CN117095695A - Wide-area voiceprint compression acquisition method and system for transformer body - Google Patents
Wide-area voiceprint compression acquisition method and system for transformer body Download PDFInfo
- Publication number
- CN117095695A CN117095695A CN202311352600.XA CN202311352600A CN117095695A CN 117095695 A CN117095695 A CN 117095695A CN 202311352600 A CN202311352600 A CN 202311352600A CN 117095695 A CN117095695 A CN 117095695A
- Authority
- CN
- China
- Prior art keywords
- sound
- curve
- analysis
- frequency
- curves
- 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
- 238000000034 method Methods 0.000 title claims abstract description 79
- 238000007906 compression Methods 0.000 title claims abstract description 25
- 230000006835 compression Effects 0.000 title claims abstract description 25
- 238000004458 analytical method Methods 0.000 claims abstract description 95
- 238000012216 screening Methods 0.000 claims abstract description 40
- 230000002159 abnormal effect Effects 0.000 claims abstract description 37
- 230000008569 process Effects 0.000 claims abstract description 30
- 238000004519 manufacturing process Methods 0.000 claims abstract description 13
- 230000015572 biosynthetic process Effects 0.000 claims abstract description 11
- 238000003786 synthesis reaction Methods 0.000 claims abstract description 11
- 230000015654 memory Effects 0.000 claims description 24
- 238000012545 processing Methods 0.000 claims description 20
- 239000003550 marker Substances 0.000 claims description 15
- 230000002776 aggregation Effects 0.000 claims description 12
- 238000004220 aggregation Methods 0.000 claims description 12
- 238000003860 storage Methods 0.000 claims description 9
- 238000000354 decomposition reaction Methods 0.000 claims description 7
- 238000012163 sequencing technique Methods 0.000 claims description 4
- 230000002194 synthesizing effect Effects 0.000 claims description 3
- 230000001419 dependent effect Effects 0.000 abstract description 4
- 230000005856 abnormality Effects 0.000 abstract description 2
- 230000006870 function Effects 0.000 description 8
- 238000010586 diagram Methods 0.000 description 7
- 238000003745 diagnosis Methods 0.000 description 6
- 238000004891 communication Methods 0.000 description 5
- 238000011156 evaluation Methods 0.000 description 5
- 238000004364 calculation method Methods 0.000 description 4
- 230000032683 aging Effects 0.000 description 3
- 230000008878 coupling Effects 0.000 description 3
- 238000010168 coupling process Methods 0.000 description 3
- 238000005859 coupling reaction Methods 0.000 description 3
- 238000013461 design Methods 0.000 description 3
- 238000001228 spectrum Methods 0.000 description 3
- 230000003068 static effect Effects 0.000 description 3
- 230000001360 synchronised effect Effects 0.000 description 3
- 238000004590 computer program Methods 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 238000012544 monitoring process Methods 0.000 description 2
- 238000004804 winding Methods 0.000 description 2
- XEEYBQQBJWHFJM-UHFFFAOYSA-N Iron Chemical group [Fe] XEEYBQQBJWHFJM-UHFFFAOYSA-N 0.000 description 1
- 238000005299 abrasion Methods 0.000 description 1
- 238000003491 array Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 238000004422 calculation algorithm Methods 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 238000012512 characterization method Methods 0.000 description 1
- 238000013144 data compression Methods 0.000 description 1
- 230000003111 delayed effect Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000018109 developmental process Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 230000004927 fusion Effects 0.000 description 1
- 238000012423 maintenance Methods 0.000 description 1
- 239000011159 matrix material Substances 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 238000003672 processing method Methods 0.000 description 1
- 230000008439 repair process Effects 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 230000004044 response Effects 0.000 description 1
- 238000005070 sampling Methods 0.000 description 1
- 239000007787 solid Substances 0.000 description 1
Classifications
-
- G—PHYSICS
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10L—SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING
- G10L25/00—Speech or voice analysis techniques not restricted to a single one of groups G10L15/00 - G10L21/00
- G10L25/03—Speech or voice analysis techniques not restricted to a single one of groups G10L15/00 - G10L21/00 characterised by the type of extracted parameters
- G10L25/18—Speech or voice analysis techniques not restricted to a single one of groups G10L15/00 - G10L21/00 characterised by the type of extracted parameters the extracted parameters being spectral information of each sub-band
-
- G—PHYSICS
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10L—SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING
- G10L21/00—Speech or voice signal processing techniques to produce another audible or non-audible signal, e.g. visual or tactile, in order to modify its quality or its intelligibility
- G10L21/04—Time compression or expansion
-
- G—PHYSICS
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10L—SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING
- G10L21/00—Speech or voice signal processing techniques to produce another audible or non-audible signal, e.g. visual or tactile, in order to modify its quality or its intelligibility
- G10L21/06—Transformation of speech into a non-audible representation, e.g. speech visualisation or speech processing for tactile aids
- G10L21/10—Transforming into visible information
- G10L21/12—Transforming into visible information by displaying time domain information
-
- G—PHYSICS
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10L—SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING
- G10L21/00—Speech or voice signal processing techniques to produce another audible or non-audible signal, e.g. visual or tactile, in order to modify its quality or its intelligibility
- G10L21/06—Transformation of speech into a non-audible representation, e.g. speech visualisation or speech processing for tactile aids
- G10L21/10—Transforming into visible information
- G10L21/14—Transforming into visible information by displaying frequency domain information
-
- G—PHYSICS
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10L—SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING
- G10L25/00—Speech or voice analysis techniques not restricted to a single one of groups G10L15/00 - G10L21/00
- G10L25/48—Speech or voice analysis techniques not restricted to a single one of groups G10L15/00 - G10L21/00 specially adapted for particular use
- G10L25/51—Speech or voice analysis techniques not restricted to a single one of groups G10L15/00 - G10L21/00 specially adapted for particular use for comparison or discrimination
-
- G—PHYSICS
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10L—SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING
- G10L25/00—Speech or voice analysis techniques not restricted to a single one of groups G10L15/00 - G10L21/00
- G10L25/48—Speech or voice analysis techniques not restricted to a single one of groups G10L15/00 - G10L21/00 specially adapted for particular use
- G10L25/69—Speech or voice analysis techniques not restricted to a single one of groups G10L15/00 - G10L21/00 specially adapted for particular use for evaluating synthetic or decoded voice signals
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02E—REDUCTION OF GREENHOUSE GAS [GHG] EMISSIONS, RELATED TO ENERGY GENERATION, TRANSMISSION OR DISTRIBUTION
- Y02E60/00—Enabling technologies; Technologies with a potential or indirect contribution to GHG emissions mitigation
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Audiology, Speech & Language Pathology (AREA)
- Computational Linguistics (AREA)
- Signal Processing (AREA)
- Health & Medical Sciences (AREA)
- Human Computer Interaction (AREA)
- Acoustics & Sound (AREA)
- Multimedia (AREA)
- Quality & Reliability (AREA)
- Data Mining & Analysis (AREA)
- Spectroscopy & Molecular Physics (AREA)
- Measurement Of Mechanical Vibrations Or Ultrasonic Waves (AREA)
Abstract
The invention relates to a wide-area voiceprint compression acquisition method and a wide-area voiceprint compression acquisition system for a transformer body, wherein the method comprises responding to an acquired sound sample, transferring the sound sample into a frequency domain for analysis, removing a standard sound curve, positioning a sound domain sound curve, and grouping the sound curves in a screening sample group according to sound production positions; transferring the sound curve in one standard sound sample group into a time domain for synthesis to obtain an analysis sound curve; determining the occurrence frequency of the repeated segments on the analysis sound curve; the number of abnormal sound curves in the repeated segment is counted, and an abnormal characteristic sound curve based on the sounding position is generated by using the abnormal sound curve. According to the acquisition method and system disclosed by the invention, possible faults of the transformer body are found by introducing position judgment and abnormality judgment in the acquisition process, and the judgment is not dependent on a perfect sound model library any more, so that a more accurate judgment result is obtained.
Description
Technical Field
The invention relates to the technical field of data processing, in particular to a wide-area voiceprint compression acquisition method and system for a transformer body.
Background
The current transformer acoustic diagnosis method mainly comprises the following steps: noise diagnosis method and ultrasonic diagnosis method. The noise diagnosis method performs fault diagnosis using noise emitted from the apparatus. When the state of a part or a component of the device changes due to abrasion, aging and the like, the characteristics of the acoustic signal of the device also change correspondingly. By monitoring these characteristics, the status of the device can be evaluated and faults can be found in time.
The noise diagnosis method can realize all-weather unmanned monitoring by means of the sound collection terminal, has stronger practicability, and simultaneously, along with the development of MEMS technology, the sound collection terminal makes great progress in the aspects of miniaturization and high precision.
However, in terms of voice recognition, further research is required, and the specific reason is that the establishment of the voice model library is delayed from data acquisition, so that accurate comparison cannot be realized in the comparison process, and meanwhile, for the known voice model, when parameters such as the size and the internal structure of the transformer are changed, inaccuracy of the comparison result is also caused.
Disclosure of Invention
The invention provides a wide-area voiceprint compression acquisition method and a wide-area voiceprint compression acquisition system for a transformer body, which discover possible faults of the transformer body by introducing position judgment and abnormality judgment in the acquisition process, wherein the judgment is not dependent on a perfect sound model library any more, and a more accurate judgment result is achieved.
The above object of the present invention is achieved by the following technical solutions:
in a first aspect, the present invention provides a wide-area voiceprint compression acquisition method for a transformer body, including:
responding to the acquired sound sample, transferring the sound sample into a frequency domain for analysis to obtain a sound sample group, wherein the sound sample group comprises a plurality of sound curves;
removing standard sound curves in the sound sample group to obtain a screening sample group;
positioning the sound curve in the screening sample group to obtain a sound producing position;
grouping the sound curves in the screening sample groups according to the sound emission positions to obtain a plurality of standard sound sample groups, wherein the sound curves in each standard sound sample group belong to the same sound emission position;
transferring the sound curve in one standard sound sample group into a time domain for synthesis to obtain an analysis sound curve;
determining the occurrence frequency of the repeated segments on the analysis sound curve;
transferring the repeated segments with the occurrence frequency meeting the requirement into a frequency domain for analysis, and decomposing the repeated segments into a plurality of frequency domains in the analysis process, wherein the amplitude of a sound curve with the frequency more than or equal to a set proportion in each frequency domain tends to be consistent;
Counting the number of abnormal sound curves in the repeated section; and
an abnormal sound curve is generated based on the sound emission position using the abnormal sound curve.
In a possible implementation manner of the first aspect, the sound samples are from a plurality of sound collection terminals;
positioning the sound curve in the screening sample group, wherein obtaining the sound producing position comprises:
positioning by using a sound curve in a screening sample group to obtain a first position; and
and fusing the plurality of first positions to obtain the sounding position.
In a possible implementation manner of the first aspect, when one sound curve in the screening sample group is associated with only one sound producing position, the sound curve is marked as a marked sound curve;
the marker sound profile is associated with another sound producing location according to a frequency, the marker sound profile being the same frequency as the sound profile associated with the other sound producing location, the magnitude of the marker sound profile being less than the magnitude of the sound profile associated with the other sound producing location.
In a possible implementation manner of the first aspect, determining the repeated segment on the analysis sound curve includes:
sequentially dividing the analysis sound curve into a plurality of sub analysis sound curves;
Transferring each sub-analysis sound curve into a frequency domain for decomposition to obtain a plurality of parameter sets, wherein each parameter set comprises frequency, amplitude and quantity;
comparing the similarity of any two parameter sets; and
and when the similarity value of the two parameter sets is larger than the first reference value, marking the sub-analysis sound curves corresponding to the two parameter sets as repeated segments.
In a possible implementation manner of the first aspect, when the similarity value of the two parameter sets is smaller than or equal to the first reference value and larger than the second reference value, the lengths of the sub analysis sound curves corresponding to the two parameter sets are adjusted and the process of determining the repeated segments on the analysis sound curve is repeated.
In a possible implementation manner of the first aspect, the adjusting includes changing a length of the sub-analysis sound curve and/or moving a dividing position of the sub-analysis sound curve.
In a possible implementation manner of the first aspect, decomposing the repeated segment into a plurality of frequency domains in the parsing includes:
sequencing the frequencies in the repeated segments obtained through analysis according to the size of the frequency values; and
grouping the ordered frequency values according to the aggregation degree to obtain a plurality of frequency domains;
Wherein frequency values located between two adjacent frequency domains are all divided into adjacent preceding or following frequency domains.
In a second aspect, the present invention provides a wide-area voiceprint compression acquisition apparatus for a transformer body, comprising:
the analysis unit is used for responding to the acquired sound samples, transferring the sound samples into a frequency domain to analyze the sound samples, and obtaining a sound sample group, wherein the sound sample group comprises a plurality of sound curves;
the rejecting unit is used for rejecting the standard sound curve in the sound sample group to obtain a screening sample group;
the first positioning unit is used for positioning the sound curves in the screening sample group to obtain sound production positions;
the first grouping unit is used for grouping the sound curves in the screening sample groups according to the sound production positions to obtain a plurality of standard sound sample groups, and the sound curves in each standard sound sample group belong to the same sound production position;
the first synthesis unit is used for converting the sound curve in one standard sound sample group into a time domain for synthesis to obtain an analysis sound curve;
a processing unit for determining a repeating segment on the analysis sound curve and a frequency of occurrence of the repeating segment;
The second grouping unit is used for transferring the repeated section with the occurrence frequency meeting the requirement into a frequency domain for analysis, and decomposing the repeated section into a plurality of frequency domains in the analysis process, wherein the amplitude of the sound curve with the frequency more than or equal to the set proportion in each frequency domain tends to be consistent;
a statistics unit for counting the number of abnormal sound curves in the repeated section; and
and a second synthesizing unit for generating an abnormal characteristic sound curve based on the sound emission position using the abnormal sound curve.
In a third aspect, the present invention provides a wide-area voiceprint compression acquisition system for a transformer body, the system comprising:
one or more memories for storing instructions; and
one or more processors configured to invoke and execute the instructions from the memory, to perform the method as described in the first aspect and any possible implementation of the first aspect.
In a fourth aspect, the present invention provides a computer-readable storage medium comprising:
a program which, when executed by a processor, performs a method as described in the first aspect and any possible implementation of the first aspect.
In a fifth aspect, the present invention provides a computer program product comprising program instructions which, when executed by a computing device, perform a method as described in the first aspect and any possible implementation of the first aspect.
In a sixth aspect, the present invention provides a chip system comprising a processor for implementing the functions involved in the above aspects, e.g. generating, receiving, transmitting, or processing data and/or information involved in the above methods.
The chip system can be composed of chips, and can also comprise chips and other discrete devices.
In one possible design, the system on a chip also includes memory to hold the necessary program instructions and data. The processor and the memory may be decoupled, provided on different devices, respectively, connected by wire or wirelessly, or the processor and the memory may be coupled on the same device.
Compared with the prior art, the invention has the following beneficial effects:
the wide-area voiceprint compression acquisition method and system for the transformer body provided by the invention can firstly perform rejection processing on the collected sound curve, and the rejection purpose is to remove the sound curve generated by the transformer body in the normal working process. And then positioning the rest sound curves, or positioning the collected sound curves, and then removing the sound curves to obtain the analysis sound curves. The analysis sound curve is then determined to analyze the repeated segments on the sound curve and the occurrence frequencies of the repeated segments, and then an abnormal sound curve is found by analyzing the repeated segments and an abnormal characteristic sound curve based on the sound emission position is generated using the abnormal sound curve. The processing mode adopts a fuzzy judgment mode, and the abnormal sound of the transformer body is collected by combining the position and the abnormal characteristic sound curve at the position, so that the judgment process is not dependent on a perfect sound model library any more, and a more accurate judgment result is obtained.
Drawings
Fig. 1 is a schematic block diagram of a step flow of a first part of a wide-area voiceprint compression acquisition method provided by the present invention.
Fig. 2 is a schematic block diagram of a step flow of a second part of a wide-area voiceprint compression acquisition method provided by the present invention.
Fig. 3 is a schematic diagram of a sounding site according to the present invention.
Fig. 4 is a schematic illustration of another proposed sound producing location according to the present invention.
FIG. 5 is a schematic illustration of a determination of a repeating segment on an analytical sound curve provided by the present invention.
Fig. 6 is a schematic diagram of a tuning sub-analysis sound curve according to the present invention.
Fig. 7 is a schematic diagram of another tuning sub-analysis sound curve provided by the present invention.
Fig. 8 is a schematic diagram of still another tuning sub-analysis sound curve according to the present invention.
Fig. 9 is a schematic diagram of a method for decomposing a repeating segment into a plurality of frequency domains according to the present invention.
Detailed Description
The technical scheme in the invention is further described in detail below with reference to the accompanying drawings.
To a broad extent, voiceprint compression acquisition can be interpreted as the completion of the data compression process during sampling, with the aim of giving the full description of the sampled location as much as possible with a smaller amount of data.
The invention discloses a wide-area voiceprint compression acquisition method for a transformer body, which is mainly used for acquiring sound generated in the operation process of the transformer body, screening and compressing acquired data in the acquisition process at the same time, so as to obtain more accurate sample data, wherein the sample data is sent to a cloud, and the cloud analyzes the sample data and then judges the operation state of the transformer body corresponding to the sample data.
The invention discloses a wide-area voiceprint compression acquisition method for a transformer body, referring to fig. 1 and 2, the acquisition method comprises the following steps:
s101, responding to an acquired sound sample, transferring the sound sample into a frequency domain for analysis to obtain a sound sample group, wherein the sound sample group comprises a plurality of sound curves;
s102, eliminating standard sound curves in a sound sample group to obtain a screening sample group;
s103, positioning sound curves in the screening sample group to obtain sound production positions;
s104, grouping sound curves in the screening sample groups according to sound production positions to obtain a plurality of standard sound sample groups, wherein the sound curves in each standard sound sample group belong to the same sound production position;
S105, transferring the sound curve in one standard sound sample group into a time domain for synthesis to obtain an analysis sound curve;
s106, determining and analyzing repeated segments on the sound curve and the occurrence frequency of the repeated segments;
s107, transferring the repeated section with the occurrence frequency meeting the requirement into a frequency domain for analysis, and decomposing the repeated section into a plurality of frequency domains in the analysis process, wherein the amplitude of a sound curve with the frequency domain being more than or equal to a set proportion tends to be consistent;
s108, counting the number of abnormal sound curves in the repeated section; and
s109, generating an abnormal characteristic sound curve based on the sounding position by using the abnormal sound curve.
The wide-area voiceprint compression acquisition method for the transformer body is applied to a sound acquisition terminal installed on the transformer body or an edge calculation server in data communication with the sound acquisition terminal, and the sound acquisition terminal or the edge calculation server in data communication with the sound acquisition terminal analyzes and processes a sound sample acquired by the sound acquisition terminal, namely the content in the steps S101 to S109.
For convenience of description, the sound collection terminal or the edge computing server that performs data communication with the sound collection terminal is collectively referred to as a data processing end.
Specifically, in step S101, in response to the acquired sound sample, the data processing end first converts the sound sample into a frequency domain to obtain a sound sample group, where the analysis uses fourier transform, and after the fourier transform processing, the sound sample becomes a sound sample group composed of a plurality of frequency-fixed and amplitude-fixed sound sample groups, that is, the sound sample group described in the present invention includes a plurality of sound curves.
In step S102, the standard sound curve in the sound sample set is first removed to obtain a screening sample set, where the standard sound curve refers to a curve corresponding to the sound generated by the transformer in normal operation. For the screening sample set, in step S103, the sound curves in the screening sample set are located to obtain the sounding position.
It will be appreciated that the transformer herein produces a curve corresponding to sound during normal operation, and also includes harmonics. For example, the main frequency spectrum component of the vibration of the iron core and the vibration of the winding is 100Hz, and the main frequency spectrum component of the vibration of the winding is formed by the propagation and superposition of a plurality of sound sources through different paths, so that the main frequency spectrum component of the vibration of the transformer is mixed with the higher harmonic component. Modeling various faults generated in the operation process of the transformer is difficult, but modeling sound generated by parts in the transformer in the operation process is easier to realize technically.
The function of obtaining the sound producing position is to determine which position or which part of the transformer body produces the sound curve in the screening sample group, and the function of determining the position is to locate the sound curve in the screening sample group so as to obtain an accurate sound producing position.
It should be understood that the transformer body has a plurality of parts therein, and the parts have a silent working state (only the sound collecting terminal does not detect the sound as a judgment standard) and a sound working state in the running process, and the sound working state is divided into a normal working state and an abnormal working state.
By means of the accurate sounding position, the running state of the transformer body can be judged more accurately, and after accurate parts are positioned, the information carried by the sound curves in the screening sample group can be judged more accurately according to the specific conditions of the parts.
In step S104, the sound curves in the screening sample sets are grouped according to the sound positions to obtain a plurality of standard sound sample sets, where the sound curves in each standard sound sample set belong to the same sound position.
The main purpose of this step is to determine the correspondence between the sound curve and the sound emission position. It should be understood that the sound collection terminal is mounted on the outer wall of the transformer body and receives various sounds within the coverage area, which may be mixed together, so that analysis and processing cannot be performed.
Therefore, in the invention, the sound curves are grouped in a mode of determining the corresponding relation between the sound curves and the sound producing positions, and a plurality of standard sound sample groups are obtained by grouping, and the sound curves in each standard sound sample group belong to the same sound producing position.
Based on the different sound emission locations, the sound curve may be further processed.
For the determination of the sounding position, the sound collecting terminal may use a matrix microphone, or determine the correspondence between the sound curve and the sounding position by means of a plurality of sound collecting terminals.
Of course, the sounding position of the sound sample may be processed in the initial step, and after determining the sounding position, the sound sample is transferred to the frequency domain for analysis.
In step S105, the sound curves in the standard sound sample set are transferred to the time domain for synthesis to obtain an analysis sound curve, where the analysis sound curve reflects the characteristics of the sound generated at a sound generating position, and the characteristics are used to analyze whether an abnormal situation occurs at the sound generating position.
In step S106, the repetition period and the occurrence frequency of the repetition period on the analysis sound curve are determined, and the repetition period means that a process is cycled or a state occurs multiple times in order to find possible problems in the transformer body, and if the cycle number and the occurrence number meet the set requirements, the repetition period on the analysis sound curve is subjected to a focus analysis.
Since it was mentioned in the foregoing that the standard sound curve in the sound sample has been rejected, there may be a fault inside the transformer body if the remaining curve in the sound sample can also occur in a regular manner at this time.
In step S107, the repeated segment whose appearance frequency meets the requirement is transferred to the frequency domain for analysis, and the repeated segment is decomposed into a plurality of frequency domains in the analysis process, and the amplitude of the sound curve with the frequency more than or equal to the set proportion in each frequency domain tends to be consistent.
The purpose of this step is to group the sound curves in the repeating segments, one for each frequency domain. The frequency of the sound curve in a frequency domain has a certain concentration or is within a fixed range.
Meanwhile, the amplitudes of the sound curves with the set proportion or more in each frequency domain tend to be consistent. The frequency and the amplitude are concentrated, so that the sound which appears inside the characterization transformer body has certain stability. Of course, the problem of part aging, which is inevitably encountered here, is solved by routine maintenance and repair, because of the stability of the sound generated by the part aging.
In step S108, the number of abnormal sound curves in the repeated segment, which are sound curves in which the frequency and amplitude of the partial sound curves in each of the frequency domains mentioned in the foregoing are in discrete states, is counted.
Here, the sound curve in the concentrated state refers to a sound curve in which the frequency and the amplitude in each frequency domain tend to agree, and the sound curve in the discrete state refers to a sound curve remaining in one frequency domain.
In step S109, an abnormal sound curve based on the sounding position is generated by using the abnormal sound curve, the abnormal sound curve obtained in the step is sent to the cloud as sample data, and the cloud analyzes the sample data and then determines the operation state of the transformer body corresponding to the sample data.
In the whole, the wide-area voiceprint compression acquisition method for the transformer body provided by the invention can firstly perform rejection processing on the collected sound curve, and the rejection purpose is to remove the sound curve generated by the transformer body in the normal working process. And then positioning the rest sound curves, or positioning the collected sound curves, and then removing the sound curves to obtain the analysis sound curves.
The analysis sound curve is then determined to analyze the repeated segments on the sound curve and the occurrence frequencies of the repeated segments, and then an abnormal sound curve is found by analyzing the repeated segments and an abnormal characteristic sound curve based on the sound emission position is generated using the abnormal sound curve.
The processing mode adopts a fuzzy judgment mode, and the abnormal sound of the transformer body is collected by combining the position and the abnormal characteristic sound curve at the position, so that the judgment process is not dependent on a perfect sound model library any more, and a more accurate judgment result is obtained.
In some examples, the sound sample is derived from a plurality of sound collection terminals, i.e. a plurality of sound collection terminals are simultaneously mounted at different locations on the transformer body, which together analyze the sound generated by the transformer body during operation.
In some examples, the process of locating the sound curve in the screening sample set to obtain the sound location is as follows:
s201, positioning by using a sound curve in a screening sample group to obtain a first position; and
s202, fusing the plurality of first positions to obtain sounding positions.
In the foregoing, it is mentioned that, for the sound curves, the grouping needs to be performed by using a positioning manner, when a plurality of sound collecting terminals are used, there are cases where the plurality of sound collecting terminals simultaneously receive the sound generated at the same position, at this time, the sound curves in each screening sample group are positioned to obtain a first position, and then the plurality of first positions are fused.
In some possible implementations, the process of fusing the plurality of first positions is to sum the coordinates of the plurality of first positions and calculate an average value, referring to fig. 3, three coordinates are obtained by the average value calculation to obtain coordinates (X 0 ，Y 0 ）。
In other possible implementations, the process of fusing the plurality of first positions is to project the coordinates of the plurality of first positions in a three-dimensional space, and create a sphere with a minimum radius, where the coordinates of all the first positions are located in the sphere, and the coordinates of the center of the sphere are used as the sounding position, as shown in fig. 4.
In some examples, when a sound curve in the screening sample set is associated with only one utterance position, the sound curve is noted as a labeled sound curve;
the marker sound profile is associated with another sound producing location according to a frequency, the marker sound profile being the same frequency as the sound profile associated with the other sound producing location, the magnitude of the marker sound profile being less than the magnitude of the sound profile associated with the other sound producing location.
In particular, the presence of a cavity or the like inside the transformer body results in the possibility of a reflection situation on the propagation path of the sound, which in the present invention corresponds to the description that one sound curve in the screening sample group is associated with only one sound emission position.
The specific solution is as follows: the marker sound profile is associated with another sound producing location according to a frequency, the marker sound profile being the same frequency as the sound profile associated with the other sound producing location, the magnitude of the marker sound profile being less than the magnitude of the sound profile associated with the other sound producing location. The processing mode can effectively reduce the number of sounding positions, and meanwhile, the data contained in the sound sample at one sounding position is more abundant.
In some examples, determining the repeated segments on the analysis sound curve includes the steps of:
s301, sequentially dividing the analysis sound curves into a plurality of sub analysis sound curves;
s302, transferring each sub-analysis sound curve into a frequency domain for decomposition to obtain a plurality of parameter sets, wherein each parameter set comprises frequency, amplitude and quantity;
s303, comparing the similarity of any two parameter sets; and
s304, when the similarity value of the two parameter sets is larger than the first reference value, marking the sub-analysis sound curves corresponding to the two parameter sets as repeated segments.
In steps S301 to S304, referring to fig. 5, the analysis sound curves are first divided into a plurality of sub-analysis sound curves sequentially, and then each sub-analysis sound curve is transferred into a frequency domain for decomposition, so as to obtain a plurality of parameter sets, wherein each parameter set includes frequency, amplitude and number.
The parameter set is used to evaluate the similarity of the two sub-analysis sound curves. It should be understood that the sub-analysis sound curves are represented in a curve manner, and for similarity evaluation of two curves, different evaluation results can be obtained by using different evaluation manners, and even a point-by-point calculation data processing manner is required in order to improve the accuracy of the evaluation results.
In order to avoid the limitations of these processing methods, the present invention proposes a method of evaluating using parameter sets (including frequency, amplitude, and number), which can quantify sub-analysis sound curves using data, and have unique evaluation criteria.
And when the similarity value of the two parameter sets is larger than the first reference value, marking the sub-analysis sound curves corresponding to the two parameter sets as repeated segments. The first reference value herein may be understood that the parameter sets include a plurality of sets of frequencies, magnitudes, and numbers, and for two sets of frequencies, magnitudes, and numbers respectively belonging to two parameter sets, whether the two sets of frequencies, magnitudes, and numbers are similar may be directly determined by comparing the values.
First reference valueIt is necessary to determine the number of sets based on the frequency, amplitude and number of sets in two sets of parameters, the sum of the number of sets in the two sets of parameters being N 1 The sum of the similar groups is N 2 ，N 2 / N 1 For example, if Q is set to 0.7 or more, the first reference value is 0.7.
In some possible embodiments, when the similarity value of the two parameter sets is smaller than or equal to the first reference value and larger than the second reference value (with the foregoing as a reference, the second reference value needs to be smaller than 0.7), the lengths of the sub-analysis sound curves corresponding to the two parameter sets need to be adjusted and the process of determining the repeated segments on the analysis sound curves is repeated.
The purpose of the adjustment is to take into account that the division of the sub-analysis sound curve is not reasonable at this time, and thus the adjustment is required.
In some possible occurrences, the adjustment may include both changing the length of the sub-analysis sound curve and/or moving the division position of the sub-analysis sound curve, as shown in fig. 6, 7 and 8.
In some examples, decomposing the repeated segment into a plurality of frequency domains during the parsing includes the steps of:
s401, ordering the frequencies in the repeated segments obtained through analysis according to the size of the frequency values; and
s402, grouping the ordered frequency values according to the aggregation degree to obtain a plurality of frequency domains;
wherein frequency values located between two adjacent frequency domains are all divided into adjacent preceding or following frequency domains.
Referring to fig. 9, solid points (horizontal coordinates may be expressed as time or order, and vertical coordinates as numerical values) in the graph represent frequency values, and an aggregation interval of frequency values in each frequency domain is represented between dotted lines in the frequency domain. Specifically, in step S401, the frequencies in the repeated segments are sorted according to the magnitudes of the frequency values, and then are grouped according to the aggregation degrees according to the sorted frequency values, and a plurality of frequency domains are obtained, each of which includes a plurality of frequency values, and the frequency values are aggregated in value.
Meanwhile, some frequency values have no aggregation, and for those frequency values having no aggregation, they are divided into a preceding or following frequency domain between two adjacent frequency domains, so that the frequency values having no aggregation in one frequency domain are concentrated on one side (upper side or lower side) of the frequency domain.
The more frequency values without aggregation, the more the frequency domain clutter, the higher the probability that the corresponding transformer body has faults. In some possible implementations, the frequency values without aggregation are processed twice, placed on the lower side of the previous frequency domain and the upper side of the next frequency domain, respectively, and then the duty cycle of the frequency values without aggregation in the total number of frequency values in the frequency domain is calculated again.
The invention also provides a wide-area voiceprint compression acquisition device for the transformer body, which comprises:
the analysis unit is used for responding to the acquired sound samples, transferring the sound samples into a frequency domain to analyze the sound samples, and obtaining a sound sample group, wherein the sound sample group comprises a plurality of sound curves;
the rejecting unit is used for rejecting the standard sound curve in the sound sample group to obtain a screening sample group;
the first positioning unit is used for positioning the sound curves in the screening sample group to obtain sound production positions;
the first grouping unit is used for grouping the sound curves in the screening sample groups according to the sound production positions to obtain a plurality of standard sound sample groups, and the sound curves in each standard sound sample group belong to the same sound production position;
the first synthesis unit is used for converting the sound curve in one standard sound sample group into a time domain for synthesis to obtain an analysis sound curve;
a processing unit for determining a repeating segment on the analysis sound curve and a frequency of occurrence of the repeating segment;
the second grouping unit is used for transferring the repeated section with the occurrence frequency meeting the requirement into a frequency domain for analysis, and decomposing the repeated section into a plurality of frequency domains in the analysis process, wherein the amplitude of the sound curve with the frequency more than or equal to the set proportion in each frequency domain tends to be consistent;
A statistics unit for counting the number of abnormal sound curves in the repeated section; and
and a second synthesizing unit for generating an abnormal characteristic sound curve based on the sound emission position using the abnormal sound curve.
Further, the sound samples are from a plurality of sound collection terminals.
Further, the method further comprises the following steps:
the second positioning unit is used for positioning by using a sound curve in a screening sample group to obtain a first position; and
and the position fusion unit is used for fusing the plurality of first positions to obtain sounding positions.
Further, when one sound curve in the screening sample group is associated with only one sound producing position, the sound curve is marked as a marked sound curve;
the marker sound profile is associated with another sound producing location according to a frequency, the marker sound profile being the same frequency as the sound profile associated with the other sound producing location, the magnitude of the marker sound profile being less than the magnitude of the sound profile associated with the other sound producing location.
Further, the method further comprises the following steps:
a decomposition unit for sequentially dividing the analysis sound curves into a plurality of sub analysis sound curves;
the parameter decomposition unit is used for converting each sub-analysis sound curve into a frequency domain for decomposition to obtain a plurality of parameter groups, wherein each parameter group comprises frequency, amplitude and quantity;
A comparison unit for comparing the similarity of any two parameter sets; and
and the marking unit is used for marking the sub-analysis sound curves corresponding to the two parameter sets as repeated segments when the similarity value of the two parameter sets is larger than the first reference value.
Further, when the similarity value of the two parameter sets is smaller than or equal to the first reference value and larger than the second reference value, the lengths of the sub analysis sound curves corresponding to the two parameter sets are adjusted, and the process of determining the repeated segments on the analysis sound curves is repeated.
Further, the adjusting includes changing a length of the sub-analysis sound curve and/or moving a dividing position of the sub-analysis sound curve.
Further, the method further comprises the following steps:
the sequencing unit is used for sequencing the frequencies in the repeated segments obtained through analysis according to the size of the frequency values; and
a third grouping unit, configured to group the ordered frequency values according to the aggregation level, to obtain a plurality of frequency domains;
wherein frequency values located between two adjacent frequency domains are all divided into adjacent preceding or following frequency domains.
In one example, the unit in any of the above apparatuses may be one or more integrated circuits configured to implement the above methods, for example: one or more application specific integrated circuits (application specific integratedcircuit, ASIC), or one or more digital signal processors (digital signal processor, DSP), or one or more field programmable gate arrays (fieldprogrammable gate array, FPGA), or a combination of at least two of these integrated circuit forms.
For another example, when the units in the apparatus may be implemented in the form of a scheduler of processing elements, the processing elements may be general-purpose processors, such as a central processing unit (central processing unit, CPU) or other processor that may invoke the program. For another example, the units may be integrated together and implemented in the form of a system-on-a-chip (SOC).
Various objects such as various messages/information/devices/network elements/systems/devices/actions/operations/processes/concepts may be named in the present invention, and it should be understood that these specific names do not constitute limitations on related objects, and that the named names may be changed according to the scenario, context, or usage habit, etc., and understanding of technical meaning of technical terms in the present invention should be mainly determined from functions and technical effects that are embodied/performed in the technical solution.
It will be clear to those skilled in the art that, for convenience and brevity of description, specific working procedures of the above-described systems, apparatuses and units may refer to corresponding procedures in the foregoing method embodiments, and are not repeated herein.
In the several embodiments provided by the present invention, it should be understood that the disclosed systems, devices, and methods may be implemented in other manners. For example, the apparatus embodiments described above are merely illustrative, e.g., the division of the units is merely a logical function division, and there may be additional divisions when actually implemented, e.g., multiple units or components may be combined or integrated into another system, or some features may be omitted or not performed. Alternatively, the coupling or direct coupling or communication connection shown or discussed with each other may be an indirect coupling or communication connection via some interfaces, devices or units, which may be in electrical, mechanical or other form.
The units described as separate units may or may not be physically separate, and units shown as units may or may not be physical units, may be located in one place, or may be distributed on a plurality of network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.
Those of ordinary skill in the art will appreciate that the various illustrative elements and algorithm steps described in connection with the embodiments disclosed herein may be implemented as electronic hardware, or combinations of computer software and electronic hardware. Whether such functionality is implemented as hardware or software depends upon the particular application and design constraints imposed on the solution. Skilled artisans may implement the described functionality in varying ways for each particular application, but such implementation decisions should not be interpreted as causing a departure from the scope of the present invention.
It should also be understood that in various embodiments of the present invention, first, second, etc. are merely intended to represent that multiple objects are different. For example, the first time window and the second time window are only intended to represent different time windows. Without any effect on the time window itself, the first, second, etc. mentioned above should not impose any limitation on the embodiments of the present invention.
It is also to be understood that in the various embodiments of the invention, where no special description or logic conflict exists, the terms and/or descriptions between the various embodiments are consistent and may reference each other, and features of the various embodiments may be combined to form new embodiments in accordance with their inherent logic relationships.
The functions, if implemented in the form of software functional units and sold or used as a stand-alone product, may be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention may be embodied essentially or in a part contributing to the prior art or in a part of the technical solution, in the form of a software product stored in a computer-readable storage medium, comprising several instructions for causing a computer device (which may be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the method according to the embodiments of the present invention. And the aforementioned computer-readable storage medium includes: a U-disk, a removable hard disk, a Read-Only Memory (ROM), a random access Memory (Random Access Memory, RAM), a magnetic disk, or an optical disk, or other various media capable of storing program codes.
The invention also provides a wide-area voiceprint compression acquisition system for the transformer body, which comprises:
one or more memories for storing instructions; and
one or more processors configured to invoke and execute the instructions from the memory to perform the method as described above.
The present invention also provides a computer program product comprising instructions which, when executed, cause the terminal device and the network device to perform operations of the terminal device and the network device corresponding to the above method.
The present invention also provides a chip system comprising a processor for implementing the functions involved in the above, e.g. generating, receiving, transmitting, or processing data and/or information involved in the above method.
The chip system can be composed of chips, and can also comprise chips and other discrete devices.
The processor referred to in any of the foregoing may be a CPU, microprocessor, ASIC, or integrated circuit that performs one or more of the procedures for controlling the transmission of feedback information described above.
In one possible design, the system on a chip also includes memory to hold the necessary program instructions and data. The processor and the memory may be decoupled, and disposed on different devices, respectively, and connected by wired or wireless means, so as to support the chip system to implement the various functions in the foregoing embodiments. In the alternative, the processor and the memory may be coupled to the same device.
Optionally, the computer instructions are stored in a memory.
Alternatively, the memory may be a storage unit in the chip, such as a register, a cache, etc., and the memory may also be a storage unit in the terminal located outside the chip, such as a ROM or other type of static storage device, a RAM, etc., that may store static information and instructions.
It will be appreciated that the memory in the present invention can be either volatile memory or nonvolatile memory, or can include both volatile and nonvolatile memory.
The non-volatile memory may be a ROM, programmable ROM (PROM), erasable programmable ROM (erasablePROM, EPROM), electrically erasable programmable EPROM (EEPROM), or flash memory.
The volatile memory may be RAM, which acts as external cache. There are many different types of RAM, such as Static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (synchronousDRAM, SDRAM), double data rate synchronous DRAM (DDR SDRAM), enhanced SDRAM (ESDRAM), synchronous Link DRAM (SLDRAM), and direct memory bus RAM.
The embodiments of the present invention are all preferred embodiments of the present invention, and are not intended to limit the scope of the present invention in this way, therefore: all equivalent changes in structure, shape and principle of the invention should be covered in the scope of protection of the invention.
Claims (10)
1. The wide-area voiceprint compression acquisition method for the transformer body is characterized by comprising the following steps of:
responding to the acquired sound sample, transferring the sound sample into a frequency domain for analysis to obtain a sound sample group, wherein the sound sample group comprises a plurality of sound curves;
removing standard sound curves in the sound sample group to obtain a screening sample group;
positioning the sound curve in the screening sample group to obtain a sound producing position;
grouping the sound curves in the screening sample groups according to the sound emission positions to obtain a plurality of standard sound sample groups, wherein the sound curves in each standard sound sample group belong to the same sound emission position;
transferring the sound curve in one standard sound sample group into a time domain for synthesis to obtain an analysis sound curve;
determining the occurrence frequency of the repeated segments on the analysis sound curve;
transferring the repeated segments with the occurrence frequency meeting the requirement into a frequency domain for analysis, and decomposing the repeated segments into a plurality of frequency domains in the analysis process, wherein the amplitude of a sound curve with the frequency more than or equal to a set proportion in each frequency domain tends to be consistent;
Counting the number of abnormal sound curves in the repeated section; and
an abnormal sound curve is generated based on the sound emission position using the abnormal sound curve.
2. The wide-area voiceprint compression acquisition method for a transformer body of claim 1, wherein the sound samples are from a plurality of sound acquisition terminals;
positioning the sound curve in the screening sample group, wherein obtaining the sound producing position comprises:
positioning by using a sound curve in a screening sample group to obtain a first position; and
and fusing the plurality of first positions to obtain the sounding position.
3. The method of claim 2, wherein when a sound curve in the screening sample set is associated with only one sound location, the sound curve is recorded as a marked sound curve;
the marker sound profile is associated with another sound producing location according to a frequency, the marker sound profile being the same frequency as the sound profile associated with the other sound producing location, the magnitude of the marker sound profile being less than the magnitude of the sound profile associated with the other sound producing location.
4. A wide-area voiceprint compression acquisition method for a transformer body according to any one of claims 1 to 3 wherein determining a repeat segment on an analytical sound curve comprises:
Sequentially dividing the analysis sound curve into a plurality of sub analysis sound curves;
transferring each sub-analysis sound curve into a frequency domain for decomposition to obtain a plurality of parameter sets, wherein each parameter set comprises frequency, amplitude and quantity;
comparing the similarity of any two parameter sets; and
and when the similarity value of the two parameter sets is larger than the first reference value, marking the sub-analysis sound curves corresponding to the two parameter sets as repeated segments.
5. The method according to claim 4, wherein when the similarity value of the two parameter sets is less than or equal to the first reference value and greater than the second reference value, the length of the sub-analysis sound curve corresponding to the two parameter sets is adjusted and the process of determining the repeated segment on the analysis sound curve is repeated.
6. The method of claim 5, wherein adjusting includes changing a length of the sub-analysis sound curve and/or moving a dividing position of the sub-analysis sound curve.
7. The method of claim 1, wherein decomposing the repeating segment into a plurality of frequency domains during parsing comprises:
Sequencing the frequencies in the repeated segments obtained through analysis according to the size of the frequency values; and
grouping the ordered frequency values according to the aggregation degree to obtain a plurality of frequency domains;
wherein frequency values located between two adjacent frequency domains are all divided into adjacent preceding or following frequency domains.
8. A wide area voiceprint compression collection system for transformer body, characterized in that includes:
the analysis unit is used for responding to the acquired sound samples, transferring the sound samples into a frequency domain to analyze the sound samples, and obtaining a sound sample group, wherein the sound sample group comprises a plurality of sound curves;
the rejecting unit is used for rejecting the standard sound curve in the sound sample group to obtain a screening sample group;
the first positioning unit is used for positioning the sound curves in the screening sample group to obtain sound production positions;
the first grouping unit is used for grouping the sound curves in the screening sample groups according to the sound production positions to obtain a plurality of standard sound sample groups, and the sound curves in each standard sound sample group belong to the same sound production position;
the first synthesis unit is used for converting the sound curve in one standard sound sample group into a time domain for synthesis to obtain an analysis sound curve;
A processing unit for determining a repeating segment on the analysis sound curve and a frequency of occurrence of the repeating segment;
the second grouping unit is used for transferring the repeated section with the occurrence frequency meeting the requirement into a frequency domain for analysis, and decomposing the repeated section into a plurality of frequency domains in the analysis process, wherein the amplitude of the sound curve with the frequency more than or equal to the set proportion in each frequency domain tends to be consistent;
a statistics unit for counting the number of abnormal sound curves in the repeated section; and
and a second synthesizing unit for generating an abnormal characteristic sound curve based on the sound emission position using the abnormal sound curve.
9. A wide area voiceprint compression acquisition system for a transformer body, the system comprising:
one or more memories for storing instructions; and
one or more processors to invoke and execute the instructions from the memory to perform the method of any of claims 1 to 7.
10. A computer-readable storage medium, the computer-readable storage medium comprising:
program which, when executed by a processor, performs a method according to any one of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311352600.XA CN117095695B (en) | 2023-10-19 | 2023-10-19 | Wide-area voiceprint compression acquisition method and system for transformer body |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311352600.XA CN117095695B (en) | 2023-10-19 | 2023-10-19 | Wide-area voiceprint compression acquisition method and system for transformer body |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN117095695A true CN117095695A (en) | 2023-11-21 |
| CN117095695B CN117095695B (en) | 2023-12-22 |
Family
ID=88783695
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311352600.XA Active CN117095695B (en) | 2023-10-19 | 2023-10-19 | Wide-area voiceprint compression acquisition method and system for transformer body |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117095695B (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117031154A (en) * | 2023-08-07 | 2023-11-10 | 国网山西省电力公司超高压变电分公司 | Transformer fault analysis method and system based on voiceprint recognition |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2013195575A (en) * | 2012-03-16 | 2013-09-30 | Nippon Telegr & Teleph Corp <Ntt> | Sound signal analysis device, method, and program |
| CN112885372A (en) * | 2021-01-15 | 2021-06-01 | 国网山东省电力公司威海供电公司 | Intelligent diagnosis method, system, terminal and medium for power equipment fault sound |
| CN113053412A (en) * | 2021-02-04 | 2021-06-29 | 国网江苏省电力有限公司检修分公司 | Sound-based transformer fault identification method |
| CN115510265A (en) * | 2021-06-07 | 2022-12-23 | 广东电网有限责任公司中山供电局 | Method and system for judging animal hazard distribution of pole tower in power transmission line |
| CN116800895A (en) * | 2022-03-14 | 2023-09-22 | 富士胶片商业创新有限公司 | Information processing apparatus, recording medium, and information processing method |
-
2023
- 2023-10-19 CN CN202311352600.XA patent/CN117095695B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2013195575A (en) * | 2012-03-16 | 2013-09-30 | Nippon Telegr & Teleph Corp <Ntt> | Sound signal analysis device, method, and program |
| CN112885372A (en) * | 2021-01-15 | 2021-06-01 | 国网山东省电力公司威海供电公司 | Intelligent diagnosis method, system, terminal and medium for power equipment fault sound |
| CN113053412A (en) * | 2021-02-04 | 2021-06-29 | 国网江苏省电力有限公司检修分公司 | Sound-based transformer fault identification method |
| CN115510265A (en) * | 2021-06-07 | 2022-12-23 | 广东电网有限责任公司中山供电局 | Method and system for judging animal hazard distribution of pole tower in power transmission line |
| CN116800895A (en) * | 2022-03-14 | 2023-09-22 | 富士胶片商业创新有限公司 | Information processing apparatus, recording medium, and information processing method |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117031154A (en) * | 2023-08-07 | 2023-11-10 | 国网山西省电力公司超高压变电分公司 | Transformer fault analysis method and system based on voiceprint recognition |
| CN117031154B (en) * | 2023-08-07 | 2024-03-22 | 国网山西省电力公司超高压变电分公司 | Transformer fault analysis method and system based on voiceprint recognition |
Also Published As
| Publication number | Publication date |
|---|---|
| CN117095695B (en) | 2023-12-22 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN117095695B (en) | Wide-area voiceprint compression acquisition method and system for transformer body | |
| KR101493552B1 (en) | Signal judgment method, signal judgment apparatus, program, and signal judgment system | |
| CN103067322B (en) | The method of the voice quality of the audio frame in assessment channel audio signal | |
| CN109933852B (en) | Method and device for predicting vehicle size deviation, storage medium and electronic equipment | |
| CN106658701A (en) | Positioning method and apparatus | |
| CN109729546B (en) | Access point and method for waveform model | |
| CN108198561A (en) | A kind of pirate recordings speech detection method based on convolutional neural networks | |
| CN116242443B (en) | Dynamic metering method of ultrasonic metering instrument | |
| CN109362084A (en) | Method, apparatus, equipment and the medium of communication service quality optimization | |
| CN108536880A (en) | A kind of stochastic collision detection algorithm of virtual reality system | |
| Torkamani et al. | Detection of system changes due to damage using a tuned hyperchaotic probe | |
| WO2010031109A1 (en) | Method of analysing an audio signal | |
| CN108519579B (en) | WiFi fingerprint positioning method for analyzing optimal AP based on interval overlapping degree | |
| CN114034928B (en) | Harmonic tracing method based on distributed multipoint feedback and power distribution network analysis system | |
| CN115810401A (en) | Recipe construction system, method, readable storage medium and computer program product | |
| CN117031154B (en) | Transformer fault analysis method and system based on voiceprint recognition | |
| US11556586B2 (en) | Sound recognition model training method and system and non-transitory computer-readable medium | |
| CN117889945B (en) | Highway bridge construction vibration testing method | |
| CN117292717B (en) | Abnormal sound identification method, device, electronic equipment and storage medium | |
| CN117871917B (en) | Signal simulation control method for multifunctional equipment | |
| Tamaki et al. | A Probabilistic Method for Constructing an Empirical Discrimination Model for Hammering Inspection of Cast-Iron Parts | |
| Tamaki et al. | A method for constructing an ADVI-based statistical discrimination model for hammering inspection of highly mixed cast-iron parts | |
| US10840942B2 (en) | Method and apparatus for compressing data | |
| CN116470975A (en) | Modeling method of SVR-based adaptive propagation prediction model | |
| CN116910677A (en) | Industrial instrument fault diagnosis method and system |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |