CN116184141A - Gas insulation equipment fault diagnosis method and system - Google Patents

Gas insulation equipment fault diagnosis method and system Download PDF

Info

Publication number
CN116184141A
CN116184141A CN202310450336.7A CN202310450336A CN116184141A CN 116184141 A CN116184141 A CN 116184141A CN 202310450336 A CN202310450336 A CN 202310450336A CN 116184141 A CN116184141 A CN 116184141A
Authority
CN
China
Prior art keywords
matrix
hankel
hankel matrix
modified
sound pressure
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
Application number
CN202310450336.7A
Other languages
Chinese (zh)
Other versions
CN116184141B (en
Inventor
康兵
许志浩
丁贵立
王宗耀
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.)
Nanchang Institute of Technology
Original Assignee
Nanchang Institute of Technology
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 Nanchang Institute of Technology filed Critical Nanchang Institute of Technology
Priority to CN202310450336.7A priority Critical patent/CN116184141B/en
Publication of CN116184141A publication Critical patent/CN116184141A/en
Application granted granted Critical
Publication of CN116184141B publication Critical patent/CN116184141B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Images

Classifications

    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01R—MEASURING ELECTRIC VARIABLES; MEASURING MAGNETIC VARIABLES
    • G01R31/00—Arrangements for testing electric properties; Arrangements for locating electric faults; Arrangements for electrical testing characterised by what is being tested not provided for elsewhere
    • G01R31/12—Testing dielectric strength or breakdown voltage ; Testing or monitoring effectiveness or level of insulation, e.g. of a cable or of an apparatus, for example using partial discharge measurements; Electrostatic testing
    • G01R31/1209—Testing dielectric strength or breakdown voltage ; Testing or monitoring effectiveness or level of insulation, e.g. of a cable or of an apparatus, for example using partial discharge measurements; Electrostatic testing using acoustic measurements
    • 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

  • Physics & Mathematics (AREA)
  • Acoustics & Sound (AREA)
  • General Physics & Mathematics (AREA)
  • Locating Faults (AREA)

Abstract

The invention discloses a fault diagnosis method and a fault diagnosis system for gas insulation equipment, wherein the method comprises the following steps: constructing a Hankel matrix about a time moment according to the frequency spectrum of each sound pressure segment in the sound pressure signal of the GIS equipment; replacing the (1 multiplied by 1) and (k multiplied by k) elements in the Hankel matrix, placing the rest elements starting from the elements of the Hankel matrix in the same column, and selecting the first n independent rows and the first n independent columns to obtain a modified Hankel matrix; calculating a corrected Hankel uniform matrix about the time moment, and carrying out eigenvector transformation on the corrected Hankel uniform matrix to obtain eigenvalues and eigenvectors of the corrected Hankel matrix; calculating a random according to the characteristic value and the actual characteristic value of the sound pressure signal of the GIS equipment; if the random is larger than the fault threshold, determining the weight coefficient of each component of the modified Hankel homomatrix based on an entropy method. Through fault feature vector learning and accurate extraction, fault detection accuracy is effectively improved.

