WO2025200548A1 - 变压器声纹局部放电检测方法、装置、设备及存储介质 - Google Patents
变压器声纹局部放电检测方法、装置、设备及存储介质Info
- Publication number
- WO2025200548A1 WO2025200548A1 PCT/CN2024/136502 CN2024136502W WO2025200548A1 WO 2025200548 A1 WO2025200548 A1 WO 2025200548A1 CN 2024136502 W CN2024136502 W CN 2024136502W WO 2025200548 A1 WO2025200548 A1 WO 2025200548A1
- Authority
- WO
- WIPO (PCT)
- Prior art keywords
- time series
- signal
- partial discharge
- transformer
- voiceprint
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01R—MEASURING ELECTRIC VARIABLES; MEASURING MAGNETIC VARIABLES
- G01R31/00—Arrangements for testing electric properties; Arrangements for locating electric faults; Arrangements for electrical testing characterised by what is being tested not provided for elsewhere
- G01R31/12—Testing dielectric strength or breakdown voltage ; Testing or monitoring effectiveness or level of insulation, e.g. of a cable or of an apparatus, for example using partial discharge measurements; Electrostatic testing
- G01R31/1209—Testing dielectric strength or breakdown voltage ; Testing or monitoring effectiveness or level of insulation, e.g. of a cable or of an apparatus, for example using partial discharge measurements; Electrostatic testing using acoustic measurements
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01R—MEASURING ELECTRIC VARIABLES; MEASURING MAGNETIC VARIABLES
- G01R31/00—Arrangements for testing electric properties; Arrangements for locating electric faults; Arrangements for electrical testing characterised by what is being tested not provided for elsewhere
- G01R31/12—Testing dielectric strength or breakdown voltage ; Testing or monitoring effectiveness or level of insulation, e.g. of a cable or of an apparatus, for example using partial discharge measurements; Electrostatic testing
- G01R31/1227—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 of components, parts or materials
Definitions
- the present application relates to the field of voiceprint fault diagnosis and detection, for example, to a transformer voiceprint partial discharge detection method, device, equipment and storage medium.
- Power transformers are crucial equipment in power systems, serving as their foundation and core. Failures in distribution transformers, in particular, can have a wide-ranging impact on a significant number of people. Economic development has led to a significant increase in both electrical equipment and total electricity consumption, placing higher demands on the operation of distribution transformers, requiring them to meet both stability and safety requirements. Partial discharge is the most common type of failure during transformer operation.
- a common method for detecting partial discharge faults in transformers is to use oil chromatography to analyze the gas content of oil samples from the oil tank of a pole-mounted distribution transformer. Abnormalities in the oil sample must accumulate for a certain period of time before they can be detected through oil chromatography analysis. This accumulation period can take anywhere from six months to several years. Furthermore, taking transformer oil samples requires a power outage for the entire transformer, which defeats the goal of early detection, diagnosis, and treatment during transformer operation and is detrimental to stable operation. Therefore, early detection and no power outages are crucial indicators during transformer operation, and routine maintenance inspections should focus on this.
- the present application provides a transformer soundprint partial discharge detection method, device, equipment and storage medium, which can improve the time of partial discharge fault diagnosis and achieve rapid diagnosis without power outage, thereby further improving the goal of early detection, early diagnosis and early treatment during transformer operation, and has significant significance for the stable and safe operation of the transformer.
- This application provides a transformer soundprint partial discharge detection method, comprising:
- the signal processing unit processes the original voiceprint signal inside the transformer to obtain parameters
- the partial discharge status is divided into categories to obtain the detection status level classification results.
- collecting the voiceprint signal inside the transformer includes: placing a sensor outside the transformer to collect the voiceprint signal inside the transformer.
- transmitting the collected voiceprint signal to the input signal processing unit includes: directly transmitting the collected voiceprint signal to the input signal processing unit through a network.
- the signal processing unit processes the original transformer internal voiceprint signal to obtain parameters, including:
- the original transformer internal voiceprint signal After obtaining the original transformer internal voiceprint signal, the original transformer internal voiceprint signal is preprocessed according to the occurrence frequency band characteristics of the partial discharge voiceprint signal.
- the low-frequency signal is filtered out by high-pass filtering, and the signal containing the occurrence frequency band of the partial discharge voiceprint signal is retained.
- the partial discharge signal is very weak and needs to be processed.
- the Duffing oscillator can exhibit many key characteristics and can be used to extract effective information from weak signals.
- ⁇ is the angular frequency of the system's driving force
- k is the damping ratio
- ⁇ is the system's internal drive amplitude, typically 0.
- ⁇ x 3 is the system's nonlinear term.
- time-synchronized phase alignment is performed on a long sequence of signals, so that the discrete signals of a long sequence are compressed into a space with a specified time phase width, so that the discrete signals are superimposed and the distribution of the discrete signals is aggregated.
- the formula for time-synchronized phase alignment is:
- x 1 ,y 1 is the curve fitted by the left time series
- k 1 is the slope of the left time series curve
- x 2 ,y 2 is the curve fitted by the right time series
- k 2 is the slope of the right time series curve
- the short time series signal is divided into two parts, namely the front time series L1 and the back time series L2 , and the signal intensity ratio of the front time series and the back time series is calculated respectively.
- the calculation formula of the signal intensity ratio is:
- p is the signal intensity ratio
- l is the unit signal intensity
- l average is the average value of the overall signal.
- This constitutes a new before and after time series P 1 and P 2 , and extracts three values at the initial moment, the truncation point of the before and after time series, and the last moment, p 0 , p mid , and p end , respectively.
- the time points corresponding to the three values constitute three coordinate points, (t 0 , p 0 ), (t mid , p mid ), and (t end , p end ).
- the formula for fitting the linear curve is:
- the parameters include: the calculated left time series curve y 1 , the left time series average distance z 1 , the right time series curve y 2 , the right time series average distance z 2 , the front time series curve y 3 , the front time series average distance z 3 , the back time series y 4 , the back time series average distance z 4 and the distance threshold ⁇ .
- determining the type of transformer partial discharge by the partial discharge classifier unit includes:
- the four flag bits are accumulated to obtain the classification result of the partial discharge.
- This application also provides a transformer soundprint partial discharge detection device, comprising:
- a signal acquisition unit configured to acquire a voiceprint signal inside the transformer and transmit the acquired voiceprint signal to an input signal processing unit for subsequent signal processing
- a signal processing unit configured to process the voiceprint signal inside the transformer to obtain parameters
- the analysis and processing unit is configured to classify the status of the partial discharge and obtain a detection status level classification result.
- the device is used to perform the transformer soundprint partial discharge detection method as described in any one of the above items.
- the present application also provides an electronic device, including a memory, a processor, and a computer program stored in the memory and executable on the processor.
- a transformer voiceprint partial discharge detection method is implemented.
- FIG1 is a flow chart of a transformer soundprint partial discharge detection method using an impulse phase method
- FIG4 is a time-compressed signal diagram according to an embodiment of the present application.
- FIG6 is a schematic diagram of the structure of a transformer soundprint partial discharge detection device according to an embodiment of the present application.
- FIG7 is a schematic structural diagram of an electronic device provided in an embodiment of the present application.
