CN117538632A - Grounding fault diagnosis device and method for converter transformer - Google Patents
Grounding fault diagnosis device and method for converter transformer Download PDFInfo
- Publication number
- CN117538632A CN117538632A CN202310993020.2A CN202310993020A CN117538632A CN 117538632 A CN117538632 A CN 117538632A CN 202310993020 A CN202310993020 A CN 202310993020A CN 117538632 A CN117538632 A CN 117538632A
- Authority
- CN
- China
- Prior art keywords
- fault diagnosis
- current
- signal
- information
- initial
- 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.)
- Pending
Links
- 238000003745 diagnosis Methods 0.000 title claims abstract description 123
- 238000000034 method Methods 0.000 title claims description 26
- 238000005070 sampling Methods 0.000 claims abstract description 105
- 230000003750 conditioning effect Effects 0.000 claims abstract description 58
- 238000000605 extraction Methods 0.000 claims abstract description 50
- 238000012545 processing Methods 0.000 claims abstract description 17
- XEEYBQQBJWHFJM-UHFFFAOYSA-N Iron Chemical group [Fe] XEEYBQQBJWHFJM-UHFFFAOYSA-N 0.000 claims description 17
- 238000004458 analytical method Methods 0.000 claims description 12
- 238000003062 neural network model Methods 0.000 claims description 9
- 238000001514 detection method Methods 0.000 claims description 6
- 238000004891 communication Methods 0.000 claims description 3
- 238000012544 monitoring process Methods 0.000 claims description 3
- 230000000737 periodic effect Effects 0.000 claims description 3
- 230000009466 transformation Effects 0.000 abstract description 5
- 239000013598 vector Substances 0.000 description 12
- 230000006870 function Effects 0.000 description 9
- 239000011159 matrix material Substances 0.000 description 8
- 238000001914 filtration Methods 0.000 description 4
- 230000008569 process Effects 0.000 description 4
- 238000001228 spectrum Methods 0.000 description 4
- 238000004422 calculation algorithm Methods 0.000 description 3
- 238000010586 diagram Methods 0.000 description 3
- 238000012423 maintenance Methods 0.000 description 3
- 238000012549 training Methods 0.000 description 3
- 230000005540 biological transmission Effects 0.000 description 2
- 238000007796 conventional method Methods 0.000 description 2
- 230000008878 coupling Effects 0.000 description 2
- 238000010168 coupling process Methods 0.000 description 2
- 238000005859 coupling reaction Methods 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 230000006872 improvement Effects 0.000 description 2
- 238000010606 normalization Methods 0.000 description 2
- 230000004913 activation Effects 0.000 description 1
- 238000013528 artificial neural network Methods 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000005259 measurement Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000010617 multipoint ground Methods 0.000 description 1
- 210000002569 neuron Anatomy 0.000 description 1
- 238000013021 overheating Methods 0.000 description 1
- 238000004088 simulation Methods 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 230000001360 synchronised effect Effects 0.000 description 1
- 238000012546 transfer Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/213—Feature extraction, e.g. by transforming the feature space; Summarisation; Mappings, e.g. subspace methods
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01R—MEASURING ELECTRIC VARIABLES; MEASURING MAGNETIC VARIABLES
- G01R19/00—Arrangements for measuring currents or voltages or for indicating presence or sign thereof
- G01R19/02—Measuring effective values, i.e. root-mean-square values
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01R—MEASURING ELECTRIC VARIABLES; MEASURING MAGNETIC VARIABLES
- G01R19/00—Arrangements for measuring currents or voltages or for indicating presence or sign thereof
- G01R19/165—Indicating that current or voltage is either above or below a predetermined value or within or outside a predetermined range of values
-
- 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
-
- 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
- G01R31/50—Testing of electric apparatus, lines, cables or components for short-circuits, continuity, leakage current or incorrect line connections
- G01R31/62—Testing of transformers
-
- 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
- G06F2218/04—Denoising
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2218/00—Aspects of pattern recognition specially adapted for signal processing
- G06F2218/08—Feature extraction
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Data Mining & Analysis (AREA)
- Theoretical Computer Science (AREA)
- Life Sciences & Earth Sciences (AREA)
- Evolutionary Biology (AREA)
- Evolutionary Computation (AREA)
- Bioinformatics & Computational Biology (AREA)
- General Engineering & Computer Science (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Artificial Intelligence (AREA)
- Power Engineering (AREA)
- Testing Of Short-Circuits, Discontinuities, Leakage, Or Incorrect Line Connections (AREA)
Abstract
The present application provides a converter transformer ground fault diagnosis apparatus including: the current transformer unit receives an initial grounding current signal of the converter transformer; the signal conditioning unit performs initial signal conditioning on the initial grounding current signal to obtain an initial conditioning signal; the sampling unit performs preset sampling processing on the initial conditioning signal to obtain current sampling data information; the fault diagnosis unit performs discrete Fourier transform on the current sampling data information, and performs feature extraction on the current sampling data information subjected to discrete Fourier transform according to a preset fault diagnosis condition; and generating the ground fault diagnosis information according to the feature extraction result. In the converter transformer grounding fault diagnosis device, the anti-interference capability and the data precision of the current sampling data information are improved by carrying out signal conditioning and signal sampling processing on the initial grounding current signal, and then, fourier transformation and feature extraction are carried out on the current sampling data, so that the accuracy of grounding fault diagnosis is effectively improved.