Description

Gas insulation equipment fault diagnosis method and system
Technical Field
The invention belongs to the technical field of fault diagnosis of gas insulation equipment, and particularly relates to a fault diagnosis method and system of gas insulation equipment.
Background
Compared with the traditional open-type transformer substation equipment, the Gas Insulated Switchgear (GIS) has the advantages of small occupied space, high safety and stability, long maintenance period, small interference from external environment and the like. Therefore, the GIS fault detection device is widely applied to all levels of substations, various GIS fault problems are more and more increased along with the wide use of GIS, but as key parts of the GIS are sealed in a metal shell, maintenance personnel can hardly find the fault.
At present, the research on insulation faults at home and abroad is deeper, but the research experience on GIS mechanical faults is relatively lacking, and the traditional mechanical fault detection method is complex, and the fault diagnosis accuracy is not high.
Disclosure of Invention
The invention provides a fault diagnosis method and system for gas-insulated equipment, which are used for solving the technical problems that the traditional mechanical fault detection method is complex and the fault diagnosis accuracy is low.
In a first aspect, the present invention provides a fault diagnosis method for a gas-insulated apparatus, comprising:
acquiring a sound pressure signal of GIS equipment, and constructing a Hankel matrix about a time moment according to the frequency spectrum of each sound pressure segment in the sound pressure signal;
will markov parameters
Figure SMS_1
Replacing the (1×1) th and (k×k) th elements in said Hankel matrix and from the elements of said Hankel matrix +.>
Figure SMS_2
The first other elements are all arranged in the same column, and the first n independent rows and the first n independent columns are selected to obtain a modified Hankel matrix +.>
Figure SMS_3
Wherein the Hankel matrix is modified>
Figure SMS_4
The expression of (2) is:
Figure SMS_5
，
in the method, in the process of the invention,
Figure SMS_6
to correct the Hankel matrix +.>
Figure SMS_7
Is->
Figure SMS_8
A time moment;
according to the modified Hankel matrix
Figure SMS_9
Calculating a modified Hankel mean matrix for the moment of time>
Figure SMS_10
And +.>
Figure SMS_11
Performing eigenvector transformation to obtain the modified Hankel matrix +.>
Figure SMS_12
Is a feature vector;
according to the modified Hankel matrix
Figure SMS_13
A diagonal matrix composed of characteristic values of the GIS equipment and a diagonal matrix composed of actual characteristic values of sound pressure signals of the GIS equipment, and calculating a random ;
determining if the random is greater than a fault threshold;
if the random is greater than the fault threshold, determining the modified Hankel homomatrix based on an entropy method
Figure SMS_14
And the weight coefficient of each component provides characteristic parameter support for fault determination of the GIS equipment.
In a second aspect, the present invention provides a gas-insulated apparatus fault diagnosis system comprising:
the construction module is configured to acquire sound pressure signals of GIS equipment and construct a Hankel matrix about time moment according to the frequency spectrums of all sound pressure fragments in the sound pressure signals;
a replacement module configured to replace Markov parameters
Figure SMS_15
Replacing the (1×1) th and (k×k) th elements in said Hankel matrix and from the elements of said Hankel matrix +.>
Figure SMS_16
The first other elements are all arranged in the same column, and the first n independent rows and the first n independent columns are selected to obtain a modified Hankel matrix +.>
Figure SMS_17
Wherein the Hankel matrix is modified>
Figure SMS_18
The expression of (2) is:
Figure SMS_19
，
in the method, in the process of the invention,
Figure SMS_20
to correct the Hankel matrix +.>
Figure SMS_21
Is->
Figure SMS_22
A time moment;
a transformation module configured to modify the Hankel matrix according to the modified Hankel matrix
Figure SMS_23
Calculating a modified Hankel mean matrix for the moment of time>
Figure SMS_24
And +.>
Figure SMS_25
Performing eigenvector transformation to obtain the modified Hankel matrix
Figure SMS_26
Is a feature vector;
a calculation module configured to correct the Hankel matrix
Figure SMS_27
A diagonal matrix composed of characteristic values of the GIS equipment and a diagonal matrix composed of actual characteristic values of sound pressure signals of the GIS equipment, and calculating a random ;
a determination module configured to determine whether the random is greater than a fault threshold;
a determination module configured to determine the modified Hankel homomatrix based on an entropy method if the random is greater than a failure threshold
Figure SMS_28
And the weight coefficient of each component provides characteristic parameter support for fault determination of the GIS equipment.
In a third aspect, there is provided an electronic device, comprising: the gas insulation equipment fault diagnosis device comprises at least one processor and a memory communicatively connected with the at least one processor, wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor can execute the steps of the gas insulation equipment fault diagnosis method according to any embodiment of the invention.
In a fourth aspect, the present invention also provides a computer-readable storage medium having stored thereon a computer program, which when executed by a processor, causes the processor to perform the steps of the gas-insulated apparatus fault diagnosis method of any of the embodiments of the present invention.
The gas-insulated equipment fault diagnosis method and system overcome the computational complexity of the traditional Hankel matrix applied to GIS fault detection, further reduce the matrix order, and effectively improve the fault detection accuracy through fault feature vector learning and accurate extraction.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings required for the description of the embodiments will be briefly described below, and it is obvious that the drawings in the following description are some embodiments of the present invention, and other drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.
FIG. 1 is a flow chart of a method for diagnosing a fault of a gas-insulated apparatus according to an embodiment of the present invention;
FIG. 2 is a modified Hankel uniform matrix of a GIS device in three different states according to one embodiment of the present invention
Figure SMS_29
And a visual result diagram of the corresponding feature vector;
FIG. 3 is a schematic diagram of a test set sample according to an embodiment of the present invention;
FIG. 4 is a block diagram illustrating a fault diagnosis system for a gas-insulated apparatus according to an embodiment of the present invention;
