CN114994454B - OPGW optical cable full-state detection analysis method and system - Google Patents
OPGW optical cable full-state detection analysis method and system Download PDFInfo
- Publication number
- CN114994454B CN114994454B CN202210509397.1A CN202210509397A CN114994454B CN 114994454 B CN114994454 B CN 114994454B CN 202210509397 A CN202210509397 A CN 202210509397A CN 114994454 B CN114994454 B CN 114994454B
- Authority
- CN
- China
- Prior art keywords
- data
- opgw
- state
- optical fiber
- optical cable
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 238000004458 analytical method Methods 0.000 title claims abstract description 79
- 230000003287 optical effect Effects 0.000 title claims abstract description 64
- 238000001514 detection method Methods 0.000 title claims abstract description 44
- 239000013307 optical fiber Substances 0.000 claims abstract description 73
- 238000012549 training Methods 0.000 claims abstract description 44
- 238000009434 installation Methods 0.000 claims abstract description 15
- 238000004422 calculation algorithm Methods 0.000 claims abstract description 13
- 238000000034 method Methods 0.000 claims abstract description 13
- 238000003062 neural network model Methods 0.000 claims abstract description 12
- 238000005457 optimization Methods 0.000 claims abstract description 11
- 230000003190 augmentative effect Effects 0.000 claims abstract description 9
- 238000013434 data augmentation Methods 0.000 claims abstract description 9
- 230000003416 augmentation Effects 0.000 claims abstract description 7
- 238000013528 artificial neural network Methods 0.000 claims description 17
- 230000002159 abnormal effect Effects 0.000 claims description 11
- 208000025274 Lightning injury Diseases 0.000 claims description 9
- 238000007781 pre-processing Methods 0.000 claims description 6
- 238000012795 verification Methods 0.000 claims description 6
- 230000007613 environmental effect Effects 0.000 claims description 4
- 238000001556 precipitation Methods 0.000 claims description 4
- 238000000253 optical time-domain reflectometry Methods 0.000 description 17
- 230000006870 function Effects 0.000 description 13
- 238000004364 calculation method Methods 0.000 description 6
- 239000000835 fiber Substances 0.000 description 4
- 238000004891 communication Methods 0.000 description 3
- 239000002131 composite material Substances 0.000 description 3
- 238000005259 measurement Methods 0.000 description 3
- 238000011897 real-time detection Methods 0.000 description 3
- 238000007665 sagging Methods 0.000 description 3
- 230000005540 biological transmission Effects 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 230000035772 mutation Effects 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000006243 chemical reaction Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 230000009977 dual effect Effects 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000012423 maintenance Methods 0.000 description 1
- 238000013507 mapping Methods 0.000 description 1
- 239000011159 matrix material Substances 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000010606 normalization Methods 0.000 description 1
- 230000000750 progressive effect Effects 0.000 description 1
- 238000000926 separation method Methods 0.000 description 1
- 238000004088 simulation Methods 0.000 description 1
- 230000001360 synchronised effect Effects 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01R—MEASURING ELECTRIC VARIABLES; MEASURING MAGNETIC VARIABLES
- G01R31/00—Arrangements for testing electric properties; Arrangements for locating electric faults; Arrangements for electrical testing characterised by what is being tested not provided for elsewhere
- G01R31/08—Locating faults in cables, transmission lines, or networks
- G01R31/081—Locating faults in cables, transmission lines, or networks according to type of conductors
- G01R31/085—Locating faults in cables, transmission lines, or networks according to type of conductors in power transmission or distribution lines, e.g. overhead
-
- 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
- G01—MEASURING; TESTING
- G01K—MEASURING TEMPERATURE; MEASURING QUANTITY OF HEAT; THERMALLY-SENSITIVE ELEMENTS NOT OTHERWISE PROVIDED FOR
- G01K11/00—Measuring temperature based upon physical or chemical changes not covered by groups G01K3/00, G01K5/00, G01K7/00 or G01K9/00
- G01K11/32—Measuring temperature based upon physical or chemical changes not covered by groups G01K3/00, G01K5/00, G01K7/00 or G01K9/00 using changes in transmittance, scattering or luminescence in optical fibres
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01L—MEASURING FORCE, STRESS, TORQUE, WORK, MECHANICAL POWER, MECHANICAL EFFICIENCY, OR FLUID PRESSURE
- G01L1/00—Measuring force or stress, in general
- G01L1/24—Measuring force or stress, in general by measuring variations of optical properties of material when it is stressed, e.g. by photoelastic stress analysis using infrared, visible light, ultraviolet
- G01L1/242—Measuring force or stress, in general by measuring variations of optical properties of material when it is stressed, e.g. by photoelastic stress analysis using infrared, visible light, ultraviolet the material being an optical fibre
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01R—MEASURING ELECTRIC VARIABLES; MEASURING MAGNETIC VARIABLES
- G01R31/00—Arrangements for testing electric properties; Arrangements for locating electric faults; Arrangements for electrical testing characterised by what is being tested not provided for elsewhere
- G01R31/08—Locating faults in cables, transmission lines, or networks
- G01R31/088—Aspects of digital computing
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02A—TECHNOLOGIES FOR ADAPTATION TO CLIMATE CHANGE
- Y02A90/00—Technologies having an indirect contribution to adaptation to climate change
- Y02A90/10—Information and communication technologies [ICT] supporting adaptation to climate change, e.g. for weather forecasting or climate simulation
Landscapes
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Mathematical Physics (AREA)
- Biomedical Technology (AREA)
- Evolutionary Computation (AREA)
- Artificial Intelligence (AREA)
- Health & Medical Sciences (AREA)
- Biophysics (AREA)
- Computational Linguistics (AREA)
- Data Mining & Analysis (AREA)
- Life Sciences & Earth Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Molecular Biology (AREA)
- Computing Systems (AREA)
- General Engineering & Computer Science (AREA)
- Software Systems (AREA)
- Testing Or Calibration Of Command Recording Devices (AREA)
Abstract
The invention discloses an OPGW optical cable full-state detection analysis method and system, and relates to the field of power optical fiber state detection. The method comprises the following steps: acquiring meteorological data and distributed optical fiber sensing data of an OPGW shaft tower setting area; performing data augmentation on the distributed optical fiber sensing data to obtain augmented data; taking the distributed optical fiber sensing data and the augmentation data as training data, and training a T-S fuzzy neural network model based on DE optimization by using the training data to obtain each state analysis model; inputting the detection data into each state analysis model to obtain a state analysis result of the OPGW optical cable; and after the state analysis result is verified with the time-space data, outputting a final OPGW optical cable full-state analysis result, wherein the time-space data comprises time data and weather data of an OPGW shaft tower installation area. On the premise of not changing the hardware complexity of the detection equipment, the invention utilizes an intelligent algorithm to complete the detection analysis of the whole state of the OPGW optical cable.
Description
Technical Field
The invention relates to the technical field of power optical fiber state detection, in particular to an OPGW optical cable full state detection analysis method and system.
Background
The OPGW optical cable (Optical Fibre Composite Overhead Ground Wire, OPGW) is also called an optical fiber composite overhead ground wire, and an optical fiber is placed in the ground wire of an overhead high-voltage transmission line to form a special power optical fiber communication network, and the structure has the dual functions of the ground wire and communication. OPGW optical cable is laid along with high-voltage transmission line, is exposed to field environment for a long time, is easily influenced by complex weather such as wind, rain, thunder, snow and the like, and is in abnormal states such as wind dance, lightning stroke, icing, sagging and the like. The abnormal state has fatal damage to the OPGW optical cable which is long in erection time and is in a severe environment for a long time, and greatly influences the service life and safe operation of the optical cable. Therefore, the full-state detection analysis of the OPGW optical cable has great significance in guaranteeing the safe and reliable operation of the power optical fiber communication private network.
Currently, OPGW optical cable on-line detection equipment mainly comprises a phi-OTDR and a C-OTDR based on Rayleigh scattering, and is used for detecting optical fiber vibration signals; B-OTDR and B-OTDA based on Brillouin scattering are used for detecting the temperature of the optical fiber and stress signals; the multi-parameter sensing OTDR can detect temperature, strain and vibration signals simultaneously.
In the prior art, the method for identifying the status of the OPGW optical cable mainly comprises the following steps: based on the vibration detection of the vibration signal, if the amplitude of the vibration signal is detected to be 2-3 times of the diameter of the OPGW optical cable and the frequency is 3-120 Hz, the vibration is judged to be breeze vibration, and if the amplitude of the vibration signal is detected to be 5-300 times of the diameter of the OPGW optical cable and the frequency is 0.1-3 Hz, the vibration is judged to be vibration; and if the temperature or stress change is large, judging that the OPGW optical cable is in a lightning stroke or icing state, and if the temperature or stress change is large, judging that the OPGW optical cable is in an icing, wind-dancing or sagging state, wherein the strain change is large.
The method can effectively detect the temperature, the strain and the vibration parameters of the optical fiber to realize the data anomaly discrimination, but lacks an intelligent analysis method and cannot accurately discriminate the specific state of the OPGW optical cable. Meanwhile, due to abnormal states such as wind dance, lightning stroke, icing, sagging and the like, temperature, strain and vibration signals are compounded and changed, and if wind dance occurs, vibration and strain signals are changed; when icing occurs, the strain and temperature signals of the optical fiber change, and the like, and the single signal change is insufficient to accurately judge the abnormal state of the optical fiber. Therefore, how to implement the OPGW optical cable full state detection analysis is a problem to be solved for those skilled in the art.
Disclosure of Invention
In view of the above, the present invention provides a method and a system for detecting and analyzing the full state of an OPGW optical cable, so as to solve the problems set forth in the background art.
In order to achieve the above purpose, the present invention adopts the following technical scheme: the OPGW optical cable full-state detection and analysis method specifically comprises the following steps:
acquiring meteorological data and distributed optical fiber sensing data of an OPGW shaft tower setting area;
performing data augmentation on the distributed optical fiber sensing data to obtain augmented data;
training the T-S fuzzy neural network model based on DE optimization by using the distributed optical fiber sensing data and the augmentation data as training data to obtain each state analysis model;
inputting the detection data into each state analysis model to obtain a state analysis result of the OPGW optical cable;
and after the state analysis result is verified with the space time data, outputting a final OPGW optical cable full state analysis result, wherein the space time data comprises time data and weather data of the OPGW tower installation area.
Optionally, the distributed optical fiber sensing data includes OPGW cable temperature, strain and vibration data.
Optionally, the method for acquiring meteorological data in the OPGW shaft tower set area comprises the following steps:
collecting longitude and latitude data of an OPGW optical cable tower to be tested;
and obtaining environmental codes corresponding to all towers according to the longitude and latitude data of the OPGW optical cable towers, and obtaining meteorological data of the installation area of the OPGW towers by using an API (application program interface) with open Chinese weather.
Optionally, the training steps of the T-S fuzzy neural network model based on DE optimization are as follows:
training data corresponding to wind dance, lightning stroke, icing and sag states are respectively used as input and output data of the T-S fuzzy neural network;
initializing a T-S fuzzy neural network, and initializing a membership function central value, a width and a link weight;
optimizing the membership function central value, the width and the link weight by adopting a differential evolution algorithm to obtain optimal parameters;
and inputting the optimized central value, width and link weight value to train and update the T-S fuzzy neural network to obtain each state analysis model.
Optionally, the training data comprises a temperature change amount, a strain change amount, a vibration amplitude, a vibration frequency, a strain amount and a temperature; the temperature variation is a difference value between the temperature of the optical fiber and meteorological data measured by the distributed optical fiber sensing equipment; the strain variation is a calibrated difference value between the optical fiber strain and the stateless strain measured by the distributed optical fiber sensing equipment; the vibration amplitude is the vibration amplitude of the optical fiber measured by the distributed optical fiber sensing equipment; the vibration frequency is frequency domain analysis data of the vibration amplitude of the optical fiber measured by the distributed optical fiber sensing equipment; the strain quantity is optical fiber strain data measured by distributed optical fiber sensing equipment; the temperature is optical fiber temperature data measured by the distributed optical fiber sensing equipment.
Optionally, the OPGW cable status includes wind dance, lightning strike, icing, sag.
Optionally, the T-S fuzzy neural network structure is a five-layer network, including: an input layer, a blurring layer, 2 fuzzy inference layers and a de-blurring layer.
On the other hand, the OPGW optical cable full-state detection analysis system comprises a data acquisition module, a data preprocessing module, a model training module, a result output module and a verification module which are connected in sequence; wherein,
the data acquisition module is used for acquiring meteorological data and distributed optical fiber sensing data of an OPGW shaft tower installation area;
the data preprocessing module is used for carrying out data augmentation on the distributed optical fiber sensing data to obtain augmented data;
the model training module is used for taking the distributed optical fiber sensing data and the augmentation data as training data, and training a T-S fuzzy neural network model based on DE optimization by utilizing the training data to obtain each state analysis model;
the result output module is used for inputting the detection data into each state analysis model to obtain a state analysis result of the OPGW optical cable;
and the verification module is used for verifying the state analysis result and space time data and outputting a final OPGW optical cable full-state analysis result, wherein the space time data comprises time data and weather data of the OPGW tower installation area.
Compared with the prior art, the invention discloses the method and the system for detecting and analyzing the full state of the OPGW optical cable, which have the following beneficial technical effects:
(1) The problem that the existing OPGW optical cable online detection technology cannot accurately identify all abnormal states is solved, and on the premise that existing detection equipment is not changed, the tower space data, the meteorological data near the tower and the optical fiber sensing data are used as DE-TSFNN analysis modeling training data, so that the OPGW optical cable all states are accurately judged;
(2) The full-state detection analysis of the whole domain of the OPGW optical cable to-be-detected line can be completed, the bottlenecks of poor adaptability, low identification accuracy, data redundancy and the like of the existing detection technology are broken through, and the problem that single parameter and single state identification cannot meet the requirements of customers is solved;
(3) The detection analysis result not only can effectively reflect the current state of the OPGW optical cable, but also can further analyze the health degree of the OPGW optical cable based on the state of the OPGW optical cable, and provides effective technical support for the operation and maintenance department of the national power grid company to ensure the safe and reliable operation of the OPGW optical cable.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings that are required to be used in the embodiments or the description of the prior art will be briefly described below, and it is obvious that the drawings in the following description are only embodiments of the present invention, and that other drawings can be obtained according to the provided drawings without inventive effort for a person skilled in the art.
FIG. 1 is a flow chart of the method of the present invention;
FIG. 2 is a schematic diagram of calculating a spatial distance according to longitude and latitude in embodiment 1 of the present invention;
FIG. 3 is a flow chart of modeling a T-S fuzzy neural network model according to the present invention;
fig. 4 is a system configuration diagram of the present invention.
Detailed Description
The following description of the embodiments of the present invention will be made clearly and completely with reference to the accompanying drawings, in which it is apparent that the embodiments described are only some embodiments of the present invention, but not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.
The embodiment of the invention discloses an OPGW optical cable full-state detection and analysis method, which is shown in fig. 1, and comprises the following specific steps:
s1, acquiring meteorological data and distributed optical fiber sensing data of an OPGW shaft tower installation area;
specifically, acquiring longitude and latitude data of an OPGW optical cable tower to be detected, and presetting an environmental code of the OPGW optical cable tower; and obtaining environmental codes corresponding to all towers according to the longitude and latitude data of the OPGW optical cable towers, and obtaining meteorological data of the installation area of the OPGW towers by using an API (application program interface) with open weather in China.
Furthermore, the longitude and latitude data of the OPGW optical cable tower to be measured is obtained through the national power grid company and the field measurement calibration.
The preset OPGW optical cable tower environment code comprises the following steps: regional large area, provincial city to which the region belongs and special state region;
the regional area comprises: north China, northeast China, east China, south China, northwest China, southwest China and harbor Australian stations;
the provinces and cities to which the region belongs include: information of Beijing city, shanghai city, guangzhou province, jilin province and the like;
the special state region includes: information such as heavy ice area, heavy thunder area, heavy wind area and the like;
the information is coded in a digital coding mode, for example, the North China is 01, the northeast China is 02, the east China is 03, the urban areas are sequentially coded, coding addresses are respectively divided into administrative areas from left to right, coding numbers are sequentially increased from north to south and from west to east according to the longitude and latitude of the areas, the heavy ice area of the special-state area is 01, the heavy thunder area is 02, the heavy wind area is 03, for example, 02020100100 coding representing information is northeast-Jilin province-white city-land 36169;
02 northeast, 02 Jilin provinces, 01 white cities, 001 land 36169, county, 00 non-special areas from left to right respectively;
further, according to the region corresponding to the coding information, acquiring longitude and latitude coordinates of each region by using an API interface opened by the hundred-degree map; calculating the distance between the OPGW optical cable tower and the nearby provincial area according to the acquired longitude and latitude data of the OPGW optical cable tower, taking the meteorological data of the area nearest to the tower as the basis of post-stage data augmentation and state analysis, and calculating the space distance according to the following calculation formula;
as shown in FIG. 2, the earth is approximately seen as a sphere, the earth's center is marked as O, the line from the earth's center to E0 degrees, N0 degrees is marked as the x-axis, the line from the earth's center to E90 degrees, the line from the earth's center to N0 degrees is marked as the y-axis, the line from the earth's center to E0 degrees, the line from the N90 degrees is marked as the z-axis, the earth's radius is R, the earth's surface has a point A, and the longitude is E A Latitude of n A Where the units are radians, the coordinates of a can be expressed as:
x＝R·cos(n A )·cos(e A )；
y＝R·cos(n A )·sin(e A )；
z＝R·sin(n A )；
similarly, the coordinates of the earth surface point B can be obtained, the chord length l of the distance between the A, B two points is calculated, and the included angle between the OA and the normal of the l is marked as alpha;
α＝arcsin(l/2/R)；
r＝2α·R；
wherein R is the arc length and is the distance between the two points of A, B, and R is the earth radius 6371km;
suppose that OPGW tower is denoted as A o Obtaining the separation A according to the environment coding o A matrix r of nearer regions Ao ＝[r 1 ,r 2 ,…,r n ] T n∈N + Each area is based on the obtained OPGW tower A o and rAo Regional center longitude and latitude data are calculated to obtain distance pole tower A o The spatial distance from each region is d Ao ＝[d r1 ,d r2 ,…,d rn ]n∈N + Will d Ao Descending order of the regions r corresponding to the shortest distance Ao Is the OPGW tower as point A o For example, the specific region is marked with a specific label closer to the specific region.
In particular, the distributed fiber sensing data includes OPGW cable temperature, strain and vibration data.
The meteorological data includes: temperature, relative humidity, wind direction, wind speed, air quality, and precipitation.
The distributed optical fiber sensing device used in the invention comprises: phi-OTDR, B-OTDA, R-OTDR, multi-parameter OTDR, etc.;
wherein, phi-OTDR can detect the vibration information of the optical fiber; the B-OTDR can detect the temperature and strain information of the optical fiber; the B-OTDA can detect the temperature and strain information of the optical fiber; the R-OTDR can detect the temperature information of the optical fiber; the multi-parameter OTDR may detect vibration, temperature and strain information. The invention aims to improve the detection and analysis capability based on the existing equipment, so that the distributed optical fiber sensing equipment is not excessively limited, and two fiber cores can be detected by using B-OTDR/B-OTDA and phi-OTDR in a combined mode; three fiber cores can be detected by using phi-OTDR, B-OTDR/B-OTDA and R-OTDR in combination; multi-parameter OTDR single fiber synchronous measurements may also be used.
S2, carrying out data augmentation on distributed optical fiber sensing data to obtain augmented data;
carrying out data augmentation on the distributed optical fiber sensing data to obtain training data of an OPGW (optical fiber composite overhead ground wire) cable wind dance, lightning stroke, icing and sag state analysis model;
specifically, wind dance, lightning strike, icing and sag state distributed optical fiber sensing data are derived from actual measurement and laboratory simulation;
specifically, the augmented training data includes: temperature variation, strain variation, vibration amplitude, vibration frequency, strain and temperature;
the temperature change amount calculation formula is as follows:
ΔT＝T h -T c ；
wherein delta isT is the temperature variation, T h Ambient temperature, T, obtained for meteorological data c Measuring a temperature for the distributed optical fiber sensing device;
the strain change amount calculation formula is as follows:
Δμ ε ＝μ εb -μ εc ；
wherein ,Δμε Mu, the strain change εb The strain calibration value, mu, of the OPGW optical cable in the breeze non-abnormal state is given εc Measuring a strain value for the distributed optical fiber sensing equipment;
the vibration amplitude, the strain quantity and the temperature are actually measured data of the distributed optical fiber sensing equipment, and the vibration frequency is obtained by amplitude-frequency conversion of the vibration amplitude;
s3, training the T-S fuzzy neural network model based on DE optimization by using the distributed optical fiber sensing data and the augmentation data as training data to obtain each state analysis model;
respectively constructing OPGW cable wind dance, lightning strike, icing and sag state analysis models;
the training data of the wind dance state detection analysis model are expressed as follows:
X f ＝[A f ,F f ,Δμ εf ,W fv ] T ；
Y f ＝[10,20,6] T ；
wherein ,Xf As input variables: a is that f For vibration amplitude, F f Is the vibration frequency, delta mu εf Is the strain change amount, W fv Is the wind speed; y is Y f As output variable: 10 is in a breeze and breeze vibration state, 20 is in a galloping state, and 6 is in a non-abnormal state.
Training data of the lightning state detection analysis model are expressed as follows:
X l ＝[ΔT l ,T l ,H,S] T ；
Y l ＝[2,6] T ；
wherein ,Xl As input variables: delta T l Is the temperature variation, T l Is the temperature and H is the phaseHumidity and S are precipitation; y is Y l As output variable: 2 is a lightning strike state, and 6 is a no anomaly state.
Training data of the icing condition detection analysis model are represented as follows:
X b ＝[ΔT b ,T b ,Δμ εb ,H] T ；
Y b ＝[1,6] T ；
wherein ,Xb As input variables: delta T b Is the temperature variation, T b Is the temperature, delta mu εb The strain change is shown as H, and the relative humidity is shown as H; y is Y b As output variable: 1 is a lightning strike state, and 6 is a no anomaly state.
Training data for Lei Huchui state detection analysis model is represented as follows:
X h ＝[Δμ εh ,μ εh ] T ；
Y h ＝[3,6] T ；
wherein ,Xh As input variables: Δμ εh Is the strain change quantity mu εh Is the strain; y is Y h As output variable: 3 is in a sagged state, and 6 is in a non-abnormal state.
Specifically, the state analysis model is a T-S fuzzy neural network model based on DE optimization, and the stochastic defect of the T-S fuzzy neural network in reconnection weight and threshold selection is overcome by utilizing differential evolution, so that the generalization capability and convergence speed of the T-S fuzzy neural network are improved.
The T-S fuzzy neural network structure is a five-layer network comprising: the input layer, the fuzzification layer, 2 fuzzy inference layers and a fuzzy layer are adopted to define a T-S model fuzzy rule expression:
wherein ,Rk Is the kth rule; x is x n Is a fuzzy linguistic variable;
is x n A fuzzy set of kth linguistic variables; y is k Outputting the rule for the kth rule; />
Is the output constant of the kth rule.
For a given input x, fitness is
The output is a weighted average of each rule:
DE-optimized T-S fuzzy neural network, training and adjusting membership function central value c of second layer (fuzzification layer) of T-S fuzzy neural network by utilizing mixed learning algorithm combining DE algorithm and BP algorithm ij And width sigma ij Link weights ω for fourth and fifth layers dc 。
The first layer of the T-S fuzzy neural network is an input layer, and the input-output relation of each node is expressed as follows:
the second layer is a blurring layer, the membership function is a Gaussian function, input data is blurred into 3 grades of low L (low), medium M (medium) and high H (high), and the input-output relationship of each node is expressed as:
the third layer is a fuzzy inference layer 1, and the input-output relationship of each node is expressed as follows:
the fourth layer is a fuzzy inference layer 2, and the output normalization calculation of the third layer is performed, and the input-output relationship of each node is expressed as:
the fifth layer node input-output relationship is expressed as:
wherein i is the number of input nodes of the first layer, 2 or 4,j is the number of linguistic variables in the embodiment, 3, I and O are respectively input and output of each layer of network, and x i Representing input variables, c ij As the central value of membership function, sigma ij Width, omega of membership function dc The link weight of the fourth layer and the fifth layer is that the number of the nodes of the third layer is 3 i D is the number of output nodes of the fifth layer, and is 2 or 3 in this embodiment.
A mixed learning algorithm combining the DE algorithm and the BP algorithm to obtain a Gaussian membership function central value c ij And width sigma ij Link weights ω for fourth and fifth layers dc Approximating an optimal solution;
BP learning algorithm, defining target cost function as:
wherein ,ye To be output, y d Is the actual output;
the iterative formula of each network parameter is:
wherein beta is learning rate, and a is momentum factor;
further, as shown in fig. 3, the training procedure of the DE-optimized T-S fuzzy neural network model is as follows:
s31, training data corresponding to wind dance, lightning strike, icing and sag states are respectively used as input and output data of the T-S fuzzy neural network;
s32, initializing a T-S fuzzy neural network, and initializing a membership function central value, a width and a link weight;
s33, optimizing the central value, the width and the link weight of the membership function by adopting a differential evolution algorithm to obtain optimal parameters;
and S34, inputting the optimized central value, the optimized width and the optimized link weight value to train and update the T-S fuzzy neural network to obtain each state analysis model.
Specifically, the differential evolution algorithm comprises the following steps:
step 1: firstly, uniformly coding parameters needing to be optimized, c ij 、σ ij and ωdc ；
Step 2: initializing related parameters of a population and DE algorithm, and setting a population scale NP, a scaling factor F, a crossover probability CR, iteration times T, iteration algebra G, a population individual number N and a population dimension D;
wherein ,
initializing individuals for a population, i de For population individual number, j de Is the population dimension;
step 3: calculating fitness value of each individual of the parent population, if the fitness value is the optimal individual, turning to a step 7, and if the fitness value is not the optimal individual, performing mutation operation on the parent individual;
specifically, the present embodimentIn the examples, the DE/rand/1 mutation strategy is adopted:
wherein ,
for individuals in the middle of population variation, < >>
and />
Three individuals selected randomly are respectively;
the fitness function is:
wherein ye To be output, y d Is the actual output;
step 4: the mutated individuals and the father individuals are subjected to cross operation, so that the diversity of the population is increased, and the specific formula is as follows:
step 5: comparing the fitness values of the father and offspring individuals, and selecting the father and offspring individuals with smaller fitness values as the next generation father population individuals, wherein the specific formula is as follows:
step 6: next generation g=g+1;
step 7: judging whether the termination condition is met, if the calculated iteration number exceeds the preset maximum iteration number or reaches the preset precision, exiting the operation, outputting the optimization parameters, otherwise, returning to the step 3.
S4, inputting the detection data into each state analysis model to obtain a state analysis result of the OPGW optical cable;
and S5, after the state analysis result is checked with the time-space data, outputting a final OPGW optical cable full-state analysis result, wherein the time-space data comprises time data and weather data of the OPGW tower installation area.
Specific real-time detection data include:
optical fiber data: temperature variation, strain variation, vibration amplitude, vibration frequency, strain and temperature;
weather data: temperature, relative humidity, wind direction, wind speed, air quality and precipitation
And after the real-time detection data are amplified, respectively inputting the amplified real-time detection data into the corresponding data interfaces of each state analysis model, carrying out union calculation on the OPGW wind dance, lightning stroke, icing and sag state codes obtained through analysis, and after the calculation result is verified with the space data of the position of the OPGW erection tower, outputting a final analysis result.
The spatial data includes: time data and weather data;
specifically, assuming that the output results obtained through model analysis are wind dance=20, lightning stroke=2, icing=6 and sag=6, carrying out union operation on the four groups of output data to obtain [20,2,6], and carrying out mapping conclusion that the output results are dancing and lightning stroke, and carrying out spatial data calibration if the domain is northeast, thunderstorm weather and wind power are large, the time is summer months, judging that the output results are normal, and outputting detection analysis results; if the area is weather and time is winter, judging that the output result is abnormal, and returning to re-analysis.
The embodiment 2 of the invention discloses an OPGW optical cable full-state detection analysis system, which comprises a data acquisition module, a data preprocessing module, a model training module, a result output module and a verification module which are connected in sequence as shown in fig. 4; wherein,
the data acquisition module is used for acquiring meteorological data and distributed optical fiber sensing data of the OPGW rod tower installation area;
the data preprocessing module is used for carrying out data augmentation on the distributed optical fiber sensing data to obtain augmented data;
the model training module is used for taking the distributed optical fiber sensing data and the augmentation data as training data, and training the T-S fuzzy neural network model based on DE optimization by utilizing the training data to obtain each state analysis model;
the result output module is used for inputting the detection data into each state analysis model to obtain a state analysis result of the OPGW optical cable;
and the verification module is used for outputting a final OPGW optical cable full-state analysis result after verifying the state analysis result and the time-space data, wherein the time-space data comprises time data and OPGW shaft tower installation area meteorological data.
In the present specification, each embodiment is described in a progressive manner, and each embodiment is mainly described in a different point from other embodiments, and identical and similar parts between the embodiments are all enough to refer to each other. For the device disclosed in the embodiment, since it corresponds to the method disclosed in the embodiment, the description is relatively simple, and the relevant points refer to the description of the method section.
The previous description of the disclosed embodiments is provided to enable any person skilled in the art to make or use the present invention. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the generic principles defined herein may be applied to other embodiments without departing from the spirit or scope of the invention. Thus, the present invention is not intended to be limited to the embodiments shown herein but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.
Claims (6)
1. The OPGW optical cable full-state detection and analysis method is characterized by comprising the following specific steps of:
acquiring meteorological data and distributed optical fiber sensing data of an OPGW shaft tower setting area;
performing data augmentation on the distributed optical fiber sensing data to obtain augmented data;
training the T-S fuzzy neural network model based on DE optimization by using the distributed optical fiber sensing data and the augmentation data as training data to obtain each state analysis model;
inputting the detection data into each state analysis model to obtain a state analysis result of the OPGW optical cable;
after the state analysis result is verified with space-time data, outputting a final OPGW optical cable full-state analysis result, wherein the space-time data comprises time data and weather data of an OPGW tower installation area;
the augmented training data includes: temperature variation, strain variation, vibration amplitude, vibration frequency, strain and temperature;
training data of the wind dance state detection analysis model are expressed as follows:
wherein ,
as input variables: />
For vibration amplitude, +.>
For vibration frequency, +.>
For strain variation, < >>
Is the wind speed; />
As output variable: 10 is in a breeze vibration state, 20 is in a galloping state, and 6 is in a non-abnormal state;
training data of the lightning state detection analysis model are expressed as follows:
wherein ,
as input variables: />
Is the temperature variation quantity->
Temperature->
Is relative humidity, < >>
Is precipitation; />
As output variable: 2 is a lightning strike state, and 6 is a non-abnormal state;
training data of the icing condition detection analysis model are represented as follows:
wherein ,
as input variables: />
Is the temperature variation quantity->
Temperature->
For strain variation, < >>
Is relative humidity; />
As output variable: 1 is in an icing state, and 6 is in an abnormal-free state;
training data of the sag state detection analysis model are expressed as follows:
wherein ,
as input variables: />
For strain variation, < >>
Is the strain; />
As output variable: 3 is in a sagged state, and 6 is in an abnormal-free state;
the training steps of the T-S fuzzy neural network model based on DE optimization are as follows:
training data corresponding to wind dance, lightning stroke, icing and sag states are respectively used as input and output data of the T-S fuzzy neural network;
initializing a T-S fuzzy neural network, and initializing a membership function central value, a width and a link weight;
optimizing the membership function central value, the width and the link weight by adopting a differential evolution algorithm to obtain optimal parameters;
and inputting the optimized central value, width and link weight value to train and update the T-S fuzzy neural network to obtain each state analysis model.
2. The OPGW cable full state detection analysis method of claim 1, wherein the distributed optical fiber sensing data comprises OPGW cable temperature, strain and vibration data.
3. The method for detecting and analyzing the full state of the OPGW optical cable according to claim 1, wherein the method for acquiring meteorological data of the OPGW tower installation area is as follows:
collecting longitude and latitude data of an OPGW optical cable tower to be tested;
and obtaining environmental codes corresponding to all towers according to the longitude and latitude data of the OPGW optical cable towers, and obtaining meteorological data of the installation area of the OPGW towers by using an API (application program interface) with open Chinese weather.
4. The method for detecting and analyzing the full state of the OPGW optical cable according to claim 1, wherein the temperature variation is a difference value between the temperature of the optical fiber measured by the distributed optical fiber sensing device and meteorological data; the strain variation is a calibrated difference value between the optical fiber strain and the stateless strain measured by the distributed optical fiber sensing equipment; the vibration amplitude is the vibration amplitude of the optical fiber measured by the distributed optical fiber sensing equipment; the vibration frequency is frequency domain analysis data of the vibration amplitude of the optical fiber measured by the distributed optical fiber sensing equipment; the strain quantity is optical fiber strain data measured by distributed optical fiber sensing equipment; the temperature is optical fiber temperature data measured by the distributed optical fiber sensing equipment.
5. The OPGW optical cable full state detection and analysis method according to claim 1, wherein the T-S fuzzy neural network structure is a five-layer network, comprising: an input layer, a blurring layer, 2 fuzzy inference layers and a de-blurring layer.