Description
Technical Field
The application relates to the technical field of electronic circuits, in particular to a converter transformer grounding fault diagnosis device and method.
Background
The converter transformer bears an important task of electric energy transmission in an extra-high voltage direct current transmission network, and the operation reliability of the converter transformer has very important significance for the whole system. The single point ground of the converter transformer core and the clamping piece and the ground current under the multipoint ground will cause local overheating of the equipment. According to actual operation data, the grounding current of the iron core and the clamping piece of the converter transformer is only a few milliamperes to tens of milliamperes under normal conditions, and according to the requirements of the national electric network company enterprise standard Q/GDW 11368-2014 transformer iron core grounding current live detection technology field application rule, when the iron core or clamping piece grounding current reaches 300mA, corresponding measures are needed to be taken for processing.
At present, the means for detecting the grounding condition of the transformer core and the clamping piece by transformer substation operation and maintenance personnel mainly comprises the following steps: and measuring the current values of the transformer iron core and the clamp grounding outgoing line by adopting a clamp ammeter so as to diagnose the fault type. However, the existing measurement means cannot accurately and rapidly identify the type of the grounding fault of the converter transformer.
Disclosure of Invention
Accordingly, it is necessary to provide a device and a method for diagnosing a ground fault of a converter transformer, which solve the problem of low accuracy in diagnosing a ground fault of a converter transformer in the prior art.
An embodiment of the present application provides a converter transformer ground fault diagnosis device, including:
the current transformer unit is used for receiving an initial grounding current signal of the converter transformer; the initial grounding current signal comprises an initial iron core current signal and an initial clamping piece current signal;
the signal conditioning unit is connected with the current transformer unit and is used for performing initial signal conditioning on the initial grounding current signal to obtain an initial conditioning signal;
the sampling unit is connected with the signal conditioning unit and is used for carrying out preset sampling treatment on the initial conditioning signal to obtain current sampling data information;
the fault diagnosis unit is connected with the sampling unit and is used for performing discrete Fourier transform on the current sampling data information and performing feature extraction on the current sampling data information subjected to discrete Fourier transform according to a preset fault diagnosis condition; and generating the ground fault diagnosis information according to the feature extraction result.
In one embodiment, the fault diagnosis unit is specifically configured to:
extracting target current characteristic information from the current sampling data information subjected to discrete Fourier transform based on a preset harmonic analysis strategy, and taking the target current characteristic information as a characteristic extraction result; the target current characteristic information comprises amplitude information, phase information and frequency information.
In one embodiment, the fault diagnosis unit is specifically configured to:
and inputting the characteristic extraction result as input information into a preset probability neural network model to obtain target fault type information corresponding to the characteristic extraction result as the ground fault diagnosis information.
In one embodiment, the current sample data information includes a current valid value; the fault diagnosis unit is further configured to:
and executing the step of performing discrete Fourier transform on the current sampling data information when the current effective value is larger than a preset current threshold value.
In one embodiment, the fault diagnosis unit is further configured to:
and when the current effective value is smaller than or equal to the preset current threshold value, determining that the converter transformer has no ground fault.
In one embodiment, the fault diagnosis unit is further configured to:
and determining the risk prompt information corresponding to the ground fault diagnosis information based on the corresponding relation between the preset fault diagnosis information and the risk prompt information.
In one embodiment, the apparatus further comprises:
the power supply unit is respectively connected with the signal conditioning unit, the sampling unit and the fault diagnosis unit and is used for providing preset voltage;
and the communication platform is respectively connected with the upper computer monitoring platform and the fault diagnosis unit and is used for sending the ground fault diagnosis information to the upper computer detection platform in real time.
In one embodiment, the apparatus further comprises:
and the clock unit is connected with the fault diagnosis unit and used for providing an operation periodic frequency signal for the fault diagnosis unit.
An embodiment of the present application provides a method for diagnosing a ground fault of a converter transformer, with the diagnostic device, the method includes:
receiving an initial grounding current signal of a converter transformer; the initial grounding current signal comprises an initial iron core current signal and an initial clamping piece current signal;
performing initial signal conditioning on the initial grounding current signal to obtain an initial conditioning signal;
the method comprises the steps of performing preset sampling processing on an initial conditioning signal to obtain current sampling data information;
performing discrete Fourier transform on the current sampling data information, and performing feature extraction on the current sampling data information subjected to the discrete Fourier transform according to a preset fault diagnosis condition; and generating the ground fault diagnosis information according to the feature extraction result.
In one embodiment, the feature extraction is performed on the current sampling data information subjected to discrete fourier transform according to a preset fault diagnosis condition; generating the ground fault diagnosis information according to the feature extraction result, including:
extracting target current characteristic information from the current sampling data information subjected to discrete Fourier transform based on a preset harmonic analysis strategy, and taking the target current characteristic information as a characteristic extraction result;
and inputting the characteristic extraction result as input information into a preset probability neural network model to obtain target fault type information corresponding to the characteristic extraction result as the ground fault diagnosis information.
The above-mentioned ground fault diagnosis device that provides a converter transformer includes: the system comprises a current transformer unit, a signal conditioning unit, a sampling unit and a fault diagnosis unit. The current transformer unit is used for receiving an initial grounding current signal of the converter transformer; the signal conditioning unit is connected with the current transformer unit and is used for performing initial signal conditioning on the initial grounding current signal to obtain an initial conditioning signal; the sampling unit is connected with the signal conditioning unit and is used for carrying out preset sampling treatment on the initial conditioning signal to obtain current sampling data information; the fault diagnosis unit is connected with the sampling unit and is used for performing discrete Fourier transform on the current sampling data information and performing feature extraction on the current sampling data information subjected to discrete Fourier transform according to a preset fault diagnosis condition; and generating the ground fault diagnosis information according to the feature extraction result. In the converter transformer grounding fault diagnosis device, the signal conditioning unit and the sampling unit are used for performing signal conditioning and signal sampling processing on the initial grounding current signal, so that the anti-interference capability and the data precision of current sampling data information are improved, and secondly, the fault diagnosis unit is used for performing Fourier transformation and feature extraction on the current sampling data, so that the accuracy of grounding fault diagnosis is effectively improved.
Drawings
In order to more clearly illustrate the technical solutions of embodiments or conventional techniques of the present application, the drawings required for the descriptions of the embodiments or conventional techniques will be briefly described below, and it is apparent that the drawings in the following description are only some embodiments of the present application, and other drawings may be obtained according to these drawings without inventive effort for a person of ordinary skill in the art.
Fig. 1 is a schematic structural diagram of a ground fault diagnosis device for a converter transformer according to an embodiment of the present disclosure;
fig. 2 is a schematic structural diagram of a ground fault diagnosis device for a converter transformer according to another embodiment of the present disclosure;
fig. 3 is a schematic structural diagram of a ground fault diagnosis device for a converter transformer according to another embodiment of the present disclosure;
fig. 4 is a flowchart of a method for diagnosing a ground fault of a converter transformer according to an embodiment of the present disclosure;
fig. 5 is a flowchart of a method for diagnosing a ground fault of a converter transformer according to another embodiment of the present application.
Detailed Description
In order to make the objects, technical solutions and advantages of the present application more apparent, the present application will be further described in detail below by way of examples with reference to the accompanying drawings. It should be understood that the specific embodiments described herein are for purposes of illustration only and are not intended to limit the present application.
The numbering of the components itself, e.g. "first", "second", etc., is used herein merely to distinguish between the described objects and does not have any sequential or technical meaning. The terms "coupled" and "connected," as used herein, are intended to encompass both direct and indirect coupling (coupling), unless otherwise indicated. In the description of the present application, it should be understood that the terms "upper," "lower," "front," "rear," "left," "right," "vertical," "horizontal," "top," "bottom," "inner," "outer," "clockwise," "counterclockwise," etc. indicate or refer to an orientation or positional relationship based on that shown in the drawings, merely for convenience of description and to simplify the description, and do not indicate or imply that the devices or elements referred to must have a specific orientation, be configured and operated in a specific orientation, and therefore should not be construed as limiting the present application.
In this application, unless expressly stated or limited otherwise, a first feature "up" or "down" a second feature may be the first and second features in direct contact, or the first and second features in indirect contact via an intervening medium. Moreover, a first feature being "above," "over" and "on" a second feature may be a first feature being directly above or obliquely above the second feature, or simply indicating that the first feature is level higher than the second feature. The first feature being "under", "below" and "beneath" the second feature may be the first feature being directly under or obliquely below the second feature, or simply indicating that the first feature is less level than the second feature.
Referring to fig. 1, an embodiment of the present application provides a device for diagnosing a grounding fault of a converter transformer, which includes a current transformer unit, a signal conditioning unit, a sampling unit and a fault diagnosis unit.
The current transformer unit is used for receiving an initial grounding current signal of the converter transformer; the initial grounding current signal comprises an initial iron core current signal and an initial clamping piece current signal;
the signal conditioning unit is connected with the current transformer unit and is used for performing initial signal conditioning on the initial grounding current signal to obtain an initial conditioning signal;
the sampling unit is connected with the signal conditioning unit and is used for carrying out preset sampling treatment on the initial conditioning signal to obtain current sampling data information;
the fault diagnosis unit is connected with the sampling unit and is used for performing discrete Fourier transform on the current sampling data information and performing feature extraction on the current sampling data information subjected to discrete Fourier transform according to the preset fault diagnosis condition; and generating the ground fault diagnosis information according to the feature extraction result.
Specifically, the current transformer unit obtains an initial iron core current signal according to the iron core grounding current of the converter transformer; the current transformer unit can also obtain an initial clamp current signal through the current transformer according to the clamp grounding current of the converter transformer. It should be noted that the initial core current signal and the initial clamp current signal are both small current signals, so as to meet the requirement of the subsequent processing unit on the current threshold.
The signal conditioning unit performs initial signal conditioning on the initial ground current signal, including filtering the initial ground current signal. Interference factors in the initial ground current signal can be reduced through the processing of the signal conditioning unit, and the anti-interference capability of the initial conditioning signal is effectively improved. It should be noted that, the method of initial signal conditioning includes, but is not limited to, filtering, and may be selected according to practical requirements.