fig. 5 is a schematic structural diagram of an electronic device according to an embodiment of the present invention.
Detailed Description
For the purpose of making the objects, technical solutions and advantages of the embodiments of the present invention more apparent, the technical solutions of 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, and it is apparent that the described embodiments are some embodiments of the present invention, but not all embodiments of the present invention. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.
Referring to fig. 1, a flow chart of a fault diagnosis method for a gas-insulated apparatus of the present application is shown.
As shown in fig. 1, the fault diagnosis method for the gas-insulated equipment specifically includes the following steps:
step S101, acquiring a sound pressure signal of GIS equipment, and constructing a Hankel matrix about a time moment according to the frequency spectrum of each sound pressure segment in the sound pressure signal.
In this embodiment, the Hankel matrix has the following expression:
Figure SMS_30
，
in the method, in the process of the invention,
Figure SMS_40
is->
Figure SMS_32
×/>
Figure SMS_37
Hankel matrix of individual elements, +.>
Figure SMS_44
Is->
Figure SMS_48
Time moment (I)>
Figure SMS_47
Is->
Figure SMS_49
Time moment (I)>
Figure SMS_39
Is->
Figure SMS_43
Time moment (I)>
Figure SMS_31
Is->
Figure SMS_36
Time moment (I)>
Figure SMS_34
Is->
Figure SMS_35
Time moment (I)>
Figure SMS_38
Is->
Figure SMS_42
Time moment (I)>
Figure SMS_41
Is->
Figure SMS_45
Time moment (I)>
Figure SMS_46
For the 1 st moment>
Figure SMS_50
For the 2 nd moment>
Figure SMS_33
Is the 3 rd moment.
The next Hankel matrix for time moment is expressed as:
Figure SMS_51
。
step S102, markov parameters are used
Figure SMS_52
Replacing the (1×1) th and (k×k) th elements in said Hankel matrix and from the elements of said Hankel matrix +.>
Figure SMS_53
The first other elements are all arranged in the same column, and the first n independent rows and the first n independent columns are selected to obtain a modified Hankel matrix +.>
Figure SMS_54
。
In this embodiment, to obtain a simplified k-th order Hankel model, a modified Hankel matrix of (n×n) th order is proposed
Figure SMS_55
It is defined by the first Markov parameter +.>
Figure SMS_56
Substitution of the (1X 1) th and (k X k) th elements, obtained from +.>
Figure SMS_57
The remaining elements are all placed in the same column, then the first n independent rows and the first n independent columns, and the same, modified Hankel matrix +_for the next (n×n) order>
Figure SMS_58
By the first Markov parameter +.>
Figure SMS_59
Substitution of the (k.times.k) th element, obtained from +.>
Figure SMS_60
The remaining elements of the start are all placed in the same column, then the first n independent rows and the first n independent columns are selected.
Correction Hankel matrix
Figure SMS_61
The expression of (2) is:
Figure SMS_62
，
in the method, in the process of the invention,
Figure SMS_63
to correct the Hankel matrix +.>
Figure SMS_64
Is->
Figure SMS_65
A time moment;
and
Figure SMS_66
。
Step S103, according to the modified Hankel matrix
Figure SMS_67
Calculating a modified Hankel homomatrix for a time moment
Figure SMS_68
And +.>
Figure SMS_69
Performing eigenvector transformation to obtain the modified Hankel matrix +.>
Figure SMS_70
Is described in (1) and a feature vector.
In the present embodiment, a modified Hankel's average matrix is calculated with respect to the moment in time
Figure SMS_71
The expression of (2) is: />
Figure SMS_72
，
In the method, in the process of the invention,
Figure SMS_73
for total number, ++>
Figure SMS_74
To correct the Hankel matrix +.>
Figure SMS_75
To correct the sequence number of the Hankel matrix.
For the modified Hankel homomatrix
Figure SMS_76
The expression for performing the feature vector transformation is:
Figure SMS_77
，
in the method, in the process of the invention,
Figure SMS_78
to correct the eigenvector matrix of the Hankel matrix, < >>
Figure SMS_79
To correct the diagonal matrix composed of eigenvalues of the Hankel matrix.
Step S104, according to the modified Hankel matrix
Figure SMS_80
A diagonal matrix composed of characteristic values of the GIS equipment and a diagonal matrix composed of actual characteristic values of sound pressure signals of the GIS equipment, and calculating a random ;
in this embodiment, the expression for calculating the random is:
Figure SMS_81
，
Figure SMS_82
，
Figure SMS_83
，
in the method, in the process of the invention,
Figure SMS_86
random , < >>
Figure SMS_87
Is a constant between 0 and 1, < >>
Figure SMS_91
The transition probability of the sequence number i, F is the Frobeniu norm of the modified Hankel matrix, < >>
Figure SMS_84
Frobeniu norm of modified Hankel matrix with number j>
Figure SMS_89
Frobe for modified Hankel matrix with sequence number iniu norm->
Figure SMS_92
To correct the sequence number of the Hankel matrix, +.>
Figure SMS_94
Is a random number with 0 to 1 evenly distributed, < >>
Figure SMS_85
For counting function +.>
Figure SMS_88
To correct the diagonal matrix of eigenvalues of the Hankel matrix, < >>
Figure SMS_90
Matrix of actual eigenvalues of sound pressure signal for GIS device +.>
Figure SMS_93
Indicating the Frobeniu norm.
Step S105, determining whether the random is greater than a failure threshold.
In this embodiment, the fault threshold is selected according to the fault detection experience value of the GIS device
Figure SMS_95
If the calculated random +.>
Figure SMS_96
Indicating that the GIS has a fault at the moment.
Step S106, if the random is greater than the failure threshold, determining the modified Hankel uniform matrix based on an entropy method
Figure SMS_97
And the weight coefficient of each component provides characteristic parameter support for fault determination of the GIS equipment.
Step S106.1, step 2
Figure SMS_99
Conversion to a phase separation matrix>
Figure SMS_105
Wherein->
Figure SMS_107
，/>
Figure SMS_100
Minimum value +.>
Figure SMS_103
，/>
Figure SMS_108
Maximum value of->
Figure SMS_110
，/>
Figure SMS_98
For ideal attribute value, ++>
Figure SMS_104
Minimum value +.>
Figure SMS_106
，
Figure SMS_109
Maximum value of->
Figure SMS_101
，/>
Figure SMS_102
。
Step S106.2, normalizing the phase separation matrix D to define a phase separation normalized matrix
Figure SMS_111
Wherein->
Figure SMS_112
，/>
Figure SMS_113
Ith row and jth column of phase separation normalization matrix PElement(s)>
Figure SMS_114
Is the j-th column element of the ith row of the phase separation matrix D, satisfies +.>
Figure SMS_115
，/>
Figure SMS_116
。
Step S106.3 definition of entropy value
Figure SMS_118
Wherein->
Figure SMS_122
Is constant, ln is natural logarithm, +.>
Figure SMS_124
If->
Figure SMS_119
All equal, i.e.)>
Figure SMS_121
，/>
Figure SMS_125
Then->
Figure SMS_126
Maximum value->
Figure SMS_117
When taking->
Figure SMS_120
There is->
Figure SMS_123
。
Step S106.4 defining a coefficient of degree of deviation of the attribute values
Figure SMS_127
。
Step S106.5, calculating the weight of each attribute:
