CN114487952A - Quench detection system and method using acoustic optical fiber - Google Patents
Quench detection system and method using acoustic optical fiber Download PDFInfo
- Publication number
- CN114487952A CN114487952A CN202210388965.7A CN202210388965A CN114487952A CN 114487952 A CN114487952 A CN 114487952A CN 202210388965 A CN202210388965 A CN 202210388965A CN 114487952 A CN114487952 A CN 114487952A
- Authority
- CN
- China
- Prior art keywords
- signal
- optical fiber
- sound
- analysis server
- voiceprint analysis
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000010791 quenching Methods 0.000 title claims abstract description 54
- 238000001514 detection method Methods 0.000 title claims abstract description 41
- 239000013307 optical fiber Substances 0.000 title claims abstract description 41
- 238000000034 method Methods 0.000 title claims abstract description 26
- 239000013598 vector Substances 0.000 claims abstract description 40
- 238000004458 analytical method Methods 0.000 claims abstract description 38
- 230000005236 sound signal Effects 0.000 claims abstract description 24
- 239000000835 fiber Substances 0.000 claims abstract description 19
- 238000004891 communication Methods 0.000 claims abstract description 16
- 230000003287 optical effect Effects 0.000 claims abstract description 14
- 238000004364 calculation method Methods 0.000 claims abstract description 11
- 238000004422 calculation algorithm Methods 0.000 claims description 18
- 230000009467 reduction Effects 0.000 claims description 17
- 238000005457 optimization Methods 0.000 claims description 14
- 238000013139 quantization Methods 0.000 claims description 12
- 238000009432 framing Methods 0.000 claims description 11
- 230000008569 process Effects 0.000 claims description 8
- 239000011159 matrix material Substances 0.000 claims description 6
- 238000007781 pre-processing Methods 0.000 claims description 6
- 230000009466 transformation Effects 0.000 claims description 6
- 238000001914 filtration Methods 0.000 claims description 5
- 238000012423 maintenance Methods 0.000 abstract 1
- 238000003745 diagnosis Methods 0.000 description 7
- 238000012549 training Methods 0.000 description 6
- 238000005516 engineering process Methods 0.000 description 4
- 238000004804 winding Methods 0.000 description 4
- 230000008859 change Effects 0.000 description 3
- 230000007547 defect Effects 0.000 description 3
- 230000004927 fusion Effects 0.000 description 3
- 230000000171 quenching effect Effects 0.000 description 3
- 238000013528 artificial neural network Methods 0.000 description 2
- 238000012850 discrimination method Methods 0.000 description 2
- 238000005259 measurement Methods 0.000 description 2
- 230000004044 response Effects 0.000 description 2
- 230000035945 sensitivity Effects 0.000 description 2
- 238000004590 computer program Methods 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 230000008878 coupling Effects 0.000 description 1
- 238000010168 coupling process Methods 0.000 description 1
- 238000005859 coupling reaction Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 238000009826 distribution Methods 0.000 description 1
- 238000004146 energy storage Methods 0.000 description 1
- 238000002474 experimental method Methods 0.000 description 1
- 238000000605 extraction Methods 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 230000006698 induction Effects 0.000 description 1
- 230000010354 integration Effects 0.000 description 1
- 238000010801 machine learning Methods 0.000 description 1
- 230000008447 perception Effects 0.000 description 1
- 238000012545 processing Methods 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 238000005070 sampling Methods 0.000 description 1
- 239000000126 substance Substances 0.000 description 1
- 239000002887 superconductor Substances 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01R—MEASURING ELECTRIC VARIABLES; MEASURING MAGNETIC VARIABLES
- G01R33/00—Arrangements or instruments for measuring magnetic variables
- G01R33/12—Measuring magnetic properties of articles or specimens of solids or fluids
- G01R33/1238—Measuring superconductive properties
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01H—MEASUREMENT OF MECHANICAL VIBRATIONS OR ULTRASONIC, SONIC OR INFRASONIC WAVES
- G01H9/00—Measuring mechanical vibrations or ultrasonic, sonic or infrasonic waves by using radiation-sensitive means, e.g. optical means
- G01H9/004—Measuring mechanical vibrations or ultrasonic, sonic or infrasonic waves by using radiation-sensitive means, e.g. optical means using fibre optic sensors
-
- 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
- G10L25/30—Speech or voice analysis techniques not restricted to a single one of groups G10L15/00 - G10L21/00 characterised by the analysis technique using neural networks
-
- 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
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Health & Medical Sciences (AREA)
- Signal Processing (AREA)
- Audiology, Speech & Language Pathology (AREA)
- Human Computer Interaction (AREA)
- Computational Linguistics (AREA)
- Acoustics & Sound (AREA)
- Multimedia (AREA)
- General Physics & Mathematics (AREA)
- Condensed Matter Physics & Semiconductors (AREA)
- Artificial Intelligence (AREA)
- Evolutionary Computation (AREA)
- Measurement Of Mechanical Vibrations Or Ultrasonic Waves (AREA)
Abstract
The invention provides a quench detection system using acoustic fiber, comprising: the system comprises an acousto-optic fiber wire, an optical fiber sound monitor and a voiceprint analysis server; one end of the acoustic optical fiber wire is wound on the outer ring of the superconducting magnet, and the other end of the acoustic optical fiber wire is connected to an optical transceiving port of the optical fiber sound monitor; the data communication port of the optical fiber sound monitor is connected with the voiceprint analysis server; the optical signal that the optic fibre sound monitor sent has partial signal reflection to the optic fibre sound monitor through the rayleigh reflection, and optic fibre sound monitor restores the reflected light signal into sound signal, transmits to the voiceprint analysis server afterwards, carries out the voiceprint analysis to sound signal by the voiceprint analysis server. The voice print recognition method based on the MFCC vector performs voice print recognition through voice print sensing, and has the advantages of high detection precision, strong anti-interference capability, high calculation speed and low maintenance cost.
Description
Technical Field
The invention relates to the technical field of quench detection for a superconducting magnet, in particular to a method for carrying out quench diagnosis on the superconducting magnet by using an acoustic fiber as a sensor and adopting a voiceprint recognition technology.
Background
A major breakthrough in the research of controllable thermonuclear fusion energy is to successfully apply the superconducting technology to the coil generating the Tokamak strong magnetic field. The full-superconducting Tokamak can realize steady-state operation, and lays engineering technology and physical foundation for future steady-state and advanced fusion reactors by greatly improving constraint under steady-state operation conditions. Future commercial stacks must therefore be fully superconducting to achieve steady state operation.
The superconducting magnet system is also one of the most important and most expensive components (accounting for 25 percent of the total cost) of the superconducting fusion device, once the superconducting magnet is quenched, the extremely high electromagnetic heat stored in the superconductor is converted into the heat energy, the quenching protection is not timely, the magnet is irreversibly damaged within a few seconds, the superconducting device cannot operate, and huge economic loss is produced! Therefore, the quench diagnosis and protection system is the highest level of guarantee for ensuring the safe operation of the large superconducting device.
When the magnet is quenched, a series of physical quantities such as resistance value, temperature, pressure and the like can be changed, and the quenching diagnosis is that the physical quantities are converted into electric signals to be used as a quenching judgment basis. The conventional superconducting coil superconducting diagnosis method mainly comprises the following steps: resistance voltage detection, temperature rise detection, pressure detection, flow detection, ultrasonic detection, and the like.
The temperature rise detection method is used for judging the quench by detecting the temperature change or the temperature change rate of the superconducting coil in real time, such as a superconducting energy storage system SMSE (simple substance integration) of a department of Chinese academy of sciences, and the detection method is close to the essence of a physical phenomenon, and is high in detection speed and sensitivity. But face many temperature distribution points, and simultaneously require that the temperature sensor and the subsequent measurement system have very high measurement accuracy and stability.
The pressure and flow detection is also the basis for mainly judging quench, but has the defects of slow response, delay and non-single influence factor of the sensor. Voltage detection methods are more commonly used in quench detection depending on the difficulty of the detection circuit construction. The voltage detection method quench is judged according to the principle that the voltage of a superconducting detection signal exceeds a threshold voltage and the quench is determined to occur after a set delay time.
The most commonly used voltage threshold discrimination methods include bridge methods and co-winding detection methods. The quench detection method utilizes the Wheatstone bridge balance principle to obtain quench detection signals, and has the advantages of convenient use and less quench detection circuits, but on one hand, quench detection blind spots exist, and on the other hand, the anti-electromagnetic interference capability is not strong. The quench detection method is mainly applied to EAST devices of plasma institute of Chinese academy of sciences, and utilizes quench detection sampling circuit formed by co-winding of co-winding and superconducting coils to obtain reference voltage signal, and at the same time utilizes sensors to respectively measure current differential signal of all electrified coils as secondary compensation voltage, and adds the secondary compensation voltage and reference voltage according to a certain compensation coefficient to counteract induction voltage produced by coupling of self coil and other quick alternating coils, and uses the voltage obtained after addition as quench detection quantity. The method can realize quench detection in the environment of rapidly changing magnetic field, but has the defect that once the same winding is broken, the line can not be repaired.
In summary, the conventional quench diagnosis techniques all have certain technical defects, and in particular, in the aspects of quench positioning, quench early warning and quench auxiliary judgment, the importance of quench diagnosis on large-scale superconducting devices is considered, and a more effective diagnosis technique is needed as effective compensation in the prior art.
Disclosure of Invention
In view of the above drawbacks and the improvement needs of the prior art, the present invention provides a method for diagnosing quench of a superconducting magnet by using an acoustic fiber as a sensor and using a voiceprint recognition technique. The superconducting magnet armor has the advantages that the superconducting magnet armor only needs to be laid outside the superconducting magnet armor, is high-voltage resistant and anti-electromagnetic interference, is high in sensitivity, shortens the response time by 20%, is high in true quench discrimination accuracy, and can be used as a quench positioning and auxiliary quench discrimination method.
In order to solve the above technical problem, the present invention provides a quench detection system using an acoustic optical fiber, the system including: the system comprises an acousto-optic fiber wire, an optical fiber sound monitor and a voiceprint analysis server; one end of the acoustic optical fiber wire is wound on the outer ring of the superconducting magnet, and the other end of the acoustic optical fiber wire is connected to an optical transceiving port of the optical fiber sound monitor; the data communication port of the optical fiber sound monitor is connected with the voiceprint analysis server; the optical signal that the optic fibre sound monitor sent has partial signal reflection to the optic fibre sound monitor through the rayleigh reflection, and optic fibre sound monitor restores the reflected light signal into sound signal, transmits to the voiceprint analysis server afterwards, carries out the voiceprint analysis to sound signal by the voiceprint analysis server.
Furthermore, the optical fiber sound monitor comprises a light emitting unit, a light receiving unit, an amplifying unit, a demodulating unit and a communication unit, wherein the light emitting unit emits a light signal according to a certain frequency, the light signal is deformed when encountering a sound wave generated by a magnet in the process of advancing in an optical fiber wire, part of the light signal is reflected back to the optical fiber sound monitor after Rayleigh reflection, and the reflected light signal is obtained after the light signal is received and processed by the light receiving unit and the amplifying unit; the demodulation unit restores the reflected light signal to a sound signal, and then the communication unit transmits the sound signal and the length information to the voiceprint analysis server. The communication unit comprises an Ethernet communication unit, a WIFI module, a 4G module, a 5G module and the like. The voiceprint analysis server firstly performs weighted dimension reduction optimization on the voice signals based on the MFCC characteristic vectors, secondly identifies the optimized voice signals by applying a vector quantization algorithm, and finally judges whether the quench occurs.
The invention also provides a quench detection method using the acoustic fiber, which applies the system and comprises the following steps:
step S1, the optical fiber sound monitor sends out optical signals;
step S2, the optical fiber sound monitor receives the reflected light signal and restores the reflected light signal into a sound signal;
s3, the voiceprint analysis server performs weighted dimension reduction optimization on the voice signal based on the MFCC feature vector;
and step S4, the voiceprint analysis server identifies the optimized voice signal by using a vector quantization algorithm, and finally judges whether the quench occurs.
The step S3 includes a voiceprint preprocessing step including:
step 31, framing the voiceprint signal, wherein the framing relation is expressed as M = n-Lb/[ L (1-b) ], where M is the frame number, n is the audio signal length, L is the frame length, and b is the overlap ratio; preferably, 20ms is taken as the frame length L of one frame, and 40% is taken as the overlapping rate b;
and step 32, respectively calculating MFCC characteristic vectors from the framing signals to form a characteristic vector group, wherein the calculation process comprises FFT (fast Fourier transform), Mel (Mel Filter), logarithmic transformation and discrete cosine transformation.
The step S3 further includes performing dimension reduction optimization on the preprocessed sound signal: specifically, the dimensionality reduction and simplification are carried out on the high-dimensional MFCC vector obtained through calculation through a PCA algorithm; the Mel filtering and PCA algorithm are described in detail in the description of the embodiments.
Further, the voiceprint analysis server analyzes the target signal to obtain a dimension-reduced optimized target MFCC feature vector v, v1, …, vh, variance contribution rate and accumulated variance contribution rate, and inputs the feature vector v, v1, …, vh, variance contribution rate and accumulated variance contribution rate into a trained vector quantization algorithm, and finally obtains a quench determination result.
The detection system and the detection method provided by the invention can be used for carrying out superconducting quench detection based on the voiceprint recognition technology, the detection system and the superconducting system are relatively independent, faults cannot occur in the superconducting system, and the overhaul cost is low; meanwhile, the invention carries out comprehensive judgment through the MFCC vector and the neural network, can extract the depth information of the fault, and has high detection precision and strong anti-interference capability; finally, in the voiceprint analysis process, the invention utilizes dimension reduction optimization, further reduces the calculated amount while ensuring the precision and improves the calculation efficiency.
Additional features and advantages of the invention will be set forth in the description which follows, and in part will be obvious from the description, or may be learned by practice of the invention. The objectives and other advantages of the invention will be realized and attained by the structure particularly pointed out in the written description and claims hereof as well as the appended drawings.
Drawings
The accompanying drawings are included to provide a further understanding of the invention and are incorporated in and constitute a part of this specification, illustrate embodiments of the invention and together with the example serve to explain the principles of the invention and not to limit the invention.
FIG. 1 is a schematic diagram of a system provided by an embodiment of the present invention;
fig. 2 is a voiceprint analysis graph and a current comparison graph of timeout provided by an embodiment of the invention.
Detailed Description
For the purpose of making the present invention more comprehensible, and for the purpose of making the present application more comprehensible, embodiments and advantages thereof, the present invention will be further described with reference to the accompanying drawings. It should be understood that the specific embodiments described herein are merely illustrative of the invention and are not intended to limit the invention. It should be noted that the embodiments and features of the embodiments in the present application may be arbitrarily combined with each other without conflict.
The present invention provides a quench detection system using an acoustic optical fiber, as shown in fig. 1, the system including: the system comprises an acousto-optic fiber wire, an optical fiber sound monitor and a voiceprint analysis server; one end of the acoustic optical fiber wire is wound on the outer ring of the superconducting magnet, and the other end of the acoustic optical fiber wire is connected to an optical transceiving port of the optical fiber sound monitor; and a data communication port of the optical fiber sound monitor is connected with the voiceprint analysis server.
The optical fiber sound monitor comprises a light emitting unit, a light receiving unit, an amplifying unit, a demodulating unit and a communication unit, wherein the light emitting unit emits light signals according to a certain frequency, the light signals are deformed (can be regarded as modulation of the sound waves on the light signals) when encountering the sound waves generated by a magnet in the process of advancing in an optical fiber wire, part of the light signals are reflected back to the optical fiber sound monitor through Rayleigh reflection, the reflected light signals are obtained after receiving and processing through the light receiving unit and the amplifying unit, the demodulating unit reduces the reflected light signals into sound signals, then the communication unit transmits the sound signals and length information to a voiceprint analysis server, and the voiceprint analysis server performs voiceprint analysis on the sound signals.
Preferably, the communication unit includes an ethernet communication unit, a WIFI module, a 4G module, a 5G module, and the like.
The voiceprint analysis server firstly performs weighted dimension reduction optimization on the voice signals based on the MFCC characteristic vectors, secondly identifies the optimized voice signals by applying a vector quantization algorithm, and finally judges whether the quench occurs.
Further, the invention also provides a quench detection method using the acoustic optical fiber, which relies on the quench detection system, and the method comprises the following steps:
step S1, the optical fiber sound monitor sends out optical signals;
step S2, the optical fiber sound monitor receives the reflected light signal and restores the reflected light signal into a sound signal;
s3, the voiceprint analysis server performs weighted dimension reduction optimization on the voice signal based on the MFCC feature vector;
and step S4, the voiceprint analysis server identifies the optimized voice signal by using a vector quantization algorithm, and finally judges whether the quench occurs.
Preferably, the weighted dimension reduction optimization of the sound signal comprises voiceprint preprocessing and dimension reduction optimization.
Firstly, a voiceprint preprocessing step: the voiceprint preprocessing comprises two substeps of framing and windowing.
(1) When framing a voiceprint signal, two frames are generally overlapped to ensure continuity between two adjacent frames. The framing relationship can be expressed as M = n-Lb/[ L (1-b) ],
where M is the number of frames, n is the audio signal length, L is the frame length, and b is the overlap ratio.
When detecting quench with voiceprint, it is preferable to take 20ms as the frame length L and 40% as the overlap rate b.
(2) The preprocessed signals need discrete Fourier transform, specifically, a Hamming window is applied to each frame signal and then discrete Fourier transform is performed to increase continuity of two ends of the signals, so that distortion caused by Fourier transform is reduced.
Wherein the MFCC coefficients are based on cepstral coefficients of the Mel frequency domain, wherein the Mel frequency is a frequency domain transformed according to the human auditory perception characteristics: b (h) =25951g (1 h/700).
And respectively solving MFCC characteristic vectors from the frame signals to form a characteristic vector group, wherein the solving process comprises FFT (fast Fourier transform), Mel filtering, logarithmic transformation and discrete cosine transformation.
Furthermore, the Mel filtering is implemented by a filter bank consisting of a plurality of triangular band-pass filters. Setting the number of filters as p, obtaining p parameters after filtering the signalThe calculation formula is as follows:
n is the number of FFT points, X (k) is the FFT of the preprocessed framed signal, Hi(k) As filter parameters, it can be expressed as:
wherein: f [ i ] is the center frequency of the triangular filter;
and after mi is obtained through calculation, taking a logarithm of the mi, performing discrete cosine transform, and obtaining a result c (i) which is the MFCC feature vector of the framing signal.
Secondly, dimension reduction and optimization: in analyzing the sound signal, the higher MFCC feature vector dimension can ensure sufficient extraction of the sound signal features, but too high dimension also consumes a lot of computation time and increases the computational complexity. In order to improve the calculation efficiency, the calculated high-dimensional MFCC vector is subjected to dimensionality reduction and simplification through a PCA algorithm, and meanwhile, the accuracy of the features is ensured.
The PCA algorithm is as follows:
(1) e eigenvectors are set to form a matrix G, the dimension of each eigenvector is h, and G can be expressed as:
The eigenvalue of the correlation matrix R is calculated according to the aboveAnd corresponding feature vectors。
(3) Calculating variance contribution rate and accumulated variance contribution rate, which are respectively:
by means of vector quantization algorithm prediction of the feature data and the audio features during quench, the occurrence of quench can be accurately judged.
By combining the voiceprint analysis chart and the current comparison chart of the quench time shown in fig. 2, experiments prove that the detection system can accurately judge the quench occurrence based on the analysis of the voiceprint.
At the same time, it was also observed experimentally: at present, the interference of the magnetic field strength to the sensor is tested, but the interference strength is kept at a lower level, the influence on the receiving of a normal voiceprint signal is avoided, and the optical fiber is not interfered by the change of the magnetic field at all, so that the anti-interference capability of the application is further verified.
Further, the vector quantization algorithm is obtained by a neural network training, and comprises the following processes:
selecting a voiceprint training set, executing the first step and the second step on the training set to obtain an MFCC feature vector, a variance contribution rate and an accumulated variance contribution rate after dimension reduction optimization, and calibrating the training set;
secondly, training a machine learning model by taking the MFCC characteristic vectors (v, v1, …, vh) after the dimensionality reduction optimization of the training set, the variance contribution rate and the accumulated variance contribution rate as input and taking the corresponding quench result as output to obtain a trained vector quantization algorithm;
and (III) inputting the dimensionality-reduced optimized target MFCC feature vector, the variance contribution rate and the accumulated variance contribution rate which are obtained by analyzing the target signal by the voiceprint analysis server into a vector quantization algorithm, and finally obtaining a quench judgment result.
The invention also provides various programmable processors (FPGA, ASIC or other integrated circuits) for running programs, wherein the steps in the above embodiments are performed when the programs are run.
The invention also provides corresponding computer equipment, which comprises a memory, a processor and a computer program which is stored on the memory and can run on the processor, wherein the steps in the embodiment are realized when the memory executes the program.
Although the embodiments of the present invention have been described above, the above description is only for the convenience of understanding the present invention, and is not intended to limit the present invention. It will be understood by those skilled in the art that various changes in form and details may be made therein without departing from the spirit and scope of the invention as defined by the appended claims. Therefore, the scope of the present invention should be determined by the following claims.
Claims (10)
1. A quench detection system utilizing an acoustic fiber, the system comprising: the system comprises an acousto-optic fiber wire, an optical fiber sound monitor and a voiceprint analysis server; one end of the acoustic optical fiber wire is wound on the outer ring of the superconducting magnet, and the other end of the acoustic optical fiber wire is connected to an optical transceiving port of the optical fiber sound monitor; the data communication port of the optical fiber sound monitor is connected with the voiceprint analysis server;
the optical signal that the optic fibre sound monitor sent has partial signal reflection to the optic fibre sound monitor through the rayleigh reflection, and optic fibre sound monitor restores the reflected light signal into sound signal, transmits to the voiceprint analysis server afterwards, carries out the voiceprint analysis to sound signal by the voiceprint analysis server.
2. The system of claim 1, wherein: the optical fiber sound monitor comprises a light emitting unit, a light receiving unit, an amplifying unit, a demodulating unit and a communication unit,
the optical signal is deformed when encountering the sound wave generated by the magnet in the process of moving in the optical fiber wire, the optical signal is reflected back to the optical fiber sound monitor by Rayleigh reflection and part of the signal is received by the optical receiving unit and the amplifying unit to obtain a reflected optical signal;
the demodulation unit restores the reflected light signal to a sound signal, and then the communication unit transmits the sound signal and the length information to the voiceprint analysis server.
3. The system of claim 2, wherein: the communication unit comprises an Ethernet communication unit, a WIFI module, a 4G module, a 5G module and the like.
4. The system of any one of claims 1-3, wherein: the voiceprint analysis server firstly performs weighted dimension reduction optimization on the voice signals based on the MFCC characteristic vectors, secondly identifies the optimized voice signals by applying a vector quantization algorithm, and finally judges whether the quench occurs.
5. A quench detection method using an acoustic fiber, using the system according to any of claims 1-4, characterized in that the method comprises the steps of:
step S1, the optical fiber sound monitor sends out optical signals;
step S2, the optical fiber sound monitor receives the reflected light signal and restores the reflected light signal into a sound signal;
s3, the voiceprint analysis server performs weighted dimension reduction optimization on the voice signal based on the MFCC feature vector;
and step S4, the voiceprint analysis server identifies the optimized voice signal by using a vector quantization algorithm, and finally judges whether the quench occurs.
6. The method according to claim 5, wherein the step S3 includes a voiceprint preprocessing step, the voiceprint preprocessing step including:
step 31, framing the voiceprint signal, wherein the framing relation is expressed as M = n-Lb/[ L (1-b) ], where M is the frame number, n is the audio signal length, L is the frame length, and b is the overlap ratio;
and step 32, respectively calculating MFCC characteristic vectors from the framing signals to form a characteristic vector group, wherein the calculation process comprises FFT (fast Fourier transform), Mel (Mel Filter), logarithmic transformation and discrete cosine transformation.
7. The method of claim 6, wherein: the Mel filtering is realized by a filter bank composed of a plurality of triangular band-pass filters, the number of the filters is p, and p parameters can be obtained after the signals are filteredThe calculation formula is as follows:
n is the number of FFT points, X (k) is the FFT of the preprocessed framed signal, Hi(k) Is the filter parameter, expressed as:
wherein: f [ i ] is the center frequency of the triangular filter;
and after mi is obtained through calculation, taking a logarithm of the mi, performing discrete cosine transform, and obtaining a result c (i) which is the MFCC feature vector of the framing signal.
8. The method according to claim 5 or 6, wherein the step S3 further comprises performing dimension reduction optimization on the preprocessed sound signals: specifically, the dimensionality reduction and simplification are carried out on the high-dimensional MFCC vector obtained through calculation through a PCA algorithm;
the PCA algorithm is as follows:
(1) e eigenvectors are set to form a matrix G, the dimension of each eigenvector is h, and G can be expressed as:
The eigenvalue of the correlation matrix R is calculated according to the aboveAnd corresponding feature vectors;
(3) Calculating variance contribution rate and accumulated variance contribution rate, which are respectively:
9. the method of claim 8, wherein the dimension-reduced optimized target MFCC feature vectors v, v1, …, vh, the variance contribution rate and the accumulated variance contribution rate obtained by analyzing the target signal by the voiceprint analysis server are input into a trained vector quantization algorithm, and finally the quench determination result is obtained.
10. The method of claim 7, wherein 20ms is taken as a frame length L, and 40% is taken as an overlap ratio b.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202210388965.7A CN114487952A (en) | 2022-04-14 | 2022-04-14 | Quench detection system and method using acoustic optical fiber |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202210388965.7A CN114487952A (en) | 2022-04-14 | 2022-04-14 | Quench detection system and method using acoustic optical fiber |
Publications (1)
Publication Number | Publication Date |
---|---|
CN114487952A true CN114487952A (en) | 2022-05-13 |
Family
ID=81488041
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202210388965.7A Pending CN114487952A (en) | 2022-04-14 | 2022-04-14 | Quench detection system and method using acoustic optical fiber |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN114487952A (en) |
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN116741493A (en) * | 2023-08-09 | 2023-09-12 | 中国科学院合肥物质科学研究院 | Fusion reactor superconducting magnet system |
CN117590300A (en) * | 2023-11-21 | 2024-02-23 | 兰州大学 | Superconducting magnet quench detection system and method based on distributed optical fiber acoustic wave sensing |
Citations (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US5430814A (en) * | 1994-01-05 | 1995-07-04 | Advec Corporation | Temperature transient detection system for superconducting magnets |
CN101680295A (en) * | 2007-02-15 | 2010-03-24 | 高真工程公司 | Method and apparatus for fluid migration profiling |
CN102096051A (en) * | 2009-12-14 | 2011-06-15 | 中国电力科学研究院 | Voltage correction circuit for detecting quench of high-temperature superconduction hybrid magnet |
CN103959044A (en) * | 2011-12-01 | 2014-07-30 | 株式会社藤仓 | Method for detecting normal conduction transition of superconducting wire rod |
CN110261799A (en) * | 2019-06-19 | 2019-09-20 | 中国科学院合肥物质科学研究院 | Detection system is quenched using the high-temperature superconducting magnet of Distributed Optical Fiber Sensing Techniques |
CN111811683A (en) * | 2020-06-22 | 2020-10-23 | 西南交通大学 | Superconducting block temperature rise detection system and method |
-
2022
- 2022-04-14 CN CN202210388965.7A patent/CN114487952A/en active Pending
Patent Citations (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US5430814A (en) * | 1994-01-05 | 1995-07-04 | Advec Corporation | Temperature transient detection system for superconducting magnets |
CN101680295A (en) * | 2007-02-15 | 2010-03-24 | 高真工程公司 | Method and apparatus for fluid migration profiling |
CN102096051A (en) * | 2009-12-14 | 2011-06-15 | 中国电力科学研究院 | Voltage correction circuit for detecting quench of high-temperature superconduction hybrid magnet |
CN103959044A (en) * | 2011-12-01 | 2014-07-30 | 株式会社藤仓 | Method for detecting normal conduction transition of superconducting wire rod |
CN110261799A (en) * | 2019-06-19 | 2019-09-20 | 中国科学院合肥物质科学研究院 | Detection system is quenched using the high-temperature superconducting magnet of Distributed Optical Fiber Sensing Techniques |
CN111811683A (en) * | 2020-06-22 | 2020-10-23 | 西南交通大学 | Superconducting block temperature rise detection system and method |
Non-Patent Citations (2)
Title |
---|
王丰华 等: "《基于改进M FCC和VQ的变压器声纹识别模型》", 《中国电机工程学报》 * |
陈佳音: "《基于光纤MOEMS声传感器技术的声纹识别***研究》", 《中国博士学位论文全文数据库》 * |
Cited By (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN116741493A (en) * | 2023-08-09 | 2023-09-12 | 中国科学院合肥物质科学研究院 | Fusion reactor superconducting magnet system |
CN116741493B (en) * | 2023-08-09 | 2023-11-10 | 中国科学院合肥物质科学研究院 | Fusion reactor superconducting magnet system |
CN117590300A (en) * | 2023-11-21 | 2024-02-23 | 兰州大学 | Superconducting magnet quench detection system and method based on distributed optical fiber acoustic wave sensing |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN109357749B (en) | DNN algorithm-based power equipment audio signal analysis method | |
CN114487952A (en) | Quench detection system and method using acoustic optical fiber | |
CN111442827B (en) | Optical fiber passive online monitoring system for transformer winding vibration | |
CN109856517B (en) | Method for distinguishing partial discharge detection data of extra-high voltage equipment | |
CN112201260B (en) | Transformer running state online detection method based on voiceprint recognition | |
CN110823356B (en) | Distributed optical fiber intrusion detection method based on Mel frequency spectrum | |
CN111044814B (en) | Method and system for identifying transformer direct-current magnetic bias abnormality | |
CN114152825B (en) | Transformer fault diagnosis method and device and transformer fault diagnosis system | |
CN112329914B (en) | Fault diagnosis method and device for buried transformer substation and electronic equipment | |
CN112599134A (en) | Transformer sound event detection method based on voiceprint recognition | |
CN115618205A (en) | Portable voiceprint fault detection system and method | |
CN115839763A (en) | Transformer vibration noise monitoring system | |
CN110161351B (en) | Transformer winding fault test system and diagnosis method under oscillatory wave | |
CN116778956A (en) | Transformer acoustic feature extraction and fault identification method | |
CN114485379A (en) | Transformer winding on-line monitoring method | |
Dang et al. | Cochlear filter cepstral coefficients of acoustic signals for mechanical faults identification of power transformer | |
CN114263621A (en) | Test method and system for diagnosing and simulating cavitation fault of centrifugal pump | |
CN117116293A (en) | Machine equipment fault diagnosis system in complex sound field environment | |
CN116818321A (en) | Bearing fault detection method and device based on ultrasonic phased array and storage medium | |
CN115754630A (en) | Non-contact partial discharge monitoring method and device based on acoustic array | |
CN114121025A (en) | Voiceprint fault intelligent detection method and device for substation equipment | |
Yu et al. | Automatic Condition Monitoring and Fault Diagnosis System for Power Transformers Based on Voiceprint Recognition | |
CN114330450A (en) | Method and system for detecting and identifying underwater vehicle by fusing multiple physical fields | |
Li et al. | Deep Q-network for the Condition Monitoring of Power Transformer with Acoustic Signals | |
Shuai et al. | Pattern recognition of partial discharge ultrahigh frequency signal based on similar matrix BSS and deep learning CNN |
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 |