The sampling unit can set a preset number of sampling points for the initial conditioning signal in a preset period, so that sampling processing is performed. It should be noted that the preset sampling process is not limited in this application, and may be selected according to actual requirements.
The fault diagnosis unit performs discrete Fourier transform on the discrete current sampling data information, performs feature extraction on the discrete Fourier transformed current sampling data information, and performs ground fault diagnosis on the converter transformer according to the obtained feature extraction result comprising amplitude information, phase information and frequency information.
In the converter transformer grounding fault diagnosis device, the signal conditioning unit and the sampling unit are used for performing signal conditioning and signal sampling processing on the initial grounding current signal, so that the anti-interference capability and the data precision of current sampling data information are improved, and secondly, the fault diagnosis unit is used for performing Fourier transformation and feature extraction on the current sampling data, so that the accuracy of grounding fault diagnosis is effectively improved.
In one embodiment of the present application, the sampling unit is ATT7022E; the fault diagnosis unit is STM32F103. The model of the sampling unit and the model of the fault diagnosis unit are not particularly limited, and the sampling unit and the model of the fault diagnosis unit can be selected according to actual requirements and only can meet the requirement of completing corresponding functions.
In one embodiment of the present application, the fault diagnosis unit is specifically configured to:
extracting target current characteristic information from current sampling data information subjected to discrete Fourier transform based on a preset harmonic analysis strategy, and taking the target current characteristic information as a characteristic extraction result; the target current characteristic information includes amplitude information, phase information, and frequency information.
Specifically, the fault diagnosis unit may detect a fundamental component of the current sampling data information, including an amplitude and a phase angle of the signal, from the discrete current sampling data information by a discrete fourier transform method based on a harmonic analysis method. In addition, the fault diagnosis unit can use the orthogonality of the trigonometric function to eliminate the interference of harmonic waves and noise, thereby improving the diagnosis accuracy of the fault diagnosis unit as much as possible.
In one embodiment of the present application, the fault diagnosis unit is specifically configured to:
and inputting the characteristic extraction result as input information into a preset probabilistic neural network model to obtain target fault type information corresponding to the characteristic extraction result as ground fault diagnosis information.
Specifically, the feature extraction result is used as input information and is input into a preset probability neural network model to obtain probability values corresponding to each fault type, the fault type with the largest probability value is used as a target fault type, and the ground fault diagnosis information is generated according to the target fault type.
In one embodiment of the present application, the current sample data information includes a current valid value; the fault diagnosis unit is further configured to:
and when the current effective value is larger than a preset current threshold value, executing the discrete Fourier transform on the current sampling data information.
In one embodiment of the present application, the fault diagnosis unit is further configured to:
and when the current effective value is smaller than or equal to a preset current threshold value, determining that the converter transformer has no ground fault.
Specifically, the sampling unit can directly obtain a sampling current effective value according to the sampling current data information, and transmits the current effective value to the fault diagnosis unit. When the fault diagnosis unit receives the current effective value and the current sampling data information transmitted by the sampling unit, the magnitude relation between the current effective value and the current threshold value is judged first. If the current effective value is less than or equal to the current threshold value, it is determined that no ground fault exists with the current converter transformer. If the current effective value is larger than the current threshold value, determining that the current converter transformer has a ground fault, performing discrete Fourier transform on the current sampling data information by a fault diagnosis unit, and performing feature extraction on the current sampling data information subjected to the discrete Fourier transform according to a preset fault diagnosis condition; and generating ground fault diagnosis information according to the feature extraction result, and diagnosing the ground fault of the converter transformer.
In one embodiment of the present application, the fault diagnosis unit is further configured to:
and determining the risk prompt information corresponding to the ground fault diagnosis information based on the corresponding relation between the preset fault diagnosis information and the risk prompt information.
Specifically, the fault diagnosis unit stores the corresponding relation between the fault type and the risk level, and can determine the risk level corresponding to the converter transformer while generating the ground fault diagnosis information and determining the ground fault type of the converter transformer, so as to generate risk prompt information according to the risk level. The risk prompt information is mainly provided for maintenance personnel, so that the maintenance personnel can understand the emergency degree of the ground fault of the converter transformer, and further provide corresponding rescue measures.
Referring also to fig. 2, in one embodiment of the present application, the apparatus further includes:
the power supply unit is respectively connected with the signal conditioning unit, the sampling unit and the fault diagnosis unit and is used for providing preset voltage;
the communication platform is respectively connected with the upper computer monitoring platform and the fault diagnosis unit and used for sending the ground fault diagnosis information to the upper computer detection platform in real time.
Referring also to fig. 3, in one embodiment of the present application, the apparatus further includes:
and the clock unit is connected with the fault diagnosis unit and used for providing an operation periodic frequency signal for the fault diagnosis unit.
In the converter transformer grounding fault diagnosis device provided by the application, the signal conditioning unit and the sampling unit are used for performing signal conditioning and signal sampling processing on the initial grounding current signal, so that the anti-interference capability and the data precision of current sampling data information are improved, and secondly, the fault diagnosis unit is used for performing Fourier transformation and feature extraction on the current sampling data, so that the accuracy of grounding fault diagnosis is effectively improved.
