CN108287016A - A kind of ocean optical fiber Recognition of Vibration Sources method, apparatus and system based on decision Tree algorithms - Google Patents
A kind of ocean optical fiber Recognition of Vibration Sources method, apparatus and system based on decision Tree algorithms Download PDFInfo
- Publication number
- CN108287016A CN108287016A CN201710016503.1A CN201710016503A CN108287016A CN 108287016 A CN108287016 A CN 108287016A CN 201710016503 A CN201710016503 A CN 201710016503A CN 108287016 A CN108287016 A CN 108287016A
- Authority
- CN
- China
- Prior art keywords
- fiber
- signal
- vibration
- optic
- vibration signal
- 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
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
- G06F18/24—Classification techniques
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- Theoretical Computer Science (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)
- Measurement Of Mechanical Vibrations Or Ultrasonic Waves (AREA)
Abstract
The invention discloses a kind of optical fiber Recognition of Vibration Sources method, apparatus and systems.Wherein, this method includes:Identification terminal obtains fiber-optic vibration signal;Classified to the fiber-optic vibration signal using Decision Tree Algorithm, obtains the vibration source type of the fiber-optic vibration signal.By the above-mentioned means, the present invention can realize the optical fiber vibration source type in intelligent recognition water, recognition efficiency is improved.
Description
Technical field
The present invention relates to fiber optic communication fields, more particularly to a kind of optical fiber Recognition of Vibration Sources method, apparatus and system.
Background technology
With optical fiber processing technology develop, using fiber-optic probe surrounding enviroment situation, for example whether have object pass through and
The object is specifically what.When detection fiber is influenced to vibrate by external interference, the part that light is transmitted in optical fiber is special
Property will change, identification terminal is acquired signal, analysis acquisition signal feature to judge the change of its light characteristic, in turn
It can detect that and the corresponding signal of vibration position occurs, and then its vibration source type is gone out according to the signal identification.
However, existing fiber Recognition of Vibration Sources method generally use manually compares vibration signal with vibration source to induction signal, to sentence
Break and whether the vibration signal belongs to the vibration source.Existing manual identified mode efficiency is low.
Submarine is by one of the grand strategy weapon recognized by the whole world, and the high low energy of submarine technology shows a country
Military strength, so every country put on submarine technology it is more, innovation it is very fast, it is technologically advanced, submarine be also compared with
Early stage, just some was hidden track carrier.The noise of submarine, which is down to 90 decibels or so, " can flood " in the vast oceans background noise
In, not being contemporary sonar can detect, and utilize light Recognition of Vibration Sources that traditional sonar can be replaced to detect, and can identify
It is more accurate.
Invention content
The invention mainly solves the technical problem of providing a kind of optical fiber Recognition of Vibration Sources method, apparatus and system, Neng Goushi
Existing intelligent recognition optical fiber vibration source, improves recognition efficiency.
In order to solve the above technical problems, one aspect of the present invention is:A kind of optical fiber Recognition of Vibration Sources side is provided
Method, including:Identification terminal obtains fiber-optic vibration signal;The fiber-optic vibration signal is divided using Decision Tree Algorithm
Class obtains the vibration source type of the fiber-optic vibration signal.
Wherein, described the step of being classified to the fiber-optic vibration signal using Decision Tree Algorithm, includes:By institute
The feature for stating fiber-optic vibration signal is matched with corresponding default characteristic model, and according to matching result, continue and its
He matches or is determined as the vibration source type of the fiber-optic vibration signal and the default character modules default characteristic model
The corresponding vibration source type of type.
Wherein.The feature by the fiber-optic vibration signal is matched with corresponding default characteristic model, and according to
Matching result, continue with other preset characteristic model matched or by the vibration source type of the fiber-optic vibration signal it is true
The step of being set to vibration source type corresponding with the default characteristic model include:Judge the ceiling capacity of the fiber-optic vibration signal
Whether feature meets the corresponding default ceiling capacity model of fish swarming vibration source type;If meeting, the fiber-optic vibration is believed
Number vibration source type be determined as fish swarming vibration source.
Wherein, the feature by the fiber-optic vibration signal is matched with corresponding default characteristic model, and according to
Matching result, continue with other preset characteristic model matched or by the vibration source type of the fiber-optic vibration signal it is true
The step of being set to vibration source type corresponding with the default characteristic model further include:If the ceiling capacity feature does not meet described
Default ceiling capacity model, then judge whether the energy information entropy feature of the fiber-optic vibration signal meets minisub type
Corresponding preset energy entropy model;If meeting, the vibration source type of the fiber-optic vibration signal is determined as small-sized diving
Device.
Wherein, the feature by the fiber-optic vibration signal is matched with corresponding default characteristic model, and according to
Matching result, continue with other preset characteristic model matched or by the vibration source type of the fiber-optic vibration signal it is true
The step of being set to vibration source type corresponding with the default characteristic model further include:If the energy information entropy feature does not meet institute
Preset energy entropy model is stated, then judges whether the duration of the fiber-optic vibration signal is more than setting time;If being more than,
The matching of fundamental frequency cycles model is then carried out to the fiber-optic vibration signal;Otherwise, signal mode is carried out to the fiber-optic vibration signal
The matching of type.
Wherein, it is described to the fiber-optic vibration signal carry out fundamental frequency cycles model matching the step of include:Described in judgement
Fiber-optic vibration signal whether has fundamental frequency and whether fundamental frequency cycles reach setting value;If so, by the fiber-optic vibration signal
Vibration source type is determined as large-scale submarine vibration source;Otherwise, the vibration source type of the fiber-optic vibration signal is determined as medium-sized submarine to shake
Source.
Wherein, it is described to the fiber-optic vibration signal carry out signal model matching the step of include:Obtain the optical fiber
The energy levels of vibration signal;If the energy levels are more than the first degree, by the vibration source type of the fiber-optic vibration signal
It is determined as large ship vibration source;If the energy levels are less than the second degree, by the vibration source type of the fiber-optic vibration signal
It is determined as small-sized steamer, wherein first degree is higher than second degree.
Wherein, the method further includes:Determine the notification level belonging to the corresponding vibration source type of the fiber-optic vibration signal;
Corresponding notice is carried out according to the notification level.
In order to solve the above technical problems, another technical solution used in the present invention is:A kind of optical fiber Recognition of Vibration Sources is provided
Device, including:Acquisition module, for obtaining fiber-optic vibration signal;Sort module, for using Decision Tree Algorithm to described
Fiber-optic vibration signal is classified, and the vibration source type of the fiber-optic vibration signal is obtained.
In order to solve the above technical problems, another technical solution that the present invention uses is:Kind of an optical fiber Recognition of Vibration Sources system is provided
System, including fibre optical sensor and identification terminal;The fibre optical sensor for sending out the first optical signal at one end, and from described one
End receives the second optical signal reflected by first optical signal;The identification terminal is for determining that the second optical signal corresponds to
Electric signal when being fiber-optic vibration signal, Recognition of Vibration Sources is carried out to the fiber-optic vibration signal, wherein the identification terminal includes
Above-mentioned optical fiber Recognition of Vibration Sources device, to carry out Recognition of Vibration Sources to the fiber-optic vibration signal.
Said program, identification terminal classify to light vibration signal using Decision Tree Algorithm, without artificial ginseng
With, realize the intelligent recognition to optical fiber vibration source, moreover, using Decision Tree Algorithm can to a nodes multiple or even up to ten thousand into
Row classification, effect is faster more more acurrate than manual identified, therefore improves recognition efficiency and accuracy.
Description of the drawings
Fig. 1 is the flow chart of one embodiment of optical fiber Recognition of Vibration Sources method of the present invention;
Fig. 2 is the structural schematic diagram of one embodiment of optical fiber Recognition of Vibration Sources system of the present invention;
Fig. 3 is the flow chart of another embodiment of optical fiber Recognition of Vibration Sources method of the present invention;
Fig. 4 is the structural schematic diagram of the decision tree used in embodiment described in Fig. 3;
Fig. 5 is the partial process view of optical fiber Recognition of Vibration Sources method another embodiment of the present invention;
Fig. 6 is the structural schematic diagram of one embodiment of optical fiber Recognition of Vibration Sources device of the present invention;
Fig. 7 is the structural schematic diagram of another embodiment of optical fiber Recognition of Vibration Sources device of the present invention.
Specific implementation mode
In being described below, for illustration and not for limitation, it is proposed that such as specific system structure, interface, technology it
The detail of class, so as to provide a thorough understanding of the present application.However, it will be clear to one skilled in the art that there is no these specific
The application can also be realized in the other embodiment of details.In other situations, omit to well-known device, circuit with
And the detailed description of method, so as not to obscure the description of the present application with unnecessary details.
Referring to Fig. 1, the flow chart of one embodiment of optical fiber Recognition of Vibration Sources method of the present invention, this method include:
S11:Identification terminal obtains fiber-optic vibration signal.
Wherein, the fiber-optic vibration signal is fiber optic telecommunications number, which is converted by the optical signal of fiber reflection
It obtains.
Incorporated by reference to Fig. 2 for example, Fig. 2 shows an optical fiber Recognition of Vibration Sources system, which can be used
Light pulse modulation system, by detect backscatter signals phase change caused by reflecting interference Strength Changes, Neng Goutong
When detect multiple concurrent vibration sources, to realize early warning and to vibration source position.The optical fiber Recognition of Vibration Sources system includes being linked in sequence
Fibre optical sensor 21, optical system 23, photoelectric switching circuit 24 and identification terminal 22.
Fibre optical sensor 21 is set in the environment that need to be monitored such as underground, to monitor the environmental aspect.Fibre optical sensor 21
In common communications optical cable idle fibre core can be used and make sensing unit, carry out Distributed Multi vibration measurement.It is substantially former
Reason is to cause fibre core in optical cable to deform upon when extraneous effect of vibration is in communications optical cable, and core length and refractive index is made to send out
Changing causes the phase of light in optical cable to change.When light transmits in optical cable, since photon and fibre core lattice are made
With constantly transmitting Rayleigh scattering light backward.When the external world has vibration to occur, the phase of back rayleigh scattering light becomes therewith
Change, these carry the signal light of extraneous vibration information, are handled through optical system 23, and faint phase change, which is converted to light intensity, to be become
Change, then after the opto-electronic conversion of photoelectric switching circuit 24 and corresponding signal processing, data analysis is carried out into people's identification terminal 22.Know
Other terminal 22 as a result, judge the generation of vibration event, and confirms vibration place according to analysis.
Specifically, 21 timing of fibre optical sensor sends out the first optical signal from one end, which can be a pulse
Signal, is such as the laser that pulse width is 15ns, and first optical signal each position in optical cable is formed by Rayleigh scattering
Second optical signal, and second optical signal is reflected back one end of the fibre optical sensor 21.Fibre optical sensor 21 is defeated from the one end
Go out second optical signal.Optical system 23 samples the second optical signal, obtains multiple Sampled optical signals.Wherein, the sampling
Interval can acquire the optical signal that optical fiber emits every setpoint distance, for example, first Sampled optical signals is corresponded to apart from optical fiber one
The optical signal of 1 meter of position reflection, second Sampled optical signals is held to correspond to the optical signal reflected apart from the 2 meters of positions in optical fiber one end,
And so on.
Due to the optical signal of backscattering and its faint, and its noise is smaller, difficult during to optical signal prosessing
Spend that larger, precision is smaller, therefore above-mentioned multiple Sampled optical signals clearance photoelectric switching circuits 23 are converted to corresponding adopt by system
Sample electric signal is convenient for the processing of signal.Here it can be converted to analog signal by such as APD of general photoelectric switching circuit 23,
Digital signal is converted analog signals by analog-digital converter again, and is sent to identification terminal 22.
In other embodiments, the opto-electronic conversion and analog-to-digital conversion step can be executed by identification terminal 22, i.e. identification is whole
End 22 receives the multiple Sampled optical signals obtained to the second light signal collection that fibre optical sensor 21 reflects, and converts thereof into more
A sampling electric signal, and the sampling electric signal is compared and analyzed with default vibration signal, if the sampling electric signal with it is default
Vibration signal waveforms match, then the sampling electric signal are directly confirmed as fiber-optic vibration signal.Alternatively, identification terminal obtain with it is pre-
If after the matched sampling electric signal of vibration signal, smooth performance of the analysis first sampling electric signal in time domain and spatial domain;It is right
Answer it is described sampling electric signal different time domain and spatial domain smooth performance, using different detection modes to the sampling electric signal into
Row detection;If the detection passes through, the sampling electric signal is confirmed as fiber-optic vibration signal.
Wherein, which acquires fiber-optic vibration signal in real time, which can be adjusted according to actual conditions,
In general, the acquisition interval is between 10 μ s-100 μ s, such as 20 μ s, 50 μ s, 100 μ s.Identification terminal 22 can in real time shake to optical fiber
Dynamic signal is handled, or timing carries out signal processing, for example, every 1024 vibration signals are divided into a frame by identification terminal 22
{ xl, x2...., x1024 } collects one minute fiber-optic vibration signal and carries out data processing.
S12:Identification terminal classifies to the fiber-optic vibration signal using Decision Tree Algorithm, obtains the optical fiber
The vibration source type of vibration signal.
Decision Tree Algorithm is otherwise known as greedy algorithm, through the recursive fashion frequently with " top-down, divide and rule ",
It is a kind of sorting algorithm of the form of expression that deducing out similar bifurcated tree at random, in chaotic case from one group, can also
Referred to as multiple judgment rules.The top mode of decision tree is referred to as root node, is the input node of fiber-optic vibration signal, output section
Point is known as leaf node, represents the vibration source classification that the identification of a classification obtains;All non-leaf nodes (inside section on tree
Point) as soon as all representing the judgement to feature, branch represents the result of judgement.
In the present embodiment, decision Tree algorithms are the sections of the feature and decision tree of the fiber-optic vibration signal by will collect
The corresponding characteristic model of point compares, and classifies to it.For example, identification terminal by the feature of the fiber-optic vibration signal with it is right
The default characteristic model answered is matched, and according to matching result, continue with other preset characteristic model matched or
The vibration source type of the fiber-optic vibration signal is determined as vibration source type corresponding with the default characteristic model by person.
In a concrete application, identification terminal 22 pre-establishes decision tree, and each node correspondence of decision tree, which is preset with, shakes
Dynamic signal model, wherein the signal characteristic of the corresponding vibration signal of a vibration source type is stored with per vibration signal model.Self-decision
The root node of tree rises, and the feature of the fiber-optic vibration signal is matched with corresponding default characteristic model, and according to matching
As a result enter next node, if next node is leaf node, then it represents that the vibration source type of the fiber-optic vibration signal is the root section
The corresponding vibration source type of point;If next node is internal node, continued optical fiber signal of vibrating and the internal node pair
The default characteristic model answered is matched, and so on, until reaching leaf node.
In the present embodiment, identification terminal classifies to light vibration signal using Decision Tree Algorithm, without artificial
It participates in, the intelligent recognition to optical fiber vibration source is realized, moreover, can be to a nodes multiple or even up to ten thousand using Decision Tree Algorithm
Classify, effect is faster more more acurrate than manual identified, therefore improves recognition efficiency and accuracy.In addition, due to decision tree
It is simple in structure to understand and be easily achieved, identification process can be simplified.
Referring to Fig. 3, Fig. 3 is the flow chart of another embodiment of method of optical fiber Recognition of Vibration Sources of the present invention.In the present embodiment,
The corresponding vibration signal of vibration source type existing for environment residing for acquisition fibre optical sensor in advance, and according to the signal of different vibration sources
Feature establishes corresponding model.The vibration source type may include fish swarming, large-scale submarine, small-sized steamer, medium-sized submarine, small-sized diving
Device, large ship vibration source etc..Identification terminal pre-establishes the corresponding model of above-mentioned vibration source type, and with above-mentioned model foundation decision
Tree is as shown in Figure 4.One actually should in, which is used to detect the environment on petroleum pipeline periphery.The method packet
Include following steps:
S301:Identification terminal obtains fiber-optic vibration signal;
Described in an embodiment as above, this will not be repeated here.
S302:Identification terminal judges whether the ceiling capacity feature of the fiber-optic vibration signal meets fish swarming vibration source class
The corresponding default ceiling capacity model of type executes S303, otherwise executes S304 if meeting.
As above-mentioned, the optical fiber vibration source type in the present embodiment includes fish swarming vibration source.Identification terminal can acquire fish in advance
The vibration signal that optical fiber corresponding position generates when group's travelling, analyzes the vibration signal and obtains, and what which generated shakes
The vibration signal vibration signal that is distinct, therefore being generated with the fish swarming vibration source of the ceiling capacity and other vibration sources of dynamic signal
Ceiling capacity establish ceiling capacity model, and fish swarming vibration source is determined whether with the ceiling capacity model.
For example, the ceiling capacity for the vibration signal that the fish swarming vibration source measured in advance generates, through the ceiling capacity is made
To touch the ceiling capacity condition met needed for optical fiber vibration source.Identification terminal shakes to optical fiber after getting fiber-optic vibration signal
Dynamic signal carry out decision tree root node -- the classification of ceiling capacity model calculates the ceiling capacity of the fiber-optic vibration signal,
And judge that the ceiling capacity of the fiber-optic vibration signal meets the ceiling capacity condition, it is fish swarming vibration source if meeting, otherwise
It is not fish swarming vibration source.The ceiling capacity of the fiber-optic vibration signal be the fiber-optic vibration signal in setting time energy and,
Or it is the corresponding energy of peak swing in setting time.The setting time can be a wave period.
S303:The vibration source type of the fiber-optic vibration signal is determined as fish swarming vibration source by identification terminal.
Such as meet the ceiling capacity model, then identification terminal executes the leaf node of the decision tree, determines the fiber-optic vibration
The vibration source type of signal is determined as fish swarming vibration source, and terminates flow.
S304:Identification terminal judges whether the energy information entropy feature of the fiber-optic vibration signal meets minisub class
The corresponding preset energy entropy model of type executes S305, otherwise executes S306 if meeting.
As above-mentioned, the optical fiber vibration source type in the present embodiment includes minisub.Identification terminal can acquire rainy in advance
When optical fiber corresponding position generate vibration signal, energy information entropy mould is established with the feature of the energy information entropy of the vibration signal
Type, and minisub is determined whether with the energy information entropy model.
For example, identification terminal extracts the feature of the energy information entropy of the vibration signal of minisub generation in advance.At this
When vibration signal does not meet the ceiling capacity model of root node, identification terminal continues to execute corresponding content node, calculates the optical fiber
The energy information entropy of vibration signal, and judge whether the energy information entropy of the fiber-optic vibration signal has default minisub pair
Otherwise the energy information entropy feature answered is not minisub if being minisub with if.The comentropy asks method that can join
According to the prior art, therefore it is not described herein.
S305:The vibration source type of the fiber-optic vibration signal is determined as minisub by identification terminal.
Such as meet the energy information entropy model, then identification terminal executes the leaf node of the decision tree, determines that the optical fiber shakes
The vibration source type of dynamic signal is determined as minisub, and terminates flow.
S306:Identification terminal judges whether the duration of the fiber-optic vibration signal is more than setting time, if being more than,
S307 is executed, S310 is otherwise executed.
The vibration source type that optical fiber vibration source type residue in the present embodiment does not judge can be divided into according to the difference of duration
Two classes.Therefore identification terminal can establish duration model in next internal node of energy information entropy model.Believe in the vibration
When number not meeting energy information entropy model, identification terminal continues to execute corresponding content node, and the fiber-optic vibration signal continues
Whether the time is more than setting time, if being more than, enters the node of fundamental frequency cycles model, otherwise carries out the node of signal model.
Wherein, the duration of the fiber-optic vibration signal, that is, since detecting the fiber-optic signal of the vibration source position for vibration signal,
To detecting time span of the fiber-optic signal of vibration source position not between vibration signal, or be interpreted as the fiber-optic vibration
Duration in vibration processes occurs for the signal vibration source.The setting time can be adjusted according to actual conditions, this reality
Applying example can be set as between 1-10 seconds, for example, 1 second, 4 seconds, 10 seconds etc..
S307:Identification terminal judges whether the fiber-optic vibration signal has fundamental frequency and whether fundamental frequency cycles reach setting
Value executes S308, otherwise executes S309 if reaching setting value with fundamental frequency and fundamental frequency cycles.
As above-mentioned, the long duration vibration source type in the present embodiment includes large-scale submarine and medium-sized submarine vibration source.Identification
The fundamental frequency cycles feature that terminal is respectively generated previously according to large-scale submarine and medium-sized submarine vibration source establishes fundamental frequency cycles model and is:It shakes
It is large-scale submarine vibration source that there is dynamic signal fundamental frequency and fundamental frequency cycles, which to reach setting value, is otherwise medium-sized submarine vibration source.
For example, when it is long duration vibration source type to determine the vibration source type, identification terminal continues to execute corresponding content
Node judges whether the fiber-optic vibration signal has fundamental frequency and whether fundamental frequency cycles reach setting value.Wherein, which can root
It is adjusted according to actual conditions, such as using the average value of the value of the fundamental frequency cycles of multiple large-scale submarine as the setting value.
S308:The vibration source type of the fiber-optic vibration signal is determined as large-scale submarine vibration source by identification terminal.
If vibration signal has fundamental frequency and fundamental frequency cycles reach setting value, identification terminal executes the leaf section of the decision tree
Point determines that the vibration source type of the fiber-optic vibration signal is determined as large-scale submarine vibration source, and terminates flow.
S309:The vibration source type of the fiber-optic vibration signal is determined as medium-sized submarine vibration source by identification terminal.
If vibration signal does not have fundamental frequency or fundamental frequency cycles do not reach setting value, identification terminal executes the leaf of the decision tree
Child node determines that the vibration source type of the fiber-optic vibration signal is determined as medium-sized submarine vibration source, and terminates flow.Wherein, this is medium-sized
Concretely train passes through vibration source etc. to submarine vibration source by vibration source, trolley.
S310:Identification terminal obtains the energy levels of the fiber-optic vibration signal, if the energy levels are more than the first journey
Degree, then execute S311, if the energy levels are less than the second degree, executes S312, wherein first degree is higher than described
Second degree.
As above-mentioned, the pulse class vibration source type in the present embodiment includes at least large ship vibration source and small-sized steamer.Identification
The signal characteristic that terminal is respectively generated previously according to large ship vibration source and small-sized steamer establishes signal model.
For example, when it is pulse class vibration source type to determine the vibration source type, identification terminal continues to execute corresponding content node,
The energy of the fiber-optic vibration signal is calculated, and when the energy for judging the fiber-optic vibration signal is more than the first degree, is determined as big
Type steamer vibration source;When the energy levels for judging the fiber-optic vibration signal are less than the second degree, it is determined as small-sized steamer;Sentencing
The energy levels of the disconnected fiber-optic vibration signal are determined as other vibration source classes not less than the second degree and when being no more than the first degree
Type.Wherein, first degree and the second degree can be adjusted according to actual conditions, such as by the signal energy of multiple large ship vibration source
Average value as first degree, using the average value of the signal energy of multiple small-sized steamer as second degree.
S311:The vibration source type of the fiber-optic vibration signal is determined as large ship vibration source by identification terminal.
If vibration signal is more than the first degree, identification terminal executes the leaf node of the decision tree, determines that the optical fiber shakes
The vibration source type of dynamic signal is determined as large ship vibration source, and terminates flow.
S312:The vibration source type of the fiber-optic vibration signal is determined as small-sized steamer by identification terminal.
If vibration signal is less than the second degree, identification terminal executes the leaf node of the decision tree, determines that the optical fiber shakes
The vibration source type of dynamic signal is determined as small-sized steamer, and terminates flow.
Further, Fig. 5 is please referred to, to improve the performance of optical fiber safety early-warning system, this method is in above-mentioned steps
Later, can also include the steps of:
S313:Identification terminal determines the notification level belonging to the corresponding vibration source type of the fiber-optic vibration signal.
Different vibration source types are arranged different notice grades in identification terminal pre-selection, such as according to different vibration sources to safe early warning
The threat degree in region, setting vibration source notice grade by height be followed successively by earth fish swarming, minisub, large ship,
Small-sized steamer, medium-sized submarine, large-scale submarine can use number 6-1 to indicate respectively, wherein 6 expression notification level highests, i.e., such
Vibration source is maximum to the threat degree of optical fiber local environment, and 1 indicates small to optical fiber local environment threat degree.
After identification terminal execution above-mentioned steps determine vibration source type, it is corresponding default logical to find determining vibration source type
Know type.
S314:Identification terminal carries out corresponding notice according to the notification level.
If for example, the notice grade highest, then send red early warning information, and it is pre- that sound can be used to set device
Police's formula notifies user's current detection situation;If the notice grade is the lowest class, then it is pre- to send yellow to set device
Alert information.
From the foregoing, it will be observed that processing terminal is identified can just judge its environmental aspect with the sampled signal of preset signals model,
Therefore it is of crucial importance to the accurately sampling of signal.Only sliding is less than sampling when processing terminal of the present invention is sampled every time using sliding window mode
The time gap of signal length so that sampled signal is more rich, and a bit of new data is only filled between adjacent sampled signal, is easy
It includes enough signals for identifying required data to collect, namely easy can come out with the matched signal acquisition of preset signals, therefore
Conducive to accurately identifying, identification and the whether matched accuracy rate of preset signals model are improved, that is, improves optic fibre environment situation
Recognition accuracy.
Refering to Fig. 6, the structural schematic diagram of one embodiment of fiber-optic signal processing unit of the present invention, which includes:
Acquisition module 61, for obtaining fiber-optic vibration signal.
Sort module 62 is obtained described for being classified to the fiber-optic vibration signal using Decision Tree Algorithm
The vibration source type of fiber-optic vibration signal.
Optionally, which is specifically used for the feature of the fiber-optic vibration signal and corresponding default character modules
Type is matched, and according to matching result, is continued to preset characteristic model with other and is matched or the optical fiber shakes
The vibration source type of dynamic signal is determined as vibration source type corresponding with the default characteristic model.
Optionally, which includes the first judging unit, the maximum energy for judging the fiber-optic vibration signal
Whether measure feature meets the corresponding default ceiling capacity model of fish swarming vibration source type;And when meeting, the optical fiber is shaken
The vibration source type of dynamic signal is determined as fish swarming vibration source.
Optionally, which includes second judgment unit, described for not met in the ceiling capacity feature
When default ceiling capacity model, judge whether the energy information entropy feature of the fiber-optic vibration signal meets minisub type
Corresponding preset energy entropy model, and when meeting, the vibration source type of the fiber-optic vibration signal is determined as small-sized latent
Hydrophone.
Optionally, which includes third judging unit, for not meeting institute in the energy information entropy feature
When stating preset energy entropy model, judge whether the duration of the fiber-optic vibration signal is more than setting time.
Optionally, which includes the 4th judging unit, for being more than in the duration of fiber-optic vibration signal
When setting time, the matching of fundamental frequency cycles model is carried out to the fiber-optic vibration signal.
Specifically, the 4th judging unit is specifically used for judging whether the fiber-optic vibration signal has fundamental frequency and fundamental frequency week
Whether the phase reaches setting value;If so, the vibration source type of the fiber-optic vibration signal is determined as large-scale submarine vibration source;Otherwise,
The vibration source type of the fiber-optic vibration signal is determined as medium-sized submarine vibration source.
Optionally, which includes the 5th judging unit, is not surpassed for the duration in fiber-optic vibration signal
When crossing setting time, the matching of signal model is carried out to the fiber-optic vibration signal.
Specifically, the 5th judging unit is specifically used for obtaining the energy levels of the fiber-optic vibration signal;If the energy
Amount degree is more than the first degree, then the vibration source type of the fiber-optic vibration signal is determined as large ship vibration source;If the energy
Amount degree is less than the second degree, then the vibration source type of the fiber-optic vibration signal is determined as small-sized steamer, wherein described first
Degree is higher than second degree.
Optionally, described device further includes notification module, for judging the corresponding vibration source type of the fiber-optic vibration signal
Affiliated notification level;Corresponding notice is carried out according to the notification level.
Wherein, the above-mentioned module of the identification terminal is respectively used to execute the corresponding steps in above method embodiment, specifically
Implementation procedure embodiment of the method explanation as above, therefore not to repeat here.
Refering to Fig. 7, the structural schematic diagram of another embodiment of optical fiber Recognition of Vibration Sources device of the present invention, the device 70 includes place
Manage device 71, memory 72, receiver 73 and bus 74.Wherein, processor 71, memory 72, receiver 73 may each be one
Or it is multiple, in Fig. 7 only for one.
Receiver 73 is used to receive the information of external equipment transmission.For example, reception optical fiber signal, as fibre optical sensor is sent
Optical signal, the electric signal after opto-electronic conversion or through be determined as fiber-optic vibration generation signal fiber-optic vibration signal.
Memory 72 provides the computer program for storing computer program to processor 71, and can store place
The data that device 71 is handled are managed, such as the fiber-optic signal lamp that receiver 73 receives.Wherein, memory 72 may include read-only storage
Device, random access memory and nonvolatile RAM(NVRAM)At least one of.
The computer program that memory 72 stores includes following element, executable modules or data structures or it
Subset or their superset:
Operational order:Including various operational orders, for realizing various operations.
Operating system:Including various system programs, for realizing various basic businesses and the hardware based task of processing.
In embodiments of the present invention, the operational order that processor 71 is stored by calling memory 72(The operational order can
Storage is in an operating system), to execute operation below.
Specifically, processor 71 can perform the computer program in memory 72, be used for:
Identification terminal obtains fiber-optic vibration signal;
Classified to the fiber-optic vibration signal using Decision Tree Algorithm, obtains the vibration source class of the fiber-optic vibration signal
Type.
Optionally, processor 71 executes the use Decision Tree Algorithm and carries out classification packet to the fiber-optic vibration signal
It includes:The feature of the fiber-optic vibration signal is matched with corresponding default characteristic model, and according to matching result, continue into
Row is matched with other default characteristic models or is determined as presetting with described by the vibration source type of the fiber-optic vibration signal
The corresponding vibration source type of characteristic model.
Optionally, processor 71 execute the feature by the fiber-optic vibration signal and corresponding default characteristic model into
Row matching continues to preset characteristic model with other and is matched or believe the fiber-optic vibration and according to matching result
Number vibration source type the step of being determined as vibration source type corresponding with the default characteristic model include:Judge the fiber-optic vibration
Whether the ceiling capacity feature of signal meets the corresponding default ceiling capacity model of fish swarming vibration source type;It, will if meeting
The vibration source type of the fiber-optic vibration signal is determined as fish swarming vibration source.
Optionally, processor 71 is additionally operable to:If the ceiling capacity feature does not meet the default ceiling capacity model,
Judge whether the energy information entropy feature of the fiber-optic vibration signal meets the corresponding preset energy information of minisub type
Entropy model;If meeting, the vibration source type of the fiber-optic vibration signal is determined as minisub.
Optionally, processor 71 is additionally operable to:If the energy information entropy feature does not meet the preset energy comentropy mould
Type then judges whether the duration of the fiber-optic vibration signal is more than setting time;If being more than, the fiber-optic vibration is believed
Number carry out fundamental frequency cycles model matching;Otherwise, the matching of signal model is carried out to the fiber-optic vibration signal.
Optionally, processor 71 executes the step of matching that fundamental frequency cycles model is carried out to the fiber-optic vibration signal
Including:Judge whether the fiber-optic vibration signal has fundamental frequency and whether fundamental frequency cycles reach setting value;If so, by the light
The vibration source type of fine vibration signal is determined as large-scale submarine vibration source;Otherwise, the vibration source type of the fiber-optic vibration signal is determined
For medium-sized submarine vibration source.
Optionally, processor 71 execute it is described to the fiber-optic vibration signal carry out signal model matching the step of wrap
It includes:Obtain the energy levels of the fiber-optic vibration signal;If the energy levels are more than the first degree, by the fiber-optic vibration
The vibration source type of signal is determined as large ship vibration source;If the energy levels are less than the second degree, by the fiber-optic vibration
The vibration source type of signal is determined as small-sized steamer, wherein first degree is higher than second degree.
Optionally, processor 71 is additionally operable to:Judge the notice grade belonging to the corresponding vibration source type of the fiber-optic vibration signal
Not;Corresponding notice is carried out according to the notification level.
Above-mentioned processor 71 can also be known as CPU(Central Processing Unit, central processing unit).Specifically
Application in, the various components of terminal are coupled by bus 74, and wherein bus 74 may be used also in addition to including data/address bus
To include power bus, controlling bus and status signal bus in addition etc..But for the sake of clear explanation, by various buses in figure
All it is designated as bus 74.
The method that aforementioned present invention embodiment discloses can also be applied in processor 71, or real by processor 71
It is existing.Processor 71 may be a kind of IC chip, the processing capacity with signal.During realization, the above method
Each step can be completed by the integrated logic circuit of the hardware in processor 71 or the instruction of software form.Above-mentioned processing
Device 71 can be general processor, digital signal processor(DSP), application-specific integrated circuit(ASIC), ready-made programmable gate array
(FPGA)Either other programmable logic device, discrete gate or transistor logic, discrete hardware components.May be implemented or
Person executes disclosed each method, step and the logic diagram in the embodiment of the present invention.General processor can be microprocessor or
Person's processor can also be any conventional processor etc..The step of method in conjunction with disclosed in the embodiment of the present invention, can be straight
Connect and be presented as that hardware decoding processor executes completion, or in decoding processor hardware and software module combination executed
At.Software module can be located at random access memory, and flash memory, read-only memory, programmable read only memory or electrically-erasable can
In the storage medium of this fields such as programmable memory, register maturation.The storage medium is located at memory 72, and processor 71 is read
Information in respective memory, in conjunction with the step of its hardware completion above method.
In said program, identification terminal classifies to light vibration signal using Decision Tree Algorithm, without artificial
It participates in, the intelligent recognition to optical fiber vibration source is realized, moreover, can be to a nodes multiple or even up to ten thousand using Decision Tree Algorithm
Classify, effect is faster more more acurrate than manual identified, therefore improves recognition efficiency and accuracy.In addition, due to decision tree
It is simple in structure to understand and be easily achieved, identification process can be simplified.
In several embodiments provided by the present invention, it should be understood that disclosed method and device, Ke Yitong
Other modes are crossed to realize.For example, device embodiments described above are only schematical, for example, the module or
The division of unit, only a kind of division of logic function, formula that in actual implementation, there may be another division manner, such as multiple units
Or component can be combined or can be integrated into another system, or some features can be ignored or not executed.
The unit illustrated as separating component may or may not be physically separated, aobvious as unit
The component shown may or may not be physical unit, you can be located at a place, or may be distributed over multiple
In network element.Some or all of unit therein can be selected according to the actual needs to realize present embodiment scheme
Purpose.
In addition, each functional unit in each embodiment of the present invention can be integrated in a processing unit, also may be used
It, can also be during two or more units be integrated in one unit to be that each unit physically exists alone.It is above-mentioned integrated
The form that hardware had both may be used in unit is realized, can also be realized in the form of SFU software functional unit.
If the integrated unit in above-mentioned other embodiment is realized in the form of SFU software functional unit and as independence
Product sale or in use, can be stored in a computer read/write memory medium.Based on this understanding, of the invention
Technical solution substantially all or part of the part that contributes to existing technology or the technical solution can be in other words
It is expressed in the form of software products, which is stored in a storage medium, including some instructions are used
So that a computer equipment(Can be personal computer, server or the network equipment etc.)Or processor
(processor)Execute all or part of step of each embodiment the method for the present invention.And storage medium packet above-mentioned
It includes:USB flash disk, mobile hard disk, read-only memory(ROM, Read-Only Memory), random access memory(RAM, Random
Access Memory), the various media that can store program code such as magnetic disc or CD.
Mode the above is only the implementation of the present invention is not intended to limit the scope of the invention, every to utilize this
Equivalent structure or equivalent flow shift made by description of the invention and accompanying drawing content, it is relevant to be applied directly or indirectly in other
Technical field is included within the scope of the present invention.
Claims (10)
1. a kind of optical fiber Recognition of Vibration Sources method, which is characterized in that including:
Identification terminal obtains fiber-optic vibration signal;
Classified to the fiber-optic vibration signal using Decision Tree Algorithm, obtains the vibration source class of the fiber-optic vibration signal
Type.
2. according to the method described in claim 1, it is characterized in that, described use Decision Tree Algorithm to the fiber-optic vibration
The step of signal is classified include:
The feature of the fiber-optic vibration signal is matched with corresponding default characteristic model, and according to matching result, is continued
Carry out with other preset characteristic models matched or by the vibration source type of the fiber-optic vibration signal be determined as with it is described pre-
If the corresponding vibration source type of characteristic model.
3. according to the method described in claim 2, it is characterized in that, the feature by the fiber-optic vibration signal with it is corresponding
Default characteristic model is matched, and according to matching result, continue with other preset characteristic model matched or will
The vibration source type of the fiber-optic vibration signal is determined as the step of vibration source type corresponding with the default characteristic model and includes:
Judge whether the ceiling capacity feature of the fiber-optic vibration signal meets the corresponding default maximum of submarine optical cable vibration source type
Energy model;
If meeting, the vibration source type of the fiber-optic vibration signal is determined as fish swarming vibration source.
4. according to the method described in claim 3, it is characterized in that, the feature by the fiber-optic vibration signal with it is corresponding
Default characteristic model is matched, and according to matching result, continue with other preset characteristic model matched or will
The vibration source type of the fiber-optic vibration signal is determined as the step of vibration source type corresponding with the default characteristic model and further includes:
If the ceiling capacity feature does not meet the default ceiling capacity model, the energy of the fiber-optic vibration signal is judged
Whether Information Entropy Features meet the corresponding preset energy entropy model of minisub type;
If meeting, the vibration source type of the fiber-optic vibration signal is determined as minisub.
5. according to the method described in claim 4, it is characterized in that, the feature by the fiber-optic vibration signal with it is corresponding
Default characteristic model is matched, and according to matching result, continue with other preset characteristic model matched or will
The vibration source type of the fiber-optic vibration signal is determined as the step of vibration source type corresponding with the default characteristic model and further includes:
If the energy information entropy feature does not meet the preset energy entropy model, the fiber-optic vibration signal is judged
Whether the duration is more than setting time;
If being more than, the matching of fundamental frequency cycles model is carried out to the fiber-optic vibration signal;
Otherwise, the matching of signal model is carried out to the fiber-optic vibration signal.
6. according to the method described in claim 5, it is characterized in that, described carry out signal model to the fiber-optic vibration signal
The step of matching includes:
Obtain the energy levels of the fiber-optic vibration signal;
If the energy levels are more than the first degree, the vibration source type of the fiber-optic vibration signal is determined as large ship;
If the energy levels are less than the second degree, the vibration source type of the fiber-optic vibration signal is determined as small-sized steamer,
Wherein, first degree is higher than second degree.
7. according to the method described in claim 5, it is characterized in that, described carry out fundamental frequency cycles mould to the fiber-optic vibration signal
The step of matching of type includes:
Judge whether the fiber-optic vibration signal has fundamental frequency and whether fundamental frequency cycles reach setting value;
If so, the vibration source type of the fiber-optic vibration signal is determined as large-scale submarine vibration source;
Otherwise, the vibration source type of the fiber-optic vibration signal is determined as medium-sized submarine vibration source.
8. method according to any one of claims 1 to 7, which is characterized in that the method further includes:
Determine the notification level belonging to the corresponding vibration source type of the fiber-optic vibration signal;
Corresponding notice is carried out according to the notification level.
9. a kind of optical fiber Recognition of Vibration Sources device, which is characterized in that including:
Acquisition module, for obtaining fiber-optic vibration signal;
Sort module is obtained the optical fiber and shaken for being classified to the fiber-optic vibration signal using Decision Tree Algorithm
The vibration source type of dynamic signal.
10. a kind of optical fiber Recognition of Vibration Sources system, which is characterized in that including fibre optical sensor and identification terminal;
The fibre optical sensor is used to send out the first optical signal at one end, and anti-by first optical signal from the reception of described one end
The second optical signal penetrated;
When the identification terminal is for determining that the corresponding electric signal of the second optical signal is fiber-optic vibration signal, to the fiber-optic vibration
Signal carries out Recognition of Vibration Sources, wherein the identification terminal includes the optical fiber Recognition of Vibration Sources device described in claim 9, with to institute
It states fiber-optic vibration signal and carries out Recognition of Vibration Sources.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201710016503.1A CN108287016A (en) | 2017-01-10 | 2017-01-10 | A kind of ocean optical fiber Recognition of Vibration Sources method, apparatus and system based on decision Tree algorithms |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201710016503.1A CN108287016A (en) | 2017-01-10 | 2017-01-10 | A kind of ocean optical fiber Recognition of Vibration Sources method, apparatus and system based on decision Tree algorithms |
Publications (1)
Publication Number | Publication Date |
---|---|
CN108287016A true CN108287016A (en) | 2018-07-17 |
Family
ID=62819927
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201710016503.1A Pending CN108287016A (en) | 2017-01-10 | 2017-01-10 | A kind of ocean optical fiber Recognition of Vibration Sources method, apparatus and system based on decision Tree algorithms |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN108287016A (en) |
Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN103994815A (en) * | 2014-05-19 | 2014-08-20 | 深圳艾瑞斯通技术有限公司 | Method for recognizing optical fiber vibration source |
CN105841793A (en) * | 2016-04-15 | 2016-08-10 | 深圳艾瑞斯通技术有限公司 | Optical fiber vibration source identification method, device and system |
CN105973449A (en) * | 2016-04-15 | 2016-09-28 | 深圳艾瑞斯通技术有限公司 | Method, device and system for recognizing optical fiber vibration source |
-
2017
- 2017-01-10 CN CN201710016503.1A patent/CN108287016A/en active Pending
Patent Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN103994815A (en) * | 2014-05-19 | 2014-08-20 | 深圳艾瑞斯通技术有限公司 | Method for recognizing optical fiber vibration source |
CN105841793A (en) * | 2016-04-15 | 2016-08-10 | 深圳艾瑞斯通技术有限公司 | Optical fiber vibration source identification method, device and system |
CN105973449A (en) * | 2016-04-15 | 2016-09-28 | 深圳艾瑞斯通技术有限公司 | Method, device and system for recognizing optical fiber vibration source |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN105841793A (en) | Optical fiber vibration source identification method, device and system | |
CN108932480B (en) | Distributed optical fiber sensing signal feature learning and classifying method based on 1D-CNN | |
CN108132092A (en) | Threshold value optical fiber vibration event recognition methods is gone based on adaptive mean value | |
CN111222743B (en) | Method for judging vertical offset distance and threat level of optical fiber sensing event | |
CN104729667A (en) | Method for recognizing disturbance type in a distributed optical fiber vibration sensing system | |
CN104240455A (en) | Method for identifying disturbance event in distributed type optical fiber pipeline security early-warning system | |
CN106530544A (en) | Fiber grating array perimeter intrusion system | |
CN102945585A (en) | Method for raising fire alarm through multi-sensor data fusion | |
CN103968933A (en) | Fuzzy domain characteristics based optical fiber vibration signal identifying method | |
CN106093722A (en) | The location of a kind of cable local discharge and recognition methods | |
CN112985574B (en) | High-precision classification identification method for optical fiber distributed acoustic sensing signals based on model fusion | |
CN103994815A (en) | Method for recognizing optical fiber vibration source | |
CA3183822A1 (en) | Method and system for simulating an event | |
CN105698916A (en) | Optical fiber vibration model determination method and optical fiber early warning device and system | |
CN110518973A (en) | A kind of optical fiber eavesdropping monitoring method and relevant device based on machine learning | |
CN116186642B (en) | Distributed optical fiber sensing event early warning method based on multidimensional feature fusion | |
CN111951505B (en) | Fence vibration intrusion positioning and mode identification method based on distributed optical fiber system | |
US20230024104A1 (en) | Identification of false transformer humming using machine learning | |
CN105698915A (en) | Optical fiber vibration source recognition method, device, and system | |
CN108287016A (en) | A kind of ocean optical fiber Recognition of Vibration Sources method, apparatus and system based on decision Tree algorithms | |
CN107664571A (en) | A kind of method of optical time domain reflectometer curve data event detection | |
CN106404016A (en) | Fiber sampling signal filtering method and device and fiber sensing system | |
CN111131279A (en) | Safety perception model construction method based on immune theory | |
CN104980211A (en) | Signal processing method and device | |
Qiu et al. | The development of an IoT instrumented bike: For assessment of road and bike trail conditions |
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 | ||
WD01 | Invention patent application deemed withdrawn after publication | ||
WD01 | Invention patent application deemed withdrawn after publication |
Application publication date: 20180717 |