- the collecting of the voiceprint signal inside the transformer includes placing a sensor outside the transformer to collect the voiceprint signal inside the transformer.
- the transmitting the collected voiceprint signal to the signal processing unit includes: directly transmitting the collected voiceprint signal to the signal processing unit through a network.
- S2 The original transformer internal voiceprint signal is processed by the signal processing unit to obtain parameters.
- the operation steps are as follows:
- y[n] is the current output of the original signal
- x[n] is the current input of the original signal
- x[n-1] is the previous input of the original signal
- y[n-1] is the previous output of the original signal
- ⁇ is the coefficient that controls the cutoff frequency of the filter.
- the occurrence frequency of partial discharge is generally higher than 10 kHz.
- the signal with a frequency lower than 10 kHz is subjected to high-pass filtering.
- ⁇ is the system's driving force angular frequency
- k is the damping ratio
- ⁇ is the system's built-in drive amplitude, typically 0.
- ⁇ x 3 is the system's nonlinear term.
- step S22 After obtaining the pre-processed signal in step S211, perform time synchronization phase alignment on the signal of a long time series, so that the discrete signal of a long sequence is compressed into a space with a specified phase width at a specific time, so that the discrete signals are superimposed and the distribution of the discrete signals is concentrated, which is more conducive to the analysis and processing of subsequent operations.
- the formula for time synchronization phase alignment is:
- f(s) is the output of the signal
- s is the unit signal strength
- t is the time of the signal
- T is the set specified time
- n is the maximum integer period of T.
- Step S22 completes the conversion of the long time series to the short time series.
- the short time series is divided into two parts, namely the left time series S1 and the right time series S2 .
- the signal strength of the initial points on the left and right sides are extracted respectively, s0 , smid , send .
- the time coordinates of the three points ( t0 , s0 ), ( tmid , smid ), ( tend , send ) are obtained from the time points corresponding to the three values.
- the three coordinate points can be fitted into two linear curves.
- the formula for fitting the linear curve is:
- S24 Arrange the discrete signal points in the left and right time series in ascending order to obtain two ordered discrete sequences S 1 ', ⁇ s 0 ',s 1 ',s 2 ',...s (t-2)/2 ',s (t-1)/2 ' ⁇ and S 2 ', ⁇ s t/2 ',s (t+1)/2 ',s (t+2)/2 '...s t-1 ',s t ' ⁇ .
- this application uses a five-point calculation method. Calculate the minimum value, value at 1/4, value at 1/2, value at 3/4, and maximum value of the ordered discrete signal points in the left time series.
- the time coordinates of these five points are (t 0 ', s 0 '), (t (t-1)/4 ', s (t-1)/4 '), (t (t-1)/2 ', s (t-1)/2 '), (t 3(t-1)/4 ', s 3(t-1)/4 '), and (t (t-1)/2 ', s (t-1)/2 ').
- the average distance z 1 from these five points to y 1 is calculated and compared with the distance threshold ⁇ .
- five points are taken from the right time series, and the average distance z 2 from the five points to y 2 is calculated and compared with the distance threshold ⁇ .
- the distance threshold ⁇ is 2.
- step S25 The short time series obtained in step S22 is divided into two parts. Different from the left and right time series in step S23, the two time series in this step are the front time series L1 and the back time series L2 . In this embodiment, the front and back time series are one-quarter of the power frequency cycle time, that is, 0.025 seconds. 0 to 0.0025 seconds is the left time series, and 0.0025 seconds to 0.02 seconds is the right time series.
- the signal strength ratio of the front and back time series is calculated respectively. The calculation formula of the signal strength ratio is:
- x 3 , y 3 are the curves fitted by the new front time series
- k 3 is the slope of the new front time series curve
- x 4 , y 4 are the curves fitted by the new back time series
- k 2 is the slope of the new back time series curve.
- step S2 In step S2, the left time series curve y 1 , the left time series average distance z 1 , the right time series curve y 2 , the right time series average distance z 2 , the front time series curve y 3 , the front time series average distance z 3 , the back time series y 4 , the back time series average distance z 4 , and the distance threshold ⁇ are calculated. These parameters are used by the partial discharge classifier unit to determine the type of partial discharge in the transformer. The steps are as follows:
- step S3 the state of the partial discharge (eg, normal, concern, and alarm) is obtained.
- S31 The four average distance values z 1 , z 2 , z 3 , and z 4 are compared with the distance threshold ⁇ respectively to make the next judgment.
- S33 Accumulate the four flag bits to obtain a classification result of the partial discharge.
- steps S2 to S4 In steps S2 to S4, the partial discharge detection results in a time series are obtained. However, the results in a time series often do not have good robustness.
- the results in a time series are then processed using a support vector machine (SVM) classification process. The steps are as follows:
- the transformer soundprint partial discharge detection method provided in the present application can determine partial discharge and can achieve real-time detection, real-time detection conclusions, and online detection and processing. This greatly improves the time for transformer partial discharge detection, eliminates the need for power outages, and improves the efficiency of daily inspections by operation and maintenance personnel.
- the method of the present application improves detection accuracy and can detect weak partial discharge signals, which is something that traditional oil chromatography detection cannot do, and live detection is also something that traditional oil chromatography cannot do.
- FIG6 is a schematic diagram of the structure of a transformer soundprint partial discharge detection device provided in the present application. As shown in FIG6, the device includes:
- the signal processing unit 220 is configured to perform preprocessing, time compression, linear curve fitting and distance calculation on the signal, thereby obtaining the distance from the point to the fitting curve and comparing it with the size of the distance threshold;
- the partial discharge classifier unit 230 is configured to update the state of the flag bit based on the difference between the distance threshold and the calculated distance value;
- the analysis and processing unit 240 is configured to calculate the cumulative value of the flag bit and provide a detection status level classification result.
- a partial discharge classifier unit configured to obtain a partial discharge state according to the parameters
- the analysis and processing unit is configured to classify the status of the partial discharge and obtain a detection status level classification result.
- the transformer soundprint partial discharge detection device provided in the embodiment of the present application can execute the transformer soundprint partial discharge detection method provided in any embodiment of the present application, and has the corresponding functional modules and effects of the execution method.
- FIG7 is a schematic diagram of the structure of an electronic device provided in an embodiment of the present application.
- the electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers.
- the electronic device can also represent various forms of mobile devices, such as personal digital assistants, cellular phones, smart phones, and other similar computing devices.
- the components shown herein, their connections and relationships, and their functions are merely examples and are not intended to limit the implementation of the present application described and/or claimed herein.
- electronic device 10 includes at least one processor 11 and a memory, such as a read-only memory (ROM) 12 and a random access memory (RAM) 13, communicatively connected to at least one processor 11.
- the memory stores a computer program that can be executed by at least one processor 11.
- Processor 11 can perform various appropriate actions and processes based on the computer program stored in ROM 12 or loaded from storage unit 18 into RAM 13.
- Various programs and data required for the operation of electronic device 10 can also be stored in RAM 13.
- Processor 11, ROM 12, and RAM 13 are interconnected via bus 14.
- An input/output (I/O) interface 15 is also connected to bus 14.