Referring to fig. 4, the embodiment of the application also provides a method for diagnosing a grounding fault of a converter transformer, which adopts the device for diagnosing a grounding fault of a converter transformer. The method comprises the following steps:
s410, receiving an initial grounding current signal of a converter transformer; the initial ground current signal includes an initial core current signal and an initial clip current signal.
Specifically, an initial iron core current signal can be obtained through a current transformer according to the iron core grounding current of the converter transformer; the initial clamp current signal can also be obtained through the current transformer according to the clamp grounding current of the converter transformer. It should be noted that the present application does not set any limitation on the type of the current transformer. The initial iron core current signal and the initial clamping piece current signal are small current signals, and the requirement of the subsequent processing step on the current threshold value is met.
S420, initial signal conditioning is carried out on the initial grounding current signal, and an initial conditioning signal is obtained.
Specifically, the initial signal conditioning of the initial ground current signal includes filtering the initial ground current signal. Interference factors in the initial ground current signal can be reduced through the processing of initial signal conditioning, the anti-interference capability of the initial conditioning signal is effectively improved, and the diagnosis precision of the ground fault detection method is improved. It should be noted that, the method of initial signal conditioning includes, but is not limited to, filtering, and may be selected according to practical requirements.
S430, performing preset sampling processing on the initial conditioning signal to obtain current sampling data information.
Specifically, the initial conditioning signal of the preset period can be sampled at the sampling point according to the preset number. For example, for an initial conditioning signal of one cycle, 64 sampling points are set to perform preset sampling processing. It should be noted that the preset sampling process is not limited in this application, and may be selected according to actual requirements.
S440, performing discrete Fourier transform on the current sampling data information, and performing feature extraction on the current sampling data information subjected to the discrete Fourier transform according to a fault diagnosis condition; and generating the ground fault diagnosis information according to the feature extraction result.
Specifically, discrete fourier transform is performed on the discrete current sampling data information, feature extraction is performed on the discrete fourier transformed current sampling data information, and ground fault diagnosis is performed on the converter transformer according to the obtained features including amplitude information, phase information and frequency information.
According to the grounding fault diagnosis method for the converter transformer, through signal conditioning and signal sampling processing on the initial grounding current signal, the anti-interference capability and the data precision of current sampling data information are improved, and the diagnosis precision of the grounding fault of the converter transformer is improved. Secondly, by carrying out Fourier transformation and feature extraction on the current sampling data, the accuracy of ground fault diagnosis is effectively improved, and the reliability of safe operation of the converter transformer is also improved.
Referring to fig. 5, in an embodiment of the present application, S440 performs feature extraction on the current sampling data information after the discrete fourier transform according to a preset fault diagnosis condition; generating the ground fault diagnosis information according to the feature extraction result, including:
s510, extracting target current characteristic information from the current sampling data information subjected to discrete Fourier transform based on a preset harmonic analysis strategy, and taking the target current characteristic information as a characteristic extraction result.
Specifically, based on a harmonic analysis method, the fundamental wave component of the current sampling data information is detected from the discrete current sampling data information through a discrete Fourier transform method, wherein the fundamental wave component comprises the amplitude and the phase angle of a signal, and meanwhile, the orthogonality of a trigonometric function is used for eliminating the interference of harmonic waves and noise, so that higher accuracy is achieved as much as possible. This was analyzed as follows.
Considering that higher harmonic and noise signals may be included, the signal X (t) may be expressed as:
where n=0 corresponds to the dc component of the signal, n=l corresponds to the fundamental signal, and n=k corresponds to the k harmonics.
From the orthogonality of the trigonometric functions, we get:
from this, the amplitude of the signal subharmonics can be calculated:
the above is for a time continuous signal, whereas for a sampled discrete signal, the integral can be discretized, expressed in the form of equation (4.20):
where N is the number of samples in a cycle, the Nyquist law requires a sampling frequencyf max The highest frequency component in the signal is referred to herein as the highest harmonic frequency.
In the algorithm, X is calculated by using a harmonic analysis method formula (2) and a harmonic analysis method formula (3) 1 ，X 1 The full current amplitude of the core grounding current is obtained.
In practical application, because complete synchronous sampling and interception of integer periods are difficult to achieve, spectrum aliasing, spectrum leakage and fence effect can be better solved by adding a proper window function and an interpolation algorithm while improving the design of a hardware circuit. The specific improvement measures are as follows:
fourier transforms decompose a signal into sine waves of different amplitude and frequency. The result of the windowing is to present as continuous a waveform as possible, reducing drastic changes.
Depending on the signal, different types of windowing functions may be selected. To understand what the effect a window has on the signal frequency, the frequency characteristics of the window will be understood first. Is provided with
x(t)＝A m e j2πfrt (4)
Complex amplitude a m Typically complex, reflecting the initial phase angle, the actual frequency f r = (l+r) F, which is at frequency l×f andbetween (l+1) ×f, l is an integer, where frequency resolution f=1/(NT) s )，T s For the sampling time interval, r is the offset of the slew rate, 0<r<1. The discrete form of x (t) is:
the DFT is as follows:
the discrete signal plus cosine window DFT is:
when k=l there are:
when N > 1, the following approximation holds:
consider e ±jπ ＝-1e ±j2π =1, when k=2, a generic form of adding 3 cosine window DFT is obtained:
will b 0 ＝7938/18608；b 1 ＝9240/18608；b 2 =1430/18608 substitution into the spectrum of the signal after the 3 Exact Blackman window stack break:
similarly, when k=l+1
The set amplitude ratio is:
since the frequency offset r varies from 0 to 1, the amplitude ratio α varies from 0.582 to 1718.
R can be solved from (12), and the corrected complex amplitude can be obtained by substituting r into (11), A m The method comprises the following steps:
the phase of the first harmonic is calculated as:
the frequency can also be calculated using the FFT difference algorithm. The frequency of the first harmonic can be obtained from r as
f r ＝(l+r)F (15)
Meanwhile, when k=3, the general form of adding 4 cosine window DFT can be obtained from equation (4.23) as
Then, three coefficients b of a 4-term Blackrman-harris window are used 0 ＝0.35875,b 1 ＝0.48829,b 2 ＝0.14128,b 3 The frequency spectrum of the signal after being truncated by adding 4 Blackman-harris window is obtained by simplifying (4.33) with 0.01168
Setting amplitude ratio
From equation (4.35), r can be solved, and substituting r into equation (4.34) can obtain corrected complex amplitude A m Is that
The phase and frequency of the first harmonic are:
according to the analysis, based on a harmonic analysis strategy, detection results of the amplitude, the phase and the frequency of the converter transformer core grounding current and the clamp grounding current can be obtained and used as target current characteristic information, so that the converter transformer grounding current fault diagnosis can be further carried out.
S520, the feature extraction result is used as input information and is input into a preset probability neural network model, and target fault type information corresponding to the target current feature information is obtained and used as ground fault diagnosis information.
Specifically, the target current characteristic information is used as input information and is input into a preset probability neural network model to obtain probability values corresponding to each fault type, the fault type with the largest probability value is used as the target fault type, and the ground fault diagnosis information is generated according to the target fault type.
In one embodiment of the present application, the pre-set probabilistic neural network model is composed of four parts: an input layer, a sample layer, a summation layer, and a competition layer. The specific working process comprises the following steps: first, input vectorInput to the input layer where the network calculates the difference between the input vector and the training sample vector +.>Absolute difference valueValue->The magnitude of (2) represents the distance between the two vectors, the resulting vector is input by the input layer, the vector reflects the proximity between the vectors; then, the output vector of the input layer +.>Into the sample layer, the number of sample layer nodes is equal to the sum of the number of training samples,where M is the total number of classes. The main work of the sample layer is: firstly judging which categories are related to the input vector, and then concentrating the categories with high relativity, wherein the output value of the sample layer represents the relativity; then, the output value of the sample layer is sent to a summation layer, the number of nodes of the summation layer is M, each node corresponds to one class, and judgment is carried out through a competition transfer function of the summation layer; and finally, outputting the judging result by the competition layer, wherein only one 1 is output in the output results, the rest results are all 0, and the output result with the largest probability value is 1.
In order to reduce errors, normalization processing is performed on the input matrix, and the input matrix is set as follows:
as can be seen from equation (21), there are m learning samples of the matrix, and n feature attributes of each sample. Before normalizing the factor, B must be calculated T Matrix:
further calculation of Cmn can be obtained
(4.48)
In the method, in the process of the invention,
the normalized m samples are fed into a network sample layer, where m=k×c.
The mode distance is calculated below, and assuming that a matrix composed of P n-dimensional vectors is referred to as a sample matrix to be identified, after normalization, an input sample matrix to be identified is:
the center vector of each network node in the sample layer, the distance between the corresponding amounts of the two vectors is as follows:
after the learning sample and the sample to be identified are normalized, neurons of the radial basis functions of the sample layer are activated. Typically, a gaussian function is taken with standard deviation σ=0.1. After activation, an initial probability matrix is obtained:
assuming that m samples exist, the total samples can be divided into c types, the number of the samples of each type is the same, and k is set, and then the initial probability sum of each sample belonging to each type can be obtained at the summation layer of the network:
wherein S is ij Representative means: among the samples to be identified, the i-th sample belongs to the initial probability sum of the j-th class.
Finally, calculating the probability prob ij I.e. the probability that the i-th sample belongs to the j-th class.
According to the invention, the measuring simulation parameters corresponding to the five states of the single-point grounding of the iron core, the single-point grounding of the clamping piece, the multi-point grounding of the iron core, and the short circuit of the iron core and the clamping piece of the converter transformer are used as one sample, all the samples form a sample space, and the prior probability of each fault is assumed to be the same. Thus, the power transformer fault based on the probabilistic neural network is trained based on the training samples.
The technical features of the above embodiments may be arbitrarily combined, and all possible combinations of the technical features in the above embodiments are not described for brevity of description, however, as long as there is no contradiction between the combinations of the technical features, they should be considered as the scope of the description.
