CN117406046A - Partial discharge detection device - Google Patents
Partial discharge detection device Download PDFInfo
- Publication number
- CN117406046A CN117406046A CN202311713387.0A CN202311713387A CN117406046A CN 117406046 A CN117406046 A CN 117406046A CN 202311713387 A CN202311713387 A CN 202311713387A CN 117406046 A CN117406046 A CN 117406046A
- Authority
- CN
- China
- Prior art keywords
- signal
- module
- partial discharge
- signals
- analog
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
- 238000001514 detection method Methods 0.000 title claims abstract description 34
- 238000012545 processing Methods 0.000 claims abstract description 46
- 230000004044 response Effects 0.000 claims abstract description 5
- 230000003321 amplification Effects 0.000 claims description 48
- 238000003199 nucleic acid amplification method Methods 0.000 claims description 48
- 238000005070 sampling Methods 0.000 claims description 32
- 238000000605 extraction Methods 0.000 claims description 16
- 238000013145 classification model Methods 0.000 claims description 15
- 238000004458 analytical method Methods 0.000 claims description 13
- 239000000284 extract Substances 0.000 claims description 12
- 230000009466 transformation Effects 0.000 claims description 12
- 238000007781 pre-processing Methods 0.000 claims description 10
- 238000012549 training Methods 0.000 claims description 9
- 238000001914 filtration Methods 0.000 claims description 6
- 230000010354 integration Effects 0.000 claims description 6
- 238000004891 communication Methods 0.000 claims description 4
- 230000001105 regulatory effect Effects 0.000 claims 1
- 238000000034 method Methods 0.000 abstract description 22
- 230000008569 process Effects 0.000 description 11
- 239000012212 insulator Substances 0.000 description 5
- 238000013461 design Methods 0.000 description 4
- 238000010586 diagram Methods 0.000 description 4
- 230000005540 biological transmission Effects 0.000 description 3
- 230000000694 effects Effects 0.000 description 3
- 230000009467 reduction Effects 0.000 description 3
- 230000006978 adaptation Effects 0.000 description 2
- 238000013528 artificial neural network Methods 0.000 description 2
- 230000008859 change Effects 0.000 description 2
- 230000007547 defect Effects 0.000 description 2
- 230000005684 electric field Effects 0.000 description 2
- 239000012535 impurity Substances 0.000 description 2
- 239000011159 matrix material Substances 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000012544 monitoring process Methods 0.000 description 2
- 230000035945 sensitivity Effects 0.000 description 2
- 239000002699 waste material Substances 0.000 description 2
- 230000004913 activation Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 230000015556 catabolic process Effects 0.000 description 1
- 238000006243 chemical reaction Methods 0.000 description 1
- 230000006835 compression Effects 0.000 description 1
- 238000007906 compression Methods 0.000 description 1
- 238000000354 decomposition reaction Methods 0.000 description 1
- 238000003745 diagnosis Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 230000036541 health Effects 0.000 description 1
- 230000001939 inductive effect Effects 0.000 description 1
- 238000012423 maintenance Methods 0.000 description 1
- 238000010606 normalization Methods 0.000 description 1
- 230000003449 preventive effect Effects 0.000 description 1
- 230000002035 prolonged effect Effects 0.000 description 1
- 238000013519 translation 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
- G01R31/00—Arrangements for testing electric properties; Arrangements for locating electric faults; Arrangements for electrical testing characterised by what is being tested not provided for elsewhere
- G01R31/12—Testing dielectric strength or breakdown voltage ; Testing or monitoring effectiveness or level of insulation, e.g. of a cable or of an apparatus, for example using partial discharge measurements; Electrostatic testing
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/10—Pre-processing; Data cleansing
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/241—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches
-
- H—ELECTRICITY
- H03—ELECTRONIC CIRCUITRY
- H03G—CONTROL OF AMPLIFICATION
- H03G3/00—Gain control in amplifiers or frequency changers
- H03G3/20—Automatic control
- H03G3/30—Automatic control in amplifiers having semiconductor devices
-
- H—ELECTRICITY
- H03—ELECTRONIC CIRCUITRY
- H03H—IMPEDANCE NETWORKS, e.g. RESONANT CIRCUITS; RESONATORS
- H03H17/00—Networks using digital techniques
- H03H17/02—Frequency selective networks
- H03H17/0248—Filters characterised by a particular frequency response or filtering method
-
- 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
- G06F2218/06—Denoising by applying a scale-space analysis, e.g. using wavelet analysis
-
- 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
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2218/00—Aspects of pattern recognition specially adapted for signal processing
- G06F2218/12—Classification; Matching
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- Computer Vision & Pattern Recognition (AREA)
- General Physics & Mathematics (AREA)
- Artificial Intelligence (AREA)
- Evolutionary Biology (AREA)
- Evolutionary Computation (AREA)
- Bioinformatics & Computational Biology (AREA)
- General Engineering & Computer Science (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Computer Hardware Design (AREA)
- Mathematical Physics (AREA)
- Testing Relating To Insulation (AREA)
Abstract
The invention provides a partial discharge detection device, which relates to the technical field of electric power detection and comprises: a digital filter for receiving the partial discharge signal byProcessing the partial discharge signal to output a filtered signalWherein, the method comprises the steps of, wherein,，in order to acquire the partial discharge signal,the impulse response of the digital filter, n being the discrete point in time,is the mean value of the partial discharge signal within the sliding window,is the standard deviation of the partial discharge signal within the sliding window,is an adjustment factor that is used to adjust the position of the device,is a sequence of thresholds. The invention can effectively filter the interference signal and improve the quality and the signal-to-noise ratio of the signal.
