satisfactory results when being applied in the actual working environment.
The invention aims to provide a transformer running state vibration sound detection method and system based on ant colony optimization. The method has better robustness and simpler calculation.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the embodiments will be briefly described below. It is obvious that the drawings in the following description are only some embodiments of the invention, and that for a person skilled in the art, other drawings can be derived from them without inventive effort.
FIG. 1 is a schematic flow diagram of the process of the present invention;
FIG. 2 is a schematic flow chart of the system of the present invention;
FIG. 3 is a flow chart illustrating an embodiment of the present invention.
Detailed Description
The technical solution in the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present invention. It is to be understood that the described embodiments are merely exemplary of the invention, and not restrictive of the full scope of the invention. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
In order to make the aforementioned objects, features and advantages of the present invention comprehensible, embodiments accompanied with figures are described in further detail below.
FIG. 1 is a schematic flow chart of a transformer operation state vibration and sound detection method using ant colony optimization
Fig. 1 is a schematic flow chart of a transformer operation state vibration and noise detection method using ant colony optimization according to the present invention. As shown in fig. 1, the method for detecting the vibration and noise of the transformer operating state by ant colony optimization specifically includes the following steps:
step 101, acquiring a signal sequence S acquired according to a time sequence;
step 102, generating a cyclic delay signal matrix, specifically: the cyclic delay signal matrix is denoted as D, and the ith row and jth column elements thereof are denoted as DijThe formula used is:
Figure GDA0003277629290000072
wherein:
Figure GDA0003277629290000073
is the | i-1+ j |' of the signal sequence SNThe number of the elements is one,
|i-1+j|Nmeaning that the remainder is taken modulo N for i-1+ j,
i is 1,2, N is a row number,
j is 1,2, N is a column number,
n is the length of the signal sequence S;
step 103, generating N window cyclic delay sub-matrices, specifically: the K window cyclic delay sub-matrix is marked as JKThe formula used is:
Figure GDA0003277629290000071
wherein:
dK-1,K-1is the K-1 column element of the K-1 row of the cyclic delay signal matrix D,
dK,K-1is the K-1 column element of the K-th row of the cyclic delay signal matrix D,
dK+1,K-1: the K +1 row, the K-1 column element of the cyclic delay signal matrix D
dK-1,K+1Is the K-1 row and the K +1 column elements of the cyclic delay signal matrix D,
dK,K+1is the K +1 th row element of the cyclic delay signal matrix D,
dK+1,K+1is the element of the K +1 th row and the K +1 th column of the cyclic delay signal matrix D,
dK-1,Kis the K-1 row and the K column element of the cyclic delay signal matrix D,
dK+1,Kis the K +1 row and K column elements of the cyclic delay signal matrix D,
dK,Kis the Kth row and the Kth column element of the cyclic delay signal matrix D,
if K-1<1, K-1 is set to K,
if K +1 > N, K +1 is set to N,
k is 1,2, N is a window serial number;
step 104 initializes process parameters, specifically: the process parameters comprise an influence factor alpha, an evaporation rate rho, a constant factor C, an iteration control parameter k and a connection matrix gamma; the initialized value of the connection matrix gamma is recorded as gamma0(ii) a The initialization formula used is:
α＝0.41
ρ＝0.6
C＝0.0001
k＝0
γ0＝03×3；
step 105 updates process parameters, specifically: the updated value of the k +1 th step of the connection matrix gamma is recorded as gammak+1The element in the first row and the m column is marked as
Figure GDA0003277629290000081
The update formula used is:
Figure GDA0003277629290000082
wherein:
Figure GDA0003277629290000083