The foregoing examples represent only a few embodiments of the present application, which are described in more detail and are not to be construed as limiting the scope of the present patent. It should be noted that it would be apparent to those skilled in the art that various modifications and improvements could be made without departing from the spirit of the present application, which would be within the scope of the present application. Accordingly, the scope of protection of the present application is to be determined by the claims appended hereto.
Claims (10)
1. A converter transformer ground fault diagnosis apparatus, the apparatus comprising:
the current transformer unit is used for receiving an initial grounding current signal of the converter transformer; the initial grounding current signal comprises an initial iron core current signal and an initial clamping piece current signal;
the signal conditioning unit is connected with the current transformer unit and is used for performing initial signal conditioning on the initial grounding current signal to obtain an initial conditioning signal;
the sampling unit is connected with the signal conditioning unit and is used for carrying out preset sampling treatment on the initial conditioning signal to obtain current sampling data information;
the fault diagnosis unit is connected with the sampling unit and is used for performing discrete Fourier transform on the current sampling data information and performing feature extraction on the current sampling data information subjected to discrete Fourier transform according to a preset fault diagnosis condition; and generating the ground fault diagnosis information according to the feature extraction result.
2. The converter transformer ground fault diagnosis device according to claim 1, characterized in that the fault diagnosis unit is specifically configured to:
extracting target current characteristic information from the current sampling data information subjected to discrete Fourier transform based on a preset harmonic analysis strategy, and taking the target current characteristic information as a characteristic extraction result; the target current characteristic information comprises amplitude information, phase information and frequency information.
3. The converter transformer ground fault diagnosis device according to claim 1, characterized in that the fault diagnosis unit is specifically configured to:
and inputting the characteristic extraction result as input information into a preset probability neural network model to obtain target fault type information corresponding to the characteristic extraction result as the ground fault diagnosis information.
4. The converter transformer ground fault diagnosis device of claim 1, wherein the current sampling data information includes a current effective value; the fault diagnosis unit is further configured to:
and executing the step of performing discrete Fourier transform on the current sampling data information when the current effective value is larger than a preset current threshold value.
5. The converter transformer ground fault diagnosis device according to claim 1, wherein the fault diagnosis unit is further configured to:
and when the current effective value is smaller than or equal to the preset current threshold value, determining that the converter transformer has no ground fault.
6. The converter transformer ground fault diagnosis device according to claim 1, wherein the fault diagnosis unit is further configured to:
and determining the risk prompt information corresponding to the ground fault diagnosis information based on the corresponding relation between the preset fault diagnosis information and the risk prompt information.
7. The converter transformer ground fault diagnosis apparatus according to claim 1, characterized in that said apparatus further comprises:
the power supply unit is respectively connected with the signal conditioning unit, the sampling unit and the fault diagnosis unit and is used for providing preset voltage;
and the communication platform is respectively connected with the upper computer monitoring platform and the fault diagnosis unit and is used for sending the ground fault diagnosis information to the upper computer detection platform in real time.
8. The converter transformer ground fault diagnosis apparatus according to claim 1, characterized in that said apparatus further comprises:
and the clock unit is connected with the fault diagnosis unit and used for providing an operation periodic frequency signal for the fault diagnosis unit.
9. A method for diagnosing a ground fault of a converter transformer, characterized in that the diagnostic apparatus of claim 1 is employed, the method comprising:
receiving an initial grounding current signal of a converter transformer; the initial grounding current signal comprises an initial iron core current signal and an initial clamping piece current signal;
performing initial signal conditioning on the initial grounding current signal to obtain an initial conditioning signal;
the method comprises the steps of performing preset sampling processing on an initial conditioning signal to obtain current sampling data information;
performing discrete Fourier transform on the current sampling data information, and performing feature extraction on the current sampling data information subjected to the discrete Fourier transform according to a preset fault diagnosis condition; and generating the ground fault diagnosis information according to the feature extraction result.