Description
Technical Field
The invention relates to the technical field of electric power detection, in particular to a partial discharge detection device.
Background
Partial discharge is a discharge phenomenon occurring in a partial region in an insulator of a high-voltage electrical apparatus. Such discharges can occur inside or on the surface of the insulator, typically caused by defects, bubbles, moisture or other impurities in the insulator. When the high-voltage electric device is operated, the electric field intensity is high, and if a defect or impurity exists in the insulator, the local electric field intensity exceeds the breakdown field intensity of the insulator, thereby inducing a partial discharge.
The partial discharge signal is a weak electrical signal, which is usually small in amplitude and short in duration. The partial discharge signal is submerged in strong electromagnetic interference and is therefore difficult to directly detect. In order to efficiently detect the partial discharge signal, a detection device with high sensitivity is required.
Currently, the commonly used partial discharge detection method includes an ultrasonic detection method, a high-frequency current detection method, and the like. However, these methods have some problems.
Ultrasonic detection methods utilize ultrasonic sensors to detect acoustic signals generated by partial discharges. However, the ultrasonic sensor is susceptible to mechanical vibration, electromagnetic interference, and other factors, resulting in insufficient detection sensitivity.
A high-frequency current detection method detects partial discharge by measuring a high-frequency current signal generated by the partial discharge. However, the high-frequency current signal is easily affected by electromagnetic interference, resulting in low signal-to-noise ratio and high detection difficulty.
Disclosure of Invention
The invention aims to solve the technical problem of providing a partial discharge detection device, which can effectively filter interference signals by adopting a digital filter to process partial discharge signals, improve the quality and the signal-to-noise ratio of the signals, and can adaptively adjust the amplification factor according to the strength of the signals by adopting a gain control module so as to further improve the recognition rate of the signals.
In order to solve the technical problems, the technical scheme of the invention is as follows:
a partial discharge detection apparatus comprising:
the sensor module is used for collecting partial discharge signals of the high-voltage electrical equipment;
a digital filter for receiving the partial discharge signal byProcessing the partial discharge signal to output a filtered signalWherein, the method comprises the steps of, wherein,，in order to acquire the partial discharge signal,the impulse response of the digital filter, n being the discrete point in time,is the mean value of the partial discharge signal within the sliding window,is the standard deviation of the partial discharge signal within the sliding window,is an adjustment factor that is used to adjust the position of the device,is a threshold sequence;
the gain control module is used for adjusting the amplification factor according to the intensity of the filtered signal so as to obtain a first gain signal;
the characteristic extraction module is used for carrying out wavelet transformation on the first gain signal so as to extract characteristic information of the first gain signal on different scales;
the classification and identification module is used for classifying and identifying the characteristic information to obtain a classification result;
and the intelligent prediction module is used for analyzing the classification result to obtain a predicted value.
Further, an analog-to-digital converter is arranged in the sensor module;
the analog-to-digital converter extracts instantaneous values from continuous-time analog signals according to preset time intervals, the sampled analog signals are converted into discrete digital values, the amplitude range of the analog signals is divided into a series of discrete levels, and each level corresponds to one digital value.
Further, the analog-to-digital converter extracts an instantaneous value from the continuous analog signal according to a preset time interval, and the method comprises the following steps:
determining the sampling period T of the analog-to-digital converter according to the time interval between two consecutive samples s ；
At each sampling period T s An analog-to-digital converter samples the analog signal;
at the sampling instant, the analog-to-digital converter extracts an instantaneous value from the analog signal；
Using a window of length M to pass through M sampling points aroundProcessing to obtain an output signalWherein, the method comprises the steps of, wherein,for calculating an instantaneous value at a discrete point in time,is an integer representing the first at a discrete point in timeSampling points and sampling periodsMultiplication for determining specific sampling instants on a continuous time axis,is an integer for iterating through a window of moving average filtering.
Further, the gain control module includes:
the detector is used for predicting the strength of the filtered signal to obtain a predicted signal, and judging the strength of the predicted signal and a preset threshold value to obtain a judging result;
the amplifier is used for adjusting the amplification factor according to the intensity of the filtered signal so as to obtain a first amplified signal;
and the controller is used for calculating the amplification factor according to the first amplification signal and generating a control signal to the amplifier.
Further, the detector includes:
the sensing module is used for converting the filtered signals into electric signals;
the signal processing module is used for processing the electric signals output by the sensing module to obtain processed signals;
and the control logic module is used for processing, analyzing and judging the processing signals output by the signal processing module so as to obtain judging signals.
Further, the amplifier includes:
the input matching module is used for matching the impedance of the signal source with the input impedance of the amplifier to obtain a matching signal;
the preamplification module is used for amplifying the matching signal to obtain a second amplified signal;
the gain controller is used for adjusting the amplification factor according to the second amplification signal so as to output a second gain signal;
and the driving amplification module is used for amplifying the second gain signal.
Further, the feature extraction module includes:
the preprocessing submodule is used for preprocessing the input first gain signal;
and the wavelet transformation submodule is used for carrying out continuous wavelet transformation on the preprocessed input signal, decomposing the signal into wavelet coefficients on different scales and positions and extracting key features from the wavelet coefficients.
