CN111736050A - Partial discharge fault monitoring and evaluating device and method - Google Patents
Partial discharge fault monitoring and evaluating device and method Download PDFInfo
- Publication number
- CN111736050A CN111736050A CN202010882204.8A CN202010882204A CN111736050A CN 111736050 A CN111736050 A CN 111736050A CN 202010882204 A CN202010882204 A CN 202010882204A CN 111736050 A CN111736050 A CN 111736050A
- Authority
- CN
- China
- Prior art keywords
- partial discharge
- sound source
- intensity
- occurrence
- fault monitoring
- 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
Images
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01R—MEASURING ELECTRIC VARIABLES; MEASURING MAGNETIC VARIABLES
- G01R31/00—Arrangements for testing electric properties; Arrangements for locating electric faults; Arrangements for electrical testing characterised by what is being tested not provided for elsewhere
- G01R31/12—Testing dielectric strength or breakdown voltage ; Testing or monitoring effectiveness or level of insulation, e.g. of a cable or of an apparatus, for example using partial discharge measurements; Electrostatic testing
- G01R31/1209—Testing dielectric strength or breakdown voltage ; Testing or monitoring effectiveness or level of insulation, e.g. of a cable or of an apparatus, for example using partial discharge measurements; Electrostatic testing using acoustic measurements
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01D—MEASURING NOT SPECIALLY ADAPTED FOR A SPECIFIC VARIABLE; ARRANGEMENTS FOR MEASURING TWO OR MORE VARIABLES NOT COVERED IN A SINGLE OTHER SUBCLASS; TARIFF METERING APPARATUS; MEASURING OR TESTING NOT OTHERWISE PROVIDED FOR
- G01D21/00—Measuring or testing not otherwise provided for
- G01D21/02—Measuring two or more variables by means not covered by a single other subclass
-
- 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
- G01R31/1218—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 optical methods; using charged particle, e.g. electron, beams or X-rays
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01S—RADIO DIRECTION-FINDING; RADIO NAVIGATION; DETERMINING DISTANCE OR VELOCITY BY USE OF RADIO WAVES; LOCATING OR PRESENCE-DETECTING BY USE OF THE REFLECTION OR RERADIATION OF RADIO WAVES; ANALOGOUS ARRANGEMENTS USING OTHER WAVES
- G01S5/00—Position-fixing by co-ordinating two or more direction or position line determinations; Position-fixing by co-ordinating two or more distance determinations
- G01S5/18—Position-fixing by co-ordinating two or more direction or position line determinations; Position-fixing by co-ordinating two or more distance determinations using ultrasonic, sonic, or infrasonic waves
- G01S5/183—Emergency, distress or locator beacons
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N20/00—Machine learning
Abstract
The invention discloses a partial discharge fault monitoring and evaluating device and a method, wherein the device comprises: the microphone array signal acquisition module comprises an ultrasonic microphone array and is configured to acquire ultrasonic signals of the tested electric equipment and cache audio data; a machine learning based partial discharge event detection module configured to perform real-time monitoring of a partial discharge event on audio data acquired by the microphone array signal acquisition module using a machine learning based partial discharge event detection algorithm, mark a time at which the partial discharge event occurs, and buffer the audio data; and the sound source positioning module is configured to find out the audio data corresponding to the marked partial discharge event occurrence time in the cached audio data, perform sound source positioning on the audio data by using a sound source positioning algorithm and obtain an intensity distribution diagram of a sound source.
Description
Technical Field
The invention relates to the field of power equipment detection, in particular to partial discharge monitoring and evaluation of power equipment.
Background
In an electric power system, a device partial discharge phenomenon is an important index reflecting an operation state of an electric power device. Currently, a commonly used partial discharge device (partial discharge device) is an ultrasonic partial discharge detector, a detection instrument needs to be manually held to inspect electric equipment, the inspection efficiency of the detection instrument is low, and hearing damage can be caused after long-time use; in addition, the positioning of the partial discharge fault and the evaluation of the severity of the partial discharge fault need to depend on the personal experience of an inspector, the test result is not intuitive, and the test experience is difficult to reuse.
Therefore, a partial discharge fault monitoring and evaluating scheme capable of improving the partial discharge detection efficiency, visually displaying the test result and quantifying the test result is needed.
Disclosure of Invention
In order to solve the problems in the prior art, the invention provides a partial discharge fault monitoring and evaluating device and a partial discharge fault monitoring and evaluating method.
The partial discharge fault monitoring and evaluating apparatus of the present invention includes at least: the system comprises a microphone array signal acquisition module, a partial discharge event detection module based on machine learning and a sound source positioning module.
The microphone array signal acquisition module comprises an ultrasonic microphone array and is configured to acquire ultrasonic signals of the tested electric equipment and cache audio data;
a machine learning based partial discharge event detection module configured to perform real-time monitoring of a partial discharge event on audio data acquired by the microphone array signal acquisition module using a machine learning based partial discharge event detection algorithm, mark a time at which the partial discharge event occurs, and buffer the audio data; and
and the sound source positioning module is configured to find out the audio data corresponding to the marked partial discharge event occurrence moment in the cached audio data, perform sound source positioning on the audio data by using a sound source positioning algorithm and obtain an intensity distribution diagram of a sound source.
In one embodiment, the machine learning-based partial discharge event detection algorithm is a convolutional neural network-based algorithm, and the sound source localization algorithm is a Beamforming algorithm.
In one embodiment, the apparatus further comprises: the optical image acquisition module comprises a camera positioned at the geometric center of the ultrasonic microphone array and is configured to acquire optical images of the power equipment and cache optical image data.
In one embodiment, the apparatus further comprises: the sensor data acquisition module is configured to acquire environmental data, including a temperature sensor, a humidity sensor, an air pressure sensor, and a distance sensor;
wherein the temperature sensor collects the temperature of a test environment; the humidity sensor acquires the humidity of a test environment; the air pressure sensor acquires the air pressure of a test environment; the distance sensor collects the linear distance between the electrical equipment to be measured and the partial discharge fault monitoring and evaluating device.
In one embodiment, the apparatus further comprises: a correction module configured to derive a distance correction parameter and an environmental attenuation correction parameter based on environmental data obtained by the sensor.
In one embodiment, the apparatus further comprises: and the local discharge intensity estimation module is configured to perform distance correction and environmental attenuation correction on the intensity of the ultrasonic signal at the sound source position in the sound source intensity distribution map obtained by the sound source positioning module by using the distance correction parameter and the environmental attenuation correction parameter to obtain an estimated value of the intensity of the ultrasonic signal of the local discharge sound source.
In one embodiment, the apparatus further comprises: and the sound image cloud image fusion module is configured to superpose and fuse the sound source intensity distribution diagram with the optical image cached in the optical image acquisition module, and identify the position of the occurrence of the partial discharge event and the distribution condition of the sound source intensity in the superposed and fused sound source distribution diagram.