- Processor 11 can be a variety of general-purpose and/or specialized processing components with processing and computing capabilities. Some examples of processor 11 include a central processing unit (CPU), a graphics processing unit (GPU), various dedicated artificial intelligence (AI) computing chips, various processors running machine learning model algorithms, a digital signal processor (DSP), and any suitable processor, controller, microcontroller, etc. Processor 11 performs the various methods and processes described above, such as the transformer voiceprint partial discharge detection method.
- CPU central processing unit
- GPU graphics processing unit
- AI dedicated artificial intelligence
- DSP digital signal processor
- Processor 11 performs the various methods and processes described above, such as the transformer voiceprint partial discharge detection method.
- An embodiment of the present application further provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements a transformer voiceprint partial discharge detection method.
- the transformer soundprint partial discharge detection method can be implemented as a computer program, which is tangibly contained in a computer-readable storage medium, such as the storage unit 18.
- part or all of the computer program can be loaded and/or installed on the electronic device 10 via the ROM 12 and/or the communication unit 19.
- the processor 11 can be configured to execute the transformer soundprint partial discharge detection method in any other appropriate manner (for example, by means of firmware).
- a computer-readable storage medium may be a tangible medium that may contain or store a computer program for use by or in conjunction with an instruction execution system, apparatus, or device.
- a computer-readable storage medium may include an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any suitable combination of the foregoing.
- a computer-readable storage medium may be a machine-readable signal medium.
- a machine-readable storage medium includes an electrical connection based on one or more wires, a portable computer disk, a hard disk, RAM, ROM, Erasable Programmable Read-Only Memory (EPROM), flash memory, optical fiber, portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.
- the storage medium may be a non-transitory storage medium.
- a computer program product or computer program includes computer instructions stored in a computer-readable storage medium.
- a processor of a computer device reads the computer instructions from the computer-readable storage medium and executes the computer instructions, causing the computer device to perform the transformer soundprint partial discharge detection method provided in the various optional implementations described above.
Landscapes
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Acoustics & Sound (AREA)
- Testing Relating To Insulation (AREA)
Abstract
一种变压器声纹局部放电检测方法、装置、设备及存储介质,包括采集变压器内部的声纹信号,将采集到的声纹信号传输入信号处理单元(220),以用于后续的信号处理(S1);通过信号处理单元(220)将变压器内部的声纹信号进行处理,以获得参数(S2);根据参数通过局放分类器单元(230)判断变压器局放的类型(S3);对局放的状态进行划分,给出检测的状态等级分类结果(S4)。
Description
本申请要求在2024年03月29日提交中国专利局、申请号为202410379824.8的中国专利申请的优先权,该申请的全部内容通过引用结合在本申请中。
本申请涉及声纹故障诊断检测领域,例如涉及一种变压器声纹局部放电检测方法、装置、设备及存储介质。
电力变压器是电力系统中的重要设备,是电力系统的基础和核心装置,尤其是配变变压器的运行,一旦发生故障,带来的影响范围广、人数多。随着经济的发展,无论是用电设备,还是用电总量,都有显著增加,这就对配变变压器的运行提出了更高的要求,既要满足稳定性,同时要具备安全性。而局部放电是变压器运行过程中,最常见的故障类型。
常用的检测变压器局部放电故障的方法,是利用油色谱的方法,对柱上配变变压器油箱里的油样做分析,分析油样里面的气体含量。油样的异常需要积累一定量后才能在油色谱的分析中被发现,这样的累积量少则半年,多则几年,同时取变压器油样的操作需要对整个变压器做停电处理,违背了变压器运行早发现早诊断早治理的目标,也不利于稳定运行目标。故,早发现、不停电的特性是变压器运行过程中重要的指标,日常的运维巡检也要围绕这一点。