Further, the classification recognition module includes:
the model training sub-module is used for receiving the input characteristic information and the corresponding class labels, and performing model training to output a trained classification model;
and the classification recognition sub-module is used for receiving the input characteristic information from the characteristic extraction module, classifying and recognizing the input characteristic information by using the trained classification model, and obtaining a classification result by matching the input characteristic with the class in the classification model.
Further, the intelligent prediction module includes:
the data integration sub-module is used for acquiring an integrated classification result and historical data so as to construct a data set;
and the prediction analysis sub-module is used for matching the new data with the data set to generate a predicted value.
Further, the partial discharge detection device further includes:
the intelligent early warning module is used for judging the running state of the electrical equipment according to the predicted value and sending out an early warning signal when the fault is predicted;
the communication module is used for sending the detected partial discharge signals, the classification result, the predicted value and the early warning signals to the mobile terminal;
and the power management module is used for providing power.
The scheme of the invention at least comprises the following beneficial effects:
according to the scheme, the digital filter is adopted to process the partial discharge signal, so that the interference signal can be effectively filtered, and the quality and the signal-to-noise ratio of the signal can be improved. Meanwhile, by adopting the gain control module, the amplification factor can be adaptively adjusted according to the strength of the signal, so that the recognition rate of the signal is further improved. By adopting the feature extraction module and the classification and identification module, the partial discharge signals can be automatically classified and identified, and the detection efficiency and accuracy are improved. Meanwhile, by adopting the intelligent prediction module, the local discharge signal can be predicted and analyzed according to historical data, and the equipment fault can be early warned and prevented in advance.
Drawings
Fig. 1 is a schematic diagram of a partial discharge detection apparatus according to an embodiment of the present invention.
Fig. 2 is a schematic diagram of a gain control module of a partial discharge detection apparatus according to an embodiment of the present invention.
Fig. 3 is a schematic diagram of a detector of a partial discharge detection apparatus according to an embodiment of the present invention.
Fig. 4 is an amplifier schematic diagram of a partial discharge detection apparatus according to an embodiment of the present invention.
Detailed Description
Exemplary embodiments of the present disclosure will be described more closely below with reference to the accompanying drawings. While exemplary embodiments of the present disclosure are shown in the drawings, it should be understood that the present disclosure may be embodied in various forms and should not be limited to the embodiments set forth herein. Rather, these embodiments are provided so that this disclosure will be thorough and complete, and will fully convey the scope of the disclosure to those skilled in the art.
As shown in fig. 1, an embodiment of the present invention proposes a partial discharge detection apparatus including:
the sensor module is used for collecting partial discharge signals of the high-voltage electrical equipment;
a digital filter for receiving the partial discharge signal byProcessing the partial discharge signal to output a filtered signalWherein, the method comprises the steps of, wherein,，in order to acquire the partial discharge signal,the impulse response of the digital filter, n being the discrete point in time,is the mean value of the partial discharge signal within the sliding window,is the standard deviation of the partial discharge signal within the sliding window,is an adjustment factor that is used to adjust the position of the device,is a threshold sequence;
the gain control module is used for adjusting the amplification factor according to the intensity of the filtered signal so as to obtain a first gain signal;
the characteristic extraction module is used for carrying out wavelet transformation on the first gain signal so as to extract characteristic information of the first gain signal on different scales;
the classification and identification module is used for classifying and identifying the characteristic information to obtain a classification result;
and the intelligent prediction module is used for analyzing the classification result to obtain a predicted value.
In the embodiment of the invention, the digital filter is adopted to process the partial discharge signal, so that the interference signal can be effectively filtered, and the quality and the signal-to-noise ratio of the signal can be improved. Meanwhile, by adopting the gain control module, the amplification factor can be adaptively adjusted according to the strength of the signal, so that the recognition rate of the signal is further improved. By adopting the feature extraction module and the classification and identification module, the partial discharge signals can be automatically classified and identified, and the detection efficiency and accuracy are improved. Meanwhile, by adopting the intelligent prediction module, the local discharge signal can be predicted and analyzed according to historical data, and the equipment fault can be early warned and prevented in advance.
In another preferred embodiment of the invention, an analog-to-digital converter is arranged inside the sensor module;
the analog-to-digital converter extracts instantaneous values from continuous-time analog signals according to preset time intervals, the sampled analog signals are converted into discrete digital values, the amplitude range of the analog signals is divided into a series of discrete levels, and each level corresponds to one digital value.
In the embodiment of the invention, the analog-to-digital converter extracts the instantaneous value from the continuous analog signal according to the preset time interval, converts the analog signal into the discrete digital value, can effectively eliminate noise and interference in the analog signal, and improves the precision and resolution of the signal. Meanwhile, the processing and analysis of the digital signals are more convenient and accurate. Analog signals are susceptible to various disturbances during transmission and processing, resulting in instability and distortion of the signal. The digital signal has good anti-interference capability, so that the interference can be eliminated to a certain extent, and the stability and reliability of the signal are enhanced. After the analog-to-digital converter converts the analog signal into the digital signal, the digital signal processing technology can be utilized to further process and analyze the signal, and meanwhile, the digital signal can be conveniently stored and transmitted, so that the remote monitoring and diagnosis of the signal can be realized. The analog-to-digital converter can be used for converting the analog signal into the digital signal, so that the signal processing and analyzing processes are simplified, and the complexity and cost of the system are reduced. Meanwhile, the processing and analysis of the digital signals can be realized by using the existing digital signal processing chip and software, so that the integration level and the expandability of the system are improved.