In one embodiment, the apparatus further comprises: a statistic and display module configured to count the time, intensity and position of occurrence of a partial discharge event based on the estimated value of the intensity of the ultrasonic signal of the partial discharge sound source; displaying the statistical result on a display screen in a form of an acoustic image; and evaluating whether the partial discharge event occurs and the degradation process and severity of the partial discharge fault according to the statistical result.
In one embodiment, the statistical manner includes: and superposing the position where the partial discharge event occurs on the image obtained by the image cloud picture fusion module to obtain a similar thermodynamic distribution map of the occurrence frequency of the partial discharge event.
In one embodiment, the statistical manner includes: and superposing the intensity of the occurrence of the partial discharge event at the occurrence position, superposing the intensity of the position overlapped part by adopting a logarithmic summation rule, and fusing the superposition result on the image obtained by the image cloud image fusion module to obtain a similar thermodynamic distribution map of the occurrence intensity of the partial discharge event.
In one embodiment, the statistical manner includes: and grouping the partial discharge events according to the occurrence positions, then solving the occurrence frequency of the partial discharge events at the positions within the calculation time according to the frequency of the partial discharge at the positions, then superposing the frequency at the occurrence positions, and fusing the superposed result with the image obtained by the acoustic image cloud image fusion module to obtain a similar thermodynamic distribution map of the occurrence intensity of the partial discharge events.
The partial discharge fault monitoring and evaluating method at least comprises the following steps:
carrying out ultrasonic signal acquisition, optical image acquisition and environmental data acquisition on the tested power equipment, and caching the acquired audio data, optical image and environmental data;
utilizing a partial discharge event detection algorithm based on machine learning to perform real-time monitoring on a partial discharge event on the collected audio data, marking the occurrence moment of the partial discharge event and caching the audio data;
and finding out the audio data corresponding to the marked partial discharge event occurrence moment in the cached audio data, and carrying out sound source positioning on the audio data by utilizing a sound source positioning algorithm to obtain a sound source intensity distribution diagram.
In one embodiment, the machine learning-based partial discharge event detection algorithm is a convolutional neural network-based algorithm, and the sound source localization algorithm is a Beamforming algorithm.
In one embodiment, the ultrasound signal acquisition comprises ultrasound signal acquisition with an ultrasound microphone array; the optical image acquisition comprises optical image acquisition by using a camera positioned at the geometric center of the ultrasonic microphone array; the environmental data acquisition comprises the steps of acquiring the temperature of the testing environment by using a temperature sensor, acquiring the humidity of the testing environment by using a humidity sensor, acquiring the air pressure of the testing environment by using an air pressure sensor and acquiring the linear distance between the tested electrical equipment and the partial discharge fault monitoring and evaluating device by using a distance sensor.
In one embodiment, the method further comprises: and superposing and fusing the sound source intensity distribution diagram and the cached optical image, and identifying the position of the occurrence of the partial discharge event and the distribution condition of the sound source intensity in the superposed and fused sound source intensity distribution diagram.
In one embodiment, the method further comprises: and performing distance correction and environment attenuation correction on the intensity of the ultrasonic signal at the sound source position in the sound source intensity distribution diagram by using the environment data to obtain an estimated value of the intensity of the ultrasonic signal of the local discharge sound source.
In one embodiment, the method further comprises: and counting the occurrence time, intensity and position of the local discharge event based on the estimated value of the intensity of the ultrasonic signal of the local discharge sound source to obtain a statistical distribution map.
In one embodiment, the statistical manner includes: and superposing the position where the partial discharge event occurs on the image obtained by the image cloud picture fusion module to obtain a similar thermodynamic distribution map of the occurrence frequency of the partial discharge event.
In one embodiment, the statistical manner includes: and superposing the intensity of the occurrence of the partial discharge event at the occurrence position, superposing the intensity of the position overlapped part by adopting a logarithmic summation rule, and fusing the superposition result on the image obtained by the image cloud image fusion module to obtain a similar thermodynamic distribution map of the occurrence intensity of the partial discharge event.
In one embodiment, the statistical manner includes: and grouping the partial discharge events according to the occurrence positions, then solving the occurrence frequency of the partial discharge events at the positions within the calculation time according to the frequency of the partial discharge at the positions, then superposing the frequency at the occurrence positions, and fusing the superposed result with the image obtained by the acoustic image cloud image fusion module to obtain a similar thermodynamic distribution map of the occurrence intensity of the partial discharge events.
In one embodiment, the method further comprises: and evaluating whether the partial discharge event occurs and the degradation process and the severity degree of the partial discharge fault based on the statistical analysis graph.
The invention has the following beneficial technical effects:
firstly, the sound source positioning can quickly capture the partial discharge event and the position where the partial discharge occurs in the routing inspection, the routing inspection efficiency is improved, and the test result is intuitive;
secondly, continuous snapshot can be carried out on the partial discharge event in a fixed-point monitoring mode, and the intensity of partial discharge is quantified through calculation;
thirdly, based on statistical analysis of the snapshot data, a user can be helped to effectively evaluate the degradation process and severity of the partial discharge fault of the equipment at different times. The method has important reference value for pre-judging and preventing the equipment state in advance.
Drawings
The foregoing summary, as well as the following detailed description of the invention, will be better understood when read in conjunction with the appended drawings. It is to be noted that the appended drawings are intended as examples of the claimed invention. In the drawings, like reference characters designate the same or similar elements.
FIG. 1 shows a schematic diagram of a partial discharge fault monitoring and evaluation apparatus according to an embodiment of the invention; and
FIG. 2 illustrates a flow diagram of a partial discharge fault monitoring and evaluation method according to an embodiment of the invention.
Detailed Description
The detailed features and advantages of the present invention are described in detail in the detailed description which follows, and will be sufficient for anyone skilled in the art to understand the technical content of the present invention and to implement the present invention, and the related objects and advantages of the present invention will be easily understood by those skilled in the art from the description, claims and drawings disclosed in the present specification.
In an electric power system, a device partial discharge phenomenon is an important index reflecting an operation state of an electric power device. Currently, a commonly used partial discharge device (called partial discharge device for short) is an ultrasonic partial discharge detector, a manual handheld instrument is needed to patrol power equipment, the polling efficiency of the instrument is low, and hearing damage can be caused after long-time use; in addition, the positioning of the partial discharge fault and the evaluation of the severity of the partial discharge fault need to depend on the personal experience of an inspector, the test result is not intuitive, and the test experience is difficult to reuse.
In order to solve the problems in the prior art, the invention provides a partial discharge fault monitoring and evaluating device and a partial discharge fault monitoring and evaluating method.
The device can be used for collecting ultrasonic signals, optical images and environmental data of the tested electrical equipment. Wherein, the ultrasonic signal collection is realized by a microphone array composed of ultrasonic microphones. A camera is designed at the geometric center of the array and is responsible for collecting optical images. The environmental data acquisition is responsible for acquiring four types of parameters of temperature, humidity, air pressure and distance respectively by 4 different types of sensors.
In addition, the signal acquisition part of the microphone array can be realized by an ultra-multi-channel (more than 100 channels) high-speed (the sampling rate can reach more than 192 kHz) data acquisition card realized based on FPGA. And extracting a path of sound signals from the microphone array signals, and detecting the partial discharge event by using a trained convolutional neural network algorithm. When a partial discharge event occurs, continuing to call the Beamforming algorithm to calculate the sound field condition in the space. And (5) fusing the sound pressure of the sound field with the optical image after the calculation result is identified according to the thermodynamic diagram. The fused image is displayed on a display screen, so that the person can conveniently observe the fused image.
After the Beamforming algorithm is completed, extracting a sound pressure level intensity calculation result of the sound source at the sound source position from the calculation result, and correcting the sound pressure level intensity of the sound source by using a sound pressure level correction value at the environment parameter calculation position tested by the environment sensor to obtain a corrected sound pressure level intensity value of the sound source.
The partial discharge fault monitoring and evaluating device and the method have the following functions:
firstly, the invention can avoid the occurrence of the partial discharge event from being missed by using a partial discharge event detection algorithm, accurately captures the position of the partial discharge event by matching the Beamforming algorithm with the optical camera, and clearly displays the position of the partial discharge fault by the acoustic image cloud picture.
Secondly, the following three statistical analysis results can be further given through the estimation value of the partial discharge intensity, the position information of the occurrence of the partial discharge event and the occurrence time of the partial discharge event.
a) Distribution of occurrence frequency of partial discharge events on tested electrical equipment
b) Distribution of occurrence intensity of partial discharge event on tested electric equipment
c) Distribution of frequency of partial discharge event (calculated by 1min or 1h as unit time) on tested electric equipment
Whether the partial discharge fault occurs to the equipment can be effectively judged through the three analysis results, and the degradation process of the partial discharge fault and the severity of the fault are explained.
FIG. 1 shows a schematic diagram of a partial discharge fault monitoring and evaluation apparatus according to an embodiment of the invention. As shown in fig. 1, the partial discharge fault monitoring and evaluating apparatus of the present invention includes a microphone array signal collecting module 101, an optical image collecting module 102, a sensor data collecting module 103, a machine learning based partial discharge event detecting module 104, a sound source localization module 105, a modification module 106, a partial discharge intensity estimating module 107, a sound image cloud image fusion module 108, and a statistics and display module 109.
The microphone array signal acquisition module 101 includes an ultrasonic microphone array configured to perform ultrasonic signal acquisition on the electrical device under test.
The optical image acquisition module 102 includes a camera located at the geometric center of the ultrasonic microphone array, and is configured to acquire and buffer an optical image of the tested electric power device.
The sensor data acquisition module 103 is configured to acquire environmental data. The sensor data acquisition module 103 includes a temperature sensor, a humidity sensor, an air pressure sensor, and a distance sensor. Wherein the temperature sensor collects the temperature of the test environment. The humidity sensor collects the humidity of the test environment. The air pressure sensor collects air pressure of a test environment. The distance sensor collects the linear distance between the electrical equipment to be measured and the partial discharge fault monitoring and evaluating device.
The machine learning based partial discharge event detection module 104 is configured to perform real-time monitoring of partial discharge events on the audio data collected by the microphone array signal collection module using a machine learning based partial discharge event detection algorithm, mark the time at which the partial discharge event occurs, and buffer the audio data.
In one embodiment, the machine learning includes a convolutional neural network based algorithm. The convolutional neural network algorithm can have extremely high recognition accuracy after being well trained.
In one embodiment, a machine learning based partial discharge event detection algorithm, such as a convolutional neural network algorithm, is run in real time. The partial discharge event detection algorithm captures real-time audio data from a certain fixed channel in the microphone array to perform event detection, and when the partial discharge event is detected, the algorithm can mark the occurrence moment of the partial discharge event.
The sound source localization module 105 is configured to find out the audio data corresponding to the occurrence time of the marked partial discharge event in the audio data buffered in advance, and perform sound source localization on the audio data by using a sound source localization algorithm and obtain an intensity distribution map of a sound source.
In one embodiment, the sound source localization algorithm may be a Beamforming algorithm.
In one embodiment, the intensity profile of the sound source is a thermodynamic-like picture in color or grayscale, and the intensity of the sound source signal in the region is represented by the color (or grayscale) in the different regions.
It should be noted that a pure sound source localization algorithm, such as the beamformation algorithm, is very computationally expensive. The algorithm with higher power consumption can process data at a lower rate, and when the data processing rate of the algorithm is lower than the data generation rate, partial data must be discarded to ensure the timeliness of data processing, which leaves a hidden danger for partial discharge event missing. And because the occurrence of the partial discharge event is random and sporadic and the occurrence duration is very short, the algorithm cannot predict in advance whether the partial discharge event is about to occur, and when the data content of the period in which the partial discharge event occurs is discarded, the partial discharge event is not detected, that is, the event is missed. The direct consequence of this may be that a partial discharge fault is not discovered or the severity of the fault is underestimated.
According to the invention, the machine learning-based partial discharge event detection module 104 and the sound source positioning module 105 can realize that partial discharge faults are not caught, and the technical problem that partial discharge events cannot be caught in time in the prior art is solved. The invention firstly utilizes the sound event detection algorithm (namely, the partial discharge event detection algorithm) based on the convolutional neural network to monitor the occurrence time of the partial discharge event in real time, then the sound source positioning algorithm (such as the Beamforming algorithm) only needs to perform sound source position positioning on the audio data corresponding to the occurrence time of the partial discharge event, and the sound source positioning algorithm (such as the Beamforming algorithm) does not need to measure and calculate all the acquired ultrasonic signal data in real time any more, thereby improving the detection efficiency. Because the partial discharge event detection algorithm based on machine learning is operated in real time, the partial discharge event can be ensured not to be missed, and extremely low missing rate can be realized. While sound source localization algorithms (e.g., beamformming algorithms) can measure after the occurrence of partial discharge events based on buffered data without requiring extremely high real-time performance. The combination of the two ensures that the partial discharge event is substantially free of scratching.
The correction module 106 is configured to derive a distance correction parameter and an environmental attenuation correction parameter based on the environmental data obtained by each sensor.
The partial discharge intensity estimation module 107 is configured to perform distance correction and environmental attenuation correction on the intensity of the ultrasonic signal at the sound source position in the sound source intensity distribution map obtained by the sound source localization module 105 by using the distance correction parameter and the environmental attenuation correction parameter, so as to obtain a partial discharge sound source ultrasonic signal intensity estimation value.
In one embodiment, the partial discharge source ultrasound signal intensity estimate = measured ultrasound signal intensity + distance correction parameter + environmental attenuation correction parameter. Wherein:
the estimated value of the ultrasonic signal intensity of the local discharge sound source is the estimation of the ultrasonic intensity of ultrasonic waves in a unit distance (generally 1 meter) in a test frequency band.
The measured ultrasonic signal intensity is the intensity of the ultrasonic signal at the sound source position in the sound source intensity distribution map calculated by the sound source localization algorithm, for example, the Beamforming algorithm, in the sound source localization module 105.
The distance correction parameter is used for correcting the actually measured ultrasonic signal intensity to a compensation value of the ultrasonic intensity in a unit distance.
The environmental attenuation correction parameter is used for correcting the attenuation caused by the propagation of the ultrasonic signal in a non-ideal medium.
The sound image cloud image fusion module 108 is configured to overlay and fuse the sound source intensity distribution map with the optical image cached in the optical image acquisition module 102, and identify the position where the partial discharge event occurs and the distribution status of the sound source intensity in the overlay and fused sound source distribution map.
The statistics and display module 109 is configured to perform statistics on the occurrence time, intensity and position of the partial discharge event based on the estimated value of the intensity of the ultrasonic signal of the partial discharge sound source; displaying the statistical result on a display screen in a form of an acoustic image; and evaluating whether a partial discharge event occurs and the degradation process and severity of the occurrence of the partial discharge fault according to the statistical result.
In one embodiment, the statistical approach includes: and superposing the position where the partial discharge event occurs on the image obtained by the acoustic image cloud image fusion module 108 to obtain a similar thermodynamic distribution map of the occurrence frequency of the partial discharge event. The time period of occurrence of the partial discharge events which are subjected to superposition can be set arbitrarily, and respective distribution graphs can be obtained for different time periods of one test.
In one embodiment, the statistical approach includes: and superposing the intensity of the occurrence of the partial discharge event at the occurrence position, superposing the intensity of the position overlapped part by adopting a logarithmic summation rule, and fusing the superposition result on the image obtained by the acoustic image cloud image fusion module 108 to obtain a similar thermodynamic distribution map of the occurrence intensity of the partial discharge event. The time period of occurrence of the partial discharge events which are subjected to superposition can be set arbitrarily, and respective distribution graphs can be obtained for different time periods of one test.
In one embodiment, the statistical approach includes: the frequency of the partial discharge events is calculated within the calculation time according to the number of the partial discharge events at the position after the partial discharge events are grouped according to the positions, the frequency calculation time can be any reasonable time length, then the frequencies are superposed at the positions, and the superposed result is fused with the image obtained by the image cloud image fusion module 108 to obtain the similar thermodynamic distribution map of the occurrence intensity of the partial discharge events. The time period of occurrence of the partial discharge events which are subjected to superposition can be set arbitrarily, and respective distribution graphs can be obtained for different time periods of one test.
The invention also provides a partial discharge fault monitoring and evaluating method. As shown in fig. 2, the method comprises the steps of:
step 1: the method comprises the steps of carrying out ultrasonic signal acquisition, optical image acquisition and environmental data acquisition on the tested power equipment, and caching the acquired ultrasonic signals (namely audio data), optical images and environmental data.
The ultrasonic signal acquisition is realized by a microphone array formed by ultrasonic microphones. A camera is disposed at a geometrically central position of the array and is configured to perform optical image acquisition. The environmental data comprises four types of parameters including the temperature of the testing environment, the humidity of the testing environment, the air pressure of the testing environment and the linear distance between the tested electrical equipment and the testing instrument. Wherein, the temperature of test environment can be gathered by temperature sensor, and the humidity of test environment can be gathered by humidity transducer, and the atmospheric pressure of test environment can be gathered by baroceptor. The linear distance between the tested electric equipment and the testing instrument can be acquired by the distance sensor.
In one embodiment, the ultrasound signal acquisition may be implemented based on an FPGA-implemented ultra-multi-channel (e.g., above 100 channels) high-speed (e.g., up to a sampling rate above 192 kHz) data acquisition card.
Step 2: the method comprises the steps of utilizing a partial discharge event detection algorithm based on machine learning to carry out real-time monitoring on collected ultrasonic signals, namely audio data, marking the occurrence time of the partial discharge event and caching the audio data.
In one embodiment, the machine learning includes a convolutional neural network based algorithm. The convolutional neural network algorithm can have extremely high recognition accuracy after being well trained.
In one embodiment, a machine learning based partial discharge event detection algorithm (e.g., a convolutional neural network algorithm) is run in real-time. The partial discharge event detection algorithm (such as a convolutional neural network algorithm) captures real-time audio data from a certain fixed channel in the microphone array to perform partial discharge event detection, and when the occurrence of a partial discharge event is detected, the algorithm can mark the occurrence moment of the partial discharge event.
And step 3: and finding out the audio data corresponding to the marked partial discharge event occurrence time from the audio data cached in advance, and carrying out sound source positioning on the audio data by utilizing a sound source positioning algorithm to obtain the intensity distribution diagram of the sound source.
In one embodiment, the sound source localization algorithm may be a Beamforming algorithm.
In one embodiment, the intensity profile of the sound source is a thermodynamic-like picture in color or grayscale, and the intensity of the sound source signal in the region is represented by the color (or grayscale) in the different regions.
It should be noted that a pure sound source localization algorithm, such as the beamformation algorithm, is very computationally expensive. The algorithm with higher power consumption can process data at a lower rate, and when the data processing rate of the algorithm is lower than the data generation rate, partial data must be discarded to ensure the timeliness of data processing, which leaves a hidden danger for partial discharge event missing. And because the occurrence of the partial discharge event is random and sporadic and the occurrence duration is very short, the algorithm cannot predict in advance whether the partial discharge event is about to occur, and when the data content of the period in which the partial discharge event occurs is discarded, the partial discharge event is not detected, that is, the event is missed. The direct consequence of this may be that a partial discharge fault is not discovered or the severity of the fault is underestimated.
According to the invention, the non-catching of the partial discharge fault can be realized through the step 2 and the step 3, and the technical problem that the partial discharge event cannot be caught in time in the prior art is solved. The invention firstly utilizes the sound event detection algorithm (namely, the partial discharge event detection algorithm) based on the convolutional neural network to monitor the occurrence time of the partial discharge event in real time, then the sound source positioning algorithm (such as the Beamforming algorithm) only needs to perform sound source position positioning on the audio data corresponding to the occurrence time of the partial discharge event, and the sound source positioning algorithm (such as the Beamforming algorithm) does not need to measure and calculate all the acquired ultrasonic signal data in real time any more, thereby improving the detection efficiency. Because the partial discharge event detection algorithm based on machine learning is operated in real time, the partial discharge event can be ensured not to be missed, and extremely low missing rate can be realized. While sound source localization algorithms (e.g., beamformming algorithms) can measure after the occurrence of partial discharge events based on buffered data without requiring extremely high real-time performance. The combination of the two ensures that the partial discharge event is substantially free of scratching.
And 4, step 4: and superposing and fusing the sound source intensity distribution diagram and the cached optical image, and identifying the position of the occurrence of the partial discharge event and the distribution condition of the sound source intensity in the superposed and fused sound source intensity distribution diagram.
And 5: and (3) performing distance correction and environment attenuation correction on the intensity of the ultrasonic signal at the sound source position in the sound source intensity distribution diagram obtained in the step (3) by using the environment data to obtain an estimated value of the intensity of the ultrasonic signal of the local discharge sound source.
In one embodiment, the partial discharge source ultrasound signal intensity estimate = measured ultrasound signal intensity + distance correction parameter + environmental attenuation correction parameter. Wherein:
local discharge sound source ultrasonic signal intensity estimation value: is the estimation of the ultrasonic intensity in unit distance (generally 1 meter) within the test frequency band.
The measured ultrasonic signal intensity is the intensity of the ultrasonic signal at the sound source position in the sound source distribution map obtained by calculation in step 3 using a sound source localization algorithm, such as beamformation algorithm.
Distance correction parameters: and the ultrasonic wave intensity compensation module is used for correcting the actually measured ultrasonic wave signal intensity to a compensation value of the ultrasonic wave intensity in a unit distance.
Environmental attenuation correction parameters: for correcting the attenuation caused by the propagation of ultrasonic signals in non-ideal media.
And 6, counting the occurrence time, intensity and position of the local discharge event based on the estimated value of the intensity of the ultrasonic signal of the local discharge sound source obtained in the step 5 to obtain a statistical distribution map.
In one embodiment, the statistical approach includes: and (4) superposing the positions where the partial discharge events occur on the image obtained in the step (4) to obtain a similar thermodynamics distribution map of the occurrence times of the partial discharge events. The time period of occurrence of the partial discharge events which are subjected to superposition can be set arbitrarily, and respective distribution graphs can be obtained for different time periods of one test.
In one embodiment, the statistical approach includes: and (4) overlapping the intensity of the occurrence of the partial discharge event at the occurrence position, overlapping the intensity of the position overlapping part by adopting a logarithmic summation rule, and then fusing the overlapping result on the image obtained in the step (4) to obtain a similar thermodynamic distribution map of the intensity of the occurrence of the partial discharge event. The time period of occurrence of the partial discharge events which are subjected to superposition can be set arbitrarily, and respective distribution graphs can be obtained for different time periods of one test.
In one embodiment, the statistical approach includes: grouping the partial discharge events according to the occurrence positions, then calculating the occurrence frequency of the partial discharge events at the positions within the calculation time according to the frequency of the partial discharge events at the positions (the calculation time of the frequency can be any reasonable time length), then overlapping the frequency at the occurrence positions, and fusing the overlapped result with the image obtained in the step 4 to obtain a similar thermodynamic distribution map of the occurrence intensity of the partial discharge events. The time period of occurrence of the partial discharge events which are subjected to superposition can be set arbitrarily, and respective distribution graphs can be obtained for different time periods of one test.
And 7, evaluating whether the partial discharge event occurs and the degradation process and the severity of the partial discharge fault on the basis of the statistical analysis chart obtained in the step 6.
As used in this application and the appended claims, the terms "a," "an," "the," and/or "the" are not intended to be inclusive in the singular, but rather are intended to be inclusive in the plural unless the context clearly dictates otherwise. In general, the terms "comprises" and "comprising" merely indicate that steps and elements are included which are explicitly identified, that the steps and elements do not form an exclusive list, and that a method or apparatus may include other steps or elements.
Although various references are made herein to certain modules according to embodiments of the present application, any number of different modules may be used and run on a processor. The modules are merely illustrative and different aspects of the method may use different modules.
Flow charts are used herein to illustrate operations performed by systems according to embodiments of the present application. It should be understood that the preceding or following operations are not necessarily performed in the exact order in which they are performed. For example, these operations or steps may be processed concurrently as appropriate. Meanwhile, other operations or steps may be added to or one or several steps may be removed from these processes or methods.
Also, this application uses specific language to describe embodiments of the application. Reference throughout this specification to "one embodiment," "an embodiment," and/or "some embodiments" means that a particular feature, structure, or characteristic described in connection with at least one embodiment of the present application is included in at least one embodiment of the present application. Therefore, it is emphasized and should be appreciated that two or more references to "an embodiment" or "one embodiment" or "an alternative embodiment" in various places throughout this specification are not necessarily all referring to the same embodiment. Furthermore, some features, structures, or characteristics of one or more embodiments of the present application may be combined as appropriate.
Moreover, those skilled in the art will appreciate that aspects of the present application may be illustrated and described in terms of several patentable species or situations, including any new and useful combination of processes, machines, manufacture, or materials, or any new and useful improvement thereon. Accordingly, various aspects of the present application may be embodied entirely in hardware, entirely in software (including firmware, resident software, micro-code, etc.) or in a combination of hardware and software. The above hardware or software may be referred to as "data block," module, "" engine, "" unit, "" component, "or" system. Furthermore, aspects of the present application may be represented as a computer product, including computer readable program code, embodied in one or more computer readable media.
Computer program code required for the operations or steps of the various components of the present application may be written in any one or more programming languages, including an object oriented programming language such as Java, Scala, Smalltalk, Eiffel, JADE, Emerald, C + +, C #, VB.NET, Python, and the like, a conventional programming language such as C, Visual Basic, Fortran 2003, Perl, COBOL 2002, PHP, ABAP, a dynamic programming language such as Python, Ruby, and Groovy, or other programming languages, and the like. The program code may run entirely on the device or module of the invention, as a stand-alone software package, partly on the device or module, partly on a remote computer or entirely on the remote computer or server. In the latter scenario, the remote computer may be connected to the user's computer through any network format, such as a Local Area Network (LAN) or a Wide Area Network (WAN), or the connection may be made to an external computer (for example, through the Internet), or in a cloud computing environment, or as a service, such as a software as a service (SaaS).
Additionally, the order in which elements and sequences of the processes described herein are processed, the use of alphanumeric characters, or the use of other designations, is not intended to limit the order of the processes and methods described herein, unless explicitly claimed. While various presently contemplated embodiments of the invention have been discussed in the foregoing disclosure by way of example, it is to be understood that such detail is solely for that purpose and that the appended claims are not limited to the disclosed embodiments, but, on the contrary, are intended to cover all modifications and equivalent arrangements that are within the spirit and scope of the embodiments herein. For example, although the above-described apparatuses or modules may be implemented by hardware devices, they may also be implemented by software-only solutions, such as installing the described system on an existing server or mobile device.
The terms and expressions which have been employed herein are used as terms of description and not of limitation. The use of such terms and expressions is not intended to exclude any equivalents of the features shown and described (or portions thereof), and it is recognized that various modifications may be made within the scope of the claims. Other modifications, variations, and alternatives are also possible. Accordingly, the claims should be looked to in order to cover all such equivalents.
Also, it should be noted that although the present invention has been described with reference to the current specific embodiments, it should be understood by those skilled in the art that the above embodiments are merely illustrative of the present invention, and various equivalent changes or substitutions may be made without departing from the spirit of the present invention, and therefore, it is intended that all changes and modifications to the above embodiments be included within the scope of the claims of the present application.
Claims (21)
1. A partial discharge fault monitoring and evaluation device, the device comprising:
the microphone array signal acquisition module comprises an ultrasonic microphone array and is configured to acquire ultrasonic signals of the tested electric equipment and cache audio data;
a machine learning based partial discharge event detection module configured to perform real-time monitoring of a partial discharge event on audio data acquired by the microphone array signal acquisition module using a machine learning based partial discharge event detection algorithm, mark a time at which the partial discharge event occurs, and buffer the audio data; and
and the sound source positioning module is configured to find out the audio data corresponding to the marked partial discharge event occurrence moment in the cached audio data, perform sound source positioning on the audio data by using a sound source positioning algorithm and obtain an intensity distribution diagram of a sound source.
2. The partial discharge fault monitoring and evaluation device of claim 1, wherein the machine learning based partial discharge event detection algorithm is a convolutional neural network based algorithm and the sound source localization algorithm is a Beamforming algorithm.
3. The partial discharge fault monitoring and evaluation device of claim 1, further comprising:
the optical image acquisition module comprises a camera positioned at the geometric center of the ultrasonic microphone array and is configured to acquire optical images of the power equipment and cache optical image data.
4. The partial discharge fault monitoring and evaluation device of claim 1, further comprising:
the sensor data acquisition module is configured to acquire environmental data, including a temperature sensor, a humidity sensor, an air pressure sensor, and a distance sensor;
wherein the temperature sensor collects the temperature of a test environment; the humidity sensor acquires the humidity of a test environment; the air pressure sensor acquires the air pressure of a test environment; the distance sensor collects the linear distance between the electrical equipment to be measured and the partial discharge fault monitoring and evaluating device.
5. The partial discharge fault monitoring and evaluation device of claim 4, further comprising:
a correction module configured to derive a distance correction parameter and an environmental attenuation correction parameter based on environmental data obtained by the sensor.
6. The partial discharge fault monitoring and evaluation device of claim 5, further comprising:
and the local discharge intensity estimation module is configured to perform distance correction and environmental attenuation correction on the intensity of the ultrasonic signal at the sound source position in the sound source intensity distribution map obtained by the sound source positioning module by using the distance correction parameter and the environmental attenuation correction parameter to obtain an estimated value of the intensity of the ultrasonic signal of the local discharge sound source.
7. The partial discharge fault monitoring and evaluation device of claim 3, further comprising:
and the sound image cloud image fusion module is configured to superpose and fuse the sound source intensity distribution diagram with the optical image cached in the optical image acquisition module, and identify the position of the occurrence of the partial discharge event and the distribution condition of the sound source intensity in the superposed and fused sound source distribution diagram.
8. The partial discharge fault monitoring and evaluation device of claim 6, further comprising:
a statistic and display module configured to count the time, intensity and position of occurrence of a partial discharge event based on the estimated value of the intensity of the ultrasonic signal of the partial discharge sound source; displaying the statistical result on a display screen in a form of an acoustic image; and evaluating whether the partial discharge event occurs and the degradation process and severity of the partial discharge fault according to the statistical result.
9. The partial discharge fault monitoring and evaluation device of claim 8, wherein the statistical manner comprises: and superposing the position where the partial discharge event occurs on the image obtained by the image cloud picture fusion module to obtain a similar thermodynamic distribution map of the occurrence frequency of the partial discharge event.
10. The partial discharge fault monitoring and evaluation device of claim 8, wherein the statistical manner comprises: and superposing the intensity of the occurrence of the partial discharge event at the occurrence position, superposing the intensity of the position overlapped part by adopting a logarithmic summation rule, and fusing the superposition result on the image obtained by the image cloud image fusion module to obtain a similar thermodynamic distribution map of the occurrence intensity of the partial discharge event.
11. The partial discharge fault monitoring and evaluation device of claim 8, wherein the statistical manner comprises: and grouping the partial discharge events according to the occurrence positions, then solving the occurrence frequency of the partial discharge events at the positions within the calculation time according to the frequency of the partial discharge at the positions, then superposing the frequency at the occurrence positions, and fusing the superposed result with the image obtained by the acoustic image cloud image fusion module to obtain a similar thermodynamic distribution map of the occurrence intensity of the partial discharge events.
12. A partial discharge fault monitoring and assessment method, characterized in that the method comprises:
carrying out ultrasonic signal acquisition, optical image acquisition and environmental data acquisition on the tested power equipment, and caching the acquired audio data, optical image and environmental data;
utilizing a partial discharge event detection algorithm based on machine learning to perform real-time monitoring on a partial discharge event on the collected audio data, marking the occurrence moment of the partial discharge event and caching the audio data;
and finding out the audio data corresponding to the marked partial discharge event occurrence moment in the cached audio data, and carrying out sound source positioning on the audio data by utilizing a sound source positioning algorithm to obtain a sound source intensity distribution diagram.
13. The partial discharge fault monitoring and assessment method of claim 12, wherein said machine learning based partial discharge event detection algorithm is a convolutional neural network based algorithm and said sound source localization algorithm is a beamformming algorithm.
14. The partial discharge fault monitoring and assessment method of claim 12, wherein said ultrasonic signal acquisition comprises ultrasonic signal acquisition with an ultrasonic microphone array; the optical image acquisition comprises optical image acquisition by using a camera positioned at the geometric center of the ultrasonic microphone array; the environmental data acquisition comprises the steps of acquiring the temperature of the testing environment by using a temperature sensor, acquiring the humidity of the testing environment by using a humidity sensor, acquiring the air pressure of the testing environment by using an air pressure sensor and acquiring the linear distance between the tested electrical equipment and the partial discharge fault monitoring and evaluating device by using a distance sensor.
15. The partial discharge fault monitoring and evaluation method of claim 12, further comprising:
and superposing and fusing the sound source intensity distribution diagram and the cached optical image, and identifying the position of the occurrence of the partial discharge event and the distribution condition of the sound source intensity in the superposed and fused sound source intensity distribution diagram.
16. The partial discharge fault monitoring and evaluation method of claim 12, further comprising:
and performing distance correction and environment attenuation correction on the intensity of the ultrasonic signal at the sound source position in the sound source intensity distribution diagram by using the environment data to obtain an estimated value of the intensity of the ultrasonic signal of the local discharge sound source.
17. The partial discharge fault monitoring and evaluation method of claim 16, further comprising:
and counting the occurrence time, intensity and position of the local discharge event based on the estimated value of the intensity of the ultrasonic signal of the local discharge sound source to obtain a statistical distribution map.
18. The partial discharge fault monitoring and evaluation method of claim 17, wherein the statistical manner comprises: and superposing the position where the partial discharge event occurs on the image obtained by the image cloud picture fusion module to obtain a similar thermodynamic distribution map of the occurrence frequency of the partial discharge event.
19. The partial discharge fault monitoring and evaluation method of claim 17, wherein the statistical manner comprises: and superposing the intensity of the occurrence of the partial discharge event at the occurrence position, superposing the intensity of the position overlapped part by adopting a logarithmic summation rule, and fusing the superposition result on the image obtained by the image cloud image fusion module to obtain a similar thermodynamic distribution map of the occurrence intensity of the partial discharge event.
20. The partial discharge fault monitoring and evaluation method of claim 17, wherein the statistical manner comprises: and grouping the partial discharge events according to the occurrence positions, then solving the occurrence frequency of the partial discharge events at the positions within the calculation time according to the frequency of the partial discharge at the positions, then superposing the frequency at the occurrence positions, and fusing the superposed result with the image obtained by the acoustic image cloud image fusion module to obtain a similar thermodynamic distribution map of the occurrence intensity of the partial discharge events.
21. The partial discharge fault monitoring and evaluation method of claim 17, further comprising:
and evaluating whether the partial discharge event occurs and the degradation process and the severity degree of the partial discharge fault based on the statistical analysis graph.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010882204.8A CN111736050B (en) | 2020-08-28 | 2020-08-28 | Partial discharge fault monitoring and evaluating device and method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010882204.8A CN111736050B (en) | 2020-08-28 | 2020-08-28 | Partial discharge fault monitoring and evaluating device and method |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN111736050A true CN111736050A (en) | 2020-10-02 |
| CN111736050B CN111736050B (en) | 2020-11-17 |
Family
ID=72658136
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010882204.8A Active CN111736050B (en) | 2020-08-28 | 2020-08-28 | Partial discharge fault monitoring and evaluating device and method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111736050B (en) |
Cited By (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112710915A (en) * | 2020-12-18 | 2021-04-27 | 北京百度网讯科技有限公司 | Method and device for monitoring power equipment, electronic equipment and computer storage medium |
| CN112857560A (en) * | 2021-02-06 | 2021-05-28 | 河海大学 | Acoustic imaging method based on sound frequency |
| CN112904139A (en) * | 2020-10-10 | 2021-06-04 | 国网山东省电力公司枣庄供电公司 | High-voltage switch cabinet partial discharge positioning method and system considering temperature field change |
| CN113092965A (en) * | 2021-04-09 | 2021-07-09 | 华北电力大学（保定） | Converter valve equipment defect partial discharge detection device based on microphone array |
| CN113267330A (en) * | 2021-05-14 | 2021-08-17 | 国网重庆市电力公司电力科学研究院 | GIS equipment mechanical fault detection system and method based on acoustic imaging |
| CN113405597A (en) * | 2021-06-02 | 2021-09-17 | 杭州电力设备制造有限公司 | Sensor layout structure in switch cabinet and evaluation method of layout structure |
| CN113791323A (en) * | 2021-09-14 | 2021-12-14 | 南京土星视界科技有限公司 | Portable abnormal discharge ultrasonic detection device based on intelligent voiceprint recognition technology |
| CN114089141A (en) * | 2022-01-24 | 2022-02-25 | 杭州兆华电子股份有限公司 | Partial discharge detection method and partial discharge detection device |
| CN114113880A (en) * | 2021-11-05 | 2022-03-01 | 国网青海省电力公司检修公司 | Detection method for positioning local discharge fault of high-voltage switch cabinet |
| CN114609493A (en) * | 2022-05-09 | 2022-06-10 | 杭州兆华电子股份有限公司 | Partial discharge signal identification method with enhanced signal data |
| CN114859194A (en) * | 2022-07-07 | 2022-08-05 | 杭州兆华电子股份有限公司 | Non-contact-based partial discharge detection method and device |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| KR101070329B1 (en) * | 2010-07-07 | 2011-10-06 | 한국전기연구원 | Portable ultrasonic partial discharge measurement device having ccd camera, and partial discharge measurement method using the same |
| CN102298107A (en) * | 2011-05-20 | 2011-12-28 | 华南理工大学 | Portable ultrasonic wave and cloud detection apparatus for partial discharge |
| CN105334435A (en) * | 2015-10-23 | 2016-02-17 | 国网山东海阳市供电公司 | Adaptive partial discharge ultrasonic monitoring method based on any array |
| CN105510787A (en) * | 2016-01-26 | 2016-04-20 | 国网上海市电力公司 | Portable ultrasonic, infrared and ultraviolet detector based on image synthesis technology |
| CN105738779A (en) * | 2016-01-26 | 2016-07-06 | 国网上海市电力公司 | Partial discharge detection method based on multi-source image fusion |
| CN107153172A (en) * | 2017-05-08 | 2017-09-12 | 重庆大学 | A kind of cross-spectrum generalized inverse Beamforming Method optimized based on cross-spectrum |
| CN109614960A (en) * | 2019-01-21 | 2019-04-12 | 莆田学院 | A kind of image acoustic array and three-dimensional space noise positioning device and method |
| CN109655720A (en) * | 2018-12-18 | 2019-04-19 | 北京三听科技有限公司 | Partial discharge detection method and device based on two-dimensional sensor array |
-
2020
- 2020-08-28 CN CN202010882204.8A patent/CN111736050B/en active Active
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| KR101070329B1 (en) * | 2010-07-07 | 2011-10-06 | 한국전기연구원 | Portable ultrasonic partial discharge measurement device having ccd camera, and partial discharge measurement method using the same |
| CN102298107A (en) * | 2011-05-20 | 2011-12-28 | 华南理工大学 | Portable ultrasonic wave and cloud detection apparatus for partial discharge |
| CN105334435A (en) * | 2015-10-23 | 2016-02-17 | 国网山东海阳市供电公司 | Adaptive partial discharge ultrasonic monitoring method based on any array |
| CN105510787A (en) * | 2016-01-26 | 2016-04-20 | 国网上海市电力公司 | Portable ultrasonic, infrared and ultraviolet detector based on image synthesis technology |
| CN105738779A (en) * | 2016-01-26 | 2016-07-06 | 国网上海市电力公司 | Partial discharge detection method based on multi-source image fusion |
| CN107153172A (en) * | 2017-05-08 | 2017-09-12 | 重庆大学 | A kind of cross-spectrum generalized inverse Beamforming Method optimized based on cross-spectrum |
| CN109655720A (en) * | 2018-12-18 | 2019-04-19 | 北京三听科技有限公司 | Partial discharge detection method and device based on two-dimensional sensor array |
| CN109614960A (en) * | 2019-01-21 | 2019-04-12 | 莆田学院 | A kind of image acoustic array and three-dimensional space noise positioning device and method |
Non-Patent Citations (6)
| Title |
|---|
| G.CAPON等: "Use of a Deep Convolutional Neural Network and Beamforming for Localisation and Diagnosis of Industry Noise Sources", 《PROCEEDINGS OF ACOUSTICS 2019》 * |
| KAI SHU等: "Beamforming with Enhanced CNN Network", 《2017 ASSOCIATION FOR COMPUTING MACHINERY》 * |
| WEI MA等: "Phased microphone array for sound source localization with deep learning", 《AEROSPACE SYSTEMS》 * |
| YU WANG等: "Partial Discharge Ultrasound Detection Using the Sagnac Interferometer System", 《SENSORS》 * |
| 宋章辰等: "基于卷积神经网络算法的麦克风阵列研究", 《中国力学大会》 * |
| 谢庆等: "基于定向准确度的局部放电超声阵列传感器声学性能定量评价", 《中国电机工程学报》 * |
Cited By (17)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112904139A (en) * | 2020-10-10 | 2021-06-04 | 国网山东省电力公司枣庄供电公司 | High-voltage switch cabinet partial discharge positioning method and system considering temperature field change |
| CN112904139B (en) * | 2020-10-10 | 2022-07-22 | 国网山东省电力公司枣庄供电公司 | High-voltage switch cabinet partial discharge positioning method and system considering temperature field change |
| CN112710915B (en) * | 2020-12-18 | 2024-02-20 | 北京百度网讯科技有限公司 | Method, device, electronic equipment and computer storage medium for monitoring power equipment |
| CN112710915A (en) * | 2020-12-18 | 2021-04-27 | 北京百度网讯科技有限公司 | Method and device for monitoring power equipment, electronic equipment and computer storage medium |
| CN112857560A (en) * | 2021-02-06 | 2021-05-28 | 河海大学 | Acoustic imaging method based on sound frequency |
| CN113092965A (en) * | 2021-04-09 | 2021-07-09 | 华北电力大学（保定） | Converter valve equipment defect partial discharge detection device based on microphone array |
| CN113267330B (en) * | 2021-05-14 | 2023-03-14 | 国网重庆市电力公司电力科学研究院 | GIS equipment mechanical fault detection system and method based on acoustic imaging |
| CN113267330A (en) * | 2021-05-14 | 2021-08-17 | 国网重庆市电力公司电力科学研究院 | GIS equipment mechanical fault detection system and method based on acoustic imaging |
| CN113405597A (en) * | 2021-06-02 | 2021-09-17 | 杭州电力设备制造有限公司 | Sensor layout structure in switch cabinet and evaluation method of layout structure |
| CN113791323A (en) * | 2021-09-14 | 2021-12-14 | 南京土星视界科技有限公司 | Portable abnormal discharge ultrasonic detection device based on intelligent voiceprint recognition technology |
| CN113791323B (en) * | 2021-09-14 | 2023-09-19 | 南京土星视界科技有限公司 | Portable abnormal discharge ultrasonic detection device based on intelligent voiceprint recognition technology |
| CN114113880A (en) * | 2021-11-05 | 2022-03-01 | 国网青海省电力公司检修公司 | Detection method for positioning local discharge fault of high-voltage switch cabinet |
| CN114089141A (en) * | 2022-01-24 | 2022-02-25 | 杭州兆华电子股份有限公司 | Partial discharge detection method and partial discharge detection device |
| CN114609493B (en) * | 2022-05-09 | 2022-08-12 | 杭州兆华电子股份有限公司 | Partial discharge signal identification method with enhanced signal data |
| CN114609493A (en) * | 2022-05-09 | 2022-06-10 | 杭州兆华电子股份有限公司 | Partial discharge signal identification method with enhanced signal data |
| CN114859194B (en) * | 2022-07-07 | 2022-09-23 | 杭州兆华电子股份有限公司 | Non-contact-based partial discharge detection method and device |
| CN114859194A (en) * | 2022-07-07 | 2022-08-05 | 杭州兆华电子股份有限公司 | Non-contact-based partial discharge detection method and device |
Also Published As
| Publication number | Publication date |
|---|---|
| CN111736050B (en) | 2020-11-17 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111736050B (en) | Partial discharge fault monitoring and evaluating device and method | |
| US20200356246A1 (en) | Non-contacting monitor for bridges and civil structures | |
| US8008926B2 (en) | UHF partial discharge and location measuring device for high-voltage power devices | |
| RU2470280C2 (en) | Method for detection and automatic identification of rolling bearing damage | |
| CN106323452B (en) | A kind of detection method and detection device of equipment abnormal sound | |
| JP4261041B2 (en) | Insulation abnormality diagnosis device for high voltage equipment and insulation abnormality diagnosis method thereof | |
| KR102058841B1 (en) | Systems and methods to detect generator collector flashover | |
| CN110687208A (en) | Non-reference Lamb wave damage monitoring method based on hyperbolic positioning | |
| JP2014137323A (en) | Abnormality diagnosis apparatus and abnormality diagnosis method using the same | |
| CN114323481B (en) | Gas multi-source leakage sound image positioning method and sound image positioning system | |
| CN112230107A (en) | Partial discharge monitoring and positioning device, method, computer equipment and storage medium | |
| TW202008278A (en) | Information processing apparatus, information processing system, method, and program | |
| JP3788297B2 (en) | FREQUENCY ANALYZING APPARATUS, ABNORMALITY DETERMINING APPARATUS AND ABNORMALITY DETERMINING SYSTEM APPLYING FFT AFFECT | |
| KR20120012103A (en) | Apparatus for automatically displaying partial discharge localization in GIS | |
| KR101386593B1 (en) | Imaging method of pipe damage | |
| CN110886970A (en) | Safety protection early warning system and method for buried natural gas pipeline | |
| CN116962669A (en) | Foreign matter removal system for monitoring equipment | |
| CN109682463B (en) | Audible noise measuring method for transformer substation | |
| KR20110034281A (en) | Method and analysis system for diagnosising exclusive vibration in generator stator windings | |
| KR20220170653A (en) | Partial discharge diagnosis method and device using ultrasonic visualization and phase resolution analysis | |
| KR101074341B1 (en) | Noise monitoring system, noise monitoring method and computer readble medium on which noise monitoring program is recorded | |
| KR102297005B1 (en) | Apparatus for diagnosing power equipment and method thereof | |
| KR102559458B1 (en) | Complex diagnostic method for power facility and industrial facility | |
| Hagiwara et al. | A method for supporting hammering test by visualization of defect diagnosis on the concrete surfaces | |
| CN111612879A (en) | Device detection method, device and readable storage medium |
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 | ||
| CP03 | Change of name, title or address |
Address after: 311121 building 3, No.10 Xianqiao Road, Zhongtai street, Yuhang District, Hangzhou City, Zhejiang Province Patentee after: Hangzhou Zhaohua Electronics Co.,Ltd. Address before: 31-1 Xianxing Road, Xianlin Industrial Park, Yuhang District, Hangzhou City, Zhejiang Province Patentee before: CRY SOUND CO.,LTD. |
|
| CP03 | Change of name, title or address |