in order to be an ant colony pheromone,
Figure GDA0003277629290000084
the distance of the ant colony is used,
t is the sampling interval of the signal sequence S,
Figure GDA0003277629290000085
updating the k-th step of the connection matrix gamma with the new value gammakThe row l and the column m elements,
l is 1,2,3 is a connection row number,
m is 1,2 and 3 are connecting column serial numbers;
step 106, obtaining an update difference value and ending the update, specifically: the updated difference is recorded as epsilon, and the solving formula is as follows:
ε＝|γk+1-γk|
if the updating difference value epsilon meets the formula epsilon is more than or equal to 0.001, adding 1 to the value of the iteration control parameter k, and returning to the step 105 and the step 106 for updating again; otherwise, iteration is finished and a filter factor omega is obtainedlmHas a value of
Figure GDA0003277629290000086
Step 107, filtering the N window delay circulation sub-matrices, specifically: filtering the K window cyclic delay sub-matrix, and recording the filtered result as yKThe filtering formula is as follows:
Figure GDA0003277629290000087
wherein:
Figure GDA0003277629290000088
cyclically delaying the submatrix J for the Kth windowKRow i, column m element of (1);
step 108, solving ant colony optimization values of N windows, specifically: the K window ant colony optimization value is recorded as HKThe formula used is:
HK＝||YG||F
wherein:
Figure GDA0003277629290000091
in the form of an intermediate circulant matrix,
Figure GDA0003277629290000092
is a linear gradient matrix, and the linear gradient matrix,
||YG||Frepresenting the Frobenius norm of the matrix YG,
σ is the mean square error of the signal sequence S;
step 109, judging the running state of the transformer, specifically: if the K window ant colony optimization value HKIs greater than or equal to
Figure GDA0003277629290000093
The transformer is in an abnormal operation state at the Kth point; otherwise, the transformer is in a normal operation state.
FIG. 2 structural intent of transformer operating state vibro-acoustic detection system using ant colony optimization
Fig. 2 is a schematic structural diagram of a transformer operating state vibration and noise detection system using ant colony optimization according to the present invention. As shown in fig. 2, the transformer operating state vibration and noise detection system using ant colony optimization includes the following structures:
the module 201 acquires a signal sequence S acquired in time sequence;
the module 202 generates a cyclic delay signal matrix, specifically: the cyclic delay signal matrix is denoted as D, and the ith row and jth column elements thereof are denoted as DijThe formula used is:
Figure GDA0003277629290000095
wherein:
Figure GDA0003277629290000096
is the | i-1+ j |' of the signal sequence SNThe number of the elements is one,
|i-1+j|Nmeaning that the remainder is taken modulo N for i-1+ j,
i is 1,2, N is a row number,
j is 1,2, N is a column number,
n is the length of the signal sequence S;
the module 203 generates N window cyclic delay sub-matrices, specifically: the K window cyclic delay sub-matrix is marked as JKThe formula used is:
Figure GDA0003277629290000094
wherein:
dK-1,K-1is the K-1 column element of the K-1 row of the cyclic delay signal matrix D,
dK,K-1is the K-1 column element of the K-th row of the cyclic delay signal matrix D,
dK+1,K-1: the K +1 row, the K-1 column element of the cyclic delay signal matrix D
dK-1,K+1Is the K-1 row and the K +1 column elements of the cyclic delay signal matrix D,
dK,K+1is the K +1 th row element of the cyclic delay signal matrix D,
dK+1,K+1is the element of the K +1 th row and the K +1 th column of the cyclic delay signal matrix D,
dK-1,Kis the K-1 row and the K column element of the cyclic delay signal matrix D,
dK+1,Kis the K +1 row and K column elements of the cyclic delay signal matrix D,
dK,Kis the Kth row and the Kth column element of the cyclic delay signal matrix D,
if K-1<1, K-1 is set to K,
if K +1 > N, K +1 is set to N,
k is 1,2, N is a window serial number;