In a preferred embodiment of the present invention, the analog-to-digital converter extracts instantaneous values from the continuous-time analog signal at preset time intervals, including:
determining the sampling period T of the analog-to-digital converter according to the time interval between two consecutive samples s ；
At each sampling period T s An analog-to-digital converter samples the analog signal;
at the sampling instant, the analog-to-digital converter extracts an instantaneous value from the analog signal；
Using a window of length M to pass through M sampling points aroundProcessing to obtain an output signalWherein, the method comprises the steps of, wherein,for calculating an instantaneous value at a discrete point in time,is an integer representing the first at a discrete point in timeSampling points and sampling periodsMultiplication for determining specific sampling instants on a continuous time axis,is an integer for iterating through a window of moving average filtering.
In the embodiment of the invention, the sampling period of the analog-to-digital converter is determined, and the analog signal is sampled at the starting moment of each sampling period, so that the time interval between sampling points is ensured to be equal, the sampling precision and efficiency are improved, the condition of signal distortion and missing sampling can be effectively avoided by adopting the timing sampling mode, and the accuracy and the integrity of sampling data are ensured. The analog-to-digital converter extracts instantaneous values from the analog signals at sampling moments, so that high-frequency noise and interference in the analog signals can be effectively eliminated, and the extraction of the instantaneous values is an instantaneous process and is not influenced by the noise and the interference. The noise reduction effect can improve the signal to noise ratio of the signal, so that the subsequent signal processing and analysis are more accurate and reliable. By processing the surrounding M sampling points by using a window with the length of M, an output signal can be obtained, burrs and abrupt changes in the signal can be effectively smoothed, and the smoothness and stability of the signal are enhanced. Meanwhile, the filtering effect and the smoothness of the output signal can be adjusted according to actual needs by adjusting the window length M. The analog-to-digital converter samples at the starting moment of each sampling period and extracts the instantaneous value at the sampling moment, and the processing mode has high instantaneity and response speed, so that the instantaneity of the system can be improved to a certain extent, and the change of the signal can be reflected in time because the data in the window are continuously updated. By using the analog-to-digital converter and the moving average filtering method, the signal processing and analyzing process can be simplified, the complexity and cost of the system can be reduced, the system can be realized by using the existing digital signal processing chip and software, and the integration level and the expandability of the system are improved.
As shown in fig. 2, the gain control module includes:
the detector is used for predicting the strength of the filtered signal to obtain a predicted signal, and judging the strength of the predicted signal and a preset threshold value to obtain a judging result;
the amplifier is used for adjusting the amplification factor according to the intensity of the filtered signal so as to obtain a first amplified signal;
and the controller is used for calculating the amplification factor according to the first amplification signal and generating a control signal to the amplifier.
In the embodiment of the invention, the gain control module can adjust the amplification factor in real time according to the strength of the filtered signal, so that the signal can be properly amplified under different strengths. The strength of the filtered signal is predicted through the detector and compared with a preset threshold value, a judging result can be obtained, and according to the judging result, the amplifier can adjust the amplification factor, so that the amplitude range of the signal is more suitable, the recognition rate of the signal is improved, the self-adaptive amplification function can enable the weak signal to be amplified sufficiently, and the strong signal is not amplified excessively, so that the performance of the whole system is improved. The gain control module can reduce the influence of noise interference by adjusting the amplification factor, and can improve the signal-to-noise ratio of a signal by proper amplification for a weak signal; for strong signals, signal distortion and noise amplification can be avoided by properly reducing the amplification factor, and the noise reduction effect can improve the quality and accuracy of the signals. The controller calculates the amplification factor according to the first amplification signal, generates a control signal to the amplifier, and realizes accurate control of the amplification factor. The gain control module can adjust a preset threshold value and amplification factor according to actual requirements, so that signals with different intensities and types can be flexibly processed and analyzed.
As shown in fig. 3, the detector includes:
the sensing module is used for converting the filtered signals into electric signals;
the signal processing module is used for processing the electric signals output by the sensing module to obtain processed signals;
and the control logic module is used for processing, analyzing and judging the processing signals output by the signal processing module so as to obtain judging signals.
In the embodiment of the invention, the sensing module converts the filtered signal into the electric signal, and the conversion can improve the sensing capability of the signal, so that the detector can accurately receive and process the signal. The sensing module can effectively convert the weak filtered signal into an electrical signal. The signal processing module processes the electric signal output by the sensing module to obtain a processed signal, so that the quality and the signal to noise ratio of the signal are improved, noise and interference in the signal can be effectively eliminated through the processing of the signal processing module, useful information is extracted, and the subsequent analysis and judgment are more accurate and reliable. The control logic module processes, analyzes and judges the processing signals output by the signal processing module to obtain judging signals. The control logic module can carry out logic judgment on the processing signals according to preset rules and algorithms, and the characteristics and the states of the signals are determined. The judging function can improve the recognition rate and accuracy of signals and avoid the situations of misjudgment and missed judgment. The detector realizes the automatic control of signal processing and analysis through the control logic module. The control logic module can automatically adjust signal processing parameters and judging threshold values, so as to realize self-adaptive processing and analysis of signals with different intensities and types. The modular design of the detector allows it to be easily integrated and expanded with other systems or devices. By adding or replacing different sensing modules, signal processing modules and control logic modules, different application scenes and requirements can be adapted, and the expandability and the adaptability of the system are improved.