6. An OPGW optical cable full state detection analysis system is characterized in that an OPGW optical cable full state detection analysis method according to any one of claims 1-5 is utilized for optical cable state detection, and the system comprises a data acquisition module, a data preprocessing module, a model training module, a result output module and a verification module which are connected in sequence; wherein,
the data acquisition module is used for acquiring meteorological data and distributed optical fiber sensing data of an OPGW shaft tower installation area;
the data preprocessing module is used for carrying out data augmentation on the distributed optical fiber sensing data to obtain augmented data;
the model training module is used for taking the distributed optical fiber sensing data and the augmentation data as training data, and training a T-S fuzzy neural network model based on DE optimization by utilizing the training data to obtain each state analysis model;
the result output module is used for inputting the detection data into each state analysis model to obtain a state analysis result of the OPGW optical cable;
and the verification module is used for verifying the state analysis result and space time data and outputting a final OPGW optical cable full-state analysis result, wherein the space time data comprises time data and weather data of the OPGW tower installation area.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210509397.1A CN114994454B (en) | 2022-05-11 | 2022-05-11 | OPGW optical cable full-state detection analysis method and system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210509397.1A CN114994454B (en) | 2022-05-11 | 2022-05-11 | OPGW optical cable full-state detection analysis method and system |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN114994454A CN114994454A (en) | 2022-09-02 |
| CN114994454B true CN114994454B (en) | 2023-05-23 |
Family
ID=83028168
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210509397.1A Active CN114994454B (en) | 2022-05-11 | 2022-05-11 | OPGW optical cable full-state detection analysis method and system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114994454B (en) |
Family Cites Families (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JPH08304505A (en) * | 1995-05-11 | 1996-11-22 | Sumitomo Electric Ind Ltd | Method for locating failure condition and failure section in aerial power line |
| CN102981104B (en) * | 2012-11-19 | 2015-03-11 | 中国能源建设集团广东省电力设计研究院 | On-line monitoring method for submarine cables |
| CN108038300B (en) * | 2017-12-07 | 2021-08-03 | 长春理工大学 | Optical fiber state evaluation method based on improved membership function combined with neural network |
| CN108375344B (en) * | 2018-02-08 | 2020-11-27 | 成都蓝炬科技有限公司 | Measuring system and method based on machine intelligent prediction multi-parameter optical fiber sensor |
| US11573152B2 (en) * | 2019-09-25 | 2023-02-07 | Cisco Technology, Inc. | Optical time domain reflectometer (OTDR)-based classification for fiber optic cables using machine learning |
| CN114362817A (en) * | 2021-12-14 | 2022-04-15 | 国网湖北省电力有限公司信息通信公司 | Automatic operation and maintenance system for closed-loop automatic optical cable line |
-
2022
- 2022-05-11 CN CN202210509397.1A patent/CN114994454B/en active Active
Also Published As
| Publication number | Publication date |
|---|---|
| CN114994454A (en) | 2022-09-02 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Fu et al. | Failure analysis of a transmission line considering the joint probability distribution of wind speed and rain intensity | |
| CN109376801A (en) | Blade of wind-driven generator icing diagnostic method based on integrated deep neural network | |
| CN113327022B (en) | Lightning protection safety risk management system and method | |
| Gentle | Concurrent wind cooling in power transmission lines | |
| CN103678865A (en) | Fault probability online evaluation method of power transmission line faults caused by freezing rain | |
| CN106650977A (en) | Short-term power prediction method used for newly-built wind farm | |
| CN110929952B (en) | Optical cable fault probability prediction method based on circuit surrounding environment and laying type | |
| Zhang et al. | Power line simulation for safety distance detection using point clouds | |
| CN110866693B (en) | Overhead transmission line icing risk assessment method based on GIS model | |
| CN106570582A (en) | Method and system for building transmission line dancing tripping risk prediction network model | |
| CN104361532A (en) | Method for researching influence of micro-landform strong wind area on safety operation of electric transmission line | |
| CN103914737A (en) | Method for calculating whole circuit in-place weather information of electric transmission and transformation circuit | |
| CN116780758A (en) | On-line monitoring system and method for multi-sensor data fusion of power transmission line | |
| CN113689053B (en) | Strong convection weather overhead line power failure prediction method based on random forest | |
| CN114994454B (en) | OPGW optical cable full-state detection analysis method and system | |
| CN107066748A (en) | A kind of wireless senser distribution method for bridge charming appearance and behaviour vibration monitoring | |
| CN104298706A (en) | Transmission tower material actual strength computing method based on data mining | |
| CN115204712B (en) | Offshore and coastal wind power plant site selection evaluation method | |
| CN110782081B (en) | Prediction early warning system and prediction early warning method for heaven-earth combined icing | |
| Deng et al. | Multimodal analysis of saddle micro-terrain prone to wind disasters on overhead transmission lines | |
| Chen et al. | Reliability Probability Evaluation Method of Electronic transformer based on Xgboost model | |
| An et al. | Typhoon inversion method combined with the YanMeng wind field and a meteorological monitoring system for transmission lines | |
| CN117894133B (en) | Icing alarm method and system for power transmission line | |
| CN115685387B (en) | Method and device for detecting consistency and similarity of typhoon path forecast | |
| Kuznetsov et al. | Full-Scale Measurements of Local Wind Loads on a High-Rise Building Using Wind Tunnel Based Predictions |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |