CN111829687A - BOTDA temperature extraction method based on kernel limit learning machine - Google Patents
BOTDA temperature extraction method based on kernel limit learning machine Download PDFInfo
- Publication number
- CN111829687A CN111829687A CN202010776974.4A CN202010776974A CN111829687A CN 111829687 A CN111829687 A CN 111829687A CN 202010776974 A CN202010776974 A CN 202010776974A CN 111829687 A CN111829687 A CN 111829687A
- Authority
- CN
- China
- Prior art keywords
- learning machine
- kernel
- output end
- brillouin
- time domain
- 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
Images
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01K—MEASURING TEMPERATURE; MEASURING QUANTITY OF HEAT; THERMALLY-SENSITIVE ELEMENTS NOT OTHERWISE PROVIDED FOR
- G01K11/00—Measuring temperature based upon physical or chemical changes not covered by groups G01K3/00, G01K5/00, G01K7/00 or G01K9/00
- G01K11/32—Measuring temperature based upon physical or chemical changes not covered by groups G01K3/00, G01K5/00, G01K7/00 or G01K9/00 using changes in transmittance, scattering or luminescence in optical fibres
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/241—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches
- G06F18/2415—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches based on parametric or probabilistic models, e.g. based on likelihood ratio or false acceptance rate versus a false rejection rate
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N20/00—Machine learning
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Data Mining & Analysis (AREA)
- General Physics & Mathematics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Evolutionary Computation (AREA)
- Software Systems (AREA)
- Artificial Intelligence (AREA)
- General Engineering & Computer Science (AREA)
- Evolutionary Biology (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Probability & Statistics with Applications (AREA)
- Medical Informatics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Computing Systems (AREA)
- Mathematical Physics (AREA)
- Testing Of Optical Devices Or Fibers (AREA)
Abstract
The invention discloses a temperature extraction method of a Brillouin optical time domain analysis system (BOTDA) based on a kernel limit learning machine, which comprises the following steps: the Brillouin gain spectrum parameters of the tested optical fiber are acquired by using a Brillouin optical time domain analysis system, the parameters acquired by the Brillouin optical time domain analysis system are analyzed by using a nuclear extreme learning machine, an obtained real matrix is used as training data of the nuclear extreme learning machine, the nuclear extreme learning machine is trained by using the training data, accurate temperature information is extracted, and the system performance is improved by using higher processing speed. The method introduces a kernel limit learning machine algorithm, improves the temperature extraction precision kernel efficiency of the Brillouin optical time domain analysis system, and is beneficial to the application of the Brillouin optical time domain analysis system in actual detection.
Description
Technical Field
The invention belongs to the field of optical fiber distributed sensing and machine learning, relates to a distributed optical fiber sensing system, and particularly relates to a Brillouin optical time domain analysis technology based on stimulated Brillouin scattering of a nuclear extreme learning machine.
Background
In the fields of civil engineering, building construction, electric power distribution and the like, in order to measure the requirements of parameters such as temperature, stress and the like of facilities (such as bridges, tunnels, oil and gas pipelines, power transmission cables and the like) in a long distance range (namely, to carry out safety monitoring on major facilities related to national civilians), test optical fibers are usually distributed, and the parameters such as the temperature, the stress and the like of the facilities in the long distance range are obtained through indirect testing by testing the parameters such as the temperature, the stress and the like of the test optical fibers.
At present, the layout length of a test optical fiber is usually several kilometers, or tens of kilometers or hundreds of kilometers, in the prior art, in order to acquire the working temperature of the laid test optical fiber in a long-distance range, a brillouin optical time domain analysis system (BOTDA for short) is often used, the BOTDA can acquire information parameters of the test optical fiber, for example, brillouin gain spectrum information of the test optical fiber in the length range is acquired at equal intervals, but the information parameters acquired by the BOTDA are all reflected in the form of electrical signals and cannot be directly read.
Therefore, in the prior art, a lorentz curve fitting algorithm is usually adopted to analyze information parameters acquired by the BOTDA, that is, electrical signal parameters acquired by the BOTDA are analyzed and converted into readable digital information parameters through a lorentz curve. Wherein: the Lorentz curve fitting algorithm has the advantages of low resolving speed and low response speed and resolving efficiency.
The Brillouin optical time domain analysis system (BOTDA for short) has wide application prospect in the field of security monitoring of important facilities of national civilians such as power transmission cables, oil and gas pipelines, civil structures and the like as an important DFS technology, is a mainstream technology in the distributed optical fiber sensing technology based on Brillouin scattering, and has the characteristics of long sensing distance and relatively simple structure.
The distributed optical fiber sensing technology is rapidly developed, and is widely applied to safety monitoring in the field of large facilities at present, so that real-time health status monitoring of the large facilities is realized, and the positions of hidden dangers are quickly and accurately positioned, so that safe operation of the facilities is ensured. The distributed optical fiber sensing system based on Brillouin scattering can realize measurement of temperature and strain, is long in sensing distance and high in precision, is applied to various fields, is a research hotspot in the field of optical fiber sensing, and is of great importance in improving the performance of the distributed optical fiber sensing system in practical application.
In the past, the temperature of the Brillouin optical time domain analysis system is mainly extracted based on a traditional fitting mode, for example, the temperature of the Brillouin optical time domain analysis system is extracted by adopting a Lorentz curve fitting algorithm, but the data processing speed of the data processing method is low.
At present, the temperature information extraction of the Brillouin optical time domain analysis system based on a machine learning method has certain advantages. In the method based on the kernel limit learning machine, the data processing speed is greatly accelerated under the condition of slight loss of precision.
Therefore, in extracting the temperature of the test fiber, it is necessary to try an algorithm other than the lorentz curve fitting. Namely: the temperature extraction method for researching the Brillouin optical time domain analysis system by using the nuclear extreme learning machine has important significance in practical application.
Disclosure of Invention
The purpose of the invention is as follows: in view of the above defects of the existing data processing technology, the invention provides a temperature extraction method of a Brillouin optical time domain analysis system (BOTDA) based on a nuclear extreme learning machine, which is characterized in that the temperature parameters of a tested optical fiber are collected by using the Brillouin optical time domain analysis system, the parameters collected by the Brillouin optical time domain analysis system are analyzed by using the nuclear extreme learning machine, more accurate temperature information is extracted from the collected Brillouin gain spectrum, and the performance of the system is improved by using a faster processing speed.
The technical scheme is as follows: the object of the present invention is achieved by the following means.
A BOTDA temperature extraction method based on a nuclear limit learning machine comprises the steps that a Brillouin optical time domain analysis system is used for collecting temperature parameters of a test optical fiber, the nuclear limit learning machine is used for analyzing the parameters collected by the Brillouin optical time domain analysis system, the Brillouin optical time domain analysis system comprises a distributed feedback laser, a coupler, an acousto-optic modulator, an electro-optic modulator, a first erbium-doped optical fiber amplifier, an isolator, a polarization scrambler, a circulator, a photoelectric detector, a piezoelectric oscillator and a mixer, laser emitted by the distributed feedback laser is divided into two paths by the coupler, namely pump pulse light and continuous detection light, the pump pulse light is generated by the acousto-optic modulator in a modulation mode, amplified by the first erbium-doped optical fiber amplifier, eliminated in polarization through the polarization scrambler and then enters the circulator; the continuous detection light is modulated by a microwave signal through the electro-optical modulator, the output end of the electro-optical modulator is connected with the isolator, the pump pulse light and the continuous detection light generate a stimulated Brillouin scattering amplification effect in the test optical fiber, in order to achieve the purpose of reducing the frequency, the local oscillation light generated by the piezoelectric oscillator and a signal detected by the photoelectric detector are mixed in the mixer to generate an intermediate frequency signal, and the intermediate frequency signal is collected and the temperature information is extracted by using a nuclear limit learning machine.
Furthermore, in the temperature extraction method of the BOTDA based on the nuclear limit learning machine, the Brillouin optical time domain analysis system further comprises a polarization controller, a second erbium-doped fiber amplifier, a logarithmic detector and a data acquisition card.
According to the BOTDA temperature extraction method based on the nuclear limit learning machine, the output end of a distributed feedback laser is connected with the input end of a coupler, the output end of the coupler is respectively connected with the input ends of an electro-optic modulator and an acoustic-optic modulator, a polarization controller is connected between the coupler and the electro-optic modulator, the output end of the acoustic-optic modulator is connected with the input end of a first erbium-doped fiber amplifier, the output end of the first erbium-doped fiber amplifier is connected with the input end of a polarization scrambler, and the output end of the polarization scrambler is connected with one input end of a circulator; the output end of the electro-optical modulator is connected with the input end of the isolator, the output end of the isolator is connected with the other input end of the circulator through the test optical fiber, the output end of the circulator is connected with the input end of the photoelectric detector through the second erbium-doped optical fiber amplifier, the output end of the photoelectric detector is connected with the input end of the mixer, the output end of the mixer is connected with the input end of the logarithmic detector, the piezoelectric oscillator is also connected with the mixer, and the output end of the logarithmic detector is connected with the data acquisition card.
Furthermore, in the temperature extraction method of the BOTDA based on the nuclear limit learning machine, the data acquisition card delivers the acquired data to the computer, the acquired temperature parameters of the test optical fiber are extracted in the computer through the nuclear limit learning machine algorithm, and the nuclear limit learning machine is adopted to carry out temperature extraction on the training dataThe training process is as follows: inputting training data into a nuclear extreme learning machine, wherein the training data comprises a Brillouin gain spectrum matrix [ x ]i1，xi2，...，xin]T∈RnAnd a label vector [ c ] corresponding to the temperature informationi1，ci2，...，cim]T∈RmWherein n represents an input feature dimension and m represents an output feature dimension; gain spectrum data in training data is subjected to kernel function mapping to generate a high-dimensional characteristic kernel matrix omegaELMThe feature matrix and a tag matrix C in a one-hot form are used for jointly solving an output weight matrix B; the prediction process of the BOTDA temperature extraction method based on the kernel limit learning machine is as follows: performing modulus taking and normalization pretreatment on Brillouin gain spectrum data to be predicted, and inputting the data into a nuclear extreme learning machine; multiplying the high-dimensional characteristics obtained by the kernel function operation with the output weight matrix to obtain a classification evaluation value Y, and mapping the temperature classification information to a 1 x K vector Y for the kernel extreme learning machinetIn the end with ytThe highest scoring category in the SoftMax distribution of (1) is taken as the predicted category.
After the technical scheme is adopted, the invention has the beneficial effects that:
the invention provides a temperature extraction method of a Brillouin optical time domain analysis system based on a kernel limit learning machine. Compared with the traditional Lorentz curve fitting method for extracting temperature information, the method based on the nuclear extreme learning machine can extract more accurate temperature information from the acquired Brillouin gain spectrum, and the processing speed is far better than that of Lorentz fitting, so that the performance of the system is improved. Furthermore, the method does not need a complex preprocessing process, greatly reduces the calculation time and the requirements on hardware, improves the real-time performance and the feasibility, and is favorable for the wide application of the Brillouin optical time domain analysis system in the actual monitoring.
The drawings illustrate the following:
fig. 1 is a system block diagram of a brillouin optical time domain analysis system (BOTDA for short).
FIG. 2 is a schematic diagram of the extraction temperature of the extreme learning machine
FIG. 3 is a schematic diagram of a network structure of a kernel-limit learning machine in the method of the present invention.
FIG. 4 is a comparison graph of BOTDA temperature extraction errors using a kernel limit learning machine at different signal-to-noise ratios.
FIG. 5 is a temperature extraction error contrast diagram of BOTDA using a kernel limit learning machine under different sweep frequency step lengths
In the figure: 1-distributed feedback laser, 2-coupler, 3-polarization controller, 4-acousto-optic modulator, 5-electro-optic modulator, 6-first erbium-doped fiber amplifier, 7-second erbium-doped fiber amplifier, 8-isolator, 9-polarization scrambler, 10-circulator, 11-photoelectric detector, 12-piezoelectric oscillator, 13-mixer, 14-logarithmic detector, 15-data acquisition card
Detailed Description
The following further describes the implementation of the present invention with reference to the accompanying drawings.
As shown in fig. 1, a brillouin optical time domain analysis system (BOTDA for short) includes: the device comprises a distributed feedback laser 1, a coupler 2, a polarization controller 3, an acousto-optic modulator 4, an electro-optic modulator 5, a first erbium-doped fiber amplifier 6, a second erbium-doped fiber amplifier 7, an isolator 8, a polarization scrambler 9, a circulator 10, a photoelectric detector 11, a piezoelectric oscillator 12, a mixer 13, a logarithmic detector 14 and a data acquisition card 15.
The connection relationship of each hardware forming the brillouin optical time domain analysis system is as follows: the output end of the distributed feedback laser 1 is connected with the input end of a coupler 2, the output end of the coupler 2 is respectively connected with the input ends of an electro-optical modulator 5 and an acousto-optical modulator 4, a polarization controller 3 is further connected between the coupler 2 and the electro-optical modulator 5, the output end of the acousto-optical modulator 4 is connected with the input end of a first erbium-doped fiber amplifier 6, the output end of the first erbium-doped fiber amplifier 6 is connected with the input end of a polarization scrambler 9, and the output end of the polarization scrambler 9 is connected with one input end of a ring-shaped device 10; the output end of the electro-optical modulator 5 is connected with the input end of an isolator 8, the output end of the isolator 8 is connected with the other input end of a circulator 10 through a test optical fiber, the output end of the circulator 10 is connected with the input end of a photoelectric detector 11 through a second erbium-doped optical fiber amplifier 7, the output end of the photoelectric detector 11 is connected with the input end of a mixer 13, the output end of the mixer 13 is connected with the input end of a logarithmic detector 14, a piezoelectric oscillator 12 is also connected with the mixer 13, the output end of the logarithmic detector 14 is connected with a data acquisition card 15, the data acquisition card 15 delivers acquired data to a computer, and the acquired temperature parameters of the test optical fiber are extracted through a nuclear limit learning machine algorithm in the computer.
In the Brillouin optical time domain analysis system, two ends of a test optical fiber are respectively connected to the output end of an isolator and one input end of a circulator.
In fig. 1, the laser light emitted from the distributed feedback laser 1 is divided into two paths by the coupler 2, and in this embodiment, the coupler 2 is a 50: 50 optical coupler. The laser light divided into two paths by the coupler 2 is pump pulse light and continuous probe light respectively. The pump pulse light is generated by modulating an acousto-optic modulator 4 with an extinction ratio of 50dB, amplified by a first erbium-doped fiber amplifier 6, and enters a circulator 10 after passing through a polarization scrambler 9 for eliminating polarization. The continuous detection light is modulated by microwave signals through the electro-optical modulator 5, the frequency of the microwave signals is 10.560GHz to 10.760GHz, the detection light is ensured to scan in a Brillouin gain region, the output end of the electro-optical modulator 5 is connected with an isolator 8 for processing reverse transmission light beams, and finally the modulated signals enter the test optical fiber after being subjected to sideband filtering. The stimulated Brillouin scattering amplification effect occurs in the test optical fiber by the pump pulse light and the continuous detection light, the scattered light is converted into an electric signal after passing through the photoelectric detection device, and then the local oscillation light generated by the piezoelectric oscillator 12 and the signal detected by the photoelectric detector 11 are mixed in the mixer 13 to generate an intermediate frequency signal, so that the frequency reduction is completed, and the signal acquisition is facilitated. The signal passes through a logarithmic detector 14, data is acquired by a data acquisition card 15, and finally temperature information extraction is carried out on the acquired Brillouin gain spectrum.
And when the temperature of the Brillouin optical time domain analysis system is extracted, a method of a kernel extreme learning machine is adopted. Compared with a Lorentz curve fitting method, the method has the advantages that the temperature extraction precision of the nuclear extreme learning machine at different signal-to-noise ratios (different positions) along the optical fiber is improved, and the performance degradation of the nuclear extreme learning machine is slower when the sweep frequency step is increased.
The principle of extracting temperature by the kernel-based extreme learning machine is shown in fig. 2, and temperature information is extracted in the training and testing stage of the kernel-based extreme learning machine (KELM for short) algorithm. According to theoretical analysis and properties of the actual brillouin gain spectrum, the actual brillouin gain spectrum has a linear shape between a lorentzian curve and a gaussian curve, and can be fitted with a pseudo Voigt curve. Thus, the pseudo Voigt curve serves as a training sample. After processing by the kernel limit learning machine algorithm, the input curve is converted to a different temperature scale in the training phase.
To verify the robustness of the kernel-limit learning algorithm, the parameters of the fiber signal-to-noise ratio and the sweep frequency step size were changed in the experiment, as shown in the test stage of fig. 2. In the experiment, the tested brillouin gain spectrum was used as an input to an algorithm along the tested fiber to extract temperature information.
Fig. 4 and 5 are comparison graphs of experimental effects of the kernel-limit learning machine algorithm. Wherein: FIG. 4 is a graph of the BOTDA temperature extraction error comparison at different signal-to-noise ratios using a kernel limit learning machine. With the increase of the distance, the signal-to-noise ratio is reduced along with the increase of the length of the optical fiber, and under different signal-to-noise ratios, the error of the extraction temperature of the nuclear extreme learning machine is smaller than that of the original extreme learning machine, and the speed is far better than that of the Lorentz fitting method, and meanwhile, the precision is equivalent to that of the Lorentz fitting method. FIG. 5 is a comparison graph of temperature extraction errors for BOTDA using a kernel-limit learning machine at different sweep frequency step lengths. The error of temperature extraction is gradually increased along with the increase of the frequency scanning step length, and compared with the original extreme learning machine algorithm, the kernel extreme learning machine is smaller in error increase amplitude and better in robustness.
In summary, the temperature extraction method of the brillouin optical time domain analysis system based on the kernel limit learning machine provided by the invention has the following characteristics:
1) the temperature extraction of the Brillouin optical time domain analysis system by the kernel limit learning machine at different distances (under different signal-to-noise ratios) along the light ray has better precision;
2) and the temperature extraction performance of the Brillouin optical time domain analysis system is degraded more slowly by the core limit learning machine model under the condition of increasing the sweep frequency step length. The method is beneficial to providing better accuracy and efficiency for temperature extraction of the Brillouin optical time domain analysis system in practical application, and a new scheme is provided for temperature extraction of the Brillouin optical time domain analysis system.
The above description is only a preferred embodiment of the method of the present invention, and it should be noted that several modifications (such as instrument parameters of the brillouin optical time domain analysis system) that can be made in practical implementation without departing from the spirit of the scheme and apparatus of the present invention are also included in the protection scope of the present invention.
Claims (4)
1. The BOTDA temperature extraction method based on the nuclear limit learning machine is characterized in that a Brillouin optical time domain analysis system is used for collecting Brillouin gain spectrum parameters of a test optical fiber, the nuclear limit learning machine is used for analyzing the parameters collected by the Brillouin optical time domain analysis system, the Brillouin optical time domain analysis system comprises a distributed feedback laser (1), a coupler (2), an acousto-optic modulator (4), an electro-optic modulator (5), a first erbium-doped optical fiber amplifier (6), an isolator (8), a polarization scrambler (9), a circulator (10), a photoelectric detector (11), a piezoelectric oscillator (12) and a mixer (13), and the BOTDA temperature extraction method is characterized in that: laser emitted by the distributed feedback laser (1) is divided into two paths by the coupler (2), namely pump pulse light and continuous detection light, the pump pulse light is generated by modulation of the acousto-optic modulator (4), amplified by the first erbium-doped fiber amplifier (6), and enters the circulator (10) after polarization is eliminated by the polarization scrambler (9); the continuous detection light is modulated by a microwave signal through the electro-optical modulator (5), the output end of the electro-optical modulator (5) is connected with the isolator (8), the pump pulse light and the continuous detection light generate a stimulated Brillouin scattering amplification effect in the test optical fiber, the local oscillation light generated by the piezoelectric oscillator (12) and a signal detected by the photoelectric detector (11) are mixed in the mixer (13) to generate an intermediate frequency signal, the intermediate frequency signal is collected, a nuclear limit learning machine is used for extracting temperature information, and temperature information is obtained.
2. The temperature extraction method of BOTDA based on kernel-based extreme learning machine as claimed in claim 1, characterized in that: the output end of the distributed feedback laser (1) is connected with the input end of a coupler (2), the output end of the coupler (2) is respectively connected with the input ends of an electro-optical modulator (5) and an electro-optical modulator (4), a polarization controller (3) is connected between the coupler (2) and the electro-optical modulator (5), the output end of the electro-optical modulator (4) is connected with the input end of a first erbium-doped fiber amplifier (6), the output end of the first erbium-doped fiber amplifier (6) is connected with the input end of a polarization scrambler (9), and the output end of the polarization scrambler (9) is connected with one input end of a circulator (10); the output end of the electro-optical modulator (5) is connected with the input end of the isolator (8), the output end of the isolator (8) is connected with the other input end of the circulator (10) through a test optical fiber, the output end of the circulator (10) is connected with the input end of the photoelectric detector (11) through the second erbium-doped optical fiber amplifier (7), the output end of the photoelectric detector (11) is connected with the input end of the mixer (13), the output end of the mixer (13) is connected with the input end of the logarithmic detector (14), the piezoelectric oscillator (12) is also connected with the mixer (13), and the output end of the logarithmic detector (14) is connected with the data acquisition card (15).
3. The temperature extraction method of BOTDA based on kernel-based extreme learning machine as claimed in claim 3, characterized in that: the data acquisition card (15) delivers the acquired data to a computer, and the acquired temperature parameters of the test optical fiber are extracted in the computer through a nuclear limit learning machine algorithm.
4. The BOTDA temperature extraction method based on the kernel-based extreme learning machine is characterized in that the kernel-based extreme learning machine is adopted to analyze parameters acquired by the Brillouin optical time domain analysis system, the kernel-based extreme learning machine is adopted to train training data, and the training process is as follows:
1) inputting training data into a nuclear extreme learning machine, wherein the training data comprises a Brillouin gain spectrum matrix [ x ]i1，xi2，...，xin]T∈RnAnd a label vector [ c ] corresponding to the temperature informationi1，ci2，...，cim]T∈RmWherein n represents an input feature dimension and m represents an output feature dimension;
2) gain spectrum data in training data is subjected to kernel function mapping to generate a high-dimensional characteristic kernel matrix omegaELMThe feature matrix and a tag matrix C in a one-hot form are used for jointly solving an output weight matrix B;
the prediction process of the BOTDA temperature extraction method based on the kernel limit learning machine is as follows:
1) performing modulus taking and normalization pretreatment on Brillouin gain spectrum data to be predicted, and inputting the data into a nuclear extreme learning machine;
2) multiplying the high-dimensional characteristics obtained by the kernel function operation with the output weight matrix to obtain a classification evaluation value Y, and mapping the temperature classification information to a 1 x K vector Y for the kernel extreme learning machinetIn the end with ytThe highest scoring category in the SoftMax distribution of (1) is taken as the predicted category.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010776974.4A CN111829687A (en) | 2020-08-05 | 2020-08-05 | BOTDA temperature extraction method based on kernel limit learning machine |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010776974.4A CN111829687A (en) | 2020-08-05 | 2020-08-05 | BOTDA temperature extraction method based on kernel limit learning machine |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN111829687A true CN111829687A (en) | 2020-10-27 |
Family
ID=72919870
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010776974.4A Pending CN111829687A (en) | 2020-08-05 | 2020-08-05 | BOTDA temperature extraction method based on kernel limit learning machine |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111829687A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114216582A (en) * | 2021-12-08 | 2022-03-22 | 电子科技大学长三角研究院(湖州) | High-precision rapid temperature field reconstruction method, system, equipment and terminal |
-
2020
- 2020-08-05 CN CN202010776974.4A patent/CN111829687A/en active Pending
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114216582A (en) * | 2021-12-08 | 2022-03-22 | 电子科技大学长三角研究院(湖州) | High-precision rapid temperature field reconstruction method, system, equipment and terminal |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Bao et al. | Recent development in the distributed fiber optic acoustic and ultrasonic detection | |
| CN103076112B (en) | The parameter measuring apparatus of single-side belt distributed optical fiber sensing system | |
| CN111051832A (en) | Photoelectric device for optical fiber distributed measurement | |
| CN109991511B (en) | Lightning stroke monitoring device and monitoring method for overhead line | |
| CN106840223A (en) | Wide-band microwave instantaneous spectrum measurement apparatus based on Brillouin scattering | |
| CN114543973B (en) | Distributed ultrahigh frequency vibration signal measurement method and optical fiber sensor | |
| CN111578971A (en) | Device and method for realizing long-distance measurement by OFDR segmented acquisition | |
| CN110530551B (en) | BOTDA temperature extraction method based on optimized support vector machine | |
| CN114088124A (en) | Brillouin optical time domain reflectometer based on double-sideband modulation | |
| CN111829687A (en) | BOTDA temperature extraction method based on kernel limit learning machine | |
| CN102445416A (en) | Real-time online nondestructive detection device for composite material | |
| Bernini et al. | All frequency domain distributed fiber-optic Brillouin sensing | |
| Xiao et al. | Frequency response enhancement of Φ-OTDR using interval-sweeping pulse equivalent sampling based on compressed sensing | |
| Ge et al. | Enabling variable high spatial resolution retrieval from a long pulse BOTDA sensor | |
| CN112697179A (en) | AdaBoost-based Brillouin frequency shift extraction method | |
| RU2428682C1 (en) | Method for thermal nondestructive inspection of thermal-technical state of long, non-uniform and hard-to-reach objects | |
| CN113375830B (en) | Long-distance and wide-measuring-range fast demodulation device and method | |
| Ruiz-Lombera et al. | Automatic strain detection in a Brillouin optical time domain sensor using principal component analysis and artificial neural networks | |
| CN112197878A (en) | High-precision optical wavelength detection method and system based on optical frequency domain reflectometer | |
| Bogachkov et al. | Application of Brillouin scattering in optic-fiber sensors | |
| Bogachkov et al. | Distributed fiber-optic sensors based on principle of stimulated brillouin scattering | |
| CN219978137U (en) | Oil immersed power equipment physical information detection device based on terahertz spectrum | |
| CN110686865A (en) | Optical fiber fusion splicing structure based on OCT technology and loss cloud detection system | |
| CN110986814B (en) | Phase sensitive optical time domain reflection system with improved dynamic strain measurement range | |
| CN202305393U (en) | Real-time online nondestructive detection device of composite material |
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 |