CN118091344B - Power converter detection method and system - Google Patents
Power converter detection method and system Download PDFInfo
- Publication number
- CN118091344B CN118091344B CN202410506161.1A CN202410506161A CN118091344B CN 118091344 B CN118091344 B CN 118091344B CN 202410506161 A CN202410506161 A CN 202410506161A CN 118091344 B CN118091344 B CN 118091344B
- Authority
- CN
- China
- Prior art keywords
- partial discharge
- parameter
- denoising
- temperature
- index
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 238000001514 detection method Methods 0.000 title claims abstract description 52
- 238000012544 monitoring process Methods 0.000 claims abstract description 168
- 230000008859 change Effects 0.000 claims abstract description 53
- 238000000034 method Methods 0.000 claims abstract description 32
- 230000008569 process Effects 0.000 claims abstract description 10
- 238000004364 calculation method Methods 0.000 claims abstract description 8
- 238000010586 diagram Methods 0.000 claims description 48
- 238000000354 decomposition reaction Methods 0.000 claims description 34
- 238000001228 spectrum Methods 0.000 claims description 26
- 230000006870 function Effects 0.000 claims description 24
- 238000012545 processing Methods 0.000 claims description 24
- 238000010606 normalization Methods 0.000 claims description 14
- 238000001914 filtration Methods 0.000 claims description 12
- 238000000605 extraction Methods 0.000 claims description 10
- 238000003062 neural network model Methods 0.000 claims description 9
- 238000010276 construction Methods 0.000 claims description 8
- 230000003044 adaptive effect Effects 0.000 claims description 5
- 238000004422 calculation algorithm Methods 0.000 claims description 4
- 238000009432 framing Methods 0.000 claims description 3
- 230000009466 transformation Effects 0.000 claims description 2
- 230000003595 spectral effect Effects 0.000 abstract description 2
- 238000010183 spectrum analysis Methods 0.000 abstract description 2
- 238000013461 design Methods 0.000 description 7
- 238000009413 insulation Methods 0.000 description 3
- 230000005236 sound signal Effects 0.000 description 3
- 230000009286 beneficial effect Effects 0.000 description 2
- 238000004590 computer program Methods 0.000 description 2
- 230000006378 damage Effects 0.000 description 2
- 230000007547 defect Effects 0.000 description 2
- 230000002093 peripheral effect Effects 0.000 description 2
- 238000012549 training Methods 0.000 description 2
- 230000032683 aging Effects 0.000 description 1
- 238000013528 artificial neural network Methods 0.000 description 1
- 238000004891 communication Methods 0.000 description 1
- 238000013135 deep learning Methods 0.000 description 1
- 210000005069 ears Anatomy 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 210000001503 joint Anatomy 0.000 description 1
- 230000007774 longterm Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 238000005070 sampling Methods 0.000 description 1
- 230000035939 shock Effects 0.000 description 1
Landscapes
- Testing Relating To Insulation (AREA)
Abstract
The invention belongs to the technical field of equipment detection, and particularly discloses a power converter detection method and a system, wherein in the process of applying pulse signals to a power converter, voltage monitoring signals, ultrasonic monitoring signals and temperature sensing signals of target points in a set time period are collected, then the voltage monitoring signals are decomposed, denoised, signal reconstructed and waveform parameter analyzed, a first partial placement reliability is determined, the temperature sensing signals are subjected to change analysis, a second partial placement reliability is determined, the ultrasonic monitoring signals are denoised, spectral characteristics are extracted and subjected to spectral analysis, a third partial placement reliability is determined, and finally the partial discharge comprehensive index of the target points is obtained based on the comprehensive calculation of the partial placement reliability of three aspects, so that a detector can rapidly and accurately judge the position and degree of partial discharge of the power converter according to the partial discharge comprehensive index of the corresponding points.
Description
Technical Field
The invention belongs to the technical field of equipment detection, and particularly relates to a power converter detection method and system.
Background
Power converters are one of the most common devices in power systems, and whether stable operation is critical to subsequent power systems, and therefore, efficient operation detection of the power converter is desirable. Partial discharge detection is an important item of power converter detection, and partial discharge refers to a partial shock discharge phenomenon occurring on electrical equipment, and is usually caused by poor insulation or damage or caused by an equipment insulation system. In the operation process of the power converter, due to long-term voltage and current effects, problems such as aging of an insulation system and dielectric destruction can be caused, so that partial discharge is caused, and the situation is generally a tiny discharge phenomenon and cannot be directly observed in equipment. At present, the common partial discharge detection of the power converter is realized by collecting partial discharge original signals through corresponding partial discharge detectors for detection analysis, and the direct sampling of the obtained partial discharge original signals contains interference noise, so that the accuracy and reliability of detection analysis results can be influenced, and the detection analysis dimension is single and not comprehensive enough, thereby being not beneficial to detecting staff to intuitively grasp the partial discharge detection condition of the power converter.
Disclosure of Invention
The present invention is directed to a method and a system for detecting a power converter, which are used for solving the above problems in the prior art.
