CN113670430B - Distributed optical fiber vibration sensing intelligent disturbance identification method - Google Patents
Distributed optical fiber vibration sensing intelligent disturbance identification method Download PDFInfo
- Publication number
- CN113670430B CN113670430B CN202110935859.1A CN202110935859A CN113670430B CN 113670430 B CN113670430 B CN 113670430B CN 202110935859 A CN202110935859 A CN 202110935859A CN 113670430 B CN113670430 B CN 113670430B
- Authority
- CN
- China
- Prior art keywords
- matrix
- optical fiber
- phase
- phase difference
- disturbance
- 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.)
- Active
Links
- 239000013307 optical fiber Substances 0.000 title claims abstract description 55
- 238000000034 method Methods 0.000 title claims abstract description 29
- 239000011159 matrix material Substances 0.000 claims abstract description 68
- 230000003287 optical effect Effects 0.000 claims abstract description 18
- 238000012545 processing Methods 0.000 claims abstract description 9
- 238000012549 training Methods 0.000 claims abstract description 8
- 230000009545 invasion Effects 0.000 claims abstract description 7
- 239000013598 vector Substances 0.000 claims description 24
- 230000035559 beat frequency Effects 0.000 claims description 12
- 238000004422 calculation algorithm Methods 0.000 claims description 6
- 238000000354 decomposition reaction Methods 0.000 claims description 5
- 238000005070 sampling Methods 0.000 claims description 4
- 238000009825 accumulation Methods 0.000 claims description 3
- 230000001427 coherent effect Effects 0.000 claims description 3
- 238000005192 partition Methods 0.000 claims description 2
- 239000000758 substrate Substances 0.000 claims 1
- 230000007613 environmental effect Effects 0.000 abstract description 2
- 238000005562 fading Methods 0.000 abstract description 2
- 239000000835 fiber Substances 0.000 description 12
- 238000001514 detection method Methods 0.000 description 5
- 238000000253 optical time-domain reflectometry Methods 0.000 description 5
- 239000000523 sample Substances 0.000 description 5
- 230000005540 biological transmission Effects 0.000 description 4
- 238000010586 diagram Methods 0.000 description 3
- 238000012544 monitoring process Methods 0.000 description 3
- 238000004891 communication Methods 0.000 description 2
- 238000003909 pattern recognition Methods 0.000 description 2
- 229910052691 Erbium Inorganic materials 0.000 description 1
- 238000010009 beating Methods 0.000 description 1
- 230000006399 behavior Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000009194 climbing Effects 0.000 description 1
- 238000009826 distribution Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- UYAHIZSMUZPPFV-UHFFFAOYSA-N erbium Chemical compound [Er] UYAHIZSMUZPPFV-UHFFFAOYSA-N 0.000 description 1
- 238000000605 extraction Methods 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 239000003208 petroleum Substances 0.000 description 1
- 238000003825 pressing Methods 0.000 description 1
- 238000007637 random forest analysis Methods 0.000 description 1
- 238000001228 spectrum Methods 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
Images
Classifications
-
- 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
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/214—Generating training patterns; Bootstrap methods, e.g. bagging or boosting
- G06F18/2148—Generating training patterns; Bootstrap methods, e.g. bagging or boosting characterised by the process organisation or structure, e.g. boosting cascade
-
- 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
Landscapes
- Engineering & Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Artificial Intelligence (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Evolutionary Biology (AREA)
- Evolutionary Computation (AREA)
- Bioinformatics & Computational Biology (AREA)
- General Engineering & Computer Science (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Optical Transform (AREA)
- Measurement Of Mechanical Vibrations Or Ultrasonic Waves (AREA)
Abstract
The invention discloses a distributed optical fiber vibration sensing intelligent disturbance identification method, which comprises the following steps: collecting various disturbance invasion signals; obtaining a phase matrix of a sensing subarea; processing the phase matrix to obtain a phase difference signal matrix; performing label definition on the phase difference signal matrix; decomposing the phase difference signal matrix; constructing a characteristic two-dimensional matrix; taking all the feature data and the labels in one-to-one correspondence as sample data, and balancing the samples of different label types; the invention effectively solves the problem of high nuisance alarm rate caused by environmental noise, light path randomness, phase fading and other problems in the phase sensitive optical time domain reflection distributed optical fiber vibration sensing system, and can identify the system intrusion event with extremely high accuracy; the invention effectively improves the real-time performance of the phase sensitive optical time domain reflection distributed optical fiber vibration sensing system, and greatly reduces training data and input redundant data required by system identification.
Description
Technical Field
The invention relates to the technical field of optical fiber sensing, in particular to a distributed optical fiber vibration sensing intelligent disturbance identification method.
Background
The Phase-sensitive Optical Time Domain Reflectometry (abbreviated as phi-OTDR) Optical fiber distributed sensing system is used for monitoring external disturbance events, can realize accurate positioning and type identification of the external vibration disturbance events, has the characteristics of high spatial resolution, long real-Time monitoring communication distance, capability of forming an intelligent sensing network and the like, and has a general application prospect in distributed long-distance alarm monitoring aspects such as petroleum pipeline side leakage detection, communication line detection, building structure detection, border security, intrusion alarm and the like.
Traditional phi-OTDR distributed optical fiber sensing systemThe intrusion disturbance positioning is usually realized by analyzing and processing amplitude signals of backward Rayleigh scattering light, and the positioning of disturbance generating places, intrusion pattern recognition, intrusion early warning and the like can be realized. In the aspect of intrusion disturbance identification, 2017 Xu Chengjin and the like of Zhejiang university extract a plurality of characteristic parameters of short-time energy ratio, short-time level-crossing rate, disturbance duration and energy spectrum density of disturbance signal amplitude, and finally, classification of the disturbance signals is realized by identifying multi-characteristic-parameter characteristic vectors through an SVM. The disturbance recognition rate of 800 groups of disturbance signals in total using four modes (beating, knocking, shaking and squeezing) is higher than 90%, and the recognition time is less than 0.6s (Xu, J.Guan, M.Bao, J.Lu, and W.Ye, "Pattern recognition based on enhanced multiple disturbance parameters for the disturbance in
-OTDR distributed optical fiber sensing system, "micro w.opt.technol.lett., vol.59, no.12, pp.3134-3141,2017); 30 time-frequency characteristics of Rayleigh scattered light amplitude time-domain signals are extracted by Wang Xin et al, beijing university of transportation in 2019, and a random forest classifier is combined to classify three events of watering, pressing and treading, so that the lowest classification error rate can reach 2% (X.Wang, Y.Liu, S.Liang, W.Zhang, and S.Lou, "Event identification base on random classifier for phi-OTDR fiber-optical distributed disturbance sensor," incorporated physics technology, vol.97, no. January, pp.319-325,2019). Although the disturbance classification with higher precision can be realized by using the amplitude signal, a large number of signals are needed to realize the intrusion disturbance identification on the whole link, the amplitude signal and the disturbance signal are not in a linear relation, and the amplitude signal is greatly influenced by the distribution of scattering points in the optical fiber.
Disclosure of Invention
This section is for the purpose of summarizing some aspects of embodiments of the invention and to briefly introduce some preferred embodiments. In this section, as well as in the abstract and the title of the invention of this application, simplifications or omissions may be made to avoid obscuring the purpose of the section, the abstract and the title, and such simplifications or omissions are not intended to limit the scope of the invention.
The invention is provided in view of the problems of the existing distributed optical fiber vibration sensing intelligent disturbance identification method.
Therefore, the invention aims to provide a distributed optical fiber vibration sensing intelligent disturbance identification method, and aims to provide a low-time-delay high-precision phase-sensitive optical time domain reflection distributed optical fiber vibration sensing intelligent identification system for accurately identifying a vibration intrusion signal on a sensing link in real time.
In order to solve the technical problems, the invention provides the following technical scheme: a distributed optical fiber vibration sensing intelligent disturbance identification method comprises the steps of collecting various disturbance invasion signals; obtaining a phase matrix of the sensing subarea; processing the phase matrix to obtain a phase difference signal matrix representing the sensing information of the area; performing label definition on the phase difference signal matrix; decomposing a phase difference signal matrix; constructing a characteristic two-dimensional matrix; and taking all the feature data and the labels in one-to-one correspondence as sample data, and balancing the samples of different label types.
As a preferred scheme of the distributed optical fiber vibration sensing intelligent disturbance identification method of the present invention, wherein: the step of collecting various disturbance intrusion signals comprises the following steps: collecting N times of optical pulses (N is more than 1) by using a data acquisition card; forming a signal time-space domain matrix data = [ d ] by the beat frequency signals corresponding to the optical pulses i，j ] N*D (ii) a Each disturbance intrusion signal is collected by more than 1 group, and the total number of the disturbance intrusion signals is M groups, d i，j A j-th beat signal representing the ith light pulse, i representing time information, and j representing position information.
As a preferred scheme of the distributed optical fiber vibration sensing intelligent disturbance identification method of the present invention, wherein: the step of obtaining the phase matrix of the sensing partition comprises: dividing the sensing optical fiber into R sections of sensing areas; and demodulating the beat frequency signals at two ends of the sensing area according to groups by adopting a digital coherent demodulation algorithm to obtain a phase matrix phi of the R-section sensing area.
Distributed optical fiber vibration as described in the present inventionA preferred solution of the sensing intelligent disturbance identification method, wherein: the step of processing the phase matrix to obtain a phase difference signal matrix representing the area sensing information comprises: and sequentially differentiating vectors in the phase matrix phi in rows to obtain a phase differential signal matrix S = [ S ] representing the sensing information of the area i ] R*M (ii) a Each column of the vector comprises N time domain sampling points, and the mth column of the phase difference signal is represented as S m ＝φ m -φ m+1 Each column vector in the phase difference signal matrix S contains the accumulation of all disturbance intrusion signals in the represented sensing area.
As a preferred scheme of the distributed optical fiber vibration sensing intelligent disturbance identification method of the present invention, wherein: the step of label defining the phase differential signal matrix comprises: perturbed phase difference vector S i The label is y i =1; undisturbed phase difference vector S j The label is y j =0; a tag vector y containing R x M elements is obtained.
As a preferred scheme of the distributed optical fiber vibration sensing intelligent disturbance identification method of the present invention, wherein: the step of decomposing the phase differential signal matrix comprises: performing four-layer decomposition on the phase difference signal matrix S by utilizing a wavelet packet decomposition algorithm; decomposing the original phase difference signal into a high-frequency signal and a low-frequency signal; and decomposing the high-frequency and low-frequency signals of the previous layer into the next layer, and decomposing the four layers.
As a preferred scheme of the distributed optical fiber vibration sensing intelligent disturbance identification method, the distributed optical fiber vibration sensing intelligent disturbance identification method comprises the following steps: the step of constructing a two-dimensional matrix of features comprises: decomposing the phase difference matrix S to obtain each time domain vector S i 16 frequency domain features of (1); constructing a characteristic two-dimensional matrix T = [ T ] from the frequency domain characteristics 1 ,…,T 16 ]。
As a preferred scheme of the distributed optical fiber vibration sensing intelligent disturbance identification method of the present invention, wherein: the method comprises the steps that all feature data and labels are in one-to-one correspondence to be used as sample data, samples of different label types are balanced, the balanced sample data are used as training data to be input into a limit gradient, a classifier XGboost is added to be used for training, and the obtained training model can successfully identify disturbance information in the phase sensitive optical time domain distributed optical fiber sensing system.
The invention has the beneficial effects that:
the invention effectively solves the problem of high nuisance alarm rate caused by environmental noise, light path randomness, phase fading and other problems in the phase sensitive optical time domain reflection distributed optical fiber vibration sensing system, and can identify the system intrusion event with extremely high accuracy; the invention effectively improves the real-time performance of the phase sensitive optical time domain reflection distributed optical fiber vibration sensing system, and greatly reduces training data and input redundant data required by system identification.
Drawings
In order to more clearly illustrate the technical solutions of 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 inventive exercise. Wherein:
fig. 1 is a schematic overall flow chart of the distributed optical fiber vibration sensing intelligent disturbance identification method of the present invention.
Fig. 2 is a detailed flow diagram of the distributed optical fiber vibration sensing intelligent disturbance identification method of the present invention.
Fig. 3 is a diagram of phase difference information after quadrature demodulation and difference operation according to the present invention.
FIG. 4 is a schematic diagram of four-layer wavelet packet decomposition feature extraction according to the present invention.
Fig. 5 is a phase sensitive optical time domain reflection distributed optical fiber vibration sensing system of the present invention.
Detailed Description
In order to make the aforementioned objects, features and advantages of the present invention comprehensible, embodiments accompanied with figures are described in detail below.
In the following description, numerous specific details are set forth in order to provide a thorough understanding of the present invention, but the present invention may be practiced in other ways than those specifically described and will be readily apparent to those of ordinary skill in the art without departing from the spirit of the present invention, and therefore the present invention is not limited to the specific embodiments disclosed below.
Furthermore, the references herein to "one embodiment" or "an embodiment" refer to a particular feature, structure, or characteristic that may be included in at least one implementation of the present invention. The appearances of the phrase "in one embodiment" in various places in the specification are not necessarily all referring to the same embodiment, nor are separate or alternative embodiments mutually exclusive of other embodiments.
Furthermore, the present invention is described in detail with reference to the drawings, and in the detailed description of the embodiments of the present invention, the cross-sectional view illustrating the structure of the device is not enlarged partially according to the general scale for convenience of illustration, and the drawings are only exemplary and should not be construed as limiting the scope of the present invention. In addition, the three-dimensional dimensions of length, width and depth should be included in the actual fabrication.
Example 1
Referring to fig. 1 to 4, for a first embodiment of the present invention, a distributed optical fiber vibration sensing intelligent disturbance identification method is provided, including:
s1: collecting various disturbance invasion signals;
s2: obtaining a phase matrix of a sensing subarea;
s3: processing the phase matrix to obtain a phase difference signal matrix representing the sensing information of the area;
s4: performing label definition on the phase difference signal matrix;
s5: decomposing the phase difference signal matrix;
s6: constructing a characteristic two-dimensional matrix;
s7: and taking all the feature data and the labels in one-to-one correspondence as sample data, and balancing the samples of different label types.
The step of collecting various disturbance intrusion signals comprises the following steps:
s11: collecting N light pulses (N > 1);
s12: forming a signal time-space domain matrix data = [ d ] by using the beat frequency signals corresponding to the acquired optical pulses i，j ] N*D ；
S13: more than 1 group of disturbance invasion signals are collected, and M groups are total i，j A j-th beat signal representing the ith light pulse, i representing time information, and j representing position information.
Specifically, the intrusion signal disturbance comprises climbing, treading, knocking and other behaviors; in the example, the disturbance intrusion signal is a trample event, rayleigh scattering light beat frequency signals returned by 500 light pulses are collected each time, the number of collected points of the Rayleigh scattering light beat frequency signals returned by each light pulse is 10000 points, all signals of 5km optical fiber space distance within 0.17s of time are represented, and 500 groups of signal matrixes containing different disturbance information are provided.
Further, the step of obtaining the phase matrix of the sensing sub-area comprises:
s21: dividing the sensing optical fiber into R sections of sensing areas;
the two ends of each sensing area are beat frequency signals, the sensing optical fiber is divided into 49 sensing areas, the distance between each sensing area is 100m, and the sensing area comprises 200 time domain sampling points.
S22: demodulating beat frequency signals at two ends of all sensing areas according to groups by adopting a digital coherent demodulation algorithm to obtain a phase matrix phi of an R-section sensing area;
the phase matrix phi contains 500 sets of 49 segments of 2450 column vectors, each containing 500 time domain data.
Further, the step of processing the phase matrix to obtain the phase difference signal matrix includes:
s31: the vectors in the phase matrix phi are differentiated in sequence by columns to obtain a phase differential signal matrix S = [ S ] representing the sensing information of the area i ] R*M ；
Calculating to obtain a phase difference signal matrix S = [ S = [ S ] i ] 24500 ；
S32: each column of vector comprises N time domain sampling points and the mth column of phaseThe differential signal is denoted as S m ＝φ m -φ m+1 Each column vector in the phase difference signal matrix S contains the accumulation of all the perturbation intrusion signals in the represented sensing area.
Specifically, the step of defining the label for the phase difference signal matrix includes:
s41: perturbed phase difference vector S i The label is y i =1, undisturbed phase difference vector S j The label is y j ＝0；
S42: obtaining a label vector y containing R x M elements;
thus obtaining a tag vector y of 2450 elements.
Specifically, the step of decomposing the phase difference signal matrix includes:
s51: decomposing the phase difference signal matrix S by utilizing a wavelet packet decomposition algorithm, and decomposing an original phase difference signal into a high-frequency signal and a low-frequency signal by referring to FIG. 4;
s52: and decomposing the high-frequency and low-frequency signals of the previous layer into the next layer, and decomposing the four layers.
Further, the step of constructing the two-dimensional matrix of features includes:
s61: decomposing the phase difference component matrix S to obtain each time domain vector S i 16 frequency domain features of (1);
s62: constructing a characteristic two-dimensional matrix T = [ T ] from the frequency domain characteristics 1 ,…,T 16 ]。
S7, the obtained model can identify disturbance information in the phase sensitive optical time domain distributed optical fiber sensing system, referring to FIG. 3, the false alarm rate is less than 1%, and the time required for identifying and judging 1000 sensing areas is less than 0.006S.
Example 2
Referring to fig. 5, a second embodiment of the present invention, which is different from the first embodiment, is: the distributed optical fiber vibration sensing intelligent disturbance identification method is carried out through a phase sensitive optical time domain reflection distributed optical fiber vibration sensing system, and the system comprises a transmitting unit 100, a modulation unit 200 and a transmission unit 300.
Specifically, the transmitting unit 100 further includes a 1`2 optical fiber coupler 102, and the 1 ″ 2 optical fiber coupler 102 has a splitting ratio of 90. A modulation unit 200 including an acousto-optic modulator (AOM) 201 and an erbium-doped fiber amplifier (EDFA) 202, the modulation unit 200 being connected to the transmission unit 100; a transmission unit 300 comprising a fiber circulator 301 and a sensing fiber 302, the transmission unit 300 being connected to an Erbium Doped Fiber Amplifier (EDFA) 202.
Preferably, the sensing fiber 302 is a single mode fiber, and the sensing fiber 302 has a length of 5km, and the treading intrusion signals are artificially made at 0.2km, 0.4km, 0.6km and 1.1 km.
The rest of the structure is the same as that of embodiment 1.
In use, the acousto-optic modulator (AOM) 201 modulates the first optical path a as probe light into an optical pulse signal, shifts the frequency of the optical pulse signal to a high frequency of 80MHz, amplifies the optical pulse signal by an erbium-doped fiber amplifier (EDFA) 202, and transmits rayleigh scattered light generated by the action of the optical pulse signal in the sensing fiber 302 entering the sensing fiber 302 through the fiber circulator 301 to be transmitted back to the fiber circulator 301.
Example 3
Referring to fig. 5, a third embodiment of the present invention is different from the second embodiment in that: the system also comprises a detection unit 400, wherein the detection unit 400 comprises a 2`2 optical fiber coupler 401, a Balanced Photoelectric Detector (BPD) 402 and a data acquisition card (DAQ) 403; the 2`2 optical fiber coupler 401 splitting ratio is 50, the optical fiber coupler is connected with the narrow linewidth laser 101 and the optical fiber circulator 301, and the rayleigh scattering light is coupled with the second light path B at the 2`2 optical fiber coupler 401; the Balanced Photoelectric Detector (BPD) 402 is connected with the 2`2 optical fiber coupler 401, and the coupled signal is divided into two parts to be transmitted into the Balanced Photoelectric Detector (BPD) 402 and converted into a beat frequency electric signal; the data acquisition card (DAQ) 403 is connected to the Balanced Photodetector (BPD) 402, and the beat frequency electrical signal is acquired by the digital acquisition card (DAQ) 403 to obtain a digital signal.
Compared with the embodiment 2, further, the system further comprises a computer (PC) 500 connected to a data acquisition card (DAQ) 403.
The rest of the structure is the same as that of embodiment 2.
In the using process, after the data acquisition card 403 acquires various types of disturbance intrusion signals, the disturbance intrusion signals are transmitted to the computer 500, and the computer 500 is used for processing and identifying the signals acquired by the digital acquisition card 403.
It should be noted that the above-mentioned embodiments are only for illustrating the technical solutions of the present invention and not for limiting, and although the present invention has been described in detail with reference to the preferred embodiments, it should be understood by those skilled in the art that modifications or equivalent substitutions may be made on the technical solutions of the present invention without departing from the spirit and scope of the technical solutions of the present invention, which should be covered by the claims of the present invention.
Claims (8)
1. A distributed optical fiber vibration sensing intelligent disturbance identification method is characterized in that: comprises the steps of (a) preparing a substrate,
collecting various disturbance invasion signals;
obtaining a phase matrix of a sensing subarea;
processing the phase matrix to obtain a phase difference signal matrix;
label definition is carried out on the phase difference signal matrix;
decomposing the phase difference signal matrix;
constructing a characteristic two-dimensional matrix;
and taking all the feature data and the labels in one-to-one correspondence as sample data, and balancing the samples of different label types.
2. The distributed optical fiber vibration sensing intelligent disturbance identification method according to claim 1, characterized in that: the step of collecting various disturbance intrusion signals comprises the following steps:
collecting by data collecting cardNA strip Rayleigh scattered light signal, whereinN>1；
Forming a signal time-space domain matrix by the beat signals corresponding to the Rayleigh scattering light
(ii) a Wherein,Dthe sampling point number of Rayleigh scattering light beat frequency signals corresponding to each light pulse is calculated;
each disturbance invasion signal is collected by more than 1 group, and the disturbance invasion signals are collected by all groups
The number of the groups is set to be,
is shown in
A second of the light pulses
The frequency of the beat signal is proportional to the frequency of the beat signal,
the information on the time is represented by,
indicating the location information.
3. The distributed optical fiber vibration sensing intelligent disturbance identification method according to claim 2, characterized in that: the step of obtaining the phase matrix of the sensing partition comprises:
dividing sensing optical fiber into
A segment sensing area;
demodulating the beat frequency signals at two ends of the sensing area according to groups by adopting a digital coherent demodulation algorithm to obtain the beat frequency signals
Phase matrix of segment sensing regions
。
4. The distributed optical fiber vibration sensing intelligent disturbance identification method according to claim 3, characterized in that: the step of processing the phase matrix to obtain a phase difference signal matrix comprises:
the phase matrix is formed
The vectors in the array are sequentially differentiated according to the columns to obtain a phase difference signal matrix representing the sensing information of the area
；
Each column of the vector comprises
A time domain sample point of
The column phase differential signal is represented as
The phase difference signal matrix
Each column of vectors in (a) contains the accumulation of all perturbed intrusion signals in the represented sensing area.
5. The distributed optical fiber vibration sensing intelligent disturbance identification method according to claim 4, characterized in that: the step of tag-defining the phase difference signal matrix comprises:
perturbed phase difference vector
The label is
Undisturbed phase difference vector
The label is
；
Obtaining a composition comprising
Tag vector of individual elements
。
6. The distributed optical fiber vibration sensing intelligent disturbance identification method according to claim 5, characterized in that: the step of decomposing the phase differential signal matrix comprises:
using wavelet packet decomposition algorithm to the phase difference signal matrix
Decomposing the original phase difference signal into a high-frequency signal and a low-frequency signal;
and decomposing the high-frequency and low-frequency signals of the previous layer into the next layer, and decomposing the four layers.
7. The distributed optical fiber vibration sensing intelligent disturbance identification method according to claim 6, characterized in that: the step of constructing a two-dimensional matrix of features comprises:
decomposing the phase difference signal matrix
Then each phase difference is obtainedComponent vector
16 frequency domain features of (1);
constructing a characteristic two-dimensional matrix by using the frequency domain characteristics
。
8. The distributed optical fiber vibration sensing intelligent disturbance identification method according to claim 7, characterized in that: the step of balancing samples of different label types by using all the feature data and the labels in one-to-one correspondence as sample data further comprises the steps of,
the balanced sample data is used as training data and input into a limit gradient adding classifier XGboost for training, and the obtained training model can successfully identify disturbance information in the phase sensitive optical time domain distributed optical fiber sensing system.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110935859.1A CN113670430B (en) | 2021-08-16 | 2021-08-16 | Distributed optical fiber vibration sensing intelligent disturbance identification method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110935859.1A CN113670430B (en) | 2021-08-16 | 2021-08-16 | Distributed optical fiber vibration sensing intelligent disturbance identification method |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN113670430A CN113670430A (en) | 2021-11-19 |
| CN113670430B true CN113670430B (en) | 2022-10-18 |
Family
ID=78543172
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110935859.1A Active CN113670430B (en) | 2021-08-16 | 2021-08-16 | Distributed optical fiber vibration sensing intelligent disturbance identification method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113670430B (en) |
Families Citing this family (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115790815B (en) * | 2023-01-17 | 2023-05-16 | 常熟理工学院 | Disturbance quick identification method and system for distributed optical fiber sensing system |
| CN117848478B (en) * | 2024-01-04 | 2024-07-12 | 中国新时代科技有限公司 | Underwater defensive optical fiber network detection method, device and storage medium |
Family Cites Families (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US9476760B2 (en) * | 2010-06-25 | 2016-10-25 | Schlumberger Technology Corporation | Precision measurements in a fiber optic distributed sensor system |
| CN105466548B (en) * | 2015-12-16 | 2019-06-04 | 上海大学 | Phase sensitive optical time domain reflection optical fiber sensing system localization method |
| CN105509868B (en) * | 2015-12-16 | 2019-06-04 | 上海大学 | Phase sensitive optical time domain reflection distributed fiber-optic sensor system phase calculation method |
| CN107425906B (en) * | 2017-07-25 | 2019-09-27 | 电子科技大学 | Distributing optical fiber sensing signal processing method towards underground pipe network safety monitoring |
| CN109391321B (en) * | 2018-11-20 | 2021-05-18 | 山东大学 | Disturbance positioning method in phase-sensitive OTDR (optical time Domain reflectometer) sensing |
| CN109961100A (en) * | 2019-03-26 | 2019-07-02 | 北京邮电大学 | WIFI indoor occupant intrusion detection method based on Principal Component Analysis |
| CN113049083B (en) * | 2021-03-09 | 2024-01-12 | 中国人民解放军国防科技大学 | Method for realizing high-frequency phase demodulation in distributed optical fiber sensing system |
-
2021
- 2021-08-16 CN CN202110935859.1A patent/CN113670430B/en active Active
Non-Patent Citations (2)
| Title |
|---|
| 分布式光纤振动检测系统信号后处理算法研究;李常 等;《山东科学》;20180630;第31卷(第3期);第61-65页 * |
| 基于φ-OTDR的振动检测研究型综合实验设计;秦祖军 等;《实验室研究与探索》;20210228;第40卷(第2期);第23-27页 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN113670430A (en) | 2021-11-19 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN113670430B (en) | Distributed optical fiber vibration sensing intelligent disturbance identification method | |
| Liu et al. | Vehicle detection and classification using distributed fiber optic acoustic sensing | |
| Riahi et al. | The seismic traffic footprint: Tracking trains, aircraft, and cars seismically | |
| CN105371943B (en) | The demodulation method and device of a kind of distributed optical fiber vibration sensing system | |
| CN101556724B (en) | Safety management system of optical fiber perimeter and pattern recognition method thereof | |
| Wu et al. | Comparison of positive and negative compact intracloud discharges | |
| Shi et al. | An easy access method for event recognition of Φ-OTDR sensing system based on transfer learning | |
| Bai et al. | Detection and identification of external intrusion signals from 33 km optical fiber sensing system based on deep learning | |
| CN105509868B (en) | Phase sensitive optical time domain reflection distributed fiber-optic sensor system phase calculation method | |
| CN113049084B (en) | Attention mechanism-based Resnet distributed optical fiber sensing signal identification method | |
| CN107167168A (en) | Phase sensitive optical time domain reflection distributed optical fiber sensing system accurate positioning method | |
| Liu et al. | Intercomparison of spring soil moisture among multiple reanalysis data sets over eastern China | |
| Kotchenova et al. | Modeling Lidar waveforms with time‐dependent stochastic radiative transfer theory for remote estimations of forest structure | |
| Delgado‐Balbuena et al. | Seasonal precipitation legacy effects determine the carbon balance of a semiarid grassland | |
| Yang et al. | Pipeline safety early warning by multifeature-fusion CNN and LightGBM analysis of signals from distributed optical fiber sensors | |
| Kepko et al. | Inherent length scales of periodic mesoscale density structures in the solar wind over two solar cycles | |
| CN103994784A (en) | Distributed optical fiber sensing positioning method based on zero crossing point analysis | |
| CN109064189A (en) | Brush list detecting and alarm device based on the detection of intensive block | |
| Wu et al. | Simultaneous extraction of multi-scale structural features and the sequential information with an end-to-end mCNN-HMM combined model for fiber distributed acoustic sensor | |
| LaRue et al. | Evaluating the sensitivity of forest structural diversity characterization to LiDAR point density | |
| Kettridge et al. | Do peatland microforms move through time? Examining the developmental history of a patterned peatland using ground‐penetrating radar | |
| Xu et al. | When remote sensing data meet ubiquitous urban data: Fine-grained air quality inference | |
| Wu et al. | Monitoring of the transmission line galloping with a novel distributed optical fibre sensor and its statistical data analysis | |
| Zhang et al. | Spatial variability and possible cause analysis of regional precipitation complexity based on optimized sample entropy | |
| Gorshkov et al. | A cost-effective distributed acoustic sensor for engineering geology |
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 |