Figure SMS_128
。
and taking the weight coefficient as a characteristic vector so as to realize the research, judgment and prediction of the fault of the gas-insulated switchgear of the improved Hankel matrix based on the time moment reconstruction.
In conclusion, the method overcomes the computational complexity of the traditional Hankel matrix applied to GIS fault detection, further reduces the matrix order, and effectively improves the fault detection accuracy through fault feature vector learning and accurate extraction.
In a specific embodiment, 110 and kV three-phase GIS model equipment of a certain manufacturer in China is taken as a research object, and two defects of loosening of a shielding cover of GIS equipment and loosening of anchor bolts are respectively simulated. And the bolt on the conductor close to the shielding cover of the insulating basin is loosened by using a torque wrench, so that the loosening defect of the shielding cover is formed. And loosening bolts at the foundation support position at one side of the GIS equipment by using a torque wrench to form the loosening defect of the foundation bolts. The experiment is to add the GIS equipment voltage to 65 kV, and the two defects and the sound pressure signals under the normal working condition are respectively collected. In order to simulate the field test conditions as much as possible, SF6 gas with rated capacity is filled in the GIS bus tube. Based on the acquisition conditions, sound pressure signals of the GIS equipment in three different states can be obtained. The main frequency of the frequency domain results in the three states is 100 Hz, the main frequency amplitude in the normal state is 4.67 mPa, the main frequency amplitude in the anchor bolt loosening state is 9.24mPa, and the main frequency amplitude in the shielding cover loosening state is 6.55 mPa. The harmonic components in the normal state and the foundation bolt loosening state are fewer, the harmonic magnitude is smaller, and obvious harmonic components appear in the shielded enclosure loosening states of 200 Hz, 300 Hz, 400 Hz, 500 Hz and 600 Hz. Although the spectra in the three states have certain differences, the overall characteristic change is not obvious, and enough manual experience is required by spectrum analysis, so that the rapid diagnosis under standardized diagnosis logic and large data input is not facilitated.
Correction Han of GIS equipment obtained by using the method under three different statesKel uniform matrix
Figure SMS_129
And the corresponding feature vector visualization results are shown in fig. 2, and the corrected Hankel matrix in three different states can be known to have more remarkable differences from fig. 2, so that further research on equipment fault judgment can be carried out by utilizing matrix property changes. And selecting 40 groups of data and 120 groups of samples in total under three states of GIS equipment, randomly selecting 20 groups of data and 60 groups of data in total under the three states as an input training set, calculating the weight coefficient of each average Hankel matrix under the three states by adopting an entropy method, inputting the weight coefficient as characteristic parameters into a support vector machine for training, and taking the rest 60 groups of data as a test set. The kernel function in the support vector machine is set as Gaussian radial basis kernel function (Radial Basis Function, RBF), meanwhile, a penalty factor c and RBF kernel parameter g are selected by using ten-fold cross validation, and the initial search range is set as ++>
Figure SMS_130
. Fig. 3 shows the result of fault recognition by the proposed method. In the figure, the abscissas 1 to 40 represent GIS shield loosening states of test samples, 41 to 80 represent normal states, and 81 to 120 represent anchor bolt loosening states. The ordinate 1 indicates the shield loosening category, 2 indicates the normal category, and 3 indicates the anchor bolt loosening category.
As can be seen from fig. 3, the fault recognition accuracy of the proposed method reaches 92.7%, which proves the correctness of the method.
Referring to fig. 4, a block diagram of a fault diagnosis system for a gas insulated apparatus according to the present application is shown.
As shown in fig. 4, the gas-insulated apparatus fault diagnosis system 200 includes a construction module 210, a replacement module 220, a transformation module 230, a calculation module 240, a judgment module 250, and a determination module 260.
The construction module 210 is configured to acquire a sound pressure signal of the GIS device, and construct a Hankel matrix about a time moment according to a frequency spectrum of each sound pressure segment in the sound pressure signal; a replacement module 220 configured to replace Markov parameters
Figure SMS_132
Replacing the (1×1) th and (k×k) th elements in said Hankel matrix and from the elements of said Hankel matrix +.>
Figure SMS_138
The first other elements are all arranged in the same column, and the first n independent rows and the first n independent columns are selected to obtain a modified Hankel matrix +.>
Figure SMS_141
Wherein the Hankel matrix is modified>
Figure SMS_133
The expression of (2) is: />
Figure SMS_137
Wherein->
Figure SMS_142
To correct the Hankel matrix +.>
Figure SMS_144
Is->
Figure SMS_134
A time moment; a transformation module 230 configured to generate a modified Hankel matrix according to the modified Hankel matrix>
Figure SMS_135
Calculating a modified Hankel mean matrix for the moment of time>
Figure SMS_140
And +.>
Figure SMS_143
Performing eigenvector transformation to obtain the modified Hankel matrix +.>
Figure SMS_131
Is a feature vector; a calculation module 240 configured to calculate a modified Hankel matrix according to the modified Hankel matrix>
Figure SMS_136
A diagonal matrix composed of characteristic values of the GIS equipment and a diagonal matrix composed of actual characteristic values of sound pressure signals of the GIS equipment, and calculating a random ; a determination module 250 configured to determine whether the random is greater than a fault threshold; a determining module 260 configured to determine the modified Hankel homomatrix based on an entropy method if the random is greater than a failure threshold
Figure SMS_139
And the weight coefficient of each component provides characteristic parameter support for fault determination of the GIS equipment.
It should be understood that the modules depicted in fig. 4 correspond to the various steps in the method described with reference to fig. 1. Thus, the operations and features described above for the method and the corresponding technical effects are equally applicable to the modules in fig. 4, and are not described here again.
In other embodiments, the present invention further provides a computer readable storage medium having stored thereon a computer program, the program instructions, when executed by a processor, cause the processor to perform the method for diagnosing a fault in a gas-insulated apparatus in any of the method embodiments described above;
as one embodiment, the computer-readable storage medium of the present invention stores computer-executable instructions configured to:
acquiring a sound pressure signal of GIS equipment, and constructing a Hankel matrix about a time moment according to the frequency spectrum of each sound pressure segment in the sound pressure signal;
will markov parameters
Figure SMS_145
Replacing the (1×1) th and (k×k) th elements in said Hankel matrix and from the elements of said Hankel matrix +.>
Figure SMS_146
The first other elements are all arranged in the same column, and the first n independent rows and the first n independent columns are selected to obtain a modified Hankel matrix +.>
Figure SMS_147
；/>
According to the modified Hankel matrix
Figure SMS_148
Calculating a modified Hankel mean matrix for the moment of time>
Figure SMS_149
And +.>
Figure SMS_150
Performing eigenvector transformation to obtain the modified Hankel matrix +.>
Figure SMS_151
Is a feature vector;
according to the modified Hankel matrix
Figure SMS_152
A diagonal matrix composed of characteristic values of the GIS equipment and a diagonal matrix composed of actual characteristic values of sound pressure signals of the GIS equipment, and calculating a random ;
determining if the random is greater than a fault threshold;
if the random is greater than the fault threshold, determining the modified Hankel homomatrix based on an entropy method
Figure SMS_153
And the weight coefficient of each component provides characteristic parameter support for fault determination of the GIS equipment.
The computer readable storage medium may include a storage program area and a storage data area, wherein the storage program area may store an operating system, at least one application program required for a function; the storage data area may store data created according to the use of the gas insulated apparatus fault diagnosis system, and the like. In addition, the computer-readable storage medium may include high-speed random access memory, and may also include memory, such as at least one magnetic disk storage device, flash memory device, or other non-volatile solid-state storage device. In some embodiments, the computer readable storage medium optionally includes memory remotely located with respect to the processor, the remote memory being connectable to the gas insulated device fault diagnosis system through a network. Examples of such networks include, but are not limited to, the internet, intranets, local area networks, mobile communication networks, and combinations thereof.
Fig. 5 is a schematic structural diagram of an electronic device according to an embodiment of the present invention, as shown in fig. 5, where the device includes: a processor 310 and a memory 320. The electronic device may further include: an input device 330 and an output device 340. The processor 310, memory 320, input device 330, and output device 340 may be connected by a bus or other means, for example in fig. 5. Memory 320 is the computer-readable storage medium described above. The processor 310 executes various functional applications of the server and data processing by running nonvolatile software programs, instructions and modules stored in the memory 320, i.e., implements the above-described method embodiment gas-insulated apparatus fault diagnosis method. The input device 330 may receive input numerical or character information and generate key signal inputs related to user settings and function control of the gas insulated apparatus fault diagnosis system. The output device 340 may include a display device such as a display screen.
The electronic equipment can execute the method provided by the embodiment of the invention, and has the corresponding functional modules and beneficial effects of the execution method. Technical details not described in detail in this embodiment may be found in the methods provided in the embodiments of the present invention.
As an embodiment, the electronic device is applied to a fault diagnosis system of a gas-insulated device, and is used for a client, and includes: at least one processor; and a memory communicatively coupled to the at least one processor; wherein the memory stores instructions executable by the at least one processor, the instructions being executable by the at least one processor to enable the at least one processor to:
acquiring a sound pressure signal of GIS equipment, and constructing a Hankel matrix about a time moment according to the frequency spectrum of each sound pressure segment in the sound pressure signal;
will markov parameters
Figure SMS_154
Replacing the (1×1) th and (k×k) th elements in said Hankel matrix and from the elements of said Hankel matrix +.>
Figure SMS_155
The first other elements are all arranged in the same column, and the first n independent rows and the first n independent columns are selected to obtain a modified Hankel matrix +.>
Figure SMS_156
；
According to the modified Hankel matrix
Figure SMS_157
Calculating a modified Hankel mean matrix for the moment of time>
Figure SMS_158
And +.>
Figure SMS_159
Performing eigenvector transformation to obtain the modified Hankel matrix +.>
Figure SMS_160
Is a feature vector; />
According to the modified Hankel matrix
Figure SMS_161
A diagonal matrix composed of characteristic values of the GIS equipment and a diagonal matrix composed of actual characteristic values of sound pressure signals of the GIS equipment, and calculating a random ;
determining if the random is greater than a fault threshold;
if the random is greater than the fault threshold, determining the modified Hankel homomatrix based on an entropy method
Figure SMS_162
And the weight coefficient of each component provides characteristic parameter support for fault determination of the GIS equipment.
From the above description of the embodiments, it will be apparent to those skilled in the art that the embodiments may be implemented by means of software plus necessary general hardware platforms, or of course may be implemented by means of hardware. Based on such understanding, the foregoing technical solutions may be embodied essentially or in part in the form of a software product, which may be stored in a computer-readable storage medium, such as a ROM/RAM, a magnetic disk, an optical disk, etc., including several instructions to cause a computer device (which may be a personal computer, a server, or a network device, etc.) to perform the various embodiments or methods of some parts of the embodiments.
Finally, it should be noted that: the above embodiments are only for illustrating the technical solution of the present invention, and are not limiting; although the invention has been described in detail with reference to the foregoing embodiments, it will be understood by those of ordinary skill in the art that: the technical scheme described in the foregoing embodiments can be modified or some technical features thereof can be replaced by equivalents; such modifications and substitutions do not depart from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims (8)

1. A gas-insulated apparatus fault diagnosis method, characterized by comprising:
acquiring a sound pressure signal of GIS equipment, and constructing a Hankel matrix about a time moment according to the frequency spectrum of each sound pressure segment in the sound pressure signal;
will markov parameters
Figure QLYQS_1
Replacing the (1×1) th and (k×k) th elements in said Hankel matrix and from the elements of said Hankel matrix +.>
Figure QLYQS_2
The first other elements are all arranged in the same column, and the first n independent rows and the first n independent columns are selected to obtain a modified Hankel matrix +.>
Figure QLYQS_3
Wherein the Hankel matrix is modified>
Figure QLYQS_4
The expression of (2) is:
Figure QLYQS_5
，
in the method, in the process of the invention,
Figure QLYQS_6
to correct the Hankel matrix +.>
Figure QLYQS_7
Is->
Figure QLYQS_8
A time moment;
according to the modified Hankel matrix
Figure QLYQS_9
Calculating a modified Hankel mean matrix for the moment of time>
Figure QLYQS_10
And +.>
Figure QLYQS_11
Performing eigenvector transformation to obtain the modified Hankel matrix +.>
Figure QLYQS_12
Is a feature vector;
according to the modified Hankel matrix
Figure QLYQS_13
A diagonal matrix composed of characteristic values of the GIS equipment and a diagonal matrix composed of actual characteristic values of sound pressure signals of the GIS equipment, and calculating a random ;
determining if the random is greater than a fault threshold;
if the random is greater than the fault threshold, determining the modified Hankel homomatrix based on an entropy method
Figure QLYQS_14
And the weight coefficient of each component provides characteristic parameter support for fault determination of the GIS equipment.
2. The method for diagnosing a fault in a gas-insulated apparatus according to claim 1, wherein the Hankel matrix has the expression:
Figure QLYQS_15
，
in the method, in the process of the invention,
Figure QLYQS_25
is->
Figure QLYQS_19
×/>
Figure QLYQS_22
Hankel matrix of individual elements, +.>
Figure QLYQS_28
Is->
Figure QLYQS_32
Time moment (I)>
Figure QLYQS_34
Is->
Figure QLYQS_35
The time-moment of the time-series,
Figure QLYQS_23
is->
Figure QLYQS_29
Time moment (I)>
Figure QLYQS_16
Is->
Figure QLYQS_20
Time moment (I)>
Figure QLYQS_18
Is->
Figure QLYQS_27
Time moment (I)>
Figure QLYQS_31
Is->
Figure QLYQS_33
Time moment (I)>
Figure QLYQS_21
Is->
Figure QLYQS_24
Time moment (I)>
Figure QLYQS_26
For the 1 st moment>
Figure QLYQS_30
For the 2 nd moment>
Figure QLYQS_17
Is the 3 rd moment.
3. A gas-insulated apparatus fault diagnosis method according to claim 1, wherein a modified Hankel's average matrix with respect to time moment is calculated
Figure QLYQS_36
The expression of (2) is: />
Figure QLYQS_37
，
In the method, in the process of the invention,
Figure QLYQS_38
for total number, ++>
Figure QLYQS_39
To correct the Hankel matrix +.>
Figure QLYQS_40
To correct the sequence number of the Hankel matrix.
4. A gas-insulated apparatus fault diagnosis method according to claim 1, wherein, for the modified Hankel homomatrix
Figure QLYQS_41
The expression for performing the feature vector transformation is:
Figure QLYQS_42
，
in the method, in the process of the invention,
Figure QLYQS_43
to correct the eigenvector matrix of the Hankel matrix, < >>
Figure QLYQS_44
To correct the diagonal matrix composed of eigenvalues of the Hankel matrix.
5. The gas-insulated apparatus fault diagnosis method according to claim 1, wherein the expression for calculating the random is:
Figure QLYQS_45
，
Figure QLYQS_46
，
Figure QLYQS_47
，
in the method, in the process of the invention,
Figure QLYQS_49
random , < >>
Figure QLYQS_52
Is a constant between 0 and 1,/o>
Figure QLYQS_57
The transition probability of the sequence number i, F is the Frobeniu norm of the modified Hankel matrix, < >>
Figure QLYQS_51
Frobeniu norm of modified Hankel matrix with number j>
Figure QLYQS_56
Frobeniu norm of modified Hankel matrix with index i>
Figure QLYQS_58
To correct the sequence number of the Hankel matrix, +.>
Figure QLYQS_59
Is a random number with 0 to 1 evenly distributed, < >>
Figure QLYQS_48
For counting function +.>
Figure QLYQS_53
To correct the diagonal matrix of eigenvalues of the Hankel matrix, < >>
Figure QLYQS_54
Matrix of actual eigenvalues of sound pressure signal for GIS device +.>
Figure QLYQS_55
Representing the Frobeniu norm, +.>
Figure QLYQS_50
Is the total sequence number.
6. A gas-insulated apparatus fault diagnosis system, characterized by comprising:
the construction module is configured to acquire sound pressure signals of GIS equipment and construct a Hankel matrix about time moment according to the frequency spectrums of all sound pressure fragments in the sound pressure signals;
a replacement module configured to replace Markov parameters
Figure QLYQS_60
Replacing the (1×1) th and (k×k) th elements in said Hankel matrix and from the elements of said Hankel matrix +.>
Figure QLYQS_61
The first other elements are all arranged in the same column, and the first n independent rows and the first n independent columns are selected to obtain a modified Hankel matrix +.>
Figure QLYQS_62
Wherein the Hankel matrix is modified>
Figure QLYQS_63
The expression of (2) is:
Figure QLYQS_64
，
in the method, in the process of the invention,
Figure QLYQS_65
to correct the Hankel matrix +.>
Figure QLYQS_66
Is->
Figure QLYQS_67
A time moment; />
A transformation module configured to modify the Hankel matrix according to the modified Hankel matrix
Figure QLYQS_68
Calculating a modified Hankel homomatrix for a time moment
Figure QLYQS_69
And +.>
Figure QLYQS_70
Performing eigenvector transformation to obtain the modified Hankel matrix +.>
Figure QLYQS_71
Is a feature vector;
a calculation module configured to correct the Hankel matrix
Figure QLYQS_72
Calculating a random of the actual characteristic value of the sound pressure signal of the GIS equipment;
a determination module configured to determine whether the random is greater than a fault threshold;
a determination module configured to determine the modified Hankel homomatrix based on an entropy method if the random is greater than a failure threshold
Figure QLYQS_73
And the weight coefficient of each component provides characteristic parameter support for fault determination of the GIS equipment.
7. An electronic device, comprising: at least one processor, and a memory communicatively coupled to the at least one processor, wherein the memory stores instructions executable by the at least one processor to enable the at least one processor to perform the method of any one of claims 1 to 5.
8. A computer readable storage medium, on which a computer program is stored, characterized in that the program, when being executed by a processor, implements the method of any one of claims 1 to 5.
CN202310450336.7A 2023-04-25 2023-04-25 Gas insulation equipment fault diagnosis method and system Active CN116184141B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202310450336.7A CN116184141B (en) 2023-04-25 2023-04-25 Gas insulation equipment fault diagnosis method and system

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202310450336.7A CN116184141B (en) 2023-04-25 2023-04-25 Gas insulation equipment fault diagnosis method and system

Publications (2)

Publication Number Publication Date
CN116184141A true CN116184141A (en) 2023-05-30
CN116184141B CN116184141B (en) 2023-08-29

Family

ID=86444671

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202310450336.7A Active CN116184141B (en) 2023-04-25 2023-04-25 Gas insulation equipment fault diagnosis method and system

Country Status (1)

Country Link
CN (1) CN116184141B (en)

Citations (16)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2005331415A (en) * 2004-05-20 2005-12-02 Toenec Corp Insulation diagnostic system
US20070019557A1 (en) * 2005-07-21 2007-01-25 Catter Bruce L System and method for locating faults in a hybrid fiber coax (HFC) cable network
US20070183629A1 (en) * 2006-02-09 2007-08-09 Porikli Fatih M Method for tracking objects in videos using covariance matrices
US20120117399A1 (en) * 2010-11-04 2012-05-10 International Business Machines Corporation Saving power by managing the state of inactive computing devices
CN103048573A (en) * 2012-12-31 2013-04-17 重庆市电力公司 Method and device for electric power system operation risk assessment
JP2015187773A (en) * 2014-03-26 2015-10-29 公立大学法人大阪市立大学 Data analysis device, data analysis program, and data analysis method
US20170214888A1 (en) * 2014-10-14 2017-07-27 China Xd Electric Co., Ltd Internal video monitoring system and method for gis device
CN107219501A (en) * 2017-04-28 2017-09-29 中国矿业大学 A kind of accurate positioning method based on GIS partial discharge
CN109507554A (en) * 2018-12-10 2019-03-22 国网四川省电力公司电力科学研究院 A kind of insulation of electrical installation state evaluating method
CN109753689A (en) * 2018-12-10 2019-05-14 东北电力大学 A kind of online identifying approach of electric system electromechanical oscillations modal characteristics parameter
CN110953179A (en) * 2020-02-26 2020-04-03 浙江上风高科专风实业有限公司 Fan state monitoring method and system based on inverse wavelet transform
CN111913391A (en) * 2020-08-12 2020-11-10 深圳职业技术学院 Method for stabilizing self-adaptive control discrete time non-minimum phase system
CN112116149A (en) * 2020-09-17 2020-12-22 河海大学 Multi-station medium and long term runoff rolling probability prediction method considering forecast uncertainty associated evolution characteristics
WO2021093381A1 (en) * 2019-11-14 2021-05-20 国网上海市电力公司 Simulation device for poor contact of gis internal contact and infrared calibration method
CN113204879A (en) * 2021-05-07 2021-08-03 西华大学 Improved Hankel matrix prediction model modeling method based on fluorescent oil film and application
CN113283297A (en) * 2021-04-20 2021-08-20 上海电力大学 Method for estimating partial discharge signal time based on singular value decomposition and improved wavelet packet

Patent Citations (16)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2005331415A (en) * 2004-05-20 2005-12-02 Toenec Corp Insulation diagnostic system
US20070019557A1 (en) * 2005-07-21 2007-01-25 Catter Bruce L System and method for locating faults in a hybrid fiber coax (HFC) cable network
US20070183629A1 (en) * 2006-02-09 2007-08-09 Porikli Fatih M Method for tracking objects in videos using covariance matrices
US20120117399A1 (en) * 2010-11-04 2012-05-10 International Business Machines Corporation Saving power by managing the state of inactive computing devices
CN103048573A (en) * 2012-12-31 2013-04-17 重庆市电力公司 Method and device for electric power system operation risk assessment
JP2015187773A (en) * 2014-03-26 2015-10-29 公立大学法人大阪市立大学 Data analysis device, data analysis program, and data analysis method
US20170214888A1 (en) * 2014-10-14 2017-07-27 China Xd Electric Co., Ltd Internal video monitoring system and method for gis device
CN107219501A (en) * 2017-04-28 2017-09-29 中国矿业大学 A kind of accurate positioning method based on GIS partial discharge
CN109507554A (en) * 2018-12-10 2019-03-22 国网四川省电力公司电力科学研究院 A kind of insulation of electrical installation state evaluating method
CN109753689A (en) * 2018-12-10 2019-05-14 东北电力大学 A kind of online identifying approach of electric system electromechanical oscillations modal characteristics parameter
WO2021093381A1 (en) * 2019-11-14 2021-05-20 国网上海市电力公司 Simulation device for poor contact of gis internal contact and infrared calibration method
CN110953179A (en) * 2020-02-26 2020-04-03 浙江上风高科专风实业有限公司 Fan state monitoring method and system based on inverse wavelet transform
CN111913391A (en) * 2020-08-12 2020-11-10 深圳职业技术学院 Method for stabilizing self-adaptive control discrete time non-minimum phase system
CN112116149A (en) * 2020-09-17 2020-12-22 河海大学 Multi-station medium and long term runoff rolling probability prediction method considering forecast uncertainty associated evolution characteristics
CN113283297A (en) * 2021-04-20 2021-08-20 上海电力大学 Method for estimating partial discharge signal time based on singular value decomposition and improved wavelet packet
CN113204879A (en) * 2021-05-07 2021-08-03 西华大学 Improved Hankel matrix prediction model modeling method based on fluorescent oil film and application

Non-Patent Citations (2)

* Cited by examiner, † Cited by third party
Title
YUQI CAI等: "Reviews of Research on Mechanical Fault Diagnosis in GIS", WEB OF CONFERENCES, pages 1 - 10 *
许惠君等: "基于DGA 的反馈云熵模型电力变压器故障诊断方法研究", 电力系统保护与控制, vol. 41, no. 23, pages 115 - 119 *

Also Published As

Publication number Publication date
CN116184141B (en) 2023-08-29

Similar Documents

Publication Publication Date Title
CN109187025B (en) Method for predicting residual service life of rolling bearing integrated with KELM
CN105004939B (en) A kind of complex electric energy quality disturbance signal quantitative analysis method
CN102221651A (en) Fault on-line diagnosis and early warning method of flameproof dry-type transformer for mine
CN105868770A (en) High-voltage circuit breaker fault diagnosis method based on unsupervised learning model
CN114065667B (en) SF6 equipment gas pressure prediction method based on Prophet-LSTM model
Jin-qiang Fault prediction of a transformer bushing based on entropy weight TOPSIS and gray theory
CN115238831B (en) Fault prediction method, device, computer equipment and storage medium
CN113743651A (en) Electronic voltage transformer error state prediction method based on machine learning and SVM algorithm
CN115313930A (en) Method for predicting excitation current of large-scale steam turbine generator in real time
Azeem et al. Real-time harmonics analysis of digital substation equipment based on IEC-61850 using hybrid intelligent approach
CN116184141B (en) Gas insulation equipment fault diagnosis method and system
CN116881825A (en) Synchronization detection method for disconnecting link state and three-phase disconnecting link action based on GIS equipment
CN115951292A (en) Electronic voltage transformer error state online evaluation method and device
CN114510469A (en) Method, device, equipment and medium for identifying bad data of power system
CN114487643A (en) On-spot handing-over of extra-high voltage GIL equipment is accepted and is synthesized test platform
CN112098066A (en) High-voltage shunt reactor fault diagnosis method and system based on gate control circulation unit
CN114384377A (en) Cable insulation condition monitoring method and system based on QGA-VMD
CN114239636A (en) Defect type identification method and device, computer equipment and storage medium
Givaki et al. Machine learning based impedance estimation in power system
CN117708685B (en) Method and system for identifying latent partial discharge defects of switch cabinet
Ma et al. Fault Identification in Power Distribution Systems based on Domain Adaptation Probabilistic Learning
CN115859162B (en) Power distribution system health diagnosis method and related device based on Internet of things
CN117171616A (en) Voltage transformer fault diagnosis method, equipment and storage medium based on data enhancement
CN117668471B (en) Tree line discharge fault identification method based on fault traveling wave current characteristics
CN117494591B (en) Wind power electric energy quality assessment method and device

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