近年来,声纹特征的故障诊断慢慢走入变压器运维人员的视野,通过分析变压器运行故障的声纹特征,能够实现快诊断早发现的目标,且无需掌握更为专业的知识,无需停电操作,极大的提高了运维人员的巡检效率。
本申请提供一种变压器声纹局部放电检测方法、装置、设备及存储介质,可以提高局放故障诊断的时间,做到快速诊断,无需做停电处理,从而进一步提高变压器运行过程中早发现早诊断早治理的目标,对变压器的稳定、安全运行有显著意义。
本申请提供了一种变压器声纹局部放电检测方法,包括:
采集变压器内部的声纹信号,将采集到的声纹信号传输入信号处理单元以用于后续的信号处理;
通过所述信号处理单元将原始的变压器内部的声纹信号进行处理,以获得参数;
根据所述参数通过局放分类器单元判断变压器局放的类型;
对局放的状态进行划分,得到检测的状态等级分类结果。
在一个或多个实施例中,所述采集变压器内部的声纹信号,包括:将传感器置于变压器外侧,采集变压器内部的声纹信号。
在一个或多个实施例中,所述将采集到的声纹信号传输入信号处理单元,包括:通过网络直接将采集到的声纹信号传输入信号处理单元。
在一个或多个实施例中,通过所述信号处理单元将原始的变压器内部声纹信号做处理,以获得参数,包括:
在通过得到原始的变压器内部的声纹信号后,根据局放声纹信号的发生频段特性,对原始的变压器内部的声纹信号做预处理,采用高通滤波的方式,将低频信号过滤,保留包含局放声纹信号发生频段的信号;其中,高通滤波操作的公式为:
y[n]=α(y[n-1]+x[n]-x[n-1])
y[n]=α(y[n-1]+x[n]-x[n-1])
式中,y[n]是原始信号当前的输出,x[n]是原始信号当前的输入,x[n-1]是原始信号前一个输入,y[n-1]是原始信号前一个输出,α是控制滤波器截止频率的系数;
在得到滤波的信号后,局部放电信号很微弱,需要对微弱信号做处理。Duffing振子可以展示许多关键特性,可以检测在微弱信号中提取到有效信息。Duffing振子的公式为:
x″+kx′-x+αx3=γcos(ω·t)
x″+kx′-x+αx3=γcos(ω·t)
式中,ω是系统策动力角频率,k是阻尼比,γ是系统内置驱动幅值,通常为0。αx3是系统的非线性项,通过控制上述公式中的k和α系数,就可以得到微弱信号,但通常非线性方程的求解,往往会比较复杂,尤其是在输入信号的时间序列越长,其复杂度也会更高。x″和x′是二阶导数和一阶导数,分别是加速度和速度的含义,t是时间。
在得到预处理后的信号后,对一段长时间序列的信号进行时间同步相位对齐,使得一段长序列的离散信号,压缩到选定时间指定相位宽度的空间内,使得离散信号叠加,聚集离散信号的分布;其中,时间同步相位对齐的公式为:
式中,f(s)是信号的输出,s是单位信号强度,t是信号的时间,T是设定的指定时间,n是T最大的整数周期;
在完成长时间序列信号到短时间序列信号的转换后,将短时间序列信号分为两个部分,左时间序列S1和右时间序列S2,分别提取左右两边初始点的信号强度,s0,smid,send(即左时间序列S1和右时间序列S2的开始点、中间点和结束点),由三个值对应的时间点得到三个点的时间坐标(t0,s0),(tmid,smid),(tend,send),通过线性函数的特性,将3个坐标点拟合成两个线性曲线,拟合线性曲线的公式为:
其中,x1,y1是左时间序列拟合成的曲线,k1是左时间序列曲线的斜率,x2,y2是右时间序列拟合成的曲线,k2是右时间序列曲线的斜率;
将左时间序列和右时间序列中的离散信号点按从小到大的排列顺序,得到两个有序的离散序列S1',{s0',s1',s2',……s(t-2)/2',s(t-1)/2'}和S2',{st/2',s(t+1)/2',s(t+2)/2'……st-1',st'};计算左时间序列中有序离散信号点的最小值、1/4处的值、1/2处的值、3/4处的值和最大值,并得到五个点的时间坐标点分别是(t0',s0'),(t(t-1)/4',s(t-1)/4'),(t(t-1)/2',s(t-1)/2'),(t3(t-1)/4',s3(t-1)/4'),(t(t-1)/2',s(t-1)/2'),计算所述5个点到y1的距离的平均值z1,并与距离阈值ε对比;同样的右时间序列取5个点,采用5点计算法计算5个点到y2的距离平均值z2,并与距离阈值ε对比;
在得到的短时间序列后,将短时间序列信号分为两个部分,分别为前时间序列L1和后时间序列L2,分别计算前时间序列和后时间序列的信号强度比,信号强度比的计算公式为:
其中,p为信号强度比,l为单位信号强度,laverage为整体信号的平均值;由此构成一个新的前后时间序列P1和P2,分别提取初始时刻,前后时间序列截断点和最后的时刻的三个值,p0,pmid,pend,由三个值对应的时间点构成三个坐标点,(t0,p0),(tmid,pmid),(tend,pend),通过线性函数的特性,将三个坐标点拟合成两个线性曲线;拟合线性曲线的公式为:
其中,x3,y3是新的前时间序列拟合成的曲线,k3是新的前时间序列曲线的斜率,x4,y4是新后时间序列拟合成的曲线,k4是新的后时间序列曲线的斜率;
将新的前后时间序列中的离散信号点按从小到大排列得到两个有序离散序列L1',{l0',l1',l2',……lm-1',lm'}和L2',{lt-m',lt-m-1',lt-m-2',……lt-1',lt'},采用5点计算法计算L1'和L2'序列中的5个值的坐标点;计算L1'和L2'序列中5个值的平均值z3,z4,并与距离阈值ε相比。
在一个或多个实施例中,所述参数包括:计算得到的左时间序列曲线y1、左时间序列平均距离z1、右时间序列曲线y2、右时间序列平均距离z2、前时间序列曲线y3、前时间序列平均距离z3、后时间序列y4、后时间序列平均距离z4以及距离阈值ε。
在一个或多个实施例中,所述通过局放分类器单元判断变压器局放的类型,包括:
将4个平均距离的值z1,z2,z3,z4分别与距离阈值ε相比较,并进行判断;
若z1≥ε,则将标志位Flag置1,否则Flag置0;同样的,若z2,z3,z4大于等于ε,则将标志位置1,否则置0;
将4个标志位累加,得到局放的分类结果。
在一个或多个实施例中,所述对局放的状态进行划分,通过将4个标志位的累加值,对局放的状态进行划分。
在一个或多个实施例中,在所述对局放的状态进行划分过程中,用正常表示无局放信号;用关注表示有轻微局放,需予以关注,需要持续关注设备的状况,防止设备恶化;用告警表示有局放信号产生,且较为明显,需要运维人员进行情况排查。
本申请还提供了一种变压器声纹局部放电检测装置,包括:
信号采集单元,设置为采集变压器内部的声纹信号,将采集到的声纹信号传输入信号处理单元以用于后续的信号处理;
信号处理单元,设置为将所述变压器内部的声纹信号进行处理,以获得参数;
局放分类器单元,设置为将距离阈值与计算的距离值大小,更新标志位的状态;
分析处理单元,设置为对局放的状态进行划分,得到检测的状态等级分类结果。
在一个或多个实施例中,该装置用于执行如上任一项所述的变压器声纹局部放电检测方法。
本申请还提供了一种电子设备,包括存储器、处理器及存储在存储器上并可在处理器上运行的计算机程序,处理器执行计算机程序时实现变压器声纹局部放电检测方法。
本申请还提供了一种计算机可读存储介质,其上存储有计算机程序,该计算机程序被处理器执行时实现变压器声纹局部放电检测方法。
图1为冲激相位法的变压器声纹局部放电检测方法的流程示意图;
图2为本申请实施例中计算冲激相位方法的流程图;
图3为本申请实施例中采集到的原始信号波形图;
图4为本申请实施例中时间压缩后的信号图;
图5为本申请实施例中检测的结果图;
图6为本申请实施例中变压器声纹局部放电检测装置的结构示意图;
图7是本申请实施例提供的一种电子设备的结构示意图。
本说明书中所有实施例公开的所有特征,或隐含公开的所有方法或过程中的步骤,除了互相排斥的特征和/或步骤以外,均可以以任何方式组合和/或扩展、替换。
声纹特征的故障诊断慢慢走入变压器运维人员的视野,通过分析变压器运行故障的声纹特征,能够实现快诊断早发现的目标,且无需掌握更为专业的知识,无需停电操作,极大的提高了运维人员的巡检效率。
如图1~图5所示,本申请提供一种冲激相位法的变压器声纹局部放电检测方法,针对变压器运行故障中的局部放电,提供的一种诊断方法。下面结合实施例,对本申请方法进行说明。该方法包括如下步骤。
S1:采集变压器内部的声纹信号,将采集到的声纹信号传输入信号处理单元,以用于后续的信号处理。
其中,所述采集变压器内部的声纹信号,包括:将传感器置于所述变压器的外侧,采集所述变压器内部的声纹信号。