In order to achieve the above purpose, the present invention adopts the following technical scheme:
in a first aspect, a power converter detection method is provided, including:
In the process of applying pulse signals to the power converter, collecting voltage monitoring signals, ultrasonic monitoring signals and temperature sensing signals of target points on the power converter within a set time period;
Performing CEEMDAN decomposition on the voltage monitoring signal to obtain a corresponding first decomposition result, and performing wavelet denoising and signal reconstruction processing on the first decomposition result to obtain a denoising voltage monitoring signal;
Constructing a voltage monitoring waveform diagram based on the denoising voltage monitoring signal and constructing a temperature monitoring waveform diagram based on the temperature sensing signal;
determining a first frequency parameter and a peak voltage parameter of a voltage monitoring waveform in a voltage monitoring waveform diagram, and determining a temperature change parameter of a temperature monitoring waveform in a temperature monitoring waveform diagram;
When the first frequency parameter is in a set frequency interval, calculating a peak voltage difference by using the peak voltage parameter and a set reference peak voltage parameter, and determining first office placement reliability according to the peak voltage difference;
Calculating a temperature change parameter difference by utilizing the temperature change parameter and the set reference temperature change parameter, and determining a second office placement reliability according to the temperature change parameter difference;
Denoising the ultrasonic monitoring signal to obtain a denoised ultrasonic monitoring signal, and extracting a Mel frequency spectrum of the denoised ultrasonic monitoring signal to obtain a corresponding Mel frequency spectrum map;
Inputting the Mel spectrogram into a pre-trained BP neural network model for partial discharge detection to obtain a partial discharge normalization parameter, and determining a third partial placement confidence level according to the partial discharge normalization parameter;
And calculating the partial discharge comprehensive index of the target point on the power converter according to the first partial discharge confidence coefficient, the second partial discharge confidence coefficient and the third partial discharge confidence coefficient, judging whether the target point has partial discharge according to the partial discharge comprehensive index, obtaining a partial discharge detection result of the target point, and outputting the partial discharge comprehensive index and the partial discharge detection result of the target point.
In one possible design, the method further comprises:
Obtaining partial discharge comprehensive indexes of a plurality of continuous target points on a power converter, and sequentially numbering the continuous target points;
constructing a comprehensive index scatter diagram based on serial numbers of a plurality of target points and the partial discharge comprehensive index, wherein the abscissa of the comprehensive index scatter diagram represents the point numbers, and the ordinate represents the partial discharge comprehensive index;
Sequentially connecting all scattered points in the comprehensive index scattered point diagram to obtain a comprehensive index broken line diagram;
Determining a point position number corresponding to a peak point in the comprehensive index line graph, wherein the peak point is a non-edge point in the comprehensive index line graph, and taking the point position number corresponding to the peak point as a judgment number;
And outputting the judging number and the partial discharge comprehensive index corresponding to the target point position.
In one possible design, the performing CEEMDAN decomposition on the voltage monitoring signal to obtain a corresponding first decomposition result, and performing wavelet denoising and signal reconstruction processing on the first decomposition result to obtain a denoised voltage monitoring signal, where the denoising step includes:
Carrying out CEEMDAN decomposition on the voltage monitoring signal to obtain a plurality of eigenmode function components and residual items, and carrying out wavelet transformation processing on each eigenmode function component to obtain corresponding wavelet coefficients;
determining a wavelet threshold by adopting an adaptive threshold method, constructing a threshold filter function based on the wavelet threshold, and substituting each wavelet coefficient into the threshold filter function to calculate so as to obtain a filtered wavelet coefficient corresponding to each wavelet coefficient, wherein the threshold filter function is that
Wherein, beta represents the wavelet coefficient after filtering, alpha represents the wavelet coefficient, and omega represents the wavelet threshold;
Removing the filtered wavelet coefficient of 0, and associating the residual filtered wavelet coefficients with corresponding eigenmode function components;
And carrying out signal reconstruction on the eigenvalue function components corresponding to the wavelet coefficients after the filtering and the residual items to obtain a denoising voltage monitoring signal.
In one possible design, the determining the first frequency parameter and the peak voltage parameter of the voltage monitoring waveform in the voltage monitoring waveform diagram, and determining the temperature variation parameter of the temperature monitoring waveform in the temperature monitoring waveform diagram includes:
Determining the average frequency and the maximum peak voltage of a voltage monitoring waveform in a voltage monitoring waveform diagram, taking the average frequency as a first frequency parameter and the maximum peak voltage as a peak voltage parameter;
And determining the temperature difference of the temperature monitoring waveform in each time interval in the temperature monitoring waveform chart, dividing the temperature difference in the corresponding time interval by the time length of the time interval to obtain the temperature change coefficient of the corresponding time interval, and taking the maximum temperature change coefficient as the temperature change parameter.
In one possible design, the calculating the peak voltage difference using the peak voltage parameter and the set reference peak voltage parameter when the first frequency parameter is in the set frequency interval, and determining the first office placement confidence according to the peak voltage difference includes:
subtracting the set reference peak voltage parameter from the peak voltage parameter when the first frequency parameter is in the set frequency interval to obtain a peak voltage difference;
The peak voltage difference is imported into a preset first office placement confidence level table for matching, corresponding first office placement confidence level is determined, the first office placement confidence level table comprises a plurality of peak voltage difference intervals, and each peak voltage difference interval is associated with the corresponding first office placement confidence level.
In one possible design, the calculating the temperature variation parameter difference using the temperature variation parameter and the set reference temperature variation parameter, and determining the second office placement confidence according to the temperature variation parameter difference includes:
Subtracting the set reference temperature variation parameter from the temperature variation parameter to obtain a temperature variation parameter difference;
And importing the temperature change parameter difference into a preset second partial discharge confidence level table for matching, and determining corresponding second partial discharge confidence level, wherein the second partial discharge confidence level table comprises a plurality of temperature change parameter difference intervals, and each temperature change parameter difference interval is associated with the corresponding second partial discharge confidence level.
In one possible design, the denoising processing is performed on the ultrasonic monitoring signal to obtain a denoised ultrasonic monitoring signal, and the extracting of mel spectrum is performed on the denoised ultrasonic monitoring signal to obtain a corresponding mel spectrum map, including:
Denoising the ultrasonic monitoring signal by adopting a Kalman filtering algorithm to obtain a denoised ultrasonic monitoring signal;
Pre-emphasis treatment is carried out on the denoising ultrasonic monitoring signal to obtain a denoising ultrasonic monitoring signal after pre-emphasis;
carrying out windowing framing treatment and fast Fourier transform treatment on the pre-emphasized denoising ultrasonic monitoring signal to obtain a denoising ultrasonic monitoring signal frequency spectrum;
and filtering the denoising ultrasonic monitoring signal frequency spectrum by adopting a Mel filter group to obtain a corresponding Mel spectrogram.
In one possible design, the calculating the partial discharge comprehensive index of the target point location on the power converter according to the first partial discharge confidence, the second partial discharge confidence and the third partial discharge confidence includes:
determining a voltage index coefficient corresponding to the voltage monitoring signal, an ultrasonic index coefficient corresponding to the ultrasonic monitoring signal and a temperature index coefficient corresponding to the temperature sensing signal;
Multiplying the first partial placement reliability by a voltage index coefficient to obtain a first partial placement index, multiplying the second partial placement reliability by an ultrasonic index coefficient to obtain a second partial placement index, and multiplying the third partial placement reliability by a temperature index coefficient to obtain a third partial placement index;
And adding the first partial discharge index, the second partial discharge index and the third partial discharge index to obtain a partial discharge comprehensive index.
In a second aspect, a power converter detection system is provided, including a signal acquisition unit, a decomposition denoising unit, a waveform construction unit, a parameter determination unit, a first determination unit, a second determination unit, a spectrum extraction unit, a third determination unit, and an index calculation unit, wherein:
The signal acquisition unit is used for acquiring a voltage monitoring signal, an ultrasonic monitoring signal and a temperature sensing signal of a target point position on the power converter in a set time period in the process of applying a pulse signal to the power converter;
The decomposition denoising unit is used for carrying out CEEMDAN decomposition on the voltage monitoring signal to obtain a corresponding first decomposition result, and carrying out wavelet denoising and signal reconstruction processing on the first decomposition result to obtain a denoising voltage monitoring signal;
The waveform construction unit is used for constructing a voltage monitoring waveform diagram based on the denoising voltage monitoring signal and constructing a temperature monitoring waveform diagram based on the temperature sensing signal;
the parameter determining unit is used for determining a first frequency parameter and a peak voltage parameter of the voltage monitoring waveform in the voltage monitoring waveform diagram and determining a temperature change parameter of the temperature monitoring waveform in the temperature monitoring waveform diagram;
The first judging unit is used for calculating a peak voltage difference by utilizing the peak voltage parameter and a set reference peak voltage parameter when the first frequency parameter is in a set frequency interval, and determining first office placement reliability according to the peak voltage difference;
The second judging unit is used for calculating a temperature change parameter difference by utilizing the temperature change parameter and the set reference temperature change parameter and determining a second office placement reliability according to the temperature change parameter difference;
the frequency spectrum extraction unit is used for carrying out denoising treatment on the ultrasonic monitoring signal to obtain a denoising ultrasonic monitoring signal, and carrying out Mel frequency spectrum extraction on the denoising ultrasonic monitoring signal to obtain a corresponding Mel frequency spectrogram;
the third judging unit is used for inputting the Mel spectrogram into the pre-trained BP neural network model to perform partial discharge detection, obtaining partial discharge normalization parameters, and determining third partial placement reliability according to the partial discharge normalization parameters;
The index calculation unit is used for calculating the partial discharge comprehensive index of the target point position on the power converter according to the first partial discharge confidence, the second partial discharge confidence and the third partial discharge confidence, judging whether the target point position has partial discharge according to the partial discharge comprehensive index, obtaining a partial discharge detection result of the target point position, and outputting the partial discharge comprehensive index and the partial discharge detection result of the target point position.
In a third aspect, a power converter detection system is provided, comprising:
A memory for storing instructions;
And a processor for reading the instructions stored in the memory and executing the method according to any one of the above first aspects according to the instructions.
In a fourth aspect, there is provided a computer readable storage medium having instructions stored thereon which, when run on a computer, cause the computer to perform the method of any of the first aspects. Also provided is a computer program product comprising instructions which, when run on a computer, cause the computer to perform the method of any of the first aspects.
The beneficial effects are that: the method comprises the steps of collecting a voltage monitoring signal, an ultrasonic monitoring signal and a temperature sensing signal of a target point in a set time period in the process of applying pulse signals to a power converter, then decomposing, denoising, reconstructing the signal and analyzing waveform parameters of the voltage monitoring signal, determining a first partial placement confidence level, performing change analysis on the temperature sensing signal, determining a second partial placement confidence level, denoising, spectral feature extraction and spectral analysis on the ultrasonic monitoring signal, determining a third partial placement confidence level, and finally obtaining a partial discharge comprehensive index of the target point based on comprehensive calculation of the partial placement confidence levels of three aspects, so that a detector can rapidly and accurately judge the position and degree of partial discharge of the power converter according to the partial discharge comprehensive index of the corresponding point. The invention can help the detection personnel to more comprehensively and intuitively detect the partial discharge defect part on the power converter by the multi-dimensional monitoring, the intelligent analysis of the sensing signals and the result summarization, and improves the partial discharge detection efficiency of the power converter.
Drawings
In order to more clearly illustrate the embodiments of the invention or the technical solutions in the prior art, the drawings that are required in the embodiments or the description of the prior art will be briefly described, it being obvious that the drawings in the following description are only some embodiments of the invention, and that other drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.
FIG. 1 is a schematic diagram showing the steps of the method of example 1 of the present invention;
FIG. 2 is a schematic diagram showing the construction of a system in embodiment 2 of the present invention;
FIG. 3 is a schematic diagram showing the construction of a system in embodiment 3 of the present invention.
Detailed Description
It should be noted that the description of these examples is for aiding in understanding the present invention, but is not intended to limit the present invention. Specific structural and functional details disclosed herein are merely representative of example embodiments of the invention. This invention may, however, be embodied in many alternate forms and should not be construed as limited to the embodiments set forth herein.
It will be appreciated that the term "coupled" is to be interpreted broadly, and may be a fixed connection, a removable connection, or an integral connection, for example, unless explicitly stated and limited otherwise; can be mechanically or electrically connected; can be directly connected or indirectly connected through an intermediate medium, and can be communication between two elements. The specific meaning of the terms in the embodiments can be understood by those of ordinary skill in the art according to the specific circumstances.
In the following description, specific details are provided to provide a thorough understanding of example embodiments. However, it will be understood by those of ordinary skill in the art that the example embodiments may be practiced without these specific details. For example, a system may be shown in block diagrams in order to avoid obscuring the examples with unnecessary detail. In other embodiments, well-known processes, structures, and techniques may be shown without unnecessary detail in order to avoid obscuring the embodiments.
Example 1:
The present embodiment provides a power converter detection method, which can be applied to a corresponding processing terminal, as shown in fig. 1, and includes the following steps:
S1, collecting a voltage monitoring signal, an ultrasonic monitoring signal and a temperature sensing signal of a target point position on a power supply converter in a set time period in the process of applying a pulse signal to the power supply converter.
When the power converter is detected, pulse current can be adopted to apply pulse signals to the power converter, then a corresponding voltage sensor is adopted to monitor the voltage of a target point position on the power converter, a corresponding ultrasonic partial discharge detector is adopted to monitor the temperature, a corresponding temperature sensor is adopted to monitor the temperature, then voltage monitoring signals of the voltage sensor in a set time period are collected, ultrasonic monitoring signals of the ultrasonic partial discharge detector in the set time period are collected, and temperature sensing signals of the temperature sensor in the set time period are collected. The ultrasonic partial discharge detector can compile high-frequency noise generated by the discharge phenomenon into audible sound signals for human ears by using a heterodyne method.
S2, carrying out CEEMDAN decomposition on the voltage monitoring signal to obtain a corresponding first decomposition result, and carrying out wavelet denoising and signal reconstruction processing on the first decomposition result to obtain a denoising voltage monitoring signal.
In specific implementation, the processing terminal may perform CEEMDAN decomposition (complete adaptive noise set empirical mode decomposition) on the voltage monitoring signal to obtain a plurality of eigenmode function components (IMFs) and remaining terms, and perform wavelet transform processing on each eigenmode function component to obtain a corresponding wavelet coefficient. The wavelet threshold is then determined using an adaptive threshold method, which may be, for example, an adaptive threshold formulaTo determine a wavelet threshold, wherein ω represents the wavelet threshold, δ is a set noise estimate, C represents the corresponding eigenmode function component, i is a set wavelet decomposition scale, and can be set to 4. Then constructing a threshold filtering function based on wavelet threshold values, and substituting each wavelet coefficient into the threshold filtering function to calculate so as to obtain a filtered wavelet coefficient corresponding to each wavelet coefficient, wherein the threshold filtering function is/>Wherein β characterizes the post-filter wavelet coefficient, α characterizes the wavelet coefficient, and ω characterizes the wavelet threshold. And removing the filtered wavelet coefficient of 0, associating the residual filtered wavelet coefficients with the corresponding eigenmode function components, and carrying out signal reconstruction on the eigenmode function components corresponding to the residual filtered wavelet coefficients and the residual terms to obtain the denoising voltage monitoring signal. The denoising voltage monitoring signal processed by the mode has higher signal quality, and is convenient for subsequent accurate signal processing.
S3, constructing a voltage monitoring waveform diagram based on the denoising voltage monitoring signal and constructing a temperature monitoring waveform diagram based on the temperature sensing signal.
In specific implementation, the processing terminal can construct a voltage monitoring waveform diagram according to the denoising voltage monitoring signal, wherein the abscissa of the voltage monitoring waveform diagram is a time parameter, and the ordinate is a voltage parameter. And the processing terminal can construct a temperature monitoring waveform diagram according to the temperature sensing signal, wherein the abscissa of the temperature monitoring waveform diagram is a time parameter, and the ordinate is a temperature parameter.
S4, determining a first frequency parameter and a peak voltage parameter of a voltage monitoring waveform in the voltage monitoring waveform diagram, and determining a temperature change parameter of a temperature monitoring waveform in the temperature monitoring waveform diagram.
In particular, the processing terminal may determine an average frequency and a maximum peak voltage of the voltage monitoring waveform in the voltage monitoring waveform diagram, and use the average frequency as the first frequency parameter and the maximum peak voltage as the peak voltage parameter. The temperature difference of the temperature monitoring waveform in each time interval in the temperature monitoring waveform diagram can be determined, the temperature difference in the corresponding time interval is divided by the time length of the time interval, the temperature change coefficient of the corresponding time interval is obtained, and the maximum temperature change coefficient is used as the temperature change parameter.
S5, when the first frequency parameter is in the set frequency interval, calculating a peak voltage difference by using the peak voltage parameter and the set reference peak voltage parameter, and determining the first office placement reliability according to the peak voltage difference.
In the implementation, when the first frequency parameter is in the set frequency interval, the set reference peak voltage parameter can be subtracted from the peak voltage parameter to obtain the peak voltage difference. And then leading the peak voltage difference into a preset first office placement confidence level table for matching, and determining corresponding first office placement confidence level, wherein the first office placement confidence level table comprises a plurality of peak voltage difference intervals, and each peak voltage difference interval is associated with the corresponding first office placement confidence level.
S6, calculating a temperature change parameter difference by using the temperature change parameter and the set reference temperature change parameter, and determining the second office placement reliability according to the temperature change parameter difference.
In specific implementation, the temperature change parameter is subtracted by the set reference temperature change parameter to obtain the temperature change parameter difference. And importing the temperature change parameter difference into a preset second partial discharge confidence level table for matching, and determining corresponding second partial discharge confidence level, wherein the second partial discharge confidence level table comprises a plurality of temperature change parameter difference intervals, and each temperature change parameter difference interval is associated with the corresponding second partial discharge confidence level.
S7, denoising the ultrasonic monitoring signal to obtain a denoising ultrasonic monitoring signal, and extracting a Mel frequency spectrum of the denoising ultrasonic monitoring signal to obtain a corresponding Mel frequency spectrum map.
In specific implementation, the processing terminal can adopt a kalman filter algorithm (kalman filter is an algorithm for optimally estimating the system state by using a linear system state equation and through system input and output observation data, and is suitable for a linear, discrete and finite-dimensional system) to perform denoising processing on an ultrasonic monitoring signal to obtain a denoising ultrasonic monitoring signal. And then pre-emphasis treatment is carried out on the denoising ultrasonic monitoring signal, so as to obtain the denoising ultrasonic monitoring signal after pre-emphasis. And then carrying out windowing framing treatment and fast Fourier transform treatment on the pre-emphasized denoising ultrasonic monitoring signal to obtain a denoising ultrasonic monitoring signal frequency spectrum. And finally, filtering the denoising ultrasonic monitoring signal spectrum by adopting a Mel filter group to obtain a corresponding Mel spectrogram. The Mel frequency spectrum is based on Mel scale, and is used for frequency domain representation of sound signal, and can be classified and identified by deep neural network, thereby realizing classification judgment of sound signal.
S8, inputting the Mel spectrogram into a pre-trained BP neural network model to perform partial discharge detection, obtaining partial discharge normalization parameters, and determining third partial placement reliability according to the partial discharge normalization parameters.
In the specific implementation, the Mel spectrogram can be input into the BP neural network model trained by deep learning to carry out partial discharge detection, so as to obtain the partial discharge normalization parameter. The BP neural network model is trained by a corresponding training set in advance, the training set can comprise a plurality of positive and negative samples, positive samples and Mel spectrograms of partial discharge denoising ultrasonic monitoring signals, the negative samples are Mel spectrograms of non-partial discharge denoising ultrasonic monitoring signals, and an output layer of the BP neural network model adopts a softmax function (normalized exponential function) to output partial discharge normalization parameters.
S9, calculating the partial discharge comprehensive index of the target point position on the power converter according to the first partial discharge confidence coefficient, the second partial discharge confidence coefficient and the third partial discharge confidence coefficient, judging whether the partial discharge condition exists in the target point position according to the partial discharge comprehensive index, obtaining a partial discharge detection result of the target point position, and outputting the partial discharge comprehensive index and the partial discharge detection result of the target point position.
In specific implementation, the processing terminal may be preconfigured with a voltage index coefficient corresponding to the voltage monitoring signal, an ultrasonic index coefficient corresponding to the ultrasonic monitoring signal, and a temperature index coefficient corresponding to the temperature sensing signal. And then multiplying the voltage index coefficient by the first partial placement confidence level to obtain a first partial placement index, multiplying the ultrasonic index coefficient by the second partial placement confidence level to obtain a second partial placement index, and multiplying the temperature index coefficient by the third partial placement confidence level to obtain a third partial placement index. And finally, adding the first partial discharge index, the second partial discharge index and the third partial discharge index to obtain a partial discharge comprehensive index, judging whether the target point position has a partial discharge condition according to the partial discharge comprehensive index to obtain a partial discharge detection result of the target point position, and indicating whether the target point position has the partial discharge condition if the partial discharge comprehensive index is larger than a set threshold value. And finally outputting the partial discharge comprehensive index of the target point location and the partial discharge detection result, wherein the partial discharge comprehensive index is a judging index for representing the partial discharge of the current target point location, so that a detector can intuitively judge the partial discharge degree according to the partial discharge comprehensive index.
Or the method steps can be adopted to detect a plurality of target points on the power converter respectively to obtain the partial discharge comprehensive index corresponding to each target point, and then the sequential numbering is carried out on a plurality of continuous target points. And constructing a comprehensive index scatter diagram based on the serial numbers of the continuous multiple target points and the partial discharge comprehensive index, wherein the abscissa of the comprehensive index scatter diagram represents the point serial numbers, and the ordinate represents the partial discharge comprehensive index. And sequentially connecting all scattered points in the comprehensive index scattered points to obtain a comprehensive index broken line graph, determining the point position number corresponding to the peak point in the comprehensive index broken line graph, wherein the peak point is a non-edge point in the comprehensive index broken line graph, and taking the point position number corresponding to the peak point as a judgment number. And finally, outputting a judging number and a partial discharge comprehensive index of a target point position corresponding to the judging number so as to represent the maximum possibility that the target point position is a partial discharge source.
According to the method, through multi-dimensional monitoring, intelligent analysis of sensing signals and result summarization, detection personnel can rapidly and accurately judge the position and degree of partial discharge of the power converter according to the partial discharge comprehensive index of the corresponding point, detection personnel can be helped to detect the partial discharge defect position on the power converter more comprehensively and intuitively, and the partial discharge detection efficiency of the power converter is improved.
Example 2:
the present embodiment provides a power converter detection system, as shown in fig. 2, including a signal acquisition unit, a decomposition denoising unit, a waveform construction unit, a parameter determination unit, a first determination unit, a second determination unit, a spectrum extraction unit, a third determination unit, and an index calculation unit, wherein:
The signal acquisition unit is used for acquiring a voltage monitoring signal, an ultrasonic monitoring signal and a temperature sensing signal of a target point position on the power converter in a set time period in the process of applying a pulse signal to the power converter;
The decomposition denoising unit is used for carrying out CEEMDAN decomposition on the voltage monitoring signal to obtain a corresponding first decomposition result, and carrying out wavelet denoising and signal reconstruction processing on the first decomposition result to obtain a denoising voltage monitoring signal;
The waveform construction unit is used for constructing a voltage monitoring waveform diagram based on the denoising voltage monitoring signal and constructing a temperature monitoring waveform diagram based on the temperature sensing signal;
the parameter determining unit is used for determining a first frequency parameter and a peak voltage parameter of the voltage monitoring waveform in the voltage monitoring waveform diagram and determining a temperature change parameter of the temperature monitoring waveform in the temperature monitoring waveform diagram;
The first judging unit is used for calculating a peak voltage difference by utilizing the peak voltage parameter and a set reference peak voltage parameter when the first frequency parameter is in a set frequency interval, and determining first office placement reliability according to the peak voltage difference;
The second judging unit is used for calculating a temperature change parameter difference by utilizing the temperature change parameter and the set reference temperature change parameter and determining a second office placement reliability according to the temperature change parameter difference;
the frequency spectrum extraction unit is used for carrying out denoising treatment on the ultrasonic monitoring signal to obtain a denoising ultrasonic monitoring signal, and carrying out Mel frequency spectrum extraction on the denoising ultrasonic monitoring signal to obtain a corresponding Mel frequency spectrogram;
the third judging unit is used for inputting the Mel spectrogram into the pre-trained BP neural network model to perform partial discharge detection, obtaining partial discharge normalization parameters, and determining third partial placement reliability according to the partial discharge normalization parameters;
The index calculation unit is used for calculating the partial discharge comprehensive index of the target point position on the power converter according to the first partial discharge confidence, the second partial discharge confidence and the third partial discharge confidence, judging whether the target point position has partial discharge according to the partial discharge comprehensive index, obtaining a partial discharge detection result of the target point position, and outputting the partial discharge comprehensive index and the partial discharge detection result of the target point position.
Example 3:
The present embodiment provides a power converter detection system, as shown in fig. 3, at a hardware level, including:
the data interface is used for establishing data butt joint between the processor and each monitoring end;
A memory for storing instructions;
and a processor for reading the instructions stored in the memory and executing the power converter detection method of embodiment 1 according to the instructions.
Optionally, the system further comprises an internal bus. The processor and memory and data interfaces may be interconnected by an internal bus, which may be an ISA (Industry Standard Architecture ) bus, a PCI (PERIPHERAL COMPONENT INTERCONNECT, peripheral component interconnect standard) bus, or EISA (Extended Industry Standard Architecture ) bus, among others. The buses may be classified as address buses, data buses, control buses, etc.
The Memory may include, but is not limited to, random access Memory (Random Access Memory, RAM), read Only Memory (ROM), flash Memory (Flash Memory), first-in first-Out Memory (First Input First Output, FIFO), and/or first-in last-Out Memory (FIRST IN LAST Out, FILO), etc. The processor may be a general-purpose processor including a central processing unit (Central Processing Unit, CPU), a network processor (Network Processor, NP), etc.; but may also be a digital signal Processor (DIGITAL SIGNAL Processor, DSP), application SPECIFIC INTEGRATED Circuit (ASIC), field-Programmable gate array (Field-Programmable GATE ARRAY, FPGA) or other Programmable logic device, discrete gate or transistor logic device, discrete hardware components.
Example 4:
The present embodiment provides a computer-readable storage medium having instructions stored thereon that, when executed on a computer, cause the computer to perform the power converter detection method of embodiment 1. The computer readable storage medium refers to a carrier for storing data, and may include, but is not limited to, a floppy disk, an optical disk, a hard disk, a flash Memory, and/or a Memory Stick (Memory Stick), etc., where the computer may be a general purpose computer, a special purpose computer, a computer network, or other programmable system.
The present embodiment also provides a computer program product comprising instructions which, when run on a computer, cause the computer to perform the power converter detection method of embodiment 1. Wherein the computer may be a general purpose computer, a special purpose computer, a computer network, or other programmable system.
Finally, it should be noted that: the foregoing description is only of the preferred embodiments of the invention and is not intended to limit the scope of the invention. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention should be included in the protection scope of the present invention.
Claims (10)
1. A power converter detection method, comprising:
In the process of applying pulse signals to the power converter, collecting voltage monitoring signals, ultrasonic monitoring signals and temperature sensing signals of target points on the power converter within a set time period;
Performing CEEMDAN decomposition on the voltage monitoring signal to obtain a corresponding first decomposition result, and performing wavelet denoising and signal reconstruction processing on the first decomposition result to obtain a denoising voltage monitoring signal;
Constructing a voltage monitoring waveform diagram based on the denoising voltage monitoring signal and constructing a temperature monitoring waveform diagram based on the temperature sensing signal;
determining a first frequency parameter and a peak voltage parameter of a voltage monitoring waveform in a voltage monitoring waveform diagram, and determining a temperature change parameter of a temperature monitoring waveform in a temperature monitoring waveform diagram;
When the first frequency parameter is in a set frequency interval, calculating a peak voltage difference by using the peak voltage parameter and a set reference peak voltage parameter, and determining first office placement reliability according to the peak voltage difference;
Calculating a temperature change parameter difference by utilizing the temperature change parameter and the set reference temperature change parameter, and determining a second office placement reliability according to the temperature change parameter difference;
Denoising the ultrasonic monitoring signal to obtain a denoised ultrasonic monitoring signal, and extracting a Mel frequency spectrum of the denoised ultrasonic monitoring signal to obtain a corresponding Mel frequency spectrum map;
Inputting the Mel spectrogram into a pre-trained BP neural network model for partial discharge detection to obtain a partial discharge normalization parameter, and determining a third partial placement confidence level according to the partial discharge normalization parameter;
And calculating the partial discharge comprehensive index of the target point on the power converter according to the first partial discharge confidence coefficient, the second partial discharge confidence coefficient and the third partial discharge confidence coefficient, judging whether the target point has partial discharge according to the partial discharge comprehensive index, obtaining a partial discharge detection result of the target point, and outputting the partial discharge comprehensive index and the partial discharge detection result of the target point.
2. The method of claim 1, further comprising:
Obtaining partial discharge comprehensive indexes of a plurality of continuous target points on a power converter, and sequentially numbering the continuous target points;
constructing a comprehensive index scatter diagram based on serial numbers of a plurality of target points and the partial discharge comprehensive index, wherein the abscissa of the comprehensive index scatter diagram represents the point numbers, and the ordinate represents the partial discharge comprehensive index;
Sequentially connecting all scattered points in the comprehensive index scattered point diagram to obtain a comprehensive index broken line diagram;
Determining a point position number corresponding to a peak point in the comprehensive index line graph, wherein the peak point is a non-edge point in the comprehensive index line graph, and taking the point position number corresponding to the peak point as a judgment number;
And outputting the judging number and the partial discharge comprehensive index corresponding to the target point position.
3. The method of claim 1, wherein the performing CEEMDAN on the voltage monitoring signal to obtain a corresponding first decomposition result, performing wavelet denoising and signal reconstruction processing on the first decomposition result to obtain a denoised voltage monitoring signal, and further comprising:
Carrying out CEEMDAN decomposition on the voltage monitoring signal to obtain a plurality of eigenmode function components and residual items, and carrying out wavelet transformation processing on each eigenmode function component to obtain corresponding wavelet coefficients;
determining a wavelet threshold by adopting an adaptive threshold method, constructing a threshold filter function based on the wavelet threshold, and substituting each wavelet coefficient into the threshold filter function to calculate so as to obtain a filtered wavelet coefficient corresponding to each wavelet coefficient, wherein the threshold filter function is that
Wherein, beta represents the wavelet coefficient after filtering, alpha represents the wavelet coefficient, and omega represents the wavelet threshold;
Removing the filtered wavelet coefficient of 0, and associating the residual filtered wavelet coefficients with corresponding eigenmode function components;
And carrying out signal reconstruction on the eigenvalue function components corresponding to the wavelet coefficients after the filtering and the residual items to obtain a denoising voltage monitoring signal.
4. The method of claim 1, wherein determining the first frequency parameter and the peak voltage parameter of the voltage monitoring waveform in the voltage monitoring waveform map, and determining the temperature variation parameter of the temperature monitoring waveform in the temperature monitoring waveform map, comprises:
Determining the average frequency and the maximum peak voltage of a voltage monitoring waveform in a voltage monitoring waveform diagram, taking the average frequency as a first frequency parameter and the maximum peak voltage as a peak voltage parameter;
And determining the temperature difference of the temperature monitoring waveform in each time interval in the temperature monitoring waveform chart, dividing the temperature difference in the corresponding time interval by the time length of the time interval to obtain the temperature change coefficient of the corresponding time interval, and taking the maximum temperature change coefficient as the temperature change parameter.
5. The method of claim 1, wherein calculating a peak voltage difference using the peak voltage parameter and the set reference peak voltage parameter when the first frequency parameter is in the set frequency interval, and determining the first local placement confidence according to the peak voltage difference, comprises:
subtracting the set reference peak voltage parameter from the peak voltage parameter when the first frequency parameter is in the set frequency interval to obtain a peak voltage difference;
The peak voltage difference is imported into a preset first office placement confidence level table for matching, corresponding first office placement confidence level is determined, the first office placement confidence level table comprises a plurality of peak voltage difference intervals, and each peak voltage difference interval is associated with the corresponding first office placement confidence level.
6. The method of claim 1, wherein calculating a temperature variation parameter difference using the temperature variation parameter and the set reference temperature variation parameter, and determining the second office placement confidence according to the temperature variation parameter difference, comprises:
Subtracting the set reference temperature variation parameter from the temperature variation parameter to obtain a temperature variation parameter difference;
And importing the temperature change parameter difference into a preset second partial discharge confidence level table for matching, and determining corresponding second partial discharge confidence level, wherein the second partial discharge confidence level table comprises a plurality of temperature change parameter difference intervals, and each temperature change parameter difference interval is associated with the corresponding second partial discharge confidence level.
7. The method for detecting a power converter according to claim 1, wherein the denoising processing is performed on the ultrasonic monitoring signal to obtain a denoised ultrasonic monitoring signal, and the extracting of a mel spectrum is performed on the denoised ultrasonic monitoring signal to obtain a corresponding mel spectrum map, and the method comprises:
Denoising the ultrasonic monitoring signal by adopting a Kalman filtering algorithm to obtain a denoised ultrasonic monitoring signal;
Pre-emphasis treatment is carried out on the denoising ultrasonic monitoring signal to obtain a denoising ultrasonic monitoring signal after pre-emphasis;
carrying out windowing framing treatment and fast Fourier transform treatment on the pre-emphasized denoising ultrasonic monitoring signal to obtain a denoising ultrasonic monitoring signal frequency spectrum;
and filtering the denoising ultrasonic monitoring signal frequency spectrum by adopting a Mel filter group to obtain a corresponding Mel spectrogram.
8. The method for detecting a power converter according to claim 1, wherein calculating the partial discharge comprehensive index of the target point location on the power converter according to the first partial discharge confidence level, the second partial discharge confidence level and the third partial discharge confidence level comprises:
determining a voltage index coefficient corresponding to the voltage monitoring signal, an ultrasonic index coefficient corresponding to the ultrasonic monitoring signal and a temperature index coefficient corresponding to the temperature sensing signal;
Multiplying the first partial placement reliability by a voltage index coefficient to obtain a first partial placement index, multiplying the second partial placement reliability by an ultrasonic index coefficient to obtain a second partial placement index, and multiplying the third partial placement reliability by a temperature index coefficient to obtain a third partial placement index;
And adding the first partial discharge index, the second partial discharge index and the third partial discharge index to obtain a partial discharge comprehensive index.
9. The utility model provides a power converter detecting system which characterized in that includes signal acquisition unit, decomposition denoising unit, wave form construction unit, parameter determination unit, first decision unit, second decision unit, frequency spectrum extraction unit, third decision unit and index calculation unit, wherein:
The signal acquisition unit is used for acquiring a voltage monitoring signal, an ultrasonic monitoring signal and a temperature sensing signal of a target point position on the power converter in a set time period in the process of applying a pulse signal to the power converter;
The decomposition denoising unit is used for carrying out CEEMDAN decomposition on the voltage monitoring signal to obtain a corresponding first decomposition result, and carrying out wavelet denoising and signal reconstruction processing on the first decomposition result to obtain a denoising voltage monitoring signal;
The waveform construction unit is used for constructing a voltage monitoring waveform diagram based on the denoising voltage monitoring signal and constructing a temperature monitoring waveform diagram based on the temperature sensing signal;
the parameter determining unit is used for determining a first frequency parameter and a peak voltage parameter of the voltage monitoring waveform in the voltage monitoring waveform diagram and determining a temperature change parameter of the temperature monitoring waveform in the temperature monitoring waveform diagram;
The first judging unit is used for calculating a peak voltage difference by utilizing the peak voltage parameter and a set reference peak voltage parameter when the first frequency parameter is in a set frequency interval, and determining first office placement reliability according to the peak voltage difference;
The second judging unit is used for calculating a temperature change parameter difference by utilizing the temperature change parameter and the set reference temperature change parameter and determining a second office placement reliability according to the temperature change parameter difference;
the frequency spectrum extraction unit is used for carrying out denoising treatment on the ultrasonic monitoring signal to obtain a denoising ultrasonic monitoring signal, and carrying out Mel frequency spectrum extraction on the denoising ultrasonic monitoring signal to obtain a corresponding Mel frequency spectrogram;
the third judging unit is used for inputting the Mel spectrogram into the pre-trained BP neural network model to perform partial discharge detection, obtaining partial discharge normalization parameters, and determining third partial placement reliability according to the partial discharge normalization parameters;
The index calculation unit is used for calculating the partial discharge comprehensive index of the target point position on the power converter according to the first partial discharge confidence, the second partial discharge confidence and the third partial discharge confidence, judging whether the target point position has partial discharge according to the partial discharge comprehensive index, obtaining a partial discharge detection result of the target point position, and outputting the partial discharge comprehensive index and the partial discharge detection result of the target point position.
10. A power converter detection system, comprising:
A memory for storing instructions;
A processor for reading the instructions stored in the memory and executing the power converter detection method according to any one of claims 1-8 according to the instructions.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410506161.1A CN118091344B (en) | 2024-04-25 | 2024-04-25 | Power converter detection method and system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410506161.1A CN118091344B (en) | 2024-04-25 | 2024-04-25 | Power converter detection method and system |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN118091344A CN118091344A (en) | 2024-05-28 |
| CN118091344B true CN118091344B (en) | 2024-06-25 |
Family
ID=91156597
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202410506161.1A Active CN118091344B (en) | 2024-04-25 | 2024-04-25 | Power converter detection method and system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN118091344B (en) |
Family Cites Families (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JPH0769372B2 (en) * | 1989-04-26 | 1995-07-31 | 富士電機株式会社 | Partial discharge monitoring device for gas insulated equipment |
| CN105911499B (en) * | 2016-06-30 | 2019-03-01 | 国网重庆市电力公司电力科学研究院 | Ultrasonic wave shelf depreciation metering system and method under site environment |
| CN111626153B (en) * | 2020-05-13 | 2022-10-18 | 电子科技大学 | Integrated learning-based partial discharge fault state identification method |
| CN114977113A (en) * | 2022-06-13 | 2022-08-30 | 北京迪赛奇正科技有限公司 | AC-DC converter control method and device |
| CN116975566A (en) * | 2023-07-27 | 2023-10-31 | 内蒙古电力(集团)有限责任公司乌海供电分公司 | Intelligent transformer monitoring system and method based on multi-source parameter analysis and diagnosis |
| CN220583474U (en) * | 2023-08-24 | 2024-03-12 | 青岛利恒电子有限公司 | Multifunctional partial discharge sensor |
| CN117214777A (en) * | 2023-09-15 | 2023-12-12 | 广东电网有限责任公司 | Fault positioning method, system, equipment and storage medium for transformer winding |
| CN117148076B (en) * | 2023-10-31 | 2024-01-26 | 南通豪强电器设备有限公司 | Multi-feature fusion type high-voltage switch cabinet partial discharge identification method and system |
| CN117783796A (en) * | 2024-02-27 | 2024-03-29 | 国网山西省电力公司太原供电公司 | Integrated sensing monitoring method and system based on partial discharge ultrasonic wave of transformer |
-
2024
- 2024-04-25 CN CN202410506161.1A patent/CN118091344B/en active Active
Non-Patent Citations (2)
| Title |
|---|
| 变压器局部放电在线监测技术的研究;杨启平;薛五德;蓝之达;;变压器;20081008(第10期);全文 * |
| 局部放电检测技术研究;李文明;李佩佩;张峰;;机电信息;20150525(第15期);全文 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN118091344A (en) | 2024-05-28 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN102680860B (en) | Automatic fault-point locating method for traveling-wave based fault location of high-voltage electric power lines | |
| Tang et al. | A correlated empirical mode decomposition method for partial discharge signal denoising | |
| CN108693448B (en) | Partial discharge mode recognition system applied to power equipment | |
| CN107080545B (en) | A kind of lie detection system based on brain electricity | |
| US20140025715A1 (en) | Neural Signal Processing and/or Interface Methods, Architectures, Apparatuses, and Devices | |
| CN114325256A (en) | Power equipment partial discharge identification method, system, equipment and storage medium | |
| CN107361764A (en) | A kind of rapid extracting method of electrocardiosignal signature waveform R ripples | |
| CN116865269A (en) | Wind turbine generator system high harmonic compensation method and system | |
| CN216848010U (en) | Cable partial discharge online monitoring device for edge calculation | |
| US5136529A (en) | Digital signal weighting processing apparatus and method | |
| CN118091344B (en) | Power converter detection method and system | |
| Pan et al. | Adaptive multi-layer empirical Ramanujan decomposition and its application in roller bearing fault diagnosis | |
| CN113221615A (en) | Partial discharge pulse extraction method based on noise reduction clustering | |
| CN112914588A (en) | Electroencephalogram outbreak inhibition index calculation method and system | |
| CN117434396A (en) | On-line monitoring system and method for transformer bushing end screen | |
| CN112033656A (en) | Mechanical system fault detection method based on broadband spectrum processing | |
| CN110507299B (en) | Heart rate signal detection device and method | |
| CN113413135B (en) | Pulse acquisition analysis-based method, system, device and storage medium | |
| CN116482526A (en) | Analysis system for non-fault phase impedance relay | |
| CN115969398A (en) | Blink detection method and device | |
| CN112114215A (en) | Transformer aging evaluation method and system based on error back propagation algorithm | |
| Das et al. | On an algorithm for detection of QRS complexes in noisy electrocardiogram signal | |
| Ieong et al. | ECG QRS complex detection with programmable hardware | |
| CN109793511A (en) | Electrocardiosignal noise detection algorithm based on depth learning technology | |
| Singh | MATLAB based ECG signal noise removal and its analysis |
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 |