As shown in fig. 4, the amplifier includes:
the input matching module is used for matching the impedance of the signal source with the input impedance of the amplifier to obtain a matching signal;
the preamplification module is used for amplifying the matching signal to obtain a second amplified signal;
the gain controller is used for adjusting the amplification factor according to the second amplification signal so as to output a second gain signal;
and the driving amplification module is used for amplifying the second gain signal.
In the embodiment of the invention, the input matching module matches the impedance of the signal source with the input impedance of the amplifier to obtain a matching signal, the impedance matching can reduce the reflection and loss of the signal in the transmission process, the transmission efficiency of the signal is improved, and the matching module ensures good connection between the signal source and the amplifier, so that the signal can be transmitted to the amplifier to be processed to the maximum extent. The pre-amplification module performs preliminary amplification on the matching signal to obtain a second amplified signal. The pre-amplification module has the characteristics of high input impedance and low output impedance, and can effectively amplify weak signals and reduce noise interference. The presence of the pre-amplification module improves the signal to noise ratio and amplitude of the signal. The gain controller adjusts the amplification factor according to the intensity and the characteristics of the second amplified signal so as to output the second gain signal, the dynamic gain control function can adjust in real time according to the actual condition of the signal, the signal can be properly amplified under different intensities and frequencies, and the self-adaptive control capability improves the flexibility and the adaptability of the amplifier, so that the signal amplification is more accurate and reliable.
In the embodiment of the invention, the driving amplification module further amplifies the second gain signal to drive a post-stage circuit or a load. The driving amplification module has the characteristics of high output power and low distortion, can effectively drive various loads, and ensures the integrity and stability of signals. The driving capability of the amplifier is enhanced by the driving amplification module, so that the amplifier can adapt to different application scenes and requirements. Through reasonable circuit design and element selection, the amplifier can reduce system noise and distortion. The input matching module reduces signal reflection and loss, the pre-amplifying module reduces noise interference, the gain controller realizes dynamic gain adjustment, and the driving amplifying module ensures signal integrity and stability. These measures together reduce noise and distortion of the system, improving the quality and accuracy of the signal. The amplifier adopts a modularized design, and each module has definite functions and interfaces, so that the whole system is more stable and reliable. Meanwhile, through reasonable circuit protection and thermal design, the amplifier can stably operate for a long time in a severe working environment, and the reliability and the service life of the system are improved.
In another preferred embodiment of the present invention, in saidIn the pre-amplifying module, the matching signal processed by the input matching module is marked as V in Inputting the signals into a pre-amplifying module, and performing voltage amplification on the input signals by the pre-amplifying module, wherein the amplification factor isThe amplified output signal is denoted as V out =×V in The method comprises the steps of carrying out a first treatment on the surface of the The amplified signal, namely the second amplified signal, is output to a next stage circuit for further processing, wherein V in Representing the voltage of the matched signal input to the pre-amplifier module, V out Representing the second amplified signal voltage output by the pre-amplification module,is the amplifier at the center frequencyAt the maximum voltage amplification factor of the light source,is the quality factor of the amplifier and,is the angular frequency of the input signal and j is the imaginary unit.
In a preferred embodiment of the present invention, the feature extraction module includes:
the preprocessing submodule is used for preprocessing the input first gain signal;
and the wavelet transformation submodule is used for carrying out continuous wavelet transformation on the preprocessed input signal, decomposing the signal into wavelet coefficients on different scales and positions and extracting key features from the wavelet coefficients.
In the embodiment of the invention, the noise or other irrelevant components in the signal can be effectively restrained or filtered by preprocessing the input first gain signal, so that the quality and definition of the signal are improved; the preprocessing can make the signal more consistent in amplitude, offset or other characteristics, and provide stable and reliable input for subsequent signal processing; through preprocessing, certain key characteristics in the signal can be highlighted or enhanced, so that subsequent feature extraction is more effective; the continuous wavelet transform allows us to analyze the signal at different scales and locations, thereby enabling capturing of the local and global characteristics of the signal; the wavelet coefficients provide information on the strength of the signal at different frequencies and at different points in time. Extracting key features from wavelet coefficients can provide us with rich information about the signal; by utilizing wavelet transformation, noise and real components in signals can be effectively separated, so that noise reduction is realized, and meanwhile, based on sparsity of wavelet coefficients, efficient compression of the signals can be realized.
In another preferred embodiment of the present invention, the preprocessing sub-module processes the data byThe input first gain signal is processed to obtain an output signal, wherein,is the output signal obtained after filtering and represents the current timeI.e. the filtered first gain signal;representing a normalization factor that computes a moving average, where M is the window size, representing the inverse of the number of data points involved in the average computation;is an attenuation factorA power operation of (c), wherein,is a number between 0 and 1,representing the first gain signal at the momentI.e. the individual data points of the input signal.
In another preferred embodiment of the present invention, in the wavelet transform submodule, continuous wavelet transform is performed on the preprocessed input signal, and the signal is decomposed into wavelet coefficients on different scales and positions, which specifically includes: by passing throughPerforming continuous wavelet transformation on the preprocessed input signal, decomposing the signal into wavelet coefficients at different scales and positions, wherein,representing the signal at scale factorsAnd location parametersThe decomposition result;the input signal is represented by a signal representative of the input signal,representing the complex conjugate of the wavelet function and performing a scale and translation transformation,representing time; key features are extracted from wavelet coefficients.