所述将采集到的声纹信号传输入信号处理单元,包括:通过网络直接将采集到的声纹信号传输入所述信号处理单元。
S2:通过信号处理单元将原始的变压器的内部声纹信号,进行处理,以获得参数,操作步骤如下:
S21:在通过S1得到所述原始声纹信号后,根据局放声纹信号的发生频段特性,对原始声纹信号做预处理,采用高通滤波的方式,将低频信号过滤,只保留包含局放声纹信号发生频段的信号。其中,高通滤波操作的公式为:
y[n]=α(y[n-1]+x[n]-x[n-1])
y[n]=α(y[n-1]+x[n]-x[n-1])
式中,y[n]是原始信号当前的输出,x[n]是原始信号当前的输入,x[n-1]是原始信号的前一个输入,y[n-1]是原始信号的前一个输出,α是控制滤波器截止频率的系数。
局部放电的发生频率一般是高于10kHz的,在本实施例中,将低于10kHz的信号做高通滤波处理。
S211:在步骤S21中得到滤波的信号后,局部放电信号很微弱,需要对微弱信号做处理。Duffing振子可以展示处许多关键特性,可以检测在微弱信号中提取到有效信息。Duffing振子的公式为:
x″+kx′-x+αx3=γcos(ω·t)
x″+kx′-x+αx3=γcos(ω·t)
式中,ω是系统策动力角频率,k是阻尼比,γ是系统内置驱动幅值,通常为0。αx3是系统的非线性项,通过控制上述公式中的k和α系数,就可以得到微弱信号,但通常非线性方程的求解,往往会比较复杂,尤其是在输入信号的时间序列越长,其复杂度也会更高。
S22:在步骤S211中得到预处理后的信号后,对一段长时间序列的信号,做时间同步相位对齐,使得一段长序列的离散信号,压缩到特定时间指定相位宽度的空间内,使得离散信号叠加,聚集离散信号的分布,更利于后续操作的分析和处理。其中,时间同步相位对齐的公式为:
式中,f(s)是信号的输出,s是单位信号强度,t是信号的时间,T是设定的指定时间,n是T最大的整数周期。
假设工频信号是50Hz,周期是0.02秒,则在本实施例中,对长时间序列信号压缩到0.02秒之内,每隔0.02秒做一次时间的压缩,将每段的时间都统一到工频周期之内。
S23:步骤S22完成了长时间序列到短时间序列的转换,将短时间序列分为两个部分,分别为左时间序列S1和右时间序列S2,分别提取左右两边初始点的信号强度,s0,smid,send,再由三个值对应的时间点得到三个点的时间坐标(t0,s0),(tmid,smid),(tend,send),通过线性函数的特性,3个坐标点,可以拟合成2个线性曲线。拟合线性曲线的公式为:
其中x1,y1是左时间序列拟合成的曲线,k1是左时间序列曲线的斜率,x2,y2是右时间序列拟合成的曲线,k2是右时间序列曲线的斜率。在本实施例中,左右时间序列取工频周期时间的一半,即0.01秒,0~0.01秒为左时间序列,0.01秒~0.02秒为右时间序列。
S24:将左右时间序列中的离散信号点按从小到大的排列顺序,得到两个有序的离散序列S1',{s0',s1',s2',……s(t-2)/2',s(t-1)/2'}和S2',{st/2',s(t+1)/2',s(t+2)/2'……st-1',st'},为了消除序列数据的突变情况,本申请采用了5点计算法。计算左时间序列中有序离散信号点的最小值、1/4处的值、1/2处的值、3/4处的值和最大值。这5个点的时间坐标点分别是(t0',s0'),(t(t-1)/4',s(t-1)/4'),(t(t-1)/2',s(t-1)/2'),(t3(t-1)/4',s3(t-1)/4'),(t(t-1)/2',s(t-1)/2'),计算这5个点到y1的距离的平均值z1,与距离阈值ε对比;同样的右时间序列取5个点,计算5个点到y2的距离平均值z2,与距离阈值ε对比。本实施例中距离阈值ε取2。
S25:在步骤S22中得到的短时间序列,将短时间序列分为2个部分,不同于步骤S23中的左右两个时间序列,为做区分,本步骤中的2个时间序列为前时间序列L1和后时间序列L2。在本实施例中,前后时间序列取工频周期时间的四分之一,即0.025秒,0~0.0025秒为左时间序列,0.0025秒~0.02秒为右时间序列。分别计算前后时间序列的信号强度比,信号强度比的计算公式为:
其中,p为信号强度比,l为单位信号强度,laverage为整体信号的平均值。由此构成一个新的前后时间序列P1和P2,分别提取初始时刻、前后时间序列截断点和最后的时刻的三个值,p0,pmid,pend,再由三个值对应的时间点构成三个坐标点,(t0,p0),(tmid,pmid),(tend,pend),通过线性函数的特性,3个坐标点,可以拟合成2个线性曲线。拟合线性曲线的公式为:
其中x3,y3是新的前时间序列拟合成的曲线,k3是新的前时间序列曲线的斜率,x4,y4是新的后时间序列拟合成的曲线,k2是新的后时间序列曲线的斜率。
S26:将新前后时间序列中的离散信号点按从小到大排列得到两个有序离散序列L1',{l0',l1',l2',……lm-1',lm'}和L2',{lt-m',lt-m-1',lt-m-2',……lt-1',lt'},计算L1'和L2'序列中的5个值的坐标点,5个值的计算方法与步骤S24一致。计算L1'和L2'序列中5个值的平均值z3,z4,与距离阈值ε相比。
S3:步骤S2中分别计算得到了左时间序列曲线y1,左时间序列平均距离z1,右时间序列曲线y2,右时间序列平均距离z2,前时间序列曲线y3,前时间序列平均距离z3,后时间序列y4,后时间序列平均距离z4,以及距离阈值ε。以上参数通过局放分类器单元判断变压器局放的类型,步骤如下:
在步骤S3中得到局放的状态(例如正常、关注、告警三个状态)。S31:将4个平均距离的值z1,z2,z3,z4分别与距离阈值ε相比较,做下一步判断。
S32:若z1≥ε,则将标志位Flag置1,否则将Flag置0;同样的,若z2,z3,z4大于或等于ε,则将标志位置1,否则置为0。即,假设z2,z3,z4中的一个大于或等于ε,将对应的那个的标志位置1,例如z2大于或等于ε,将z2对应的标志位置1。
S33:将4个标志位累加,得到局放的分类结果。
如表1所示,为4个标志位的统计结果
表1
S4:通过S33所述的标志位累加值,对局放的状态进行划分,其中,正常表示无局放信号;关注表示有轻微局放,需予以关注,需要持续关注设备的状况,防止设备恶化;告警表示有局放信号产生,且较为明显,需要结合运维进行情况排查。标志位的累计值与等级状态的对应关系如表2所示。在S4中对局放的状态进行分类(分为正常、关注、告警三个状态)。
表2
在本实施例中,从表1中得到的标志位的累计值为4,按照表2的等级状态对应,为告警等级。由此给出的建议是需要运维人员排查故障点,做到故障点的消缺操作。
S5:步骤S2~S4中得到了一个时间序列下的局放检测结果,但一个时间序列下的结果,往往不具备良好的鲁棒性,对一个时间序列下的结果,再进行支持向量机(Support Vector Machine,SVM)分类的处理,步骤如下:
S51:将每个时间序列下,得到的三种检测结果正常、关注和告警作为分类器的输入。两两为一组,组成三个键对,(正常,关注)、(正常,告警)、(关注,告警)。
S52:定义一个超平面,用来分隔每个类别,其公式为:
f(x)=ω·x+b
f(x)=ω·x+b
其中,ω是法向量,b是偏置。
S53:那么超平面两侧的样本点,距离越远,那么分类的效果就会更好,通过不断更新ω和b的值来调整平面的方程。
S54:寻找ω和b,使间隔最大化,同时满足所有样本点被正确分类,当满足且满足yi(ω·xi+b)≥1时,则此刻的两个参数为最佳参数。
S55:如上操作,将三个键对依次进行分类重组,得到最终的结果。由此给出的建议是需要运维人员继续排查的故障点,做到故障点的消缺操作。
本申请提供的变压器声纹局部放电检测方法判断局部放电,可以做到实时检测,实时出检测结论,在线式检测处理,这极大的提高了变压器局部放电检测的时间,无需停电处理,运维人员的日常巡检效率也可以提高;此外,本申请方法除提高检测时间外,提高了检测精度,可检测出微弱的局放信号,这一点是传统油色谱检测无法做到的,带电检测也是传统油色谱无法做到的。
本申请实施例还提供了一种变压器声纹局部放电检测装置。图6是本申请实施例提供的一种变压器声纹局部放电检测装置的结构示意图。如图6所示,该装置包括:
信号采集单元210,设置为采集原始声纹信号;
信号处理单元220,设置为对信号进行预处理、时间压缩、线性曲线拟合并计算距离,从而得到点到拟合曲线的距离,并与距离阈值的大小相比;
局放分类器单元230,设置为将距离阈值与计算的距离值大小,更新标志位的状态;
分析处理单元240,设置为计算标志位的累计值,给出检测的状态等级分类结果。
信号采集单元,设置为采集变压器内部的声纹信号,将采集到的声纹信号传输入信号处理单元以用于后续的信号处理;
信号处理单元,设置为将所述变压器内部的声纹信号进行处理,以获得参数;
局放分类器单元,设置为根据所述参数得到局放的状态;
分析处理单元,设置为对局放的状态进行划分,得到检测的状态等级分类结果。
本申请实施例所提供的变压器声纹局部放电检测装置可执行本申请任意实施例所提供的变压器声纹局部放电检测方法,具备执行方法相应的功能模块和效果。
本申请实施例还提供了一种电子设备。图7为本申请实施例提供的一种电子设备的结构示意图。电子设备旨在表示多种形式的数字计算机,诸如,膝上型计算机、台式计算机、工作台、个人数字助理、服务器、刀片式服务器、大型计算机、和其它适合的计算机。电子设备还可以表示多种形式的移动装置,诸如,个人数字处理、蜂窝电话、智能电话和其它类似的计算装置。本文所示的部件、它们的连接和关系、以及它们的功能仅仅作为示例,并且不意在限制本文中描述的和/或者要求的本申请的实现。
如图7所示,电子设备10包括至少一个处理器11,以及与至少一个处理器11通信连接的存储器,如只读存储器(Read-Only Memory,ROM)12、随机访问存储器(Random Access Memory,RAM)13等,其中,存储器存储有可被至少一个处理器11执行的计算机程序,处理器11可以根据存储在ROM12中的计算机程序或者从存储单元18加载到RAM13中的计算机程序,来执行多种适当的动作和处理。在RAM 13中,还可存储电子设备10操作所需的多种程序和数据。处理器11、ROM 12以及RAM 13通过总线14彼此相连。输入/输出(Input/Output,I/O)接口15也连接至总线14。
电子设备10中的多个部件连接至I/O接口15,包括:输入单元16,例如键盘、鼠标等;输出单元17,例如多种类型的显示器、扬声器等;存储单元18,例如磁盘、光盘等;以及通信单元19,例如网卡、调制解调器、无线通信收发机等。通信单元19允许电子设备10通过诸如因特网的计算机网络和/或多种电信网络与其他设备交换信息/数据。
处理器11可以是多种具有处理和计算能力的通用和/或专用处理组件。处理器11的一些示例包括中央处理单元(Central Processing Unit,CPU)、图形处理单元(Graphics Processing Unit,GPU)、多种专用的人工智能(Artificial Intelligence,AI)计算芯片、多种运行机器学习模型算法的处理器、数字信号处理器(Digital Signal Processor,DSP)、以及任何适当的处理器、控制器、微控制器等。处理器11执行上文所描述的多个方法和处理,例如变压器声纹局部放电检测方法。
本申请实施例还提供了一种计算机可读存储介质,其上存储有计算机程序,该计算机程序被处理器执行时实现变压器声纹局部放电检测方法。
在一些实施例中,变压器声纹局部放电检测方法可被实现为计算机程序,其被有形地包含于计算机可读存储介质,例如存储单元18。在一些实施例中,计算机程序的部分或者全部可以经由ROM 12和/或通信单元19而被载入和/或安装到电子设备10上。当计算机程序加载到RAM 13并由处理器11执行时,可以执行上文描述的变压器声纹局部放电检测方法的一个或多个步骤。备选地,在其他实施例中,处理器11可以通过其他任何适当的方式(例如,借助于固件)而被配置为执行变压器声纹局部放电检测方法。
在本申请的上下文中,计算机可读存储介质可以是有形的介质,其可以包含或存储以供指令执行系统、装置或设备使用或与指令执行系统、装置或设备结合地使用的计算机程序。计算机可读存储介质可以包括电子的、磁性的、光学的、电磁的、红外的、或半导体系统、装置或设备,或者上述内容的任何合适组合。备选地,计算机可读存储介质可以是机器可读信号介质。机器可读存储介质包括基于一个或多个线的电气连接、便携式计算机盘、硬盘、RAM、ROM、可擦除可编程只读存储器(Erasable Programmable Read-Only Memory,EPROM)、快闪存储器、光纤、便捷式紧凑盘只读存储器(Compact Disc Read Only Memory,CD-ROM)、光学储存设备、磁储存设备、或上述内容的任何合适组合。存储介质可以是非暂态(non-transitory)存储介质。
描述于本申请实施例中所涉及到的单元可以通过软件的方式实现,也可以通过硬件的方式来实现,所描述的单元也可以设置在处理器中。其中,这些单元的名称在一种情况下并不构成对该单元本身的限定。
根据本申请实施例的一个方面,提供了一种计算机程序产品或计算机程序,该计算机程序产品或计算机程序包括计算机指令,该计算机指令存储在计算机可读存储介质中。计算机设备的处理器从计算机可读存储介质读取该计算机指令,处理器执行该计算机指令,使得该计算机设备执行上述多种可选实现方式中提供的变压器声纹局部放电检测方法。
Claims (11)
- 一种变压器声纹局部放电检测方法,包括:采集变压器内部的声纹信号,将采集到的声纹信号传输入信号处理单元以用于后续的信号处理;通过所述信号处理单元将所述变压器内部的声纹信号进行处理,以获得参数;根据所述参数通过局放分类器单元得到局放的状态;对局放的状态进行划分,得到检测的状态等级分类结果。
- 根据权利要求1所述的方法,其中,所述采集变压器内部的声纹信号,包括:将传感器置于所述变压器的外侧,采集所述变压器内部的声纹信号。
- 根据权利要求1所述的方法,其中,所述将采集到的声纹信号传输入信号处理单元,包括:通过网络直接将采集到的声纹信号传输入所述信号处理单元。
- 根据权利要求1所述的方法,其中,所述通过所述信号处理单元将所述变压器内部的声纹信号进行处理,以获得参数,包括:在得到所述变压器内部的声纹信号后,根据局放声纹信号的发生频段特性,对所述变压器内部的声纹信号进行预处理,其中,所述预处理包括:采用高通滤波的方式,将低频信号过滤,保留包含局放声纹信号发生频段的信号;其中,所述高通滤波操作的公式为:
y[n]=α(y[n-1]+x[n]-x[n-1])式中,y[n]是所述变压器内部的声纹信号当前的输出,x[n]是所述变压器内部的声纹信号当前的输入,x[n-1]是所述变压器内部的声纹信号的前一个输入,y[n-1]是所述变压器内部的声纹信号的前一个输出,α是控制滤波器截止频率的系数;在得到预处理后的信号后,对一段长时间序列的离散信号,进行时间同步相位对齐,使得一段长时间序列的离散信号,压缩到选定时间指定相位宽度的空间内以得到短时间序列信号,使得所述离散信号叠加,并聚集所述离散信号的分布;其中,所述时间同步相位对齐的公式为:
式中,f(s)是信号的输出,s是单位信号强度,t是信号的时间,T是设定的指定时间,n是T最大的整数周期;在完成长时间序列的离散信号到短时间序列信号的转换后,将所述短时间序列信号分为两个部分,分别为左时间序列S1和右时间序列S2,分别提取左右两边初始点、左时间序列S1和右时间序列S2的截断点的信号强度,s0,smid,send,由三个值对应的时间点得到3个点的时间坐标点(t0,s0),(tmid,smid),(tend,send),通过线性函数的特性,将3个点的时间坐标点拟合成两个线性曲线,拟合线性曲线的公式为:
其中,x1,y1是所述左时间序列拟合成的曲线,k1是所述左时间序列拟合成的曲线的斜率,x2,y2是所述右时间序列拟合成的曲线,k2是所述右时间序列拟合成的曲线的斜率;将所述左时间序列和所述右时间序列中的离散信号点按从小到大的排列顺序,得到两个有序的离散序列S1',{s0',s1',s2',……s(t-2)/2',s(t-1)/2'}和S2',{st/2',s(t+1)/2',s(t+2)/2'……st-1',st'};计算所述左时间序列中有序离散信号点的最小值、1/4处的值、1/2处的值、3/4处的值和最大值,得到5个点的时间坐标点分别是(t0',s0'),(t(t-1)/4',s(t-1)/4'),(t(t-1)/2',s(t-1)/2'),(t3(t-1)/4',s3(t-1)/4'),(t(t-1)/2',s(t-1)/2'),计算所述5个点到y1的距离的平均值:左时间序列平均距离z1,并将z1与距离阈值ε对比;在所述右时间序列取5个点,分别为所述右时间序列的最小值、1/4处的值、1/2处的值、3/4处的值和最大值,采用5点计算法计算5个点到y2的距离的平均值:右时间序列平均距离z2,并将z2与所述距离阈值ε对比;将所述短时间序列信号分为两个部分,分别为前时间序列L1和后时间序列L2,分别计算所述前时间序列和所述后时间序列的信号强度比,信号强度比的计算公式为:
其中,p为信号强度比,l为单位信号强度,laverage为整体信号的平均值;由此构成一个新的前时间序列P1和新的后时间序列P2,分别提取初始时刻、前后时间序列截断点和最后的时刻的三个值,p0,pmid,pend,由三个值对应的时间点构成三个坐标点,(t0,p0),(tmid,pmid),(tend,pend),通过线性函数的特性,将3个坐标点拟合成两个线性曲线;拟合线性曲线的公式为:
其中,x3,y3是所述新的前时间序列拟合成的曲线,k3是所述新的前时间序列曲线的斜率,x4,y4是所述新的后时间序列拟合成的曲线,k4是所述新的后时间序列曲线的斜率;将新的前时间序列和新的后时间序列中的离散信号点按从小到大排列得到两个有序离散序列L1',{l0',l1',l2',……lm-1',lm'}和L2',{lt-m',lt-m-1',lt-m-2',……lt-1',lt'},采用5点计算法计算L1'和L2'序列中的5个值的坐标点;计算L1'和L2'序列中5个值的平均值,分别为:前时间序列平均距离z3和后时间序列平均距离z4,并将z3和z4分别与所述距离阈值ε相比。 - 根据权利要求4所述的方法,其中,所述参数包括:计算得到的左时间序列曲线y1、左时间序列平均距离z1、右时间序列曲线y2、右时间序列平均距离z2、前时间序列曲线y3、前时间序列平均距离z3、后时间序列y4、后时间序列平均距离z4以及距离阈值ε。
- 根据权利要求5所述的方法,其中,所述根据所述参数通过局放分类器单元得到局放的状态,包括:将四个平均距离的值z1,z2,z3,z4分别与所述距离阈值ε相比较,并进行判断;响应于z1大于或等于ε,将z1对应的标志位Flag置1,响应于z1小于ε,将z1对应的Flag置0;响应于z2,z3,z4中之一大于或等于ε,将z2,z3,z4对应的Flag置1,响应于z2,z3,z4中至少之一小于ε,将z2,z3,z4对应的Flag置0,得到四个标志位;将所述四个标志位累加,得到局放的分类结果。
- 根据权利要求6所述的方法,其中,所述对局放的状态进行划分,包括:通过所述四个标志位的累加值,对所述局放的状态进行划分。
- 根据权利要求7所述的方法,其中,在所述对局放的状态进行划分过程中,采用正常表示无局放信号;采用关注表示有轻微局放;采用告警表示有局放信号产生。
- 一种变压器声纹局部放电检测装置,包括:信号采集单元,设置为采集变压器内部的声纹信号,将采集到的声纹信号传输入信号处理单元以用于后续的信号处理;信号处理单元,设置为将所述变压器内部的声纹信号进行处理,以获得参数;局放分类器单元,设置为根据所述参数得到局放的状态;分析处理单元,设置为对局放的状态进行划分,得到检测的状态等级分类结果。
- 一种电子设备,存储器、至少一个处理器及存储在所述存储器上并可在所述处理器上运行的计算机程序,其中,所述处理器执行所述计算机程序时实现如权利要求1至8中任一项所述的变压器声纹局部放电检测方法。
- 一种计算机可读存储介质,其上存储有计算机程序,其中,所述计算机程序被处理器执行时实现如权利要求1至8中任一项所述的变压器声纹局部放电检测方法。
Applications Claiming Priority (2)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410379824.8 | 2024-03-29 | ||
| CN202410379824.8A CN118244064A (zh) | 2024-03-29 | 2024-03-29 | 一种变压器声纹局部放电检测方法及装置 |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| WO2025200548A1 true WO2025200548A1 (zh) | 2025-10-02 |
Family
ID=91550544
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| PCT/CN2024/136502 Pending WO2025200548A1 (zh) | 2024-03-29 | 2024-12-03 | 变压器声纹局部放电检测方法、装置、设备及存储介质 |
Country Status (2)
| Country | Link |
|---|---|
| CN (1) | CN118244064A (zh) |
| WO (1) | WO2025200548A1 (zh) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN121237125A (zh) * | 2025-12-02 | 2025-12-30 | 国网山西省电力有限公司电力科学研究院 | 基于多通道声信号时频空间谱图融合的局部放电模式识别方法 |
Families Citing this family (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN118244064A (zh) * | 2024-03-29 | 2024-06-25 | 国网重庆市电力公司电力科学研究院 | 一种变压器声纹局部放电检测方法及装置 |
| CN121071701A (zh) * | 2025-08-27 | 2025-12-05 | 国家电网有限公司 | 一种故障检测方法、装置、设备及计算机可读存储介质 |
Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20050194979A1 (en) * | 2004-03-05 | 2005-09-08 | Roman Harry T. | Online fiber optic sensor for detecting partial discharge and similar events in large utility station transformers and the like |
| US20150091597A1 (en) * | 2013-10-01 | 2015-04-02 | Rockwell Automation Technologies, Inc. | Systems and methods for detecting partial discharge in electrical components |
| CN112201260A (zh) * | 2020-09-07 | 2021-01-08 | 北京科技大学 | 一种基于声纹识别的变压器运行状态在线检测方法 |
| US20210190849A1 (en) * | 2018-05-07 | 2021-06-24 | Senvion Gmbh | Acoustic condition monitoring method and system for electrical power components, in particular transformers |
| CN113866570A (zh) * | 2021-08-06 | 2021-12-31 | 厦门欧易奇机器人有限公司 | 一种基于声纹的局放监测方法 |
| CN115291056A (zh) * | 2022-07-29 | 2022-11-04 | 国网安徽省电力有限公司超高压分公司 | 一种基于声纹识别模型的变压器工作状态识别系统及方法 |
| CN115754630A (zh) * | 2022-11-15 | 2023-03-07 | 宁格朗电气股份有限公司 | 基于声阵列的非接触式局放监测方法及监测装置 |
| CN116840631A (zh) * | 2023-06-16 | 2023-10-03 | 国网吉林省电力有限公司长春供电公司 | 基于联合诊断模型的变压器局部放电监测与定位方法 |
| CN118150956A (zh) * | 2024-03-20 | 2024-06-07 | 中国电力科学研究院有限公司 | 一种用于变压器局部放电类型的识别方法和系统 |
| CN118244064A (zh) * | 2024-03-29 | 2024-06-25 | 国网重庆市电力公司电力科学研究院 | 一种变压器声纹局部放电检测方法及装置 |
-
2024
- 2024-03-29 CN CN202410379824.8A patent/CN118244064A/zh active Pending
- 2024-12-03 WO PCT/CN2024/136502 patent/WO2025200548A1/zh active Pending
Patent Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20050194979A1 (en) * | 2004-03-05 | 2005-09-08 | Roman Harry T. | Online fiber optic sensor for detecting partial discharge and similar events in large utility station transformers and the like |
| US20150091597A1 (en) * | 2013-10-01 | 2015-04-02 | Rockwell Automation Technologies, Inc. | Systems and methods for detecting partial discharge in electrical components |
| US20210190849A1 (en) * | 2018-05-07 | 2021-06-24 | Senvion Gmbh | Acoustic condition monitoring method and system for electrical power components, in particular transformers |
| CN112201260A (zh) * | 2020-09-07 | 2021-01-08 | 北京科技大学 | 一种基于声纹识别的变压器运行状态在线检测方法 |
| CN113866570A (zh) * | 2021-08-06 | 2021-12-31 | 厦门欧易奇机器人有限公司 | 一种基于声纹的局放监测方法 |
| CN115291056A (zh) * | 2022-07-29 | 2022-11-04 | 国网安徽省电力有限公司超高压分公司 | 一种基于声纹识别模型的变压器工作状态识别系统及方法 |
| CN115754630A (zh) * | 2022-11-15 | 2023-03-07 | 宁格朗电气股份有限公司 | 基于声阵列的非接触式局放监测方法及监测装置 |
| CN116840631A (zh) * | 2023-06-16 | 2023-10-03 | 国网吉林省电力有限公司长春供电公司 | 基于联合诊断模型的变压器局部放电监测与定位方法 |
| CN118150956A (zh) * | 2024-03-20 | 2024-06-07 | 中国电力科学研究院有限公司 | 一种用于变压器局部放电类型的识别方法和系统 |
| CN118244064A (zh) * | 2024-03-29 | 2024-06-25 | 国网重庆市电力公司电力科学研究院 | 一种变压器声纹局部放电检测方法及装置 |
Non-Patent Citations (1)
| Title |
|---|
| SHI, SHENGDAN, HUANG JINJUN, XIAOXUN ZHU, WANG YU, BAIYUN QIAN: "Partial Discharge Pattern Recognition on Transformer Based on Voiceprint SDP-CNN", ELECTRIC POWER INFORMATION AND COMMUNICATION TECHNOLOGY, vol. 20, no. 10, 1 January 2022 (2022-01-01), pages 105 - 112, XP093359857, DOI: 10.16543/j.2095-641x.electric.power.ict.2022.10.013 * |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN121237125A (zh) * | 2025-12-02 | 2025-12-30 | 国网山西省电力有限公司电力科学研究院 | 基于多通道声信号时频空间谱图融合的局部放电模式识别方法 |
Also Published As
| Publication number | Publication date |
|---|---|
| CN118244064A (zh) | 2024-06-25 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| WO2025200548A1 (zh) | 变压器声纹局部放电检测方法、装置、设备及存储介质 | |
| CN117057517B (zh) | 基于数字孪生的电力数据高效处理方法及系统 | |
| CN105737909B (zh) | 基于卡尔曼滤波的涡街流量计抗瞬态冲击干扰的信号处理方法和系统 | |
| CN118278624A (zh) | 一种基于互感器的电力监测数据智能化分析系统 | |
| CN108347352B (zh) | 一种电力系统中信息系统及设备性能的诊断方法 | |
| CN109633368A (zh) | 基于vmd和dfa的含分布式电源配电网电能质量扰动检测方法 | |
| CN112598303A (zh) | 基于1d卷积神经网络和lstm结合的非侵入式负荷分解方法 | |
| CN110987348A (zh) | 基于弓网动态响应的接触网硬点确定方法及装置 | |
| CN118673816A (zh) | 基于数字孪生的锂电池系统故障检测方法及系统 | |
| CN110082082A (zh) | 一种基于振动信号主成分分析法的gis状态识别方法 | |
| CN115618205A (zh) | 一种便携式声纹故障检测系统及方法 | |
| CN107607342B (zh) | 空调机房设备群的健康能效检测方法 | |
| WO2026082134A1 (zh) | 配电网隐蔽性故障识别方法、装置、电子设备以及存储介质 | |
| CN119179982A (zh) | 一种基于数据分析的化工生产智能管理系统 | |
| CN105867353B (zh) | 一种振荡监测方法及系统 | |
| CN119903372A (zh) | 一种基于数据多源融合的电气设备故障分析系统 | |
| CN106546918A (zh) | 一种水电机组的故障诊断方法 | |
| CN120632624A (zh) | 一种柴油发电机组的故障诊断方法与系统 | |
| CN114358048A (zh) | Gil机械故障诊断模型的构造方法及其应用、计算机可读介质、故障诊断系统 | |
| CN117633611B (zh) | 一种危险用电器及用电行为识别方法及系统 | |
| CN118796796A (zh) | 性能优化方法、装置、存储介质及电子设备 | |
| CN119989300A (zh) | 一种卷烟机设备健康评价方法、装置、设备及介质 | |
| CN119198102A (zh) | 一种摩托车动力组流水线管理系统 | |
| CN113420436B (zh) | 基于gru和arima-t的非侵入式事件检测方法 | |
| CN115629312A (zh) | 一种基于单分类张量超圆盘的电机故障检测方法 |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| REG | Reference to national code |
Ref country code: BR Ref legal event code: B01A Ref document number: 112025000404 Country of ref document: BR |
|
| 121 | Ep: the epo has been informed by wipo that ep was designated in this application |
Ref document number: 24933066 Country of ref document: EP Kind code of ref document: A1 |