CN111916091A - Method and device for extracting coal rock instability precursor information features by using voice recognition - Google Patents
Method and device for extracting coal rock instability precursor information features by using voice recognition Download PDFInfo
- Publication number
- CN111916091A CN111916091A CN202010680193.5A CN202010680193A CN111916091A CN 111916091 A CN111916091 A CN 111916091A CN 202010680193 A CN202010680193 A CN 202010680193A CN 111916091 A CN111916091 A CN 111916091A
- Authority
- CN
- China
- Prior art keywords
- signal
- coal rock
- vibration wave
- frame
- instability
- 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
- 239000003245 coal Substances 0.000 title claims abstract description 157
- 239000011435 rock Substances 0.000 title claims abstract description 115
- 238000000034 method Methods 0.000 title claims abstract description 69
- 239000002243 precursor Substances 0.000 title claims abstract description 65
- 230000005236 sound signal Effects 0.000 claims abstract description 63
- 238000009826 distribution Methods 0.000 claims abstract description 36
- 230000008569 process Effects 0.000 claims abstract description 31
- 238000000605 extraction Methods 0.000 claims abstract description 23
- 230000008859 change Effects 0.000 claims abstract description 16
- 238000009432 framing Methods 0.000 claims abstract description 14
- 238000012163 sequencing technique Methods 0.000 claims abstract description 14
- 230000035939 shock Effects 0.000 claims description 35
- 238000004364 calculation method Methods 0.000 claims description 28
- 210000005069 ears Anatomy 0.000 claims description 17
- 238000001228 spectrum Methods 0.000 claims description 12
- 238000006243 chemical reaction Methods 0.000 claims description 6
- 238000012546 transfer Methods 0.000 claims description 6
- 238000010183 spectrum analysis Methods 0.000 claims description 5
- 238000001914 filtration Methods 0.000 claims description 3
- 238000012545 processing Methods 0.000 claims description 3
- 238000012544 monitoring process Methods 0.000 abstract description 14
- 208000010392 Bone Fractures Diseases 0.000 description 21
- 206010017076 Fracture Diseases 0.000 description 21
- 230000006870 function Effects 0.000 description 19
- 238000010586 diagram Methods 0.000 description 8
- 230000015654 memory Effects 0.000 description 6
- 238000004458 analytical method Methods 0.000 description 5
- 238000003860 storage Methods 0.000 description 5
- 239000011159 matrix material Substances 0.000 description 3
- 230000035772 mutation Effects 0.000 description 3
- 230000008092 positive effect Effects 0.000 description 3
- 230000009286 beneficial effect Effects 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 230000003287 optical effect Effects 0.000 description 2
- 238000012360 testing method Methods 0.000 description 2
- 238000009412 basement excavation Methods 0.000 description 1
- 238000012669 compression test Methods 0.000 description 1
- 238000013500 data storage Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000002474 experimental method Methods 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 238000005065 mining Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
Images
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
- G10L19/00—Speech or audio signals analysis-synthesis techniques for redundancy reduction, e.g. in vocoders; Coding or decoding of speech or audio signals, using source filter models or psychoacoustic analysis
- G10L19/04—Speech or audio signals analysis-synthesis techniques for redundancy reduction, e.g. in vocoders; Coding or decoding of speech or audio signals, using source filter models or psychoacoustic analysis using predictive techniques
- G10L19/16—Vocoder architecture
- G10L19/173—Transcoding, i.e. converting between two coded representations avoiding cascaded coding-decoding
-
- 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
- G10L15/00—Speech recognition
- G10L15/02—Feature extraction for speech recognition; Selection of recognition unit
-
- 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
- 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
- G10L25/24—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 the cepstrum
-
- 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
- G10L25/27—Speech or voice analysis techniques not restricted to a single one of groups G10L15/00 - G10L21/00 characterised by the analysis technique
-
- 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
- G10L25/45—Speech or voice analysis techniques not restricted to a single one of groups G10L15/00 - G10L21/00 characterised by the type of analysis window
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Health & Medical Sciences (AREA)
- Audiology, Speech & Language Pathology (AREA)
- Human Computer Interaction (AREA)
- Computational Linguistics (AREA)
- Acoustics & Sound (AREA)
- Multimedia (AREA)
- Signal Processing (AREA)
- Spectroscopy & Molecular Physics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Measurement Of Mechanical Vibrations Or Ultrasonic Waves (AREA)
- Geophysics And Detection Of Objects (AREA)
Abstract
The invention provides a method and a device for extracting coal rock instability precursor information features by using voice recognition, and belongs to the field of coal rock dynamic disaster monitoring and early warning. The method comprises the following steps: converting a vibration wave signal in the coal rock deformation and fracture process into an audio signal and framing the audio signal to obtain a frame signal; obtaining cepstrum coefficients of all frame signals by utilizing a feature extraction technology in the field of voice recognition; sequencing all cepstral coefficients to obtain time sequence distribution of the cepstral coefficients; and analyzing the change rule of the cepstrum coefficient before the coal rock instability according to the obtained time sequence distribution of the cepstrum coefficient to obtain the precursor information characteristic of the coal rock instability. By adopting the method and the device, the precursor information characteristic of coal rock instability can be accurately extracted.
Description
Technical Field
The invention relates to the field of coal rock dynamic disaster monitoring and early warning, in particular to a method and a device for extracting coal rock instability precursor information features by using voice recognition.
Background
Coal petrography instability can cause coal petrography dynamic disasters, and accurate early warning on the coal petrography instability is beneficial to taking targeted measures in advance to prevent the dynamic disasters. At present, the micro-seismic, earthquake sound and sound emission technology is widely applied to monitoring and early warning of coal and rock dynamic disasters due to the characteristics of small workload, no influence on production, dynamic continuity in space and time and the like, and although a good application effect is obtained, the actual requirements cannot be completely met.
The monitoring and early warning principle of the micro-seismic, earthquake sound and sound emission technology is mainly that the monitoring of the coal rock fracture development and expansion process is realized by collecting the vibration wave signals of the coal rock deformation and fracture process, and then the precursor information characteristics of the coal rock instability are extracted to realize the early warning of the coal rock instability.
In the prior art, the analysis means and analysis indexes of the vibration wave signals collected by micro-vibration, ground sound, acoustic emission and the like are single, statistical parameters such as energy, frequency, counting and the like are mostly used simply, and the precursor information characteristics of coal rock instability are difficult to extract accurately only by the parameters.
Disclosure of Invention
The embodiment of the invention provides a method and a device for extracting coal rock instability precursor information features by using voice recognition, which can accurately extract the coal rock instability precursor information features. The technical scheme is as follows:
in one aspect, a method for extracting coal rock instability precursor information features by using voice recognition is provided, and the method is applied to electronic equipment and comprises the following steps:
converting a vibration wave signal in the coal rock deformation and fracture process into an audio signal and framing the audio signal to obtain a frame signal;
obtaining cepstrum coefficients of all frame signals by utilizing a feature extraction technology in the field of voice recognition;
sequencing all cepstral coefficients to obtain time sequence distribution of the cepstral coefficients;
and analyzing the change rule of the cepstrum coefficient before the coal rock instability according to the obtained time sequence distribution of the cepstrum coefficient to obtain the precursor information characteristic of the coal rock instability.
Further, before converting the vibration wave signal of the coal rock deformation and fracture process into an audio signal and framing the audio signal to obtain a frame signal, the method comprises the following steps:
arranging sensors on the coal rock mass, and acquiring vibration wave signals of the coal rock deformation and fracture process through the arranged sensors;
wherein, the shock wave signal refers to a series of independent shock waves or a continuous shock wave full waveform.
Further, the converting the vibration wave signal of the coal rock deformation and fracture process into the audio signal comprises:
carrying out frequency spectrum analysis on the collected shock wave signal to obtain a main frequency range of the shock wave signal;
the time interval of adjacent shock wave signal data points is adjusted according to the frequency band range of the audio signal which can be felt by human ears, the shock wave signal is zoomed on a time axis, the main frequency range of the shock wave signal is consistent with the frequency band range of the audio signal which can be felt by human ears, and therefore the collected shock wave signal is converted into the audio signal which can be felt by human ears.
Further, the conversion function of converting the collected shock wave signal into an audio signal that can be felt by the human ear is:
wherein f isα、fαl、fαhThe original frequency of the vibration wave signal, the lower limit and the upper limit of the main frequency range of the vibration wave signal, fβ、fβl、fβhThe frequency of the audio signal after the vibration wave signal is converted into the audio signal, and the lower limit and the upper limit of the frequency band range of the audio signal which can be felt by human ears are respectively, and lambda is a signal scaling multiple.
Further, the framing the audio signal to obtain a frame signal includes:
if the vibration wave signals are independent vibration waves, taking each independent vibration wave waveform as a frame signal;
if the vibration wave signal is a continuous vibration wave full waveform, the vibration wave full waveform is divided into segments with equal length, a section of length is overlapped between adjacent segments, and the vibration wave full waveform is converted into a frame signal, namely:
wherein, x (t) is the full waveform of the vibration wave; n is the length of each frame of data; r is the number of frames, and the calculation formula of R is as follows:
wherein L isxIs the length of the shock wave signal, L is the overlap length between adjacent frames [. degree]Is a rounding function;
let x be the R-th frame signal, x [ n ] be the n-th value in the frame signal x, R is greater than or equal to 0 and less than or equal to R-1, then x [ n ], x are:
x[n]=x[r(N-L)+n],n=0,1,2,…,N-1
x={x[r(N-L)],x[r(N-L)+1],…,x[r(N-L)+N-1]}。
further, the obtaining cepstrum coefficients of all frame signals by using the feature extraction technology in the speech recognition field includes:
b1, performing window function processing on a certain frame signal x to obtain a signal x', wherein the calculation formula is as follows:
x′=wx
wherein w is a window function;
b2, extracting the short-time energy spectrum W of the signal x' using discrete fourier transform, the calculation formula is:
wherein, W [ k ] is the kth value of the short-time energy spectrum W, N is the length of each frame of data, and x 'N is the nth value of x';
b3, filtering the short-time energy spectrum W by using a filter bank to obtain an energy signal W' in a corresponding frequency domain, wherein the calculation formula is as follows:
wherein, W' [ m ]]Is the mth value of W', M is the total number of filters of the filter bank, H is the filter bank, Hm[k]For the kth value of the mth filter transfer function;
b4, solving the logarithm of the energy signal W' to obtain a signal S, wherein the calculation formula is as follows:
S[m]=log10W′[m],m=0,1,2,…,M-1
wherein Sm is the mth value of S;
b5, performing discrete cosine transform on the signal S to obtain a cepstrum coefficient MFCC of the frame signal x, where the calculation formula is:
wherein, MFCC [ C ] is the C-th parameter of the cepstrum coefficient MFCC, C is the number of the parameters of the cepstrum coefficient MFCC, ac is the orthogonal coefficient, and the calculation formula of ac is:
and B6, repeating the steps B1 to B5 to obtain cepstrum coefficients of all the frame signals.
Further, the window function may be a tapered window function, and the calculation formula is:
wherein, w [ n ]]Is the nth value of the cone window function, LwIs the window length, LwN, α is the window coefficient.
Further, the frequency band range of the filter bank is consistent with the frequency band range of the audio signal which can be felt by human ears;
the filter bank is a Mel filter bank, the Mel filter bank is composed of M triangular band-pass filters, and the transfer function of each triangular band-pass filter is as follows:
where M is 0,1,2, …, M-1, k is 1,2, …, N/2-1, f (M) is the center frequency of the triangular band-pass filter.
Further, the sorting all cepstral coefficients to obtain the time sequence distribution of the cepstral coefficients includes:
if the vibration wave signals are independent vibration waves, the occurrence time of the vibration waves is used as the time of cepstrum coefficients of the frame signals, and the cepstrum coefficients are sequenced according to the time sequence to obtain the time sequence distribution of the cepstrum coefficients;
if the vibration wave signal is a continuous vibration wave full waveform, sequencing the cepstrum coefficients according to the sequence of frames and the time interval between adjacent frames to obtain the time sequence distribution of the cepstrum coefficients, wherein the time interval T isMThe calculation formula of (2) is as follows:
wherein f isxN is the length of each frame of data, and L is the overlap length between adjacent frames.
In one aspect, a device for extracting coal rock instability precursor information features by using voice recognition is provided, and the device is applied to electronic equipment and comprises:
the conversion module is used for converting the vibration wave signals in the coal rock deformation and fracture process into audio signals and framing the audio signals to obtain frame signals;
the acquisition module is used for acquiring cepstrum coefficients of all frame signals by utilizing a feature extraction technology in the field of voice recognition;
the sequencing module is used for sequencing all cepstrum coefficients to obtain time sequence distribution of the cepstrum coefficients;
and the extraction module is used for analyzing the change rule of the cepstrum coefficient before the coal rock instability according to the obtained time sequence distribution of the cepstrum coefficient to obtain the precursor information characteristic of the coal rock instability.
In one aspect, an electronic device is provided, and the electronic device includes a processor and a memory, where the memory stores at least one instruction, and the at least one instruction is loaded and executed by the processor to implement the method for extracting coal rock instability precursor information features by using speech recognition.
In one aspect, a computer-readable storage medium is provided, in which at least one instruction is stored, and the at least one instruction is loaded and executed by a processor to implement the method for extracting coal petrography instability precursor information features by using voice recognition.
The technical scheme provided by the embodiment of the invention has the beneficial effects that at least:
in the embodiment of the invention, a vibration wave signal in the deformation and fracture process of the coal rock is converted into an audio signal, and the audio signal is subjected to framing to obtain a frame signal; obtaining cepstrum coefficients of all frame signals by utilizing a feature extraction technology in the field of voice recognition; sequencing all cepstral coefficients to obtain time sequence distribution of the cepstral coefficients; and analyzing the change rule of the cepstrum coefficient before the coal rock instability according to the obtained time sequence distribution of the cepstrum coefficient to obtain the precursor information characteristic of the coal rock instability. Therefore, the characteristic extraction technology in the field of voice recognition is applied to vibration wave signal analysis in the coal rock deformation and fracture process, so that the precursor information characteristic of coal rock instability is accurately extracted, the precursor information characteristic can be used for evaluating the coal rock stable state, the accuracy of coal rock dynamic disaster monitoring and early warning is improved, and the method has a positive effect on the coal rock dynamic disaster monitoring and early warning.
Drawings
In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the drawings needed to be used in the description of the embodiments will be briefly introduced below, and it is obvious that the drawings in the following description are only some embodiments of the present invention, and it is obvious for those skilled in the art to obtain other drawings based on these drawings without creative efforts.
Fig. 1 is a schematic flow chart of a method for extracting coal petrography instability precursor information features by using speech recognition according to an embodiment of the present invention;
FIG. 2 is a schematic diagram of a test loading apparatus provided in an embodiment of the present invention;
FIG. 3 is a schematic diagram of an original acoustic emission full-waveform signal of a collected coal sample according to an embodiment of the present invention;
FIG. 4 is a schematic diagram of the frequency spectrum distribution of the original acoustic emission signal and the frequency band range thereof corresponding to the converted audio signal according to an embodiment of the present invention;
FIG. 5 is a schematic diagram of a flow of computing Mel cepstrum coefficients of acoustic emission signals of a coal sample according to an embodiment of the present invention;
fig. 6(a) - (l) are schematic diagrams of time-series distributions of 12 parameters of mel-frequency cepstrum coefficients of a coal sample according to an embodiment of the present invention;
fig. 7 is a schematic structural diagram of an apparatus for extracting coal petrography instability precursor information features by using speech recognition according to an embodiment of the present invention;
fig. 8 is a schematic structural diagram of an electronic device according to an embodiment of the present invention.
Detailed Description
In order to make the objects, technical solutions and advantages of the present invention more apparent, embodiments of the present invention will be described in detail with reference to the accompanying drawings.
As shown in fig. 1, an embodiment of the present invention provides a method for extracting coal petrography instability precursor information features by using speech recognition, where the method may be implemented by an electronic device, and the electronic device may be a terminal or a server, and the method includes:
s101, converting a vibration wave signal in the coal rock deformation and fracture process into an audio signal and framing the audio signal to obtain a frame signal;
s102, obtaining cepstrum coefficients of all frame signals by utilizing a feature extraction technology in the field of voice recognition;
s103, sequencing all cepstrum coefficients to obtain time sequence distribution of the cepstrum coefficients;
and S104, analyzing the change rule of the cepstrum coefficient before the coal rock instability according to the obtained time sequence distribution of the cepstrum coefficient to obtain the precursor information characteristic of the coal rock instability.
The method for extracting the coal rock instability precursor information features by using voice recognition converts vibration wave signals in the coal rock deformation and fracture process into audio signals and frames the audio signals to obtain frame signals; obtaining cepstrum coefficients of all frame signals by utilizing a feature extraction technology in the field of voice recognition; sequencing all cepstral coefficients to obtain time sequence distribution of the cepstral coefficients; and analyzing the change rule of the cepstrum coefficient before the coal rock instability according to the obtained time sequence distribution of the cepstrum coefficient to obtain the precursor information characteristic of the coal rock instability. Therefore, the characteristic extraction technology in the field of voice recognition is applied to vibration wave signal analysis in the coal rock deformation and fracture process, so that the precursor information characteristic of coal rock instability is accurately extracted, the precursor information characteristic can be used for evaluating the coal rock stable state, the accuracy of coal rock dynamic disaster monitoring and early warning is improved, and the method has a positive effect on the coal rock dynamic disaster monitoring and early warning.
In this embodiment, as an optional embodiment, before converting a vibration wave signal in a coal rock deformation and fracture process into an audio signal and framing the audio signal to obtain a frame signal (S101), the method includes:
arranging sensors on the coal rock mass, and acquiring vibration wave signals of the coal rock deformation and fracture process through the arranged sensors;
wherein, the shock wave signal refers to a series of independent shock waves or a continuous shock wave full waveform.
In this embodiment, the coal rock mass refers to a coal rock mass around the excavation of an engineering site or a coal rock sample for indoor experiments; a microseismic or earthquake sound sensor is generally arranged on a coal rock body of an engineering site, and an acoustic emission sensor is generally arranged on an indoor coal rock sample.
In the embodiment, the vibration wave signals of the coal rock deformation and fracture process are acquired by the sensors arranged on the coal rock body to serve as original data, so that the vibration wave signals can be deeply excavated and analyzed by a feature extraction technology in the field of voice recognition in the following process, precursor information features of coal rock instability can be obtained, and the accuracy of coal rock dynamic disaster monitoring and early warning can be improved.
In this embodiment, the converting the vibration wave signal of the coal rock deformation and fracture process into the audio signal in S101 includes:
a1, carrying out frequency spectrum analysis on the collected shock wave signal to obtain a main frequency range of the shock wave signal;
a2, adjusting the time interval of the data points of the adjacent shock wave signals according to the frequency band range of the audio signals which can be felt by human ears, and zooming the shock wave signals on a time axis to make the main frequency range of the shock wave signals consistent with the frequency band range of the audio signals which can be felt by human ears, thereby converting the collected shock wave signals into the audio signals which can be felt by human ears; wherein, the conversion function of converting the collected shock wave signal into the audio signal that the human ear can feel is:
wherein f isα、fαl、fαhThe original frequency of the vibration wave signal, the lower limit and the upper limit of the main frequency range of the vibration wave signal, fβ、fβl、fβhThe frequency of the audio signal after the vibration wave signal is converted into the audio signal, and the lower limit and the upper limit of the frequency band range of the audio signal which can be felt by human ears are respectively, and lambda is a signal scaling multiple.
In this embodiment, a discrete fourier transform is used for spectrum analysis.
In this embodiment, the main frequency range of the shock wave signal refers to a frequency range of main energy distribution of the shock wave signal, and preferably, a minimum continuous frequency band range in which energy ratio exceeds 90% in the entire frequency spectrum range is used as the main frequency range of the shock wave signal.
In this embodiment, the frequency band of the audio signal that can be perceived by the human ear is 133Hz to 6854 Hz.
In this embodiment, the framing the audio signal in S101 to obtain a frame signal includes:
if the vibration wave signals are independent vibration waves, taking each independent vibration wave waveform as a frame signal;
if the vibration wave signal is a continuous vibration wave full waveform, the vibration wave full waveform is divided into segments with equal length, a section of length is overlapped between adjacent segments, and the vibration wave full waveform is converted into a frame signal, namely:
wherein,representing a frame signal matrix, wherein x (t) is a full waveform of the vibration wave; n is the length of each frame of data; r is the number of frames, and the calculation formula of R is as follows:
wherein L isxIs a vibrationLength of the moving wave signal, L being the length of overlap between adjacent frames [ ·]Is a rounding function;
let x be the R-th frame signal corresponding to the R-th row in the frame signal matrix, x [ n ] be the n-th value in the frame signal x, R is greater than or equal to 0 and less than or equal to R-1, then x [ n ], x are:
x[n]=x[r(N-L)+n],n=0,1,2,…,N-1
x={x[r(N-L)],x[r(N-L)+1],…,x[r(N-L)+N-1]}
wherein x is a number sequence, r (N-L) + N is a corner mark, x [ r (N-L) + N ] represents the value of r (N-L) + N in the extracted number sequence x, and x [ r (N-L) + N ] corresponds to a certain value in the frame signal matrix.
In this embodiment, the obtaining cepstrum coefficients of all frame signals by using the feature extraction technology in the speech recognition field (S102) includes:
b1, performing window function processing on a certain frame signal x to obtain a signal x', wherein the calculation formula is as follows:
x′=wx
wherein w is a window function, the window function may be a tapered window function, and the calculation formula is:
wherein, w [ n ]]Is the nth value of the cone window function, LwIs the window length, Lwα is a window coefficient, e.g., α is 0.46164;
b2, extracting the short-time energy spectrum W of the signal x' using discrete fourier transform, the calculation formula is:
wherein, W [ k ] is the kth value of the short-time energy spectrum W, and x 'n is the nth value of x';
b3, filtering the short-time energy spectrum W by using a filter bank to obtain an energy signal W' in a corresponding frequency domain, wherein the calculation formula is as follows:
wherein, W' [ m ]]Is the mth value of W', M is the total number of filters of the filter bank, H is the filter bank, Hm[k]For the kth value of the mth filter transfer function;
in this embodiment, the frequency band range of the filter bank is consistent with the frequency band range of the audio signal that can be felt by human ears, that is: 133Hz to 6854 Hz;
the filter bank may be a mel filter bank consisting of M (e.g., M-40) triangular band pass filters, each having a transfer function of:
where m is 0,1,2, …,39, k is 1,2, …, N/2-1, f (m) is the center frequency of the triangular band-pass filter, and f (m) is expressed as:
in the present embodiment, when M is 40, M is 12 as a boundary point, and 12 is used as a boundary point, and a preferable center frequency can be obtained.
B4, solving the logarithm of the energy signal W' to obtain a signal S, wherein the calculation formula is as follows:
S[m]=log10W′[m],m=0,1,2,…,M-1
wherein Sm is the mth value of S;
b5, performing discrete cosine transform on the signal S to obtain a cepstrum coefficient MFCC of the frame signal x, where the calculation formula is:
wherein, MFCC [ C ] is the C-th parameter of the cepstrum coefficient MFCC, C is the number of the parameters of the cepstrum coefficient MFCC, ac is the orthogonal coefficient, and the calculation formula of ac is:
and B6, repeating the steps B1 to B5 to obtain cepstrum coefficients of all the frame signals.
In this embodiment, the obtaining the time sequence distribution (S103) of the cepstrum coefficients by sorting all the cepstrum coefficients includes:
if the vibration wave signals are independent vibration waves, the occurrence time of the vibration waves is used as the time of cepstrum coefficients of the frame signals, and the cepstrum coefficients are sequenced according to the time sequence to obtain the time sequence distribution of the cepstrum coefficients;
if the vibration wave signal is a continuous vibration wave full waveform, sequencing the cepstrum coefficients according to the sequence of frames and the time interval between adjacent frames to obtain the time sequence distribution of the cepstrum coefficients, wherein the time interval T isMThe calculation formula of (2) is as follows:
wherein f isxN is the length of each frame of data, and L is the overlap length between adjacent frames.
In this embodiment, the analyzing a change rule of the cepstrum coefficient before coal petrography instability according to the obtained time sequence distribution of the cepstrum coefficient to obtain a precursor information feature of the coal petrography instability (S104) includes:
analyzing the change rule of the cepstrum coefficient before coal rock instability according to the obtained time sequence distribution of the cepstrum coefficient, selecting one or more parameters which have high correlation with the coal rock instability (the correlation is higher than a preset threshold value) and show stable cepstrum coefficient as a precursor index of the coal rock instability, and taking the change rule of the precursor index before the coal rock instability as the precursor information characteristic of the coal rock instability.
In this example, coal petrography destabilizationThe mark of (2) comprises: the occurrence of coal rock dynamic disasters, the occurrence of high-energy mine earthquakes, the stress reaching the strength limit of coal rocks and the like; wherein, the high energy mine earthquake can be given by on-site monitoring, the high energy mine earthquake of different mines is different, generally the earthquake energy is more than 104~105J, mine shaking.
Next, the method for extracting coal rock instability precursor information features by using speech recognition provided in this embodiment is further described with reference to specific application scenarios:
in this embodiment, as shown in fig. 2, taking a coal sample taken from a certain coal mine as an example, firstly, making the coal sample into a standard coal sample, performing a loading (load) test on the coal sample in a laboratory, arranging an acoustic emission sensor (sonar) and a stress sensor on the coal sample, synchronously acquiring an acoustic emission full-waveform signal (short for acoustic emission signal) and a stress signal in the coal sample loading process, amplifying the acoustic emission signal (one of vibration wave signals) acquired by the acoustic emission sensor by using a signal amplifier (amplifier), and transmitting the amplified signal to a computer (computer), wherein the computer is provided with acoustic emission data acquisition software for acquiring and storing the acoustic emission signal; then, mining the collected signals by using a feature extraction technology in the field of voice recognition to obtain the precursor information features of coal rock instability, and specifically comprising the following steps:
(1) preparing an original coal block taken from a coal bed into a square columnar standard coal sample with the size of 50mm multiplied by 100mm, arranging an acoustic emission sensor and a stress sensor on the surface of the standard coal sample, carrying out a uniaxial compression test on a loading device shown in fig. 2, synchronously acquiring an acoustic emission full waveform signal and a stress signal in the coal sample loading process, wherein the acquired original acoustic emission full waveform signal is shown in fig. 3, load represents load, the unit is 'kN', and the unit is 'MPa'; AE amplitude represents the acoustic emission signal amplitude in "V"; time represents time in units of "s";
in the embodiment, the discrete Fourier transform is adopted to carry out frequency spectrum analysis on the collected acoustic emission signals, and the main frequency range of the acoustic emission signals is 50 kHz-300 kHz; through increasing the time interval of adjacent acoustic emission signal data point, the acoustic emission signal that will gather has stretched 45.5 times on the time axis, makes the collection frequency of acoustic emission signal change frequency 22kHz into by 1MHz, and the dominant frequency range changes the frequency band scope into the audio signal that the people's ear can experience: 133Hz to 6854 Hz; the frequency of the converted audio signal corresponding to the original acoustic emission signal is 6.0kHz to 311.5kHz, as shown in fig. 4, the frequency spectrum distribution of the acoustic emission signal in a period of 40ms intercepted at three moments of 20s, 30s and 40s of the original acoustic emission signal of the coal sample and the frequency band range corresponding to the converted audio signal, wherein frequency represents frequency and the unit is "Hz";
the converted audio signal is framed, each frame is set to be 2ms in length and comprises 2000 data points, adjacent frames are overlapped for 0.5ms, and 500 data points are contained, namely, the time interval between the adjacent frames is 1.5 ms.
(2) The method of the present invention is combined with the mfcc function programming of MATLAB to calculate the Mel cepstrum coefficients of all frame signals, the calculation steps of the Mel cepstrum coefficients are shown in FIG. 5, and the input parameters are shown in Table 1:
table 1 parameter information
(3) The cepstral coefficients are ordered in the order of the frames and with a time interval of 1.5ms between adjacent frames to obtain a time sequence distribution of the cepstral coefficients, and the results are shown in fig. 6(a) - (l), where MFCCs-j represents the jth parameter of mel cepstral coefficients, j is 1,2, …,12, stress represents stress, and the unit is "MPa".
(4) As can be seen from FIGS. 6(a) - (l), 4 Mel cepstrum coefficient parameters such as MFCCs-7, MFCCs-9, MFCCs-10, MFCCs-12 and the like have large fluctuation along with the coal sample loading process, are not obvious in regularity, and are not suitable for being used as parameters for representing the coal sample stability; the other 8 mel-frequency cepstrum coefficient parameters show obvious regularity before the coal sample is unstable, the 8 mel-frequency cepstrum coefficient parameters stably change along with the increase of the coal sample load and generate obvious discontinuity and mutation at the moment of the coal sample instability, the 8 mel-frequency cepstrum coefficient parameters have high correlation with the coal sample load, therefore, MFCCs-1, MFCCs-2, MFCCs-3, MFCCs-4, MFCCs-5, MFCCs-6, MFCCs-8 and MFCCs-11 are used as precursor indicators of coal rock instability, the law that MFCCs-1, MFCCs-4, MFCCs-6 and MFCCs-11 slowly increase and generate discontinuity and mutation is used as a precursor information characteristic of coal rock instability, and the law that MFCCs-2, MFCCs-3, MFCCs-5 and MFCCs-8 slowly decrease and generate discontinuity and mutation is also used as a precursor information characteristic of coal rock instability.
To sum up, in the embodiment of the present invention, a sensor arranged on a coal rock body is used to collect a vibration wave signal of the coal rock deformation and fracture process as original data, the vibration wave signal is converted into an audio signal which can be sensed by human ears, the audio signal is subjected to framing to obtain a frame signal, then, a feature extraction technology in the speech recognition field is used to obtain cepstrum coefficients of all the frame signals, all the cepstrum coefficients are arranged according to a time sequence and then a change rule of the cepstrum coefficients before coal rock instability is analyzed, and one or more parameters of the cepstrum coefficients which have high correlation with the coal rock instability and show stability are selected as a precursor index of the coal rock instability. Therefore, parameters capable of accurately representing the whole deformation and fracture process of the coal rock can be extracted from the original vibration wave signals, and the purpose of accurately identifying and extracting the precursor information characteristics of coal rock instability and further improving the monitoring and early warning accuracy rate of coal rock dynamic disasters is achieved.
The invention also provides a concrete implementation mode of the device for extracting the coal rock instability precursor information characteristics by utilizing the voice recognition, since the device for extracting the coal rock instability precursor information features by using voice recognition provided by the invention corresponds to the specific implementation mode of the method for extracting the coal rock instability precursor information features by using voice recognition, the device for extracting coal rock instability precursor information features by utilizing voice recognition can realize the aim of the invention by executing the flow steps in the concrete embodiment of the method, therefore, the explanation of the specific embodiment of the method for extracting coal rock instability precursor information features by using speech recognition is also applicable to the specific embodiment of the device for extracting coal rock instability precursor information features by using speech recognition, and will not be repeated in the following specific embodiment of the present invention.
As shown in fig. 7, an embodiment of the present invention further provides a device for extracting coal petrography instability precursor information features by using speech recognition, including:
the conversion module 11 is configured to convert a vibration wave signal in a coal rock deformation and fracture process into an audio signal and frame the audio signal to obtain a frame signal;
an obtaining module 12, configured to obtain cepstrum coefficients of all frame signals by using a feature extraction technology in the speech recognition field;
a sorting module 13, configured to sort all cepstral coefficients to obtain a time sequence distribution of the cepstral coefficients;
and the extraction module 14 is configured to analyze a change rule of the cepstrum coefficient before the coal rock instability according to the obtained time sequence distribution of the cepstrum coefficient, so as to obtain a precursor information feature of the coal rock instability.
The device for extracting the coal rock instability precursor information features by using voice recognition converts vibration wave signals in the coal rock deformation and fracture process into audio signals and frames the audio signals to obtain frame signals; obtaining cepstrum coefficients of all frame signals by utilizing a feature extraction technology in the field of voice recognition; sequencing all cepstral coefficients to obtain time sequence distribution of the cepstral coefficients; and analyzing the change rule of the cepstrum coefficient before the coal rock instability according to the obtained time sequence distribution of the cepstrum coefficient to obtain the precursor information characteristic of the coal rock instability. Therefore, the characteristic extraction technology in the field of voice recognition is applied to vibration wave signal analysis in the coal rock deformation and fracture process, so that the precursor information characteristic of coal rock instability is accurately extracted, the precursor information characteristic can be used for evaluating the coal rock stable state, the accuracy of coal rock dynamic disaster monitoring and early warning is improved, and the method has a positive effect on the coal rock dynamic disaster monitoring and early warning.
Fig. 8 is a schematic structural diagram of an electronic device 600 according to an embodiment of the present invention, where the electronic device 600 may generate relatively large differences due to different configurations or performances, and may include one or more processors (CPUs) 601 and one or more memories 602, where the memory 602 stores at least one instruction, and the at least one instruction is loaded and executed by the processor 601 to implement the method for extracting coal petrography instability precursor information features by using voice recognition.
In an exemplary embodiment, a computer-readable storage medium, such as a memory, including instructions executable by a processor in a terminal to perform the above method for extracting coal petrography instability precursor information features using speech recognition is also provided. For example, the computer readable storage medium may be a ROM, a Random Access Memory (RAM), a CD-ROM, a magnetic tape, a floppy disk, an optical data storage device, and the like.
It will be understood by those skilled in the art that all or part of the steps for implementing the above embodiments may be implemented by hardware, or may be implemented by a program instructing relevant hardware, where the program may be stored in a computer-readable storage medium, and the above-mentioned storage medium may be a read-only memory, a magnetic disk or an optical disk, etc.
The above description is only for the purpose of illustrating the preferred embodiments of the present invention and is not to be construed as limiting the invention, and any modifications, equivalents, improvements and the like that fall within the spirit and principle of the present invention are intended to be included therein.
Claims (10)
1. A method for extracting coal rock instability precursor information features by using voice recognition is characterized by comprising the following steps:
converting a vibration wave signal in the coal rock deformation and fracture process into an audio signal and framing the audio signal to obtain a frame signal;
obtaining cepstrum coefficients of all frame signals by utilizing a feature extraction technology in the field of voice recognition;
sequencing all cepstral coefficients to obtain time sequence distribution of the cepstral coefficients;
and analyzing the change rule of the cepstrum coefficient before the coal rock instability according to the obtained time sequence distribution of the cepstrum coefficient to obtain the precursor information characteristic of the coal rock instability.
2. The method for extracting coal rock instability precursor information features by utilizing speech recognition as claimed in claim 1, wherein before converting the vibration wave signal of the coal rock deformation and fracture process into the audio signal and framing the audio signal to obtain the frame signal, the method comprises:
arranging sensors on the coal rock mass, and acquiring vibration wave signals of the coal rock deformation and fracture process through the arranged sensors;
wherein, the shock wave signal refers to a series of independent shock waves or a continuous shock wave full waveform.
3. The method for extracting coal rock instability precursor information features by utilizing voice recognition as claimed in claim 1, wherein the converting the vibration wave signal of the coal rock deformation and fracture process into the audio signal comprises:
carrying out frequency spectrum analysis on the collected shock wave signal to obtain a main frequency range of the shock wave signal;
the time interval of adjacent shock wave signal data points is adjusted according to the frequency band range of the audio signal which can be felt by human ears, the shock wave signal is zoomed on a time axis, the main frequency range of the shock wave signal is consistent with the frequency band range of the audio signal which can be felt by human ears, and therefore the collected shock wave signal is converted into the audio signal which can be felt by human ears.
4. The method for extracting coal petrography instability precursor information features through voice recognition according to claim 3, wherein the conversion function of converting the collected shock wave signal into an audio signal which can be felt by human ears is as follows:
wherein f isα、fαl、fαhThe original frequency of the vibration wave signal, the lower limit and the upper limit of the main frequency range of the vibration wave signal, fβ、fβl、fβhRespectively converting vibration wave signals into audio signalsThe frequency of the audio signal after the signal, the lower limit and the upper limit of the frequency band range of the audio signal which can be felt by human ears, and lambda is the signal scaling multiple.
5. The method of extracting coal petrography instability precursor information features by using speech recognition according to claim 1, wherein the framing the audio signal to obtain a frame signal comprises:
if the vibration wave signals are independent vibration waves, taking each independent vibration wave waveform as a frame signal;
if the vibration wave signal is a continuous vibration wave full waveform, the vibration wave full waveform is divided into segments with equal length, a section of length is overlapped between adjacent segments, and the vibration wave full waveform is converted into a frame signal, namely:
wherein, x (t) is the full waveform of the vibration wave; n is the length of each frame of data; r is the number of frames, and the calculation formula of R is as follows:
wherein L isxIs the length of the shock wave signal, L is the overlap length between adjacent frames [. degree]Is a rounding function;
let x be the R-th frame signal, x [ n ] be the n-th value in the frame signal x, R is greater than or equal to 0 and less than or equal to R-1, then x [ n ], x are:
x[n]=x[r(N-L)+n],n=0,1,2,…,N-1
x={x[r(N-L)],x[r(N-L)+1],…,x[r(N-L)+N-1]}。
6. the method for extracting coal petrography instability precursor information features by using voice recognition according to claim 1, wherein the obtaining cepstrum coefficients of all frame signals by using a feature extraction technology in the field of voice recognition comprises:
b1, performing window function processing on a certain frame signal x to obtain a signal x', wherein the calculation formula is as follows:
x′=wx
wherein w is a window function;
b2, extracting the short-time energy spectrum W of the signal x' using discrete fourier transform, the calculation formula is:
wherein, W [ k ] is the kth value of the short-time energy spectrum W, N is the length of each frame of data, and x 'N is the nth value of x';
b3, filtering the short-time energy spectrum W by using a filter bank to obtain an energy signal W' in a corresponding frequency domain, wherein the calculation formula is as follows:
wherein, W' [ m ]]Is the mth value of W', M is the total number of filters of the filter bank, H is the filter bank, Hm[k]For the kth value of the mth filter transfer function;
b4, solving the logarithm of the energy signal W' to obtain a signal S, wherein the calculation formula is as follows:
S[m]=log10W′[m],m=0,1,2,…,M-1
wherein Sm is the mth value of S;
b5, performing discrete cosine transform on the signal S to obtain a cepstrum coefficient MFCC of the frame signal x, where the calculation formula is:
wherein, MFCC [ C ] is the C-th parameter of the cepstrum coefficient MFCC, C is the number of the parameters of the cepstrum coefficient MFCC, ac is the orthogonal coefficient, and the calculation formula of ac is:
and B6, repeating the steps B1 to B5 to obtain cepstrum coefficients of all the frame signals.
7. The method for extracting coal petrography instability precursor information features by using speech recognition as claimed in claim 6, wherein the window function can be a cone window function, and the calculation formula is as follows:
wherein, w [ n ]]Is the nth value of the cone window function, LwIs the window length, LwN, α is the window coefficient.
8. The method of extracting coal petrography instability precursor information features through voice recognition according to claim 6, wherein the frequency band range of the filter bank is consistent with the frequency band range of audio signals that can be felt by human ears;
the filter bank is a Mel filter bank, the Mel filter bank is composed of M triangular band-pass filters, and the transfer function of each triangular band-pass filter is as follows:
where M is 0,1,2, …, M-1, k is 1,2, …, N/2-1, f (M) is the center frequency of the triangular band-pass filter.
9. The method of extracting coal petrography instability precursor information features by using speech recognition according to claim 1, wherein the step of sorting all cepstral coefficients to obtain a time sequence distribution of the cepstral coefficients comprises:
if the vibration wave signals are independent vibration waves, the occurrence time of the vibration waves is used as the time of cepstrum coefficients of the frame signals, and the cepstrum coefficients are sequenced according to the time sequence to obtain the time sequence distribution of the cepstrum coefficients;
if the vibration wave signal is a continuous vibration wave full waveform, sequencing the cepstrum coefficients according to the sequence of frames and the time interval between adjacent frames to obtain the time sequence distribution of the cepstrum coefficients, wherein the time interval T isMThe calculation formula of (2) is as follows:
wherein f isxN is the length of each frame of data, and L is the overlap length between adjacent frames.
10. A coal petrography instability precursor information feature extraction device utilizing voice recognition is characterized by comprising the following steps:
the conversion module is used for converting the vibration wave signals in the coal rock deformation and fracture process into audio signals and framing the audio signals to obtain frame signals;
the acquisition module is used for acquiring cepstrum coefficients of all frame signals by utilizing a feature extraction technology in the field of voice recognition;
the sequencing module is used for sequencing all cepstrum coefficients to obtain time sequence distribution of the cepstrum coefficients;
and the extraction module is used for analyzing the change rule of the cepstrum coefficient before the coal rock instability according to the obtained time sequence distribution of the cepstrum coefficient to obtain the precursor information characteristic of the coal rock instability.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202010680193.5A CN111916091B (en) | 2020-07-15 | 2020-07-15 | Method and device for extracting coal rock instability precursor information features by utilizing voice recognition |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202010680193.5A CN111916091B (en) | 2020-07-15 | 2020-07-15 | Method and device for extracting coal rock instability precursor information features by utilizing voice recognition |
Publications (2)
Publication Number | Publication Date |
---|---|
CN111916091A true CN111916091A (en) | 2020-11-10 |
CN111916091B CN111916091B (en) | 2022-06-17 |
Family
ID=73280117
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202010680193.5A Active CN111916091B (en) | 2020-07-15 | 2020-07-15 | Method and device for extracting coal rock instability precursor information features by utilizing voice recognition |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN111916091B (en) |
Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US5136551A (en) * | 1989-03-23 | 1992-08-04 | Armitage Kenneth R L | System for evaluation of velocities of acoustical energy of sedimentary rocks |
CN102253414A (en) * | 2011-06-20 | 2011-11-23 | 成都理工大学 | Reservoir detecting method based on analysis of earthquake lines |
CN110308485A (en) * | 2019-07-05 | 2019-10-08 | 中南大学 | Microseismic signals classification method, device and storage medium based on deep learning |
-
2020
- 2020-07-15 CN CN202010680193.5A patent/CN111916091B/en active Active
Patent Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US5136551A (en) * | 1989-03-23 | 1992-08-04 | Armitage Kenneth R L | System for evaluation of velocities of acoustical energy of sedimentary rocks |
CN102253414A (en) * | 2011-06-20 | 2011-11-23 | 成都理工大学 | Reservoir detecting method based on analysis of earthquake lines |
CN110308485A (en) * | 2019-07-05 | 2019-10-08 | 中南大学 | Microseismic signals classification method, device and storage medium based on deep learning |
Non-Patent Citations (3)
Title |
---|
"《国际地震动态》2012年总目录索引", 《国际地震动态》 * |
刘鑫锦等: "基于声音信号的室内岩爆动态预测方法", 《岩土力学》 * |
李振雷等: "煤冲击破坏过程规律及同源声电相应特征", 《岩石力学与工程学报》 * |
Also Published As
Publication number | Publication date |
---|---|
CN111916091B (en) | 2022-06-17 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN110308485B (en) | Microseismic signal classification method and device based on deep learning and storage medium | |
Ding et al. | Feature extraction, recognition, and classification of acoustic emission waveform signal of coal rock sample under uniaxial compression | |
US4905285A (en) | Analysis arrangement based on a model of human neural responses | |
US20210193149A1 (en) | Method, apparatus and device for voiceprint recognition, and medium | |
Liu et al. | Cough signal recognition with gammatone cepstral coefficients | |
Wang et al. | Acoustic emission characteristics of coal failure using automatic speech recognition methodology analysis | |
CN109409308A (en) | A method of the birds species identification based on birdvocalization | |
CN106992011A (en) | Engineering machinery sound identification method based on MF PLPCC features | |
Lesage | Interactive Matlab software for the analysis of seismic volcanic signals | |
CN111696580A (en) | Voice detection method and device, electronic equipment and storage medium | |
Hall et al. | Identification of transient vibration characteristics of pile-group models during liquefaction using wavelet transform | |
CN111916091B (en) | Method and device for extracting coal rock instability precursor information features by utilizing voice recognition | |
CN117542373A (en) | Non-air conduction voice recovery system and method | |
Cabrera et al. | PsySound3: a program for the analysis of sound recordings | |
Jiang et al. | An improved method of local mean decomposition with adaptive noise and its application to microseismic signal processing in rock engineering | |
Xie et al. | Acoustic feature extraction using perceptual wavelet packet decomposition for frog call classification | |
Wang et al. | A novel acoustic emission parameter for predicting rock failure during Brazilian test based on cepstrum analysis | |
Zhang et al. | Computer-assisted sampling of acoustic data for more efficient determination of bird species richness | |
CN112908343B (en) | Acquisition method and system for bird species number based on cepstrum spectrogram | |
Jia et al. | Study on infrasonic characteristics of coal samples in failure process under uniaxial loading | |
US20120006183A1 (en) | Automatic analysis and manipulation of digital musical content for synchronization with motion | |
CN113782054A (en) | Method and system for automatically identifying lightning whistle sound waves based on intelligent voice technology | |
Su et al. | A two-step method for predicting rockburst using sound signals | |
CN111915844B (en) | Method and device for evaluating coal rock stability by analyzing vibration signal through cepstrum coefficient | |
Tun | Audio feature extraction using mel-frequency cepstral coefficients |
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 |