CN114217149A - Transformer acoustic fingerprint uninterrupted power detection and state early warning method - Google Patents
Transformer acoustic fingerprint uninterrupted power detection and state early warning method Download PDFInfo
- Publication number
- CN114217149A CN114217149A CN202111343860.1A CN202111343860A CN114217149A CN 114217149 A CN114217149 A CN 114217149A CN 202111343860 A CN202111343860 A CN 202111343860A CN 114217149 A CN114217149 A CN 114217149A
- Authority
- CN
- China
- Prior art keywords
- transformer
- state
- noise
- acoustic
- sound
- 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
- 238000000034 method Methods 0.000 title claims abstract description 42
- 238000001514 detection method Methods 0.000 title claims abstract description 15
- 238000012544 monitoring process Methods 0.000 claims abstract description 36
- 238000000605 extraction Methods 0.000 claims abstract description 14
- 230000002159 abnormal effect Effects 0.000 claims abstract description 8
- 230000009467 reduction Effects 0.000 claims abstract description 8
- 238000011156 evaluation Methods 0.000 claims abstract description 7
- 230000005236 sound signal Effects 0.000 claims description 16
- 238000004422 calculation algorithm Methods 0.000 claims description 15
- 239000013598 vector Substances 0.000 claims description 14
- 238000004458 analytical method Methods 0.000 claims description 8
- 238000003745 diagnosis Methods 0.000 claims description 8
- 230000001133 acceleration Effects 0.000 claims description 6
- 230000005291 magnetic effect Effects 0.000 claims description 6
- 230000009466 transformation Effects 0.000 claims description 6
- XEEYBQQBJWHFJM-UHFFFAOYSA-N Iron Chemical group [Fe] XEEYBQQBJWHFJM-UHFFFAOYSA-N 0.000 claims description 5
- 238000010276 construction Methods 0.000 claims description 5
- 238000004804 winding Methods 0.000 claims description 5
- 230000008901 benefit Effects 0.000 claims description 4
- 230000008859 change Effects 0.000 claims description 4
- 238000009432 framing Methods 0.000 claims description 4
- 230000004044 response Effects 0.000 claims description 4
- 230000005856 abnormality Effects 0.000 claims description 3
- 230000005540 biological transmission Effects 0.000 claims description 3
- 238000006243 chemical reaction Methods 0.000 claims description 3
- 230000007613 environmental effect Effects 0.000 claims description 3
- 238000005457 optimization Methods 0.000 claims description 3
- 230000008447 perception Effects 0.000 claims description 3
- 238000007781 pre-processing Methods 0.000 claims description 3
- 238000000513 principal component analysis Methods 0.000 claims description 3
- 238000013528 artificial neural network Methods 0.000 claims description 2
- 238000004364 calculation method Methods 0.000 claims description 2
- 238000005516 engineering process Methods 0.000 claims description 2
- 238000001914 filtration Methods 0.000 claims description 2
- 238000010606 normalization Methods 0.000 claims description 2
- 238000003909 pattern recognition Methods 0.000 claims description 2
- 238000012549 training Methods 0.000 claims description 2
- 238000012800 visualization Methods 0.000 claims 1
- 238000012423 maintenance Methods 0.000 abstract description 4
- 230000008439 repair process Effects 0.000 abstract description 3
- 230000007547 defect Effects 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 210000005069 ears Anatomy 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 230000000737 periodic effect Effects 0.000 description 2
- 230000000007 visual effect Effects 0.000 description 2
- 230000004075 alteration Effects 0.000 description 1
- 238000013473 artificial intelligence Methods 0.000 description 1
- 238000009412 basement excavation Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000009529 body temperature measurement Methods 0.000 description 1
- 238000001816 cooling Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000005284 excitation Effects 0.000 description 1
- 230000005350 ferromagnetic resonance Effects 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 239000007787 solid Substances 0.000 description 1
- 239000000126 substance Substances 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 208000024891 symptom Diseases 0.000 description 1
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
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01H—MEASUREMENT OF MECHANICAL VIBRATIONS OR ULTRASONIC, SONIC OR INFRASONIC WAVES
- G01H17/00—Measuring mechanical vibrations or ultrasonic, sonic or infrasonic waves, not provided for in the preceding groups
Landscapes
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Measurement Of Mechanical Vibrations Or Ultrasonic Waves (AREA)
Abstract
The invention provides a method for detecting acoustic fingerprints of a transformer without power outage and early warning states. The method comprises the following aspects: the method comprises the steps of sensing and monitoring of on-line acquisition of acoustic fingerprints of the operation condition of the transformer, an acoustic fingerprint identification model of the transformer, dimension reduction and classification of the acoustic fingerprints of the transformer, and abnormal evaluation and fault location of the acoustic fingerprints of the transformer. Establishing an artificial intelligent transformer voiceprint state recognition method, extracting noise in real time, extracting features after background noise is removed, inputting the feature extraction as a loaded and trained equipment voiceprint model, giving equipment prediction judgment by the model, and giving early warning or decision information according to an equipment prediction judgment result. The invention can timely early warn in a non-power-off state and timely inform operation and maintenance personnel to quickly deal with the power-off state, thereby improving the safety performance of the equipment, realizing multi-azimuth, full-perception and early-warning equipment state modeling and monitoring, and leading the 'passive first-aid repair' to be 'active early warning'. The method is suitable for being applied as a transformer acoustic fingerprint uninterrupted power detection and state early warning method.
Description
Technical Field
The invention relates to a transformer in the field of power, in particular to a method for detecting acoustic fingerprints of a transformer without power outage and early warning a state.
Background
With the development of social economy and the advance of urbanization in China, the power supply load is continuously increased, and the power transformer is widely applied to residential areas, commercial areas and other places, so that the problems of operation maintenance and fault early warning caused by the large-scale application are more and more serious. Scholars at home and abroad strive to use methods such as infrared temperature measurement and transformer oil chromatographic component analysis as important basis of the running state of the transformer, but a complete and mature detection system is not formed at present in the analysis and research of the transformer state based on acoustic fingerprints. The noise of the transformer body caused by vibration is an urgent engineering problem to be solved in the power industry and is an important criterion for monitoring the state of new-generation electrical equipment. When the transformer equipment operates in an abnormal working state or a fault defect state, a certain amount of deformation can be generated on internal structural components of the transformer equipment, a vibration signal and an acoustic signal generated by the transformer can be changed along with the deformation, the change can be used as a characteristic parameter for state monitoring, and the operation defect and fault symptoms can be reflected to a certain extent through deep excavation of data characteristics.
Large power transformers play an important role in voltage conversion and power transmission. The transformer in the power system has large usage amount, various capacity grades and specifications and long operation time, so that the accident rate is correspondingly increased. Once the transformer fails, huge economic loss can be brought to the power grid, and personal safety of operation and maintenance personnel is endangered. Therefore, the working state of the transformer is effectively monitored, potential fault hidden dangers are found as soon as possible, and the problem of important attention of researchers in the power industry is solved. Among a plurality of transformer monitoring means, a non-electric quantity monitoring method represented by noise, temperature and vibration is widely applied because the non-electric quantity monitoring method does not generate direct electrical and magnetic connection with the tested equipment and has little influence on the safe operation of a power system. Since the transformer operates in an alternating electromagnetic environment, the periodic variations in the electric and magnetic fields cause periodic vibrations in the transformer core and windings, which are transmitted through multiple paths to the transformer tank and ultimately appear as noise through the tank vibrations. The transformer vibration in operation mainly comprises winding vibration, iron core vibration, cooling system vibration and the like. Mechanical waves generated by vibration are radiated outwards through media such as solid structural parts of the transformer, insulating oil, air and the like to form sound wave signals, and the sound wave signals contain a large amount of transformer working state information. 20Hz to 20k Hz is a sound frequency range which can be heard by human ears, and an experienced substation worker can directly judge whether the state is normal or not by hearing the sound of the running transformer by the ears. For a running transformer, the sound signal contains rich equipment state information, and when the transformer has abnormal working states such as overload, iron core looseness, direct current magnetic biasing, ferromagnetic resonance and the like, the characteristics of the sound signal emitted by the transformer can be correspondingly changed. The sound print monitoring of the transformer utilizes the sound pressure sensor to carry out quasi-continuous acquisition and analysis on the transformer body, can intuitively and effectively reflect the abnormal state of the transformer, and particularly can effectively reflect the abnormal state of the transformer by means of noise change under the conditions that the transformer experiences direct current magnetic biasing, excitation inrush current, power factor fluctuation and the like, so that the acoustic fingerprint monitoring of the transformer becomes an important non-electric quantity on-line monitoring means.
Disclosure of Invention
The invention provides a transformer acoustic fingerprint uninterrupted power detection and state early warning method, and aims to solve the problems that on-line fault monitoring or off-line fault detection of a transformer is generally based on visual identification, electrical and chemical detection and lacks multi-dimensional fault diagnosis. According to the method, by researching the vibration acoustic characteristics of the transformer in operation, analyzing the equipment voiceprint, and utilizing an artificial intelligence analysis algorithm, the state characteristics of the equipment under various operation conditions are mined, the corresponding relation and rule between the equipment normality and abnormality and various faults and mechanical vibration acoustic are extracted, a model suitable for large-scale power transformation equipment voiceprint data monitoring is established, effective state early warning is carried out, and the comprehensive capability and level of online monitoring of the equipment are improved. The technical problems of real-time online monitoring, fault diagnosis and early warning of the transformer are solved.
The technical scheme adopted by the invention for realizing the purpose is as follows:
a transformer acoustic fingerprint uninterrupted power detection and state early warning method comprises the following aspects: sensing monitoring of on-line acquisition of acoustic fingerprints of the operation condition of the transformer, an acoustic fingerprint identification model of the transformer, dimension reduction and classification of the acoustic fingerprints of the transformer, and abnormal evaluation and fault location of the acoustic fingerprints of the transformer; establishing an artificial intelligent transformer voiceprint state recognition method, extracting noise in real time, extracting features after background noise is removed, inputting the feature extraction as a loaded and trained equipment voiceprint model, giving equipment prediction judgment by the model, and giving early warning or decision information according to an equipment prediction judgment result.
In the sensing monitoring of the on-line acquisition of the acoustic fingerprints under the operation condition of the transformer, an active acceleration sensor is adopted to acquire vibration or sound signals, and the frequency response range of the active acceleration sensor is 20 Hz-1 MHz; the acoustic fingerprint detects the states of a winding and an iron core of the transformer by detecting the vibration signal transmitted to the box wall; the sound level meter is used for detecting vibration noise of the transformer/reactor and environmental noise of the transformer substation, and sound signals with the bandwidth of 10 Hz-10 kHz and the sound pressure level of 30-130 dB can be collected.
The transformer acoustic fingerprint identification model is an abstract description model of typical characteristics of the transformer noise state monitoring information formed by dynamic extraction of the transformer noise state monitoring information; the acquired and preprocessed model information is classified according to an 'electrical equipment layer', a 'monitoring object layer' and an 'application layer', a model construction rule is formulated according to the combination of expert knowledge, corresponding state monitoring data is retrieved through the rule to construct a transformer noise fingerprint, and the application layer is divided into 'global noise' and 'measuring point noise'; the two types of noise are respectively used for describing the noise state of the whole transformer and describing the local noise state of a noise measuring point of the transformer;
the transformer acoustic fingerprint dimension reduction and classification is based on MFCC feature vectors, and a transformer acoustic fingerprint modeling method is researched aiming at the transformer noise characteristics; firstly, preprocessing transformer noise, then extracting MFCC characteristic vectors, further performing weighting optimization on the characteristic vectors, reducing the dimension of the characteristic vectors by using a principal component analysis algorithm, and finally establishing a transformer voiceprint recognition model base by using an LVQ algorithm to realize effective recognition of transformer working conditions.
The transformer acoustic fingerprint abnormity evaluation and fault location are realized by applying a transformer acoustic fingerprint model to express, describe, compare and explain noise monitoring information.
Compared with the prior art, the invention has the following advantages and beneficial effects:
the intelligent diagnosis analysis and positioning of the faults of the large power transformer can be realized, the intelligent early warning is realized in a non-power-off state, and operation and maintenance personnel are informed to rapidly deal with the faults in time, so that the safety performance of the equipment is improved, the modeling and monitoring of the equipment state of multi-azimuth, full perception and early warning are realized, and the passive emergency repair is realized as active early warning. The power transformation reliability and the power quality are improved, and the product economy and other losses of power utilization enterprises and customers are reduced, so that the satisfaction degree of the customers is greatly improved, the power utilization promise of national power grids to China and common people 'you use power, i use your heart' is realized, and a good enterprise image is established in society. The intelligent diagnosis, analysis and positioning of the large transformer fault can be realized with less investment, the fault first-aid repair response capability of the power transformation equipment is improved, the power failure time is shortened, the increase of supply and expansion is facilitated, and the economic benefit is obvious. The method is suitable for being applied as a transformer acoustic fingerprint uninterrupted power detection and state early warning method.
Drawings
FIG. 1 is an overall architecture diagram of the present invention;
FIG. 2 is a flow chart of the acoustic feature extraction of the present invention;
FIG. 3 is a flow chart of the acoustic dimension reduction and fault detection of the present invention;
FIG. 4 is a diagram of an application of the transformer noise fingerprint model of the present invention.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. Although embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that changes, modifications, substitutions and alterations can be made in these embodiments without departing from the principles and spirit of the invention, the scope of which is defined in the appended claims and their equivalents. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
As shown in the figure, the method for detecting the acoustic fingerprint of the transformer without power failure and early warning the state comprises the following aspects: sensing monitoring of on-line acquisition of acoustic fingerprints of the operation condition of the transformer, an acoustic fingerprint identification model of the transformer, dimension reduction and classification of the acoustic fingerprints of the transformer, and abnormal evaluation and fault location of the acoustic fingerprints of the transformer; establishing an artificial intelligent transformer voiceprint state recognition method, extracting noise in real time, extracting features after background noise is removed, inputting the feature extraction as a loaded and trained equipment voiceprint model, giving equipment prediction judgment by the model, and giving early warning or decision information according to an equipment prediction judgment result.
In the sensing monitoring of the on-line acquisition of the acoustic fingerprints under the operation condition of the transformer, an active acceleration sensor is adopted to acquire vibration or sound signals, and the frequency response range of the active acceleration sensor is 20 Hz-1 MHz; the acoustic fingerprint detects the states of a winding and an iron core of the transformer by detecting the vibration signal transmitted to the box wall; the sound level meter is used for detecting vibration noise of the transformer/reactor and environmental noise of the transformer substation, and sound signals with the bandwidth of 10 Hz-10 kHz and the sound pressure level of 30-130 dB can be collected.
The transformer acoustic fingerprint identification model is an abstract description model of typical characteristics of the transformer noise state monitoring information formed by dynamic extraction of the transformer noise state monitoring information; the acquired and preprocessed model information is classified according to an 'electrical equipment layer', a 'monitoring object layer' and an 'application layer', a model construction rule is formulated according to the combination of expert knowledge, corresponding state monitoring data is retrieved through the rule to construct a transformer noise fingerprint, and the application layer is divided into 'global noise' and 'measuring point noise'; the two types of noise are respectively used for describing the noise state of the whole transformer and describing the local noise state of a noise measuring point of the transformer;
the transformer acoustic fingerprint identification model mainly comprises a voiceprint feature extraction part and a mode identification part, wherein the feature extraction has a large influence on the identification rate;
the method comprises the following steps of (1) a voiceprint feature extraction process, namely a voice signal → A/D conversion → filtering and normalization → pre-emphasis → framing and windowing → short-time Fourier change → voice signal features;
the pre-emphasis uses a first-order high-pass filter, the sampled and quantized waveform is represented as x [ n ], where n is a time index and 0.9< = a < =1.0, the filter expresses the formula in the time domain:
the framing and windowing are carried out, and in a quite short period of time, the sound signal is a stable signal, namely, the sound has the characteristic of short-time stability; in order to obtain a smooth sound signal, the sound signal needs to be framed and windowed:
and according to the amplitude-frequency characteristic of the power transformer sound frequency domain, dividing the frequency of each frame of sound after Fourier transformation into L sub-frequency bands according to blocks. And taking the mean value and the variance in each sub-frequency band in each frame of sound data as the characteristic value of the corresponding frequency band, thereby obtaining a group of characteristics representing the frame of sound data, and arranging the group of characteristics into a characteristic vector according to lines.
The voiceprint pattern recognition comprises a perception layer, a network layer, a platform layer and an application layer; the sensing layer mainly realizes high-precision acquisition of the voiceprint of the running transformer by using a 5G/wired transmission mode and the like, and simultaneously realizes initial diagnosis of the voiceprint by using the edge computing capability of a station end; the network layer uploads the audio collected by the voiceprint collection device to a voiceprint data center through a power private network; the platform layer has strong calculation and storage capacities, can perform training iteration of the algorithm and construction of a standard sample library, and performs upgrading iteration on the algorithm of the sensing layer device; the application layer provides application capabilities of a voiceprint recognition algorithm, such as capabilities of transformer audio event detection, magnetic bias abnormality diagnosis, operation state recognition and the like, and provides a visual interface of transformer state information and the like.
The transformer acoustic fingerprint dimension reduction and classification is based on MFCC feature vectors, and a transformer acoustic fingerprint modeling method is researched aiming at the transformer noise characteristics; firstly, preprocessing transformer noise, then extracting MFCC characteristic vectors, further performing weighting optimization on the characteristic vectors, reducing the dimension of the characteristic vectors by using a principal component analysis algorithm, and finally establishing a transformer voiceprint recognition model base by using an LVQ algorithm to realize effective recognition of transformer working conditions.
The transformer acoustic fingerprint abnormity evaluation and fault location are realized by applying a transformer acoustic fingerprint model to express, describe, compare and explain noise monitoring information.
The method has the advantages that the acoustic fingerprints of the transformer are subjected to uninterrupted power supply detection and state early warning, the neural network algorithm, statistics and acoustic technology are combined, the essential characteristics of the sound of the equipment are highlighted on the basis that sound signals and sound characteristics are effectively processed, the voiceprint characteristics of the equipment are easier to extract and identify, and therefore whether the running sound of the equipment is normal or not is accurately judged, and an analysis result is returned.
Finally, it should be noted that: although the present invention has been described in detail with reference to the foregoing embodiments, it will be apparent to those skilled in the art that modifications may be made to the embodiments or portions thereof without departing from the spirit and scope of the invention.
Claims (7)
1. A transformer acoustic fingerprint uninterrupted power detection and state early warning method is characterized by comprising the following steps: the method comprises the following aspects: sensing monitoring of on-line acquisition of acoustic fingerprints of the operation condition of the transformer, an acoustic fingerprint identification model of the transformer, dimension reduction and classification of the acoustic fingerprints of the transformer, and abnormal evaluation and fault location of the acoustic fingerprints of the transformer; establishing an artificial intelligent transformer voiceprint state recognition method, extracting noise in real time, extracting features after background noise is removed, inputting the feature extraction as a loaded and trained equipment voiceprint model, giving equipment prediction judgment by the model, and giving early warning or decision information according to an equipment prediction judgment result.
2. The method for detecting the uninterrupted power supply of the acoustic fingerprint and warning the state of the transformer according to claim 1, wherein the method comprises the following steps:
in the sensing monitoring of the on-line acquisition of the acoustic fingerprints under the operation condition of the transformer, an active acceleration sensor is adopted to acquire vibration or sound signals, and the frequency response range of the active acceleration sensor is 20 Hz-1 MHz; the acoustic fingerprint detects the states of a winding and an iron core of the transformer by detecting the vibration signal transmitted to the box wall; the sound level meter is used for detecting vibration noise of the transformer/reactor and environmental noise of the transformer substation, and sound signals with the bandwidth of 10 Hz-10 kHz and the sound pressure level of 30-130 dB can be collected.
3. The method for detecting the uninterrupted power supply of the acoustic fingerprint and warning the state of the transformer according to claim 1, wherein the method comprises the following steps:
the transformer acoustic fingerprint identification model is an abstract description model of typical characteristics of the transformer noise state monitoring information formed by dynamic extraction of the transformer noise state monitoring information; the acquired and preprocessed model information is classified according to an 'electrical equipment layer', a 'monitoring object layer' and an 'application layer', a model construction rule is formulated according to the combination of expert knowledge, corresponding state monitoring data is retrieved through the rule to construct a transformer noise fingerprint, and the application layer is divided into 'global noise' and 'measuring point noise'; the two types of noise are respectively used for describing the noise state of the whole transformer and describing the local noise state of a noise measuring point of the transformer.
4. The method for detecting the acoustic fingerprint of the transformer without power outage and warning the state of the transformer according to claim 3, wherein the method comprises the following steps:
the transformer acoustic fingerprint identification model mainly comprises a voiceprint feature extraction part and a mode identification part, wherein the feature extraction has a large influence on the identification rate;
the method comprises the following steps of (1) a voiceprint feature extraction process, namely a voice signal → A/D conversion → filtering and normalization → pre-emphasis → framing and windowing → short-time Fourier change → voice signal features;
the pre-emphasis uses a first-order high-pass filter, the sampled and quantized waveform is represented as x [ n ], where n is a time index and 0.9< = a < =1.0, the filter expresses the formula in the time domain:
the framing and windowing are carried out, and in a quite short period of time, the sound signal is a stable signal, namely, the sound has the characteristic of short-time stability; in order to obtain a smooth sound signal, the sound signal needs to be framed and windowed:
short-time Fourier transformation is carried out on each frame of sound data to obtain amplitude-frequency characteristics under the frequency domain of the sound data, and the frequency after the Fourier transformation of each frame of sound is divided into L sub-frequency bands according to the amplitude-frequency characteristics under the sound frequency domain of the power transformer;
taking the mean value and the variance in each sub-frequency band in each frame of sound data as the characteristic value of the corresponding frequency band, thereby obtaining a group of characteristics representing the frame of sound data, and arranging the group of characteristics into a characteristic vector according to lines;
the voiceprint pattern recognition comprises a perception layer, a network layer, a platform layer and an application layer; the sensing layer mainly realizes high-precision acquisition of the voiceprint of the running transformer by using a 5G/wired transmission mode and the like, and simultaneously realizes initial diagnosis of the voiceprint by using the edge computing capability of a station end; the network layer uploads the audio collected by the voiceprint collection device to a voiceprint data center through a power private network; the platform layer has strong calculation and storage capacities, can perform training iteration of the algorithm and construction of a standard sample library, and performs upgrading iteration on the algorithm of the sensing layer device; the application layer provides the application capability of the voiceprint recognition algorithm, such as the capability of transformer audio event detection, magnetic bias abnormality diagnosis and operation state recognition, and provides a transformer state information visualization interface.
5. The method for detecting the uninterrupted power supply of the acoustic fingerprint and warning the state of the transformer according to claim 1, wherein the method comprises the following steps:
the transformer acoustic fingerprint dimension reduction and classification is based on MFCC feature vectors, and a transformer acoustic fingerprint modeling method is researched aiming at the transformer noise characteristics; firstly, preprocessing transformer noise, then extracting MFCC characteristic vectors, further performing weighting optimization on the characteristic vectors, reducing the dimension of the characteristic vectors by using a principal component analysis algorithm, and finally establishing a transformer voiceprint recognition model base by using an LVQ algorithm to realize effective recognition of transformer working conditions.
6. The method for detecting the uninterrupted power supply of the acoustic fingerprint and warning the state of the transformer according to claim 1, wherein the method comprises the following steps:
the transformer acoustic fingerprint abnormity evaluation and fault location are realized by applying a transformer acoustic fingerprint model to express, describe, compare and explain noise monitoring information.
7. The method for detecting the uninterrupted power supply of the acoustic fingerprint and warning the state of the transformer according to claim 1, wherein the method comprises the following steps:
the method has the advantages that the acoustic fingerprints of the transformer are subjected to uninterrupted power supply detection and state early warning, the neural network algorithm, statistics and acoustic technology are combined, the essential characteristics of the sound of the equipment are highlighted on the basis that sound signals and sound characteristics are effectively processed, the voiceprint characteristics of the equipment are easier to extract and identify, and therefore whether the running sound of the equipment is normal or not is accurately judged, and an analysis result is returned.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111343860.1A CN114217149A (en) | 2021-11-14 | 2021-11-14 | Transformer acoustic fingerprint uninterrupted power detection and state early warning method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111343860.1A CN114217149A (en) | 2021-11-14 | 2021-11-14 | Transformer acoustic fingerprint uninterrupted power detection and state early warning method |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN114217149A true CN114217149A (en) | 2022-03-22 |
Family
ID=80697094
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202111343860.1A Pending CN114217149A (en) | 2021-11-14 | 2021-11-14 | Transformer acoustic fingerprint uninterrupted power detection and state early warning method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114217149A (en) |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115240691A (en) * | 2022-09-23 | 2022-10-25 | 山西振中电力股份有限公司 | Substation equipment running state monitoring control system based on data analysis |
| CN116359642A (en) * | 2023-03-10 | 2023-06-30 | 湖南金烽信息科技有限公司 | Transformer running state 5G intelligent monitoring system and method |
| CN117153193A (en) * | 2023-10-30 | 2023-12-01 | 国网安徽省电力有限公司电力科学研究院 | Power equipment fault voiceprint recognition method integrating physical characteristics and data diagnosis |
| CN117894317A (en) * | 2024-03-14 | 2024-04-16 | 沈阳智帮电气设备有限公司 | Box-type transformer on-line monitoring method and system based on voiceprint analysis |
Citations (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112201260A (en) * | 2020-09-07 | 2021-01-08 | 北京科技大学 | Transformer running state online detection method based on voiceprint recognition |
-
2021
- 2021-11-14 CN CN202111343860.1A patent/CN114217149A/en active Pending
Patent Citations (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112201260A (en) * | 2020-09-07 | 2021-01-08 | 北京科技大学 | Transformer running state online detection method based on voiceprint recognition |
Non-Patent Citations (4)
| Title |
|---|
| 侯增起: "基于声音特征的变电设备故障分类与定位方法研究", 《中国优秀硕士论文全文数据库工程科技辑》, pages 10 - 13 * |
| 尹康涌: "油浸式变压器噪声状态监测关键技术研究与应用", 《中国优秀硕士论文全文数据库 工程科技辑》, pages 15 * |
| 李 鹏: "变电设备智能传感与状态感知技术及应用", 《高压电技术》, pages 3097 - 3113 * |
| 林春清: "面向电力变压器的声纹智能诊断装置设计与应用", 《传感技术学报》, pages 1412 - 1420 * |
Cited By (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115240691A (en) * | 2022-09-23 | 2022-10-25 | 山西振中电力股份有限公司 | Substation equipment running state monitoring control system based on data analysis |
| CN115240691B (en) * | 2022-09-23 | 2022-12-06 | 山西振中电力股份有限公司 | Substation equipment running state monitoring control system based on data analysis |
| CN116359642A (en) * | 2023-03-10 | 2023-06-30 | 湖南金烽信息科技有限公司 | Transformer running state 5G intelligent monitoring system and method |
| CN116359642B (en) * | 2023-03-10 | 2024-01-23 | 湖南金烽信息科技有限公司 | Transformer running state 5G intelligent monitoring system and method |
| CN117153193A (en) * | 2023-10-30 | 2023-12-01 | 国网安徽省电力有限公司电力科学研究院 | Power equipment fault voiceprint recognition method integrating physical characteristics and data diagnosis |
| CN117153193B (en) * | 2023-10-30 | 2024-02-13 | 国网安徽省电力有限公司电力科学研究院 | Power equipment fault voiceprint recognition method integrating physical characteristics and data diagnosis |
| CN117894317A (en) * | 2024-03-14 | 2024-04-16 | 沈阳智帮电气设备有限公司 | Box-type transformer on-line monitoring method and system based on voiceprint analysis |
| CN117894317B (en) * | 2024-03-14 | 2024-05-24 | 沈阳智帮电气设备有限公司 | Box-type transformer on-line monitoring method and system based on voiceprint analysis |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN114217149A (en) | Transformer acoustic fingerprint uninterrupted power detection and state early warning method | |
| CN112201260B (en) | Transformer running state online detection method based on voiceprint recognition | |
| CN212207527U (en) | Transformer on-line monitoring device based on multi-source information fusion | |
| CN113124929A (en) | Transformer substation multi-parameter signal acquisition comprehensive analysis system and method | |
| CN111638028A (en) | High-voltage parallel reactor mechanical state evaluation method based on vibration characteristics | |
| CN103487749A (en) | On-line monitoring and diagnosing system and method for mechanical state of high-voltage circuit breaker | |
| WO2012171300A1 (en) | Sound abnormality detection system for power device and method thereof | |
| CN108362966B (en) | High-precision noise online monitoring method and system for oil immersed transformer | |
| CN102931728B (en) | Online identification and visualization method for power grid disturbances based on multi-resolution wavelet analysis | |
| CN109443190B (en) | Transient traveling wave-based transformer winding deformation online monitoring method and device | |
| CN105626502A (en) | Plunger pump health assessment method based on wavelet packet and Laplacian Eigenmap | |
| CN112305462A (en) | System for recognizing typical faults of transformer based on transformer sound | |
| CN115358110A (en) | Transformer fault detection system based on acoustic sensor array | |
| CN110299758A (en) | A kind of comprehensive on-line monitoring and diagnosis system of substation | |
| CN114046869A (en) | Broadband oscillation information online monitoring method and system based on daily disturbance response of power system | |
| CN115406522A (en) | Power plant equipment running state research and application based on voiceprint recognition | |
| Yang et al. | Transient fault diagnosis of track circuit based on MFCC-DTW | |
| CN117932525A (en) | Method, system, equipment and medium for identifying acoustic fiber faults of hydroelectric generating set | |
| CN202091172U (en) | Device for monitoring state and analyzing reliability of gas compressor | |
| CN116879727A (en) | Real-time monitoring method and system based on current characteristics of opening and closing coil of circuit breaker | |
| CN114091533B (en) | Transformer noise identification and reverse reduction method and medium based on laser vibration measurement | |
| CN116243230A (en) | On-line fault diagnosis method for voltage transformer | |
| CN115468751A (en) | Method and device for sound collection and defect identification of transformer | |
| Lai et al. | Study on vibration monitoring and multi-feature analysis of oil-immersed power transformer in arctic area | |
| Dong | Application of Power System Wide-Band Oscillation Monitoring and Alarm System Based on PMU Data |
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 | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20220322 |