10. The method for diagnosing a ground fault of a converter transformer according to claim 9, wherein the feature extraction is performed on the discrete fourier transformed current sample data information according to a preset fault diagnosis condition; generating the ground fault diagnosis information according to the feature extraction result, including:
extracting target current characteristic information from the current sampling data information subjected to discrete Fourier transform based on a preset harmonic analysis strategy, and taking the target current characteristic information as a characteristic extraction result;
and inputting the characteristic extraction result as input information into a preset probability neural network model to obtain target fault type information corresponding to the characteristic extraction result as the ground fault diagnosis information.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310993020.2A CN117538632A (en) | 2023-08-08 | 2023-08-08 | Grounding fault diagnosis device and method for converter transformer |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310993020.2A CN117538632A (en) | 2023-08-08 | 2023-08-08 | Grounding fault diagnosis device and method for converter transformer |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN117538632A true CN117538632A (en) | 2024-02-09 |
Family
ID=89790641
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310993020.2A Pending CN117538632A (en) | 2023-08-08 | 2023-08-08 | Grounding fault diagnosis device and method for converter transformer |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117538632A (en) |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2004040732A1 (en) * | 2002-10-29 | 2004-05-13 | Alstom Technology Ltd | Earth fault protection for synchronous machines |
| CN206274265U (en) * | 2016-11-28 | 2017-06-23 | 山东科技大学 | A kind of transformer online monitoring device |
| CN107449954A (en) * | 2016-06-01 | 2017-12-08 | 李朝晖 | Power transformer iron core earth current holography on-Line Monitor Device and method |
| CN112327221A (en) * | 2020-11-04 | 2021-02-05 | 国网河南省电力公司郑州供电公司 | Transformer internal insulation defect live-line diagnosis device |
| CN113311359A (en) * | 2021-05-13 | 2021-08-27 | 上海远观物联网科技有限公司 | Transformer internal fault discrimination method based on vector analysis |
| CN114780308A (en) * | 2022-03-07 | 2022-07-22 | 国网陕西省电力有限公司超高压公司 | Transformer fault remote intelligent diagnosis system based on 5G and satellite communication technology |
| CN115327445A (en) * | 2022-08-11 | 2022-11-11 | 国网四川省电力公司电力科学研究院 | Method and system for judging abnormity of grounding currents of iron core and clamping piece of converter transformer |
| CN116111558A (en) * | 2023-03-02 | 2023-05-12 | 国网四川省电力公司技能培训中心 | Transformer differential protection method, system and medium for graph Fourier transformation |
-
2023
- 2023-08-08 CN CN202310993020.2A patent/CN117538632A/en active Pending
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2004040732A1 (en) * | 2002-10-29 | 2004-05-13 | Alstom Technology Ltd | Earth fault protection for synchronous machines |
| CN107449954A (en) * | 2016-06-01 | 2017-12-08 | 李朝晖 | Power transformer iron core earth current holography on-Line Monitor Device and method |
| CN206274265U (en) * | 2016-11-28 | 2017-06-23 | 山东科技大学 | A kind of transformer online monitoring device |
| CN112327221A (en) * | 2020-11-04 | 2021-02-05 | 国网河南省电力公司郑州供电公司 | Transformer internal insulation defect live-line diagnosis device |
| CN113311359A (en) * | 2021-05-13 | 2021-08-27 | 上海远观物联网科技有限公司 | Transformer internal fault discrimination method based on vector analysis |
| CN114780308A (en) * | 2022-03-07 | 2022-07-22 | 国网陕西省电力有限公司超高压公司 | Transformer fault remote intelligent diagnosis system based on 5G and satellite communication technology |
| CN115327445A (en) * | 2022-08-11 | 2022-11-11 | 国网四川省电力公司电力科学研究院 | Method and system for judging abnormity of grounding currents of iron core and clamping piece of converter transformer |
| CN116111558A (en) * | 2023-03-02 | 2023-05-12 | 国网四川省电力公司技能培训中心 | Transformer differential protection method, system and medium for graph Fourier transformation |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109375060B (en) | Method for calculating fault waveform similarity of power distribution network | |
| Valtierra-Rodriguez et al. | Detection and classification of single and combined power quality disturbances using neural networks | |
| CN101907437B (en) | Wavelet difference algorithm-based cable fault localization method | |
| CN113219300B (en) | Power distribution network single-phase earth fault sensing method based on phase current transient state steady state | |
| CN106841949B (en) | Method and device for monitoring stator insulation of three-phase asynchronous alternating current motor on line | |
| CN102288857B (en) | Fault arc identification and detection method and detection protection device | |
| CN105424172B (en) | A kind of distributed power transformer noise detection system and its noise detecting method | |
| CN101701986A (en) | System for pre-testing and diagnosing electro magnetic interference of electronic equipment and method thereof | |
| CN103116090A (en) | Three-phrase pulse-width modulation (PWM) rectifier fault diagnosis method based on wavelet packet analysis and support vector machine | |
| CN110222765A (en) | A kind of permanent magnet synchronous motor health status monitoring method and system | |
| CN107942192A (en) | A kind of controller switching equipment CT automatic test approach and system | |
| CN115932659A (en) | Transformer fault detection method based on voiceprint characteristics | |
| Li et al. | Fault diagnosis of star-connected auto-transformer based 24-pulse rectifier | |
| CN111398814A (en) | Motor fault detection and intelligent rapid diagnosis method controlled by soft starter | |
| Bhandari et al. | Real-time signal-to-noise ratio estimation by universal grid analyzer | |
| Deng et al. | A Single-Ended Fault Location Method for Transmission Line Based on Full Waveform Feature Extraction of Traveling Waves | |
| CN109635430A (en) | Grid power transmission route transient signal monitoring method and system | |
| CN105203937A (en) | Internal discharge mode recognition method and fault diagnosis system for transformer | |
| CN117538632A (en) | Grounding fault diagnosis device and method for converter transformer | |
| Kale et al. | Detection and classification of faults on parallel transmission lines using wavelet transform and neural network | |
| CN117420385A (en) | High-voltage direct-current transmission line fault identification method based on convolution | |
| Chang et al. | Anomaly Detection for Shielded Cable Including Cable Joint Using a Deep Learning Approach | |
| CN114118166A (en) | Transformer fault diagnosis system and method based on intelligent frequency spectrum monitoring | |
| CN117872039B (en) | Line fault location method and system based on improved RBF network | |
| Zhu et al. | Aiming to Complex Power Quality Disturbances: A Novel Decomposition and Detection Framework |
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 |