CN104269006A - Optical fiber early warning system and mode identification method - Google Patents
Optical fiber early warning system and mode identification method Download PDFInfo
- Publication number
- CN104269006A CN104269006A CN201410494088.7A CN201410494088A CN104269006A CN 104269006 A CN104269006 A CN 104269006A CN 201410494088 A CN201410494088 A CN 201410494088A CN 104269006 A CN104269006 A CN 104269006A
- Authority
- CN
- China
- Prior art keywords
- light
- signal
- region
- optical fiber
- light source
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
Classifications
-
- G—PHYSICS
- G08—SIGNALLING
- G08B—SIGNALLING OR CALLING SYSTEMS; ORDER TELEGRAPHS; ALARM SYSTEMS
- G08B13/00—Burglar, theft or intruder alarms
- G08B13/02—Mechanical actuation
- G08B13/12—Mechanical actuation by the breaking or disturbance of stretched cords or wires
- G08B13/122—Mechanical actuation by the breaking or disturbance of stretched cords or wires for a perimeter fence
- G08B13/124—Mechanical actuation by the breaking or disturbance of stretched cords or wires for a perimeter fence with the breaking or disturbance being optically detected, e.g. optical fibers in the perimeter fence
-
- 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
- G06F18/2411—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches based on the proximity to a decision surface, e.g. support vector machines
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- Theoretical Computer Science (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Artificial Intelligence (AREA)
- Bioinformatics & Computational Biology (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Evolutionary Biology (AREA)
- Evolutionary Computation (AREA)
- General Engineering & Computer Science (AREA)
- Life Sciences & Earth Sciences (AREA)
- Investigating, Analyzing Materials By Fluorescence Or Luminescence (AREA)
Abstract
The invention discloses an optical fiber early warning system and a mode identification method, which relate to the field of pipeline monitoring.A signal acquisition and upper computer module amplifies and filters an electric signal, and converts the electric signal into a digital signal in an analog-to-digital manner, and then the digital signal is processed and analyzed; meanwhile, continuous light is generated in the Raman light source, the continuous light passes through a 2X2 branching unit and is divided into 2 beams of light which respectively enter a first wavelength division multiplexer and a second wavelength division multiplexer, the light is respectively injected into the sensing optical fiber from the forward direction and the reverse direction, and the light pulse generated by the laser light source is subjected to distributed amplification through a Raman scattering effect, so that the signal intensity along the sensing optical fiber is ensured; and finally, rearranging signals obtained in the multiple pulse processes in a signal acquisition and upper computer module to obtain two-dimensional signals related to space and time for subsequent use. The invention can effectively identify the events of people walking, manual excavation and vehicle passing, and carry out event positioning, thereby effectively reducing the false alarm rate of the early warning system.
Description
Technical field
The present invention relates to Monitoring Pinpelines field, particularly relate to a kind of predispersed fiber alarm system and mode identification method.
Background technology
Distribution type fiber-optic early warning system based on relevant Ruili scattering (Φ-OTDR) technology is the light intensity by detecting the rear orientation light of returning from the scattering of optical fiber each several part, detects extraneous vibration signal and locates it.Φ-OTDR is using general single mode fiber as optical transport and sensing carrier, can realize the Real-Time Monitoring of long distance and accurately locate, be convenient to lay, anti-electromagnetic interference capability is strong, be easy to through engineering approaches, be usually used in the fields such as the safety detection of engineering structure, optical fiber perimeter protection and oil-gas pipeline safety early warning.
In predispersed fiber alarm system, the Classification and Identification of vibration signal is most important, if produce wrong report, not only may cause the waste in manpower and materials, serious may incur loss through delay processing time threat to life property safety.Therefore how accurately intrusion event kind is identified, and alarm, reduce wrong report, avoid the unnecessary wasting of resources to be the critical problem that predispersed fiber alarm system is studied all the time.Meanwhile, due to fiber nonlinear effect and fiber Rayleigh scattering coefficient little, the distance sensing of coherent rayleigh scatter-type OTDR is always not long, makes it apply and is restricted.
In fixation and recognition, existing method is the position of locating events signal on spatial domain first, then extracts the time-domain signal of this position, carries out feature extraction to one dimension time-domain signal, then carries out Classification and Identification.
Inventor is realizing in process of the present invention, finds at least there is following shortcoming and defect in prior art:
This method first positions due to needs, therefore considerably increases the time of identification, and as multipoint positioning, operand is very big.In addition, the accuracy requirement for location is very high, once Wrong localization, then correctly can not identify kind of event, easily produce wrong report, can not satisfy the demands.Therefore be badly in need of a kind of efficient, mode identification method is applied to predispersed fiber alarm system accurately.
Summary of the invention
The invention provides a kind of predispersed fiber alarm system and mode identification method, the present invention efficiently can identify event type accurately, avoids unnecessary waste, and the generation of peril, described below:
A kind of predispersed fiber alarm system, comprise: LASER Light Source and Raman light source, continuous light that described LASER Light Source produces, carrying out modulation conversion via acousto-optic/electrooptic modulator is light pulse, wherein said acousto-optic/electrooptic modulator and driver thereof write the programmed control break-make of FGPA by the upper computer module in signals collecting and upper computer module, make continuous light form pulsed light;
Described pulsed light is after image intensifer amplifies, sensor fibre is injected by the first optical fiber circulator, the second optical fiber circulator, the scattered light of propagation dorsad that described pulsed light produces in communication process and reflected light along propagating in described sensor fibre in the opposite direction with light pulse propagation side, enter photodetector via the second optical fiber circulator and forming electric signal;
After described electric signal carries out amplifying through described signals collecting and upper computer module, filtering, analog to digital conversion be digital signal, complete the treatment and analyses of digital signal;
Simultaneously, continuous light is produced in described Raman light source, through 2X2 shunt, be divided into 2 bundle light, enter first wave division multiplexer, Second Wave division multiplexer respectively, inject described sensor fibre respectively from forward and inverse direction, pass through Raman scattering effect, distributed air-defense is carried out to the light pulse produced by described LASER Light Source, ensures in described sensor fibre signal intensity along the line;
Finally, in described signals collecting and upper computer module, the signal obtained in multiple pulses process is reset, obtain the 2D signal about room and time, for follow-up.
Described mode identification method comprises the following steps:
Adopt and calculate the method for scatter matrix 10 of image Expressive Features are selected, using the feature chosen as the input of sorter, carry out Classification and Identification;
By gaussian kernel function and man-to-man many categorised decisions, all training samples are tested, obtains final classification results;
By multiple sorter integrally and select 5-to roll over the method for cross validation to evaluate accuracy rate; Draw Average Accuracy and recognition efficiency;
The sorter designed is applied to described predispersed fiber alarm system scene and Real-Time Monitoring identification is carried out to intrusion event.
Described 10 Expressive Features are specially:
Pixel count in region convex hull pixel count, region, there is the excentricity of the ellipse of identical second moment with region, have the major axis of the ellipse of identical second moment with region, have the minor axis of the ellipse of identical second moment with region, have with region the quantity of object in diameter of a circle of the same area, region to deduct the quantity of these object Holes and barycenter minor increment, shape facility and shape to fill coefficient and form 10 features.
The beneficial effect of technical scheme provided by the invention is: this method is by carrying out discriminator process to the two-dimensional digital image that system acquisition signal is formed, effectively can identify people's walking, hand digging and cross car event, and carry out state event location, effectively reduce the rate of false alarm of early warning system.On the other hand, common coherent rayleigh scattering system distance sensing only has 20 kilometers, and this programme carries out continuing to amplify to detection light by raman pump light, distance sensing is increased to more than 50 kilometers.
Accompanying drawing explanation
Fig. 1 is the light path schematic diagram of predispersed fiber alarm system;
Fig. 2 is three kinds of event 2D signal spacetime diagrams;
Wherein, (a) behaves; B () is hand digging; C () is passed by for cart.
Fig. 3 is image after three kinds of event flags;
Wherein, (a) behaves; B () is hand digging; C () is passed by for cart.
Fig. 4 is regional quality distance schematic diagram in the heart;
Fig. 5 is region shape schematic diagram;
Fig. 6 is the stroll criterion matrix value schematic diagram of 10 eigenwerts;
Fig. 7 is RVM sorter training process schematic diagram;
Fig. 8 is RVM sorter identifying schematic diagram.
In accompanying drawing, the list of parts representated by each label is as follows:
1: LASER Light Source; 2: acousto-optic/electrooptic modulator and driver thereof;
3: image intensifer; 4-1: the first optical fiber circulator;
4-2: the second optical fiber circulator; 5: Raman light source;
6:2X2 shunt; 7-1: first wave division multiplexer;
7-2: Second Wave division multiplexer; 8: photodetector;
9: signals collecting and upper computer module; 10: sensor fibre.
Embodiment
For making the object, technical solutions and advantages of the present invention clearly, below embodiment of the present invention is described further in detail.
See Fig. 1, predispersed fiber alarm system by: LASER Light Source 1, acousto-optic/electrooptic modulator and driver 2 thereof, image intensifer 3, first optical fiber circulator 4-1, the second optical fiber circulator 4-2, Raman light source 5,2X2 shunt 6, first wave division multiplexer 7-1, Second Wave division multiplexer 7-2, photodetector 8, signals collecting and upper computer module 9, sensor fibre 10 are formed.
By LASER Light Source 1 produce continuous light, carrying out modulation conversion via acousto-optic/electrooptic modulator 2 is light pulse, wherein acousto-optic/electrooptic modulator and driver 2 thereof write the programmed control break-make of FGPA by upper computer module, continuous light is made to form pulsed light, light pulse is after image intensifer 3 amplifies, by the first optical fiber circulator 4-1, second optical fiber circulator 4-2 injects sensor fibre 10, the scattered light of propagation dorsad produced in its communication process and reflected light can along propagating in sensor fibre 10 in the opposite direction with light pulse propagation side, enter photodetector 8 via the second optical fiber circulator 4-2 and form electric signal, amplify through signals collecting and upper computer module 9, filtering, analog to digital conversion is after digital signal, complete the treatment and analyses of digital signal, thus the test result of the distributed fiberoptic sensor based on principle of interference and Rayleigh scattering principle can be obtained.
Simultaneously, continuous light is produced in Raman light source 5, through 2X2 shunt 6, be divided into 2 bundle light, enter first wave division multiplexer 7-1, Second Wave division multiplexer 7-2 respectively, inject sensor fibre 10 respectively from forward and inverse direction, pass through Raman scattering effect, distributed air-defense is carried out to the pulsed light produced by LASER Light Source 1, ensures that predispersed fiber alarm system is in sensor fibre 10 signal intensity along the line.Finally, in signals collecting and upper computer module 9, the signal obtained in multiple pulses process is reset, obtain the 2D signal about room and time, for follow-up.
Based on a security incident mode identification method for predispersed fiber alarm system, said method comprising the steps of:
1, vibration signal characteristics leaching process
1) 2D signal that Φ-OTDR predispersed fiber alarm system collects is exported in the form of images, utilize image procossing
Technology carries out Iamge Segmentation to 2D signal, is separated 2D signal event generation area with background area;
The embodiment of the present invention selects the threshold segmentation method based on Ostu.Utilize the noise in the method removal image of medium filtering, select the cavity in the method elimination region of image expansion, then with different colours, event area in image is marked.
2) people's walking, hand digging and mistake car are the event types that system is mainly differentiated, three kinds of events are because acting force is different, the amplitude of the two-dimension vibration signal therefore obtained is different, utilizes the original signal amplitude (Amplitude) of different marked region as the eigenwert of in proper vector.
3) different events is under identical sampling rate, and the interval of case point in time domain is different.First the barycenter of regional is calculated, barycenter C=[c
1, c
2..., c
n] represent, wherein n represents the number in region.The distance of the barycenter be then adjacent for each centroid calculation also asks minor increment.
d
min1＝min(|c
i-c
i-1|,|c
i-c
i+1|)，i∈(2,…,n-1) (1)
If only there is a characteristic area in image, when cannot obtain barycenter spacing, then give the larger value of this characteristic area one to represent distance.
The region shape can also observing different event from image also also exists difference, utilizes shape (Shap) feature to increase the diversity of feature.First the border b in each region is calculated
i, the distance of barycenter is then arrived a little according to formula (3) computation bound.
D
ik＝|b
ik-c
i|，k∈(1,…,K) (2)
In formula, K is the number of each zone boundary point, asks each zone boundary point to the ultimate range D of barycenter
imaxwith minor increment D
imin, the shape coefficient S in each region is calculated by formula (4).
S
i＝|D
imax-D
imin|(3)
In order to more fully describe provincial characteristics, this method utilizes general region description to join in proper vector.Region description subcategory is a lot, join in proper vector according to wherein relevant 7 of the feature selecting in security incident region, comprise: region convex hull pixel count ConvesArea, pixel count Area in region, the excentricity Eccentricity of the ellipse of identical second moment is had with region, the major axis MajorAxisLength of the ellipse of identical second moment is had with region, the minor axis MinorAxisLength of the ellipse of identical second moment is had with region, diameter of a circle EquivDiameter of the same area is had with region, EulerNumber is the quantity that the quantity of object in region deducts these object Holes.Above 7 features and barycenter minor increment, shape facility and shape dress coefficient form 10 features, as the Expressive Features amount of image, are input to next step and analyze.
As far as possible comprehensively describing provincial characteristics will inevitably make feature vector dimension too much, not only increase complicacy, and too much feature can increase the correlativity between feature, causes classification error.Therefore, utilizing the method for feature selecting to carry out dimensionality reduction can not only improve nicety of grading, and greatly reduces recognition efficiency.The present invention adopts the method calculating scatter matrix to carry out feature selecting.First in the class calculating three class event samples for 10 iamge description characteristic quantities mentioned above respectively, scatter matrix between scatter matrix and class, utilizes separability criterion formula (4) to carry out evaluating characteristic performance.
J＝tr{S
ω -1S
m} (4)
Wherein S
ωscatter matrix in class, S
mfor mixing scatter matrix:
S
m＝S
ω+S
b (5)
Wherein, S
bit is scatter matrix between class
In l dimension space, all well cluster is around average for the sample of each class, and inhomogeneity is when being separated completely, and this formula calculated value is large.Calculate the separability criterion value of each feature according to formula (4), select the larger feature of criterion value and carry out Classification and Identification.As shown in Figure 6, calculate the criterion value of each feature respectively, the criterion value of the 2nd, 3,4, No. 6 feature is more remarkable compared with the criterion value of other features, shows that it is more suitable for as classification foundation, when applying in sorter afterwards, these 4 features will be chosen and input as sorter.
2. security event classification identification
(1), after selecting the most significant feature of criterion value, feature is inputted sorter and carry out Classification and Identification.The present invention adopts the method for Method Using Relevance Vector Machine RVM (Relevance Vector Machine) to carry out the design of sorter.Sorter Selection of kernel function gaussian kernel function.Carry out many categorised decisions time, many categorised decisions of " one to one " that selection sort precision is the highest, namely 3 RVM are adopted to carry out following test to all samples respectively: whether whether whether be that people walks or excavated by manual work office, be that people walks or car passes through, be that hand digging or car pass through; Judging event type identical in 3 RVM results afterwards, is final classification results.Before use sorter, first with the training sample gathered in advance, sorter is trained, and test the performance of the sorter of training by ready test sample book.
(2) by multiple sorter integrally and select 5-to roll over the method [1] of cross validation to evaluate accuracy rate.Draw Average Accuracy and the recognition efficiency of algorithm.
(3) sorter designed is applied to Φ-OTDR distribution type fiber-optic early warning system scene and Real-Time Monitoring identification is carried out to intrusion event.
Below in conjunction with the drawings and specific embodiments, the present invention is further detailed explanation:
(1) Figure 1 shows that the System Working Principle schematic diagram of predispersed fiber alarm system.System is made up of LASER Light Source 1, acousto-optic/electrooptic modulator 2, image intensifer 3, optical fiber circulator 4, Raman light source 5,2X2 shunt 6, wavelength division multiplexer 7, photodetector 8, signals collecting and upper computer module 9, sensor fibre 10.By LASER Light Source 1 produce continuous light, carrying out modulation conversion via acousto-optic/electrooptic modulator 2 is light pulse, light pulse is by the first optical fiber circulator 4-1, second optical fiber circulator 4-2 injects sensor fibre 10, the scattered light of propagation dorsad produced in its communication process and reflected light can along propagating in sensor fibre 10 in the opposite direction with light pulse propagation side, via the electric signal entering photodetector 8 formation of the second optical fiber circulator 4-2, amplify through signals collecting and upper computer module 9, filtering, analog to digital conversion is after digital signal, send into the treatment and analyses completing digital signal in host computer, thus the test result of the distributed fiberoptic sensor based on principle of interference and Rayleigh scattering principle can be obtained.Simultaneously, continuous light is produced in Raman light source 5, through 2X2 shunt 6, be divided into 2 bundle light, enter first wave division multiplexer 7-1 and Second Wave division multiplexer 7-2 respectively, inject sensor fibre 10 respectively from forward and inverse direction, pass through Raman scattering effect, distributed air-defense is carried out to the pulsed light produced by LASER Light Source 1, ensures that predispersed fiber alarm system is in sensor fibre 10 signal intensity along the line.Finally, in host computer, the signal obtained in multiple pulses process is reset, obtain the 2D signal about room and time, for follow-up.
(2) 2D signal passed by of predispersed fiber alarm system collects people's walking, hand digging and cart after filtering after image as shown in Figure 2.
(3) method of Threshold segmentation in image processing techniques is utilized event area to be extracted from background image, and medium filtering removal noise is carried out to it, utilize the hole in the method elimination region of image expansion, the event area in image is marked, as shown in Figure 3.
(4) morphologic feature extracting method is utilized to carry out feature extraction to the region in three types occurrence diagram picture, comprise event amplitude, interregional every, region shape and region description, as shown in Figure 4 and Figure 5, utilize after feature extraction and calculate the method for scatter matrix and carry out screening to proper vector and remove redundancy feature, larger front four features of selection criteria values, as proper vector, calculate scatter matrix result as Fig. 6.
(5) above-mentioned proper vector be input in RVM sorter and train sorter, the present invention adopts man-to-man many categorised decisions, and event to be sorted has people to walk, hand digging and calling a taxi is passed by, therefore needs three RVM sorters.Training flow process and identifying are as Fig. 7, sorter RVM1 is responsible for distinguishing people and walks about and hand digging event, sorter RVM2 is responsible for differentiation hand digging and event passed by by cart, sorter RVM3 be responsible for distinguish people walk about and cart pass by event, use ready data sample to carry out the classification based training of corresponding event to three sorters respectively.Identifying as shown in Figure 8, the characteristic quantity of event to be identified is sent in RVM1, RVM2 and RVM3 simultaneously, three sorters all provide classification results afterwards, and wherein the result of 2 sorters is corresponding real event types, finally select the result of final classification with majority principle.
(6) select 20 samples to test classifier performance in often kind of event 100 samples, and utilize the method evaluation test result of cross validation.
(7) signal characteristic enters in the sorter trained subsequently, and the result obtained is the result of sorter to intrusion event identification, and this result is sent to host computer and shows.
List of references
[1] military graceful. Classifier Performance Evaluation research [D]. Beijing Jiaotong University, 2010.
It will be appreciated by those skilled in the art that accompanying drawing is the schematic diagram of a preferred embodiment, the invention described above embodiment sequence number, just to describing, does not represent the quality of embodiment.
The foregoing is only preferred embodiment of the present invention, not in order to limit the present invention, within the spirit and principles in the present invention all, any amendment done, equivalent replacement, improvement etc., all should be included within protection scope of the present invention.
Claims (3)
1. a predispersed fiber alarm system, comprising: LASER Light Source and Raman light source, is characterized in that,
Continuous light that described LASER Light Source produces, carrying out modulation conversion via acousto-optic/electrooptic modulator is light pulse, wherein said acousto-optic/electrooptic modulator and driver thereof write the programmed control break-make of FGPA by the upper computer module in signals collecting and upper computer module, make continuous light form pulsed light;
Described pulsed light is after image intensifer amplifies, sensor fibre is injected by the first optical fiber circulator, the second optical fiber circulator, the scattered light of propagation dorsad that described pulsed light produces in communication process and reflected light along propagating in described sensor fibre in the opposite direction with light pulse propagation side, enter photodetector via the second optical fiber circulator and forming electric signal;
After described electric signal carries out amplifying through described signals collecting and upper computer module, filtering, analog to digital conversion be digital signal, complete the treatment and analyses of digital signal;
Simultaneously, continuous light is produced in described Raman light source, through 2X2 shunt, be divided into 2 bundle light, enter first wave division multiplexer, Second Wave division multiplexer respectively, inject described sensor fibre respectively from forward and inverse direction, pass through Raman scattering effect, distributed air-defense is carried out to the light pulse produced by described LASER Light Source, ensures in described sensor fibre signal intensity along the line;
Finally, in described signals collecting and upper computer module, the signal obtained in multiple pulses process is reset, obtain the 2D signal about room and time, for follow-up.
2. for a mode identification method for predispersed fiber alarm system according to claim 1, it is characterized in that, described mode identification method comprises the following steps:
Adopt and calculate the method for scatter matrix 10 of image Expressive Features are selected, using the feature chosen as the input of sorter, carry out Classification and Identification;
By gaussian kernel function and man-to-man many categorised decisions, all training samples are tested, obtains final classification results;
By multiple sorter integrally and select 5-to roll over the method for cross validation to evaluate accuracy rate; Draw Average Accuracy and recognition efficiency;
The sorter designed is applied to described predispersed fiber alarm system scene and Real-Time Monitoring identification is carried out to intrusion event.
3. method according to claim 2, is characterized in that, described 10 Expressive Features are specially:
Pixel count in region convex hull pixel count, region, there is the excentricity of the ellipse of identical second moment with region, have the major axis of the ellipse of identical second moment with region, have the minor axis of the ellipse of identical second moment with region, have with region the quantity of object in diameter of a circle of the same area, region to deduct the quantity of these object Holes and barycenter minor increment, shape facility and shape to fill coefficient and form 10 features.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201410494088.7A CN104269006B (en) | 2014-09-24 | 2014-09-24 | Mode identification method for optical fiber early warning system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201410494088.7A CN104269006B (en) | 2014-09-24 | 2014-09-24 | Mode identification method for optical fiber early warning system |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN104269006A true CN104269006A (en) | 2015-01-07 |
| CN104269006B CN104269006B (en) | 2016-08-03 |
Family
ID=52160524
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201410494088.7A Active CN104269006B (en) | 2014-09-24 | 2014-09-24 | Mode identification method for optical fiber early warning system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN104269006B (en) |
Cited By (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105141477A (en) * | 2015-08-20 | 2015-12-09 | 中国人民解放军西安通信学院 | Optical network information security monitoring system based on optical fiber sensing and monitoring method |
| CN105698916A (en) * | 2016-03-01 | 2016-06-22 | 深圳艾瑞斯通技术有限公司 | Optical fiber vibration model determination method and optical fiber early warning device and system |
| CN105931402A (en) * | 2016-06-27 | 2016-09-07 | 上海波汇科技股份有限公司 | Optical fiber perimeter intrusion monitoring method based on image recognition |
| CN106441773A (en) * | 2016-11-03 | 2017-02-22 | 北京航天易联科技发展有限公司 | Adjustable vibration impact testing device |
| CN106504451A (en) * | 2016-11-14 | 2017-03-15 | 中国人民解放军国防科学技术大学 | A kind of demodulating algorithm of the optical fiber perimeter safety signal based on matrix theory |
| CN108133559A (en) * | 2016-11-30 | 2018-06-08 | 光子瑞利科技（北京）有限公司 | Application of the optical fiber end-point detection in circumference early warning system |
| CN108197646A (en) * | 2017-12-28 | 2018-06-22 | 中国电子科技集团公司第五十四研究所 | A kind of target classification identification method for distributed optical fiber sensing system |
| CN109272017A (en) * | 2018-08-08 | 2019-01-25 | 太原理工大学 | The vibration signal mode identification method and system of distributed fiberoptic sensor |
| CN110335430A (en) * | 2019-06-19 | 2019-10-15 | 中国科学院自动化研究所 | Monitoring pipeline safety system, method and apparatus based on deep learning |
| CN114166331A (en) * | 2021-12-03 | 2022-03-11 | 武汉理工光科股份有限公司 | Non-threat signal identification method and device, electronic equipment and storage medium |
| CN114268365A (en) * | 2021-12-02 | 2022-04-01 | 国网甘肃省电力公司酒泉供电公司 | Intelligent communication optical cable early warning method and system based on visualization technology |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| EP0605301A1 (en) * | 1992-12-29 | 1994-07-06 | Ando Electric Co., Ltd. | Optical time domain reflectometer |
| CN104034409A (en) * | 2014-06-27 | 2014-09-10 | 天津大学 | Distributed optical fiber vibration sensing method and system based on pulse code external modulation |
-
2014
- 2014-09-24 CN CN201410494088.7A patent/CN104269006B/en active Active
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| EP0605301A1 (en) * | 1992-12-29 | 1994-07-06 | Ando Electric Co., Ltd. | Optical time domain reflectometer |
| CN104034409A (en) * | 2014-06-27 | 2014-09-10 | 天津大学 | Distributed optical fiber vibration sensing method and system based on pulse code external modulation |
Non-Patent Citations (3)
| Title |
|---|
| TAOZHU，XIANGHUI XIAO，QIAN HE，DONGMEI DIAO: "Enhancement of SNR and Spatial Resolution in φ-OTDR System by Using Two-Dimensional Edge Detection Method", 《LIGHTWAVE TECHNOLOGY》, 30 September 2013 (2013-09-30) * |
| 安阳等: "基于双光束干涉的相位敏感光时域反射计", 《光学学报》, vol. 33, no. 7, 31 July 2013 (2013-07-31) * |
| 王杰等: "基于双向拉曼放大的相位敏感光时域反射仪", 《物理学报》, vol. 62, no. 4, 31 December 2013 (2013-12-31) * |
Cited By (14)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105141477B (en) * | 2015-08-20 | 2018-12-04 | 中国人民解放军西安通信学院 | A kind of optical-fiber network information security monitoring system and monitoring method based on Fibre Optical Sensor |
| CN105141477A (en) * | 2015-08-20 | 2015-12-09 | 中国人民解放军西安通信学院 | Optical network information security monitoring system based on optical fiber sensing and monitoring method |
| CN105698916A (en) * | 2016-03-01 | 2016-06-22 | 深圳艾瑞斯通技术有限公司 | Optical fiber vibration model determination method and optical fiber early warning device and system |
| CN105698916B (en) * | 2016-03-01 | 2019-07-26 | 深圳艾瑞斯通技术有限公司 | Fiber-optic vibration model determines method and optical fiber prior-warning device, system |
| CN105931402A (en) * | 2016-06-27 | 2016-09-07 | 上海波汇科技股份有限公司 | Optical fiber perimeter intrusion monitoring method based on image recognition |
| CN106441773A (en) * | 2016-11-03 | 2017-02-22 | 北京航天易联科技发展有限公司 | Adjustable vibration impact testing device |
| CN106504451A (en) * | 2016-11-14 | 2017-03-15 | 中国人民解放军国防科学技术大学 | A kind of demodulating algorithm of the optical fiber perimeter safety signal based on matrix theory |
| CN108133559A (en) * | 2016-11-30 | 2018-06-08 | 光子瑞利科技（北京）有限公司 | Application of the optical fiber end-point detection in circumference early warning system |
| CN108197646A (en) * | 2017-12-28 | 2018-06-22 | 中国电子科技集团公司第五十四研究所 | A kind of target classification identification method for distributed optical fiber sensing system |
| CN109272017A (en) * | 2018-08-08 | 2019-01-25 | 太原理工大学 | The vibration signal mode identification method and system of distributed fiberoptic sensor |
| CN109272017B (en) * | 2018-08-08 | 2022-07-12 | 太原理工大学 | Vibration signal mode identification method and system of distributed optical fiber sensor |
| CN110335430A (en) * | 2019-06-19 | 2019-10-15 | 中国科学院自动化研究所 | Monitoring pipeline safety system, method and apparatus based on deep learning |
| CN114268365A (en) * | 2021-12-02 | 2022-04-01 | 国网甘肃省电力公司酒泉供电公司 | Intelligent communication optical cable early warning method and system based on visualization technology |
| CN114166331A (en) * | 2021-12-03 | 2022-03-11 | 武汉理工光科股份有限公司 | Non-threat signal identification method and device, electronic equipment and storage medium |
Also Published As
| Publication number | Publication date |
|---|---|
| CN104269006B (en) | 2016-08-03 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN104269006B (en) | Mode identification method for optical fiber early warning system | |
| Tejedor et al. | Toward prevention of pipeline integrity threats using a smart fiber-optic surveillance system | |
| CN106503642B (en) | A kind of model of vibration method for building up applied to optical fiber sensing system | |
| US11783452B2 (en) | Traffic monitoring using distributed fiber optic sensing | |
| Singh et al. | Buried object detection and analysis of GPR images: Using neural network and curve fitting | |
| CN109272017B (en) | Vibration signal mode identification method and system of distributed optical fiber sensor | |
| CN111537056A (en) | Pipeline along-line third-party construction dynamic early warning method based on SVM and time-frequency domain characteristics | |
| CN101017573A (en) | Method for detecting and identifying moving target based on video monitoring | |
| CN102280001B (en) | Distributed optical fiber fence intrusion detection and location method based on phi-OTDR (Optical Time Domain Reflectometer) | |
| Amiri et al. | Estimation of regeneration coverage in a temperate forest by 3D segmentation using airborne laser scanning data | |
| CN112985574B (en) | High-precision classification identification method for optical fiber distributed acoustic sensing signals based on model fusion | |
| CN109120336B (en) | False alarm prevention and false alarm prevention method based on phase sensitive optical time domain reflection sensor | |
| Zhu et al. | A comprehensive bibliometric analysis of signal processing and pattern recognition based on distributed optical fiber | |
| KR20200123537A (en) | Method for detecting sinkhole using deep learning and data association and sinkhole detecting system using it | |
| CN106706109B (en) | Vibration source identification method and system based on time domain two-dimensional characteristics | |
| CN103914707A (en) | Green channel product auxiliary discriminating method based on support vector machine | |
| CN108241150B (en) | Method for detecting and tracking moving object in three-dimensional sonar point cloud environment | |
| CN118314513A (en) | Distributed optical fiber sensing signal processing method and system | |
| CN101976342A (en) | Space-time collaborative determination-based cat eye effect target identification method | |
| CN109614926B (en) | Distributed optical fiber sensing signal mode identification method and system based on prediction model | |
| CN116504005B (en) | Perimeter security intrusion signal identification method based on improved CDIL-Bi-LSTM | |
| CN116561536A (en) | Landslide hidden danger identification method, terminal equipment and medium | |
| Kumar et al. | The Real Time Vehicle License Plate Identification System | |
| Tian et al. | Detection and recognition of mechanical, digging and vehicle signals in the optical fiber pre-warning system | |
| Tejedor et al. | Towards detection of pipeline integrity threats using a SmarT fiber-OPtic surveillance system: PIT-STOP project blind field test results |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| C14 | Grant of patent or utility model | ||
| GR01 | Patent grant | ||
| TR01 | Transfer of patent right |
Effective date of registration: 20220525 Address after: 300392 East Second floor, building 5, Haitai development liudao Star Enterprise Center, Huayuan Industrial Zone (outside the ring), Tianjin Binhai high tech Zone, Xiqing District, Tianjin Patentee after: TIANJIN PRECISION INSTRUMENT AND PRECISION MEASUREMENT TECHNOLOGY CO.,LTD. Address before: 300072 Tianjin City, Nankai District Wei Jin Road No. 92 Patentee before: Tianjin University |
|
| TR01 | Transfer of patent right |