the module 204 initializes process parameters, specifically: the process parameters comprise an influence factor alpha, an evaporation rate rho, a constant factor C, an iteration control parameter k and a connection matrix gamma; the initialized value of the connection matrix gamma is recorded as gamma0(ii) a The initialization formula used is:
α＝0.41
ρ＝0.6
C＝0.0001
k＝0
γ0＝03×3；
the module 205 updates the process parameters, specifically: the updated value of the k +1 th step of the connection matrix gamma is recorded as gammak+1The element in the first row and the m column is marked as
Figure GDA0003277629290000101
The update formula used is:
Figure GDA0003277629290000102
wherein:
Figure GDA0003277629290000103
in order to be an ant colony pheromone,
Figure GDA0003277629290000104
the distance of the ant colony is used,
t is the sampling interval of the signal sequence S,
Figure GDA0003277629290000105
updating the k-th step of the connection matrix gamma with the new value gammakThe row l and the column m elements,
l is 1,2,3 is a connection row number,
m is 1,2 and 3 are connecting column serial numbers;
the module 206 calculates an update difference and finishes updating, specifically: the updated difference is recorded as epsilon, and the solving formula is as follows:
ε＝|γk+1-γk|
if the update difference epsilon satisfies the formula epsilon is more than or equal to 0.001, adding 1 to the value of the iteration control parameter k, and returning to the module 205 and the module 206 for updating again; otherwise, iteration is finished and a filter factor omega is obtainedlmHas a value of
Figure GDA0003277629290000111
The module 207 filters the N window delay cyclic sub-matrices, specifically: filtering the K window cyclic delay sub-matrix, and recording the filtered result as yKFiltering ofThe formula is as follows:
Figure GDA0003277629290000112
wherein:
Figure GDA0003277629290000113
cyclically delaying the submatrix J for the Kth windowKRow i, column m element of (1);
the module 208 calculates ant colony optimization values for N windows, specifically: the K window ant colony optimization value is recorded as HKThe formula used is:
HK＝||YG||F
wherein:
Figure GDA0003277629290000114
in the form of an intermediate circulant matrix,
Figure GDA0003277629290000115
is a linear gradient matrix, and the linear gradient matrix,
||YG||Frepresenting the Frobenius norm of the matrix YG,
σ is the mean square error of the signal sequence S;
the module 209 determines the running state of the transformer, specifically: if the K window ant colony optimization value HKIs greater than or equal to
Figure GDA0003277629290000116
The transformer is in an abnormal operation state at the Kth point; otherwise, the transformer is in a normal operation state.
The following provides an embodiment for further illustrating the invention
FIG. 3 is a flow chart illustrating an embodiment of the present invention. As shown in fig. 3, the method specifically includes the following steps:
step 301, acquiring a signal sequence S acquired according to a time sequence;
step 302 generates a cyclic delay signal matrix, specifically: the cyclic delay signal matrix is denoted as D, and the ith row and jth column elements thereof are denoted as DijThe formula used is:
Figure GDA0003277629290000122
wherein:
Figure GDA0003277629290000123
is the | i-1+ j |' of the signal sequence SNThe number of the elements is one,
|i-1+j|Nmeaning that the remainder is taken modulo N for i-1+ j,
i is 1,2, N is a row number,
j is 1,2, N is a column number,
n is the length of the signal sequence S;
step 303 generates N window cyclic delay sub-matrices, specifically: the K window cyclic delay sub-matrix is marked as JKThe formula used is:
Figure GDA0003277629290000121
wherein:
dK-1,K-1is the K-1 column element of the K-1 row of the cyclic delay signal matrix D,
dK,K-1is the K-1 column element of the K-th row of the cyclic delay signal matrix D,
dK+1,K-1: the K +1 row, the K-1 column element of the cyclic delay signal matrix D
dK-1,K+1Is the K-1 row and the K +1 column elements of the cyclic delay signal matrix D,
dK,K+1is the K +1 th row element of the cyclic delay signal matrix D,
dK+1,K+1for the K +1 th row of the cyclic delay signal matrix DThe elements of the K +1 th column,
dK-1,Kis the K-1 row and the K column element of the cyclic delay signal matrix D,
dK+1,Kis the K +1 row and K column elements of the cyclic delay signal matrix D,
dK,Kis the Kth row and the Kth column element of the cyclic delay signal matrix D,
if K-1<1, K-1 is set to K,
if K +1 > N, K +1 is set to N,
k is 1,2, N is a window serial number;
step 304 initializes process parameters, specifically: the process parameters comprise an influence factor alpha, an evaporation rate rho, a constant factor C, an iteration control parameter k and a connection matrix gamma; the initialized value of the connection matrix gamma is recorded as gamma0(ii) a The initialization formula used is:
α＝0.41
ρ＝0.6
C＝0.0001
k＝0
γ0＝03×3；
step 305 updates process parameters, specifically: the updated value of the k +1 th step of the connection matrix gamma is recorded as gammak+1The element in the first row and the m column is marked as
Figure GDA0003277629290000131
The update formula used is:
Figure GDA0003277629290000132
wherein:
Figure GDA0003277629290000133
in order to be an ant colony pheromone,
Figure GDA0003277629290000134
the distance of the ant colony is used,
t is the sampling interval of the signal sequence S,
Figure GDA0003277629290000135
updating the k-th step of the connection matrix gamma with the new value gammakThe row l and the column m elements,
l is 1,2,3 is a connection row number,
m is 1,2 and 3 are connecting column serial numbers;
step 306, calculating an update difference and ending the update, specifically: the updated difference is recorded as epsilon, and the solving formula is as follows:
ε＝|γk+1-γk|
if the updating difference value epsilon meets the formula epsilon is more than or equal to 0.001, adding 1 to the value of the iteration control parameter k, and returning to the step 305 and the step 306 for updating again; otherwise, iteration is finished and a filter factor omega is obtainedlmHas a value of
Figure GDA0003277629290000136
Step 307, filtering the N window delay circulation sub-matrices, specifically: filtering the K window cyclic delay sub-matrix, and recording the filtered result as yKThe filtering formula is as follows:
Figure GDA0003277629290000137
wherein:
Figure GDA0003277629290000138
cyclically delaying the submatrix J for the Kth windowKRow i, column m element of (1);
step 308, obtaining ant colony optimization values of N windows, specifically: the K window ant colony optimization value is recorded as HKThe formula used is:
HK＝||YG||F
wherein:
Figure GDA0003277629290000139
in the form of an intermediate circulant matrix,
Figure GDA00032776292900001310
is a linear gradient matrix, and the linear gradient matrix,
||YG||Frepresenting the Frobenius norm of the matrix YG,
σ is the mean square error of the signal sequence S;
step 309, determining the running state of the transformer, specifically: if the K window ant colony optimization value HKIs greater than or equal to
Figure GDA0003277629290000141
The transformer is in an abnormal operation state at the Kth point; otherwise, the transformer is in a normal operation state.
The embodiments in the present description are described in a progressive manner, each embodiment focuses on differences from other embodiments, and the same and similar parts among the embodiments are referred to each other. For the system disclosed by the embodiment, the description is simple because the system corresponds to the method disclosed by the embodiment, and the relevant part can be referred to the method part for description.
The principles and embodiments of the present invention have been described herein using specific examples, which are provided only to help understand the method and the core concept of the present invention; meanwhile, for a person skilled in the art, according to the idea of the present invention, the specific embodiments and the application range may be changed. In view of the above, the present disclosure should not be construed as limiting the invention.

Claims (2)

1. A transformer running state vibration and noise detection method using ant colony optimization is characterized by comprising the following steps:
step 101, acquiring a signal sequence S acquired according to a time sequence;
step 102, generating a cyclic delay signal matrix, specifically: the cyclic delay signal matrix is denoted as D, and the ith row and jth column elements thereof are denoted as DijThe formula used is:
Figure FDA0003277629280000012
wherein:
Figure FDA0003277629280000013
is the | i-1+ j |' of the signal sequence SNThe number of the elements is one,
|i-1+j|Nmeaning that the remainder is taken modulo N for i-1+ j,
i is 1,2, N is a row number,
j is 1,2, N is a column number,
n is the length of the signal sequence S;
step 103, generating N window cyclic delay sub-matrices, specifically: the K window cyclic delay sub-matrix is marked as JKThe formula used is:
Figure FDA0003277629280000011
wherein:
dK-1,K-1is the K-1 column element of the K-1 row of the cyclic delay signal matrix D,
dK,K-1is the K-1 column element of the K-th row of the cyclic delay signal matrix D,
dK+1,K-1: the K +1 row, the K-1 column element of the cyclic delay signal matrix D
dK-1,K+1Is the K-1 row and the K +1 column elements of the cyclic delay signal matrix D,
dK,K+1is the K +1 th row element of the cyclic delay signal matrix D,
dK+1,K+1is the element of the K +1 th row and the K +1 th column of the cyclic delay signal matrix D,
dK-1,Kis the K-1 row and the K column element of the cyclic delay signal matrix D,
dK+1,Kis the K +1 row and K column elements of the cyclic delay signal matrix D,
dK,Kis the Kth row and the Kth column element of the cyclic delay signal matrix D,
if K-1<1, K-1 is set to K,
if K +1 > N, K +1 is set to N,
k is 1,2, N is a window serial number;
step 104 initializes process parameters, specifically: the process parameters comprise an influence factor alpha, an evaporation rate rho, a constant factor C, an iteration control parameter k and a connection matrix gamma; the initialized value of the connection matrix gamma is recorded as gamma0(ii) a The initialization formula used is:
α＝0.41
ρ＝0.6
C＝0.0001
k＝0
γ0＝03×3；
step 105 updates process parameters, specifically: the updated value of the k +1 th step of the connection matrix gamma is recorded as gammak+1The element in the first row and the m column is marked as
Figure FDA0003277629280000021
The update formula used is:
Figure FDA0003277629280000022
wherein:
Figure FDA0003277629280000023
in order to be an ant colony pheromone,
Figure FDA0003277629280000024
the distance of the ant colony is used,
t is the sampling interval of the signal sequence S,
Figure FDA0003277629280000025
updating the k-th step of the connection matrix gamma with the new value gammakThe row l and the column m elements,
l is 1,2,3 is a connection row number,
m is 1,2 and 3 are connecting column serial numbers;
step 106, obtaining an update difference value and ending the update, specifically: the updated difference is recorded as epsilon, and the solving formula is as follows:
ε＝|γk+1-γk|
if the updating difference value epsilon meets the formula epsilon is more than or equal to 0.001, adding 1 to the value of the iteration control parameter k, and returning to the step 105 and the step 106 for updating again; otherwise, iteration is finished and a filter factor omega is obtainedlmHas a value of
Figure FDA0003277629280000026
Step 107, filtering the N window delay circulation sub-matrices, specifically: filtering the K window cyclic delay sub-matrix, and recording the filtered result as yKThe filtering formula is as follows:
Figure FDA0003277629280000027
wherein:
Figure FDA0003277629280000028
cyclically delaying the submatrix J for the Kth windowKRow i, column m element of (1);
step 108, solving ant colony optimization values of N windows, specifically: the K window ant colony optimization value is recorded as HKThe formula used is:
HK＝||YG||F
wherein:
Figure FDA0003277629280000029
in the form of an intermediate circulant matrix,
Figure FDA0003277629280000031
is a linear gradient matrix, and the linear gradient matrix,
||YG||Frepresenting the Frobenius norm of the matrix YG,
σ is the mean square error of the signal sequence S;
step 109, judging the running state of the transformer, specifically: if the K window ant colony optimization value HKIs greater than or equal to
Figure FDA0003277629280000032
The transformer is in an abnormal operation state at the Kth point; otherwise, the transformer is in a normal operation state.
2. An ant colony-optimized transformer operating state vibration and sound detection system, comprising:
the module 201 acquires a signal sequence S acquired in time sequence;
the module 202 generates a cyclic delay signal matrix, specifically: the cyclic delay signal matrix is denoted as D, and the ith row and jth column elements thereof are denoted as DijThe formula used is:
Figure FDA0003277629280000034
wherein:
Figure FDA0003277629280000035
is the | i-1+ j |' of the signal sequence SNThe number of the elements is one,
|i-1+j|Nrepresenting modulo N to i-1+ j takes the remainder,
i is 1,2, N is a row number,
j is 1,2, N is a column number,
n is the length of the signal sequence S;
the module 203 generates N window cyclic delay sub-matrices, specifically: the K window cyclic delay sub-matrix is marked as JKThe formula used is:
Figure FDA0003277629280000033
wherein:
dK-1,K-1is the K-1 column element of the K-1 row of the cyclic delay signal matrix D,
dK,K-1is the K-1 column element of the K-th row of the cyclic delay signal matrix D,
dK+1,K-1: the K +1 row, the K-1 column element of the cyclic delay signal matrix D
dK-1,K+1Is the K-1 row and the K +1 column elements of the cyclic delay signal matrix D,
dK,K+1is the K +1 th row element of the cyclic delay signal matrix D,
dK+1,K+1is the element of the K +1 th row and the K +1 th column of the cyclic delay signal matrix D,
dK-1,Kis the K-1 row and the K column element of the cyclic delay signal matrix D,
dK+1,Kis the K +1 row and K column elements of the cyclic delay signal matrix D,
dK,Kis the Kth row and the Kth column element of the cyclic delay signal matrix D,
if K-1<1, K-1 is set to K,
if K +1 > N, K +1 is set to N,
k is 1,2, N is a window serial number;
the module 204 initializes process parameters, specifically: the process parameters comprise an influence factor alpha, an evaporation rate rho, a constant factor C, an iteration control parameter k and a connection matrix gamma; is connected withThe initialized value of the connection matrix gamma is recorded as gamma0(ii) a The initialization formula used is:
α＝0.41
ρ＝0.6
C＝0.0001
k＝0
γ0＝03×3；
the module 205 updates the process parameters, specifically: the updated value of the k +1 th step of the connection matrix gamma is recorded as gammak+1The element in the first row and the m column is marked as
Figure FDA0003277629280000041
The update formula used is:
Figure FDA0003277629280000042
wherein:
Figure FDA0003277629280000043
in order to be an ant colony pheromone,
Figure FDA0003277629280000044
the distance of the ant colony is used,
t is the sampling interval of the signal sequence S,
Figure FDA0003277629280000045
updating the k-th step of the connection matrix gamma with the new value gammakThe row l and the column m elements,
l is 1,2,3 is a connection row number,
m is 1,2 and 3 are connecting column serial numbers;
the module 206 calculates an update difference and finishes updating, specifically: the updated difference is recorded as epsilon, and the solving formula is as follows:
ε＝|γk+1-γk|
if the difference epsilon is updatedIf the formula epsilon is more than or equal to 0.001, adding 1 to the value of the iteration control parameter k, and returning to the module 205 and the module 206 for updating again; otherwise, iteration is finished and a filter factor omega is obtainedlmHas a value of
Figure FDA0003277629280000046
The module 207 filters the N window delay cyclic sub-matrices, specifically: filtering the K window cyclic delay sub-matrix, and recording the filtered result as yKThe filtering formula is as follows:
Figure FDA0003277629280000047
wherein:
Figure FDA0003277629280000048
cyclically delaying the submatrix J for the Kth windowKRow i, column m element of (1);
the module 208 calculates ant colony optimization values for N windows, specifically: the K window ant colony optimization value is recorded as HKThe formula used is:
HK＝||YG||F
wherein:
Figure FDA0003277629280000051
in the form of an intermediate circulant matrix,
Figure FDA0003277629280000052
is a linear gradient matrix, and the linear gradient matrix,
||YG||Frepresenting the Frobenius norm of the matrix YG,
σ is the mean square error of the signal sequence S;
the module 209 determines the running state of the transformer, specifically: if the Kth window is ant colony excellentChange value HKIs greater than or equal to
Figure FDA0003277629280000053
The transformer is in an abnormal operation state at the Kth point; otherwise, the transformer is in a normal operation state.
CN202011229107.5A 2020-11-06 2020-11-06 Transformer running state vibration and noise detection method and system based on ant colony optimization Active CN112307999B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202011229107.5A CN112307999B (en) 2020-11-06 2020-11-06 Transformer running state vibration and noise detection method and system based on ant colony optimization

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202011229107.5A CN112307999B (en) 2020-11-06 2020-11-06 Transformer running state vibration and noise detection method and system based on ant colony optimization

Publications (2)

Publication Number Publication Date
CN112307999A CN112307999A (en) 2021-02-02
CN112307999B true CN112307999B (en) 2021-11-19

Family

ID=74326357

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202011229107.5A Active CN112307999B (en) 2020-11-06 2020-11-06 Transformer running state vibration and noise detection method and system based on ant colony optimization

Country Status (1)

Country Link
CN (1) CN112307999B (en)

Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN109142946A (en) * 2018-06-29 2019-01-04 东华大学 Transformer fault detection method based on ant group algorithm optimization random forest
CN109214527A (en) * 2018-08-09 2019-01-15 南瑞集团有限公司 A kind of transformer fault early diagnosis method for early warning and system
CN111624522A (en) * 2020-05-29 2020-09-04 上海海事大学 Ant colony optimization-based RBF neural network control transformer fault diagnosis method

Family Cites Families (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US8660322B2 (en) * 2011-08-25 2014-02-25 King Saud University Passive continuous authentication method
US9536192B2 (en) * 2014-06-23 2017-01-03 International Business Machines Corporation Solving vehicle routing problems using evolutionary computing techniques

Patent Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN109142946A (en) * 2018-06-29 2019-01-04 东华大学 Transformer fault detection method based on ant group algorithm optimization random forest
CN109214527A (en) * 2018-08-09 2019-01-15 南瑞集团有限公司 A kind of transformer fault early diagnosis method for early warning and system
CN111624522A (en) * 2020-05-29 2020-09-04 上海海事大学 Ant colony optimization-based RBF neural network control transformer fault diagnosis method

Non-Patent Citations (1)

* Cited by examiner, † Cited by third party
Title
基于无线数据网的高压输电线路智能检测系统;翟明岳;《电力设备》;20040815(第08期);全文 *

Also Published As

Publication number Publication date
CN112307999A (en) 2021-02-02

Similar Documents

Publication Publication Date Title
CN112052796A (en) Permanent magnet synchronous motor fault diagnosis method based on deep learning
CN104101833A (en) Broken rotor bar detection based on current signature analysis of an electric machine
CN111780867A (en) Transformer running state vibration and sound detection method and system based on Frobenius mode optimization
CN112307999B (en) Transformer running state vibration and noise detection method and system based on ant colony optimization
CN105181120A (en) High-sensitivity transformer winding loosening determination method
CN115219015A (en) Transformer fault voiceprint identification method based on multi-dimensional time-frequency characteristics
CN113268730B (en) Smart power grid false data injection attack detection method based on reinforcement learning
CN111665405A (en) Vibration and sound detection signal filtering method and system based on sparsity minimization
EP2271948B1 (en) Phasor estimation during current transformer saturation
CN112254808B (en) Method and system for detecting vibration and sound of running state of transformer by utilizing gradient change
CN111664933A (en) Method and system for filtering vibration and sound detection signal by utilizing static vector optimization
CN106772193B (en) Measuring method using current transformer frequency characteristic measuring device
CN109946542B (en) Inverter direct-current loop capacitance fault detection method based on long-time and short-time information fusion
CN111649819A (en) Transformer state vibration and sound detection signal filtering method and system using iteration soft threshold
Kiltz et al. Fault diagnosis on a magnetically supported plate
CN110703145A (en) Transformer vibration sound signal reconstruction method and system by using multiple optimization theories
CN115828144A (en) Signal sparse representation and fusion detection method, storage medium and electronic device
CN110286291B (en) Method and system for detecting vibration and sound of running state of transformer by using principal components
CN112307998B (en) Transformer running state vibration and sound detection method and system by means of mode judgment
CN112307993B (en) Method and system for filtering vibration and sound detection signals by using local similarity
CN110837013A (en) Transformer state vibration and sound detection signal reconstruction method and system represented by sparse dictionary
CN114859266A (en) Open-circuit fault diagnosis method for CHB photovoltaic grid-connected inverter system
CN110702215B (en) Transformer running state vibration and sound detection method and system using regression tree
CN110632477A (en) Transformer running state vibration and sound detection method and system by using Hilbert space factor
CN114978586A (en) Power grid attack detection method and system based on attack genes and electronic equipment

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