In a preferred embodiment of the present invention, the classification and identification module includes:
the model training sub-module is used for receiving the input characteristic information and the corresponding class labels, and performing model training to output a trained classification model;
and the classification recognition sub-module is used for receiving the input characteristic information from the characteristic extraction module, classifying and recognizing the input characteristic information by using the trained classification model, and obtaining a classification result by matching the input characteristic with the class in the classification model.
In the embodiment of the invention, a customized classification model can be trained according to specific application requirements and data characteristics through the model training submodule, so that different classification tasks and data characteristics can be better adapted, and the classification accuracy is improved. The classification recognition sub-module can automatically classify and recognize the input features by using a trained classification model, so that the requirement of manual intervention can be reduced, and the processing efficiency and accuracy are improved. The classification recognition sub-module can rapidly match the input features with the categories in the classification model so as to generate classification results, and the classification results can be rapidly obtained in real-time or near real-time application scenes. Since the feature extraction module and the classification model are separated, the feature extraction method and the classification model can be flexibly updated as required, and new feature extraction technology or improved classification model can be introduced when required to improve classification performance.
In a preferred embodiment of the present invention, the intelligent prediction module includes:
the data integration sub-module is used for acquiring an integrated classification result and historical data so as to construct a data set;
and the prediction analysis sub-module is used for matching the new data with the data set to generate a predicted value.
In the embodiment of the invention, the model can learn more modes and trends by integrating the classification result and the historical data, so that more accurate predictions can be made when new data are processed. By training with a rich data set, the prediction analysis sub-module can better identify the underlying structure and rules of the data, so that the prediction analysis sub-module can have better prediction performance on new data which does not appear in the training set. By matching the new data with the historical data in the dataset, the predictive analysis sub-module may generate more pertinent personalized predictions based on the individual's particular patterns and historical behavior. Through effective data integration and analysis, unnecessary resource waste can be reduced, and decision making is more accurate and targeted.
In a preferred embodiment of the present invention, the partial discharge detecting device further includes:
the intelligent early warning module is used for judging the running state of the electrical equipment according to the predicted value and sending out an early warning signal when the fault is predicted;
the communication module is used for sending the detected partial discharge signals, the classification result, the predicted value and the early warning signals to the mobile terminal;
and the power management module is used for providing power.
In the embodiment of the invention, the intelligent early warning module can judge the running state of the electrical equipment according to the predicted value, so that possible faults are predicted; the communication module can send the detected partial discharge signals, the classification result, the predicted value and the early warning signals to the mobile terminal in real time, so that workers can monitor the state of the electrical equipment remotely and obtain information about the health condition of the equipment in time no matter where they are located. Through continuous monitoring and early warning of partial discharge, potential safety hazards caused by equipment faults can be reduced, and safety of staff and equipment is guaranteed. The power management module can ensure that the device effectively uses power, avoids unnecessary energy waste, is particularly important for equipment which operates for a long time or in remote areas, and can reduce the operation cost and the influence on the environment. By predictive and preventive maintenance, the service life of the electrical equipment can be prolonged and damage due to unexpected failure can be reduced.
In another preferred embodiment of the present invention, the power management module may further perform calculation by using a fuzzy control algorithm according to the obtained power state parameter to determine the output power of the power supply, where the method specifically includes:
the power state parameters are obtained through the electric quantity sensor, the power state parameters comprise input voltage and current, the analog signals are converted into digital signals, and a power state parameter vector g= [ g ] is obtained 1 ，g 2 ，…，g l ]；
By p=σ 1 (W p ×g＋b p ) Computing the hiddenOutput result p of the hidden layer, wherein W p Is a weight matrix of the hidden layer, b p Is the bias vector, sigma, of the hidden layer 1 Is an activation function;
according to the output result p of the hidden layer, through y NN =W o ×p＋b o Calculating the output result y of the neural network NN Wherein W is o Is the weight matrix of the output layer, b o Is the bias vector of the output layer;
according to the output result y of the neural network NN By e=y setpoint－ y NN Calculating an error e between the output power set value and the actual output power;
according to the error e, byCalculating the adjustment amount of output powerWherein, the method comprises the steps of, wherein,、andis the proportional, integral and differential coefficient, K, of the PID controller f Is the adjustment coefficient of the fuzzy control,is the adjustment amount of the fuzzy control.
In another preferred embodiment of the present invention, the power management module may further adjust the output voltage according to a load change and a control command of the power management system, and specifically includes:
detecting a load current by a measuring current sensor;
by means of detected load current and expected power
The required output voltage is calculated, wherein,expressed in timeIs used for the output voltage of the (a),expressed in timeIs used for the reference voltage of the (c),the proportionality constant is represented by the formula,the integral constant is represented by a value of,which represents the differential constant of the sample,is the reference voltage(s) that are used to generate the reference voltage,is a virtual variable for integrating items,is the current point in time.
While the foregoing is directed to the preferred embodiments of the present invention, it will be appreciated by those skilled in the art that various modifications and adaptations can be made without departing from the principles of the present invention, and such modifications and adaptations are intended to be comprehended within the scope of the present invention.
Claims (10)
1. A partial discharge detection apparatus, comprising:
the sensor module is used for collecting partial discharge signals of the high-voltage electrical equipment;
a digital filter for receiving the partial discharge signal byProcessing the partial discharge signal to output a filtered signal +.>Wherein->，/>For the detected partial discharge signal, +.>Impulse response of digital filter, n is discrete time point,/for the digital filter>Is the mean value of the partial discharge signal in the sliding window, < >>Is the standard deviation of the partial discharge signal in the sliding window, < >>Is a regulating factor, is->Is a threshold sequence;
the gain control module is used for adjusting the amplification factor according to the intensity of the filtered signal so as to obtain a first gain signal;
the characteristic extraction module is used for carrying out wavelet transformation on the first gain signal so as to extract characteristic information of the first gain signal on different scales;
the classification and identification module is used for classifying and identifying the characteristic information to obtain a classification result;
and the intelligent prediction module is used for analyzing the classification result to obtain a predicted value.
2. The partial discharge detection apparatus according to claim 1, wherein an analog-to-digital converter is provided inside the sensor module;
the analog-to-digital converter extracts instantaneous values from continuous-time analog signals according to preset time intervals, the sampled analog signals are converted into discrete digital values, the amplitude range of the analog signals is divided into a series of discrete levels, and each level corresponds to one digital value.
3. The partial discharge detection apparatus according to claim 2, wherein the analog-to-digital converter extracts instantaneous values from the continuous-time analog signal at preset time intervals, comprising:
determining the sampling period T of the analog-to-digital converter according to the time interval between two consecutive samples s ；
At each sampling period T s An analog-to-digital converter samples the analog signal;
at the sampling instant, the analog-to-digital converter extracts an instantaneous value from the analog signal；
Using a window of length M to pass through M sampling points aroundProcessing to obtain an output signal +>Wherein->For calculating the instantaneous value at discrete points in time, < >>Is an integer representing +.>Sampling points and sampling period->Multiplication for determining specific sampling instants on the continuous time axis,/>Is an integer for iterating through a window of moving average filtering.
4. The partial discharge detection apparatus of claim 3 wherein the gain control module comprises:
the detector is used for predicting the strength of the filtered signal to obtain a predicted signal, and judging the strength of the predicted signal and a preset threshold value to obtain a judging result;
the amplifier is used for adjusting the amplification factor according to the intensity of the filtered signal so as to obtain a first amplified signal;
and the controller is used for calculating the amplification factor according to the first amplification signal and generating a control signal to the amplifier.
5. The partial discharge detection apparatus according to claim 4, wherein the detector comprises:
the sensing module is used for converting the filtered signals into electric signals;
the signal processing module is used for processing the electric signals output by the sensing module to obtain processed signals;
and the control logic module is used for processing, analyzing and judging the processing signals output by the signal processing module so as to obtain judging signals.
6. The partial discharge detection apparatus of claim 5 wherein the amplifier comprises:
the input matching module is used for matching the impedance of the signal source with the input impedance of the amplifier to obtain a matching signal;
the preamplification module is used for amplifying the matching signal to obtain a second amplified signal;
the gain controller is used for adjusting the amplification factor according to the second amplification signal so as to output a second gain signal;
and the driving amplification module is used for amplifying the second gain signal.
7. The partial discharge detection apparatus of claim 6, wherein the feature extraction module comprises:
the preprocessing submodule is used for preprocessing the input first gain signal;
and the wavelet transformation submodule is used for carrying out continuous wavelet transformation on the preprocessed input signal, decomposing the signal into wavelet coefficients on different scales and positions and extracting key features from the wavelet coefficients.
8. The partial discharge detection apparatus of claim 7, wherein the classification recognition module comprises:
the model training sub-module is used for receiving the input characteristic information and the corresponding class labels, and performing model training to output a trained classification model;
and the classification recognition sub-module is used for receiving the input characteristic information from the characteristic extraction module, classifying and recognizing the input characteristic information by using the trained classification model, and obtaining a classification result by matching the input characteristic with the class in the classification model.
9. The partial discharge detection apparatus of claim 8, wherein the intelligent prediction module comprises:
the data integration sub-module is used for acquiring an integrated classification result and historical data so as to construct a data set;
and the prediction analysis sub-module is used for matching the new data with the data set to generate a predicted value.
10. The partial discharge detection apparatus according to claim 9, further comprising:
the intelligent early warning module is used for judging the running state of the electrical equipment according to the predicted value and sending out an early warning signal when the fault is predicted;
the communication module is used for sending the detected partial discharge signals, the classification result, the predicted value and the early warning signals to the mobile terminal;
and the power management module is used for providing power.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311713387.0A CN117406046B (en) | 2023-12-14 | 2023-12-14 | Partial discharge detection device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311713387.0A CN117406046B (en) | 2023-12-14 | 2023-12-14 | Partial discharge detection device |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN117406046A true CN117406046A (en) | 2024-01-16 |
| CN117406046B CN117406046B (en) | 2024-03-08 |
Family
ID=89489387
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311713387.0A Active CN117406046B (en) | 2023-12-14 | 2023-12-14 | Partial discharge detection device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117406046B (en) |
Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102095938A (en) * | 2010-03-08 | 2011-06-15 | 北京信息科技大学 | High-precision signal processing method for insulation online monitoring of high-voltage electric-power capacitive equipment |
| CN103699033A (en) * | 2013-12-10 | 2014-04-02 | 沈阳航空航天大学 | Embedded magnetorheological shock load buffer controller based on DSP (digital signal processor), and control method |
| CN108446632A (en) * | 2018-03-20 | 2018-08-24 | 珠海华网科技有限责任公司 | It a kind of partial discharge pulse edge finds and shelf depreciation confirmation method |
| CN111104887A (en) * | 2019-12-11 | 2020-05-05 | 北京化工大学 | Whole-period keyless phase monitoring method based on vibration mechanism and deep learning technology |
| CN112220443A (en) * | 2020-09-01 | 2021-01-15 | 北京九辰智能医疗设备有限公司 | Self-adaptive signal noise reduction eye axial length measuring method |
| JP2021105533A (en) * | 2019-12-26 | 2021-07-26 | 日置電機株式会社 | Partial discharge detection device and partial discharge detection method |
| CN114492538A (en) * | 2022-02-16 | 2022-05-13 | 国网江苏省电力有限公司宿迁供电分公司 | Local discharge signal denoising method for urban medium-voltage distribution cable |
| CN115993511A (en) * | 2023-03-22 | 2023-04-21 | 武汉纺织大学 | Partial discharge type high-precision detection and identification device, method and equipment |
| CN116148612A (en) * | 2023-03-30 | 2023-05-23 | 成都宝屯沧网络科技有限公司 | Power distribution cabinet fault detection method, system, electronic equipment and storage medium |
-
2023
- 2023-12-14 CN CN202311713387.0A patent/CN117406046B/en active Active
Patent Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102095938A (en) * | 2010-03-08 | 2011-06-15 | 北京信息科技大学 | High-precision signal processing method for insulation online monitoring of high-voltage electric-power capacitive equipment |
| CN103699033A (en) * | 2013-12-10 | 2014-04-02 | 沈阳航空航天大学 | Embedded magnetorheological shock load buffer controller based on DSP (digital signal processor), and control method |
| CN108446632A (en) * | 2018-03-20 | 2018-08-24 | 珠海华网科技有限责任公司 | It a kind of partial discharge pulse edge finds and shelf depreciation confirmation method |
| CN111104887A (en) * | 2019-12-11 | 2020-05-05 | 北京化工大学 | Whole-period keyless phase monitoring method based on vibration mechanism and deep learning technology |
| JP2021105533A (en) * | 2019-12-26 | 2021-07-26 | 日置電機株式会社 | Partial discharge detection device and partial discharge detection method |
| CN112220443A (en) * | 2020-09-01 | 2021-01-15 | 北京九辰智能医疗设备有限公司 | Self-adaptive signal noise reduction eye axial length measuring method |
| CN114492538A (en) * | 2022-02-16 | 2022-05-13 | 国网江苏省电力有限公司宿迁供电分公司 | Local discharge signal denoising method for urban medium-voltage distribution cable |
| CN115993511A (en) * | 2023-03-22 | 2023-04-21 | 武汉纺织大学 | Partial discharge type high-precision detection and identification device, method and equipment |
| CN116148612A (en) * | 2023-03-30 | 2023-05-23 | 成都宝屯沧网络科技有限公司 | Power distribution cabinet fault detection method, system, electronic equipment and storage medium |
Non-Patent Citations (2)
| Title |
|---|
| JURAJ KURIMSKY´ 等: "Electrical and acoustic investigation of partial discharges in two types of nanofluids", 《JOURNAL OF MOLECULAR LIQUIDS》, pages 1 - 8 * |
| 杨攀烁 等: "基于小波变换和灰度-梯度共生矩阵的局部放电特征提取及识别", 《科学技术与工程》, vol. 27, no. 23, pages 11673 - 11680 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN117406046B (en) | 2024-03-08 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN203811750U (en) | Live-line detection system for partial discharge of transformer | |
| CN110231529A (en) | A kind of control cabinet intelligent Fault Diagnose Systems and method for diagnosing faults | |
| CN108693448B (en) | Partial discharge mode recognition system applied to power equipment | |
| CN111597877A (en) | Fall detection method based on wireless signals | |
| CN116517860A (en) | Ventilator fault early warning system based on data analysis | |
| CN114371353A (en) | Power equipment abnormity monitoring method and system based on voiceprint recognition | |
| WO2023279382A1 (en) | Motor bearing running state fault detection method and system | |
| CN110632484A (en) | ELM-based GIS partial discharge defect diagnosis and classification system and method | |
| CN116800199A (en) | Distributed photovoltaic operation electric energy quality monitoring and analyzing method | |
| CN117406046B (en) | Partial discharge detection device | |
| Wang et al. | Research on a sound-based method for belt conveyor longitudinal tear detection | |
| CN115376526A (en) | Power equipment fault detection method and system based on voiceprint recognition | |
| CN116230013A (en) | Transformer fault voiceprint detection method based on x-vector | |
| CN115078912A (en) | Method and system for detecting abnormity of roof high-voltage cable connector in real time and train | |
| CN115064183A (en) | Wind generating set running state monitoring method and system based on artificial intelligence algorithm | |
| CN117497004B (en) | Noise level monitoring device and method based on neural network and electronic equipment | |
| CN112666430B (en) | Intelligent fault detection method and system for voiceprint of transformer | |
| CN117169639B (en) | Product detection method and system for power adapter production | |
| CN113719269A (en) | On-line monitoring method for circuit working state of logging-while-drilling instrument | |
| CN110579657A (en) | Transformer fault detection system based on vibration signal analysis and detection method thereof | |
| CN211478951U (en) | Fault diagnosis device and fault diagnosis system | |
| CN116884432A (en) | VMD-JS divergence-based power transformer fault voiceprint diagnosis method | |
| CN109884483A (en) | Insulating tube type busbar shelf depreciation acoustics on-line monitoring method and device | |
| CN114897029A (en) | Integrated cooker fan fault diagnosis method based on deep residual error shrinkage network | |
| CN211477587U (en) | Online safety early warning device and fault diagnosis system |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |